Compare commits
14
Commits
0a4bf843ff
...
master
| Author | SHA1 | Date | |
|---|---|---|---|
 grabowski
|
32399f1899 | ||
|
grabowski
|
f4d42c90f4 | ||
|
grabowski
|
039d24a5c3 | ||
|
grabowski
|
777b230baf | ||
|
grabowski
|
0ec675e9c5 | ||
|
grabowski
|
7b31d4d0dd | ||
|
grabowski
|
2e19974fad | ||
|
grabowski
|
b03318210c | ||
|
grabowski
|
97a6694ab2 | ||
|
grabowski
|
5ad8e4eac3 | ||
|
grabowski
|
6f4a86edbb | ||
|
grabowski
|
ce08312c0f | ||
|
grabowski
|
d621aa9ce7 | ||
|
grabowski
|
764764e07e |
@@ -84,6 +84,19 @@ SMTP_PORT=587
|
||||
SMTP_USERNAME=
|
||||
SMTP_PASSWORD=
|
||||
|
||||
# Public push notifications via self-hosted ntfy (https://ntfy.sh, single binary).
|
||||
# Leave NTFY_SERVER empty to disable. Topics published: <prefix>-<station>-warning,
|
||||
# <prefix>-<station>-danger, <prefix>-warning, <prefix>-danger, <prefix>-p1-outlook,
|
||||
# <prefix>-status. See docs/NOTIFICATIONS.md.
|
||||
NTFY_SERVER=
|
||||
# Where the monitor POSTs (defaults to NTFY_SERVER). Use the local ntfy
|
||||
# address (loopback or Tailscale IP) so publishing does not depend on
|
||||
# DNS / the reverse proxy being up.
|
||||
NTFY_PUBLISH_URL=
|
||||
NTFY_TOPIC_PREFIX=ping
|
||||
NTFY_TOKEN=
|
||||
PUBLIC_URL=https://water.buildfor.life/
|
||||
|
||||
# Matrix Alerting Configuration
|
||||
MATRIX_HOMESERVER=https://matrix.org
|
||||
MATRIX_ACCESS_TOKEN=
|
||||
|
||||
+60
-327
@@ -1,342 +1,75 @@
|
||||
name: CI/CD Pipeline - Northern Thailand Ping River Monitor
|
||||
name: CI
|
||||
|
||||
# What this checks, on every push and PR to master:
|
||||
# 1. formatting contract (black + isort, config in pyproject.toml)
|
||||
# 2. flake8 hard-error gate (syntax, undefined names)
|
||||
# 3. the pytest suite (synthetic data, no DB/network; ~1 min)
|
||||
# Docker build / staging / production / perf jobs from the original template
|
||||
# were removed: there is no registry, no staging host, and production is a
|
||||
# systemd unit deployed by `git pull` on the server (docs/FLOOD_FORECASTING.md
|
||||
# section 6, scripts/install.sh). Re-add a job when the thing it deploys exists.
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [ master, develop ]
|
||||
branches: [master, develop]
|
||||
pull_request:
|
||||
branches: [ master ]
|
||||
branches: [master]
|
||||
schedule:
|
||||
# Run tests daily at 2 AM UTC
|
||||
- cron: '0 2 * * *'
|
||||
# daily, catches dependency drift / upstream API changes in the tests
|
||||
- cron: "0 2 * * *"
|
||||
workflow_dispatch:
|
||||
|
||||
env:
|
||||
PYTHON_VERSION: '3.11'
|
||||
REGISTRY: git.b4l.co.th
|
||||
IMAGE_NAME: b4l/northern-thailand-ping-river-monitor
|
||||
# GitHub token for better rate limits and authentication
|
||||
GH_TOKEN: ${{ secrets.GH_TOKEN }}
|
||||
PYTHON_VERSION: "3.11" # pandas 2.0.3 ships no 3.12 wheels; psycopg2-binary 2.9.9 breaks on 3.13
|
||||
|
||||
jobs:
|
||||
# Test job
|
||||
lint:
|
||||
name: Format & lint
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
cache: pip
|
||||
cache-dependency-path: requirements-dev.txt
|
||||
|
||||
- name: Install tools
|
||||
run: |
|
||||
python -m pip install --upgrade pip --root-user-action=ignore
|
||||
pip install --root-user-action=ignore black==26.5.1 isort==5.12.0 flake8==6.1.0
|
||||
|
||||
- name: black
|
||||
run: black --check --diff src/ *.py
|
||||
|
||||
- name: isort
|
||||
run: isort --check-only --diff src/ *.py
|
||||
|
||||
- name: flake8 (errors only)
|
||||
run: flake8 src/ --count --select=E9,F63,F7,F82 --show-source --statistics
|
||||
|
||||
test:
|
||||
name: Test Suite
|
||||
name: Test suite
|
||||
runs-on: ubuntu-latest
|
||||
strategy:
|
||||
matrix:
|
||||
python-version: ['3.11'] # pandas 2.0.3 ships no 3.12 wheels; widen after upgrading pandas
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
token: ${{ secrets.GITEA_TOKEN }}
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
cache: pip
|
||||
cache-dependency-path: |
|
||||
requirements.txt
|
||||
requirements-dev.txt
|
||||
|
||||
- name: Cache pip dependencies
|
||||
uses: actions/cache@v3
|
||||
with:
|
||||
path: ~/.cache/pip
|
||||
key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements*.txt') }}
|
||||
restore-keys: |
|
||||
${{ runner.os }}-pip-
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip --root-user-action=ignore
|
||||
pip install --root-user-action=ignore -r requirements.txt
|
||||
pip install --root-user-action=ignore pytest==9.1.1 pytest-asyncio==0.21.1
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip --root-user-action=ignore
|
||||
pip install --root-user-action=ignore -r requirements.txt
|
||||
pip install --root-user-action=ignore -r requirements-dev.txt
|
||||
|
||||
- name: Lint with flake8
|
||||
run: |
|
||||
flake8 src/ --count --select=E9,F63,F7,F82 --show-source --statistics
|
||||
flake8 src/ --count --exit-zero --max-complexity=10 --max-line-length=100 --statistics
|
||||
|
||||
- name: Type check with mypy (advisory)
|
||||
run: |
|
||||
# 86 pre-existing errors; blocking typing gate deferred until the debt is paid down
|
||||
mypy src/ --ignore-missing-imports || true
|
||||
|
||||
- name: Format check with black
|
||||
run: |
|
||||
black --check src/ *.py
|
||||
|
||||
- name: Import sort check
|
||||
run: |
|
||||
isort --check-only src/ *.py
|
||||
|
||||
- name: Run integration tests
|
||||
run: |
|
||||
python tests/test_integration.py
|
||||
|
||||
- name: Run station management tests
|
||||
run: |
|
||||
python tests/test_station_management.py
|
||||
|
||||
- name: Test application startup
|
||||
run: |
|
||||
timeout 10s python run.py --test || true
|
||||
|
||||
- name: Security scan with bandit
|
||||
run: |
|
||||
bandit -r src/ -f json -o bandit-report.json || true
|
||||
|
||||
- name: Upload test artifacts
|
||||
uses: actions/upload-artifact@v3
|
||||
if: always()
|
||||
with:
|
||||
name: test-results-${{ matrix.python-version }}
|
||||
path: |
|
||||
bandit-report.json
|
||||
*.log
|
||||
|
||||
# Code quality job
|
||||
code-quality:
|
||||
name: Code Quality
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
token: ${{ secrets.GITEA_TOKEN }}
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip --root-user-action=ignore
|
||||
pip install --root-user-action=ignore -r requirements-dev.txt
|
||||
|
||||
- name: Run safety check
|
||||
run: |
|
||||
safety check -r requirements.txt --json --output safety-report.json || true
|
||||
|
||||
- name: Run bandit security scan
|
||||
run: |
|
||||
bandit -r src/ -f json -o bandit-report.json || true
|
||||
|
||||
- name: Upload security reports
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: security-reports
|
||||
path: |
|
||||
safety-report.json
|
||||
bandit-report.json
|
||||
|
||||
# Build Docker image
|
||||
build:
|
||||
name: Build Docker Image
|
||||
runs-on: ubuntu-latest
|
||||
needs: test
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
token: ${{ secrets.GITEA_TOKEN }}
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@v3
|
||||
|
||||
- name: Log in to Container Registry
|
||||
uses: docker/login-action@v3
|
||||
with:
|
||||
registry: ${{ env.REGISTRY }}
|
||||
username: ${{ github.actor }}
|
||||
password: ${{ secrets.GITEA_TOKEN }}
|
||||
|
||||
- name: Extract metadata
|
||||
id: meta
|
||||
uses: docker/metadata-action@v5
|
||||
with:
|
||||
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
|
||||
tags: |
|
||||
type=ref,event=branch
|
||||
type=ref,event=pr
|
||||
type=sha,prefix={{branch}}-
|
||||
type=raw,value=latest,enable={{is_default_branch}}
|
||||
|
||||
- name: Build and push Docker image
|
||||
uses: docker/build-push-action@v5
|
||||
with:
|
||||
context: .
|
||||
platforms: linux/amd64,linux/arm64
|
||||
push: true
|
||||
tags: ${{ steps.meta.outputs.tags }}
|
||||
labels: ${{ steps.meta.outputs.labels }}
|
||||
cache-from: type=gha
|
||||
cache-to: type=gha,mode=max
|
||||
env:
|
||||
GITHUB_TOKEN: ${{ secrets.GH_TOKEN }}
|
||||
|
||||
- name: Test Docker image
|
||||
run: |
|
||||
docker run --rm ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ github.sha }} python run.py --test
|
||||
|
||||
# Integration test with services
|
||||
integration-test:
|
||||
name: Integration Test with Services
|
||||
runs-on: ubuntu-latest
|
||||
needs: build
|
||||
|
||||
services:
|
||||
victoriametrics:
|
||||
image: victoriametrics/victoria-metrics:latest
|
||||
ports:
|
||||
- 8428:8428
|
||||
options: >-
|
||||
--health-cmd "wget --quiet --tries=1 --spider http://localhost:8428/health"
|
||||
--health-interval 30s
|
||||
--health-timeout 10s
|
||||
--health-retries 3
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
token: ${{ secrets.GITEA_TOKEN }}
|
||||
|
||||
- name: Wait for VictoriaMetrics
|
||||
run: |
|
||||
timeout 60s bash -c 'until curl -f http://localhost:8428/health; do sleep 2; done'
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip --root-user-action=ignore
|
||||
pip install --root-user-action=ignore -r requirements.txt
|
||||
|
||||
- name: Test with VictoriaMetrics
|
||||
env:
|
||||
DB_TYPE: victoriametrics
|
||||
VM_HOST: localhost
|
||||
VM_PORT: 8428
|
||||
run: |
|
||||
python run.py --test
|
||||
|
||||
- name: Start API server
|
||||
env:
|
||||
DB_TYPE: victoriametrics
|
||||
VM_HOST: localhost
|
||||
VM_PORT: 8428
|
||||
run: |
|
||||
python run.py --web-api &
|
||||
sleep 10
|
||||
|
||||
- name: Test API endpoints
|
||||
run: |
|
||||
curl -f http://localhost:8000/health
|
||||
curl -f http://localhost:8000/stations
|
||||
curl -f http://localhost:8000/metrics
|
||||
|
||||
# Deploy to staging (only on develop branch)
|
||||
deploy-staging:
|
||||
name: Deploy to Staging
|
||||
runs-on: ubuntu-latest
|
||||
needs: [test, build, integration-test]
|
||||
if: github.ref == 'refs/heads/develop'
|
||||
environment:
|
||||
name: staging
|
||||
url: https://staging.ping-river-monitor.b4l.co.th
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
token: ${{ secrets.GITEA_TOKEN }}
|
||||
|
||||
- name: Deploy to staging
|
||||
run: |
|
||||
echo "Deploying to staging environment..."
|
||||
# Add your staging deployment commands here
|
||||
# Example: kubectl, docker-compose, or webhook call
|
||||
|
||||
- name: Health check staging
|
||||
run: |
|
||||
sleep 30
|
||||
curl -f https://staging.ping-river-monitor.b4l.co.th/health
|
||||
|
||||
# Deploy to production (only on main branch, manual approval)
|
||||
deploy-production:
|
||||
name: Deploy to Production
|
||||
runs-on: ubuntu-latest
|
||||
needs: [test, build, integration-test]
|
||||
if: github.ref == 'refs/heads/master'
|
||||
environment:
|
||||
name: production
|
||||
url: https://ping-river-monitor.b4l.co.th
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
token: ${{ secrets.GITEA_TOKEN }}
|
||||
|
||||
- name: Deploy to production
|
||||
run: |
|
||||
echo "Deploying to production environment..."
|
||||
# Add your production deployment commands here
|
||||
|
||||
- name: Health check production
|
||||
run: |
|
||||
sleep 30
|
||||
curl -f https://ping-river-monitor.b4l.co.th/health
|
||||
|
||||
- name: Notify deployment
|
||||
run: |
|
||||
echo "✅ Production deployment successful!"
|
||||
echo "🌐 URL: https://ping-river-monitor.b4l.co.th"
|
||||
echo "📊 Grafana: https://grafana.ping-river-monitor.b4l.co.th"
|
||||
|
||||
# Performance test (only on main branch)
|
||||
performance-test:
|
||||
name: Performance Test
|
||||
runs-on: ubuntu-latest
|
||||
needs: deploy-production
|
||||
if: github.ref == 'refs/heads/master'
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
token: ${{ secrets.GITEA_TOKEN }}
|
||||
|
||||
- name: Install Apache Bench
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y apache2-utils
|
||||
|
||||
- name: Performance test API endpoints
|
||||
run: |
|
||||
# Test health endpoint
|
||||
ab -n 100 -c 10 https://ping-river-monitor.b4l.co.th/health
|
||||
|
||||
# Test stations endpoint
|
||||
ab -n 50 -c 5 https://ping-river-monitor.b4l.co.th/stations
|
||||
|
||||
# Test metrics endpoint
|
||||
ab -n 50 -c 5 https://ping-river-monitor.b4l.co.th/metrics
|
||||
|
||||
# Cleanup old artifacts
|
||||
cleanup:
|
||||
name: Cleanup
|
||||
runs-on: ubuntu-latest
|
||||
if: always()
|
||||
needs: [test, build, integration-test]
|
||||
|
||||
steps:
|
||||
- name: Clean up old Docker images
|
||||
run: |
|
||||
echo "Cleaning up old Docker images..."
|
||||
# Add cleanup commands for old images/artifacts
|
||||
- name: pytest
|
||||
env:
|
||||
DB_TYPE: sqlite
|
||||
run: pytest -q -p no:cacheprovider
|
||||
|
||||
+81
-349
@@ -1,367 +1,99 @@
|
||||
name: Documentation
|
||||
name: Docs
|
||||
|
||||
# Checks that the documentation the project actually ships stays consistent:
|
||||
# - every relative link / image path in docs/*.md and README.md resolves
|
||||
# inside the repo (external URLs are NOT fetched: localhost examples,
|
||||
# rate-limited hosts and the Tailscale-era links made that gate permanently
|
||||
# red, and a 200 on a curl --head proves nothing about a doc anyway)
|
||||
# - the FastAPI app imports and its OpenAPI schema is exportable (that is
|
||||
# the reference at https://water.buildfor.life/docs)
|
||||
# The previous Sphinx/apidoc jobs produced artifacts nobody read and were
|
||||
# removed. Reference docs live in docs/*.md; the public overview is at
|
||||
# https://buildfor.life/docs/tooling/ping-river-monitor/.
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [ master, develop ]
|
||||
branches: [master, develop]
|
||||
paths:
|
||||
- 'docs/**'
|
||||
- 'README.md'
|
||||
- 'CONTRIBUTING.md'
|
||||
- 'src/**/*.py'
|
||||
- "docs/**"
|
||||
- "README.md"
|
||||
- "CONTRIBUTING.md"
|
||||
- "src/web_api.py"
|
||||
- "src/schemas.py"
|
||||
- ".gitea/workflows/docs.yml"
|
||||
pull_request:
|
||||
paths:
|
||||
- 'docs/**'
|
||||
- 'README.md'
|
||||
- 'CONTRIBUTING.md'
|
||||
- "docs/**"
|
||||
- "README.md"
|
||||
- "CONTRIBUTING.md"
|
||||
workflow_dispatch:
|
||||
|
||||
env:
|
||||
PYTHON_VERSION: '3.11'
|
||||
PYTHON_VERSION: "3.11"
|
||||
|
||||
jobs:
|
||||
# Validate documentation
|
||||
validate-docs:
|
||||
name: Validate Documentation
|
||||
docs:
|
||||
name: Validate documentation
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
token: ${{ secrets.GITEA_TOKEN }}
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
- name: Relative links and images resolve
|
||||
run: |
|
||||
python3 - <<'PY'
|
||||
import re, sys, pathlib
|
||||
root = pathlib.Path(".")
|
||||
files = [root / "README.md", root / "CONTRIBUTING.md", *root.glob("docs/**/*.md")]
|
||||
link = re.compile(r"!?\[[^\]]*\]\(([^)\s]+)(?:\s+\"[^\"]*\")?\)")
|
||||
bad = []
|
||||
for md in files:
|
||||
if not md.exists():
|
||||
continue
|
||||
for m in link.finditer(md.read_text(encoding="utf-8")):
|
||||
target = m.group(1)
|
||||
if target.startswith(("http://", "https://", "mailto:", "#")):
|
||||
continue
|
||||
path = target.split("#", 1)[0]
|
||||
if not path:
|
||||
continue
|
||||
resolved = (md.parent / path).resolve()
|
||||
if not resolved.exists():
|
||||
bad.append(f"{md}: {target}")
|
||||
if bad:
|
||||
print("Broken relative links:")
|
||||
print("\n".join(" " + b for b in bad))
|
||||
sys.exit(1)
|
||||
print(f"checked {len(files)} files, all relative links resolve")
|
||||
PY
|
||||
|
||||
- name: Install documentation tools
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r requirements.txt
|
||||
pip install sphinx sphinx-rtd-theme sphinx-autodoc-typehints
|
||||
pip install markdown-link-check || true
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
cache: pip
|
||||
cache-dependency-path: requirements.txt
|
||||
|
||||
- name: Check markdown links
|
||||
run: |
|
||||
echo "🔗 Checking markdown links..."
|
||||
find . -name "*.md" -not -path "./.git/*" -not -path "./node_modules/*" | while read file; do
|
||||
echo "Checking $file"
|
||||
# Basic link validation (you can enhance this)
|
||||
grep -o 'http[s]*://[^)]*' "$file" | while read url; do
|
||||
if curl -s --head "$url" | head -n 1 | grep -q "200 OK"; then
|
||||
echo "✅ $url"
|
||||
else
|
||||
echo "❌ $url (in $file)"
|
||||
fi
|
||||
done
|
||||
done
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip --root-user-action=ignore
|
||||
pip install --root-user-action=ignore -r requirements.txt
|
||||
|
||||
- name: Validate README structure
|
||||
run: |
|
||||
echo "📋 Validating README structure..."
|
||||
- name: OpenAPI schema exports
|
||||
env:
|
||||
DB_TYPE: sqlite
|
||||
run: |
|
||||
python - <<'PY'
|
||||
import json
|
||||
from src.web_api import app
|
||||
spec = app.openapi()
|
||||
paths = sorted(spec["paths"])
|
||||
required = {"/forecast", "/measurements/latest", "/measurements/history/{station_code}", "/stations", "/api/stats", "/health"}
|
||||
missing = required - set(paths)
|
||||
assert not missing, f"documented endpoints missing from the app: {missing}"
|
||||
json.dump(spec, open("openapi.json", "w"), indent=1)
|
||||
print(f"{len(paths)} paths; schema written to openapi.json")
|
||||
PY
|
||||
|
||||
required_sections=(
|
||||
"# Northern Thailand Ping River Monitor"
|
||||
"## Features"
|
||||
"## Quick Start"
|
||||
"## Installation"
|
||||
"## Usage"
|
||||
"## API Endpoints"
|
||||
"## Docker"
|
||||
"## Contributing"
|
||||
"## License"
|
||||
)
|
||||
|
||||
for section in "${required_sections[@]}"; do
|
||||
if grep -q "$section" README.md; then
|
||||
echo "✅ Found: $section"
|
||||
else
|
||||
echo "❌ Missing: $section"
|
||||
fi
|
||||
done
|
||||
|
||||
- name: Check documentation completeness
|
||||
run: |
|
||||
echo "📚 Checking documentation completeness..."
|
||||
|
||||
# Check if all Python modules have docstrings
|
||||
python -c "
|
||||
import ast
|
||||
import os
|
||||
|
||||
def check_docstrings(filepath):
|
||||
with open(filepath, 'r', encoding='utf-8') as f:
|
||||
tree = ast.parse(f.read())
|
||||
|
||||
missing_docstrings = []
|
||||
|
||||
for node in ast.walk(tree):
|
||||
if isinstance(node, (ast.FunctionDef, ast.ClassDef, ast.AsyncFunctionDef)):
|
||||
if not ast.get_docstring(node):
|
||||
missing_docstrings.append(f'{node.name} in {filepath}')
|
||||
|
||||
return missing_docstrings
|
||||
|
||||
all_missing = []
|
||||
for root, dirs, files in os.walk('src'):
|
||||
for file in files:
|
||||
if file.endswith('.py') and not file.startswith('__'):
|
||||
filepath = os.path.join(root, file)
|
||||
missing = check_docstrings(filepath)
|
||||
all_missing.extend(missing)
|
||||
|
||||
if all_missing:
|
||||
print('⚠️ Missing docstrings:')
|
||||
for item in all_missing[:10]: # Show first 10
|
||||
print(f' - {item}')
|
||||
if len(all_missing) > 10:
|
||||
print(f' ... and {len(all_missing) - 10} more')
|
||||
else:
|
||||
print('✅ All functions and classes have docstrings')
|
||||
"
|
||||
|
||||
# Generate API documentation
|
||||
generate-api-docs:
|
||||
name: Generate API Documentation
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
token: ${{ secrets.GITEA_TOKEN }}
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r requirements.txt
|
||||
|
||||
- name: Generate OpenAPI spec
|
||||
run: |
|
||||
echo "📝 Generating OpenAPI specification..."
|
||||
python -c "
|
||||
import json
|
||||
import sys
|
||||
sys.path.insert(0, 'src')
|
||||
|
||||
try:
|
||||
from web_api import app
|
||||
openapi_spec = app.openapi()
|
||||
|
||||
with open('openapi.json', 'w') as f:
|
||||
json.dump(openapi_spec, f, indent=2)
|
||||
|
||||
print('✅ OpenAPI spec generated: openapi.json')
|
||||
except Exception as e:
|
||||
print(f'❌ Failed to generate OpenAPI spec: {e}')
|
||||
"
|
||||
|
||||
- name: Generate API documentation
|
||||
run: |
|
||||
echo "📖 Generating API documentation..."
|
||||
|
||||
# Create API documentation from OpenAPI spec
|
||||
if [ -f openapi.json ]; then
|
||||
cat > api-docs.md << 'EOF'
|
||||
# API Documentation
|
||||
|
||||
This document describes the REST API endpoints for the Northern Thailand Ping River Monitor.
|
||||
|
||||
## Base URL
|
||||
|
||||
- Production: `https://ping-river-monitor.b4l.co.th`
|
||||
- Staging: `https://staging.ping-river-monitor.b4l.co.th`
|
||||
- Development: `http://localhost:8000`
|
||||
|
||||
## Authentication
|
||||
|
||||
Currently, the API does not require authentication. This may change in future versions.
|
||||
|
||||
## Endpoints
|
||||
|
||||
EOF
|
||||
|
||||
# Extract endpoints from OpenAPI spec
|
||||
python -c "
|
||||
import json
|
||||
|
||||
with open('openapi.json', 'r') as f:
|
||||
spec = json.load(f)
|
||||
|
||||
for path, methods in spec.get('paths', {}).items():
|
||||
for method, details in methods.items():
|
||||
print(f'### {method.upper()} {path}')
|
||||
print()
|
||||
print(details.get('summary', 'No description available'))
|
||||
print()
|
||||
if 'parameters' in details:
|
||||
print('**Parameters:**')
|
||||
for param in details['parameters']:
|
||||
print(f'- `{param[\"name\"]}` ({param.get(\"in\", \"query\")}): {param.get(\"description\", \"No description\")}')
|
||||
print()
|
||||
print('---')
|
||||
print()
|
||||
" >> api-docs.md
|
||||
|
||||
echo "✅ API documentation generated: api-docs.md"
|
||||
fi
|
||||
|
||||
- name: Upload documentation artifacts
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: documentation-${{ github.run_number }}
|
||||
path: |
|
||||
openapi.json
|
||||
api-docs.md
|
||||
|
||||
# Build Sphinx documentation
|
||||
build-sphinx-docs:
|
||||
name: Build Sphinx Documentation
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
token: ${{ secrets.GITEA_TOKEN }}
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install -r requirements.txt
|
||||
pip install sphinx sphinx-rtd-theme sphinx-autodoc-typehints
|
||||
|
||||
- name: Create Sphinx configuration
|
||||
run: |
|
||||
mkdir -p docs/sphinx
|
||||
|
||||
cat > docs/sphinx/conf.py << 'EOF'
|
||||
import os
|
||||
import sys
|
||||
sys.path.insert(0, os.path.abspath('../../src'))
|
||||
|
||||
project = 'Northern Thailand Ping River Monitor'
|
||||
copyright = '2025, Ping River Monitor Team'
|
||||
author = 'Ping River Monitor Team'
|
||||
version = '3.1.3'
|
||||
release = '3.1.3'
|
||||
|
||||
extensions = [
|
||||
'sphinx.ext.autodoc',
|
||||
'sphinx.ext.viewcode',
|
||||
'sphinx.ext.napoleon',
|
||||
'sphinx_autodoc_typehints',
|
||||
]
|
||||
|
||||
templates_path = ['_templates']
|
||||
exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
|
||||
|
||||
html_theme = 'sphinx_rtd_theme'
|
||||
html_static_path = ['_static']
|
||||
|
||||
autodoc_default_options = {
|
||||
'members': True,
|
||||
'member-order': 'bysource',
|
||||
'special-members': '__init__',
|
||||
'undoc-members': True,
|
||||
'exclude-members': '__weakref__'
|
||||
}
|
||||
EOF
|
||||
|
||||
cat > docs/sphinx/index.rst << 'EOF'
|
||||
Northern Thailand Ping River Monitor Documentation
|
||||
================================================
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 2
|
||||
:caption: Contents:
|
||||
|
||||
modules
|
||||
|
||||
Indices and tables
|
||||
==================
|
||||
|
||||
* :ref:`genindex`
|
||||
* :ref:`modindex`
|
||||
* :ref:`search`
|
||||
EOF
|
||||
|
||||
- name: Generate module documentation
|
||||
run: |
|
||||
cd docs/sphinx
|
||||
sphinx-apidoc -o . ../../src
|
||||
|
||||
- name: Build documentation
|
||||
run: |
|
||||
cd docs/sphinx
|
||||
sphinx-build -b html . _build/html
|
||||
|
||||
- name: Upload Sphinx documentation
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: sphinx-docs-${{ github.run_number }}
|
||||
path: docs/sphinx/_build/html/
|
||||
|
||||
# Documentation summary
|
||||
docs-summary:
|
||||
name: Documentation Summary
|
||||
runs-on: ubuntu-latest
|
||||
needs: [validate-docs, generate-api-docs, build-sphinx-docs]
|
||||
if: always()
|
||||
|
||||
steps:
|
||||
- name: Generate documentation summary
|
||||
run: |
|
||||
echo "# 📚 Documentation Build Summary" > docs-summary.md
|
||||
echo "" >> docs-summary.md
|
||||
echo "**Build Date:** $(date -u)" >> docs-summary.md
|
||||
echo "**Repository:** ${{ github.repository }}" >> docs-summary.md
|
||||
echo "**Commit:** ${{ github.sha }}" >> docs-summary.md
|
||||
echo "" >> docs-summary.md
|
||||
|
||||
echo "## 📊 Results" >> docs-summary.md
|
||||
echo "" >> docs-summary.md
|
||||
|
||||
if [ "${{ needs.validate-docs.result }}" = "success" ]; then
|
||||
echo "- ✅ **Documentation Validation**: Passed" >> docs-summary.md
|
||||
else
|
||||
echo "- ❌ **Documentation Validation**: Failed" >> docs-summary.md
|
||||
fi
|
||||
|
||||
if [ "${{ needs.generate-api-docs.result }}" = "success" ]; then
|
||||
echo "- ✅ **API Documentation**: Generated" >> docs-summary.md
|
||||
else
|
||||
echo "- ❌ **API Documentation**: Failed" >> docs-summary.md
|
||||
fi
|
||||
|
||||
if [ "${{ needs.build-sphinx-docs.result }}" = "success" ]; then
|
||||
echo "- ✅ **Sphinx Documentation**: Built" >> docs-summary.md
|
||||
else
|
||||
echo "- ❌ **Sphinx Documentation**: Failed" >> docs-summary.md
|
||||
fi
|
||||
|
||||
echo "" >> docs-summary.md
|
||||
echo "## 🔗 Available Documentation" >> docs-summary.md
|
||||
echo "" >> docs-summary.md
|
||||
echo "- [README.md](../README.md)" >> docs-summary.md
|
||||
echo "- [API Documentation](../docs/)" >> docs-summary.md
|
||||
echo "- [Contributing Guide](../CONTRIBUTING.md)" >> docs-summary.md
|
||||
|
||||
cat docs-summary.md
|
||||
|
||||
- name: Upload documentation summary
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: docs-summary-${{ github.run_number }}
|
||||
path: docs-summary.md
|
||||
- uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: openapi-${{ github.run_number }}
|
||||
path: openapi.json
|
||||
|
||||
+70
-254
@@ -1,293 +1,109 @@
|
||||
name: Security & Dependency Updates
|
||||
name: Security
|
||||
|
||||
# Two gates that can actually fail, plus one report:
|
||||
# - pip-audit against requirements.txt: any known vulnerability in a runtime
|
||||
# dependency fails the job (dev-only tools are reported, not gated)
|
||||
# - bandit on src/: HIGH severity findings fail; medium/low are listed.
|
||||
# B104 (bind 0.0.0.0) is skipped: the service is meant to listen on all
|
||||
# interfaces behind Cloudflare/Caddy.
|
||||
# - pip-licenses report as an artifact (informational; the project is MIT
|
||||
# and its runtime deps are MIT/BSD/Apache/PSF)
|
||||
# The old file ran safety/bandit/semgrep with `|| true` and could not go red.
|
||||
|
||||
on:
|
||||
schedule:
|
||||
# Run security scans daily at 3 AM UTC
|
||||
- cron: "0 3 * * *"
|
||||
- cron: "0 3 * * 1" # weekly, Monday 03:00 UTC
|
||||
workflow_dispatch:
|
||||
push:
|
||||
paths:
|
||||
- "requirements*.txt"
|
||||
- "Dockerfile"
|
||||
- "pyproject.toml"
|
||||
- "uv.lock"
|
||||
- "src/**/*.py"
|
||||
- ".gitea/workflows/security.yml"
|
||||
pull_request:
|
||||
paths:
|
||||
- "requirements*.txt"
|
||||
- "pyproject.toml"
|
||||
- "src/**/*.py"
|
||||
|
||||
env:
|
||||
PYTHON_VERSION: "3.11"
|
||||
# GitHub token for better rate limits and authentication
|
||||
GH_TOKEN: ${{ secrets.GH_TOKEN }}
|
||||
|
||||
jobs:
|
||||
# Dependency vulnerability scan
|
||||
dependency-scan:
|
||||
name: Dependency Security Scan
|
||||
dependencies:
|
||||
name: Dependency vulnerabilities
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
token: ${{ secrets.GITEA_TOKEN }}
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
|
||||
- name: Install dependencies
|
||||
- name: Install pip-audit
|
||||
run: |
|
||||
python -m pip install --upgrade pip --root-user-action=ignore
|
||||
pip install --root-user-action=ignore safety bandit semgrep
|
||||
pip install --root-user-action=ignore pip-audit
|
||||
|
||||
- name: Run Safety check
|
||||
run: |
|
||||
safety check -r requirements.txt --json --output safety-report.json || true
|
||||
safety check -r requirements-dev.txt --json --output safety-dev-report.json || true
|
||||
- name: Runtime dependencies (gate)
|
||||
run: pip-audit -r requirements.txt --strict --desc on
|
||||
|
||||
- name: Run Bandit security scan
|
||||
run: |
|
||||
bandit -r src/ -f json -o bandit-report.json || true
|
||||
- name: Dev dependencies (report only)
|
||||
run: pip-audit -r requirements-dev.txt --desc on || echo "::warning::dev-only dependency advisories above"
|
||||
|
||||
- name: Run Semgrep security scan
|
||||
run: |
|
||||
semgrep --config=auto src/ --json --output=semgrep-report.json || true
|
||||
|
||||
- name: Upload security reports
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: security-reports-${{ github.run_number }}
|
||||
path: |
|
||||
safety-report.json
|
||||
safety-dev-report.json
|
||||
bandit-report.json
|
||||
semgrep-report.json
|
||||
|
||||
- name: Check for critical vulnerabilities
|
||||
run: |
|
||||
echo "Checking for critical vulnerabilities..."
|
||||
|
||||
# Check Safety results
|
||||
if [ -f safety-report.json ]; then
|
||||
critical_count=$(jq '.vulnerabilities | length' safety-report.json 2>/dev/null || echo "0")
|
||||
if [ "$critical_count" -gt 0 ]; then
|
||||
echo "Found $critical_count dependency vulnerabilities"
|
||||
jq '.vulnerabilities[] | "- \(.package_name) \(.installed_version): \(.vulnerability_id)"' safety-report.json
|
||||
else
|
||||
echo "No dependency vulnerabilities found"
|
||||
fi
|
||||
fi
|
||||
|
||||
# Check Bandit results
|
||||
if [ -f bandit-report.json ]; then
|
||||
high_severity=$(jq '.results[] | select(.issue_severity == "HIGH") | length' bandit-report.json 2>/dev/null | wc -l)
|
||||
if [ "$high_severity" -gt 0 ]; then
|
||||
echo "Found $high_severity high-severity security issues"
|
||||
else
|
||||
echo "No high-severity security issues found"
|
||||
fi
|
||||
fi
|
||||
|
||||
# License compliance check
|
||||
license-check:
|
||||
name: License Compliance
|
||||
code:
|
||||
name: Static analysis
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
token: ${{ secrets.GITEA_TOKEN }}
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
|
||||
- name: Install pip-licenses
|
||||
- name: Install bandit
|
||||
run: |
|
||||
python -m pip install --upgrade pip --root-user-action=ignore
|
||||
pip install --root-user-action=ignore pip-licenses
|
||||
pip install --root-user-action=ignore -r requirements.txt
|
||||
pip install --root-user-action=ignore bandit
|
||||
|
||||
- name: Check licenses
|
||||
- name: bandit (HIGH fails; medium/low listed)
|
||||
run: |
|
||||
echo "Checking dependency licenses..."
|
||||
bandit -r src/ -q --skip B104 -ll -ii || true
|
||||
bandit -r src/ -q --skip B104 --severity-level high --confidence-level medium
|
||||
|
||||
licenses:
|
||||
name: License report
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
cache: pip
|
||||
cache-dependency-path: requirements.txt
|
||||
|
||||
# A fresh venv, not the runner's site-packages: the report must list the
|
||||
# project's runtime deps, not whatever the runner image or a previous
|
||||
# workflow happened to leave installed (semgrep once showed up here).
|
||||
- name: Install into a clean venv
|
||||
run: |
|
||||
python -m venv .lic && . .lic/bin/activate
|
||||
pip install --upgrade pip --root-user-action=ignore
|
||||
pip install --root-user-action=ignore -r requirements.txt pip-licenses
|
||||
|
||||
- name: Report
|
||||
run: |
|
||||
. .lic/bin/activate
|
||||
pip-licenses --format=markdown --with-urls --output-file=licenses.md
|
||||
pip-licenses --format=json --output-file=licenses.json
|
||||
pip-licenses --format=markdown --output-file=licenses.md
|
||||
echo "Copyleft licenses among runtime deps (informational; LGPL is fine to link from MIT):"
|
||||
pip-licenses --format=plain --ignore-packages pip-licenses | grep -iE 'GPL|AGPL|LGPL' || echo " none"
|
||||
|
||||
# Check for problematic licenses
|
||||
problematic_licenses=("GPL" "AGPL" "LGPL")
|
||||
|
||||
for license in "${problematic_licenses[@]}"; do
|
||||
if grep -i "$license" licenses.json; then
|
||||
echo "Found potentially problematic license: $license"
|
||||
fi
|
||||
done
|
||||
|
||||
echo "License check completed"
|
||||
|
||||
- name: Upload license report
|
||||
uses: actions/upload-artifact@v3
|
||||
- uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: license-report-${{ github.run_number }}
|
||||
name: licenses-${{ github.run_number }}
|
||||
path: |
|
||||
licenses.json
|
||||
licenses.md
|
||||
|
||||
# Dependency update check
|
||||
dependency-update:
|
||||
name: Check for Dependency Updates
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
token: ${{ secrets.GITEA_TOKEN }}
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
|
||||
- name: Install pip-check-updates equivalent
|
||||
run: |
|
||||
python -m pip install --upgrade pip --root-user-action=ignore
|
||||
pip install --root-user-action=ignore pip-review
|
||||
|
||||
- name: Check for outdated packages
|
||||
run: |
|
||||
echo "Checking for outdated packages..."
|
||||
pip install --root-user-action=ignore -r requirements.txt
|
||||
pip list --outdated --format=json > outdated-packages.json || true
|
||||
|
||||
if [ -s outdated-packages.json ]; then
|
||||
echo "Outdated packages found:"
|
||||
cat outdated-packages.json | jq -r '.[] | "- \(.name): \(.version) -> \(.latest_version)"'
|
||||
else
|
||||
echo "All packages are up to date"
|
||||
fi
|
||||
|
||||
- name: Upload dependency reports
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: dependency-reports-${{ github.run_number }}
|
||||
path: |
|
||||
outdated-packages.json
|
||||
|
||||
# Code quality metrics
|
||||
code-quality:
|
||||
name: Code Quality Metrics
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
token: ${{ secrets.GITEA_TOKEN }}
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v4
|
||||
with:
|
||||
python-version: ${{ env.PYTHON_VERSION }}
|
||||
|
||||
- name: Install quality tools
|
||||
run: |
|
||||
python -m pip install --upgrade pip --root-user-action=ignore
|
||||
pip install --root-user-action=ignore radon xenon vulture
|
||||
pip install --root-user-action=ignore -r requirements.txt
|
||||
|
||||
- name: Calculate code complexity
|
||||
run: |
|
||||
echo "Calculating code complexity..."
|
||||
radon cc src/ --json > complexity-report.json
|
||||
radon mi src/ --json > maintainability-report.json
|
||||
|
||||
echo "Complexity Summary:"
|
||||
radon cc src/ --average
|
||||
|
||||
echo "Maintainability Summary:"
|
||||
radon mi src/
|
||||
|
||||
- name: Find dead code
|
||||
run: |
|
||||
echo "Checking for dead code..."
|
||||
vulture src/ --json > dead-code-report.json || true
|
||||
|
||||
- name: Check for code smells
|
||||
run: |
|
||||
echo "Checking for code smells..."
|
||||
xenon --max-absolute B --max-modules A --max-average A src/ || true
|
||||
|
||||
- name: Upload quality reports
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: code-quality-reports-${{ github.run_number }}
|
||||
path: |
|
||||
complexity-report.json
|
||||
maintainability-report.json
|
||||
dead-code-report.json
|
||||
|
||||
# Security summary
|
||||
security-summary:
|
||||
name: Security Summary
|
||||
runs-on: ubuntu-latest
|
||||
needs: [dependency-scan, license-check, code-quality]
|
||||
if: always()
|
||||
|
||||
steps:
|
||||
- name: Download all artifacts
|
||||
uses: actions/download-artifact@v3
|
||||
|
||||
- name: Generate security summary
|
||||
run: |
|
||||
echo "# Security Scan Summary" > security-summary.md
|
||||
echo "" >> security-summary.md
|
||||
echo "**Scan Date:** $(date -u)" >> security-summary.md
|
||||
echo "**Repository:** ${{ github.repository }}" >> security-summary.md
|
||||
echo "**Commit:** ${{ github.sha }}" >> security-summary.md
|
||||
echo "" >> security-summary.md
|
||||
|
||||
echo "## Results" >> security-summary.md
|
||||
echo "" >> security-summary.md
|
||||
|
||||
# Dependency scan results
|
||||
if [ -f security-reports-*/safety-report.json ]; then
|
||||
vuln_count=$(jq '.vulnerabilities | length' security-reports-*/safety-report.json 2>/dev/null || echo "0")
|
||||
if [ "$vuln_count" -eq 0 ]; then
|
||||
echo "- Dependency Scan: No vulnerabilities found" >> security-summary.md
|
||||
else
|
||||
echo "- Dependency Scan: $vuln_count vulnerabilities found" >> security-summary.md
|
||||
fi
|
||||
else
|
||||
echo "- Dependency Scan: Results not available" >> security-summary.md
|
||||
fi
|
||||
|
||||
# Docker scan results (removed Trivy)
|
||||
echo "- Docker Scan: Skipped (Trivy removed)" >> security-summary.md
|
||||
|
||||
# License check results
|
||||
if [ -f license-report-*/licenses.json ]; then
|
||||
echo "- License Check: Completed" >> security-summary.md
|
||||
else
|
||||
echo "- License Check: Results not available" >> security-summary.md
|
||||
fi
|
||||
|
||||
# Code quality results
|
||||
if [ -f code-quality-reports-*/complexity-report.json ]; then
|
||||
echo "- Code Quality: Analyzed" >> security-summary.md
|
||||
else
|
||||
echo "- Code Quality: Results not available" >> security-summary.md
|
||||
fi
|
||||
|
||||
echo "" >> security-summary.md
|
||||
echo "## Detailed Reports" >> security-summary.md
|
||||
echo "" >> security-summary.md
|
||||
echo "Detailed reports are available in the workflow artifacts." >> security-summary.md
|
||||
|
||||
cat security-summary.md
|
||||
|
||||
- name: Upload security summary
|
||||
uses: actions/upload-artifact@v3
|
||||
with:
|
||||
name: security-summary-${{ github.run_number }}
|
||||
path: security-summary.md
|
||||
licenses.json
|
||||
|
||||
@@ -148,6 +148,9 @@ grafana_data/
|
||||
models/*.joblib
|
||||
models/cache/
|
||||
models/metrics.json
|
||||
# scripts/retrain.sh working dirs (staging + one rollback generation)
|
||||
models/.staging/
|
||||
models/.previous/
|
||||
|
||||
# Playwright MCP browser artifacts (screenshots/snapshots from agent sessions)
|
||||
.playwright-mcp/
|
||||
|
||||
@@ -19,22 +19,20 @@ repos:
|
||||
|
||||
# Python code formatting with Black
|
||||
- repo: https://github.com/psf/black
|
||||
rev: 23.11.0
|
||||
rev: 26.5.1
|
||||
hooks:
|
||||
- id: black
|
||||
language_version: python3
|
||||
args: ['--line-length=120']
|
||||
|
||||
# Import sorting with isort
|
||||
- repo: https://github.com/pycqa/isort
|
||||
rev: 5.12.0
|
||||
hooks:
|
||||
- id: isort
|
||||
args: ['--profile', 'black', '--line-length', '120']
|
||||
|
||||
# Linting with flake8
|
||||
- repo: https://github.com/pycqa/flake8
|
||||
rev: 6.1.0
|
||||
hooks:
|
||||
- id: flake8
|
||||
args: ['--max-line-length=120', '--extend-ignore=E203,W503']
|
||||
args: ['--max-line-length=100', '--extend-ignore=E203,W503']
|
||||
|
||||
@@ -0,0 +1,40 @@
|
||||
# CLAUDE.md
|
||||
|
||||
Guidance for AI coding agents working in this repository.
|
||||
|
||||
## What this is
|
||||
|
||||
Flood monitoring and forecasting for the Ping River, Chiang Mai. Public dashboard and
|
||||
API at https://water.buildfor.life/ (never publish the server's private/Tailscale IP).
|
||||
Production: one systemd unit on a small VPS, `/opt/thailand-water-monitor`, user
|
||||
`water-monitor`, interpreter `.venv/bin/python` (uv-managed), updated by `git pull`.
|
||||
|
||||
## Rules
|
||||
|
||||
- Python 3.11 only. `uv sync --python 3.11`; run everything as `uv run ...`.
|
||||
- `make format` (black 88 / isort black profile, config in pyproject.toml) before
|
||||
committing; CI fails on formatting. `make test` must stay green — tests are
|
||||
synthetic-data only, never add one that needs the DB or network.
|
||||
- Timestamps everywhere are Asia/Bangkok wall-clock with no offset. The dashboard
|
||||
parses them with `parseTs()` and renders with `timeZone: TZ`; keep it that way.
|
||||
- Model changes go through the rolling-origin harness (`scripts/evaluate_variants.py`)
|
||||
and are judged on first-alert LEAD and false alarms, not MAE. Record results, positive
|
||||
or negative, in `docs/FLOOD_FORECASTING.md` section 5. Do not change what is deployed
|
||||
(`rise_rain` / hgb-v3) without a harness result that beats it on lead.
|
||||
- `train_all()` must never silently produce a gauge-only (v2) model; the guard that
|
||||
raises `RainUnavailableError` stays.
|
||||
- No `git add -A`: zero-byte shell-accident files (`#`, `$(wc`, ...) have been committed
|
||||
before. Stage files by name.
|
||||
- Do not add Co-Authored-By trailers.
|
||||
- The dashboard is a single file, `src/static/dashboard.html`, EN + TH via the `t()`
|
||||
table: every user-visible string needs both languages.
|
||||
|
||||
## Where things are
|
||||
|
||||
- `src/web_api.py` FastAPI app; `src/water_scraper_v3.py` RID collector;
|
||||
`src/hii_collector.py` ThaiWater/HII; `src/ml/` features/train/evaluate/predict,
|
||||
`rain.py` (Open-Meteo), `dam.py`, `hii_rain.py`.
|
||||
- `scripts/retrain.sh` + `water-monitor-retrain.timer`: monthly retrain with staged
|
||||
promote. `scripts/dev_proxy.py`: serve the working-copy dashboard against the live API.
|
||||
- `docs/FLOOD_FORECASTING.md` is the authoritative model write-up; `docs/DATA_SOURCES.md`
|
||||
the source catalog.
|
||||
@@ -1,492 +1,157 @@
|
||||
# Northern Thailand Ping River Monitor 🏔️
|
||||
# Northern Thailand Ping River Monitor
|
||||
|
||||
A comprehensive real-time water level monitoring system for the Ping River Basin in Northern Thailand, covering Royal Irrigation Department (RID) stations from Chiang Dao to Nakhon Sawan with advanced data collection, storage, and visualization capabilities.
|
||||
Live water levels, discharge, rainfall and machine-learning flood forecasts for the
|
||||
Ping River basin around Chiang Mai. Collects hourly gauge data from public sources,
|
||||
keeps the full history in PostgreSQL, and serves a bilingual dashboard, an open REST
|
||||
API, and 6/12/24-hour flood-risk forecasts per gauge.
|
||||
|
||||
[](https://git.b4l.co.th/B4L/Northern-Thailand-Ping-River-Monitor/actions) [](https://git.b4l.co.th/B4L/Northern-Thailand-Ping-River-Monitor/actions) [](https://git.b4l.co.th/B4L/Northern-Thailand-Ping-River-Monitor/actions) [](https://python.org) [](https://fastapi.tiangolo.com) [](https://docker.com) [](LICENSE) [](https://git.b4l.co.th/B4L/Northern-Thailand-Ping-River-Monitor/releases)
|
||||
**Live: [water.buildfor.life](https://water.buildfor.life/)** · API reference at
|
||||
[/docs](https://water.buildfor.life/docs) · built by [buildfor.life](https://buildfor.life)
|
||||
after the [October 2024 flood](https://buildfor.life/blog/chiang-mai-flood-2024/) —
|
||||
background in [Teaching a Model to See the Ping River Rise 13 Hours Early](https://buildfor.life/blog/ping-river-monitor/).
|
||||
|
||||
## 🌟 Features
|
||||
[](https://git.b4l.co.th/B4L/Northern-Thailand-Ping-River-Monitor/actions)
|
||||
[](https://git.b4l.co.th/B4L/Northern-Thailand-Ping-River-Monitor/actions)
|
||||
[](https://git.b4l.co.th/B4L/Northern-Thailand-Ping-River-Monitor/actions)
|
||||
[](https://python.org)
|
||||
[](LICENSE)
|
||||
|
||||
### 📊 **Real-time Data Collection**
|
||||
- **16 Monitoring Stations** across Thailand
|
||||
- **15-minute Collection Frequency** with intelligent scheduling
|
||||
- **Automatic Gap Filling** for missing historical data
|
||||
- **Data Validation** and error recovery mechanisms
|
||||
- **Rate Limiting** to prevent API abuse
|
||||
## What it does
|
||||
|
||||
### 🌐 **Web API Interface (NEW!)**
|
||||
- **FastAPI-powered REST API** with interactive documentation
|
||||
- **Station Management** - Add, update, and remove monitoring stations
|
||||
- **Real-time health monitoring** and system status
|
||||
- **Manual data collection triggers** via web interface
|
||||
- **Comprehensive metrics** and performance monitoring
|
||||
- **CORS support** for web applications
|
||||
- **Collects** hourly water level and discharge from 16 Royal Irrigation Department
|
||||
(RID) telemetry gauges, Chiang Dao to the southern basin, since 2018-08; hourly
|
||||
rainfall and water level from 400+ ThaiWater/HII stations; Open-Meteo catchment
|
||||
rainfall (archive + 48 h forecast); daily Mae Ngat reservoir state. Every source and
|
||||
its quirks: [docs/DATA_SOURCES.md](docs/DATA_SOURCES.md).
|
||||
- **Fills gaps.** The raw RID grid had readings for ~56 % of hours; a full-history
|
||||
re-fetch plus HII cross-fill brought it to ~93 %. `GET /api/stats` reports the
|
||||
current figure.
|
||||
- **Forecasts.** Per gauge and horizon, a gradient-boosted model predicts the rise
|
||||
within 6/12/24 h and the probability of crossing the station's warning and danger
|
||||
levels. Trained on the monitor's own history plus catchment rain; evaluated
|
||||
rolling-origin, event by event. On the October 2024 record flood, trained only on
|
||||
data through August 2024, the first alert came **13 hours before** P.1 crossed
|
||||
3.70 m. Everything about the model, including what did not work:
|
||||
[docs/FLOOD_FORECASTING.md](docs/FLOOD_FORECASTING.md).
|
||||
- **Shows it.** A Leaflet map with the river drawn as OSM geometry and styled by live
|
||||
discharge, rain gauges, the Chiang Mai inundation zones, per-station history, the
|
||||
forecast card, a replay of the 2024 flood, English/Thai, light/dark.
|
||||
- **Notifies.** Public push alerts over a self-hosted [ntfy](https://ntfy.sh): one
|
||||
message when a gauge crosses its warning or danger level, one all-clear on the
|
||||
way down, an opt-in early-warning topic from the model, nothing in between.
|
||||
Subscribe from the free app, no account. Matrix room alerts for a team are
|
||||
also supported.
|
||||
|
||||
### 🗄️ **Multi-Database Support**
|
||||
- **VictoriaMetrics** (Recommended) - High-performance time-series
|
||||
- **InfluxDB** - Purpose-built time-series database
|
||||
- **PostgreSQL + TimescaleDB** - Relational with time-series optimization
|
||||
- **MySQL** - Traditional relational database
|
||||
- **SQLite** - Local development and testing
|
||||
## Quick start
|
||||
|
||||
### 🗺️ **Geolocation Support**
|
||||
- **Grafana Geomap** integration ready
|
||||
- **GPS coordinates** and geohash support
|
||||
- **Interactive mapping** of water stations
|
||||
|
||||
### 📈 **Visualization & Monitoring**
|
||||
- **Pre-built Grafana dashboards**
|
||||
- **Real-time alerts** and notifications
|
||||
- **Historical trend analysis**
|
||||
- **Built-in metrics collection** (counters, gauges, histograms)
|
||||
- **Health checks** for database, API, and system resources
|
||||
|
||||
### 🚀 **Production Ready**
|
||||
- **Docker containerization** with multi-service support
|
||||
- **Systemd service** configuration
|
||||
- **HTTPS support** with SSL certificates
|
||||
- **Comprehensive logging** with rotation and colored output
|
||||
- **Type safety** with Pydantic models and type hints
|
||||
- **Custom exception handling** for better error management
|
||||
|
||||
## 🚀 Quick Start
|
||||
|
||||
### Prerequisites
|
||||
- Python 3.9 or higher
|
||||
- Internet connection for data fetching
|
||||
- Database server (optional - SQLite works out of the box)
|
||||
|
||||
### Installation
|
||||
Python **3.11** (3.13 breaks the pinned `psycopg2-binary`), PostgreSQL for anything
|
||||
beyond a quick look, [uv](https://docs.astral.sh/uv/).
|
||||
|
||||
```bash
|
||||
# Clone the repository
|
||||
git clone https://git.b4l.co.th/B4L/Northern-Thailand-Ping-River-Monitor.git
|
||||
cd Northern-Thailand-Ping-River-Monitor
|
||||
|
||||
# Quick setup with Make
|
||||
make dev-setup
|
||||
|
||||
# Or manual setup:
|
||||
python -m venv venv
|
||||
source venv/bin/activate # Windows: venv\Scripts\activate
|
||||
pip install -r requirements.txt
|
||||
cp .env.example .env
|
||||
uv sync --python 3.11
|
||||
cp .env.example .env # DB_TYPE, POSTGRES_CONNECTION_STRING, optional MATRIX_*
|
||||
uv run python run.py --web-api # dashboard + API on http://localhost:8000
|
||||
```
|
||||
|
||||
### Basic Usage
|
||||
`DB_TYPE=sqlite` works for the dashboard and API; the forecasting path expects the
|
||||
PostgreSQL history.
|
||||
|
||||
```bash
|
||||
# Test run with SQLite (default)
|
||||
make run-test
|
||||
# or: python run.py --test
|
||||
|
||||
# Run continuous monitoring
|
||||
make run
|
||||
# or: python run.py
|
||||
|
||||
# Start web API server (NEW!)
|
||||
make run-api
|
||||
# or: python run.py --web-api
|
||||
|
||||
# Run all tests
|
||||
make test
|
||||
|
||||
# Demo different databases
|
||||
python src/demo_databases.py
|
||||
uv run python run.py --status # collector status
|
||||
uv run python run.py --test # one collection cycle
|
||||
uv run python run.py --fill-gaps 7 # re-fetch the last 7 days from RID
|
||||
uv run python run.py --collect-hii # one ThaiWater/HII collection cycle
|
||||
uv run python run.py --alert-check # evaluate thresholds, notify Matrix
|
||||
uv run python scripts/train_flood_model.py --stations all # retrain (~12 min)
|
||||
make test # pytest, synthetic data, no network
|
||||
make format # black + isort (the CI contract)
|
||||
```
|
||||
|
||||
### 🌐 Web API Interface (NEW!)
|
||||
## API
|
||||
|
||||
The system now includes a comprehensive FastAPI web interface:
|
||||
Read-only, no key, JSON. Base URL `https://water.buildfor.life`; timestamps are
|
||||
Asia/Bangkok wall-clock without an offset suffix.
|
||||
|
||||
| Endpoint | Returns |
|
||||
| --- | --- |
|
||||
| `GET /stations` | The 16 RID gauges: code, Thai/English names, coordinates |
|
||||
| `GET /measurements/latest?limit=N` | Newest reading per station |
|
||||
| `GET /measurements/history/{code}?hours=N` | Hourly history; or `?start=YYYY-MM-DD&end=YYYY-MM-DD`; `limit` ≤ 100000 |
|
||||
| `GET /forecast` | Current flood-risk forecast, every station × horizon, with thresholds and P.1 inundation-stage probabilities |
|
||||
| `GET /api/forecast/history/{code}?hours=N&horizon=24` | Forecasts as issued, for auditing lead time after the fact |
|
||||
| `GET /api/hii/rainfall/latest`, `/api/hii/waterlevel/latest` | Latest ThaiWater/HII gauge readings |
|
||||
| `GET /api/hii/rainfall/catchment?days=N` | HII gauge catchment-mean rain next to the Open-Meteo series the model uses |
|
||||
| `GET /api/forecast/skill?station_code=P.1` | Issued forecasts vs what happened, per deployed model version |
|
||||
| `GET /api/notifications` | ntfy server and topic names for the subscribe panel |
|
||||
| `GET /api/stats` | Row counts per source, date range, coverage |
|
||||
| `GET /health` | DB / upstream / memory checks |
|
||||
|
||||
Interactive reference with schemas: [water.buildfor.life/docs](https://water.buildfor.life/docs).
|
||||
Responses are cached briefly server-side; poll no faster than once a minute — the data
|
||||
changes hourly.
|
||||
|
||||
## Deployment
|
||||
|
||||
Production is a systemd unit on a small VPS behind Cloudflare, updated by `git pull`.
|
||||
`scripts/install.sh` (run as root from a checkout) creates the `water-monitor` user,
|
||||
deploys to `/opt/thailand-water-monitor`, runs `uv sync` into `.venv`, installs
|
||||
`water-monitor.service` and the monthly `water-monitor-retrain.timer`.
|
||||
|
||||
```bash
|
||||
# Start the web API
|
||||
python run.py --web-api
|
||||
|
||||
# Access the API at:
|
||||
# - Dashboard: http://localhost:8000
|
||||
# - Interactive docs: http://localhost:8000/docs
|
||||
# - Health check: http://localhost:8000/health
|
||||
# - Latest data: http://localhost:8000/measurements/latest
|
||||
```
|
||||
|
||||
**Key API Endpoints:**
|
||||
- `GET /` - Web dashboard
|
||||
- `GET /health` - System health status
|
||||
- `GET /metrics` - Application metrics
|
||||
- `GET /stations` - List all monitoring stations
|
||||
- `POST /stations` - Add new monitoring station
|
||||
- `PUT /stations/{id}` - Update station information
|
||||
- `DELETE /stations/{id}` - Remove monitoring station
|
||||
- `GET /measurements/latest` - Latest measurements
|
||||
- `GET /measurements/station/{code}` - Station-specific data
|
||||
- `POST /scrape/trigger` - Trigger manual data collection
|
||||
|
||||
## 📊 Station Information
|
||||
|
||||
The system monitors **16 water stations** along the Ping River Basin in Northern Thailand:
|
||||
|
||||
| Station | Thai Name | English Name | Location |
|
||||
|---------|-----------|--------------|----------|
|
||||
| P.1 | สะพานนวรัฐ | Nawarat Bridge | Nakhon Sawan |
|
||||
| P.5 | สะพานท่านาง | Tha Nang Bridge | - |
|
||||
| P.20 | บ้านเชียงดาว | Ban Chiang Dao | Chiang Mai |
|
||||
| P.21 | บ้านริมใต้ | Ban Rim Tai | - |
|
||||
| P.4A | บ้านแม่แตง | Ban Mae Taeng | Chiang Mai |
|
||||
| P.67 | บ้านแม่แต | Ban Tae | - |
|
||||
| P.75 | บ้านช่อแล | Ban Chai Lat | - |
|
||||
| P.76 | บ้านแม่อีไฮ | Banb Mae I Hai | - |
|
||||
| P.77 | บ้านสบแม่สะป๊วด | Baan Sop Mae Sapuord | - |
|
||||
| P.81 | บ้านโป่ง | Ban Pong | - |
|
||||
| P.82 | บ้านสบวิน | Ban Sob win | - |
|
||||
| P.84 | บ้านพันตน | Ban Panton | - |
|
||||
| P.85 | บ้านหล่ายแก้ว | Baan Lai Kaew | - |
|
||||
| P.87 | บ้านป่าซาง | Ban Pa Sang | - |
|
||||
| P.92 | บ้านเมืองกึ๊ด | Ban Muang Aut | - |
|
||||
| P.103 | สะพานวงแหวนรอบ 3 | Ring Bridge 3 | Bangkok |
|
||||
|
||||
### Data Metrics
|
||||
- **Water Level**: Measured in meters (m)
|
||||
- **Discharge**: Flow rate in cubic meters per second (cms)
|
||||
- **Discharge Percentage**: Relative to station capacity
|
||||
- **Timestamp**: Thai time (UTC+7) with Buddhist calendar support
|
||||
|
||||
## 🗄️ Database Configuration
|
||||
|
||||
### VictoriaMetrics (Recommended)
|
||||
|
||||
**High-performance time-series database with excellent compression and query speed.**
|
||||
|
||||
```bash
|
||||
# Environment variables
|
||||
export DB_TYPE=victoriametrics
|
||||
export VM_HOST=localhost
|
||||
export VM_PORT=8428
|
||||
|
||||
# Quick start with Docker
|
||||
docker run -d \
|
||||
--name victoriametrics \
|
||||
-p 8428:8428 \
|
||||
-v victoria-metrics-data:/victoria-metrics-data \
|
||||
victoriametrics/victoria-metrics:latest \
|
||||
--storageDataPath=/victoria-metrics-data \
|
||||
--retentionPeriod=2y \
|
||||
--httpListenAddr=:8428
|
||||
```
|
||||
|
||||
### Complete Stack with Grafana
|
||||
|
||||
```bash
|
||||
# Start the complete monitoring stack
|
||||
docker-compose -f docker-compose.victoriametrics.yml up -d
|
||||
|
||||
# Access Grafana at http://localhost:3000
|
||||
# Username: admin, Password: admin_password
|
||||
```
|
||||
|
||||
### Other Database Options
|
||||
|
||||
<details>
|
||||
<summary>InfluxDB Configuration</summary>
|
||||
|
||||
```bash
|
||||
export DB_TYPE=influxdb
|
||||
export INFLUX_HOST=localhost
|
||||
export INFLUX_PORT=8086
|
||||
export INFLUX_DATABASE=water_monitoring
|
||||
export INFLUX_USERNAME=water_user
|
||||
export INFLUX_PASSWORD=your_password
|
||||
```
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>PostgreSQL Configuration</summary>
|
||||
|
||||
```bash
|
||||
export DB_TYPE=postgresql
|
||||
export POSTGRES_CONNECTION_STRING=postgresql://user:password@localhost:5432/water_monitoring
|
||||
```
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary>MySQL Configuration</summary>
|
||||
|
||||
```bash
|
||||
export DB_TYPE=mysql
|
||||
export MYSQL_CONNECTION_STRING=mysql://user:password@localhost:3306/water_monitoring
|
||||
```
|
||||
</details>
|
||||
|
||||
## 📈 Grafana Dashboards
|
||||
|
||||
### Pre-built Dashboard Features
|
||||
- **Real-time water levels** across all stations
|
||||
- **Historical trends** and patterns
|
||||
- **Discharge monitoring** with percentage indicators
|
||||
- **Station status** and health monitoring
|
||||
- **Geomap visualization** of station locations
|
||||
- **Alert thresholds** for critical water levels
|
||||
|
||||
### Sample Queries
|
||||
|
||||
**VictoriaMetrics/Prometheus:**
|
||||
```promql
|
||||
# Current water levels
|
||||
water_level
|
||||
|
||||
# High discharge alerts
|
||||
water_discharge_percent > 80
|
||||
|
||||
# Station-specific data
|
||||
water_level{station_code="P.1"}
|
||||
```
|
||||
|
||||
**SQL Databases:**
|
||||
```sql
|
||||
-- Latest readings from all stations
|
||||
SELECT s.station_code, s.english_name, m.water_level, m.discharge
|
||||
FROM stations s
|
||||
JOIN water_measurements m ON s.id = m.station_id
|
||||
WHERE m.timestamp = (SELECT MAX(timestamp) FROM water_measurements WHERE station_id = s.id);
|
||||
```
|
||||
|
||||
## 🚀 Production Deployment
|
||||
|
||||
### Docker Deployment
|
||||
|
||||
```bash
|
||||
# Build the image
|
||||
docker build -t thailand-water-monitor .
|
||||
|
||||
# Run with environment variables
|
||||
docker run -d \
|
||||
--name water-monitor \
|
||||
-e DB_TYPE=victoriametrics \
|
||||
-e VM_HOST=victoriametrics \
|
||||
thailand-water-monitor
|
||||
```
|
||||
|
||||
### Systemd Service (Linux)
|
||||
|
||||
The install script sets everything up: a dedicated `water-monitor` system user,
|
||||
a deploy to `/opt/thailand-water-monitor`, a uv-managed virtualenv, and the
|
||||
enabled systemd unit.
|
||||
|
||||
```bash
|
||||
# From a checkout of the repo, as root:
|
||||
sudo bash scripts/install.sh
|
||||
|
||||
# Then start and check:
|
||||
sudo systemctl start water-monitor.service
|
||||
systemctl status water-monitor.service
|
||||
systemctl list-timers water-monitor-retrain.timer
|
||||
```
|
||||
|
||||
Fill in `/opt/thailand-water-monitor/.env` (Matrix token/room, DB settings)
|
||||
before starting if the script reports it is missing.
|
||||
The retrain timer runs `scripts/retrain.sh`, which trains into `models/.staging`,
|
||||
refuses to promote anything that is not a rain-enabled (`hgb-v3+`) set covering the
|
||||
expected stations, and renames the bundles into place. Details and the operations
|
||||
runbook: [docs/FLOOD_FORECASTING.md](docs/FLOOD_FORECASTING.md) sections 6–8.
|
||||
|
||||
<details>
|
||||
<summary>Manual setup (if you prefer not to use the script)</summary>
|
||||
|
||||
```bash
|
||||
sudo useradd --system --no-create-home --shell /usr/sbin/nologin water-monitor
|
||||
sudo cp scripts/water-monitor.service /etc/systemd/system/
|
||||
sudo systemctl enable water-monitor.service
|
||||
sudo systemctl start water-monitor.service
|
||||
```
|
||||
</details>
|
||||
|
||||
|
||||
## 🔧 Command Line Tools
|
||||
|
||||
### Main Application
|
||||
```bash
|
||||
python src/water_scraper_v3.py # Run continuous monitoring
|
||||
python src/water_scraper_v3.py --test # Single test cycle
|
||||
python src/water_scraper_v3.py --help # Show help
|
||||
```
|
||||
|
||||
### Data Management
|
||||
```bash
|
||||
python src/water_scraper_v3.py --check-gaps 7 # Check for missing data (7 days)
|
||||
python src/water_scraper_v3.py --fill-gaps 7 # Fill missing data gaps
|
||||
python src/water_scraper_v3.py --update-data 2 # Update existing data (2 days)
|
||||
```
|
||||
|
||||
### Database Testing
|
||||
```bash
|
||||
python src/demo_databases.py # SQLite demo
|
||||
python src/demo_databases.py victoriametrics # VictoriaMetrics demo
|
||||
python src/demo_databases.py all # Test all databases
|
||||
```
|
||||
|
||||
## 📚 Documentation
|
||||
|
||||
### Core Documentation
|
||||
- **[Data Sources & API Catalog](docs/DATA_SOURCES.md)** - Every ingested and available data source (RID, ThaiWater/HII, dams, rainfall, forecasts)
|
||||
- **[Installation Guide](docs/DATABASE_DEPLOYMENT_GUIDE.md)** - Complete setup instructions
|
||||
- **[Gap Filling Guide](docs/GAP_FILLING_GUIDE.md)** - Data integrity management
|
||||
|
||||
### Deployment Guides
|
||||
- **[VictoriaMetrics Setup](docs/VICTORIAMETRICS_SETUP.md)** - High-performance deployment
|
||||
- **[Debian Troubleshooting](docs/DEBIAN_TROUBLESHOOTING.md)** - Linux deployment issues
|
||||
|
||||
### References
|
||||
- **[Notable Documents](docs/references/NOTABLE_DOCUMENTS.md)** - Official Thai government resources
|
||||
|
||||
## 🔍 Troubleshooting
|
||||
|
||||
### Common Issues
|
||||
|
||||
**Database Connection Errors:**
|
||||
```bash
|
||||
# Check database status
|
||||
python src/demo_databases.py
|
||||
|
||||
# Test specific database
|
||||
python src/demo_databases.py victoriametrics
|
||||
```
|
||||
|
||||
**Missing Data:**
|
||||
```bash
|
||||
# Check for gaps
|
||||
python src/water_scraper_v3.py --check-gaps 7
|
||||
|
||||
# Fill missing data
|
||||
python src/water_scraper_v3.py --fill-gaps 7
|
||||
```
|
||||
|
||||
**Service Issues:**
|
||||
```bash
|
||||
# Check service status
|
||||
sudo systemctl status water-monitor
|
||||
|
||||
# View logs
|
||||
sudo journalctl -u water-monitor -f
|
||||
```
|
||||
|
||||
### Health Checks
|
||||
|
||||
```bash
|
||||
# VictoriaMetrics health
|
||||
curl http://localhost:8428/health
|
||||
|
||||
# Check latest data
|
||||
curl "http://localhost:8428/api/v1/query?query=water_level"
|
||||
|
||||
# Application logs
|
||||
tail -f water_monitor.log
|
||||
```
|
||||
|
||||
## 🌐 API Integration
|
||||
|
||||
### VictoriaMetrics API Examples
|
||||
|
||||
```bash
|
||||
# Query current water levels
|
||||
curl "http://localhost:8428/api/v1/query?query=water_level"
|
||||
|
||||
# Query discharge rates for last hour
|
||||
curl "http://localhost:8428/api/v1/query_range?query=water_discharge&start=$(date -d '1 hour ago' +%s)&end=$(date +%s)&step=300"
|
||||
|
||||
# Query specific station
|
||||
curl "http://localhost:8428/api/v1/query?query=water_level{station_code=\"P.1\"}"
|
||||
|
||||
# High discharge alerts
|
||||
curl "http://localhost:8428/api/v1/query?query=water_discharge_percent>80"
|
||||
```
|
||||
|
||||
## 📊 Performance
|
||||
|
||||
### System Requirements
|
||||
- **CPU**: 1-2 cores (minimal load)
|
||||
- **RAM**: 512MB - 2GB (depending on database)
|
||||
- **Storage**: 1GB+ (for historical data)
|
||||
- **Network**: Stable internet connection
|
||||
|
||||
### Performance Metrics
|
||||
- **Data Collection**: ~300 data points every 15 minutes
|
||||
- **Database Write Speed**: 1000+ points/second (VictoriaMetrics)
|
||||
- **Query Response**: <100ms for recent data
|
||||
- **Storage Efficiency**: 70x compression vs. raw data
|
||||
|
||||
## 🤝 Contributing
|
||||
|
||||
Contributions are welcome! Please:
|
||||
|
||||
1. Fork the repository
|
||||
2. Create a feature branch
|
||||
3. Make your changes
|
||||
4. Add tests if applicable
|
||||
5. Submit a pull request
|
||||
|
||||
### Development Setup
|
||||
|
||||
```bash
|
||||
# Clone your fork
|
||||
git clone https://github.com/your-username/thailand-water-monitor.git
|
||||
cd thailand-water-monitor
|
||||
|
||||
# Install development dependencies
|
||||
pip install -r requirements.txt
|
||||
pip install pytest black flake8
|
||||
|
||||
# Run tests
|
||||
pytest
|
||||
|
||||
# Format code
|
||||
black src/
|
||||
```
|
||||
|
||||
## 📄 License
|
||||
|
||||
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
|
||||
|
||||
## 🙏 Acknowledgments
|
||||
|
||||
- **Royal Irrigation Department (RID)** of Thailand for providing the data API
|
||||
- **VictoriaMetrics** team for the excellent time-series database
|
||||
- **Grafana** team for the visualization platform
|
||||
- **Python community** for the amazing libraries and tools
|
||||
|
||||
## 📞 Support
|
||||
|
||||
- **Issues**: [GitHub Issues](https://github.com/your-username/thailand-water-monitor/issues)
|
||||
- **Discussions**: [GitHub Discussions](https://github.com/your-username/thailand-water-monitor/discussions)
|
||||
- **Documentation**: [Project Wiki](https://github.com/your-username/thailand-water-monitor/wiki)
|
||||
|
||||
---
|
||||
|
||||
## 📁 Project Structure
|
||||
## Repository layout
|
||||
|
||||
```
|
||||
Northern-Thailand-Ping-River-Monitor/
|
||||
├── src/ # Main application code
|
||||
├── tests/ # Test suite
|
||||
├── docs/ # Documentation
|
||||
├── grafana/ # Grafana dashboards
|
||||
├── scripts/ # Utility scripts
|
||||
├── docker-compose.yml # Docker deployment
|
||||
├── Makefile # Development tasks
|
||||
└── requirements.txt # Dependencies
|
||||
src/ collector, API (web_api.py), dashboard (static/dashboard.html)
|
||||
src/ml/ features, training, evaluation harness, prediction, rain/dam/HII loaders
|
||||
scripts/ train_flood_model.py, retrain.sh, evaluate_variants.py, install.sh, dev_proxy.py
|
||||
tests/ pytest suite (synthetic data; no DB or network)
|
||||
docs/ FLOOD_FORECASTING.md, DATA_SOURCES.md, deployment and station guides
|
||||
models/ trained bundles + metrics.json (gitignored) and evaluation results (tracked)
|
||||
.gitea/workflows/ ci (format/lint/tests), security (pip-audit/bandit), docs (link + OpenAPI checks)
|
||||
```
|
||||
|
||||
See [docs/FLOOD_FORECASTING.md](docs/FLOOD_FORECASTING.md) for the forecasting architecture and [docs/DATA_SOURCES.md](docs/DATA_SOURCES.md) for the data pipeline.
|
||||
## Documentation
|
||||
|
||||
## 🔄 CI/CD & Automation
|
||||
- [docs/FLOOD_FORECASTING.md](docs/FLOOD_FORECASTING.md) — the model: data, features, evaluation, measured performance, negatives, deployment, retraining
|
||||
- [docs/DATA_SOURCES.md](docs/DATA_SOURCES.md) — every ingested and candidate source, endpoints, quirks
|
||||
- [docs/STATION_MANAGEMENT_GUIDE.md](docs/STATION_MANAGEMENT_GUIDE.md) — adding/editing gauges
|
||||
- [docs/DATABASE_DEPLOYMENT_GUIDE.md](docs/DATABASE_DEPLOYMENT_GUIDE.md), [POSTGRESQL_SETUP.md](POSTGRESQL_SETUP.md) — database setup
|
||||
- [docs/NOTIFICATIONS.md](docs/NOTIFICATIONS.md) — public push alerts: topics, semantics, ntfy deployment
|
||||
- [docs/MATRIX_QUICK_START.md](docs/MATRIX_QUICK_START.md) — Matrix room alerts for a team
|
||||
- [docs/GAP_FILLING_GUIDE.md](docs/GAP_FILLING_GUIDE.md) — data integrity tooling
|
||||
- [docs/references/NOTABLE_DOCUMENTS.md](docs/references/NOTABLE_DOCUMENTS.md) — official Thai government resources
|
||||
- Public overview: [buildfor.life/docs/tooling/ping-river-monitor](https://buildfor.life/docs/tooling/ping-river-monitor/)
|
||||
|
||||
The project includes comprehensive Gitea Actions workflows:
|
||||
Other database backends (VictoriaMetrics, InfluxDB, MySQL, SQLite) and the Grafana
|
||||
dashboards under `grafana/` are supported by the adapters but not what production
|
||||
runs; see [docs/VICTORIAMETRICS_SETUP.md](docs/VICTORIAMETRICS_SETUP.md) if you want them.
|
||||
|
||||
- **🧪 CI/CD Pipeline** - Automated testing, building, and deployment
|
||||
- **🔒 Security Scanning** - Daily vulnerability and dependency checks
|
||||
- **📚 Documentation** - Automated API docs and validation
|
||||
- **🚀 Release Management** - Automated releases with multi-arch Docker builds
|
||||
## Contributing
|
||||
|
||||
See [docs/GITEA_WORKFLOWS.md](docs/GITEA_WORKFLOWS.md) for detailed workflow documentation.
|
||||
`make format` before committing (black 88 columns, isort black profile — the CI gate),
|
||||
`make test` must stay green, tests use synthetic data only. See
|
||||
[CONTRIBUTING.md](CONTRIBUTING.md). Issues and merge requests on
|
||||
[git.b4l.co.th](https://git.b4l.co.th/B4L/Northern-Thailand-Ping-River-Monitor).
|
||||
|
||||
## 🔗 Repository
|
||||
## Data sources and thanks
|
||||
|
||||
- **Main Repository**: https://git.b4l.co.th/B4L/Northern-Thailand-Ping-River-Monitor
|
||||
- **Issues**: https://git.b4l.co.th/B4L/Northern-Thailand-Ping-River-Monitor/issues
|
||||
- **Actions**: https://git.b4l.co.th/B4L/Northern-Thailand-Ping-River-Monitor/actions
|
||||
- **Documentation**: [docs/](docs/)
|
||||
Royal Irrigation Department (RID) gauge telemetry; Hydro-Informatics Institute (HII) /
|
||||
ThaiWater open API; Open-Meteo; OpenStreetMap contributors for the river geometry;
|
||||
Chiang Mai Municipality for the inundation map the P.1 stages are keyed to. All
|
||||
instruments are theirs; we aggregate, store, fill gaps and forecast.
|
||||
|
||||
**Made with ❤️ for water resource monitoring in Northern Thailand's Ping River Basin**
|
||||
## License
|
||||
|
||||
MIT — see [LICENSE](LICENSE).
|
||||
|
||||
@@ -68,7 +68,7 @@ environment variable, then `Config.get_database_config()` when `DB_TYPE` is
|
||||
1. **PostgreSQL** (`_fetch_from_db`) — the primary path. NULL discharge stays
|
||||
NULL, which matters because the models must learn from the real missingness
|
||||
pattern.
|
||||
2. **HTTP API** (`_fetch_from_api`, default `http://100.81.167.42:8000`) — a
|
||||
2. **HTTP API** (`_fetch_from_api`, default `https://water.buildfor.life`) — a
|
||||
fallback for running off-server. **Caveat:** the public history endpoint
|
||||
backfills missing discharge with a synthetic rating-curve estimate, so this
|
||||
path is not equivalent to the DB path. It is flagged as
|
||||
@@ -536,6 +536,54 @@ exists alongside its flood events.
|
||||
(`fill_from_hii`, +9,341 h at P.81, +682 h at P.92, +810 h at P.20) is
|
||||
lead-neutral — the gate holds at 13 h with fill on — and ships enabled.
|
||||
|
||||
### 2026-09-12: three candidates on top of hgb-v3 — two rejected, one deferred
|
||||
|
||||
Same rolling-origin harness (`src/ml/evaluate.py`, five monsoon folds
|
||||
2021–2025, P.1 and P.103), all variants run from the identical
|
||||
`models/cache/` snapshot (`--from-cache`), results in
|
||||
`models/eval_2026-09-12*.json`, tables via `scripts/summarize_eval.py`.
|
||||
Baseline is `rise_rain`, the deployed configuration.
|
||||
|
||||
**Quantile regression heads (`rise_rain_quantile`, `_uw`) — rejected.** The
|
||||
August result that quantile loss beat L2 on MAE held with rain in the model
|
||||
(P.1 0.083/0.081 vs 0.087; P.103 0.143/0.124 vs 0.152), and Brier improved a
|
||||
hair, but the operational numbers went the wrong way: at P.103 the 2022-08-14
|
||||
crossing dropped from +6 h to +1 h lead, 2022-10-02 from +9 h to +5/+3 h, and
|
||||
the 2024-09-30 event from +9 h to +4 h; at P.1 2022 dropped +5 → +3/+2 h and
|
||||
2025 +2 → +1 h, with one false-alarm episode where the baseline had none. A
|
||||
median predicts the *typical* rise, and on the run-up to a crossing the typical
|
||||
rise is not the one that matters. MAE is not the objective; lead is.
|
||||
|
||||
**Quantile heads for sigma only (`rise_rain_qsigma`) — no effect.** The
|
||||
hybrid keeps the L2 point prediction (so every lead is identical to the
|
||||
baseline by construction — p≥0.5 alerts are sigma-independent) and derives a
|
||||
per-row sigma from q90−q50. Brier moved 0.0031 → 0.0029 at P.1 and
|
||||
0.0061 → 0.0060 at P.103, i.e. within noise, at the cost of three fitted
|
||||
heads per horizon instead of one. Per-row uncertainty from this family of
|
||||
models is not informative enough here to be worth the training time; the
|
||||
0.15 m floor stays.
|
||||
|
||||
**Forward-48 h forecast rain (`rise_rain_fc48`) — deferred.** Adding the
|
||||
`(t, t+48]` Open-Meteo sum alongside `rain_fc24` left MAE, Brier and false
|
||||
alarms unchanged and every event lead within ±1 h of baseline, *except* the
|
||||
2024-10-03 P.1 record crossing, which went from +21 h to +72 h (and +55 → +69 h
|
||||
at P.103). That is one event with the highest stakes in the record, on the
|
||||
same feature family that already produced the 2024 gain, but n=1 is not
|
||||
evidence: the P.103 2025-09-26 event lost 2 h in the same run. Rerun after the
|
||||
2026 season adds events; if the 48 h window still moves only the biggest
|
||||
onsets, promote it. Serving would need no new data source (`fetch_forecast`
|
||||
already pulls `forecast_days=2`).
|
||||
|
||||
**HII gauge rain — not evaluable yet.** `hii_rainfall` (~130 gauges in the
|
||||
upper-Ping box, DWR/FOP/HII/RID/TMD) is the obvious independent rain source,
|
||||
but the table only exists since 2026-08-11 and the api-v3 archive endpoint
|
||||
ignores its date range (see `docs/DATA_SOURCES.md` §2.1), so every training
|
||||
row before that is NaN and no fold in the harness has gauge data in its test
|
||||
span. `src/ml/hii_rain.py` builds the catchment mean and
|
||||
`GET /api/hii/rainfall/catchment` exposes it next to the Open-Meteo series with
|
||||
a 24 h-sum bias/MAE/correlation, so the two sources' relationship is on record
|
||||
by the time the 2027 fold (train ≤ 2027-04-30, test Jun–Nov 2027) can test it.
|
||||
|
||||
## 6. Deployment
|
||||
|
||||
### API
|
||||
@@ -733,6 +781,32 @@ timestamp in every bundle. Both are echoed in every `/forecast` row, so you can
|
||||
tell from the API response alone which code produced a forecast and how old the
|
||||
model is.
|
||||
|
||||
**Scheduled retrain (since 2026-09-12).** `scripts/water-monitor-retrain.timer`
|
||||
fires `water-monitor-retrain.service` on the 1st of every month at 03:30 server
|
||||
time (`Persistent=true`, so a missed run catches up at boot). The unit runs
|
||||
`scripts/retrain.sh` as the service user with `OMP_NUM_THREADS=4`, `Nice=15`:
|
||||
|
||||
1. trains all stations into `models/.staging/` (the API keeps serving the old
|
||||
bundles throughout);
|
||||
2. refuses to promote unless `metrics.json` reports a `hgb-v3+` version and at
|
||||
least 14 trained stations (exit 3, staging discarded, old models untouched);
|
||||
3. renames the new bundles into `models/`, moving the previous generation to
|
||||
`models/.previous/` for rollback.
|
||||
|
||||
No API restart: `predict.py` reloads bundles by mtime on the next hourly
|
||||
precompute. `systemctl list-timers water-monitor-retrain.timer` shows the next
|
||||
run; `sudo systemctl start water-monitor-retrain.service` runs it now (after a
|
||||
flood, say); `journalctl -u water-monitor-retrain` has the log. The installer
|
||||
(`scripts/install.sh`) enables the timer.
|
||||
|
||||
**Why the trainer refuses to run without rain (since 2026-09-12).** On
|
||||
2026-09-01 the server retrain could not reach the Open-Meteo archive on a
|
||||
checkout with no `models/cache/`, logged a warning, and quietly overwrote the
|
||||
v3 bundles with gauge-only v2 ones — the 13-hour early warning on the 2024 flood
|
||||
became an 18-hour late one and nothing on the dashboard said so. `train_all()`
|
||||
now raises `RainUnavailableError` (CLI exit 2) in that situation. Gauge-only
|
||||
bundles are still available, but only by asking for them: `--no-rain`.
|
||||
|
||||
## 8. Operations runbook
|
||||
|
||||
All commands assume the project virtualenv is active (`.venv` locally).
|
||||
@@ -786,10 +860,12 @@ that went quiet, or a bad backfill) rather than a modelling one.
|
||||
python -m pytest tests/test_flood_forecast.py -v
|
||||
```
|
||||
|
||||
Seven tests covering leakage, label alignment, the coverage gate, forward-fill and
|
||||
staleness, a train/predict round trip, the heuristic fallback, and feature-name
|
||||
stability. The whole suite runs in about 8 seconds, so there is no excuse for
|
||||
skipping it before a deploy.
|
||||
Tests cover leakage, label alignment, the coverage gate, forward-fill and
|
||||
staleness, a train/predict round trip, the heuristic fallback, feature-name
|
||||
stability, and the rain-downgrade guard (no rain series → `RainUnavailableError`,
|
||||
nothing written; `--no-rain` → v2; rain present → v3 with the rain columns in
|
||||
`feature_names`). The file runs in well under a minute, so there is no excuse
|
||||
for skipping it before a deploy.
|
||||
|
||||
**Understanding graceful degradation.** Three things can make a forecast row
|
||||
non-model-backed, and all of them are visible in the payload:
|
||||
|
||||
@@ -0,0 +1,132 @@
|
||||
# Flood notifications (ntfy)
|
||||
|
||||
Public push notifications for threshold crossings, without accounts, mailing
|
||||
lists or app-store review: the monitor publishes to a self-hosted
|
||||
[ntfy](https://ntfy.sh) server, and anyone subscribes to the topics they care
|
||||
about from the free ntfy app (iOS, Android, F-Droid) or a browser tab.
|
||||
|
||||
ntfy is one Go binary with a sqlite cache: ~30 MB RSS idle, negligible CPU. It
|
||||
runs on the same VPS as the monitor.
|
||||
|
||||
## What subscribers get
|
||||
|
||||
Every message is a **transition**, never a state. Crossing up into a level sends
|
||||
one message; dropping back below it (with 0.10 m hysteresis) sends one
|
||||
all-clear. A river that sits at 3.9 m for three days produces two messages, not
|
||||
seventy-two. In a quiet season a subscriber hears nothing.
|
||||
|
||||
| Topic | Trigger | Priority |
|
||||
|---|---|---|
|
||||
| `ping-warning` | any gauge crosses its warning threshold; levels falling back | 4 (high) / 2 |
|
||||
| `ping-danger` | any gauge crosses its danger threshold | 5 (max, breaks Do-Not-Disturb) |
|
||||
| `ping-<station>-warning` | that gauge crosses warning; back to normal | 4 / 2 |
|
||||
| `ping-<station>-danger` | that gauge crosses danger; back below danger | 5 / 3 |
|
||||
| `ping-p1-outlook` | model P(warning within 24 h) at P.1 rises through 50 % (clears below 25 %) | 4 / 2 |
|
||||
| `ping-status` | gauge feed stale ≥ 3 h; feed recovered | 3 / 2 |
|
||||
|
||||
Station slugs are the code lowercased without the dot: `p1`, `p103`, `p67`.
|
||||
Thresholds are the ones in `src/ml/features.py` (`THRESHOLDS`): P.1 3.70 /
|
||||
4.20 m, P.103 5.95 / 6.75 m, and so on.
|
||||
|
||||
The outlook topic is opt-in for a reason: it is model output, and the message
|
||||
says so. Observed-crossing topics only ever report a gauge reading.
|
||||
|
||||
Each message carries a click-through and an "Open dashboard" action button to
|
||||
the public dashboard.
|
||||
|
||||
## How it runs
|
||||
|
||||
`src/notify.py` is called once per collection cycle inside the API process
|
||||
(leader only), right after the forecast precompute, so it sees exactly the
|
||||
readings and forecasts the dashboard shows. Per-key last-sent state is stored
|
||||
in the `notification_state` table of the monitor's own database, so a restart
|
||||
or redeploy never re-sends and never misses a crossing that happened while
|
||||
the service was down (the next cycle compares against the persisted state).
|
||||
|
||||
If ntfy is unreachable the transition is **not** recorded, so it is retried
|
||||
on the next cycle rather than silently lost. Any other failure in the notify
|
||||
step is logged and never reaches the collection loop.
|
||||
|
||||
The dashboard's "🔔 Get alerts" button appears only when `NTFY_SERVER` is
|
||||
set; it reads `GET /api/notifications` and renders subscribe links
|
||||
(`ntfy://` deep links for the app, https links for the web UI).
|
||||
|
||||
## Deployment
|
||||
|
||||
On the monitor VPS, as root:
|
||||
|
||||
```bash
|
||||
cd /opt/thailand-water-monitor
|
||||
NTFY_DOMAIN=ntfy.buildfor.life bash scripts/install_ntfy.sh
|
||||
```
|
||||
|
||||
This installs the ntfy .deb, writes `/etc/ntfy/server.yml` (listen on the
|
||||
host's Tailscale address, port 2586; anonymous read, token-only write, 72 h
|
||||
message cache, signup/login/metrics off, tight visitor limits), enables the
|
||||
systemd unit,
|
||||
creates the `monitor` user with **write-only access to `ping-*`**, mints a
|
||||
token, and appends `NTFY_SERVER` (public URL for subscribers),
|
||||
`NTFY_PUBLISH_URL` (loopback, what the monitor POSTs to), `NTFY_TOPIC_PREFIX`
|
||||
and `NTFY_TOKEN` to `.env` if they are not there yet. Then:
|
||||
|
||||
```bash
|
||||
systemctl restart water-monitor
|
||||
journalctl -u water-monitor -n 20 | grep ntfy # "ntfy notifications: https://... topics ping-*"
|
||||
curl -s 'https://ntfy.buildfor.life/ping-status/json?poll=1' # anonymous read works
|
||||
```
|
||||
|
||||
The reverse proxy is a separate VPS on the same tailnet, so ntfy listens on
|
||||
the monitor host's Tailscale address and nothing is exposed on a public
|
||||
interface. On the Caddy machine:
|
||||
|
||||
```caddyfile
|
||||
ntfy.buildfor.life {
|
||||
reverse_proxy <monitor tailscale ip>:2586
|
||||
}
|
||||
```
|
||||
|
||||
Caddy proxies websockets and keeps long-poll connections open by default;
|
||||
subscribers hold one open. `behind-proxy: true` makes ntfy rate-limit on
|
||||
`X-Forwarded-For` rather than treating every subscriber as the proxy.
|
||||
|
||||
Publishing does not depend on the domain: `NTFY_PUBLISH_URL` points the
|
||||
monitor at the Tailscale address directly, so a DNS or proxy problem never
|
||||
holds back an alert. Test the pipeline before the domain is live with
|
||||
`curl -s 'http://<tailscale ip>:2586/ping-status/json?poll=1'`.
|
||||
|
||||
## Configuration
|
||||
|
||||
| Variable | Default | Meaning |
|
||||
|---|---|---|
|
||||
| `NTFY_SERVER` | *(empty = off)* | public base URL subscribers use; shown on the dashboard |
|
||||
| `NTFY_PUBLISH_URL` | = `NTFY_SERVER` | where the monitor POSTs; the local ntfy address (`http://<tailscale ip>:2586`), so publishing never waits on DNS/proxy |
|
||||
| `NTFY_TOPIC_PREFIX` | `ping` | first segment of every topic |
|
||||
| `NTFY_TOKEN` | *(empty)* | bearer token if the server requires auth to publish (it does, see above) |
|
||||
| `PUBLIC_URL` | `https://water.buildfor.life/` | click-through target in messages |
|
||||
|
||||
Tunables in `src/notify.py`: `CLEAR_MARGIN_M` (0.10), `OUTLOOK_ON` / `OUTLOOK_OFF`
|
||||
(0.50 / 0.25), stale feed threshold (3 h, argument to `evaluate`).
|
||||
|
||||
## Testing
|
||||
|
||||
`tests/test_notify.py` covers the state machine: quiet river sends nothing;
|
||||
crossing once, then silence while above, then all-clear; hysteresis on the way
|
||||
down; escalation to danger and back; basin digest grouping; outlook on/off;
|
||||
heuristic forecasts ignored; stale feed and recovery; state survives a restart
|
||||
through sqlite; a failed publish is retried next cycle.
|
||||
|
||||
To exercise the real path against a real ntfy locally: run `ntfy serve` (any
|
||||
platform, same binary), set `NTFY_SERVER`/`NTFY_TOKEN`, seed readings, and
|
||||
poll the topic JSON. `scripts/e2e_notify.py` does exactly that if you want a
|
||||
template.
|
||||
|
||||
## Why ntfy and not …
|
||||
|
||||
- **Matrix** (`src/alerting.py`, still there): needs a homeserver account per
|
||||
subscriber and a room invite; fine for a team, wrong for the public.
|
||||
- **Gotify**: also self-hosted and light, but Android-only client and one
|
||||
account per subscriber.
|
||||
- **Email / SMS**: deliverability work, cost per message, no priority
|
||||
semantics; ntfy can forward to email per subscription if someone wants it.
|
||||
- **Telegram / LINE bots**: platform lock-in and a bot token in the loop; can be
|
||||
added later as ntfy→webhook fan-out without touching the monitor.
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 122 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 522 KiB |
@@ -0,0 +1,723 @@
|
||||
[
|
||||
{
|
||||
"station": "P.1",
|
||||
"warn_thr": 3.7,
|
||||
"folds": [
|
||||
{
|
||||
"year": 2021,
|
||||
"n_train": 20024,
|
||||
"n_test": 4392,
|
||||
"events": [],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.07375926701460789,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 0.0,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_fc48": {
|
||||
"mae": 0.07332598842242062,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 0.0,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_quantile": {
|
||||
"mae": 0.07383022350644125,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 1.0850721383440065e-12,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_quantile_uw": {
|
||||
"mae": 0.06977345537342049,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 7.128994064266462e-16,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"year": 2022,
|
||||
"n_train": 28784,
|
||||
"n_test": 4392,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2022-10-02T19:00:00",
|
||||
"peak_ts": "2022-10-03T15:00:00",
|
||||
"peak_level": 4.65
|
||||
}
|
||||
],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.08452847354970178,
|
||||
"mae_above_2p5": 0.25082252888260664,
|
||||
"brier_warn": 0.004300908725927739,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2022-10-02T19:00:00",
|
||||
"lead_h": 5.0,
|
||||
"peak_level": 4.65,
|
||||
"peak_pred_24h_before": 3.8173954245046406
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_fc48": {
|
||||
"mae": 0.08369773912557228,
|
||||
"mae_above_2p5": 0.24702357745371217,
|
||||
"brier_warn": 0.004325741658698973,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2022-10-02T19:00:00",
|
||||
"lead_h": 5.0,
|
||||
"peak_level": 4.65,
|
||||
"peak_pred_24h_before": 3.8114190118860223
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_quantile": {
|
||||
"mae": 0.08230165237819607,
|
||||
"mae_above_2p5": 0.2599241552494541,
|
||||
"brier_warn": 0.004191550822623699,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2022-10-02T19:00:00",
|
||||
"lead_h": 3.0,
|
||||
"peak_level": 4.65,
|
||||
"peak_pred_24h_before": 3.693734826616603
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_quantile_uw": {
|
||||
"mae": 0.08181109208140971,
|
||||
"mae_above_2p5": 0.2639358812546371,
|
||||
"brier_warn": 0.004581181754314636,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2022-10-02T19:00:00",
|
||||
"lead_h": 2.0,
|
||||
"peak_level": 4.65,
|
||||
"peak_pred_24h_before": 3.620470606696475
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"year": 2023,
|
||||
"n_train": 37539,
|
||||
"n_test": 4392,
|
||||
"events": [],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.07696637416933236,
|
||||
"mae_above_2p5": 0.10643655855133666,
|
||||
"brier_warn": 1.919860722404625e-15,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_fc48": {
|
||||
"mae": 0.07708101918232377,
|
||||
"mae_above_2p5": 0.09974894450126857,
|
||||
"brier_warn": 1.7028444765622288e-15,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_quantile": {
|
||||
"mae": 0.06968496247786034,
|
||||
"mae_above_2p5": 0.10210094973854984,
|
||||
"brier_warn": 1.0987601008721297e-09,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_quantile_uw": {
|
||||
"mae": 0.06726603345661021,
|
||||
"mae_above_2p5": 0.09716644572204487,
|
||||
"brier_warn": 2.7085590803510675e-09,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"year": 2024,
|
||||
"n_train": 46323,
|
||||
"n_test": 4392,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2024-09-24T17:00:00",
|
||||
"peak_ts": "2024-09-26T02:00:00",
|
||||
"peak_level": 4.93
|
||||
},
|
||||
{
|
||||
"crossing": "2024-10-03T09:00:00",
|
||||
"peak_ts": "2024-10-05T12:00:00",
|
||||
"peak_level": 5.3
|
||||
}
|
||||
],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.0890019157543212,
|
||||
"mae_above_2p5": 0.2093245927883516,
|
||||
"brier_warn": 0.005826169840715695,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2024-09-24T17:00:00",
|
||||
"lead_h": 10.0,
|
||||
"peak_level": 4.93,
|
||||
"peak_pred_24h_before": 4.817519939833057
|
||||
},
|
||||
{
|
||||
"crossing": "2024-10-03T09:00:00",
|
||||
"lead_h": 21.0,
|
||||
"peak_level": 5.3,
|
||||
"peak_pred_24h_before": 5.546588884631041
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_fc48": {
|
||||
"mae": 0.08875916089292855,
|
||||
"mae_above_2p5": 0.20975114218621593,
|
||||
"brier_warn": 0.006061154593275248,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2024-09-24T17:00:00",
|
||||
"lead_h": 11.0,
|
||||
"peak_level": 4.93,
|
||||
"peak_pred_24h_before": 4.800924141216692
|
||||
},
|
||||
{
|
||||
"crossing": "2024-10-03T09:00:00",
|
||||
"lead_h": 72.0,
|
||||
"peak_level": 5.3,
|
||||
"peak_pred_24h_before": 5.577164984770105
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_quantile": {
|
||||
"mae": 0.08341835741803395,
|
||||
"mae_above_2p5": 0.18688839374651373,
|
||||
"brier_warn": 0.003188229521816099,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2024-09-24T17:00:00",
|
||||
"lead_h": 17.0,
|
||||
"peak_level": 4.93,
|
||||
"peak_pred_24h_before": 5.058029430632501
|
||||
},
|
||||
{
|
||||
"crossing": "2024-10-03T09:00:00",
|
||||
"lead_h": 21.0,
|
||||
"peak_level": 5.3,
|
||||
"peak_pred_24h_before": 5.3311787370709975
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_quantile_uw": {
|
||||
"mae": 0.08412336465267245,
|
||||
"mae_above_2p5": 0.19173218504592401,
|
||||
"brier_warn": 0.0034722638888286116,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2024-09-24T17:00:00",
|
||||
"lead_h": 15.0,
|
||||
"peak_level": 4.93,
|
||||
"peak_pred_24h_before": 5.0118284217314
|
||||
},
|
||||
{
|
||||
"crossing": "2024-10-03T09:00:00",
|
||||
"lead_h": 21.0,
|
||||
"peak_level": 5.3,
|
||||
"peak_pred_24h_before": 5.3520431553190155
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"year": 2025,
|
||||
"n_train": 55083,
|
||||
"n_test": 4392,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2025-09-27T18:00:00",
|
||||
"peak_ts": "2025-09-27T22:00:00",
|
||||
"peak_level": 3.93
|
||||
}
|
||||
],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.11202835461695825,
|
||||
"mae_above_2p5": 0.2456782496767171,
|
||||
"brier_warn": 0.005178356039745929,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2025-09-27T18:00:00",
|
||||
"lead_h": 2.0,
|
||||
"peak_level": 3.93,
|
||||
"peak_pred_24h_before": 3.23
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_fc48": {
|
||||
"mae": 0.11083068059655521,
|
||||
"mae_above_2p5": 0.23787013498709667,
|
||||
"brier_warn": 0.005228043825289021,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2025-09-27T18:00:00",
|
||||
"lead_h": 2.0,
|
||||
"peak_level": 3.93,
|
||||
"peak_pred_24h_before": 3.23
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_quantile": {
|
||||
"mae": 0.10372526043263834,
|
||||
"mae_above_2p5": 0.23846363852091013,
|
||||
"brier_warn": 0.005898259026876986,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2025-09-27T18:00:00",
|
||||
"lead_h": 1.0,
|
||||
"peak_level": 3.93,
|
||||
"peak_pred_24h_before": 3.23
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 1
|
||||
},
|
||||
"rise_rain_quantile_uw": {
|
||||
"mae": 0.10267267834487567,
|
||||
"mae_above_2p5": 0.2507951319537275,
|
||||
"brier_warn": 0.005020467408392599,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2025-09-27T18:00:00",
|
||||
"lead_h": 2.0,
|
||||
"peak_level": 3.93,
|
||||
"peak_pred_24h_before": 3.2417205711942434
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 1
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"station": "P.103",
|
||||
"warn_thr": 5.95,
|
||||
"folds": [
|
||||
{
|
||||
"year": 2021,
|
||||
"n_train": 20009,
|
||||
"n_test": 4392,
|
||||
"events": [],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.14438683486790602,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 0.0,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_fc48": {
|
||||
"mae": 0.14305613024043953,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 0.0,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_quantile": {
|
||||
"mae": 0.13512418754716052,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 6.937198832251013e-10,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_quantile_uw": {
|
||||
"mae": 0.10270057685061172,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 6.565945930999852e-14,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"year": 2022,
|
||||
"n_train": 28769,
|
||||
"n_test": 4392,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2022-08-14T04:00:00",
|
||||
"peak_ts": "2022-08-14T08:00:00",
|
||||
"peak_level": 6.09
|
||||
},
|
||||
{
|
||||
"crossing": "2022-10-02T16:00:00",
|
||||
"peak_ts": "2022-10-03T16:00:00",
|
||||
"peak_level": 7.54
|
||||
}
|
||||
],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.14392334606606189,
|
||||
"mae_above_2p5": 0.41075382386412596,
|
||||
"brier_warn": 0.00764679988213082,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2022-08-14T04:00:00",
|
||||
"lead_h": 6.0,
|
||||
"peak_level": 6.09,
|
||||
"peak_pred_24h_before": 4.825270553204425
|
||||
},
|
||||
{
|
||||
"crossing": "2022-10-02T16:00:00",
|
||||
"lead_h": 9.0,
|
||||
"peak_level": 7.54,
|
||||
"peak_pred_24h_before": 7.194064117976157
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_fc48": {
|
||||
"mae": 0.14284722696431765,
|
||||
"mae_above_2p5": 0.39401132538096667,
|
||||
"brier_warn": 0.007427375799450148,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2022-08-14T04:00:00",
|
||||
"lead_h": 6.0,
|
||||
"peak_level": 6.09,
|
||||
"peak_pred_24h_before": 4.845896993132048
|
||||
},
|
||||
{
|
||||
"crossing": "2022-10-02T16:00:00",
|
||||
"lead_h": 9.0,
|
||||
"peak_level": 7.54,
|
||||
"peak_pred_24h_before": 7.194661123502819
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_quantile": {
|
||||
"mae": 0.1458954690776336,
|
||||
"mae_above_2p5": 0.4674051188369517,
|
||||
"brier_warn": 0.00899991317044724,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2022-08-14T04:00:00",
|
||||
"lead_h": 1.0,
|
||||
"peak_level": 6.09,
|
||||
"peak_pred_24h_before": 4.82714042795344
|
||||
},
|
||||
{
|
||||
"crossing": "2022-10-02T16:00:00",
|
||||
"lead_h": 5.0,
|
||||
"peak_level": 7.54,
|
||||
"peak_pred_24h_before": 6.59871451008115
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_quantile_uw": {
|
||||
"mae": 0.13203958422483053,
|
||||
"mae_above_2p5": 0.4902773906613983,
|
||||
"brier_warn": 0.008514527559601331,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2022-08-14T04:00:00",
|
||||
"lead_h": 4.0,
|
||||
"peak_level": 6.09,
|
||||
"peak_pred_24h_before": 4.895369771408423
|
||||
},
|
||||
{
|
||||
"crossing": "2022-10-02T16:00:00",
|
||||
"lead_h": 3.0,
|
||||
"peak_level": 7.54,
|
||||
"peak_pred_24h_before": 6.294082735853337
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"year": 2023,
|
||||
"n_train": 37524,
|
||||
"n_test": 4392,
|
||||
"events": [],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.16195301512514512,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 3.0208441147560167e-07,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_fc48": {
|
||||
"mae": 0.16334224973870387,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 1.1626187140381066e-08,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_quantile": {
|
||||
"mae": 0.14755024879522577,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 3.850104714388072e-05,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_quantile_uw": {
|
||||
"mae": 0.10589805327026759,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 1.8896757611081001e-07,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"year": 2024,
|
||||
"n_train": 46308,
|
||||
"n_test": 4058,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2024-09-24T10:00:00",
|
||||
"peak_ts": "2024-09-26T00:00:00",
|
||||
"peak_level": 8.27
|
||||
},
|
||||
{
|
||||
"crossing": "2024-09-30T03:00:00",
|
||||
"peak_ts": "2024-09-30T06:00:00",
|
||||
"peak_level": 5.99
|
||||
},
|
||||
{
|
||||
"crossing": "2024-10-03T06:00:00",
|
||||
"peak_ts": "2024-10-05T07:00:00",
|
||||
"peak_level": 9.93
|
||||
}
|
||||
],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.13901842325128816,
|
||||
"mae_above_2p5": 0.2887416310966684,
|
||||
"brier_warn": 0.0072040857753137046,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2024-09-24T10:00:00",
|
||||
"lead_h": 19.0,
|
||||
"peak_level": 8.27,
|
||||
"peak_pred_24h_before": 8.212734363860193
|
||||
},
|
||||
{
|
||||
"crossing": "2024-09-30T03:00:00",
|
||||
"lead_h": 9.0,
|
||||
"peak_level": 5.99,
|
||||
"peak_pred_24h_before": 5.47565489914091
|
||||
},
|
||||
{
|
||||
"crossing": "2024-10-03T06:00:00",
|
||||
"lead_h": 55.0,
|
||||
"peak_level": 9.93,
|
||||
"peak_pred_24h_before": 8.780278464915938
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_fc48": {
|
||||
"mae": 0.13850733053801131,
|
||||
"mae_above_2p5": 0.29817392926900865,
|
||||
"brier_warn": 0.007928846574280278,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2024-09-24T10:00:00",
|
||||
"lead_h": 19.0,
|
||||
"peak_level": 8.27,
|
||||
"peak_pred_24h_before": 8.166020251020889
|
||||
},
|
||||
{
|
||||
"crossing": "2024-09-30T03:00:00",
|
||||
"lead_h": 10.0,
|
||||
"peak_level": 5.99,
|
||||
"peak_pred_24h_before": 5.524584037259288
|
||||
},
|
||||
{
|
||||
"crossing": "2024-10-03T06:00:00",
|
||||
"lead_h": 69.0,
|
||||
"peak_level": 9.93,
|
||||
"peak_pred_24h_before": 8.595120917488185
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_quantile": {
|
||||
"mae": 0.12640546558686208,
|
||||
"mae_above_2p5": 0.27944115421093924,
|
||||
"brier_warn": 0.007730268539879654,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2024-09-24T10:00:00",
|
||||
"lead_h": 20.0,
|
||||
"peak_level": 8.27,
|
||||
"peak_pred_24h_before": 8.336487732683672
|
||||
},
|
||||
{
|
||||
"crossing": "2024-09-30T03:00:00",
|
||||
"lead_h": 4.0,
|
||||
"peak_level": 5.99,
|
||||
"peak_pred_24h_before": 5.45284915024346
|
||||
},
|
||||
{
|
||||
"crossing": "2024-10-03T06:00:00",
|
||||
"lead_h": 69.0,
|
||||
"peak_level": 9.93,
|
||||
"peak_pred_24h_before": 8.575915226697406
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_quantile_uw": {
|
||||
"mae": 0.12480975852168202,
|
||||
"mae_above_2p5": 0.2857575557415695,
|
||||
"brier_warn": 0.005894928998647136,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2024-09-24T10:00:00",
|
||||
"lead_h": 21.0,
|
||||
"peak_level": 8.27,
|
||||
"peak_pred_24h_before": 8.444720326882825
|
||||
},
|
||||
{
|
||||
"crossing": "2024-09-30T03:00:00",
|
||||
"lead_h": 9.0,
|
||||
"peak_level": 5.99,
|
||||
"peak_pred_24h_before": 5.42
|
||||
},
|
||||
{
|
||||
"crossing": "2024-10-03T06:00:00",
|
||||
"lead_h": 32.0,
|
||||
"peak_level": 9.93,
|
||||
"peak_pred_24h_before": 8.781001847167515
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"year": 2025,
|
||||
"n_train": 54577,
|
||||
"n_test": 4392,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2025-09-26T06:00:00",
|
||||
"peak_ts": "2025-09-27T21:00:00",
|
||||
"peak_level": 6.64
|
||||
},
|
||||
{
|
||||
"crossing": "2025-10-03T06:00:00",
|
||||
"peak_ts": "2025-10-03T12:00:00",
|
||||
"peak_level": 6.14
|
||||
}
|
||||
],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.17206685418009837,
|
||||
"mae_above_2p5": 0.3840520085986099,
|
||||
"brier_warn": 0.015824852891785323,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2025-09-26T06:00:00",
|
||||
"lead_h": 6.0,
|
||||
"peak_level": 6.64,
|
||||
"peak_pred_24h_before": 5.73043665401637
|
||||
},
|
||||
{
|
||||
"crossing": "2025-10-03T06:00:00",
|
||||
"lead_h": 8.0,
|
||||
"peak_level": 6.14,
|
||||
"peak_pred_24h_before": 5.609919760117381
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 2
|
||||
},
|
||||
"rise_rain_fc48": {
|
||||
"mae": 0.1722274451362234,
|
||||
"mae_above_2p5": 0.3872216974630654,
|
||||
"brier_warn": 0.016245727130063177,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2025-09-26T06:00:00",
|
||||
"lead_h": 4.0,
|
||||
"peak_level": 6.64,
|
||||
"peak_pred_24h_before": 5.7312263707793685
|
||||
},
|
||||
{
|
||||
"crossing": "2025-10-03T06:00:00",
|
||||
"lead_h": 8.0,
|
||||
"peak_level": 6.14,
|
||||
"peak_pred_24h_before": 5.685511824758637
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 2
|
||||
},
|
||||
"rise_rain_quantile": {
|
||||
"mae": 0.15912275848686555,
|
||||
"mae_above_2p5": 0.3845695612674703,
|
||||
"brier_warn": 0.014797606329811499,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2025-09-26T06:00:00",
|
||||
"lead_h": 11.0,
|
||||
"peak_level": 6.64,
|
||||
"peak_pred_24h_before": 5.73
|
||||
},
|
||||
{
|
||||
"crossing": "2025-10-03T06:00:00",
|
||||
"lead_h": 10.0,
|
||||
"peak_level": 6.14,
|
||||
"peak_pred_24h_before": 5.58133012298031
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 2
|
||||
},
|
||||
"rise_rain_quantile_uw": {
|
||||
"mae": 0.15385355845103685,
|
||||
"mae_above_2p5": 0.41314645854725585,
|
||||
"brier_warn": 0.016528116336109958,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2025-09-26T06:00:00",
|
||||
"lead_h": 9.0,
|
||||
"peak_level": 6.64,
|
||||
"peak_pred_24h_before": 5.741254234340573
|
||||
},
|
||||
{
|
||||
"crossing": "2025-10-03T06:00:00",
|
||||
"lead_h": 8.0,
|
||||
"peak_level": 6.14,
|
||||
"peak_pred_24h_before": 5.418105405306207
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 2
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
@@ -0,0 +1,439 @@
|
||||
[
|
||||
{
|
||||
"station": "P.1",
|
||||
"warn_thr": 3.7,
|
||||
"folds": [
|
||||
{
|
||||
"year": 2021,
|
||||
"n_train": 20024,
|
||||
"n_test": 4392,
|
||||
"events": [],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.07375926701460789,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 0.0,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_qsigma": {
|
||||
"mae": 0.07375926701460789,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 7.852802408474157e-14,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"year": 2022,
|
||||
"n_train": 28784,
|
||||
"n_test": 4392,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2022-10-02T19:00:00",
|
||||
"peak_ts": "2022-10-03T15:00:00",
|
||||
"peak_level": 4.65
|
||||
}
|
||||
],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.08452847354970178,
|
||||
"mae_above_2p5": 0.25082252888260664,
|
||||
"brier_warn": 0.004300908725927739,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2022-10-02T19:00:00",
|
||||
"lead_h": 5.0,
|
||||
"peak_level": 4.65,
|
||||
"peak_pred_24h_before": 3.8173954245046406
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_qsigma": {
|
||||
"mae": 0.08452847354970178,
|
||||
"mae_above_2p5": 0.25082252888260664,
|
||||
"brier_warn": 0.0039815091186836665,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2022-10-02T19:00:00",
|
||||
"lead_h": 5.0,
|
||||
"peak_level": 4.65,
|
||||
"peak_pred_24h_before": 3.8173954245046406
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"year": 2023,
|
||||
"n_train": 37539,
|
||||
"n_test": 4392,
|
||||
"events": [],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.07696637416933236,
|
||||
"mae_above_2p5": 0.10643655855133666,
|
||||
"brier_warn": 1.919860722404625e-15,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_qsigma": {
|
||||
"mae": 0.07696637416933236,
|
||||
"mae_above_2p5": 0.10643655855133666,
|
||||
"brier_warn": 4.0844243581898366e-08,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"year": 2024,
|
||||
"n_train": 46323,
|
||||
"n_test": 4392,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2024-09-24T17:00:00",
|
||||
"peak_ts": "2024-09-26T02:00:00",
|
||||
"peak_level": 4.93
|
||||
},
|
||||
{
|
||||
"crossing": "2024-10-03T09:00:00",
|
||||
"peak_ts": "2024-10-05T12:00:00",
|
||||
"peak_level": 5.3
|
||||
}
|
||||
],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.0890019157543212,
|
||||
"mae_above_2p5": 0.2093245927883516,
|
||||
"brier_warn": 0.005826169840715695,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2024-09-24T17:00:00",
|
||||
"lead_h": 10.0,
|
||||
"peak_level": 4.93,
|
||||
"peak_pred_24h_before": 4.817519939833057
|
||||
},
|
||||
{
|
||||
"crossing": "2024-10-03T09:00:00",
|
||||
"lead_h": 21.0,
|
||||
"peak_level": 5.3,
|
||||
"peak_pred_24h_before": 5.546588884631041
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_qsigma": {
|
||||
"mae": 0.0890019157543212,
|
||||
"mae_above_2p5": 0.2093245927883516,
|
||||
"brier_warn": 0.005475787026695418,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2024-09-24T17:00:00",
|
||||
"lead_h": 10.0,
|
||||
"peak_level": 4.93,
|
||||
"peak_pred_24h_before": 4.817519939833057
|
||||
},
|
||||
{
|
||||
"crossing": "2024-10-03T09:00:00",
|
||||
"lead_h": 21.0,
|
||||
"peak_level": 5.3,
|
||||
"peak_pred_24h_before": 5.546588884631041
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"year": 2025,
|
||||
"n_train": 55083,
|
||||
"n_test": 4392,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2025-09-27T18:00:00",
|
||||
"peak_ts": "2025-09-27T22:00:00",
|
||||
"peak_level": 3.93
|
||||
}
|
||||
],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.11202835461695825,
|
||||
"mae_above_2p5": 0.2456782496767171,
|
||||
"brier_warn": 0.005178356039745929,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2025-09-27T18:00:00",
|
||||
"lead_h": 2.0,
|
||||
"peak_level": 3.93,
|
||||
"peak_pred_24h_before": 3.23
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_qsigma": {
|
||||
"mae": 0.11202835461695825,
|
||||
"mae_above_2p5": 0.2456782496767171,
|
||||
"brier_warn": 0.00491346243876589,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2025-09-27T18:00:00",
|
||||
"lead_h": 2.0,
|
||||
"peak_level": 3.93,
|
||||
"peak_pred_24h_before": 3.23
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"station": "P.103",
|
||||
"warn_thr": 5.95,
|
||||
"folds": [
|
||||
{
|
||||
"year": 2021,
|
||||
"n_train": 20009,
|
||||
"n_test": 4392,
|
||||
"events": [],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.14438683486790602,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 0.0,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_qsigma": {
|
||||
"mae": 0.14438683486790602,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 3.5349670949872053e-13,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"year": 2022,
|
||||
"n_train": 28769,
|
||||
"n_test": 4392,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2022-08-14T04:00:00",
|
||||
"peak_ts": "2022-08-14T08:00:00",
|
||||
"peak_level": 6.09
|
||||
},
|
||||
{
|
||||
"crossing": "2022-10-02T16:00:00",
|
||||
"peak_ts": "2022-10-03T16:00:00",
|
||||
"peak_level": 7.54
|
||||
}
|
||||
],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.14392334606606189,
|
||||
"mae_above_2p5": 0.41075382386412596,
|
||||
"brier_warn": 0.00764679988213082,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2022-08-14T04:00:00",
|
||||
"lead_h": 6.0,
|
||||
"peak_level": 6.09,
|
||||
"peak_pred_24h_before": 4.825270553204425
|
||||
},
|
||||
{
|
||||
"crossing": "2022-10-02T16:00:00",
|
||||
"lead_h": 9.0,
|
||||
"peak_level": 7.54,
|
||||
"peak_pred_24h_before": 7.194064117976157
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_qsigma": {
|
||||
"mae": 0.14392334606606189,
|
||||
"mae_above_2p5": 0.41075382386412596,
|
||||
"brier_warn": 0.006975493312169236,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2022-08-14T04:00:00",
|
||||
"lead_h": 6.0,
|
||||
"peak_level": 6.09,
|
||||
"peak_pred_24h_before": 4.825270553204425
|
||||
},
|
||||
{
|
||||
"crossing": "2022-10-02T16:00:00",
|
||||
"lead_h": 9.0,
|
||||
"peak_level": 7.54,
|
||||
"peak_pred_24h_before": 7.194064117976157
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"year": 2023,
|
||||
"n_train": 37524,
|
||||
"n_test": 4392,
|
||||
"events": [],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.16195301512514512,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 3.0208441147560167e-07,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_qsigma": {
|
||||
"mae": 0.16195301512514512,
|
||||
"mae_above_2p5": null,
|
||||
"brier_warn": 3.2176039819636275e-05,
|
||||
"events": [],
|
||||
"false_alarm_episodes": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"year": 2024,
|
||||
"n_train": 46308,
|
||||
"n_test": 4058,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2024-09-24T10:00:00",
|
||||
"peak_ts": "2024-09-26T00:00:00",
|
||||
"peak_level": 8.27
|
||||
},
|
||||
{
|
||||
"crossing": "2024-09-30T03:00:00",
|
||||
"peak_ts": "2024-09-30T06:00:00",
|
||||
"peak_level": 5.99
|
||||
},
|
||||
{
|
||||
"crossing": "2024-10-03T06:00:00",
|
||||
"peak_ts": "2024-10-05T07:00:00",
|
||||
"peak_level": 9.93
|
||||
}
|
||||
],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.13901842325128816,
|
||||
"mae_above_2p5": 0.2887416310966684,
|
||||
"brier_warn": 0.0072040857753137046,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2024-09-24T10:00:00",
|
||||
"lead_h": 19.0,
|
||||
"peak_level": 8.27,
|
||||
"peak_pred_24h_before": 8.212734363860193
|
||||
},
|
||||
{
|
||||
"crossing": "2024-09-30T03:00:00",
|
||||
"lead_h": 9.0,
|
||||
"peak_level": 5.99,
|
||||
"peak_pred_24h_before": 5.47565489914091
|
||||
},
|
||||
{
|
||||
"crossing": "2024-10-03T06:00:00",
|
||||
"lead_h": 55.0,
|
||||
"peak_level": 9.93,
|
||||
"peak_pred_24h_before": 8.780278464915938
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
},
|
||||
"rise_rain_qsigma": {
|
||||
"mae": 0.13901842325128816,
|
||||
"mae_above_2p5": 0.2887416310966684,
|
||||
"brier_warn": 0.006910847607098417,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2024-09-24T10:00:00",
|
||||
"lead_h": 19.0,
|
||||
"peak_level": 8.27,
|
||||
"peak_pred_24h_before": 8.212734363860193
|
||||
},
|
||||
{
|
||||
"crossing": "2024-09-30T03:00:00",
|
||||
"lead_h": 9.0,
|
||||
"peak_level": 5.99,
|
||||
"peak_pred_24h_before": 5.47565489914091
|
||||
},
|
||||
{
|
||||
"crossing": "2024-10-03T06:00:00",
|
||||
"lead_h": 55.0,
|
||||
"peak_level": 9.93,
|
||||
"peak_pred_24h_before": 8.780278464915938
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 0
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"year": 2025,
|
||||
"n_train": 54577,
|
||||
"n_test": 4392,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2025-09-26T06:00:00",
|
||||
"peak_ts": "2025-09-27T21:00:00",
|
||||
"peak_level": 6.64
|
||||
},
|
||||
{
|
||||
"crossing": "2025-10-03T06:00:00",
|
||||
"peak_ts": "2025-10-03T12:00:00",
|
||||
"peak_level": 6.14
|
||||
}
|
||||
],
|
||||
"variants": {
|
||||
"rise_rain": {
|
||||
"mae": 0.17206685418009837,
|
||||
"mae_above_2p5": 0.3840520085986099,
|
||||
"brier_warn": 0.015824852891785323,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2025-09-26T06:00:00",
|
||||
"lead_h": 6.0,
|
||||
"peak_level": 6.64,
|
||||
"peak_pred_24h_before": 5.73043665401637
|
||||
},
|
||||
{
|
||||
"crossing": "2025-10-03T06:00:00",
|
||||
"lead_h": 8.0,
|
||||
"peak_level": 6.14,
|
||||
"peak_pred_24h_before": 5.609919760117381
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 2
|
||||
},
|
||||
"rise_rain_qsigma": {
|
||||
"mae": 0.17206685418009837,
|
||||
"mae_above_2p5": 0.3840520085986099,
|
||||
"brier_warn": 0.015889933586185904,
|
||||
"events": [
|
||||
{
|
||||
"crossing": "2025-09-26T06:00:00",
|
||||
"lead_h": 6.0,
|
||||
"peak_level": 6.64,
|
||||
"peak_pred_24h_before": 5.73043665401637
|
||||
},
|
||||
{
|
||||
"crossing": "2025-10-03T06:00:00",
|
||||
"lead_h": 8.0,
|
||||
"peak_level": 6.14,
|
||||
"peak_pred_24h_before": 5.609919760117381
|
||||
}
|
||||
],
|
||||
"false_alarm_episodes": 2
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
+26
-13
@@ -34,23 +34,23 @@ classifiers = [
|
||||
"Environment :: Web Environment",
|
||||
"Framework :: FastAPI"
|
||||
]
|
||||
requires-python = ">=3.11"
|
||||
requires-python = ">=3.11,<3.12"
|
||||
dependencies = [
|
||||
# Core dependencies
|
||||
"requests==2.31.0",
|
||||
"requests==2.34.2",
|
||||
"schedule==1.2.0",
|
||||
"pandas==2.0.3",
|
||||
"numpy>=1.24,<2",
|
||||
# Flood forecasting (ML)
|
||||
"scikit-learn==1.9.0",
|
||||
# Web API framework
|
||||
"fastapi==0.104.1",
|
||||
"uvicorn[standard]==0.24.0",
|
||||
"pydantic==2.5.0",
|
||||
"fastapi==0.141.1",
|
||||
"uvicorn[standard]==0.52.4",
|
||||
"pydantic==2.13.5",
|
||||
# Database adapters
|
||||
"sqlalchemy==2.0.23",
|
||||
"influxdb==5.3.1",
|
||||
"pymysql==1.1.0",
|
||||
"pymysql==1.2.0",
|
||||
"psycopg2-binary==2.9.9",
|
||||
# Monitoring and metrics
|
||||
"psutil==5.9.6"
|
||||
@@ -59,11 +59,11 @@ dependencies = [
|
||||
[project.optional-dependencies]
|
||||
dev = [
|
||||
# Testing
|
||||
"pytest==7.4.3",
|
||||
"pytest==9.1.1",
|
||||
"pytest-cov==4.1.0",
|
||||
"pytest-asyncio==0.21.1",
|
||||
# Code formatting and linting
|
||||
"black==23.11.0",
|
||||
"black==26.5.1",
|
||||
"flake8==6.1.0",
|
||||
"isort==5.12.0",
|
||||
"mypy==1.7.1",
|
||||
@@ -73,7 +73,7 @@ dev = [
|
||||
"ipython==8.17.2",
|
||||
"jupyter==1.0.0",
|
||||
# Type stubs
|
||||
"types-requests==2.31.0.10",
|
||||
"types-requests==2.33.0.20260906",
|
||||
"types-python-dateutil==2.8.19.14"
|
||||
]
|
||||
docs = [
|
||||
@@ -83,7 +83,7 @@ docs = [
|
||||
]
|
||||
all = [
|
||||
"influxdb==5.3.1",
|
||||
"pymysql==1.1.0",
|
||||
"pymysql==1.2.0",
|
||||
"psycopg2-binary==2.9.9"
|
||||
]
|
||||
|
||||
@@ -100,11 +100,11 @@ Documentation = "https://git.b4l.co.th/B4L/Northern-Thailand-Ping-River-Monitor/
|
||||
[dependency-groups]
|
||||
dev = [
|
||||
# Testing
|
||||
"pytest==7.4.3",
|
||||
"pytest==9.1.1",
|
||||
"pytest-cov==4.1.0",
|
||||
"pytest-asyncio==0.21.1",
|
||||
# Code formatting and linting
|
||||
"black==23.11.0",
|
||||
"black==26.5.1",
|
||||
"flake8==6.1.0",
|
||||
"isort==5.12.0",
|
||||
"mypy==1.7.1",
|
||||
@@ -114,7 +114,7 @@ dev = [
|
||||
"ipython==8.17.2",
|
||||
"jupyter==1.0.0",
|
||||
# Type stubs
|
||||
"types-requests==2.31.0.10",
|
||||
"types-requests==2.33.0.20260906",
|
||||
"types-python-dateutil==2.8.19.14",
|
||||
# Documentation
|
||||
"sphinx==7.2.6",
|
||||
@@ -128,3 +128,16 @@ where = ["src"]
|
||||
|
||||
[tool.setuptools.package-dir]
|
||||
"" = "src"
|
||||
|
||||
# One formatting contract for CI, pre-commit and editors. Black's default 88
|
||||
# columns; isort in black-compatible mode. Run `make format` before committing.
|
||||
[tool.black]
|
||||
line-length = 88
|
||||
target-version = ["py311"]
|
||||
extend-exclude = '/(\.venv|venv|models|\.claude-flow|\.swarm)/'
|
||||
|
||||
[tool.isort]
|
||||
profile = "black"
|
||||
line_length = 88
|
||||
known_first_party = ["src"]
|
||||
skip_gitignore = true
|
||||
|
||||
@@ -2,12 +2,12 @@
|
||||
-r requirements.txt
|
||||
|
||||
# Testing
|
||||
pytest==7.4.3
|
||||
pytest==9.1.1
|
||||
pytest-cov==4.1.0
|
||||
pytest-asyncio==0.21.1
|
||||
|
||||
# Code formatting and linting
|
||||
black==23.11.0
|
||||
black==26.5.1
|
||||
flake8==6.1.0
|
||||
isort==5.12.0
|
||||
mypy==1.7.1
|
||||
@@ -25,5 +25,5 @@ ipython==8.17.2
|
||||
jupyter==1.0.0
|
||||
|
||||
# Type stubs
|
||||
types-requests==2.31.0.10
|
||||
types-requests==2.33.0.20260906
|
||||
types-python-dateutil==2.8.19.14
|
||||
+7
-7
@@ -1,5 +1,5 @@
|
||||
# Core dependencies
|
||||
requests==2.31.0
|
||||
requests==2.34.2
|
||||
schedule==1.2.0
|
||||
pandas==2.0.3
|
||||
numpy>=1.24,<2 # pandas 2.0.3 wheels are ABI-incompatible with numpy 2.x
|
||||
@@ -8,23 +8,23 @@ numpy>=1.24,<2 # pandas 2.0.3 wheels are ABI-incompatible with numpy 2.x
|
||||
scikit-learn==1.9.0
|
||||
|
||||
# Web API framework
|
||||
fastapi==0.104.1
|
||||
uvicorn[standard]==0.24.0
|
||||
pydantic==2.5.0
|
||||
fastapi==0.141.1
|
||||
uvicorn[standard]==0.52.4
|
||||
pydantic==2.13.5
|
||||
|
||||
# Database adapters
|
||||
sqlalchemy==2.0.23
|
||||
influxdb==5.3.1
|
||||
pymysql==1.1.0
|
||||
pymysql==1.2.0
|
||||
psycopg2-binary==2.9.9
|
||||
|
||||
# Monitoring and metrics
|
||||
psutil==5.9.6
|
||||
|
||||
# Development dependencies (optional)
|
||||
pytest==7.4.3
|
||||
pytest==9.1.1
|
||||
pytest-cov==4.1.0
|
||||
black==23.11.0
|
||||
black==26.5.1
|
||||
flake8==6.1.0
|
||||
mypy==1.7.1
|
||||
pre-commit==3.5.0
|
||||
|
||||
@@ -0,0 +1,58 @@
|
||||
"""Serve the working-copy dashboard locally with API calls proxied to the
|
||||
live server, so browser-side changes can be checked against real data
|
||||
before deploy. Usage: python scripts/dev_proxy.py [port]"""
|
||||
|
||||
import http.server
|
||||
import os
|
||||
import sys
|
||||
import urllib.request
|
||||
from pathlib import Path
|
||||
|
||||
UPSTREAM = "https://water.buildfor.life"
|
||||
STATIC = Path(__file__).resolve().parents[1] / "src" / "static"
|
||||
|
||||
|
||||
class Handler(http.server.BaseHTTPRequestHandler):
|
||||
def do_GET(self):
|
||||
if self.path == "/" or self.path.startswith("/?"):
|
||||
body = (STATIC / "dashboard.html").read_bytes()
|
||||
self._send(200, "text/html; charset=utf-8", body)
|
||||
return
|
||||
# Local overrides for endpoints not yet deployed: DEV_PROXY_LOCAL=/api/x=file.json,...
|
||||
for pair in filter(None, os.environ.get("DEV_PROXY_LOCAL", "").split(",")):
|
||||
prefix, file = pair.split("=", 1)
|
||||
if self.path.split("?")[0] == prefix:
|
||||
self._send(200, "application/json", Path(file).read_bytes())
|
||||
return
|
||||
if self.path.startswith("/static/"):
|
||||
f = STATIC / self.path[len("/static/"):].split("?")[0]
|
||||
if f.is_file():
|
||||
ctype = "application/json" if f.suffix in (".json", ".geojson") else "application/octet-stream"
|
||||
self._send(200, ctype, f.read_bytes())
|
||||
return
|
||||
try:
|
||||
req = urllib.request.Request(
|
||||
UPSTREAM + self.path,
|
||||
headers={"User-Agent": "Mozilla/5.0 (dev_proxy; +https://buildfor.life)", "Accept": "application/json"},
|
||||
)
|
||||
with urllib.request.urlopen(req, timeout=60) as r:
|
||||
self._send(r.status, r.headers.get("Content-Type", "application/json"), r.read())
|
||||
except urllib.error.HTTPError as e:
|
||||
self._send(e.code, "application/json", e.read())
|
||||
|
||||
def _send(self, code, ctype, body):
|
||||
self.send_response(code)
|
||||
self.send_header("Content-Type", ctype)
|
||||
self.send_header("Content-Length", str(len(body)))
|
||||
self.send_header("Cache-Control", "no-store")
|
||||
self.end_headers()
|
||||
self.wfile.write(body)
|
||||
|
||||
def log_message(self, *a):
|
||||
pass
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
port = int(sys.argv[1]) if len(sys.argv) > 1 else 8765
|
||||
print(f"http://localhost:{port}/ (API -> {UPSTREAM})")
|
||||
http.server.ThreadingHTTPServer(("127.0.0.1", port), Handler).serve_forever()
|
||||
@@ -0,0 +1,132 @@
|
||||
"""Drive the production notify path in-process: startup init -> seeded readings
|
||||
-> forecast cache -> _notify_transitions -> sqlite state -> real ntfy."""
|
||||
|
||||
import asyncio
|
||||
import datetime
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
|
||||
import requests
|
||||
|
||||
os.environ.update(
|
||||
DB_TYPE="sqlite",
|
||||
WATER_DB_PATH=os.path.join(os.environ["LOCALAPPDATA"], "Temp", "smoke3.db"),
|
||||
NTFY_SERVER="http://127.0.0.1:2586",
|
||||
NTFY_TOKEN=os.environ.get("NTFY_TOKEN", ""),
|
||||
NTFY_TOPIC_PREFIX="ping",
|
||||
)
|
||||
for f in ("smoke3.db",):
|
||||
p = os.path.join(os.environ["LOCALAPPDATA"], "Temp", f)
|
||||
if os.path.exists(p):
|
||||
os.remove(p)
|
||||
|
||||
from src import web_api # noqa: E402
|
||||
from src.config import Config # noqa: E402
|
||||
|
||||
assert Config.NTFY_SERVER
|
||||
|
||||
|
||||
async def main():
|
||||
# what the lifespan does at startup, minus the scheduler
|
||||
from src import notify as notify_mod
|
||||
from src.forecast_history import ForecastHistoryStore
|
||||
from src.water_scraper_v3 import EnhancedWaterMonitorScraper
|
||||
|
||||
db_config = Config.get_database_config()
|
||||
web_api.app_state["scraper"] = EnhancedWaterMonitorScraper(db_config)
|
||||
store = ForecastHistoryStore(db_config["connection_string"], db_config["type"])
|
||||
store.connect()
|
||||
web_api.app_state["forecast_store"] = store
|
||||
state = notify_mod.NotificationState(store.engine, store.db_type)
|
||||
pub = notify_mod.NtfyPublisher(
|
||||
Config.NTFY_SERVER, prefix=Config.NTFY_TOPIC_PREFIX, token=Config.NTFY_TOKEN
|
||||
)
|
||||
web_api.app_state["notify"] = (pub, state)
|
||||
|
||||
scraper = web_api.app_state["scraper"]
|
||||
now = datetime.datetime.now().replace(minute=0, second=0, microsecond=0)
|
||||
|
||||
def seed(level_p1, level_p103, ts):
|
||||
rows = [
|
||||
{
|
||||
"station_code": "P.1",
|
||||
"station_id": 1,
|
||||
"timestamp": ts,
|
||||
"water_level": level_p1,
|
||||
"discharge": 400.0,
|
||||
"station_name_en": "Nawarat Bridge",
|
||||
"station_name_th": "สะพานนวรัฐ",
|
||||
"discharge_percent": 30.0,
|
||||
"status": "active",
|
||||
},
|
||||
{
|
||||
"station_code": "P.103",
|
||||
"station_id": 2,
|
||||
"timestamp": ts,
|
||||
"water_level": level_p103,
|
||||
"discharge": 300.0,
|
||||
"station_name_en": "Ring Road 3",
|
||||
"station_name_th": "วงแหวน 3",
|
||||
"discharge_percent": 20.0,
|
||||
"status": "active",
|
||||
},
|
||||
]
|
||||
scraper.db_adapter.save_measurements(rows)
|
||||
|
||||
def forecast(p):
|
||||
with web_api.FORECAST_CACHE_LOCK:
|
||||
web_api.FORECAST_CACHE["all"] = (
|
||||
0,
|
||||
[
|
||||
{
|
||||
"station_code": "P.1",
|
||||
"horizon_hours": 24,
|
||||
"p_warning": p,
|
||||
"predicted_max_level": 3.9,
|
||||
"source": "model",
|
||||
}
|
||||
],
|
||||
)
|
||||
|
||||
def poll(topic):
|
||||
out = []
|
||||
for line in (
|
||||
requests.get(f"{Config.NTFY_SERVER}/{topic}/json?poll=1", timeout=5)
|
||||
.text.strip()
|
||||
.splitlines()
|
||||
):
|
||||
m = json.loads(line)
|
||||
if m.get("event") == "message":
|
||||
out.append(m.get("title") or m.get("message", "")[:40])
|
||||
return out
|
||||
|
||||
# cycle 1: quiet
|
||||
seed(1.6, 3.2, now - datetime.timedelta(hours=2))
|
||||
forecast(0.02)
|
||||
await web_api._notify_transitions()
|
||||
# cycle 2: P.1 crosses warning, model outlook on
|
||||
seed(3.75, 3.3, now - datetime.timedelta(hours=1))
|
||||
forecast(0.7)
|
||||
await web_api._notify_transitions()
|
||||
# cycle 3: same state -> silence
|
||||
seed(3.80, 3.3, now)
|
||||
forecast(0.65)
|
||||
await web_api._notify_transitions()
|
||||
|
||||
print("ping-p1-warning:", poll("ping-p1-warning"))
|
||||
print("ping-warning: ", poll("ping-warning"))
|
||||
print("ping-p1-outlook:", poll("ping-p1-outlook"))
|
||||
print("ping-p103-warning:", poll("ping-p103-warning"))
|
||||
from sqlalchemy import text
|
||||
|
||||
with store.engine.connect() as c:
|
||||
print(
|
||||
"state table:",
|
||||
c.execute(
|
||||
text("SELECT key, state, value FROM notification_state ORDER BY key")
|
||||
).fetchall(),
|
||||
)
|
||||
|
||||
|
||||
asyncio.run(main())
|
||||
+19
-6
@@ -18,6 +18,7 @@ APP_DIR="${APP_DIR:-/opt/thailand-water-monitor}"
|
||||
SERVICE_USER="${SERVICE_USER:-water-monitor}"
|
||||
SERVICE_GROUP="${SERVICE_GROUP:-${SERVICE_USER}}"
|
||||
SERVICE_NAME="water-monitor.service"
|
||||
RETRAIN_NAME="water-monitor-retrain"
|
||||
|
||||
# Resolve the repo root (parent of this scripts/ directory).
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
@@ -72,11 +73,18 @@ if ! command -v uv >/dev/null 2>&1; then
|
||||
fi
|
||||
UV="$(command -v uv)"
|
||||
|
||||
log "Creating virtualenv at ${APP_DIR}/venv"
|
||||
log "Syncing uv-managed virtualenv at ${APP_DIR}/.venv"
|
||||
cd "${APP_DIR}"
|
||||
# Named 'venv' (not uv's default .venv) to match the systemd unit's ExecStart.
|
||||
"${UV}" venv venv
|
||||
"${UV}" pip install --python venv/bin/python -r requirements.txt
|
||||
# ONE environment: uv sync owns .venv/ (from pyproject.toml + uv.lock, so the
|
||||
# ML extras such as scikit-learn/joblib are present) and both systemd units
|
||||
# run its interpreter directly. Never create a second env by another name --
|
||||
# a stale 'venv/' once coexisted here and broke manual retrains with
|
||||
# ModuleNotFoundError while the service itself ran fine.
|
||||
"${UV}" sync --python 3.11 --frozen
|
||||
if [ -d "${APP_DIR}/venv" ]; then
|
||||
warn "Removing stale ${APP_DIR}/venv (superseded by .venv)"
|
||||
rm -rf "${APP_DIR}/venv"
|
||||
fi
|
||||
|
||||
# 4. Environment file ----------------------------------------------------------
|
||||
if [ ! -f "${APP_DIR}/.env" ]; then
|
||||
@@ -100,11 +108,14 @@ if [ -f "${APP_DIR}/.env" ]; then
|
||||
chmod 0600 "${APP_DIR}/.env"
|
||||
fi
|
||||
|
||||
# 6. Install and enable the systemd unit --------------------------------------
|
||||
log "Installing systemd unit"
|
||||
# 6. Install and enable the systemd units -------------------------------------
|
||||
log "Installing systemd units"
|
||||
install -m 0644 "${SCRIPT_DIR}/${SERVICE_NAME}" "/etc/systemd/system/${SERVICE_NAME}"
|
||||
install -m 0644 "${SCRIPT_DIR}/${RETRAIN_NAME}.service" "/etc/systemd/system/${RETRAIN_NAME}.service"
|
||||
install -m 0644 "${SCRIPT_DIR}/${RETRAIN_NAME}.timer" "/etc/systemd/system/${RETRAIN_NAME}.timer"
|
||||
systemctl daemon-reload
|
||||
systemctl enable "${SERVICE_NAME}"
|
||||
systemctl enable --now "${RETRAIN_NAME}.timer"
|
||||
|
||||
log "Done."
|
||||
echo
|
||||
@@ -112,3 +123,5 @@ echo "Next steps:"
|
||||
echo " sudo systemctl start ${SERVICE_NAME}"
|
||||
echo " systemctl status ${SERVICE_NAME}"
|
||||
echo " sudo journalctl -u ${SERVICE_NAME} -f"
|
||||
echo " systemctl list-timers ${RETRAIN_NAME}.timer # monthly flood-model retrain"
|
||||
echo " sudo systemctl start ${RETRAIN_NAME}.service # retrain now"
|
||||
|
||||
@@ -0,0 +1,102 @@
|
||||
#!/usr/bin/env bash
|
||||
# Install ntfy (https://ntfy.sh) as the public notification server for the
|
||||
# Ping River Monitor. Run as root on the monitor VPS. Idempotent.
|
||||
#
|
||||
# NTFY_DOMAIN=ntfy.buildfor.life bash scripts/install_ntfy.sh
|
||||
#
|
||||
# What it does:
|
||||
# - installs the ntfy .deb from the official GitHub release (single Go
|
||||
# binary, ~30 MB RSS, sqlite message cache)
|
||||
# - writes /etc/ntfy/server.yml: listens on the Tailscale address only
|
||||
# (the reverse proxy is another VPS on the tailnet; nothing is exposed
|
||||
# on a public interface), anonymous READ on all topics, WRITE only with
|
||||
# a token. Override with NTFY_LISTEN=host:port.
|
||||
# - creates the `monitor` publishing user + token, writes NTFY_SERVER /
|
||||
# NTFY_TOKEN into /opt/thailand-water-monitor/.env if not present
|
||||
#
|
||||
# Reverse proxy (on the Caddy VPS, over Tailscale):
|
||||
# ntfy.buildfor.life {
|
||||
# reverse_proxy <this host's tailscale ip>:2586
|
||||
# }
|
||||
# Caddy passes websockets and keeps long-poll connections open by default;
|
||||
# subscribers hold one open. ntfy runs with behind-proxy: true so rate
|
||||
# limits key on X-Forwarded-For, not on the proxy's address.
|
||||
set -euo pipefail
|
||||
|
||||
NTFY_DOMAIN="${NTFY_DOMAIN:?set NTFY_DOMAIN, e.g. ntfy.buildfor.life}"
|
||||
NTFY_VERSION="${NTFY_VERSION:-2.28.0}"
|
||||
MONITOR_DIR="${MONITOR_DIR:-/opt/thailand-water-monitor}"
|
||||
TS_IP="$(tailscale ip -4 2>/dev/null | head -1 || true)"
|
||||
LISTEN="${NTFY_LISTEN:-${TS_IP:-127.0.0.1}:2586}"
|
||||
echo "ntfy will listen on ${LISTEN}"
|
||||
|
||||
if ! command -v ntfy >/dev/null || [[ "$(ntfy --version 2>/dev/null | awk '{print $3}')" != "$NTFY_VERSION" ]]; then
|
||||
tmp=$(mktemp -d)
|
||||
curl -fsSL -o "$tmp/ntfy.deb" \
|
||||
"https://github.com/binwiederhier/ntfy/releases/download/v${NTFY_VERSION}/ntfy_${NTFY_VERSION}_linux_amd64.deb"
|
||||
dpkg -i "$tmp/ntfy.deb"
|
||||
rm -rf "$tmp"
|
||||
fi
|
||||
|
||||
install -d -m 755 /var/cache/ntfy /var/lib/ntfy
|
||||
cat > /etc/ntfy/server.yml <<EOF
|
||||
# Ping River Monitor notification server. Managed by scripts/install_ntfy.sh.
|
||||
base-url: "https://${NTFY_DOMAIN}"
|
||||
listen-http: "${LISTEN}"
|
||||
behind-proxy: true
|
||||
|
||||
# Messages are kept so a phone that was offline still gets the crossing.
|
||||
cache-file: "/var/cache/ntfy/cache.db"
|
||||
cache-duration: "72h"
|
||||
|
||||
# Everyone may subscribe; only the monitor (token) may publish.
|
||||
auth-file: "/var/lib/ntfy/user.db"
|
||||
auth-default-access: "read-only"
|
||||
|
||||
# The monitor publishes a handful of messages per flood; be strict with
|
||||
# everything else so the box cannot be used as a free relay.
|
||||
visitor-request-limit-burst: 30
|
||||
visitor-request-limit-replenish: "10s"
|
||||
visitor-subscription-limit: 60
|
||||
visitor-message-daily-limit: 200
|
||||
attachment-cache-dir: ""
|
||||
enable-signup: false
|
||||
enable-login: false
|
||||
enable-metrics: false
|
||||
EOF
|
||||
|
||||
systemctl enable --now ntfy
|
||||
systemctl restart ntfy
|
||||
sleep 1
|
||||
curl -fsS "http://${LISTEN}/v1/health" >/dev/null && echo "ntfy up on ${LISTEN}"
|
||||
|
||||
# Publishing identity for the monitor
|
||||
if ! ntfy user list 2>/dev/null | grep -q '^user monitor (role'; then
|
||||
NTFY_PASSWORD="$(openssl rand -base64 24)" ntfy user add --role=user monitor
|
||||
fi
|
||||
ntfy access monitor 'ping-*' write-only >/dev/null
|
||||
# 'ping-*' read stays anonymous via auth-default-access
|
||||
|
||||
token=$(ntfy token list monitor 2>/dev/null | awk '/^- tk_/{print $2; exit}') # '- tk_xxx (label), ...'
|
||||
if [[ -z "$token" ]]; then
|
||||
token=$(ntfy token add --label "water-monitor" monitor | grep -oE 'tk_[A-Za-z0-9]+' | head -1) # 'token tk_xxx created for user monitor'
|
||||
fi
|
||||
|
||||
env_file="${MONITOR_DIR}/.env"
|
||||
if [[ -f "$env_file" ]] && ! grep -q '^NTFY_SERVER=' "$env_file"; then
|
||||
{
|
||||
echo ""
|
||||
echo "# ntfy public notifications (scripts/install_ntfy.sh)"
|
||||
echo "NTFY_SERVER=https://${NTFY_DOMAIN}"
|
||||
echo "NTFY_PUBLISH_URL=http://${LISTEN}"
|
||||
echo "NTFY_TOPIC_PREFIX=ping"
|
||||
echo "NTFY_TOKEN=${token}"
|
||||
} >> "$env_file"
|
||||
echo "wrote NTFY_* to ${env_file}; restart water-monitor to enable"
|
||||
else
|
||||
echo "NTFY_TOKEN=${token}"
|
||||
fi
|
||||
|
||||
echo
|
||||
echo "Subscribe test (anonymous read): curl -s 'http://${LISTEN}/ping-status/json?poll=1'"
|
||||
echo "Publish test (needs token): curl -s -H 'Authorization: Bearer ${token}' -d 'hello' http://${LISTEN}/ping-status"
|
||||
@@ -0,0 +1,90 @@
|
||||
#!/usr/bin/env bash
|
||||
#
|
||||
# Retrain the flood forecast models safely. Run by water-monitor-retrain.timer
|
||||
# (monthly) or by hand: sudo systemctl start water-monitor-retrain.service
|
||||
#
|
||||
# Why a script rather than ExecStart=train_flood_model.py:
|
||||
# * train.py writes each station's bundle straight into models/ over ~12 min,
|
||||
# and the API's hourly precompute reloads bundles by mtime. Training into
|
||||
# a staging dir and mv-ing (atomic on one filesystem) means the API never
|
||||
# sees a half-written joblib file or a mixed old/new set.
|
||||
# * A run that produced gauge-only (v2) bundles, or trained too few stations,
|
||||
# must NOT replace the deployed models. train.py already aborts on a
|
||||
# missing rain series; this script re-checks the written metrics anyway.
|
||||
# * No API restart is needed: predict.py reloads changed bundles on the next
|
||||
# precompute (every scrape cycle, hourly), so the new models are live
|
||||
# within an hour. Restart manually if you want them live immediately.
|
||||
#
|
||||
# Exit codes: 0 ok, 2 training refused (see log), 3 verification failed.
|
||||
set -euo pipefail
|
||||
|
||||
APP_DIR="${APP_DIR:-/opt/thailand-water-monitor}"
|
||||
PYTHON="${PYTHON:-${APP_DIR}/.venv/bin/python}"
|
||||
MODELS_DIR="${APP_DIR}/models"
|
||||
STAGE_DIR="${MODELS_DIR}/.staging"
|
||||
# P.4A is NOT_TRAINABLE by design (17% fill); 15 of 16 is the normal outcome.
|
||||
MIN_TRAINED="${MIN_TRAINED:-14}"
|
||||
EXPECT_VERSION_PREFIX="${EXPECT_VERSION_PREFIX:-hgb-v3+}"
|
||||
|
||||
log() { printf '%s retrain: %s\n' "$(date '+%Y-%m-%d %H:%M:%S')" "$*"; }
|
||||
|
||||
cd "${APP_DIR}"
|
||||
[ -x "${PYTHON}" ] || { log "no interpreter at ${PYTHON} (run uv sync)"; exit 3; }
|
||||
|
||||
rm -rf "${STAGE_DIR}"
|
||||
mkdir -p "${STAGE_DIR}"
|
||||
log "training into ${STAGE_DIR} (python=${PYTHON}, OMP_NUM_THREADS=${OMP_NUM_THREADS:-unset})"
|
||||
|
||||
# train_flood_model.py exits 2 on a missing rain series (RainUnavailableError)
|
||||
# instead of silently writing v2 bundles -- propagate that unchanged.
|
||||
set +e
|
||||
"${PYTHON}" scripts/train_flood_model.py --stations all --models-dir "${STAGE_DIR}" "$@"
|
||||
rc=$?
|
||||
set -e
|
||||
if [ "${rc}" -ne 0 ]; then
|
||||
log "training failed (exit ${rc}); deployed models untouched"
|
||||
rm -rf "${STAGE_DIR}"
|
||||
exit "${rc}"
|
||||
fi
|
||||
|
||||
# Verify before promoting. Reads metrics.json from the stage dir.
|
||||
VERSION="$("${PYTHON}" - "${STAGE_DIR}/metrics.json" <<'PY'
|
||||
import json, sys
|
||||
m = json.load(open(sys.argv[1]))
|
||||
print(m["model_version"])
|
||||
PY
|
||||
)"
|
||||
TRAINED="$("${PYTHON}" - "${STAGE_DIR}/metrics.json" <<'PY'
|
||||
import json, sys
|
||||
m = json.load(open(sys.argv[1]))
|
||||
print(sum(1 for s in m["stations"].values() if s.get("status") == "trained"))
|
||||
PY
|
||||
)"
|
||||
log "staged model_version=${VERSION} trained_stations=${TRAINED}"
|
||||
|
||||
case "${VERSION}" in
|
||||
"${EXPECT_VERSION_PREFIX}"*) ;;
|
||||
*)
|
||||
log "REFUSING to deploy: version '${VERSION}' does not start with '${EXPECT_VERSION_PREFIX}'"
|
||||
rm -rf "${STAGE_DIR}"
|
||||
exit 3
|
||||
;;
|
||||
esac
|
||||
if [ "${TRAINED}" -lt "${MIN_TRAINED}" ]; then
|
||||
log "REFUSING to deploy: only ${TRAINED} stations trained (< ${MIN_TRAINED})"
|
||||
rm -rf "${STAGE_DIR}"
|
||||
exit 3
|
||||
fi
|
||||
|
||||
# Promote: per-file rename is atomic; readers see either the old or the new
|
||||
# bundle, never a partial one. Keep one previous generation for rollback.
|
||||
mkdir -p "${MODELS_DIR}/.previous"
|
||||
for f in "${STAGE_DIR}"/flood_*.joblib "${STAGE_DIR}/metrics.json"; do
|
||||
name="$(basename "${f}")"
|
||||
if [ -f "${MODELS_DIR}/${name}" ]; then
|
||||
mv -f "${MODELS_DIR}/${name}" "${MODELS_DIR}/.previous/${name}"
|
||||
fi
|
||||
mv -f "${f}" "${MODELS_DIR}/${name}"
|
||||
done
|
||||
rm -rf "${STAGE_DIR}"
|
||||
log "deployed ${VERSION} (${TRAINED} stations); previous generation in models/.previous. The API picks it up on its next hourly precompute."
|
||||
@@ -0,0 +1,62 @@
|
||||
"""Summarise rolling-origin harness output side by side.
|
||||
|
||||
Usage:
|
||||
uv run python scripts/summarize_eval.py models/eval_2026-09-12.json [more.json ...]
|
||||
|
||||
Aggregates each (station, variant) across folds: mean MAE, mean flood-regime
|
||||
MAE, mean Brier, total false-alarm episodes, and every warning event with its
|
||||
first-alert lead and the 24 h-ahead peak error -- the operational numbers that
|
||||
decide whether a variant ships.
|
||||
"""
|
||||
|
||||
import json
|
||||
import statistics
|
||||
import sys
|
||||
from collections import OrderedDict
|
||||
|
||||
|
||||
def summarize(paths):
|
||||
for path in paths:
|
||||
results = json.load(open(path, encoding="utf-8"))
|
||||
print(f"\n##### {path}")
|
||||
for station in results:
|
||||
print(f"\n=== {station['station']} (warn {station['warn_thr']:.2f} m) ===")
|
||||
agg = OrderedDict()
|
||||
for fold in station["folds"]:
|
||||
for name, m in fold["variants"].items():
|
||||
a = agg.setdefault(
|
||||
name, {"mae": [], "mae_hi": [], "brier": [], "fa": 0, "events": []}
|
||||
)
|
||||
a["mae"].append(m["mae"])
|
||||
if m.get("mae_above_2p5") is not None:
|
||||
a["mae_hi"].append(m["mae_above_2p5"])
|
||||
if m.get("brier_warn") is not None:
|
||||
a["brier"].append(m["brier_warn"])
|
||||
a["fa"] += m["false_alarm_episodes"]
|
||||
for e in m["events"]:
|
||||
err = (
|
||||
None
|
||||
if e["peak_pred_24h_before"] is None
|
||||
else e["peak_pred_24h_before"] - e["peak_level"]
|
||||
)
|
||||
a["events"].append((fold["year"], e["crossing"][:10], e["lead_h"], e["peak_level"], err))
|
||||
print(f"{'variant':22} {'MAE':>6} {'MAE_hi':>7} {'Brier':>7} {'FA':>3} events: year crossing lead_h peak(err24h)")
|
||||
for name, a in agg.items():
|
||||
ev = " ".join(
|
||||
f"{y} {d} {'—' if l is None else format(l, '+.0f')}h {p:.2f}({'—' if err is None else format(err, '+.2f')})"
|
||||
for y, d, l, p, err in a["events"]
|
||||
)
|
||||
leads = [l for *_, l, _, _ in a["events"] if l is not None]
|
||||
print(
|
||||
f"{name:22} {statistics.mean(a['mae']):6.3f} "
|
||||
f"{statistics.mean(a['mae_hi']) if a['mae_hi'] else float('nan'):7.3f} "
|
||||
f"{statistics.mean(a['brier']) if a['brier'] else float('nan'):7.4f} "
|
||||
f"{a['fa']:>3} {ev}"
|
||||
)
|
||||
if leads:
|
||||
print(f"{'':22} lead: mean {statistics.mean(leads):+.1f} h, min {min(leads):+.0f} h, "
|
||||
f"missed {sum(1 for *_, l, _, _ in a['events'] if l is None)}/{len(a['events'])}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
summarize(sys.argv[1:] or ["models/eval_variants.json"])
|
||||
@@ -11,7 +11,7 @@ import sys
|
||||
|
||||
sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
|
||||
|
||||
from src.ml.train import main
|
||||
from src.ml.train import cli
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
raise SystemExit(cli())
|
||||
|
||||
@@ -0,0 +1,39 @@
|
||||
[Unit]
|
||||
Description=Retrain the Ping River flood forecast models
|
||||
Documentation=https://git.b4l.co.th/B4L/Northern-Thailand-Ping-River-Monitor/-/blob/master/docs/FLOOD_FORECASTING.md
|
||||
After=network-online.target
|
||||
Wants=network-online.target
|
||||
|
||||
[Service]
|
||||
Type=oneshot
|
||||
User=water-monitor
|
||||
Group=water-monitor
|
||||
WorkingDirectory=/opt/thailand-water-monitor
|
||||
EnvironmentFile=/opt/thailand-water-monitor/.env
|
||||
# Same interpreter as water-monitor.service -- the uv-managed .venv.
|
||||
# scripts/retrain.sh trains into models/.staging, refuses to promote anything
|
||||
# that is not a rain-enabled (hgb-v3) set covering the expected stations, then
|
||||
# renames the bundles into place. The API reloads them on its next hourly
|
||||
# precompute; no restart, so a failed run leaves the old models serving.
|
||||
ExecStart=/bin/bash /opt/thailand-water-monitor/scripts/retrain.sh
|
||||
# HistGradientBoosting is CPU-bound; cap threads so training cannot starve
|
||||
# the API (docs/FLOOD_FORECASTING.md section 6 measured 4 as the sweet spot).
|
||||
Environment=OMP_NUM_THREADS=4
|
||||
Environment=PYTHONPATH=/opt/thailand-water-monitor
|
||||
Environment=PYTHONUNBUFFERED=1
|
||||
Nice=15
|
||||
IOSchedulingClass=idle
|
||||
# 15 stations at ~50 s each plus data load: 12 min observed on 2026-09-12.
|
||||
TimeoutStartSec=45min
|
||||
|
||||
# Same sandbox as the API unit.
|
||||
NoNewPrivileges=true
|
||||
PrivateTmp=true
|
||||
ProtectSystem=strict
|
||||
ProtectHome=true
|
||||
ReadWritePaths=/opt/thailand-water-monitor
|
||||
CapabilityBoundingSet=
|
||||
|
||||
StandardOutput=journal
|
||||
StandardError=journal
|
||||
SyslogIdentifier=water-monitor-retrain
|
||||
@@ -0,0 +1,17 @@
|
||||
[Unit]
|
||||
Description=Monthly flood-model retrain (docs/FLOOD_FORECASTING.md section 7)
|
||||
|
||||
[Timer]
|
||||
# Policy: at minimum once pre-monsoon (May-June), monthly through the season
|
||||
# (July-November), and after any major flood. A retrain costs ~12 min and RAM
|
||||
# peaks ~300 MB, so running it every month all year is cheaper than remembering
|
||||
# which months matter. 1st of the month, 03:30 server-local -- between the
|
||||
# hourly scrapes and outside Thai daytime traffic.
|
||||
OnCalendar=*-*-01 03:30:00
|
||||
# Catch up if the box was off at the scheduled time.
|
||||
Persistent=true
|
||||
RandomizedDelaySec=20min
|
||||
Unit=water-monitor-retrain.service
|
||||
|
||||
[Install]
|
||||
WantedBy=timers.target
|
||||
@@ -9,17 +9,19 @@ Type=simple
|
||||
User=water-monitor
|
||||
Group=water-monitor
|
||||
WorkingDirectory=/opt/thailand-water-monitor
|
||||
ExecStart=/opt/thailand-water-monitor/venv/bin/python src/water_scraper_v3.py
|
||||
# The uv-managed env (uv sync -> .venv). Same interpreter for water-monitor-retrain.service.
|
||||
ExecStart=/opt/thailand-water-monitor/.venv/bin/python run.py --web-api
|
||||
ExecReload=/bin/kill -HUP $MAINPID
|
||||
Restart=always
|
||||
RestartSec=60
|
||||
TimeoutStopSec=30
|
||||
|
||||
# Environment variables
|
||||
Environment=DB_TYPE=victoriametrics
|
||||
Environment=VM_HOST=localhost
|
||||
Environment=VM_PORT=8428
|
||||
# DB_TYPE / POSTGRES_CONNECTION_STRING / MATRIX_* come from the .env file.
|
||||
EnvironmentFile=/opt/thailand-water-monitor/.env
|
||||
Environment=PYTHONPATH=/opt/thailand-water-monitor
|
||||
# Serving path is latency-bound; single-threaded BLAS is 2.6x faster per call
|
||||
# (docs/FLOOD_FORECASTING.md section 6). Training sets its own value.
|
||||
Environment=OMP_NUM_THREADS=1
|
||||
Environment=PYTHONUNBUFFERED=1
|
||||
|
||||
# Security settings
|
||||
|
||||
+7
-3
@@ -12,9 +12,13 @@ __description__ = "Northern Thailand Ping River Monitoring System"
|
||||
|
||||
from .config import Config
|
||||
from .database_adapters import DatabaseAdapter, create_database_adapter
|
||||
from .exceptions import (APIConnectionError, ConfigurationError,
|
||||
DatabaseConnectionError, DataValidationError,
|
||||
WaterMonitorException)
|
||||
from .exceptions import (
|
||||
APIConnectionError,
|
||||
ConfigurationError,
|
||||
DatabaseConnectionError,
|
||||
DataValidationError,
|
||||
WaterMonitorException,
|
||||
)
|
||||
from .models import DatabaseConfig, StationInfo, WaterMeasurement
|
||||
from .water_scraper_v3 import EnhancedWaterMonitorScraper
|
||||
|
||||
|
||||
@@ -38,6 +38,17 @@ class Config:
|
||||
TARGET_URL = "https://hyd-app-db.rid.go.th/hydro1h.html"
|
||||
API_URL = "https://hyd-app-db.rid.go.th/webservice/getGroupHourlyWaterLevelReportAllHL.ashx"
|
||||
THAIWATER_API_KEY = os.getenv("THAIWATER_API_KEY")
|
||||
|
||||
# Public flood notifications (ntfy). Off unless NTFY_SERVER is set.
|
||||
# NTFY_SERVER is what subscribers use (public https URL, shown on the
|
||||
# dashboard). NTFY_PUBLISH_URL is where the monitor POSTs; defaults to
|
||||
# NTFY_SERVER, set it to http://127.0.0.1:2586 when ntfy runs on the same
|
||||
# host so publishing never depends on DNS/proxy/tunnel being up.
|
||||
NTFY_SERVER = os.getenv("NTFY_SERVER", "").strip()
|
||||
NTFY_PUBLISH_URL = os.getenv("NTFY_PUBLISH_URL", "").strip() or NTFY_SERVER
|
||||
NTFY_TOPIC_PREFIX = os.getenv("NTFY_TOPIC_PREFIX", "ping").strip()
|
||||
NTFY_TOKEN = os.getenv("NTFY_TOKEN", "").strip() # publish token if ACL enabled
|
||||
PUBLIC_URL = os.getenv("PUBLIC_URL", "https://water.buildfor.life/").strip()
|
||||
REQUEST_TIMEOUT = int(os.getenv("REQUEST_TIMEOUT", "30"))
|
||||
USER_AGENT = (
|
||||
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
|
||||
|
||||
+30
-30
@@ -139,12 +139,16 @@ class InfluxDBAdapter(DatabaseAdapter):
|
||||
"time": measurement["timestamp"].isoformat(),
|
||||
"fields": {
|
||||
"water_level": float(measurement["water_level"]),
|
||||
"discharge": float(measurement["discharge"])
|
||||
if measurement.get("discharge") is not None
|
||||
else None,
|
||||
"discharge_percent": float(measurement["discharge_percent"])
|
||||
if measurement.get("discharge_percent")
|
||||
else None,
|
||||
"discharge": (
|
||||
float(measurement["discharge"])
|
||||
if measurement.get("discharge") is not None
|
||||
else None
|
||||
),
|
||||
"discharge_percent": (
|
||||
float(measurement["discharge_percent"])
|
||||
if measurement.get("discharge_percent")
|
||||
else None
|
||||
),
|
||||
},
|
||||
}
|
||||
points.append(point)
|
||||
@@ -551,13 +555,13 @@ class SQLAdapter(DatabaseAdapter):
|
||||
"station_code": row[1],
|
||||
"station_name_en": row[2],
|
||||
"station_name_th": row[3],
|
||||
"water_level": float(row[4])
|
||||
if row[4] is not None
|
||||
else None,
|
||||
"water_level": (
|
||||
float(row[4]) if row[4] is not None else None
|
||||
),
|
||||
"discharge": float(row[5]) if row[5] is not None else None,
|
||||
"discharge_percent": float(row[6])
|
||||
if row[6] is not None
|
||||
else None,
|
||||
"discharge_percent": (
|
||||
float(row[6]) if row[6] is not None else None
|
||||
),
|
||||
"status": row[7],
|
||||
}
|
||||
)
|
||||
@@ -611,13 +615,13 @@ class SQLAdapter(DatabaseAdapter):
|
||||
"station_code": row[1],
|
||||
"station_name_en": row[2],
|
||||
"station_name_th": row[3],
|
||||
"water_level": float(row[4])
|
||||
if row[4] is not None
|
||||
else None,
|
||||
"water_level": (
|
||||
float(row[4]) if row[4] is not None else None
|
||||
),
|
||||
"discharge": float(row[5]) if row[5] is not None else None,
|
||||
"discharge_percent": float(row[6])
|
||||
if row[6] is not None
|
||||
else None,
|
||||
"discharge_percent": (
|
||||
float(row[6]) if row[6] is not None else None
|
||||
),
|
||||
"status": row[7],
|
||||
}
|
||||
)
|
||||
@@ -666,13 +670,13 @@ class SQLAdapter(DatabaseAdapter):
|
||||
"station_id": row[1],
|
||||
"station_code": row[2] or f"Station_{row[1]}",
|
||||
"station_name_th": row[3] or f"Station {row[1]}",
|
||||
"water_level": float(row[4])
|
||||
if row[4] is not None
|
||||
else None,
|
||||
"water_level": (
|
||||
float(row[4]) if row[4] is not None else None
|
||||
),
|
||||
"discharge": float(row[5]) if row[5] is not None else None,
|
||||
"discharge_percent": float(row[6])
|
||||
if row[6] is not None
|
||||
else None,
|
||||
"discharge_percent": (
|
||||
float(row[6]) if row[6] is not None else None
|
||||
),
|
||||
"status": row[7],
|
||||
}
|
||||
)
|
||||
@@ -767,9 +771,7 @@ class SQLAdapter(DatabaseAdapter):
|
||||
return hours_by_day
|
||||
|
||||
except Exception as e:
|
||||
logging.error(
|
||||
f"Error querying {self.db_type.upper()} recorded hours: {e}"
|
||||
)
|
||||
logging.error(f"Error querying {self.db_type.upper()} recorded hours: {e}")
|
||||
return None
|
||||
|
||||
def get_database_stats(self) -> Optional[Dict]:
|
||||
@@ -814,9 +816,7 @@ class SQLAdapter(DatabaseAdapter):
|
||||
# the DISTINCT day-hour slots and coverage cannot exceed 100%
|
||||
first_slot = first_ts.replace(minute=0, second=0, microsecond=0)
|
||||
last_slot = last_ts.replace(minute=0, second=0, microsecond=0)
|
||||
expected_hours = (
|
||||
int((last_slot - first_slot).total_seconds() // 3600) + 1
|
||||
)
|
||||
expected_hours = int((last_slot - first_slot).total_seconds() // 3600) + 1
|
||||
recorded_hours = int(row[4])
|
||||
coverage_percent = round(100.0 * recorded_hours / expected_hours, 1)
|
||||
|
||||
|
||||
+3
-3
@@ -125,9 +125,9 @@ class DatabaseHealthCheck(HealthCheck):
|
||||
"message": "Database connection OK",
|
||||
"details": {
|
||||
"latest_data_count": len(latest_data),
|
||||
"latest_timestamp": str(latest_data[0].get("timestamp"))
|
||||
if latest_data
|
||||
else None,
|
||||
"latest_timestamp": (
|
||||
str(latest_data[0].get("timestamp")) if latest_data else None
|
||||
),
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
+2
-4
@@ -17,9 +17,9 @@ import time
|
||||
from typing import Dict, List, Optional
|
||||
|
||||
from .hii_collector import (
|
||||
PING_BASIN_CODE,
|
||||
HiiClient,
|
||||
HiiStore,
|
||||
PING_BASIN_CODE,
|
||||
_parse_datetime,
|
||||
_to_float,
|
||||
)
|
||||
@@ -145,9 +145,7 @@ def backfill(
|
||||
station_rows += store.save_waterlevel_history(sid, rows)
|
||||
except Exception as e:
|
||||
totals["errors"] += 1
|
||||
logger.warning(
|
||||
f"{label}: {chunk_start}..{chunk_end} failed: {e}"
|
||||
)
|
||||
logger.warning(f"{label}: {chunk_start}..{chunk_end} failed: {e}")
|
||||
time.sleep(sleep_seconds)
|
||||
totals["rows"] += station_rows
|
||||
logger.info(f"{label} (id {sid}): {station_rows} rows saved")
|
||||
|
||||
@@ -66,9 +66,7 @@ def rid_code_from_oldcode(oldcode: Optional[str]) -> Optional[str]:
|
||||
return match.group(1) if match else None
|
||||
|
||||
|
||||
def parse_rain_records(
|
||||
payload: Dict, basin_code: int = PING_BASIN_CODE
|
||||
) -> List[Dict]:
|
||||
def parse_rain_records(payload: Dict, basin_code: int = PING_BASIN_CODE) -> List[Dict]:
|
||||
"""Extract per-station rainfall rows from a rain_24h payload."""
|
||||
records = []
|
||||
for row in payload.get("data") or []:
|
||||
@@ -186,9 +184,7 @@ class HiiStore:
|
||||
def __init__(self, connection_string: str, db_type: str):
|
||||
self.db_type = db_type.lower()
|
||||
if self.db_type not in ("sqlite", "postgresql", "mysql"):
|
||||
raise ValueError(
|
||||
f"HII collection requires a SQL database, got '{db_type}'"
|
||||
)
|
||||
raise ValueError(f"HII collection requires a SQL database, got '{db_type}'")
|
||||
self.connection_string = connection_string
|
||||
self.engine = None
|
||||
|
||||
@@ -400,9 +396,7 @@ class HiiStore:
|
||||
from sqlalchemy import text
|
||||
|
||||
now = datetime.datetime.now()
|
||||
station_sql = self._upsert(
|
||||
station_table, ["id"], station_cols + ["updated_at"]
|
||||
)
|
||||
station_sql = self._upsert(station_table, ["id"], station_cols + ["updated_at"])
|
||||
measurement_sql = self._upsert(
|
||||
measurement_table, ["station_id", "timestamp"], measurement_cols
|
||||
)
|
||||
|
||||
+1
-3
@@ -61,9 +61,7 @@ def load_daily(
|
||||
params["start"] = start
|
||||
engine = create_engine(resolved, pool_pre_ping=True)
|
||||
with engine.connect() as conn:
|
||||
daily = pd.read_sql(
|
||||
text(query + " ORDER BY date"), conn, params=params
|
||||
)
|
||||
daily = pd.read_sql(text(query + " ORDER BY date"), conn, params=params)
|
||||
daily["date"] = pd.to_datetime(daily["date"])
|
||||
daily = daily.set_index("date")
|
||||
for col in DAM_COLUMNS:
|
||||
|
||||
+11
-7
@@ -23,7 +23,9 @@ from .features import UPSTREAM_LEADS
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
DEFAULT_API_URL = "http://100.81.167.42:8000"
|
||||
# Public dashboard. Override with --api-url for a local instance; the
|
||||
# Tailscale address of the server is deliberately not the default here.
|
||||
DEFAULT_API_URL = "https://water.buildfor.life"
|
||||
# Anchored to the repo root so training/prediction work from any CWD; a relative
|
||||
# path here silently produced 0 rows when the CLI ran outside the repo root.
|
||||
CACHE_DIR = Path(__file__).resolve().parents[2] / "models" / "cache"
|
||||
@@ -205,15 +207,13 @@ def fill_from_hii(
|
||||
"timestamp": missing["timestamp"],
|
||||
"station_code": code,
|
||||
"water_level": missing["wl_msl"] - offset,
|
||||
"discharge": missing["discharge"]
|
||||
if code in _HII_EXACT_MIRRORS
|
||||
else float("nan"),
|
||||
"discharge": (
|
||||
missing["discharge"] if code in _HII_EXACT_MIRRORS else float("nan")
|
||||
),
|
||||
}
|
||||
)
|
||||
fills.append(fill)
|
||||
logger.info(
|
||||
f"HII gap-fill {code}: +{len(fill)} hours (offset {offset:.3f} m)"
|
||||
)
|
||||
logger.info(f"HII gap-fill {code}: +{len(fill)} hours (offset {offset:.3f} m)")
|
||||
if not fills:
|
||||
return df
|
||||
return _normalize_long(pd.concat([df] + fills, ignore_index=True))
|
||||
@@ -282,6 +282,10 @@ def _read_cache(cache_dir: Path, stations: Optional[List[str]]) -> pd.DataFrame:
|
||||
frames = []
|
||||
for path in sorted(cache_dir.glob("*.csv.gz")):
|
||||
code = path.name[: -len(".csv.gz")]
|
||||
# The dir is shared with rain.py / dam.py caches (rain_openmeteo,
|
||||
# dam_<id>): only station files (P.<n>) are measurements.
|
||||
if not code.startswith("P."):
|
||||
continue
|
||||
if stations and code not in stations:
|
||||
continue
|
||||
with gzip.open(path, "rt", encoding="utf-8") as handle:
|
||||
|
||||
+125
-43
@@ -52,22 +52,40 @@ def _flood_weights(y_abs: pd.Series) -> np.ndarray:
|
||||
return 1.0 + 4.0 * np.clip((y_abs.to_numpy() - 2.5) / 1.2, 0.0, 1.0)
|
||||
|
||||
|
||||
# Experimental forward-48h rain sum, built in evaluate_station (not in
|
||||
# features.build_features) so the served feature set is untouched until the
|
||||
# harness says it helps. Serving could supply it: fetch_forecast() already
|
||||
# pulls forecast_days=2.
|
||||
EXTRA_RAIN_FEATURES = ("rain_fc48",)
|
||||
|
||||
|
||||
class Variant:
|
||||
"""A trainable candidate producing (pred_abs, sigma_per_row) on test rows."""
|
||||
|
||||
def __init__(self, name: str, target: str, weighted: bool = False,
|
||||
quantile: bool = False, use_rain: bool = False,
|
||||
use_dam: bool = False):
|
||||
def __init__(
|
||||
self,
|
||||
name: str,
|
||||
target: str,
|
||||
weighted: bool = False,
|
||||
quantile: bool = False,
|
||||
use_rain: bool = False,
|
||||
use_dam: bool = False,
|
||||
use_fc48: bool = False,
|
||||
qsigma: bool = False,
|
||||
):
|
||||
self.name = name
|
||||
self.target = target # 'abs' or 'rise'
|
||||
self.weighted = weighted
|
||||
self.quantile = quantile
|
||||
self.use_rain = use_rain
|
||||
self.use_dam = use_dam
|
||||
self.use_fc48 = use_fc48
|
||||
# Hybrid: L2 head for the point prediction (keeps the lead-time
|
||||
# behaviour of the deployed model exactly, since p>=0.5 alerts are
|
||||
# sigma-independent) and quantile heads ONLY for a per-row sigma.
|
||||
self.qsigma = qsigma
|
||||
|
||||
def fit_predict(
|
||||
self, X_tr, y_abs_tr, X_te
|
||||
) -> Tuple[np.ndarray, np.ndarray]:
|
||||
def fit_predict(self, X_tr, y_abs_tr, X_te) -> Tuple[np.ndarray, np.ndarray]:
|
||||
if not self.use_rain:
|
||||
drop = [c for c in features.RAIN_FEATURES if c in X_tr.columns]
|
||||
X_tr = X_tr.drop(columns=drop)
|
||||
@@ -84,6 +102,12 @@ class Variant:
|
||||
raise ValueError(
|
||||
f"{self.name} requires the dam series (rid_reservoir_daily backfilled)"
|
||||
)
|
||||
if not self.use_fc48:
|
||||
drop = [c for c in EXTRA_RAIN_FEATURES if c in X_tr.columns]
|
||||
X_tr = X_tr.drop(columns=drop)
|
||||
X_te = X_te.drop(columns=drop)
|
||||
elif "rain_fc48" not in X_tr.columns:
|
||||
raise ValueError(f"{self.name} requires the rain series")
|
||||
level_tr = X_tr["level"]
|
||||
level_te = X_te["level"].to_numpy()
|
||||
y_tr = (y_abs_tr - level_tr) if self.target == "rise" else y_abs_tr
|
||||
@@ -99,7 +123,13 @@ class Variant:
|
||||
else:
|
||||
reg = _make_regressor().fit(X_tr, y_tr, sample_weight=weights)
|
||||
pred = reg.predict(X_te)
|
||||
sigma = np.full(len(X_te), FIXED_SIGMA)
|
||||
if self.qsigma:
|
||||
q50 = _quantile_regressor(0.5).fit(X_tr, y_tr, sample_weight=weights)
|
||||
q90 = _quantile_regressor(0.9).fit(X_tr, y_tr, sample_weight=weights)
|
||||
spread = np.maximum(q90.predict(X_te) - q50.predict(X_te), 0.0)
|
||||
sigma = np.maximum(spread / 1.2816, 0.05)
|
||||
else:
|
||||
sigma = np.full(len(X_te), FIXED_SIGMA)
|
||||
|
||||
pred_abs = pred + level_te if self.target == "rise" else pred
|
||||
pred_abs = np.maximum(pred_abs, level_te) # peak >= current, as served
|
||||
@@ -110,18 +140,44 @@ VARIANTS: Dict[str, Variant] = {
|
||||
"baseline_abs": Variant("baseline_abs", target="abs"),
|
||||
"rise": Variant("rise", target="rise"),
|
||||
"rise_weighted": Variant("rise_weighted", target="rise", weighted=True),
|
||||
"rise_quantile": Variant("rise_quantile", target="rise", weighted=True,
|
||||
quantile=True),
|
||||
"rise_quantile": Variant(
|
||||
"rise_quantile", target="rise", weighted=True, quantile=True
|
||||
),
|
||||
"rise_rain": Variant("rise_rain", target="rise", use_rain=True),
|
||||
"rise_rain_dam": Variant("rise_rain_dam", target="rise", use_rain=True,
|
||||
use_dam=True),
|
||||
"rise_rain_dam": Variant(
|
||||
"rise_rain_dam", target="rise", use_rain=True, use_dam=True
|
||||
),
|
||||
"rise_dam": Variant("rise_dam", target="rise", use_dam=True),
|
||||
# 2026-09-12 experiments on top of the deployed rise_rain configuration:
|
||||
# per-row sigma from quantile heads (the served sigma sits on the 0.15
|
||||
# floor at every P.1 horizon, so stage probabilities are constant-
|
||||
# calibrated), and a longer forecast-rain window for the 24 h horizon.
|
||||
"rise_rain_quantile": Variant(
|
||||
"rise_rain_quantile", target="rise", weighted=True, quantile=True, use_rain=True
|
||||
),
|
||||
"rise_rain_quantile_uw": Variant(
|
||||
"rise_rain_quantile_uw", target="rise", quantile=True, use_rain=True
|
||||
),
|
||||
"rise_rain_fc48": Variant(
|
||||
"rise_rain_fc48", target="rise", use_rain=True, use_fc48=True
|
||||
),
|
||||
"rise_rain_qsigma": Variant(
|
||||
"rise_rain_qsigma", target="rise", use_rain=True, qsigma=True
|
||||
),
|
||||
}
|
||||
|
||||
# Dam variants are opt-in by name: they require dam columns that only exist
|
||||
# for features.DAM_STATIONS and only when the reservoir series loaded, and
|
||||
# the 2026-08-13 ablation concluded them a negative result.
|
||||
DEFAULT_VARIANTS = [k for k, v in VARIANTS.items() if not v.use_dam]
|
||||
# the 2026-08-13 ablation concluded them a negative result. The 2026-09-12
|
||||
# experiments are opt-in too (see their results in docs/FLOOD_FORECASTING.md).
|
||||
DEFAULT_VARIANTS = [
|
||||
k
|
||||
for k, v in VARIANTS.items()
|
||||
if not v.use_dam
|
||||
and not v.use_fc48
|
||||
and not v.qsigma
|
||||
and not (v.quantile and v.use_rain)
|
||||
]
|
||||
|
||||
|
||||
def _find_events(observed: pd.Series, thr: float) -> List[dict]:
|
||||
@@ -167,12 +223,16 @@ def _first_alert_lead(
|
||||
start = crossing - pd.Timedelta(hours=72)
|
||||
if window_start_floor is not None and window_start_floor > start:
|
||||
start = window_start_floor
|
||||
window = p.loc[start: crossing + pd.Timedelta(hours=24)]
|
||||
window = p.loc[start : crossing + pd.Timedelta(hours=24)]
|
||||
if len(window) < 2:
|
||||
return None
|
||||
alert = (window >= ALERT_P) & (window.shift(-1) >= ALERT_P) & (
|
||||
(window.index.to_series().shift(-1) - window.index.to_series())
|
||||
<= pd.Timedelta(hours=2)
|
||||
alert = (
|
||||
(window >= ALERT_P)
|
||||
& (window.shift(-1) >= ALERT_P)
|
||||
& (
|
||||
(window.index.to_series().shift(-1) - window.index.to_series())
|
||||
<= pd.Timedelta(hours=2)
|
||||
)
|
||||
)
|
||||
hits = window.index[alert.fillna(False)]
|
||||
if len(hits) == 0:
|
||||
@@ -180,9 +240,7 @@ def _first_alert_lead(
|
||||
return float((crossing - hits[0]).total_seconds() / 3600.0)
|
||||
|
||||
|
||||
def _false_alarm_episodes(
|
||||
p: pd.Series, observed: pd.Series, thr: float
|
||||
) -> int:
|
||||
def _false_alarm_episodes(p: pd.Series, observed: pd.Series, thr: float) -> int:
|
||||
"""Alert episodes with no observed >=thr within +/- FALSE_ALARM_GRACE_H."""
|
||||
alert_hours = p[p >= ALERT_P].index
|
||||
if len(alert_hours) == 0:
|
||||
@@ -222,6 +280,12 @@ def evaluate_station(
|
||||
warn_thr, _ = features.get_thresholds(station)
|
||||
grid = features.make_hourly_grid(df_long)
|
||||
X_all = features.build_features(grid, station, rain=rain, dam=dam)
|
||||
if rain is not None:
|
||||
# forward sum over (t, t+48]; same construction as rain_fc24
|
||||
r = rain.reindex(X_all.index)
|
||||
X_all["rain_fc48"] = (
|
||||
r.shift(-1).iloc[::-1].rolling(48, min_periods=1).sum().iloc[::-1]
|
||||
)
|
||||
observed = grid.observed[(station, "water_level")]
|
||||
|
||||
keep = X_all["obs_age_h"].notna()
|
||||
@@ -247,7 +311,9 @@ def evaluate_station(
|
||||
tr = (X_all.index <= train_end) & y_abs.notna()
|
||||
te = (X_all.index >= test_lo) & (X_all.index <= test_hi)
|
||||
if tr.sum() < 5000 or te.sum() < 500:
|
||||
logger.info(f"{station} {year}: skipped (train {tr.sum()}, test {te.sum()})")
|
||||
logger.info(
|
||||
f"{station} {year}: skipped (train {tr.sum()}, test {te.sum()})"
|
||||
)
|
||||
continue
|
||||
|
||||
X_tr, X_te = X_all.loc[tr], X_all.loc[te]
|
||||
@@ -323,9 +389,7 @@ def evaluate_station(
|
||||
)
|
||||
fold["variants"][name] = {
|
||||
"mae": float(errors.mean()) if len(errors) else None,
|
||||
"mae_above_2p5": (
|
||||
float(errors[high].mean()) if high.any() else None
|
||||
),
|
||||
"mae_above_2p5": (float(errors[high].mean()) if high.any() else None),
|
||||
"brier_warn": brier,
|
||||
"events": event_rows,
|
||||
"false_alarm_episodes": _false_alarm_episodes(
|
||||
@@ -346,17 +410,20 @@ def summarize(results: Dict) -> str:
|
||||
lines.append(header)
|
||||
for fold in results["folds"]:
|
||||
for name, m in fold["variants"].items():
|
||||
events = " ".join(
|
||||
f"[{e['crossing'][:10]}: "
|
||||
f"{'—' if e['lead_h'] is None else format(e['lead_h'], '+.0f')}h"
|
||||
+ (
|
||||
f" | {e['peak_pred_24h_before'] - e['peak_level']:+.2f}"
|
||||
if e["peak_pred_24h_before"] is not None
|
||||
else ""
|
||||
events = (
|
||||
" ".join(
|
||||
f"[{e['crossing'][:10]}: "
|
||||
f"{'—' if e['lead_h'] is None else format(e['lead_h'], '+.0f')}h"
|
||||
+ (
|
||||
f" | {e['peak_pred_24h_before'] - e['peak_level']:+.2f}"
|
||||
if e["peak_pred_24h_before"] is not None
|
||||
else ""
|
||||
)
|
||||
+ "]"
|
||||
for e in m["events"]
|
||||
)
|
||||
+ "]"
|
||||
for e in m["events"]
|
||||
) or "no events"
|
||||
or "no events"
|
||||
)
|
||||
lines.append(
|
||||
f"{name:16} {fold['year']:>5} "
|
||||
f"{m['mae'] if m['mae'] is not None else float('nan'):6.3f} "
|
||||
@@ -373,19 +440,32 @@ def main(argv=None) -> int:
|
||||
parser = argparse.ArgumentParser(description=__doc__)
|
||||
parser.add_argument("--stations", default="P.1")
|
||||
parser.add_argument("--db-url", default=None)
|
||||
parser.add_argument("--variants", default=None,
|
||||
help="comma list; default all")
|
||||
parser.add_argument("--variants", default=None, help="comma list; default all")
|
||||
parser.add_argument("--out", default="models/eval_variants.json")
|
||||
parser.add_argument("--no-rain", action="store_true",
|
||||
help="skip loading the Open-Meteo rain series")
|
||||
parser.add_argument("--no-dam", action="store_true",
|
||||
help="skip loading the Mae Ngat reservoir series")
|
||||
parser.add_argument(
|
||||
"--no-rain", action="store_true", help="skip loading the Open-Meteo rain series"
|
||||
)
|
||||
parser.add_argument(
|
||||
"--no-dam",
|
||||
action="store_true",
|
||||
help="skip loading the Mae Ngat reservoir series",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--from-cache",
|
||||
action="store_true",
|
||||
help="offline: read models/cache/ only (no DB, no API, "
|
||||
"no Open-Meteo refresh) -- reproducible reruns",
|
||||
)
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
logging.basicConfig(
|
||||
level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s"
|
||||
)
|
||||
df = data.load_measurements(db_url=args.db_url)
|
||||
if args.from_cache:
|
||||
df = data._read_cache(data.CACHE_DIR, None)
|
||||
logger.info(f"measurements from cache: {len(df)} rows")
|
||||
else:
|
||||
df = data.load_measurements(db_url=args.db_url)
|
||||
if df.empty:
|
||||
logger.error("no measurement data")
|
||||
return 1
|
||||
@@ -394,7 +474,9 @@ def main(argv=None) -> int:
|
||||
if not args.no_rain:
|
||||
from . import rain as rain_mod
|
||||
|
||||
rain_series = rain_mod.catchment_mean(rain_mod.load_history())
|
||||
rain_series = rain_mod.catchment_mean(
|
||||
rain_mod.load_history(refresh=not args.from_cache)
|
||||
)
|
||||
if rain_series is None:
|
||||
logger.warning("rain history unavailable; rain features will be NaN")
|
||||
else:
|
||||
@@ -404,7 +486,7 @@ def main(argv=None) -> int:
|
||||
)
|
||||
|
||||
dam_frame = None
|
||||
if not args.no_dam:
|
||||
if not args.no_dam and not args.from_cache:
|
||||
from . import dam as dam_mod
|
||||
|
||||
dam_frame = dam_mod.load_history(db_url=args.db_url)
|
||||
|
||||
+10
-2
@@ -37,9 +37,17 @@ THRESHOLDS: Dict[str, Tuple[float, float]] = {
|
||||
"P.4A": (3.40, 3.90),
|
||||
"P.5": (4.55, 4.95),
|
||||
"P.67": (2.45, 2.90),
|
||||
"P.75": (2.75, 3.50),
|
||||
# P.75: 2024 (the only year with a full flood record, 191% capacity peak)
|
||||
# puts 75-85% at 3.45 m and 95-105% at 3.72 m; 2018/2022 agree within
|
||||
# 0.15 m. The 2026-08 value (2.75) alerted on 15 quiet-season hours.
|
||||
"P.75": (3.20, 3.65),
|
||||
"P.76": (5.35, 5.45),
|
||||
"P.77": (2.85, 3.35),
|
||||
# P.77: recalibrated 2026-09-12. The 2026-08 value (2.85) sat below the
|
||||
# gauge's own dry-season baseline (2.6-2.7 m at 8-14% capacity), so the
|
||||
# first ntfy cycle fired a "warning" at 22% capacity. Across 2018-2024,
|
||||
# 75-85% capacity reads 3.35-4.57 m and 95-105% 4.27-5.08 m; 2024 (the
|
||||
# best-sampled flood year) gives 4.57 / 5.08. Slightly conservative:
|
||||
"P.77": (4.30, 4.90),
|
||||
"P.81": (5.15, 6.30),
|
||||
# P.82 never reached 100% capacity in the record (max level 3.78, max 96.4%);
|
||||
# danger sits just below the observed maximum so the head can actually train.
|
||||
|
||||
@@ -0,0 +1,122 @@
|
||||
"""Catchment-mean hourly rain from the HII/ThaiWater gauge network.
|
||||
|
||||
Independent of Open-Meteo (src/ml/rain.py): those are model-analysis values,
|
||||
these are what the gauges measured. The `hii_rainfall` table has been filled
|
||||
by the hourly collector since 2026-08-11 and there is NO archive behind it
|
||||
(the api-v3 rain_24h_graph endpoint ignores its date range, see
|
||||
docs/DATA_SOURCES.md 2.1), so this series cannot yet be a training feature:
|
||||
every training row before 2026-08 would be NaN and HistGradientBoosting
|
||||
would learn nothing from the column. It becomes a candidate once a full
|
||||
monsoon season of gauge rows exists in the rolling-origin harness's test
|
||||
span -- the 2027 fold (train through 2027-04-30, test Jun-Nov 2027) is the
|
||||
first that could show anything.
|
||||
|
||||
Until then it serves two purposes:
|
||||
* a live cross-check of the Open-Meteo catchment mean (/api/hii/rainfall
|
||||
already exposes the raw gauges; this gives the comparable aggregate);
|
||||
* accumulating the comparison so the eventual feature evaluation has a
|
||||
documented bias/variance relationship between the two sources.
|
||||
"""
|
||||
|
||||
import logging
|
||||
from typing import Optional, Sequence, Tuple
|
||||
|
||||
import pandas as pd
|
||||
|
||||
from .data import resolve_db_url
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Same footprint as rain.CATCHMENT_POINTS: the upper Ping above P.1. Gauges
|
||||
# inside this box are averaged; there are ~130 with recent data (DWR, FOP,
|
||||
# HII, RID, TMD), far denser than the five Open-Meteo points.
|
||||
CATCHMENT_BOX: Tuple[float, float, float, float] = (18.75, 19.60, 98.60, 99.30)
|
||||
# A gauge that reports the same rain_24h for many hours is stuck; drop hours
|
||||
# where fewer than this many gauges reported at all.
|
||||
MIN_GAUGES_PER_HOUR = 5
|
||||
|
||||
|
||||
def load_gauge_mean(
|
||||
db_url: Optional[str] = None,
|
||||
start: Optional[pd.Timestamp] = None,
|
||||
end: Optional[pd.Timestamp] = None,
|
||||
box: Sequence[float] = CATCHMENT_BOX,
|
||||
engine=None,
|
||||
) -> Optional[pd.Series]:
|
||||
"""Hourly catchment-mean rain_1h (mm) across HII gauges in `box`.
|
||||
|
||||
Pass `engine` (the API's HII store engine) to reuse a pool; otherwise a
|
||||
connection is resolved from db_url / config. Returns None if the DB is
|
||||
unavailable or the table is empty. Hours with fewer than
|
||||
MIN_GAUGES_PER_HOUR reporting gauges are NaN.
|
||||
"""
|
||||
if engine is None:
|
||||
resolved = resolve_db_url(db_url)
|
||||
if not resolved:
|
||||
return None
|
||||
lat_lo, lat_hi, lon_lo, lon_hi = box
|
||||
try:
|
||||
from sqlalchemy import create_engine, text
|
||||
|
||||
query = (
|
||||
"SELECT m.timestamp, COUNT(m.rain_1h) AS n, AVG(m.rain_1h) AS rain_1h "
|
||||
"FROM hii_rainfall m JOIN hii_rain_stations s ON s.id = m.station_id "
|
||||
"WHERE s.latitude BETWEEN :lat_lo AND :lat_hi "
|
||||
"AND s.longitude BETWEEN :lon_lo AND :lon_hi "
|
||||
"AND m.rain_1h IS NOT NULL"
|
||||
)
|
||||
params = {
|
||||
"lat_lo": lat_lo,
|
||||
"lat_hi": lat_hi,
|
||||
"lon_lo": lon_lo,
|
||||
"lon_hi": lon_hi,
|
||||
}
|
||||
if start is not None:
|
||||
query += " AND m.timestamp >= :start"
|
||||
params["start"] = pd.Timestamp(start).to_pydatetime()
|
||||
if end is not None:
|
||||
query += " AND m.timestamp <= :end"
|
||||
params["end"] = pd.Timestamp(end).to_pydatetime()
|
||||
query += " GROUP BY m.timestamp ORDER BY m.timestamp"
|
||||
if engine is None:
|
||||
engine = create_engine(resolved, pool_pre_ping=True)
|
||||
with engine.connect() as conn:
|
||||
frame = pd.read_sql(text(query), conn, params=params)
|
||||
except Exception as error:
|
||||
logger.warning(f"HII gauge rain load failed: {error}")
|
||||
return None
|
||||
if frame.empty:
|
||||
return None
|
||||
frame["timestamp"] = pd.to_datetime(frame["timestamp"]).dt.floor("h")
|
||||
frame = frame.groupby("timestamp").agg(n=("n", "sum"), rain_1h=("rain_1h", "mean"))
|
||||
series = pd.to_numeric(frame["rain_1h"], errors="coerce")
|
||||
series[frame["n"] < MIN_GAUGES_PER_HOUR] = float("nan")
|
||||
series.name = "hii_gauge_mean"
|
||||
return series
|
||||
|
||||
|
||||
def compare_with_openmeteo(
|
||||
gauge: pd.Series, openmeteo: pd.Series, window_h: int = 24
|
||||
) -> dict:
|
||||
"""Bias/correlation of Open-Meteo against the gauges over the overlap.
|
||||
|
||||
Both are summed over trailing `window_h` so single-hour timing offsets
|
||||
(gauges report at :00, the model's hour is an interval) do not dominate.
|
||||
"""
|
||||
joined = pd.concat({"gauge": gauge, "openmeteo": openmeteo}, axis=1).dropna()
|
||||
if joined.empty:
|
||||
return {"overlap_hours": 0}
|
||||
g = joined["gauge"].rolling(window_h, min_periods=window_h).sum()
|
||||
o = joined["openmeteo"].rolling(window_h, min_periods=window_h).sum()
|
||||
both = pd.concat({"g": g, "o": o}, axis=1).dropna()
|
||||
if both.empty:
|
||||
return {"overlap_hours": int(len(joined))}
|
||||
return {
|
||||
"overlap_hours": int(len(joined)),
|
||||
"window_h": window_h,
|
||||
"gauge_mean_mm": float(both["g"].mean()),
|
||||
"openmeteo_mean_mm": float(both["o"].mean()),
|
||||
"bias_mm": float((both["o"] - both["g"]).mean()),
|
||||
"mae_mm": float((both["o"] - both["g"]).abs().mean()),
|
||||
"corr": float(both["g"].corr(both["o"])),
|
||||
}
|
||||
+7
-5
@@ -182,14 +182,18 @@ def _model_forecast(
|
||||
)
|
||||
p_warning = _sigmoid_probability(predicted_max, warn_thr, sigma_h)
|
||||
if warn_head is not None:
|
||||
p_warning = max(p_warning, float(warn_head.predict_proba(feature_row)[0][1]))
|
||||
p_warning = max(
|
||||
p_warning, float(warn_head.predict_proba(feature_row)[0][1])
|
||||
)
|
||||
|
||||
danger_head = (
|
||||
None if thresholds_stale else bundle["heads"].get(f"danger_{horizon_h}")
|
||||
)
|
||||
p_danger = _sigmoid_probability(predicted_max, danger_thr, sigma_h)
|
||||
if danger_head is not None:
|
||||
p_danger = max(p_danger, float(danger_head.predict_proba(feature_row)[0][1]))
|
||||
p_danger = max(
|
||||
p_danger, float(danger_head.predict_proba(feature_row)[0][1])
|
||||
)
|
||||
|
||||
p_warning = _clip_probability(p_warning)
|
||||
p_danger = min(_clip_probability(p_danger), p_warning)
|
||||
@@ -400,6 +404,4 @@ def get_latest_forecasts(
|
||||
logger.warning("dam state unavailable; dam features will be NaN")
|
||||
dam = pd.DataFrame()
|
||||
|
||||
return get_forecasts(
|
||||
readings_by_station, models_dir=models_dir, rain=rain, dam=dam
|
||||
)
|
||||
return get_forecasts(readings_by_station, models_dir=models_dir, rain=rain, dam=dam)
|
||||
|
||||
+4
-9
@@ -121,12 +121,8 @@ def load_history(
|
||||
cursor = fetch_from.date()
|
||||
try:
|
||||
while cursor <= end:
|
||||
chunk_end = min(
|
||||
datetime.date(cursor.year, 12, 31), end
|
||||
)
|
||||
chunks.append(
|
||||
fetch_history(cursor.isoformat(), chunk_end.isoformat())
|
||||
)
|
||||
chunk_end = min(datetime.date(cursor.year, 12, 31), end)
|
||||
chunks.append(fetch_history(cursor.isoformat(), chunk_end.isoformat()))
|
||||
cursor = datetime.date(cursor.year + 1, 1, 1)
|
||||
except Exception as error:
|
||||
logger.warning(f"Open-Meteo history fetch failed: {error}")
|
||||
@@ -174,7 +170,7 @@ def backfill_db(engine, db_type: str, chunk_rows: int = 5000) -> int:
|
||||
return 0
|
||||
total = 0
|
||||
for start in range(0, len(history), chunk_rows):
|
||||
part = history.iloc[start: start + chunk_rows]
|
||||
part = history.iloc[start : start + chunk_rows]
|
||||
total += save_to_db(part, engine, db_type)
|
||||
logger.info(f"openmeteo_rain backfill: {total}/{len(history)} rows")
|
||||
return total
|
||||
@@ -204,8 +200,7 @@ def save_to_db(df: pd.DataFrame, engine, db_type: str) -> int:
|
||||
cols = ["timestamp"] + point_cols + ["catchment_mean"]
|
||||
placeholders = ", ".join(f":{c}" for c in cols)
|
||||
updates = ", ".join(
|
||||
f"{c} = "
|
||||
+ (f"VALUES({c})" if db_type == "mysql" else f"EXCLUDED.{c}")
|
||||
f"{c} = " + (f"VALUES({c})" if db_type == "mysql" else f"EXCLUDED.{c}")
|
||||
for c in cols[1:]
|
||||
)
|
||||
if db_type == "mysql":
|
||||
|
||||
+170
@@ -0,0 +1,170 @@
|
||||
"""Live forecast skill: what the deployed model said versus what the river did.
|
||||
|
||||
Every hour the precompute stores the issued 24 h forecast (forecast_history);
|
||||
water_measurements holds what actually happened. Joining the two gives a
|
||||
verification that needs no retraining and answers the question the dashboard
|
||||
is asked most: "is the model getting better?" — per model version, on the
|
||||
hours that version was actually serving.
|
||||
|
||||
Metrics per version and horizon:
|
||||
n verified forecasts (issued, and the horizon has since elapsed)
|
||||
mae |predicted_max - observed_max| over the horizon window, metres
|
||||
bias mean(predicted - observed): >0 over-predicts the peak
|
||||
persistence MAE of the trivial "peak = current level" forecast on the
|
||||
same rows; a model is only useful if it beats this
|
||||
skill 1 - mae/persistence (0 = no better than persistence, 1 = perfect)
|
||||
above_2m same MAE restricted to rows where the observed peak >= 2 m,
|
||||
i.e. the flood-relevant regime
|
||||
|
||||
Only the P.1 gauge is verified by default: it is the one the city threshold
|
||||
is keyed to, and one station keeps the query cheap enough to run on request.
|
||||
"""
|
||||
|
||||
import datetime
|
||||
import logging
|
||||
from typing import Dict, List, Optional
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
DEFAULT_STATION = "P.1"
|
||||
DEFAULT_HORIZON = 24
|
||||
MIN_VERIFIED = 24 # fewer than a day of verified hours is not a number
|
||||
|
||||
|
||||
def _sql_for(db_type: str) -> str:
|
||||
"""Join each issued forecast to the observed max over (as_of, as_of + h]."""
|
||||
if db_type == "postgresql":
|
||||
window_end = "f.as_of + (f.horizon_hours || ' hours')::interval"
|
||||
elif db_type == "mysql":
|
||||
window_end = "DATE_ADD(f.as_of, INTERVAL f.horizon_hours HOUR)"
|
||||
else: # sqlite
|
||||
window_end = "datetime(f.as_of, '+' || f.horizon_hours || ' hours')"
|
||||
return f"""
|
||||
SELECT f.as_of, f.model_version, f.predicted_max_level, f.current_level,
|
||||
(SELECT MAX(m.water_level) FROM water_measurements m
|
||||
JOIN stations s ON s.id = m.station_id
|
||||
WHERE s.station_code = f.station_code
|
||||
AND m.timestamp > f.as_of AND m.timestamp <= {window_end}) AS observed_max,
|
||||
(SELECT COUNT(m.water_level) FROM water_measurements m
|
||||
JOIN stations s ON s.id = m.station_id
|
||||
WHERE s.station_code = f.station_code
|
||||
AND m.timestamp > f.as_of AND m.timestamp <= {window_end}) AS observed_n
|
||||
FROM forecast_history f
|
||||
WHERE f.station_code = :code AND f.horizon_hours = :horizon
|
||||
AND f.source = 'model' AND f.predicted_max_level IS NOT NULL
|
||||
AND f.as_of <= :verifiable_before
|
||||
ORDER BY f.as_of
|
||||
"""
|
||||
|
||||
|
||||
def compute_skill(
|
||||
engine,
|
||||
db_type: str,
|
||||
station_code: str = DEFAULT_STATION,
|
||||
horizon_hours: int = DEFAULT_HORIZON,
|
||||
now: Optional[datetime.datetime] = None,
|
||||
) -> Dict:
|
||||
"""Per-model-version verification of issued forecasts against observations."""
|
||||
from sqlalchemy import text
|
||||
|
||||
now = now or datetime.datetime.now()
|
||||
verifiable_before = now - datetime.timedelta(hours=horizon_hours)
|
||||
with engine.connect() as conn:
|
||||
rows = [
|
||||
dict(r._mapping)
|
||||
for r in conn.execute(
|
||||
text(_sql_for(db_type)),
|
||||
{
|
||||
"code": station_code,
|
||||
"horizon": horizon_hours,
|
||||
"verifiable_before": verifiable_before,
|
||||
},
|
||||
)
|
||||
]
|
||||
|
||||
def _ts(value):
|
||||
# sqlite hands back strings; postgres/mysql give datetimes
|
||||
if isinstance(value, datetime.datetime):
|
||||
return value
|
||||
return datetime.datetime.fromisoformat(str(value).replace(" ", "T"))
|
||||
|
||||
by_version: Dict[str, List[dict]] = {}
|
||||
for r in rows:
|
||||
r["as_of"] = _ts(r["as_of"])
|
||||
# need most of the window observed, or the "max" is not the peak
|
||||
if r["observed_max"] is None or (r["observed_n"] or 0) < horizon_hours * 0.75:
|
||||
continue
|
||||
by_version.setdefault(r["model_version"] or "unknown", []).append(r)
|
||||
|
||||
versions = []
|
||||
for version, vrows in by_version.items():
|
||||
pred = [float(r["predicted_max_level"]) for r in vrows]
|
||||
obs = [float(r["observed_max"]) for r in vrows]
|
||||
cur = [
|
||||
float(r["current_level"]) if r["current_level"] is not None else None
|
||||
for r in vrows
|
||||
]
|
||||
err = [p - o for p, o in zip(pred, obs)]
|
||||
mae = sum(abs(e) for e in err) / len(err)
|
||||
bias = sum(err) / len(err)
|
||||
pers_rows = [(c, o) for c, o in zip(cur, obs) if c is not None]
|
||||
persistence = (
|
||||
sum(abs(c - o) for c, o in pers_rows) / len(pers_rows)
|
||||
if pers_rows
|
||||
else None
|
||||
)
|
||||
high = [(p, o) for p, o in zip(pred, obs) if o >= 2.0]
|
||||
versions.append(
|
||||
{
|
||||
"model_version": version,
|
||||
"first_issued": min(r["as_of"] for r in vrows).isoformat(),
|
||||
"last_issued": max(r["as_of"] for r in vrows).isoformat(),
|
||||
"n": len(vrows),
|
||||
"mae_m": round(mae, 3),
|
||||
"bias_m": round(bias, 3),
|
||||
"persistence_mae_m": (
|
||||
None if persistence is None else round(persistence, 3)
|
||||
),
|
||||
"skill": (
|
||||
None if not persistence else round(1.0 - mae / persistence, 3)
|
||||
),
|
||||
"above_2m_n": len(high),
|
||||
"above_2m_mae_m": (
|
||||
round(sum(abs(p - o) for p, o in high) / len(high), 3)
|
||||
if high
|
||||
else None
|
||||
),
|
||||
"enough_data": len(vrows) >= MIN_VERIFIED,
|
||||
}
|
||||
)
|
||||
versions.sort(key=lambda v: v["first_issued"])
|
||||
|
||||
# Headline: current version vs the previous one that had enough data
|
||||
current = versions[-1] if versions else None
|
||||
previous = (
|
||||
next((v for v in reversed(versions[:-1]) if v["enough_data"]), None)
|
||||
if versions
|
||||
else None
|
||||
)
|
||||
trend = None
|
||||
if current and previous and current["enough_data"]:
|
||||
trend = {
|
||||
"previous_version": previous["model_version"],
|
||||
"mae_delta_m": round(current["mae_m"] - previous["mae_m"], 3),
|
||||
"skill_delta": (
|
||||
None
|
||||
if current["skill"] is None or previous["skill"] is None
|
||||
else round(current["skill"] - previous["skill"], 3)
|
||||
),
|
||||
"better": current["mae_m"] < previous["mae_m"],
|
||||
}
|
||||
|
||||
return {
|
||||
"station_code": station_code,
|
||||
"horizon_hours": horizon_hours,
|
||||
"verified_until": verifiable_before.isoformat(),
|
||||
"min_verified": MIN_VERIFIED,
|
||||
"versions": versions,
|
||||
"current": current,
|
||||
"trend": trend,
|
||||
}
|
||||
+53
-15
@@ -45,6 +45,15 @@ MIN_SIGMA = 0.15
|
||||
MIN_ROWS_TO_TRAIN = 200
|
||||
MIN_ROWS_FOR_HEAD = 50
|
||||
|
||||
|
||||
class RainUnavailableError(RuntimeError):
|
||||
"""Raised when a rain-enabled training run cannot obtain the rain series.
|
||||
|
||||
Training would otherwise fall through to gauge-only (v2) bundles and
|
||||
overwrite the deployed v3 artifacts without anyone noticing.
|
||||
"""
|
||||
|
||||
|
||||
HGB_PARAMS = {
|
||||
"max_iter": 300,
|
||||
"learning_rate": 0.06,
|
||||
@@ -311,9 +320,9 @@ def train_station(
|
||||
skipped_heads,
|
||||
)
|
||||
else:
|
||||
skipped_heads[
|
||||
head_key
|
||||
] = f"only {n_pos} positives in train span (< {MIN_POSITIVES_FOR_CLASSIFIER})"
|
||||
skipped_heads[head_key] = (
|
||||
f"only {n_pos} positives in train span (< {MIN_POSITIVES_FOR_CLASSIFIER})"
|
||||
)
|
||||
heads[head_key] = clf
|
||||
|
||||
if not skip_eval:
|
||||
@@ -408,9 +417,9 @@ def train_station(
|
||||
if clf is not None:
|
||||
skipped_heads.pop(head_key, None)
|
||||
else:
|
||||
skipped_heads[
|
||||
head_key
|
||||
] = f"only {n_pos} positives in train span (< {MIN_POSITIVES_FOR_CLASSIFIER})"
|
||||
skipped_heads[head_key] = (
|
||||
f"only {n_pos} positives in train span (< {MIN_POSITIVES_FOR_CLASSIFIER})"
|
||||
)
|
||||
final_heads[head_key] = None
|
||||
|
||||
# v4 = + Mae Ngat dam features; v3 = rise + rain; v2 = rise target only
|
||||
@@ -456,8 +465,13 @@ def train_all(
|
||||
models_dir = Path(models_dir)
|
||||
models_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# Catchment rain (Open-Meteo archive, 2021+). Optional: without it the
|
||||
# models train as v2 (no rain columns) and still serve correctly.
|
||||
# Catchment rain (Open-Meteo archive, 2021+). A rain-less run produces v2
|
||||
# bundles that serve fine but have measurably less flood lead (the 2024
|
||||
# record flood: 13 h early with rain vs 18 h late without). The 2026-09-01
|
||||
# server retrain hit exactly that -- the archive fetch failed on a checkout
|
||||
# with no models/cache/ and the run quietly wrote v2 over v3. So the
|
||||
# downgrade is now an error unless the caller opts out with use_rain=False
|
||||
# (the --no-rain flag), which is the only way to get v2 deliberately.
|
||||
rain_series = None
|
||||
if use_rain:
|
||||
try:
|
||||
@@ -465,7 +479,19 @@ def train_all(
|
||||
|
||||
rain_series = rain_mod.catchment_mean(rain_mod.load_history())
|
||||
except Exception as error:
|
||||
logger.warning(f"rain history unavailable, training without it: {error}")
|
||||
raise RainUnavailableError(
|
||||
f"rain history unavailable ({error}); refusing to silently "
|
||||
"downgrade to v2 bundles -- fix Open-Meteo access or restore "
|
||||
"models/cache/rain_openmeteo.csv.gz, or pass --no-rain to "
|
||||
"train gauge-only bundles on purpose"
|
||||
) from error
|
||||
if rain_series is None:
|
||||
raise RainUnavailableError(
|
||||
"rain history unavailable (Open-Meteo archive unreachable and "
|
||||
"no models/cache/rain_openmeteo.csv.gz); refusing to silently "
|
||||
"downgrade to v2 bundles -- fix access, restore the cache file, "
|
||||
"or pass --no-rain to train gauge-only bundles on purpose"
|
||||
)
|
||||
if rain_series is not None:
|
||||
logger.info(
|
||||
f"rain series: {rain_series.index.min()} .. {rain_series.index.max()}"
|
||||
@@ -493,9 +519,7 @@ def train_all(
|
||||
"training v3-style bundles WITHOUT dam features"
|
||||
)
|
||||
if dam_frame is not None:
|
||||
logger.info(
|
||||
f"dam series: {dam_frame.index.min()} .. {dam_frame.index.max()}"
|
||||
)
|
||||
logger.info(f"dam series: {dam_frame.index.min()} .. {dam_frame.index.max()}")
|
||||
|
||||
# Run-level version: v4 only if some requested station actually receives
|
||||
# dam columns (they are gated to DAM_STATIONS; per-bundle versions are
|
||||
@@ -584,7 +608,9 @@ def main(argv: Optional[List[str]] = None) -> None:
|
||||
parser.add_argument(
|
||||
"--no-rain",
|
||||
action="store_true",
|
||||
help="train without the Open-Meteo rain features (v2-style bundles)",
|
||||
help="DELIBERATELY train without the Open-Meteo rain features "
|
||||
"(v2-style bundles). Without this flag a missing rain series aborts "
|
||||
"the run instead of quietly downgrading the deployed model",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--dam",
|
||||
@@ -627,9 +653,21 @@ def main(argv: Optional[List[str]] = None) -> None:
|
||||
1 for s in metrics_payload["stations"].values() if s["status"] == "trained"
|
||||
)
|
||||
logger.info(
|
||||
f"Done: {trained}/{len(stations)} stations trained. metrics.json written to {args.models_dir}"
|
||||
f"Done: {trained}/{len(stations)} stations trained "
|
||||
f"({metrics_payload['model_version']}). "
|
||||
f"metrics.json written to {args.models_dir}"
|
||||
)
|
||||
|
||||
|
||||
def cli() -> int:
|
||||
"""Console entry: RainUnavailableError becomes a one-line error, exit 2."""
|
||||
try:
|
||||
main()
|
||||
except RainUnavailableError as error:
|
||||
logger.error(str(error))
|
||||
return 2
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
raise SystemExit(cli())
|
||||
|
||||
+454
@@ -0,0 +1,454 @@
|
||||
"""Public flood notifications over ntfy.
|
||||
|
||||
Runs once per collection cycle inside the API process (leader only), right
|
||||
after the forecast precompute, so it sees the same readings and forecasts the
|
||||
dashboard shows. Publishes to a self-hosted ntfy server; anyone subscribes to
|
||||
a topic from the free app or a browser, no account needed.
|
||||
|
||||
Topics (all under one configurable prefix, default "ping"):
|
||||
|
||||
{prefix}-{station}-warning observed level crossed the station's warning threshold
|
||||
{prefix}-{station}-danger observed level crossed the danger threshold
|
||||
{prefix}-warning any station crossed warning (basin-wide digest)
|
||||
{prefix}-danger any station crossed danger
|
||||
{prefix}-p1-outlook model early warning for Chiang Mai city: P.1's 24 h
|
||||
warning probability crossed the alert level (opt-in;
|
||||
the forecast is experimental and says so)
|
||||
{prefix}-status feed/monitor health: data stale, recovered
|
||||
|
||||
Each notification is a TRANSITION, not a state: crossing UP into a level sends
|
||||
one message; dropping back below (with hysteresis) sends an all-clear. While
|
||||
the river sits above a threshold nothing is repeated, so a subscriber in a
|
||||
flood gets a handful of messages, not one an hour. The per-topic state is
|
||||
persisted (notification_state table) so a restart never re-sends.
|
||||
|
||||
Everything is fail-safe: ntfy unreachable, table missing, malformed
|
||||
reading -> a logged warning, never an exception into the collection loop.
|
||||
"""
|
||||
|
||||
import datetime
|
||||
import logging
|
||||
from dataclasses import dataclass
|
||||
from typing import Dict, Iterable, List, Optional
|
||||
|
||||
import requests
|
||||
|
||||
from .ml import features
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# Hysteresis: an all-clear needs the level this far BELOW the threshold, so a
|
||||
# river bobbing around 3.70 m does not toggle warning/clear every hour.
|
||||
CLEAR_MARGIN_M = 0.10
|
||||
# Capacity guard. The level thresholds in features.THRESHOLDS were calibrated
|
||||
# from RID's discharge_percent (% of channel capacity); if RID re-rates a
|
||||
# gauge or moves its datum, the level crosses while capacity says the channel
|
||||
# is nearly empty (P.77, 2026-09: 3.0 m "warning" at 22 %). A crossing is
|
||||
# only announced when the reported capacity agrees that the river is high.
|
||||
# P.1 is exempt: its stages come from the municipal inundation map, not from
|
||||
# capacity. Readings without a capacity figure fall back to level only.
|
||||
CAPACITY_GUARD_MIN_PCT = 60.0
|
||||
CAPACITY_GUARD_EXEMPT = {"P.1"}
|
||||
# Outlook alert fires when p_warning(24h) rises through ON, clears below OFF.
|
||||
OUTLOOK_ON = 0.50
|
||||
OUTLOOK_OFF = 0.25
|
||||
# Below this the outlook is not announced at all (avoid "5 % chance" noise).
|
||||
OUTLOOK_HORIZON = 24
|
||||
|
||||
STATION_NAMES: Dict[str, str] = {
|
||||
"P.1": "Nawarat Bridge, Chiang Mai city",
|
||||
"P.103": "Ring Road Bridge 3, Chiang Mai",
|
||||
"P.67": "Ban Tae (Mae Taeng)",
|
||||
"P.21": "Ban Rim Tai (Mae Rim)",
|
||||
"P.75": "Ban Chai Lat",
|
||||
"P.92": "Ban Muang Aut",
|
||||
"P.20": "Ban Chiang Dao",
|
||||
"P.4A": "Ban Mae Taeng",
|
||||
"P.5": "Tha Nang Bridge (downstream)",
|
||||
"P.81": "Ban Pong (downstream)",
|
||||
"P.82": "Ban Sob Win",
|
||||
"P.84": "Ban Panton",
|
||||
"P.87": "Ban Pa Sang",
|
||||
"P.77": "Ban Sop Mae Sapuat",
|
||||
"P.85": "Ban Lai Kaew",
|
||||
"P.76": "Ban Mae I Hai",
|
||||
}
|
||||
|
||||
|
||||
def _slug(code: str) -> str:
|
||||
return code.lower().replace(".", "")
|
||||
|
||||
|
||||
@dataclass
|
||||
class Notification:
|
||||
topic: str
|
||||
title: str
|
||||
message: str
|
||||
priority: int = 3 # ntfy: 1 min .. 5 max
|
||||
tags: Optional[List[str]] = None
|
||||
click: Optional[str] = None
|
||||
|
||||
|
||||
class NtfyPublisher:
|
||||
def __init__(
|
||||
self,
|
||||
server: str,
|
||||
prefix: str = "ping",
|
||||
token: Optional[str] = None,
|
||||
dashboard_url: str = "https://water.buildfor.life/",
|
||||
timeout: int = 10,
|
||||
):
|
||||
self.server = server.rstrip("/")
|
||||
self.prefix = prefix
|
||||
self.token = token
|
||||
self.dashboard_url = dashboard_url
|
||||
self.timeout = timeout
|
||||
|
||||
def topic(self, *parts: str) -> str:
|
||||
return "-".join([self.prefix, *parts])
|
||||
|
||||
def publish(self, n: Notification) -> bool:
|
||||
headers = {
|
||||
"Title": n.title,
|
||||
"Priority": str(n.priority),
|
||||
"Click": n.click or self.dashboard_url,
|
||||
"Actions": f"view, Open dashboard, {n.click or self.dashboard_url}",
|
||||
}
|
||||
if n.tags:
|
||||
headers["Tags"] = ",".join(n.tags)
|
||||
if self.token:
|
||||
headers["Authorization"] = f"Bearer {self.token}"
|
||||
try:
|
||||
r = requests.post(
|
||||
f"{self.server}/{n.topic}",
|
||||
data=n.message.encode("utf-8"),
|
||||
headers=headers,
|
||||
timeout=self.timeout,
|
||||
)
|
||||
if r.status_code >= 300:
|
||||
logger.warning(f"ntfy {n.topic}: HTTP {r.status_code} {r.text[:120]}")
|
||||
return False
|
||||
return True
|
||||
except Exception as error:
|
||||
logger.warning(f"ntfy {n.topic}: {error}")
|
||||
return False
|
||||
|
||||
|
||||
class NotificationState:
|
||||
"""Per-key last-sent state, in the monitor's own SQL database."""
|
||||
|
||||
def __init__(self, engine, db_type: str):
|
||||
self.engine = engine
|
||||
self.db_type = db_type
|
||||
self._ensure()
|
||||
|
||||
def _ensure(self) -> None:
|
||||
from sqlalchemy import text
|
||||
|
||||
ddl = (
|
||||
"CREATE TABLE IF NOT EXISTS notification_state ("
|
||||
"key VARCHAR(64) PRIMARY KEY, state VARCHAR(16) NOT NULL, "
|
||||
"value NUMERIC(8,3), updated_at TIMESTAMP NOT NULL)"
|
||||
)
|
||||
try:
|
||||
with self.engine.begin() as conn:
|
||||
conn.execute(text(ddl))
|
||||
except Exception as error:
|
||||
# Postgres: two sessions racing CREATE TABLE IF NOT EXISTS can
|
||||
# both pass the existence check; the loser fails with a unique
|
||||
# violation on pg_type. The table exists either way; verify.
|
||||
with self.engine.connect() as conn:
|
||||
conn.execute(text("SELECT 1 FROM notification_state WHERE 1=0"))
|
||||
logger.debug(f"notification_state DDL raced, table present: {error}")
|
||||
|
||||
def get(self, key: str) -> Optional[str]:
|
||||
from sqlalchemy import text
|
||||
|
||||
with self.engine.connect() as conn:
|
||||
row = conn.execute(
|
||||
text("SELECT state FROM notification_state WHERE key = :k"), {"k": key}
|
||||
).fetchone()
|
||||
return row[0] if row else None
|
||||
|
||||
def set(self, key: str, state: str, value: Optional[float] = None) -> None:
|
||||
from sqlalchemy import text
|
||||
|
||||
now = datetime.datetime.now()
|
||||
with self.engine.begin() as conn:
|
||||
if self.db_type == "mysql":
|
||||
sql = (
|
||||
"INSERT INTO notification_state (key, state, value, updated_at) "
|
||||
"VALUES (:k, :s, :v, :t) ON DUPLICATE KEY UPDATE "
|
||||
"state = VALUES(state), value = VALUES(value), updated_at = VALUES(updated_at)"
|
||||
)
|
||||
else:
|
||||
sql = (
|
||||
"INSERT INTO notification_state (key, state, value, updated_at) "
|
||||
"VALUES (:k, :s, :v, :t) ON CONFLICT (key) DO UPDATE SET "
|
||||
"state = EXCLUDED.state, value = EXCLUDED.value, updated_at = EXCLUDED.updated_at"
|
||||
)
|
||||
conn.execute(text(sql), {"k": key, "s": state, "v": value, "t": now})
|
||||
|
||||
|
||||
class InMemoryState(NotificationState):
|
||||
"""For tests and when no SQL engine is available (loses state on restart)."""
|
||||
|
||||
def __init__(self): # noqa: D107 - intentionally skips the SQL parent
|
||||
self._d: Dict[str, str] = {}
|
||||
|
||||
def get(self, key: str) -> Optional[str]:
|
||||
return self._d.get(key)
|
||||
|
||||
def set(self, key: str, state: str, value: Optional[float] = None) -> None:
|
||||
self._d[key] = state
|
||||
|
||||
|
||||
def _level_state(level: float, warn: float, danger: float, prev: Optional[str]) -> str:
|
||||
"""'clear' | 'warning' | 'danger', with hysteresis on the way down."""
|
||||
if level >= danger:
|
||||
return "danger"
|
||||
if level >= warn:
|
||||
# from danger: stay 'danger' until below danger - margin
|
||||
if prev == "danger" and level >= danger - CLEAR_MARGIN_M:
|
||||
return "danger"
|
||||
return "warning"
|
||||
if prev in ("warning", "danger") and level >= warn - CLEAR_MARGIN_M:
|
||||
return "warning"
|
||||
return "clear"
|
||||
|
||||
|
||||
def evaluate(
|
||||
readings: Iterable[dict],
|
||||
forecasts: Iterable[dict],
|
||||
state: NotificationState,
|
||||
publisher: NtfyPublisher,
|
||||
stale_after_h: float = 3.0,
|
||||
now: Optional[datetime.datetime] = None,
|
||||
) -> List[Notification]:
|
||||
"""Compare current readings/forecasts with last-sent state; publish transitions.
|
||||
|
||||
readings: rows with station_code, water_level, timestamp (latest per station)
|
||||
forecasts: /forecast rows (station_code, horizon_hours, p_warning, predicted_max_level)
|
||||
Returns the notifications that were published (for logs/tests).
|
||||
"""
|
||||
now = now or datetime.datetime.now()
|
||||
sent: List[Notification] = []
|
||||
|
||||
def emit(n: Notification) -> bool:
|
||||
ok = publisher.publish(n)
|
||||
if ok:
|
||||
sent.append(n)
|
||||
return ok
|
||||
|
||||
# ---- observed levels, per station, plus basin-wide fan-out
|
||||
basin_changes: Dict[str, List[str]] = {"warning": [], "danger": [], "clear": []}
|
||||
latest_ts: Optional[datetime.datetime] = None
|
||||
for r in readings:
|
||||
code = r.get("station_code")
|
||||
level = r.get("water_level")
|
||||
if not code or level is None:
|
||||
continue
|
||||
try:
|
||||
level = float(level)
|
||||
except (TypeError, ValueError):
|
||||
continue
|
||||
ts = r.get("timestamp")
|
||||
if isinstance(ts, str):
|
||||
try:
|
||||
ts = datetime.datetime.fromisoformat(ts)
|
||||
except ValueError:
|
||||
ts = None
|
||||
if isinstance(ts, datetime.datetime) and (latest_ts is None or ts > latest_ts):
|
||||
latest_ts = ts
|
||||
warn, danger = features.get_thresholds(code)
|
||||
key = f"level:{code}"
|
||||
prev = state.get(key) or "clear"
|
||||
cur = _level_state(level, warn, danger, prev)
|
||||
pct = r.get("discharge_percent")
|
||||
if (
|
||||
cur != "clear"
|
||||
and prev == "clear"
|
||||
and code not in CAPACITY_GUARD_EXEMPT
|
||||
and pct is not None
|
||||
):
|
||||
try:
|
||||
if float(pct) < CAPACITY_GUARD_MIN_PCT:
|
||||
logger.info(
|
||||
f"{code}: level {level:.2f} m >= {warn:.2f} but only "
|
||||
f"{float(pct):.0f}% capacity; threshold looks stale, not alerting"
|
||||
)
|
||||
continue
|
||||
except (TypeError, ValueError):
|
||||
pass
|
||||
if cur == prev:
|
||||
continue
|
||||
name = STATION_NAMES.get(code, code)
|
||||
slug = _slug(code)
|
||||
when = (
|
||||
ts.strftime("%d %b %H:%M") if isinstance(ts, datetime.datetime) else "now"
|
||||
)
|
||||
if cur == "danger":
|
||||
ok = emit(
|
||||
Notification(
|
||||
publisher.topic(slug, "danger"),
|
||||
f"DANGER level at {code}",
|
||||
f"{name}: {level:.2f} m at {when}, above the danger level of {danger:.2f} m.",
|
||||
priority=5,
|
||||
tags=["rotating_light", code],
|
||||
)
|
||||
)
|
||||
basin_changes["danger"].append(f"{code} {level:.2f} m")
|
||||
elif cur == "warning":
|
||||
if prev == "danger":
|
||||
ok = emit(
|
||||
Notification(
|
||||
publisher.topic(slug, "danger"),
|
||||
f"{code} back below danger level",
|
||||
f"{name}: {level:.2f} m at {when}; still above the warning level of {warn:.2f} m.",
|
||||
priority=3,
|
||||
tags=["arrow_down", code],
|
||||
)
|
||||
)
|
||||
basin_changes["clear"].append(f"{code} below danger ({level:.2f} m)")
|
||||
else:
|
||||
ok = emit(
|
||||
Notification(
|
||||
publisher.topic(slug, "warning"),
|
||||
f"Warning level at {code}",
|
||||
f"{name}: {level:.2f} m at {when}, above the warning level of {warn:.2f} m.",
|
||||
priority=4,
|
||||
tags=["warning", code],
|
||||
)
|
||||
)
|
||||
basin_changes["warning"].append(f"{code} {level:.2f} m")
|
||||
else: # clear
|
||||
ok = emit(
|
||||
Notification(
|
||||
publisher.topic(slug, "warning"),
|
||||
f"{code} back to normal",
|
||||
f"{name}: {level:.2f} m at {when}, below the warning level of {warn:.2f} m.",
|
||||
priority=2,
|
||||
tags=["white_check_mark", code],
|
||||
)
|
||||
)
|
||||
basin_changes["clear"].append(f"{code} normal ({level:.2f} m)")
|
||||
# Only remember the transition once it was actually delivered: if ntfy
|
||||
# was down, the next cycle retries instead of silently swallowing a
|
||||
# flood crossing.
|
||||
if ok:
|
||||
state.set(key, cur, level)
|
||||
|
||||
if basin_changes["danger"]:
|
||||
emit(
|
||||
Notification(
|
||||
publisher.topic("danger"),
|
||||
"Ping River: danger level reached",
|
||||
"; ".join(basin_changes["danger"]),
|
||||
priority=5,
|
||||
tags=["rotating_light"],
|
||||
)
|
||||
)
|
||||
if basin_changes["warning"]:
|
||||
emit(
|
||||
Notification(
|
||||
publisher.topic("warning"),
|
||||
"Ping River: warning level reached",
|
||||
"; ".join(basin_changes["warning"]),
|
||||
priority=4,
|
||||
tags=["warning"],
|
||||
)
|
||||
)
|
||||
if basin_changes["clear"]:
|
||||
emit(
|
||||
Notification(
|
||||
publisher.topic("warning"),
|
||||
"Ping River: levels falling",
|
||||
"; ".join(basin_changes["clear"]),
|
||||
priority=2,
|
||||
tags=["white_check_mark"],
|
||||
)
|
||||
)
|
||||
|
||||
# ---- model outlook for the city gauge (opt-in topic, experimental)
|
||||
p1 = next(
|
||||
(
|
||||
f
|
||||
for f in forecasts
|
||||
if f.get("station_code") == "P.1"
|
||||
and f.get("horizon_hours") == OUTLOOK_HORIZON
|
||||
and f.get("source") == "model"
|
||||
),
|
||||
None,
|
||||
)
|
||||
if p1 and p1.get("p_warning") is not None:
|
||||
p = float(p1["p_warning"])
|
||||
key = "outlook:P.1"
|
||||
prev = state.get(key) or "off"
|
||||
cur = (
|
||||
"on" if (p >= OUTLOOK_ON or (prev == "on" and p >= OUTLOOK_OFF)) else "off"
|
||||
)
|
||||
if cur != prev:
|
||||
peak = p1.get("predicted_max_level")
|
||||
warn, _ = features.get_thresholds("P.1")
|
||||
if cur == "on":
|
||||
ok = emit(
|
||||
Notification(
|
||||
publisher.topic("p1-outlook"),
|
||||
"Early warning: Chiang Mai flood risk rising",
|
||||
f"The forecast model gives a {p * 100:.0f}% chance that Nawarat Bridge (P.1) "
|
||||
f"reaches {warn:.2f} m within 24 h"
|
||||
+ (
|
||||
f" (expected peak {float(peak):.2f} m)"
|
||||
if peak is not None
|
||||
else ""
|
||||
)
|
||||
+ ". Experimental model output, not an official warning; "
|
||||
"follow ThaiWater/TMD for official alerts.",
|
||||
priority=4,
|
||||
tags=["crystal_ball"],
|
||||
)
|
||||
)
|
||||
else:
|
||||
ok = emit(
|
||||
Notification(
|
||||
publisher.topic("p1-outlook"),
|
||||
"Chiang Mai flood risk easing",
|
||||
f"The model's 24 h probability of reaching {warn:.2f} m at P.1 has dropped to {p * 100:.0f}%.",
|
||||
priority=2,
|
||||
tags=["crystal_ball"],
|
||||
)
|
||||
)
|
||||
if ok:
|
||||
state.set(key, cur, p)
|
||||
|
||||
# ---- feed health
|
||||
if latest_ts is not None:
|
||||
age_h = (now - latest_ts).total_seconds() / 3600.0
|
||||
key = "feed"
|
||||
prev = state.get(key) or "ok"
|
||||
cur = "stale" if age_h >= stale_after_h else "ok"
|
||||
if cur != prev:
|
||||
if cur == "stale":
|
||||
ok = emit(
|
||||
Notification(
|
||||
publisher.topic("status"),
|
||||
"Ping River monitor: gauge feed stale",
|
||||
f"No new readings for {age_h:.0f} h (last {latest_ts:%d %b %H:%M}). "
|
||||
"Levels and forecasts on the dashboard are not current.",
|
||||
priority=3,
|
||||
tags=["hourglass"],
|
||||
)
|
||||
)
|
||||
else:
|
||||
ok = emit(
|
||||
Notification(
|
||||
publisher.topic("status"),
|
||||
"Ping River monitor: feed recovered",
|
||||
f"Readings are current again (latest {latest_ts:%d %b %H:%M}).",
|
||||
priority=2,
|
||||
tags=["white_check_mark"],
|
||||
)
|
||||
)
|
||||
if ok:
|
||||
state.set(key, cur, age_h)
|
||||
return sent
|
||||
@@ -51,8 +51,7 @@ class PostgresHistory:
|
||||
if start >= end:
|
||||
raise ValueError("start must be before end")
|
||||
|
||||
query = text(
|
||||
"""
|
||||
query = text("""
|
||||
SELECT m.timestamp, s.station_code, m.water_level,
|
||||
m.discharge, m.discharge_percent
|
||||
FROM water_measurements m
|
||||
@@ -62,8 +61,7 @@ class PostgresHistory:
|
||||
AND m.timestamp <= :end_time
|
||||
ORDER BY m.timestamp ASC
|
||||
LIMIT :limit
|
||||
"""
|
||||
)
|
||||
""")
|
||||
with self.engine.connect() as connection:
|
||||
rows = connection.execute(
|
||||
query,
|
||||
@@ -91,9 +89,9 @@ class PostgresHistory:
|
||||
"station_code": station_code,
|
||||
"water_level": water_level,
|
||||
"discharge": discharge,
|
||||
"discharge_percent": float(row[4])
|
||||
if row[4] is not None
|
||||
else None,
|
||||
"discharge_percent": (
|
||||
float(row[4]) if row[4] is not None else None
|
||||
),
|
||||
}
|
||||
)
|
||||
return result
|
||||
|
||||
+5
-3
@@ -173,8 +173,10 @@ class RequestTracker:
|
||||
"failed_requests": self.failed_requests,
|
||||
"success_rate": self.successful_requests / self.total_requests,
|
||||
"average_response_time": self.total_response_time / self.total_requests,
|
||||
"last_request_time": self.last_request_time.isoformat()
|
||||
if self.last_request_time
|
||||
else None,
|
||||
"last_request_time": (
|
||||
self.last_request_time.isoformat()
|
||||
if self.last_request_time
|
||||
else None
|
||||
),
|
||||
"error_breakdown": dict(self.error_count_by_type),
|
||||
}
|
||||
|
||||
+17
-15
@@ -323,9 +323,11 @@ class RidReservoirStore:
|
||||
if not preserve_cols:
|
||||
return f"INSERT OR REPLACE INTO {table} ({col_list}) VALUES ({params})"
|
||||
updates = ", ".join(
|
||||
f"{c} = COALESCE(excluded.{c}, {table}.{c})"
|
||||
if c in preserve_cols
|
||||
else f"{c} = excluded.{c}"
|
||||
(
|
||||
f"{c} = COALESCE(excluded.{c}, {table}.{c})"
|
||||
if c in preserve_cols
|
||||
else f"{c} = excluded.{c}"
|
||||
)
|
||||
for c in value_cols
|
||||
)
|
||||
return (
|
||||
@@ -334,9 +336,11 @@ class RidReservoirStore:
|
||||
)
|
||||
if self.db_type == "postgresql":
|
||||
updates = ", ".join(
|
||||
f"{c} = COALESCE(EXCLUDED.{c}, {table}.{c})"
|
||||
if c in preserve_cols
|
||||
else f"{c} = EXCLUDED.{c}"
|
||||
(
|
||||
f"{c} = COALESCE(EXCLUDED.{c}, {table}.{c})"
|
||||
if c in preserve_cols
|
||||
else f"{c} = EXCLUDED.{c}"
|
||||
)
|
||||
for c in value_cols
|
||||
)
|
||||
return (
|
||||
@@ -344,9 +348,11 @@ class RidReservoirStore:
|
||||
f"ON CONFLICT ({conflict}) DO UPDATE SET {updates}"
|
||||
)
|
||||
updates = ", ".join(
|
||||
f"{c} = COALESCE(VALUES({c}), {c})"
|
||||
if c in preserve_cols
|
||||
else f"{c} = VALUES({c})"
|
||||
(
|
||||
f"{c} = COALESCE(VALUES({c}), {c})"
|
||||
if c in preserve_cols
|
||||
else f"{c} = VALUES({c})"
|
||||
)
|
||||
for c in value_cols
|
||||
)
|
||||
return (
|
||||
@@ -402,9 +408,7 @@ class RidReservoirStore:
|
||||
measure_row = {
|
||||
c: _bounded(record.get(c), _MEASURE_BOUNDS[c]) for c in measure_cols
|
||||
}
|
||||
measure_row.update(
|
||||
{"dam_id": record["dam_id"], "date": record["date"]}
|
||||
)
|
||||
measure_row.update({"dam_id": record["dam_id"], "date": record["date"]})
|
||||
measurements.append(measure_row)
|
||||
try:
|
||||
with self.engine.begin() as conn:
|
||||
@@ -495,9 +499,7 @@ def backfill(
|
||||
if not store.engine and not store.connect():
|
||||
logger.error("backfill aborted: database connection failed")
|
||||
return 0
|
||||
span = [
|
||||
start + datetime.timedelta(days=i) for i in range((end - start).days + 1)
|
||||
]
|
||||
span = [start + datetime.timedelta(days=i) for i in range((end - start).days + 1)]
|
||||
present = store.present_dates(start, end)
|
||||
targets = [d for d in span if d not in present]
|
||||
logger.info(
|
||||
|
||||
+433
-53
@@ -33,6 +33,57 @@
|
||||
--red: #cc4b37;
|
||||
--border: #dce7e3;
|
||||
--shadow: 0 16px 40px rgba(23, 57, 67, .10);
|
||||
--surface: #ffffff; /* buttons, inputs, overlays */
|
||||
--surface-2: #f1f7f5; /* hover rows, popup metrics */
|
||||
--surface-3: #f7fbfa; /* outlook box */
|
||||
--overlay: rgba(255,255,255,.93);
|
||||
--overlay-border: rgba(207,224,218,.9);
|
||||
--map-bg: #dcebea;
|
||||
--glow: rgba(56, 180, 213, .12);
|
||||
--map-filter: none;
|
||||
--chart-grid: rgba(19,43,53,.08);
|
||||
--mint-ink: #146644;
|
||||
--mint-border: #b6dfc9;
|
||||
--ok-bg: #e2f3ea; --ok-ink: #0c5138; --ok-border: #bfe3d2;
|
||||
--watch-bg: #fdf1dc; --watch-ink: #6b4a05; --watch-border: #f0d9a8;
|
||||
--danger-bg: #fbe3de; --danger-ink: #7c1d10; --danger-border: #f2c0b6;
|
||||
--demo-bg: #fdeeda; --demo-ink: #9a6200;
|
||||
color-scheme: light;
|
||||
}
|
||||
/* Dark theme: same hues, inverted lightness. Flow/rain/marker colours
|
||||
on the map are data encodings and stay identical in both themes. */
|
||||
[data-theme="dark"] {
|
||||
--ink: #e6eef1;
|
||||
--muted: #97a9b0;
|
||||
--paper: #0f1a1f;
|
||||
--card: #16252c;
|
||||
--river: #3fb3d8;
|
||||
--river-light: #5ccbe8;
|
||||
--mint: #143b2c;
|
||||
--green: #3fb07f;
|
||||
--amber: #e6a83a;
|
||||
--red: #e46a55;
|
||||
--border: #27393f;
|
||||
--shadow: 0 16px 40px rgba(0, 0, 0, .45);
|
||||
--surface: #1c2c33;
|
||||
--surface-2: #213238;
|
||||
--surface-3: #1a2a30;
|
||||
--overlay: rgba(22,37,44,.92);
|
||||
--overlay-border: rgba(64,86,94,.9);
|
||||
--map-bg: #1a262b;
|
||||
--glow: rgba(63, 179, 216, .10);
|
||||
/* OSM tiles are light; invert + rotate keeps roads/labels legible
|
||||
while the water/river overlays (drawn in SVG, unfiltered) keep
|
||||
their real colours. */
|
||||
--map-filter: invert(1) hue-rotate(180deg) brightness(.92) contrast(.9) saturate(.75);
|
||||
--chart-grid: rgba(230,238,241,.10);
|
||||
--mint-ink: #7fd7ac;
|
||||
--mint-border: #2a5c45;
|
||||
--ok-bg: #143b2c; --ok-ink: #9fe3c3; --ok-border: #2a6b4d;
|
||||
--watch-bg: #3d2f0d; --watch-ink: #f3d489; --watch-border: #6b4f14;
|
||||
--danger-bg: #421c15; --danger-ink: #ffb3a6; --danger-border: #7a2f22;
|
||||
--demo-bg: #3d2f0d; --demo-ink: #f3d489;
|
||||
color-scheme: dark;
|
||||
}
|
||||
* { box-sizing: border-box; }
|
||||
html, body { margin: 0; min-height: 100%; }
|
||||
@@ -43,7 +94,7 @@
|
||||
color: var(--ink);
|
||||
overflow-x: hidden;
|
||||
background:
|
||||
radial-gradient(circle at 8% 0%, rgba(56, 180, 213, .12), transparent 25rem),
|
||||
radial-gradient(circle at 8% 0%, var(--glow), transparent 25rem),
|
||||
var(--paper);
|
||||
/* Thai families first so Thai text uses a proper Thai face where one
|
||||
is installed (Android/iOS/Windows all ship one); Latin falls
|
||||
@@ -60,7 +111,32 @@
|
||||
html[lang="th"] body { line-break: normal; overflow-wrap: anywhere; }
|
||||
html[lang="th"] .stat-value, html[lang="th"] .flow-value { overflow-wrap: normal; }
|
||||
.lang-toggle { padding: 9px 12px; font-size: .78rem; font-weight: 800; white-space: nowrap; }
|
||||
.lang-toggle[data-active-lang="th"] { background: var(--mint); border-color: #b6dfc9; color: #146644; }
|
||||
.lang-toggle[data-active-lang="th"] { background: var(--mint); border-color: var(--mint-border); color: var(--mint-ink); }
|
||||
.theme-toggle { padding: 9px 11px; font-size: .95rem; line-height: 1; }
|
||||
.alerts-panel { margin-bottom: 14px; padding: 18px 20px; border-radius: 16px; background: var(--card); border: 1px solid var(--border); box-shadow: var(--shadow); }
|
||||
.alerts-head { display: flex; justify-content: space-between; align-items: center; gap: 12px; }
|
||||
.alerts-head h2 { margin: 0; font-size: 1.15rem; }
|
||||
.alerts-close { background: transparent; border: 0; color: var(--muted); font-size: 1.1rem; cursor: pointer; padding: 4px 8px; }
|
||||
.alerts-intro { color: var(--muted); font-size: .92rem; line-height: 1.5; margin: 8px 0 12px; }
|
||||
.alerts-server { display: flex; align-items: center; gap: 10px; flex-wrap: wrap; font-size: .9rem; margin-bottom: 12px; }
|
||||
.alerts-server code { background: var(--surface); border: 1px solid var(--border); padding: 4px 8px; border-radius: 8px; font-size: .9rem; }
|
||||
.alerts-server button { padding: 4px 10px; font-size: .8rem; }
|
||||
.alerts-grid { display: grid; grid-template-columns: repeat(auto-fill, minmax(280px, 1fr)); gap: 10px; }
|
||||
.alerts-topic { border: 1px solid var(--border); border-radius: 12px; padding: 10px 12px; background: var(--surface); display: flex; flex-direction: column; gap: 4px; }
|
||||
.alerts-topic .name { font-weight: 600; font-size: .95rem; }
|
||||
.alerts-topic .desc { color: var(--muted); font-size: .82rem; line-height: 1.4; }
|
||||
.alerts-topic .row { display: flex; align-items: center; gap: 8px; margin-top: 4px; flex-wrap: wrap; }
|
||||
.alerts-topic code { font-size: .82rem; background: var(--card); border: 1px solid var(--border); padding: 2px 6px; border-radius: 6px; }
|
||||
.alerts-topic a { font-size: .82rem; }
|
||||
.alerts-topic.danger { border-color: rgba(220, 38, 38, .45); }
|
||||
.alerts-topic.outlook { border-style: dashed; }
|
||||
.alerts-foot { color: var(--muted); font-size: .82rem; margin: 12px 0 0; line-height: 1.6; }
|
||||
.alerts-disclaimer { display: block; margin-top: 4px; }
|
||||
.leaflet-popup-content-wrapper, .leaflet-popup-tip { background: var(--card); color: var(--ink); }
|
||||
.leaflet-container a.leaflet-popup-close-button { color: var(--muted); }
|
||||
.leaflet-bar a, .leaflet-control-attribution { background: var(--surface); color: var(--ink); border-color: var(--border); }
|
||||
.leaflet-control-attribution a { color: var(--river); }
|
||||
[data-theme="dark"] .leaflet-control-attribution { background: var(--overlay); }
|
||||
.shell { max-width: 1500px; margin: 0 auto; padding: 24px; }
|
||||
header {
|
||||
display: flex; align-items: center; justify-content: space-between; gap: 20px;
|
||||
@@ -78,16 +154,16 @@
|
||||
.header-actions { display: flex; align-items: center; gap: 12px; flex-wrap: wrap; }
|
||||
.live-pill {
|
||||
display: flex; gap: 8px; align-items: center; padding: 9px 13px; border-radius: 999px;
|
||||
background: var(--mint); color: #146644; font-weight: 750; font-size: .8rem;
|
||||
background: var(--mint); color: var(--mint-ink); font-weight: 750; font-size: .8rem;
|
||||
}
|
||||
.live-dot { width: 8px; height: 8px; border-radius: 50%; background: #22a66c; box-shadow: 0 0 0 5px rgba(34,166,108,.12); }
|
||||
.live-pill.demo { background: #fdeeda; color: #9a6200; }
|
||||
.live-pill.demo { background: var(--demo-bg); color: var(--demo-ink); }
|
||||
.live-pill.demo .live-dot { background: #e6a23c; box-shadow: 0 0 0 5px rgba(230,162,60,.15); }
|
||||
button {
|
||||
border: 1px solid var(--border); border-radius: 11px; background: white; color: var(--ink);
|
||||
border: 1px solid var(--border); border-radius: 11px; background: var(--surface); color: var(--ink);
|
||||
padding: 10px 14px; cursor: pointer; font-weight: 700; box-shadow: 0 3px 10px rgba(22,52,62,.05);
|
||||
}
|
||||
button:hover { border-color: #a9c4bb; transform: translateY(-1px); }
|
||||
button:hover { border-color: var(--river-light); transform: translateY(-1px); }
|
||||
button:disabled { opacity: .55; cursor: wait; transform: none; }
|
||||
.stats { display: grid; grid-template-columns: repeat(4, minmax(0,1fr)); gap: 14px; margin-bottom: 14px; }
|
||||
.stat {
|
||||
@@ -97,16 +173,31 @@
|
||||
.stat-label { color: var(--muted); text-transform: uppercase; letter-spacing: .09em; font-size: .68rem; font-weight: 800; }
|
||||
.stat-value { margin-top: 9px; font-size: 1.65rem; font-weight: 800; letter-spacing: -.04em; white-space: nowrap; }
|
||||
.stat-note { color: var(--muted); margin-top: 3px; font-size: .77rem; }
|
||||
.stat.stale { border-color: var(--red); background: rgba(204,75,55,.08); }
|
||||
.skill-panel { border: 1px solid var(--border); border-radius: 12px; padding: 12px 14px; margin-top: 14px; background: var(--surface-3); }
|
||||
.skill-head { display: flex; justify-content: space-between; align-items: baseline; gap: 12px; flex-wrap: wrap; }
|
||||
.skill-headline { margin: 8px 0 10px; font-weight: 700; font-size: .9rem; }
|
||||
.skill-headline.better { color: var(--green); }
|
||||
.skill-headline.worse { color: var(--amber); }
|
||||
.skill-table-wrap { overflow-x: auto; }
|
||||
.skill-table { border-collapse: collapse; font-size: .76rem; width: 100%; min-width: 560px; }
|
||||
.skill-table th { text-align: left; color: var(--muted); font-weight: 700; font-size: .66rem; text-transform: uppercase; letter-spacing: .06em; padding: 4px 8px; border-bottom: 1px solid var(--border); }
|
||||
.skill-table td { padding: 5px 8px; border-bottom: 1px solid var(--border); white-space: nowrap; }
|
||||
.skill-table tr.current td { font-weight: 700; }
|
||||
.skill-table td.num { text-align: right; font-variant-numeric: tabular-nums; }
|
||||
.skill-table td.dim { color: var(--muted); }
|
||||
.stat.stale .stat-value, .stat.stale .stat-note { color: var(--red); }
|
||||
.workspace { display: grid; grid-template-columns: minmax(0, 1fr) 330px; gap: 14px; min-height: 640px; }
|
||||
.map-card, .side-card { background: var(--card); border: 1px solid var(--border); border-radius: 19px; box-shadow: var(--shadow); overflow: hidden; }
|
||||
.map-card { position: relative; }
|
||||
#station-map { height: 640px; width: 100%; background: #dcebea; }
|
||||
#station-map { height: 640px; width: 100%; background: var(--map-bg); }
|
||||
.leaflet-tile-pane { filter: var(--map-filter); }
|
||||
.map-overlay {
|
||||
position: absolute; z-index: 500; top: 16px; left: 52px; right: 16px;
|
||||
display: flex; justify-content: space-between; align-items: flex-start; pointer-events: none;
|
||||
}
|
||||
.map-heading, .legend {
|
||||
background: rgba(255,255,255,.93); backdrop-filter: blur(9px); border: 1px solid rgba(207,224,218,.9);
|
||||
background: var(--overlay); backdrop-filter: blur(9px); border: 1px solid var(--overlay-border);
|
||||
border-radius: 13px; padding: 11px 13px; box-shadow: 0 7px 20px rgba(22,58,68,.12);
|
||||
pointer-events: auto; /* .map-overlay disables events; re-enable for the legend's rain toggle */
|
||||
}
|
||||
@@ -128,7 +219,7 @@
|
||||
width: 100%; display: grid; grid-template-columns: 40px minmax(0,1fr) auto; gap: 10px; align-items: center;
|
||||
padding: 11px; border: 0; border-radius: 12px; box-shadow: none; text-align: left; background: transparent;
|
||||
}
|
||||
.station-row:hover { background: #f1f7f5; transform: none; }
|
||||
.station-row:hover { background: var(--surface-2); transform: none; }
|
||||
.station-code { width: 40px; height: 40px; display: grid; place-items: center; border-radius: 11px; color: white; font-size: .68rem; font-weight: 850; }
|
||||
.station-code.long { font-size: .55rem; word-break: break-all; line-height: 1.15; padding: 2px; text-align: center; }
|
||||
.station-name { overflow: hidden; }
|
||||
@@ -137,9 +228,9 @@
|
||||
.station-name span { color: var(--muted); font-size: .68rem; margin-top: 3px; }
|
||||
.flow-value { text-align: right; font-size: .82rem; font-weight: 800; }
|
||||
.flow-value span { display: block; color: var(--muted); font-size: .61rem; font-weight: 650; margin-top: 2px; }
|
||||
.loading-panel, .error-panel { position: absolute; z-index: 600; inset: 0; display: grid; place-items: center; background: rgba(243,247,245,.88); }
|
||||
.loading-card { background: white; padding: 18px 22px; border-radius: 14px; box-shadow: var(--shadow); font-weight: 750; }
|
||||
.error-panel { display: none; color: #8d2f22; text-align: center; padding: 25px; }
|
||||
.loading-panel, .error-panel { position: absolute; z-index: 600; inset: 0; display: grid; place-items: center; background: var(--overlay); }
|
||||
.loading-card { background: var(--card); padding: 18px 22px; border-radius: 14px; box-shadow: var(--shadow); font-weight: 750; }
|
||||
.error-panel { display: none; color: var(--red); text-align: center; padding: 25px; }
|
||||
.marker-wrap { background: none; border: 0; }
|
||||
.flow-marker {
|
||||
--marker-color: #087da5; --marker-size: 26px;
|
||||
@@ -179,7 +270,7 @@
|
||||
.risk-chips { display: flex; gap: 6px; }
|
||||
.risk-chip { flex: 1; text-align: center; border-radius: 8px; padding: 5px 4px; font-size: .64rem; font-weight: 800; color: white; }
|
||||
.risk-chip span { display: block; font-weight: 650; font-size: .58rem; opacity: .85; }
|
||||
.p1-outlook { border: 1px solid var(--border); border-left: 4px solid var(--river); border-radius: 12px; padding: 12px 14px; margin-top: 14px; background: #f7fbfa; }
|
||||
.p1-outlook { border: 1px solid var(--border); border-left: 4px solid var(--river); border-radius: 12px; padding: 12px 14px; margin-top: 14px; background: var(--surface-3); }
|
||||
.p1-outlook-head { display: flex; justify-content: space-between; align-items: center; gap: 10px; flex-wrap: wrap; }
|
||||
.p1-outlook-head strong { font-size: .88rem; }
|
||||
.p1-peak { color: var(--muted); font-size: .76rem; }
|
||||
@@ -193,16 +284,16 @@
|
||||
.popup h3 { margin: 4px 0 2px; font-size: 1rem; }
|
||||
.popup-th { color: var(--muted); font-size: .74rem; }
|
||||
.popup-grid { display: grid; grid-template-columns: 1fr 1fr; gap: 8px; margin-top: 12px; }
|
||||
.popup-metric { background: #f1f7f5; padding: 8px; border-radius: 9px; }
|
||||
.popup-metric { background: var(--surface-2); padding: 8px; border-radius: 9px; }
|
||||
.popup-metric span { display: block; color: var(--muted); font-size: .62rem; }
|
||||
.popup-metric strong { display: block; margin-top: 2px; font-size: .86rem; }
|
||||
.popup-time { margin-top: 9px; color: var(--muted); font-size: .64rem; }
|
||||
/* Verdict banner: light tinted backgrounds with dark ink (contrast-safe) */
|
||||
#flood-verdict.ok { background: #e2f3ea; color: #0c5138; border-color: #bfe3d2; }
|
||||
#flood-verdict.watch { background: #fdf1dc; color: #6b4a05; border-color: #f0d9a8; }
|
||||
#flood-verdict.danger { background: #fbe3de; color: #7c1d10; border-color: #f2c0b6; }
|
||||
#flood-verdict.ok { background: var(--ok-bg); color: var(--ok-ink); border-color: var(--ok-border); }
|
||||
#flood-verdict.watch { background: var(--watch-bg); color: var(--watch-ink); border-color: var(--watch-border); }
|
||||
#flood-verdict.danger { background: var(--danger-bg); color: var(--danger-ink); border-color: var(--danger-border); }
|
||||
#legend-toggle {
|
||||
display: none; pointer-events: auto; background: rgba(255,255,255,.93); border: 1px solid rgba(207,224,218,.9);
|
||||
display: none; pointer-events: auto; background: var(--overlay); border: 1px solid var(--overlay-border);
|
||||
border-radius: 11px; padding: 8px 12px; font-size: .72rem; font-weight: 800; color: var(--ink);
|
||||
box-shadow: 0 7px 20px rgba(22,58,68,.12);
|
||||
}
|
||||
@@ -275,10 +366,34 @@
|
||||
<div class="live-pill" id="live-pill"><span class="live-dot"></span> <span id="live-pill-text" data-i18n="pill.live">LIVE DATA</span></div>
|
||||
<button id="refresh-button" type="button" data-i18n="action.refresh">↻ Refresh</button>
|
||||
<button id="lang-toggle" class="lang-toggle" type="button" data-active-lang="en" aria-label="Switch to Thai">ไทย</button>
|
||||
<button id="theme-toggle" class="theme-toggle" type="button" data-i18n-aria="theme.toggle" aria-label="Switch to dark mode" title="Switch to dark mode">🌙</button>
|
||||
<button id="alerts-button" type="button" data-i18n="alerts.button" style="display:none">🔔 Get alerts</button>
|
||||
<button id="replay-2024" type="button" data-i18n="replay.start">▶ Replay Oct 2024 flood</button>
|
||||
</div>
|
||||
</header>
|
||||
|
||||
<section id="alerts-panel" class="alerts-panel" style="display:none" aria-labelledby="alerts-title">
|
||||
<div class="alerts-head">
|
||||
<h2 id="alerts-title" data-i18n="alerts.title">Flood alerts on your phone</h2>
|
||||
<button type="button" class="alerts-close" id="alerts-close" data-i18n-aria="alerts.close" aria-label="Close">✕</button>
|
||||
</div>
|
||||
<p class="alerts-intro" data-i18n="alerts.intro">Free push notifications when a gauge crosses its warning or danger level, and an all-clear when it drops back. No account: install the ntfy app (iOS / Android / any browser), add the server, subscribe to the topics you want. You get a message only when something changes: a few per flood, none in a quiet season.</p>
|
||||
<div class="alerts-server">
|
||||
<span data-i18n="alerts.server">Server</span>
|
||||
<code id="alerts-server-url"></code>
|
||||
<button type="button" id="alerts-copy" data-i18n="alerts.copy">Copy</button>
|
||||
</div>
|
||||
<div class="alerts-grid" id="alerts-topics"></div>
|
||||
<p class="alerts-foot">
|
||||
<span data-i18n="alerts.apps">Apps:</span>
|
||||
<a href="https://apps.apple.com/us/app/ntfy/id1625396347" target="_blank" rel="noopener">iOS</a> ·
|
||||
<a href="https://play.google.com/store/apps/details?id=io.heckel.ntfy" target="_blank" rel="noopener">Android</a> ·
|
||||
<a href="https://f-droid.org/en/packages/io.heckel.ntfy/" target="_blank" rel="noopener">F-Droid</a> ·
|
||||
<a id="alerts-web-link" href="#" target="_blank" rel="noopener" data-i18n="alerts.web">Web (no install)</a>
|
||||
<span class="alerts-disclaimer" data-i18n="alerts.disclaimer">Unofficial community service, best effort. For official warnings follow ThaiWater / TMD / your district office.</span>
|
||||
</p>
|
||||
</section>
|
||||
|
||||
<section id="flood-verdict" role="status" aria-live="polite" style="display:none;margin-bottom:14px;padding:15px 18px;border-radius:16px;border:1px solid;display:none">
|
||||
<div style="display:flex;gap:12px;align-items:baseline;flex-wrap:wrap">
|
||||
<strong id="verdict-icon" style="font-size:1.2rem"></strong>
|
||||
@@ -321,7 +436,7 @@
|
||||
<div class="legend-row"><i class="swatch" style="background:#2a1668;border-radius:50%"></i> <span data-i18n="legend.rain.extreme">Extreme > 150</span></div>
|
||||
<div class="legend-title" style="margin-top:10px" data-i18n="legend.other">Other markers</div>
|
||||
<div class="legend-row"><i class="swatch" style="background:#7b8f94"></i> <span data-i18n="legend.other.nodata">Gauge · no recent data</span></div>
|
||||
<div class="legend-row"><span style="font-weight:800;color:#0f6844">+</span> <span data-i18n="legend.other.sensor">Water-level sensor · colour = % of bank height</span></div>
|
||||
<div class="legend-row"><span style="font-weight:800;color:var(--green)">+</span> <span data-i18n="legend.other.sensor">Water-level sensor · colour = % of bank height</span></div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -332,7 +447,7 @@
|
||||
|
||||
<aside class="side-card">
|
||||
<div class="side-head"><h2 data-i18n="side.title">Current station flow</h2><p data-i18n="side.subtitle">Select a station to locate it and load its history</p>
|
||||
<input type="search" id="station-search" data-i18n-placeholder="search.placeholder" data-i18n-aria="search.aria" placeholder="Search stations · code, name, river…" aria-label="Search stations" style="margin-top:10px;width:100%;box-sizing:border-box;padding:9px 12px;border:1px solid var(--border);border-radius:10px;background:white;font-size:.8rem">
|
||||
<input type="search" id="station-search" data-i18n-placeholder="search.placeholder" data-i18n-aria="search.aria" placeholder="Search stations · code, name, river…" aria-label="Search stations" style="margin-top:10px;width:100%;box-sizing:border-box;padding:9px 12px;border:1px solid var(--border);border-radius:10px;background:var(--surface);color:var(--ink);font-size:.8rem">
|
||||
</div>
|
||||
<div class="station-list" id="river-flow" aria-live="polite"></div>
|
||||
<div class="side-head" id="sensors-head" style="cursor:pointer" role="button" tabindex="0" aria-expanded="false" aria-controls="thaiwater-sensors" data-i18n-title="sensors.tip" title="Show / hide the ThaiWater/HII station list"><h2><span data-i18n="sensors.title">Additional basin stations</span> <span id="sensors-arrow" style="color:var(--muted);font-size:.8rem">▸</span></h2><p id="thaiwater-count" data-i18n="sensors.loading">Loading ThaiWater/HII stations…</p></div>
|
||||
@@ -356,6 +471,16 @@
|
||||
<div class="p1-peak" style="margin-top:7px" data-i18n="outlook.explainer">Chance the river reaches each official inundation stage within 24 h — city flooding begins at stage 1 (3.70 m); each stage floods additional districts.</div>
|
||||
</div>
|
||||
<button type="button" class="zones-button" id="forecast-expand" style="display:none;margin-top:12px">Show all station forecasts ▾</button>
|
||||
<div class="skill-panel" id="skill-panel" style="display:none">
|
||||
<div class="skill-head">
|
||||
<strong data-i18n="skill.title">Is the model getting better?</strong>
|
||||
<span class="subtitle" id="skill-sub"></span>
|
||||
</div>
|
||||
<div class="skill-headline" id="skill-headline"></div>
|
||||
<p class="subtitle skill-caveat" id="skill-caveat" style="margin:-4px 0 10px"></p>
|
||||
<div class="skill-table-wrap"><table class="skill-table" id="skill-table"></table></div>
|
||||
<p class="subtitle" style="margin:8px 0 0" data-i18n="skill.explain">Every hour the deployed model's 24 h peak forecast for P.1 is stored; once those 24 hours have passed it is compared with what the river actually did. "Skill" is how much better the model was than assuming the level stays where it is (0 = no better, 1 = perfect). Versions retrained on more data appear as new rows, so improvement, or its absence, is visible here rather than claimed.</p>
|
||||
</div>
|
||||
<div class="forecast-grid" id="forecast-grid" style="display:none"></div>
|
||||
</section>
|
||||
|
||||
@@ -363,10 +488,10 @@
|
||||
<div style="display:flex;justify-content:space-between;align-items:center;gap:14px;flex-wrap:wrap">
|
||||
<div><h2 id="history-title" style="margin:0;font-size:1rem" data-i18n="history.title">Station history</h2><p id="history-status" class="subtitle" data-i18n="history.status">Select a station to load the last 7 days</p></div>
|
||||
<div class="history-controls" style="display:flex;gap:8px;align-items:center;flex-wrap:wrap">
|
||||
<select id="history-range" style="padding:9px 12px;border:1px solid var(--border);border-radius:10px;background:white"><option value="24" data-i18n="range.24h">Last 24 hours</option><option value="168" selected data-i18n="range.7d">Last 7 days</option><option value="720" data-i18n="range.30d">Last 30 days</option><option value="2160" data-i18n="range.90d">Last 90 days</option><option value="876000" data-i18n="range.all">All time</option><option value="custom" hidden data-i18n="range.custom">Custom range</option></select>
|
||||
<input type="date" id="history-start" data-i18n-title="range.from" title="From date" style="padding:8px 10px;border:1px solid var(--border);border-radius:10px;background:white">
|
||||
<select id="history-range" style="padding:9px 12px;border:1px solid var(--border);border-radius:10px;background:var(--surface);color:var(--ink)"><option value="24" data-i18n="range.24h">Last 24 hours</option><option value="168" selected data-i18n="range.7d">Last 7 days</option><option value="720" data-i18n="range.30d">Last 30 days</option><option value="2160" data-i18n="range.90d">Last 90 days</option><option value="876000" data-i18n="range.all">All time</option><option value="custom" hidden data-i18n="range.custom">Custom range</option></select>
|
||||
<input type="date" id="history-start" data-i18n-title="range.from" title="From date" style="padding:8px 10px;border:1px solid var(--border);border-radius:10px;background:var(--surface);color:var(--ink)">
|
||||
<span style="color:var(--muted)">–</span>
|
||||
<input type="date" id="history-end" data-i18n-title="range.to" title="To date" style="padding:8px 10px;border:1px solid var(--border);border-radius:10px;background:white">
|
||||
<input type="date" id="history-end" data-i18n-title="range.to" title="To date" style="padding:8px 10px;border:1px solid var(--border);border-radius:10px;background:var(--surface);color:var(--ink)">
|
||||
</div>
|
||||
</div>
|
||||
<div style="height:260px;margin-top:14px;overflow:hidden;position:relative"><canvas id="history-chart" data-i18n-aria="aria.chart" aria-label="Historical water level and discharge chart" style="display:block"></canvas><div id="history-placeholder" data-i18n="history.placeholder" style="position:absolute;inset:0;display:grid;place-items:center;color:var(--muted);font-size:.85rem;text-align:center;padding:20px">Click any station on the map or in the list to see its history</div></div>
|
||||
@@ -407,6 +532,8 @@
|
||||
'app.title': 'Ping River Live Monitor',
|
||||
'app.subtitle': 'Current water level and discharge across Northern Thailand',
|
||||
'pill.live': 'LIVE DATA',
|
||||
'theme.toggle': 'Toggle dark mode',
|
||||
'pill.stale': '⚠ STALE FEED',
|
||||
'pill.replay': '⏪ 2024 REPLAY',
|
||||
'pill.sim': '⚠ SIMULATION',
|
||||
'action.refresh': '↻ Refresh',
|
||||
@@ -439,7 +566,9 @@
|
||||
'stat.stress.tip': 'How full the river channel is at the busiest gauge — 100% means water reaches the top of the bank',
|
||||
'stat.updated': 'Last updated',
|
||||
'stat.updated.note': 'Loading latest readings',
|
||||
'stat.updated.ago': (date, mins) => `${date} · ${mins} min ago`,
|
||||
'stat.updated.ago': (date, mins) => `${date} · ${mins} min ago (ICT)`,
|
||||
'stat.updated.agoh': (date, hours) => `${date} · ${hours} h ago (ICT)`,
|
||||
'stat.updated.stale': (date, hours) => `⚠ Feed stale · last reading ${date}, ${hours} h ago`,
|
||||
'stat.updated.none': 'No timestamp available',
|
||||
'map.title': 'Station flow map',
|
||||
'map.subtitle': 'River width, colour & dash speed follow live discharge',
|
||||
@@ -491,6 +620,51 @@
|
||||
'forecast.chip.peak': (lvl) => ` · peak ~${lvl} m`,
|
||||
'forecast.chip.heuristic': ' · heuristic fallback',
|
||||
'forecast.expand': (n) => `Show all ${n} station forecasts ▾`,
|
||||
'skill.title': 'Is the model getting better?',
|
||||
'skill.sub': (n, since) => `${n} verified 24 h forecasts for P.1 since ${since}`,
|
||||
'skill.explain': 'Every hour the deployed model\'s 24 h peak forecast for P.1 is stored; once those 24 hours have passed it is compared with what the river actually did. "Skill" is how much better the model was than assuming the level stays where it is (0 = no better, 1 = perfect). Versions retrained on more data appear as new rows, so improvement, or its absence, is visible here rather than claimed.',
|
||||
'skill.better': (v, prev, d) => `Current model ${v} is more accurate than ${prev}: peak error ${d} cm lower on the hours it has served.`,
|
||||
'skill.worse': (v, prev, d) => `Current model ${v} has a higher peak error than ${prev} so far (+${d} cm).`,
|
||||
'skill.caveat.quiet': 'All verified hours so far were below 2 m: this measures quiet-river accuracy only. The model is built and judged for flood onset (lead time before 3.70 m), which no quiet week can test — see the backtests in the documentation.',
|
||||
'skill.caveat.regime': 'Versions served different weeks; the ≥ 2 m column compares them on the hours that matter.',
|
||||
'alerts.button': '🔔 Get alerts',
|
||||
'alerts.title': 'Flood alerts on your phone',
|
||||
'alerts.intro': 'Free push notifications when a gauge crosses its warning or danger level, and an all-clear when it drops back. No account: install the ntfy app (iOS / Android / any browser), add the server, subscribe to the topics you want. You get a message only when something changes: a few per flood, none in a quiet season.',
|
||||
'alerts.server': 'Server',
|
||||
'alerts.copy': 'Copy',
|
||||
'alerts.copied': 'Copied',
|
||||
'alerts.close': 'Close',
|
||||
'alerts.apps': 'Apps:',
|
||||
'alerts.web': 'Web (no install)',
|
||||
'alerts.disclaimer': 'Unofficial community service, best effort. For official warnings follow ThaiWater / TMD / your district office.',
|
||||
'alerts.subscribe': 'Subscribe in app',
|
||||
'alerts.t.warning': 'Any gauge: warning level',
|
||||
'alerts.t.warning.d': 'One message when any Ping River gauge crosses its warning level, and when levels fall back. The one to pick if unsure.',
|
||||
'alerts.t.danger': 'Any gauge: danger level',
|
||||
'alerts.t.danger.d': 'Only the serious crossings, basin-wide. Highest priority: rings through Do Not Disturb on most phones.',
|
||||
'alerts.t.p1.warning': 'Chiang Mai city (P.1) warning',
|
||||
'alerts.t.p1.warning.d': 'Nawarat Bridge crosses 3.70 m (stage 1: low-lying riverside areas), and the all-clear.',
|
||||
'alerts.t.p1.danger': 'Chiang Mai city (P.1) danger',
|
||||
'alerts.t.p1.danger.d': 'Nawarat Bridge crosses 4.20 m (stage 5: inner city districts).',
|
||||
'alerts.t.p103.warning': 'Ring Road 3 (P.103) warning',
|
||||
'alerts.t.p103.warning.d': 'Downstream city gauge crosses 5.95 m.',
|
||||
'alerts.t.outlook': 'Early warning (model forecast)',
|
||||
'alerts.t.outlook.d': 'Experimental: the forecast model gives a ≥ 50 % chance that P.1 reaches its warning level within 24 h. Up to ~13 h earlier than the gauge, but it can be wrong.',
|
||||
'alerts.t.status': 'Monitor status',
|
||||
'alerts.t.status.d': 'Gauge feed stale / recovered. For people who rely on the dashboard.',
|
||||
'skill.single': (v) => `Only ${v} has enough verified hours yet; the next retrain adds a row to compare.`,
|
||||
'skill.young': (v, n, min) => `${v} has ${n} verified hours; a comparison needs ${min}.`,
|
||||
'skill.none': 'No verified forecasts yet — the first appear 24 h after a model starts serving.',
|
||||
'skill.col.version': 'Model',
|
||||
'skill.col.period': 'Served',
|
||||
'skill.col.n': 'Hours',
|
||||
'skill.col.mae': 'Peak error',
|
||||
'skill.col.bias': 'Bias',
|
||||
'skill.col.pers': 'Persistence',
|
||||
'skill.col.skill': 'Skill',
|
||||
'skill.col.high': '≥ 2 m error',
|
||||
'skill.cm': (v) => `${v} cm`,
|
||||
'skill.na': '—',
|
||||
'forecast.collapse': 'Hide station forecasts ▴',
|
||||
'outlook.title': 'Chiang Mai city flood outlook · P.1 Nawarat Bridge',
|
||||
'outlook.explainer': 'Chance the river reaches each official inundation stage within 24 h — city flooding begins at stage 1 (3.70 m); each stage floods additional districts.',
|
||||
@@ -579,6 +753,8 @@
|
||||
'app.title': 'ติดตามระดับน้ำปิงแบบเรียลไทม์',
|
||||
'app.subtitle': 'ระดับน้ำและอัตราการไหลปัจจุบันทั่วภาคเหนือของประเทศไทย',
|
||||
'pill.live': 'ข้อมูลสด',
|
||||
'theme.toggle': 'สลับโหมดมืด/สว่าง',
|
||||
'pill.stale': '⚠ ข้อมูลไม่อัปเดต',
|
||||
'pill.replay': '⏪ ย้อนเหตุการณ์ 2567',
|
||||
'pill.sim': '⚠ การจำลอง',
|
||||
'action.refresh': '↻ รีเฟรช',
|
||||
@@ -611,7 +787,9 @@
|
||||
'stat.stress.tip': 'ระดับความเต็มของลำน้ำที่สถานีที่มีน้ำมากที่สุด — 100% หมายถึงน้ำถึงระดับตลิ่ง',
|
||||
'stat.updated': 'อัปเดตล่าสุด',
|
||||
'stat.updated.note': 'กำลังโหลดข้อมูลล่าสุด',
|
||||
'stat.updated.ago': (date, mins) => `${date} · ${mins} นาทีที่แล้ว`,
|
||||
'stat.updated.ago': (date, mins) => `${date} · ${mins} นาทีที่แล้ว (เวลาไทย)`,
|
||||
'stat.updated.agoh': (date, hours) => `${date} · ${hours} ชั่วโมงที่แล้ว (เวลาไทย)`,
|
||||
'stat.updated.stale': (date, hours) => `⚠ ข้อมูลไม่อัปเดต · ค่าล่าสุด ${date}, ${hours} ชั่วโมงที่แล้ว`,
|
||||
'stat.updated.none': 'ไม่มีข้อมูลเวลา',
|
||||
'map.title': 'แผนที่การไหลของน้ำ',
|
||||
'map.subtitle': 'ความกว้าง สี และความเร็วเส้นประของแม่น้ำแสดงอัตราการไหลจริง',
|
||||
@@ -663,6 +841,51 @@
|
||||
'forecast.chip.peak': (lvl) => ` · ระดับสูงสุดประมาณ ${lvl} ม.`,
|
||||
'forecast.chip.heuristic': ' · ใช้การประมาณอย่างง่าย',
|
||||
'forecast.expand': (n) => `แสดงพยากรณ์ทั้ง ${n} สถานี ▾`,
|
||||
'skill.title': 'โมเดลแม่นยำขึ้นหรือไม่?',
|
||||
'skill.sub': (n, since) => `พยากรณ์ 24 ชม. ของ P.1 ที่ตรวจสอบแล้ว ${n} ครั้ง ตั้งแต่ ${since}`,
|
||||
'skill.explain': 'ทุกชั่วโมงระบบบันทึกค่าพยากรณ์ระดับน้ำสูงสุดใน 24 ชม. ของ P.1 ไว้ เมื่อครบ 24 ชม. จึงนำมาเทียบกับระดับน้ำจริง "ทักษะ" คือโมเดลดีกว่าการสมมติว่าระดับน้ำคงที่มากเพียงใด (0 = ไม่ดีกว่า, 1 = สมบูรณ์แบบ) โมเดลที่ฝึกใหม่ด้วยข้อมูลมากขึ้นจะปรากฏเป็นแถวใหม่ จึงเห็นได้ว่าดีขึ้นจริงหรือไม่',
|
||||
'skill.better': (v, prev, d) => `โมเดลปัจจุบัน ${v} แม่นยำกว่า ${prev}: ค่าคลาดเคลื่อนต่ำกว่า ${d} ซม. ในช่วงที่ให้บริการ`,
|
||||
'skill.worse': (v, prev, d) => `โมเดลปัจจุบัน ${v} มีค่าคลาดเคลื่อนสูงกว่า ${prev} (+${d} ซม.)`,
|
||||
'skill.caveat.quiet': 'ชั่วโมงที่ตรวจสอบทั้งหมดอยู่ต่ำกว่า 2 ม.: วัดได้เพียงความแม่นยำช่วงน้ำปกติ โมเดลถูกสร้างและประเมินสำหรับช่วงน้ำเริ่มท่วม (เวลาเตือนล่วงหน้าก่อน 3.70 ม.) ซึ่งสัปดาห์ปกติทดสอบไม่ได้ — ดูผลทดสอบย้อนหลังในเอกสาร',
|
||||
'skill.caveat.regime': 'แต่ละเวอร์ชันให้บริการคนละช่วงเวลา คอลัมน์ ≥ 2 ม. เปรียบเทียบเฉพาะชั่วโมงที่สำคัญ',
|
||||
'alerts.button': '🔔 รับการแจ้งเตือน',
|
||||
'alerts.title': 'แจ้งเตือนน้ำท่วมบนมือถือของคุณ',
|
||||
'alerts.intro': 'การแจ้งเตือนฟรีเมื่อระดับน้ำที่สถานีใดข้ามระดับเฝ้าระวังหรือระดับอันตราย และแจ้งเมื่อกลับสู่ปกติ ไม่ต้องสมัครสมาชิก: ติดตั้งแอป ntfy (iOS / Android / เบราว์เซอร์) เพิ่มเซิร์ฟเวอร์ แล้วเลือกหัวข้อที่ต้องการ คุณจะได้รับข้อความเฉพาะเมื่อมีการเปลี่ยนแปลง: ไม่กี่ข้อความต่อเหตุการณ์น้ำท่วม และไม่มีเลยในช่วงปกติ',
|
||||
'alerts.server': 'เซิร์ฟเวอร์',
|
||||
'alerts.copy': 'คัดลอก',
|
||||
'alerts.copied': 'คัดลอกแล้ว',
|
||||
'alerts.close': 'ปิด',
|
||||
'alerts.apps': 'แอป:',
|
||||
'alerts.web': 'เว็บ (ไม่ต้องติดตั้ง)',
|
||||
'alerts.disclaimer': 'บริการชุมชนอย่างไม่เป็นทางการ พยายามอย่างดีที่สุด สำหรับคำเตือนอย่างเป็นทางการโปรดติดตาม ThaiWater / กรมอุตุนิยมวิทยา / สำนักงานอำเภอของคุณ',
|
||||
'alerts.subscribe': 'สมัครในแอป',
|
||||
'alerts.t.warning': 'สถานีใดก็ได้: ระดับเฝ้าระวัง',
|
||||
'alerts.t.warning.d': 'หนึ่งข้อความเมื่อสถานีใดในแม่น้ำปิงข้ามระดับเฝ้าระวัง และเมื่อระดับน้ำลดลง หากไม่แน่ใจให้เลือกอันนี้',
|
||||
'alerts.t.danger': 'สถานีใดก็ได้: ระดับอันตราย',
|
||||
'alerts.t.danger.d': 'เฉพาะการข้ามระดับที่ร้ายแรง ทั้งลุ่มน้ำ ความสำคัญสูงสุด: ดังผ่านโหมดห้ามรบกวนในโทรศัพท์ส่วนใหญ่',
|
||||
'alerts.t.p1.warning': 'เมืองเชียงใหม่ (P.1) ระดับเฝ้าระวัง',
|
||||
'alerts.t.p1.warning.d': 'สะพานนวรัฐข้าม 3.70 ม. (ระยะที่ 1: พื้นที่ริมน้ำที่ต่ำ) และแจ้งเมื่อกลับสู่ปกติ',
|
||||
'alerts.t.p1.danger': 'เมืองเชียงใหม่ (P.1) ระดับอันตราย',
|
||||
'alerts.t.p1.danger.d': 'สะพานนวรัฐข้าม 4.20 ม. (ระยะที่ 5: ย่านใจกลางเมือง)',
|
||||
'alerts.t.p103.warning': 'ถนนวงแหวน 3 (P.103) ระดับเฝ้าระวัง',
|
||||
'alerts.t.p103.warning.d': 'สถานีท้ายเมืองข้าม 5.95 ม.',
|
||||
'alerts.t.outlook': 'เตือนล่วงหน้า (แบบจำลองพยากรณ์)',
|
||||
'alerts.t.outlook.d': 'ทดลอง: แบบจำลองพยากรณ์ให้โอกาส ≥ 50% ที่ P.1 จะถึงระดับเฝ้าระวังภายใน 24 ชม. เร็วกว่าสถานีวัดได้ถึง ~13 ชม. แต่อาจผิดพลาดได้',
|
||||
'alerts.t.status': 'สถานะระบบ',
|
||||
'alerts.t.status.d': 'ข้อมูลสถานีล่าช้า / กลับมาปกติ สำหรับผู้ที่พึ่งพาแดชบอร์ด',
|
||||
'skill.single': (v) => `มีเพียง ${v} ที่มีข้อมูลตรวจสอบเพียงพอ การฝึกครั้งถัดไปจะเพิ่มแถวให้เปรียบเทียบ`,
|
||||
'skill.young': (v, n, min) => `${v} มีข้อมูลตรวจสอบ ${n} ชั่วโมง ต้องการอย่างน้อย ${min} เพื่อเปรียบเทียบ`,
|
||||
'skill.none': 'ยังไม่มีพยากรณ์ที่ตรวจสอบได้ — จะเริ่มมี 24 ชม. หลังโมเดลเริ่มทำงาน',
|
||||
'skill.col.version': 'โมเดล',
|
||||
'skill.col.period': 'ช่วงเวลา',
|
||||
'skill.col.n': 'ชั่วโมง',
|
||||
'skill.col.mae': 'คลาดเคลื่อน',
|
||||
'skill.col.bias': 'อคติ',
|
||||
'skill.col.pers': 'ระดับคงที่',
|
||||
'skill.col.skill': 'ทักษะ',
|
||||
'skill.col.high': 'คลาดเคลื่อน ≥ 2 ม.',
|
||||
'skill.cm': (v) => `${v} ซม.`,
|
||||
'skill.na': '—',
|
||||
'forecast.collapse': 'ซ่อนพยากรณ์รายสถานี ▴',
|
||||
'outlook.title': 'แนวโน้มน้ำท่วมเมืองเชียงใหม่ · P.1 สะพานนวรัฐ',
|
||||
'outlook.explainer': 'โอกาสที่ระดับน้ำจะถึงแต่ละระดับการท่วมตามประกาศทางการภายใน 24 ชม. — น้ำเริ่มท่วมเมืองที่ระดับ 1 (3.70 ม.) และแต่ละระดับจะท่วมพื้นที่เพิ่มขึ้น',
|
||||
@@ -774,6 +997,60 @@
|
||||
return typeof value === 'function' ? value(...args) : value;
|
||||
}
|
||||
|
||||
// ---- public push notifications (ntfy) -------------------------------------
|
||||
let ALERTS_CFG = null;
|
||||
const ALERT_TOPICS = [
|
||||
{ key: 'warning', topic: 'warning', cls: '' },
|
||||
{ key: 'danger', topic: 'danger', cls: 'danger' },
|
||||
{ key: 'p1.warning', topic: 'p1-warning', cls: '' },
|
||||
{ key: 'p1.danger', topic: 'p1-danger', cls: 'danger' },
|
||||
{ key: 'p103.warning', topic: 'p103-warning', cls: '' },
|
||||
{ key: 'outlook', topic: 'p1-outlook', cls: 'outlook' },
|
||||
{ key: 'status', topic: 'status', cls: '' },
|
||||
];
|
||||
async function loadAlertsConfig() {
|
||||
try {
|
||||
const r = await fetch('/api/notifications');
|
||||
if (!r.ok) return;
|
||||
const cfg = await r.json();
|
||||
if (!cfg.enabled || !cfg.server) return;
|
||||
ALERTS_CFG = cfg;
|
||||
$('alerts-button').style.display = '';
|
||||
renderAlertsPanel();
|
||||
} catch (e) { /* no notifications configured */ }
|
||||
}
|
||||
function renderAlertsPanel() {
|
||||
if (!ALERTS_CFG) return;
|
||||
const server = ALERTS_CFG.server.replace(/\/$/, '');
|
||||
const host = server.replace(/^https?:\/\//, '');
|
||||
$('alerts-server-url').textContent = host;
|
||||
$('alerts-web-link').href = server + '/' + ALERTS_CFG.prefix + '-warning';
|
||||
$('alerts-topics').innerHTML = ALERT_TOPICS.map(tp => {
|
||||
const full = ALERTS_CFG.prefix + '-' + tp.topic;
|
||||
const url = server + '/' + full;
|
||||
return `<div class="alerts-topic ${tp.cls}">
|
||||
<div class="name">${esc(t('alerts.t.' + tp.key))}</div>
|
||||
<div class="desc">${esc(t('alerts.t.' + tp.key + '.d'))}</div>
|
||||
<div class="row"><code>${esc(full)}</code> <a href="ntfy://${esc(host)}/${esc(full)}">${esc(t('alerts.subscribe'))}</a> · <a href="${esc(url)}" target="_blank" rel="noopener">web</a></div>
|
||||
</div>`;
|
||||
}).join('');
|
||||
}
|
||||
function esc(x) { return String(x).replace(/[&<>"']/g, c => ({'&':'&','<':'<','>':'>','"':'"',"'":'''}[c])); }
|
||||
$('alerts-button').addEventListener('click', () => {
|
||||
const p = $('alerts-panel');
|
||||
const open = p.style.display === 'none';
|
||||
p.style.display = open ? '' : 'none';
|
||||
if (open) { renderAlertsPanel(); p.scrollIntoView({ behavior: 'smooth', block: 'start' }); }
|
||||
});
|
||||
$('alerts-close').addEventListener('click', () => { $('alerts-panel').style.display = 'none'; });
|
||||
$('alerts-copy').addEventListener('click', async () => {
|
||||
try {
|
||||
await navigator.clipboard.writeText(ALERTS_CFG ? ALERTS_CFG.server : '');
|
||||
$('alerts-copy').textContent = t('alerts.copied');
|
||||
setTimeout(() => { $('alerts-copy').textContent = t('alerts.copy'); }, 1500);
|
||||
} catch (e) { /* clipboard blocked */ }
|
||||
});
|
||||
|
||||
function applyTranslations() {
|
||||
document.documentElement.lang = state.lang;
|
||||
document.querySelectorAll('[data-i18n]').forEach((el) => {
|
||||
@@ -801,7 +1078,34 @@
|
||||
}
|
||||
}
|
||||
|
||||
// Theme: explicit choice persists; otherwise follow the OS and track its changes.
|
||||
const THEME_KEY = 'ping-river-theme';
|
||||
const osDark = window.matchMedia('(prefers-color-scheme: dark)');
|
||||
function currentTheme() { return document.documentElement.dataset.theme === 'dark' ? 'dark' : 'light'; }
|
||||
function applyTheme(theme, persist) {
|
||||
document.documentElement.dataset.theme = theme;
|
||||
const button = $('theme-toggle');
|
||||
if (button) {
|
||||
button.textContent = theme === 'dark' ? '☀️' : '🌙';
|
||||
}
|
||||
if (persist) { try { localStorage.setItem(THEME_KEY, theme); } catch (e) { /* private mode */ } }
|
||||
// Chart.js reads colours at construction: rebuild the open chart
|
||||
if (state.historyChart && state.selectedStation) loadHistory(state.selectedStation);
|
||||
}
|
||||
(() => {
|
||||
let saved = null;
|
||||
try { saved = localStorage.getItem(THEME_KEY); } catch (e) { /* private mode */ }
|
||||
applyTheme(saved === 'dark' || saved === 'light' ? saved : (osDark.matches ? 'dark' : 'light'), false);
|
||||
osDark.addEventListener('change', (e) => {
|
||||
let pinned = null;
|
||||
try { pinned = localStorage.getItem(THEME_KEY); } catch (err) { /* ignore */ }
|
||||
if (!pinned) applyTheme(e.matches ? 'dark' : 'light', false);
|
||||
});
|
||||
})();
|
||||
function cssVar(name) { return getComputedStyle(document.documentElement).getPropertyValue(name).trim(); }
|
||||
|
||||
function setLang(lang) {
|
||||
setTimeout(renderAlertsPanel, 0);
|
||||
state.lang = lang;
|
||||
try { localStorage.setItem(LANG_KEY, lang); } catch (e) { /* private mode */ }
|
||||
applyTranslations();
|
||||
@@ -841,6 +1145,25 @@
|
||||
// what the replay label ("ต.ค. 2567") already says — pinning Gregorian here
|
||||
// put two different year systems on the same screen.
|
||||
function loc() { return state.lang === 'th' ? 'th-TH' : 'en-GB'; }
|
||||
// Every timestamp the API emits is Asia/Bangkok wall-clock WITHOUT an
|
||||
// offset ("2026-09-12T02:00:00"). new Date() on such a string uses the
|
||||
// browser's own zone, so a viewer in Europe read a 02:00 ICT reading as
|
||||
// five hours in the future and saw "0 min ago" forever. Pin the offset
|
||||
// here and always format with timeZone: TZ so the site shows river time
|
||||
// no matter where it is opened.
|
||||
const TZ = 'Asia/Bangkok';
|
||||
const STALE_AFTER_MIN = 180;
|
||||
function parseTs(value) {
|
||||
if (value == null || value === '') return null;
|
||||
if (value instanceof Date) return value;
|
||||
const text = String(value).trim();
|
||||
const naive = /^\d{4}-\d\d-\d\d[T ]\d\d:\d\d(:\d\d(\.\d+)?)?$/.test(text);
|
||||
const date = new Date(naive ? text.replace(' ', 'T') + '+07:00' : text);
|
||||
return Number.isNaN(date.getTime()) ? null : date;
|
||||
}
|
||||
// Bucket keys in river-local time (a Bangkok calendar day, not a UTC one)
|
||||
const dayKey = (value) => parseTs(value).toLocaleDateString('en-CA', { timeZone: TZ });
|
||||
const hourKey = (value) => `${dayKey(value)}-${parseTs(value).toLocaleTimeString('en-GB', { timeZone: TZ, hour: '2-digit' })}`;
|
||||
// Metre abbreviation: "ม." reads as a unit in Thai, "m" mid-sentence does not.
|
||||
function metres(value, digits = 2) {
|
||||
return `${Number(value).toFixed(digits)} ${t('unit.m')}`;
|
||||
@@ -885,7 +1208,7 @@
|
||||
const mm = r.rain_24h == null ? null : Number(r.rain_24h);
|
||||
const bin = rainBin(mm);
|
||||
const name = (state.lang === 'th' ? r.name_th || r.name_en : r.name_en || r.name_th) || r.oldcode || `Station ${r.station_id}`;
|
||||
const time = r.timestamp ? new Date(r.timestamp).toLocaleString(loc(), { dateStyle: 'medium', timeStyle: 'short' }) : t('popup.noreading');
|
||||
const time = r.timestamp ? parseTs(r.timestamp).toLocaleString(loc(), { timeZone: TZ, dateStyle: 'medium', timeStyle: 'short' }) : t('popup.noreading');
|
||||
L.circleMarker([r.latitude, r.longitude], {
|
||||
radius: bin.radius, color: '#ffffff', weight: 1.5,
|
||||
fillColor: bin.color, fillOpacity: bin.opacity ?? .85
|
||||
@@ -912,7 +1235,7 @@
|
||||
const latest = new Map();
|
||||
measurements.forEach((item) => {
|
||||
const prior = latest.get(item.station_code);
|
||||
if (!prior || new Date(item.timestamp) > new Date(prior.timestamp)) latest.set(item.station_code, item);
|
||||
if (!prior || parseTs(item.timestamp) > parseTs(prior.timestamp)) latest.set(item.station_code, item);
|
||||
});
|
||||
return latest;
|
||||
}
|
||||
@@ -945,7 +1268,7 @@
|
||||
function buildPopup(station, measurement) {
|
||||
const flow = measurement ? measurement.discharge : null;
|
||||
const level = measurement ? measurement.water_level : null;
|
||||
const time = measurement ? new Date(measurement.timestamp).toLocaleString(loc(), { dateStyle: 'medium', timeStyle: 'short' }) : t('popup.noreading');
|
||||
const time = measurement ? parseTs(measurement.timestamp).toLocaleString(loc(), { timeZone: TZ, dateStyle: 'medium', timeStyle: 'short' }) : t('popup.noreading');
|
||||
// Station names are bilingual in the data: lead with the reader's language
|
||||
const primary = state.lang === 'th' ? station.thai_name : station.english_name;
|
||||
const secondary = state.lang === 'th' ? station.english_name : station.thai_name;
|
||||
@@ -1125,8 +1448,7 @@
|
||||
const downsample = (data) => {
|
||||
const buckets = {};
|
||||
data.forEach((row) => {
|
||||
const date = new Date(row.timestamp);
|
||||
const key = `${date.getUTCFullYear()}-${date.getUTCMonth()}-${date.getUTCDate()}`;
|
||||
const key = dayKey(row.timestamp);
|
||||
if (!buckets[key]) buckets[key] = { ts: row.timestamp, discharge: [], level: [] };
|
||||
const b = buckets[key];
|
||||
if (row.discharge != null) b.discharge.push(row.discharge);
|
||||
@@ -1147,12 +1469,7 @@
|
||||
const fr = await fetch(`/api/forecast/history/${encodeURIComponent(stationCode)}?${query}&horizon=24`);
|
||||
const forecastRows = fr.ok ? await fr.json() : [];
|
||||
if (forecastRows.length) {
|
||||
const keyOf = (value) => {
|
||||
const d = new Date(value);
|
||||
return rows.length > 2000
|
||||
? `${d.getUTCFullYear()}-${d.getUTCMonth()}-${d.getUTCDate()}`
|
||||
: `${d.getUTCFullYear()}-${d.getUTCMonth()}-${d.getUTCDate()}-${d.getUTCHours()}`;
|
||||
};
|
||||
const keyOf = (value) => rows.length > 2000 ? dayKey(value) : hourKey(value);
|
||||
const byKey = new Map();
|
||||
forecastRows.forEach((r) => {
|
||||
if (r.predicted_max_level == null) return;
|
||||
@@ -1177,7 +1494,7 @@
|
||||
state.historyChart = new Chart($('history-chart'), {
|
||||
type: 'line',
|
||||
data: {
|
||||
labels: sampled.map((row) => new Date(row.timestamp).toLocaleString(loc(), { timeZone: 'Asia/Bangkok', month: 'short', day: 'numeric', year: '2-digit', hour: '2-digit' })),
|
||||
labels: sampled.map((row) => parseTs(row.timestamp).toLocaleString(loc(), { timeZone: TZ, month: 'short', day: 'numeric', year: '2-digit', hour: '2-digit' })),
|
||||
datasets: [
|
||||
{ label: t('chart.discharge'), data: sampled.map((row) => row.discharge), borderColor: '#087da5', backgroundColor: 'rgba(8,125,165,.12)', yAxisID: 'flow', pointRadius: 0, tension: .25 },
|
||||
{ label: t('chart.level'), data: sampled.map((row) => row.water_level), borderColor: '#d99018', yAxisID: 'level', pointRadius: 0, tension: .25 },
|
||||
@@ -1187,13 +1504,14 @@
|
||||
options: {
|
||||
responsive: true, maintainAspectRatio: false, animation: { duration: 0 },
|
||||
interaction: { mode: 'index', intersect: false },
|
||||
color: cssVar('--ink'),
|
||||
scales: {
|
||||
flow: { type: 'linear', position: 'left' },
|
||||
level: { type: 'linear', position: 'right', grid: { drawOnChartArea: false } },
|
||||
x: { ticks: { maxTicksLimit: 12 } }
|
||||
flow: { type: 'linear', position: 'left', grid: { color: cssVar('--chart-grid') }, ticks: { color: cssVar('--muted') } },
|
||||
level: { type: 'linear', position: 'right', grid: { drawOnChartArea: false }, ticks: { color: cssVar('--muted') } },
|
||||
x: { ticks: { maxTicksLimit: 12, color: cssVar('--muted') }, grid: { color: cssVar('--chart-grid') } }
|
||||
},
|
||||
plugins: {
|
||||
legend: { display: true },
|
||||
legend: { display: true, labels: { color: cssVar('--ink') } },
|
||||
floodBands: { enabled: true }
|
||||
}
|
||||
},
|
||||
@@ -1343,7 +1661,7 @@
|
||||
function setP1Level(value, at, opts) {
|
||||
const options = opts || {};
|
||||
if (value == null || Number.isNaN(Number(value))) return;
|
||||
const stamp = at ? new Date(at).getTime() : null;
|
||||
const stamp = at ? (parseTs(at)?.getTime() ?? NaN) : null;
|
||||
const known = Number.isFinite(stamp) ? stamp : null;
|
||||
if (!options.force && known != null && state.p1NowAt != null && known < state.p1NowAt) {
|
||||
return; // an older snapshot must not overwrite a newer one
|
||||
@@ -1383,7 +1701,7 @@
|
||||
|
||||
function renderSummary(stations, readings) {
|
||||
const current = stations.map((s) => readings.get(s.station_code)).filter(Boolean);
|
||||
const timestamps = current.map((m) => new Date(m.timestamp)).filter((date) => !Number.isNaN(date.getTime()));
|
||||
const timestamps = current.map((m) => parseTs(m.timestamp)).filter(Boolean);
|
||||
const latest = timestamps.length ? new Date(Math.max(...timestamps.map((date) => date.getTime()))) : null;
|
||||
$('station-count').textContent = `${current.length} / ${stations.length}`;
|
||||
if (state.hiiReportingCount != null) {
|
||||
@@ -1403,12 +1721,24 @@
|
||||
const worst = stressed.length ? stressed.reduce((max, item) => item.percent > max.percent ? item : max) : null;
|
||||
$('peak-flow').textContent = worst ? `${worst.percent.toFixed(0)}%` : '—';
|
||||
$('peak-station').textContent = worst ? t('stat.stress.capacity', worst.code) : t('stat.stress.nodata');
|
||||
$('last-updated').textContent = latest ? latest.toLocaleTimeString(loc(), { hour: '2-digit', minute: '2-digit' }) : '—';
|
||||
$('last-updated').textContent = latest ? latest.toLocaleTimeString(loc(), { timeZone: TZ, hour: '2-digit', minute: '2-digit' }) : '—';
|
||||
const tile = $('last-updated').closest('.stat');
|
||||
if (latest) {
|
||||
const minutes = Math.max(0, Math.round((Date.now() - latest.getTime()) / 60000));
|
||||
$('data-age').textContent = t('stat.updated.ago',
|
||||
latest.toLocaleDateString(loc(), { day: 'numeric', month: 'short' }), minutes);
|
||||
} else $('data-age').textContent = t('stat.updated.none');
|
||||
const day = latest.toLocaleDateString(loc(), { timeZone: TZ, day: 'numeric', month: 'short' });
|
||||
// RID publishes hourly and the scrape runs hourly, so anything past
|
||||
// ~3 h means the feed or the collector has stopped: say so loudly
|
||||
// instead of letting "6000 min ago" pass as a number.
|
||||
const stale = minutes >= STALE_AFTER_MIN;
|
||||
$('data-age').textContent = stale
|
||||
? t('stat.updated.stale', day, Math.round(minutes / 60))
|
||||
: minutes >= 120 ? t('stat.updated.agoh', day, Math.round(minutes / 60))
|
||||
: t('stat.updated.ago', day, minutes);
|
||||
tile.classList.toggle('stale', stale);
|
||||
if (!state.replayTimer && (state.liveMode === 'live' || state.liveMode === 'stale')) {
|
||||
setLiveIndicator(stale ? 'stale' : 'live', stale ? 'pill.stale' : 'pill.live');
|
||||
}
|
||||
} else { $('data-age').textContent = t('stat.updated.none'); tile.classList.remove('stale'); }
|
||||
}
|
||||
|
||||
async function loadDashboard() {
|
||||
@@ -1655,13 +1985,13 @@
|
||||
// force: replay frames are 2024 timestamps, older than anything live
|
||||
if (p1Level != null) setP1Level(p1Level, null, { force: true });
|
||||
restyleFloodZones();
|
||||
const ts = new Date(data.timestamps[frame]);
|
||||
const ts = parseTs(data.timestamps[frame]);
|
||||
// minute included: a lone "17" reads as a year in Thai output
|
||||
const when = ts.toLocaleString(loc(), { day: 'numeric', month: 'short', hour: '2-digit', minute: '2-digit' });
|
||||
const when = ts.toLocaleString(loc(), { timeZone: TZ, day: 'numeric', month: 'short', hour: '2-digit', minute: '2-digit' });
|
||||
const p1Text = state.p1Now == null ? '—' : metres(state.p1Now);
|
||||
const basinFlow = Math.round(totalFlow).toLocaleString(loc());
|
||||
$('p1-peak').textContent = t('replay.peak', when, p1Text, basinFlow);
|
||||
$('replay-clock-time').textContent = ts.toLocaleString(loc(), { day: 'numeric', month: 'short', year: 'numeric', hour: '2-digit', minute: '2-digit' });
|
||||
$('replay-clock-time').textContent = ts.toLocaleString(loc(), { timeZone: TZ, day: 'numeric', month: 'short', year: 'numeric', hour: '2-digit', minute: '2-digit' });
|
||||
$('replay-clock-sub').textContent = t('replay.clock.sub', p1Text, basinFlow);
|
||||
// model track: what the forecast system (trained pre-flood) said at this moment
|
||||
const model = data.model || {};
|
||||
@@ -1850,9 +2180,9 @@
|
||||
`<div class="risk-chips">${chips}</div>`;
|
||||
grid.appendChild(cardEl);
|
||||
});
|
||||
const asOf = rows[0].as_of ? new Date(rows[0].as_of).toLocaleString(loc(), { dateStyle: 'medium', timeStyle: 'short' }) : null;
|
||||
const asOf = rows[0].as_of ? parseTs(rows[0].as_of).toLocaleString(loc(), { timeZone: TZ, dateStyle: 'medium', timeStyle: 'short' }) : null;
|
||||
const modelRow = rows.find((r) => r.source === 'model');
|
||||
const trainedAt = modelRow?.trained_at ? new Date(modelRow.trained_at).toLocaleDateString(loc(), { day: 'numeric', month: 'short' }) : null;
|
||||
const trainedAt = modelRow?.trained_at ? parseTs(modelRow.trained_at).toLocaleDateString(loc(), { timeZone: TZ, day: 'numeric', month: 'short' }) : null;
|
||||
const modelInfo = modelRow?.model_version
|
||||
? t('forecast.status.model', modelRow.model_version, trainedAt ? t('forecast.status.trained', trainedAt) : '')
|
||||
: '';
|
||||
@@ -1868,11 +2198,60 @@
|
||||
? t('forecast.collapse')
|
||||
: t('forecast.expand', stations.length);
|
||||
card.style.display = 'block';
|
||||
loadSkill(); // non-blocking; panel stays hidden until there is verified data
|
||||
loadAlertsConfig(); // shows the "Get alerts" button only when ntfy is configured
|
||||
} catch (error) {
|
||||
card.style.display = 'none';
|
||||
}
|
||||
}
|
||||
|
||||
async function loadSkill() {
|
||||
const panel = $('skill-panel');
|
||||
try {
|
||||
const response = await fetch('/api/forecast/skill?station_code=P.1&horizon=24');
|
||||
if (!response.ok) throw new Error(`HTTP ${response.status}`);
|
||||
const data = await response.json();
|
||||
const versions = (data.versions || []).filter((v) => v.n > 0);
|
||||
if (!versions.length) { panel.style.display = 'none'; return; }
|
||||
const cm = (m) => m == null ? t('skill.na') : t('skill.cm', (m * 100).toFixed(1));
|
||||
const fmtDay = (v) => parseTs(v).toLocaleDateString(loc(), { timeZone: TZ, day: 'numeric', month: 'short' });
|
||||
const total = versions.reduce((a, v) => a + v.n, 0);
|
||||
$('skill-sub').textContent = t('skill.sub', total.toLocaleString(loc()), fmtDay(versions[0].first_issued));
|
||||
const head = $('skill-headline');
|
||||
head.className = 'skill-headline';
|
||||
const cur = data.current;
|
||||
if (data.trend && cur) {
|
||||
const delta = Math.abs(data.trend.mae_delta_m * 100).toFixed(1);
|
||||
head.textContent = data.trend.better
|
||||
? t('skill.better', cur.model_version, data.trend.previous_version, delta)
|
||||
: t('skill.worse', cur.model_version, data.trend.previous_version, delta);
|
||||
head.classList.add(data.trend.better ? 'better' : 'worse');
|
||||
} else if (cur && cur.enough_data) {
|
||||
head.textContent = t('skill.single', cur.model_version);
|
||||
} else if (cur) {
|
||||
head.textContent = t('skill.young', cur.model_version, cur.n, data.min_verified);
|
||||
} else head.textContent = t('skill.none');
|
||||
const anyHigh = versions.some((v) => v.above_2m_n > 0);
|
||||
const compared = versions.filter((v) => v.enough_data).length > 1;
|
||||
$('skill-caveat').textContent = !anyHigh ? t('skill.caveat.quiet') : compared ? t('skill.caveat.regime') : '';
|
||||
const cols = ['version', 'period', 'n', 'mae', 'bias', 'pers', 'skill', 'high'];
|
||||
const rows = versions.map((v) => `<tr class="${v === cur ? 'current' : ''}${v.enough_data ? '' : ' young'}">`
|
||||
+ `<td>${escapeHtml(v.model_version)}</td>`
|
||||
+ `<td class="dim">${fmtDay(v.first_issued)} – ${fmtDay(v.last_issued)}</td>`
|
||||
+ `<td class="num">${v.n.toLocaleString(loc())}</td>`
|
||||
+ `<td class="num">${cm(v.mae_m)}</td>`
|
||||
+ `<td class="num">${v.bias_m == null ? t('skill.na') : (v.bias_m >= 0 ? '+' : '') + (v.bias_m * 100).toFixed(1)}</td>`
|
||||
+ `<td class="num dim">${cm(v.persistence_mae_m)}</td>`
|
||||
+ `<td class="num">${v.skill == null ? t('skill.na') : v.skill.toFixed(2)}</td>`
|
||||
+ `<td class="num">${v.above_2m_n ? `${cm(v.above_2m_mae_m)} <span class="dim">(${v.above_2m_n})</span>` : t('skill.na')}</td>`
|
||||
+ '</tr>').join('');
|
||||
$('skill-table').innerHTML = `<thead><tr>${cols.map((c) => `<th>${escapeHtml(t('skill.col.' + c))}</th>`).join('')}</tr></thead><tbody>${rows}</tbody>`;
|
||||
panel.style.display = 'block';
|
||||
} catch (error) {
|
||||
panel.style.display = 'none';
|
||||
}
|
||||
}
|
||||
|
||||
async function loadDbStats() {
|
||||
const strip = $('db-stats');
|
||||
try {
|
||||
@@ -1888,7 +2267,7 @@
|
||||
const strip = $('db-stats');
|
||||
try {
|
||||
state.lastStats = stats;
|
||||
const fmtDate = (value) => new Date(value).toLocaleDateString(loc(), { day: 'numeric', month: 'short', year: 'numeric' });
|
||||
const fmtDate = (value) => parseTs(value).toLocaleDateString(loc(), { timeZone: TZ, day: 'numeric', month: 'short', year: 'numeric' });
|
||||
state.dbFirstDate = String(stats.first_timestamp).slice(0, 10); // feeds the All-time date range
|
||||
$('db-total').textContent = Number(stats.total_measurements).toLocaleString(loc());
|
||||
if (stats.rid_measurements != null) {
|
||||
@@ -1924,6 +2303,7 @@
|
||||
: t('forecast.expand', count);
|
||||
});
|
||||
$('lang-toggle').addEventListener('click', () => setLang(state.lang === 'th' ? 'en' : 'th'));
|
||||
$('theme-toggle').addEventListener('click', () => applyTheme(currentTheme() === 'dark' ? 'light' : 'dark', true));
|
||||
$('station-search').addEventListener('input', applyStationSearch);
|
||||
$('sensors-head').addEventListener('click', () => setSensorsOpen(!state.sensorsOpen));
|
||||
$('sensors-head').addEventListener('keydown', (event) => {
|
||||
|
||||
@@ -632,9 +632,7 @@ class EnhancedWaterMonitorScraper:
|
||||
if data:
|
||||
if self.save_to_database(data):
|
||||
filled_count += len(data)
|
||||
logger.info(
|
||||
f"Filled {len(data)} measurements for {fetch_date}"
|
||||
)
|
||||
logger.info(f"Filled {len(data)} measurements for {fetch_date}")
|
||||
else:
|
||||
logger.warning(f"Failed to save data for {fetch_date}")
|
||||
else:
|
||||
|
||||
+239
-19
@@ -210,7 +210,9 @@ async def lifespan(app: FastAPI):
|
||||
app_state["leader_lock"] = _acquire_collection_leadership(
|
||||
Config.COLLECTION_LEADER_PORT
|
||||
)
|
||||
app_state["notify"] = None
|
||||
if app_state["leader_lock"]:
|
||||
app_state["notify"] = _init_notifications()
|
||||
app_state["scraping_task"] = asyncio.create_task(background_scraping_task())
|
||||
logger.info("This worker is the background-collection leader")
|
||||
else:
|
||||
@@ -296,6 +298,73 @@ async def _persist_rain():
|
||||
logger.warning(f"rain persistence failed: {e}")
|
||||
|
||||
|
||||
def _init_notifications():
|
||||
"""Publisher + persisted state for ntfy, or None if off/unavailable.
|
||||
|
||||
Called only by the collection leader: it is the one process that
|
||||
publishes, so the notification_state DDL runs exactly once per host.
|
||||
"""
|
||||
if not Config.NTFY_SERVER:
|
||||
return None
|
||||
try:
|
||||
from . import notify as notify_mod
|
||||
|
||||
store = app_state.get("forecast_store")
|
||||
if store and not store.engine:
|
||||
store.connect()
|
||||
state = (
|
||||
notify_mod.NotificationState(store.engine, store.db_type)
|
||||
if store and store.engine
|
||||
else notify_mod.InMemoryState()
|
||||
)
|
||||
if isinstance(state, notify_mod.InMemoryState):
|
||||
logger.warning(
|
||||
"ntfy: no SQL store; notification state is in-memory "
|
||||
"(a restart may re-send the current level)"
|
||||
)
|
||||
publisher = notify_mod.NtfyPublisher(
|
||||
Config.NTFY_PUBLISH_URL,
|
||||
prefix=Config.NTFY_TOPIC_PREFIX,
|
||||
token=Config.NTFY_TOKEN or None,
|
||||
dashboard_url=Config.PUBLIC_URL,
|
||||
)
|
||||
logger.info(
|
||||
f"ntfy notifications: publish to {Config.NTFY_PUBLISH_URL}, "
|
||||
f"subscribers use {Config.NTFY_SERVER}, topics {Config.NTFY_TOPIC_PREFIX}-*"
|
||||
)
|
||||
return publisher, state
|
||||
except Exception as e:
|
||||
logger.error(f"ntfy init failed (notifications off): {e}")
|
||||
return None
|
||||
|
||||
|
||||
async def _notify_transitions():
|
||||
"""Publish flood/outlook/feed transitions to ntfy (leader only, fail-safe)."""
|
||||
cfg = app_state.get("notify")
|
||||
if not cfg:
|
||||
return
|
||||
publisher, state = cfg
|
||||
try:
|
||||
from . import notify as notify_mod
|
||||
|
||||
scraper = app_state["scraper"]
|
||||
readings = await asyncio.to_thread(
|
||||
scraper.db_adapter.get_latest_measurements, 200
|
||||
)
|
||||
with FORECAST_CACHE_LOCK:
|
||||
cached = FORECAST_CACHE.get("all")
|
||||
forecasts = cached[1] if cached else []
|
||||
sent = await asyncio.to_thread(
|
||||
notify_mod.evaluate, readings, forecasts, state, publisher
|
||||
)
|
||||
if sent:
|
||||
logger.info(
|
||||
"ntfy: published " + ", ".join(f"{n.topic}: {n.title}" for n in sent)
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning(f"ntfy notify cycle failed: {e}")
|
||||
|
||||
|
||||
async def _precompute_forecasts():
|
||||
"""Refresh the forecast cache and persist the issued forecasts (leader only)."""
|
||||
try:
|
||||
@@ -374,9 +443,7 @@ async def background_scraping_task():
|
||||
hii_counts = await asyncio.get_event_loop().run_in_executor(
|
||||
None, hii_collector.run_cycle
|
||||
)
|
||||
set_gauge(
|
||||
"hii_rainfall_rows_saved", hii_counts["rainfall"]
|
||||
)
|
||||
set_gauge("hii_rainfall_rows_saved", hii_counts["rainfall"])
|
||||
set_gauge(
|
||||
"hii_waterlevel_rows_saved", hii_counts["waterlevel"]
|
||||
)
|
||||
@@ -404,6 +471,10 @@ async def background_scraping_task():
|
||||
# evaluation.
|
||||
await _precompute_forecasts()
|
||||
|
||||
# Push notifications for threshold crossings (uses the
|
||||
# forecasts just computed; no-op unless NTFY_SERVER set).
|
||||
await _notify_transitions()
|
||||
|
||||
app_state["is_scraping"] = False
|
||||
|
||||
# Calculate next run time
|
||||
@@ -521,7 +592,9 @@ _STATIC_DIR = os.path.dirname(_DASHBOARD_HTML_PATH)
|
||||
|
||||
@app.get("/robots.txt", include_in_schema=False)
|
||||
async def robots_txt():
|
||||
return FileResponse(os.path.join(_STATIC_DIR, "robots.txt"), media_type="text/plain")
|
||||
return FileResponse(
|
||||
os.path.join(_STATIC_DIR, "robots.txt"), media_type="text/plain"
|
||||
)
|
||||
|
||||
|
||||
@app.get("/llms.txt", include_in_schema=False)
|
||||
@@ -864,7 +937,7 @@ def _hii_rows(sql: str, params: Dict[str, Any]) -> List[Dict[str, Any]]:
|
||||
# flood, slightly stale readings with a visible timestamp beat an error page.
|
||||
HII_CACHE: Dict[str, Any] = {}
|
||||
HII_CACHE_LOCK = Lock()
|
||||
_HII_COMPUTE_LOCKS = {"rain": Lock(), "waterlevel": Lock()}
|
||||
_HII_COMPUTE_LOCKS = {"rain": Lock(), "waterlevel": Lock(), "skill": Lock()}
|
||||
LATEST_CACHE: Dict[str, Any] = {}
|
||||
LATEST_CACHE_LOCK = Lock()
|
||||
_LATEST_COMPUTE_LOCK = Lock()
|
||||
@@ -1001,6 +1074,91 @@ async def get_hii_rainfall_latest(
|
||||
return rows
|
||||
|
||||
|
||||
@app.get("/api/hii/rainfall/catchment")
|
||||
async def get_hii_rainfall_catchment(
|
||||
response: Response, days: int = Query(14, ge=1, le=60)
|
||||
):
|
||||
"""Upper-Ping catchment-mean hourly rain: HII gauges vs the Open-Meteo
|
||||
series the flood model actually uses, plus their agreement over the window.
|
||||
|
||||
Evidence-gathering endpoint (docs/FLOOD_FORECASTING.md, HII gauge rain):
|
||||
the gauge table only exists since 2026-08 so it cannot be a training
|
||||
feature yet; this makes the two sources' relationship observable meanwhile.
|
||||
"""
|
||||
increment_counter("api_requests", labels={"endpoint": "hii_rain_catchment"})
|
||||
start = datetime.now() - timedelta(days=days)
|
||||
|
||||
def compute():
|
||||
import pandas as pd
|
||||
|
||||
from .ml import hii_rain
|
||||
|
||||
engine = _hii_engine()
|
||||
if engine is None:
|
||||
return {
|
||||
"box": hii_rain.CATCHMENT_BOX,
|
||||
"gauge": [],
|
||||
"openmeteo": [],
|
||||
"comparison_24h_sums": {"overlap_hours": 0},
|
||||
}
|
||||
gauge = hii_rain.load_gauge_mean(start=pd.Timestamp(start), engine=engine)
|
||||
openmeteo = None
|
||||
try:
|
||||
from sqlalchemy import text
|
||||
|
||||
with engine.connect() as conn:
|
||||
frame = pd.read_sql(
|
||||
text(
|
||||
"SELECT timestamp, catchment_mean FROM openmeteo_rain "
|
||||
"WHERE timestamp >= :start ORDER BY timestamp"
|
||||
),
|
||||
conn,
|
||||
params={"start": start},
|
||||
)
|
||||
if not frame.empty:
|
||||
frame["timestamp"] = pd.to_datetime(frame["timestamp"])
|
||||
openmeteo = pd.to_numeric(
|
||||
frame.set_index("timestamp")["catchment_mean"], errors="coerce"
|
||||
)
|
||||
except Exception as error: # openmeteo_rain may not exist yet
|
||||
logger.warning(f"openmeteo_rain read failed: {error}")
|
||||
|
||||
def series_rows(s):
|
||||
if s is None:
|
||||
return []
|
||||
return [
|
||||
{
|
||||
"timestamp": ts.isoformat(),
|
||||
"rain_mm": None if pd.isna(v) else round(float(v), 2),
|
||||
}
|
||||
for ts, v in s.items()
|
||||
]
|
||||
|
||||
comparison = (
|
||||
hii_rain.compare_with_openmeteo(gauge, openmeteo)
|
||||
if gauge is not None and openmeteo is not None
|
||||
else {"overlap_hours": 0}
|
||||
)
|
||||
return {
|
||||
"box": hii_rain.CATCHMENT_BOX,
|
||||
"gauge": series_rows(gauge),
|
||||
"openmeteo": series_rows(openmeteo),
|
||||
"comparison_24h_sums": comparison,
|
||||
}
|
||||
|
||||
payload, stale = await _cached_swr(
|
||||
HII_CACHE,
|
||||
HII_CACHE_LOCK,
|
||||
_HII_COMPUTE_LOCKS["rain"],
|
||||
f"rain_catchment:{days}",
|
||||
Config.HII_CACHE_TTL_SECONDS,
|
||||
compute,
|
||||
)
|
||||
if stale:
|
||||
response.headers["X-Data-Stale"] = "true"
|
||||
return payload
|
||||
|
||||
|
||||
@app.get("/api/hii/waterlevel/latest")
|
||||
async def get_hii_waterlevel_latest(
|
||||
response: Response, hours: int = Query(26, ge=1, le=168)
|
||||
@@ -1043,9 +1201,7 @@ async def get_postgres_history(
|
||||
return cached[1]
|
||||
try:
|
||||
db_config = Config.get_database_config()
|
||||
end_time = (
|
||||
datetime.combine(end, datetime.max.time()) if end else datetime.now()
|
||||
)
|
||||
end_time = datetime.combine(end, datetime.max.time()) if end else datetime.now()
|
||||
start_time = (
|
||||
datetime.combine(start, datetime.min.time())
|
||||
if start
|
||||
@@ -1138,17 +1294,85 @@ async def get_forecast_history(
|
||||
store = app_state.get("forecast_store")
|
||||
if not store:
|
||||
return []
|
||||
end_dt = (
|
||||
datetime.combine(end, datetime.max.time()) if end else datetime.now()
|
||||
)
|
||||
end_dt = datetime.combine(end, datetime.max.time()) if end else datetime.now()
|
||||
start_dt = (
|
||||
datetime.combine(start, datetime.min.time())
|
||||
if start
|
||||
else end_dt - timedelta(hours=hours)
|
||||
)
|
||||
return await asyncio.to_thread(
|
||||
store.fetch, station_code, start_dt, end_dt, horizon
|
||||
return await asyncio.to_thread(store.fetch, station_code, start_dt, end_dt, horizon)
|
||||
|
||||
|
||||
@app.get("/api/notifications")
|
||||
async def get_notifications_config():
|
||||
"""Public ntfy settings so the dashboard can offer subscribe links."""
|
||||
server = Config.NTFY_SERVER
|
||||
if not server:
|
||||
return {"enabled": False}
|
||||
prefix = Config.NTFY_TOPIC_PREFIX
|
||||
return {
|
||||
"enabled": True,
|
||||
"server": server,
|
||||
"prefix": prefix,
|
||||
"topics": {
|
||||
"warning": f"{prefix}-warning",
|
||||
"danger": f"{prefix}-danger",
|
||||
"p1_outlook": f"{prefix}-p1-outlook",
|
||||
"status": f"{prefix}-status",
|
||||
"station_pattern": f"{prefix}-<station>-warning | {prefix}-<station>-danger (station code lowercase, no dot: p1, p103)",
|
||||
},
|
||||
"semantics": "transitions only: one message on crossing up, one all-clear on the way down (0.10 m hysteresis)",
|
||||
}
|
||||
|
||||
|
||||
@app.get("/api/forecast/skill")
|
||||
async def get_forecast_skill(
|
||||
response: Response,
|
||||
station_code: str = Query("P.1"),
|
||||
horizon: int = Query(24, ge=1, le=48),
|
||||
):
|
||||
"""Is the model getting better? Issued forecasts verified against what the
|
||||
river then did, per model version, with a persistence baseline.
|
||||
|
||||
Read from forecast_history (what each deployed version predicted, hourly)
|
||||
joined to water_measurements; no retraining involved. Cached like the HII
|
||||
feeds because the join is a few hundred correlated subqueries.
|
||||
"""
|
||||
increment_counter("api_requests", labels={"endpoint": "forecast_skill"})
|
||||
store = app_state.get("forecast_store")
|
||||
if not store:
|
||||
return {
|
||||
"station_code": station_code,
|
||||
"horizon_hours": horizon,
|
||||
"versions": [],
|
||||
"current": None,
|
||||
"trend": None,
|
||||
}
|
||||
|
||||
def compute():
|
||||
from .ml import skill
|
||||
|
||||
if not store.engine and not store.connect():
|
||||
return {
|
||||
"station_code": station_code,
|
||||
"horizon_hours": horizon,
|
||||
"versions": [],
|
||||
"current": None,
|
||||
"trend": None,
|
||||
}
|
||||
return skill.compute_skill(store.engine, store.db_type, station_code, horizon)
|
||||
|
||||
payload, stale = await _cached_swr(
|
||||
HII_CACHE,
|
||||
HII_CACHE_LOCK,
|
||||
_HII_COMPUTE_LOCKS["skill"],
|
||||
f"skill:{station_code}:{horizon}",
|
||||
max(Config.HII_CACHE_TTL_SECONDS, 900),
|
||||
compute,
|
||||
)
|
||||
if stale:
|
||||
response.headers["X-Data-Stale"] = "true"
|
||||
return payload
|
||||
|
||||
|
||||
@app.get("/measurements/latest", response_model=List[MeasurementResponse])
|
||||
@@ -1234,9 +1458,7 @@ async def get_database_stats():
|
||||
from sqlalchemy import text
|
||||
|
||||
with engine.connect() as conn:
|
||||
return conn.execute(
|
||||
text(
|
||||
"""
|
||||
return conn.execute(text("""
|
||||
SELECT (SELECT COUNT(*) FROM hii_rainfall) AS rain_n,
|
||||
(SELECT COUNT(*) FROM hii_waterlevel) AS wl_n,
|
||||
(SELECT COUNT(*) FROM hii_rain_stations) AS rain_s,
|
||||
@@ -1245,9 +1467,7 @@ async def get_database_stats():
|
||||
(SELECT MAX(timestamp) FROM hii_rainfall) AS rain_hi,
|
||||
(SELECT MIN(timestamp) FROM hii_waterlevel) AS wl_lo,
|
||||
(SELECT MAX(timestamp) FROM hii_waterlevel) AS wl_hi
|
||||
"""
|
||||
)
|
||||
).one()
|
||||
""")).one()
|
||||
|
||||
def compute():
|
||||
# Heavy: full-table counts and coverage over ~1.7M rows. Runs at most
|
||||
|
||||
@@ -233,6 +233,75 @@ def test_heuristic_fallback(tmp_path):
|
||||
assert row["trained_at"] is None
|
||||
|
||||
|
||||
def _p1_synth(n: int = 300, seed: int = 11) -> pd.DataFrame:
|
||||
upstream = [code for code, _lead in features.UPSTREAM_LEADS["P.1"]]
|
||||
return make_synth(n, ["P.1"] + upstream, seed=seed, pulses={"P.1": [(100, 20, 2.0)]})
|
||||
|
||||
|
||||
def test_train_refuses_silent_rain_downgrade(tmp_path, monkeypatch):
|
||||
"""use_rain=True with no rain series must abort, not write v2 bundles.
|
||||
|
||||
Regression for the 2026-09-01 server retrain that overwrote v3 with v2
|
||||
because the Open-Meteo archive fetch failed on a cache-less checkout.
|
||||
"""
|
||||
from src.ml import rain as rain_mod
|
||||
|
||||
df = _p1_synth()
|
||||
overrides = {"max_iter": 10}
|
||||
|
||||
# Case 1: the loader returns None (archive unreachable, no cache file)
|
||||
monkeypatch.setattr(rain_mod, "load_history", lambda *a, **k: None)
|
||||
with pytest.raises(train.RainUnavailableError, match="--no-rain"):
|
||||
train.train_all(df, ["P.1"], models_dir=tmp_path, skip_eval=True, hgb_overrides=overrides, use_rain=True, use_dam=False)
|
||||
assert not (tmp_path / "flood_P.1.joblib").exists()
|
||||
assert not (tmp_path / "metrics.json").exists()
|
||||
|
||||
# Case 2: the loader raises (network / parse error)
|
||||
def boom(*a, **k):
|
||||
raise ConnectionError("simulated Open-Meteo outage")
|
||||
|
||||
monkeypatch.setattr(rain_mod, "load_history", boom)
|
||||
with pytest.raises(train.RainUnavailableError, match="simulated Open-Meteo outage"):
|
||||
train.train_all(df, ["P.1"], models_dir=tmp_path, skip_eval=True, hgb_overrides=overrides, use_rain=True, use_dam=False)
|
||||
assert not (tmp_path / "flood_P.1.joblib").exists()
|
||||
|
||||
# Explicit opt-out still produces v2 bundles as before
|
||||
metrics = train.train_all(df, ["P.1"], models_dir=tmp_path, skip_eval=True, hgb_overrides=overrides, use_rain=False, use_dam=False)
|
||||
assert metrics["model_version"].startswith("hgb-v2+")
|
||||
assert (tmp_path / "flood_P.1.joblib").exists()
|
||||
|
||||
|
||||
def test_train_with_rain_series_yields_v3(tmp_path, monkeypatch):
|
||||
from src.ml import rain as rain_mod
|
||||
|
||||
df = _p1_synth()
|
||||
idx = pd.date_range(df["timestamp"].min(), df["timestamp"].max(), freq="h")
|
||||
fake_rain = pd.DataFrame({"a": np.linspace(0, 1, len(idx)), "b": 0.5}, index=idx)
|
||||
monkeypatch.setattr(rain_mod, "load_history", lambda *a, **k: fake_rain)
|
||||
|
||||
metrics = train.train_all(df, ["P.1"], models_dir=tmp_path, skip_eval=True, hgb_overrides={"max_iter": 10}, use_rain=True, use_dam=False)
|
||||
assert metrics["model_version"].startswith("hgb-v3+")
|
||||
bundle = joblib.load(tmp_path / "flood_P.1.joblib")
|
||||
assert set(features.RAIN_FEATURES) <= set(bundle["feature_names"])
|
||||
|
||||
|
||||
def test_cli_exit_code_on_rain_failure(tmp_path, monkeypatch, caplog):
|
||||
"""The console entry turns the guard into a one-line error and exit 2."""
|
||||
from src.ml import rain as rain_mod
|
||||
|
||||
df = _p1_synth()
|
||||
monkeypatch.setattr(rain_mod, "load_history", lambda *a, **k: None)
|
||||
monkeypatch.setattr(train, "load_measurements", lambda *a, **k: df)
|
||||
monkeypatch.setattr(train, "resolve_db_url", lambda *a, **k: None)
|
||||
monkeypatch.setattr(
|
||||
"sys.argv",
|
||||
["train", "--stations", "P.1", "--models-dir", str(tmp_path), "--skip-eval"],
|
||||
)
|
||||
assert train.cli() == 2
|
||||
assert "refusing to silently downgrade" in caplog.text
|
||||
assert not (tmp_path / "metrics.json").exists()
|
||||
|
||||
|
||||
def test_feature_name_stability(tmp_path):
|
||||
upstream = [code for code, _lead in features.UPSTREAM_LEADS["P.1"]]
|
||||
data_stations = ["P.1"] + upstream
|
||||
|
||||
@@ -0,0 +1,93 @@
|
||||
"""Forecast skill verification: issued forecasts vs observed peaks (sqlite)."""
|
||||
|
||||
import datetime
|
||||
|
||||
import pytest
|
||||
from sqlalchemy import create_engine, text
|
||||
|
||||
from src.ml import skill
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def engine(tmp_path):
|
||||
eng = create_engine(f"sqlite:///{tmp_path / 'skill.db'}")
|
||||
with eng.begin() as c:
|
||||
c.execute(text("CREATE TABLE stations (id INTEGER PRIMARY KEY, station_code TEXT)"))
|
||||
c.execute(text("INSERT INTO stations VALUES (1, 'P.1')"))
|
||||
c.execute(
|
||||
text(
|
||||
"CREATE TABLE water_measurements (timestamp DATETIME, station_id INTEGER, water_level REAL)"
|
||||
)
|
||||
)
|
||||
c.execute(
|
||||
text(
|
||||
"CREATE TABLE forecast_history (as_of TIMESTAMP, station_code TEXT, horizon_hours INTEGER, "
|
||||
"predicted_max_level REAL, p_warning REAL, p_danger REAL, current_level REAL, "
|
||||
"model_version TEXT, source TEXT)"
|
||||
)
|
||||
)
|
||||
return eng
|
||||
|
||||
|
||||
def _fill(engine, start, hours, level_fn, forecasts):
|
||||
"""hours of hourly observations from `start`, plus (as_of_offset_h, version, pred) rows."""
|
||||
with engine.begin() as c:
|
||||
for h in range(hours):
|
||||
ts = start + datetime.timedelta(hours=h)
|
||||
c.execute(
|
||||
text("INSERT INTO water_measurements VALUES (:t, 1, :l)"),
|
||||
{"t": ts, "l": level_fn(h)},
|
||||
)
|
||||
for off, version, pred in forecasts:
|
||||
ts = start + datetime.timedelta(hours=off)
|
||||
c.execute(
|
||||
text(
|
||||
"INSERT INTO forecast_history VALUES (:t, 'P.1', 24, :p, 0, 0, :cur, :v, 'model')"
|
||||
),
|
||||
{"t": ts, "p": pred, "cur": level_fn(off), "v": version},
|
||||
)
|
||||
|
||||
|
||||
def test_skill_per_version_and_trend(engine):
|
||||
start = datetime.datetime(2026, 8, 1)
|
||||
# river: flat 1.5 m, with a bump to 2.4 m around hour 100
|
||||
level = lambda h: 2.4 if 96 <= h <= 104 else 1.5
|
||||
forecasts = []
|
||||
# old version: always predicts 1.5 (persistence-like, misses the bump)
|
||||
for off in range(0, 60):
|
||||
forecasts.append((off, "hgb-v2+aaaaaaa", 1.5))
|
||||
# new version: predicts 1.5 normally and 2.3 ahead of the bump
|
||||
for off in range(60, 200):
|
||||
pred = 2.3 if 72 <= off <= 104 else 1.5
|
||||
forecasts.append((off, "hgb-v3+bbbbbbb", pred))
|
||||
_fill(engine, start, 260, level, forecasts)
|
||||
|
||||
out = skill.compute_skill(engine, "sqlite", "P.1", 24, now=start + datetime.timedelta(hours=300))
|
||||
assert [v["model_version"] for v in out["versions"]] == ["hgb-v2+aaaaaaa", "hgb-v3+bbbbbbb"]
|
||||
old, new = out["versions"]
|
||||
assert old["n"] == 60 and old["enough_data"]
|
||||
assert new["n"] == 140 and new["enough_data"]
|
||||
# the old version issued only on flat hours: perfect there, no bump rows
|
||||
assert old["mae_m"] == 0.0 and old["above_2m_n"] == 0
|
||||
# the new version saw the bump: nonzero MAE but positive skill vs persistence
|
||||
assert new["above_2m_n"] > 0
|
||||
assert new["skill"] is not None and new["skill"] > 0
|
||||
assert out["current"]["model_version"] == "hgb-v3+bbbbbbb"
|
||||
assert out["trend"]["previous_version"] == "hgb-v2+aaaaaaa"
|
||||
assert out["trend"]["better"] is False # honest: old had an easier period
|
||||
|
||||
|
||||
def test_skill_requires_full_window(engine):
|
||||
start = datetime.datetime(2026, 8, 1)
|
||||
# forecasts issued at the very end have no observed window yet
|
||||
_fill(engine, start, 30, lambda h: 1.5, [(o, "hgb-v3+ccccccc", 1.5) for o in range(0, 30)])
|
||||
out = skill.compute_skill(engine, "sqlite", "P.1", 24, now=start + datetime.timedelta(hours=30))
|
||||
# only as_of <= now-24h AND with >= 18 observed hours in the window count
|
||||
assert out["versions"] and out["versions"][0]["n"] == 7 # as_of 0..6 h: <= now-24h with >= 18 observed hours
|
||||
assert out["versions"][0]["enough_data"] is False
|
||||
assert out["trend"] is None
|
||||
|
||||
|
||||
def test_skill_empty(engine):
|
||||
out = skill.compute_skill(engine, "sqlite", "P.1", 24)
|
||||
assert out["versions"] == [] and out["current"] is None and out["trend"] is None
|
||||
@@ -353,6 +353,29 @@ class TestHiiApiEndpoints:
|
||||
self._get(web_api, "get_hii_rainfall_latest", hours=48)
|
||||
assert calls["n"] == 2
|
||||
|
||||
def test_rainfall_catchment(self, web_api):
|
||||
"""One gauge in the box (CHM005, 19.12N 98.94E) is below the
|
||||
MIN_GAUGES_PER_HOUR floor, so the catchment mean is NaN -> null, the
|
||||
openmeteo_rain table does not exist in this store, and the comparison
|
||||
reports no overlap. Shape is what matters: the endpoint must not 500
|
||||
on a fresh database."""
|
||||
payload, response = self._get(web_api, "get_hii_rainfall_catchment", days=7)
|
||||
assert "x-data-stale" not in response.headers
|
||||
assert list(payload) == ["box", "gauge", "openmeteo", "comparison_24h_sums"]
|
||||
assert payload["openmeteo"] == []
|
||||
assert payload["comparison_24h_sums"] == {"overlap_hours": 0}
|
||||
assert len(payload["gauge"]) == 1
|
||||
assert payload["gauge"][0]["rain_mm"] is None # < MIN_GAUGES_PER_HOUR
|
||||
|
||||
def test_rainfall_catchment_disabled(self, monkeypatch):
|
||||
from src import web_api
|
||||
|
||||
monkeypatch.setitem(web_api.app_state, "hii_collector", None)
|
||||
web_api.HII_CACHE.clear()
|
||||
web_api._REFRESH_IN_FLIGHT.clear()
|
||||
payload, _ = self._get(web_api, "get_hii_rainfall_catchment", days=7)
|
||||
assert payload["gauge"] == [] and payload["openmeteo"] == []
|
||||
|
||||
def test_stale_served_on_recompute_failure(self, web_api, monkeypatch):
|
||||
# Prime the cache, expire it, break the DB: the stale copy is served
|
||||
# and flagged via the X-Data-Stale header.
|
||||
|
||||
@@ -0,0 +1,47 @@
|
||||
"""HII gauge-rain aggregate: pure-function tests (no DB)."""
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
|
||||
from src.ml import hii_rain
|
||||
|
||||
|
||||
def _hourly(start, n):
|
||||
return pd.date_range(start, periods=n, freq="h")
|
||||
|
||||
|
||||
def test_compare_identical_series_has_zero_bias():
|
||||
idx = _hourly("2026-08-12", 200)
|
||||
rng = np.random.default_rng(1)
|
||||
rain = pd.Series(rng.exponential(0.5, len(idx)), index=idx)
|
||||
out = hii_rain.compare_with_openmeteo(rain, rain.copy(), window_h=24)
|
||||
assert out["overlap_hours"] == 200
|
||||
assert out["bias_mm"] == 0.0
|
||||
assert out["mae_mm"] == 0.0
|
||||
assert out["corr"] > 0.999
|
||||
|
||||
|
||||
def test_compare_reports_constant_bias():
|
||||
idx = _hourly("2026-08-12", 100)
|
||||
gauge = pd.Series(1.0, index=idx)
|
||||
model = pd.Series(1.5, index=idx) # model wetter by 0.5 mm/h
|
||||
out = hii_rain.compare_with_openmeteo(gauge, model, window_h=24)
|
||||
assert abs(out["bias_mm"] - 12.0) < 1e-9 # 0.5 mm/h x 24 h
|
||||
|
||||
|
||||
def test_compare_uses_overlap_only():
|
||||
gauge = pd.Series(1.0, index=_hourly("2026-08-12", 100))
|
||||
model = pd.Series(1.0, index=_hourly("2026-08-14", 100)) # 52 h overlap
|
||||
out = hii_rain.compare_with_openmeteo(gauge, model, window_h=24)
|
||||
assert out["overlap_hours"] == 52
|
||||
|
||||
|
||||
def test_compare_no_overlap():
|
||||
gauge = pd.Series(1.0, index=_hourly("2026-01-01", 10))
|
||||
model = pd.Series(1.0, index=_hourly("2026-06-01", 10))
|
||||
assert hii_rain.compare_with_openmeteo(gauge, model) == {"overlap_hours": 0}
|
||||
|
||||
|
||||
def test_load_gauge_mean_without_db_returns_none(monkeypatch):
|
||||
monkeypatch.setattr(hii_rain, "resolve_db_url", lambda *a, **k: None)
|
||||
assert hii_rain.load_gauge_mean() is None
|
||||
@@ -0,0 +1,285 @@
|
||||
"""ntfy notification state machine: transitions only, hysteresis, restart-safe."""
|
||||
|
||||
import datetime
|
||||
|
||||
import pytest
|
||||
|
||||
from src import notify
|
||||
|
||||
|
||||
class FakePublisher(notify.NtfyPublisher):
|
||||
def __init__(self):
|
||||
super().__init__("http://ntfy.test", prefix="ping")
|
||||
self.sent = []
|
||||
|
||||
def publish(self, n):
|
||||
self.sent.append(n)
|
||||
return True
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def pub():
|
||||
return FakePublisher()
|
||||
|
||||
|
||||
def _reading(code, level, ts="2026-09-24T12:00:00"):
|
||||
return {"station_code": code, "water_level": level, "timestamp": ts}
|
||||
|
||||
|
||||
def _fc(p, peak=None):
|
||||
return [
|
||||
{
|
||||
"station_code": "P.1",
|
||||
"horizon_hours": 24,
|
||||
"p_warning": p,
|
||||
"predicted_max_level": peak,
|
||||
"source": "model",
|
||||
}
|
||||
]
|
||||
|
||||
|
||||
NOW = datetime.datetime(2026, 9, 24, 12, 30)
|
||||
|
||||
|
||||
def topics(pub):
|
||||
return [n.topic for n in pub.sent]
|
||||
|
||||
|
||||
def test_quiet_river_sends_nothing(pub):
|
||||
state = notify.InMemoryState()
|
||||
for h in range(48):
|
||||
notify.evaluate(
|
||||
[_reading("P.1", 1.6), _reading("P.103", 3.2)],
|
||||
_fc(0.01),
|
||||
state,
|
||||
pub,
|
||||
now=NOW,
|
||||
)
|
||||
assert pub.sent == []
|
||||
|
||||
|
||||
def test_warning_crossing_once_then_silence_then_clear(pub):
|
||||
state = notify.InMemoryState()
|
||||
# rising through 3.70 (P.1 warning)
|
||||
notify.evaluate([_reading("P.1", 3.65)], [], state, pub, now=NOW)
|
||||
assert pub.sent == []
|
||||
notify.evaluate([_reading("P.1", 3.72)], [], state, pub, now=NOW)
|
||||
assert topics(pub) == ["ping-p1-warning", "ping-warning"]
|
||||
assert pub.sent[0].priority == 4 and "3.72 m" in pub.sent[0].message
|
||||
# stays above: no repeats for many hours
|
||||
for level in (3.80, 3.95, 4.05, 3.90, 3.75):
|
||||
notify.evaluate([_reading("P.1", level)], [], state, pub, now=NOW)
|
||||
assert len(pub.sent) == 2
|
||||
# dips to 3.65: within hysteresis, still no message
|
||||
notify.evaluate([_reading("P.1", 3.65)], [], state, pub, now=NOW)
|
||||
assert len(pub.sent) == 2
|
||||
# 3.55: clear
|
||||
notify.evaluate([_reading("P.1", 3.55)], [], state, pub, now=NOW)
|
||||
assert topics(pub)[2:] == ["ping-p1-warning", "ping-warning"]
|
||||
assert "back to normal" in pub.sent[2].title
|
||||
|
||||
|
||||
def test_danger_escalation_and_deescalation(pub):
|
||||
state = notify.InMemoryState()
|
||||
notify.evaluate([_reading("P.1", 3.9)], [], state, pub, now=NOW) # warning
|
||||
notify.evaluate(
|
||||
[_reading("P.1", 4.25)], [], state, pub, now=NOW
|
||||
) # danger (>= 4.20)
|
||||
assert topics(pub) == [
|
||||
"ping-p1-warning",
|
||||
"ping-warning",
|
||||
"ping-p1-danger",
|
||||
"ping-danger",
|
||||
]
|
||||
assert pub.sent[2].priority == 5
|
||||
notify.evaluate(
|
||||
[_reading("P.1", 4.15)], [], state, pub, now=NOW
|
||||
) # hysteresis: still danger
|
||||
assert len(pub.sent) == 4
|
||||
notify.evaluate([_reading("P.1", 4.05)], [], state, pub, now=NOW) # back to warning
|
||||
assert topics(pub)[4:] == ["ping-p1-danger", "ping-warning"]
|
||||
assert "below danger" in pub.sent[4].title
|
||||
|
||||
|
||||
def test_jump_straight_to_danger(pub):
|
||||
state = notify.InMemoryState()
|
||||
notify.evaluate(
|
||||
[_reading("P.103", 7.0)], [], state, pub, now=NOW
|
||||
) # P.103 danger 6.75
|
||||
assert topics(pub) == ["ping-p103-danger", "ping-danger"]
|
||||
|
||||
|
||||
def test_basin_digest_groups_stations(pub):
|
||||
state = notify.InMemoryState()
|
||||
notify.evaluate(
|
||||
[_reading("P.1", 3.8), _reading("P.103", 6.0), _reading("P.67", 1.0)],
|
||||
[],
|
||||
state,
|
||||
pub,
|
||||
now=NOW,
|
||||
)
|
||||
basin = [n for n in pub.sent if n.topic == "ping-warning"]
|
||||
assert len(basin) == 1 and "P.1" in basin[0].message and "P.103" in basin[0].message
|
||||
|
||||
|
||||
def test_outlook_on_off_with_hysteresis(pub):
|
||||
state = notify.InMemoryState()
|
||||
r = [_reading("P.1", 2.9)]
|
||||
notify.evaluate(r, _fc(0.30), state, pub, now=NOW)
|
||||
assert pub.sent == []
|
||||
notify.evaluate(r, _fc(0.55, 3.9), state, pub, now=NOW)
|
||||
assert topics(pub) == ["ping-p1-outlook"]
|
||||
assert "55%" in pub.sent[0].message and "3.90 m" in pub.sent[0].message
|
||||
assert "not an official warning" in pub.sent[0].message
|
||||
notify.evaluate(
|
||||
r, _fc(0.40), state, pub, now=NOW
|
||||
) # between OFF and ON: stays on, silent
|
||||
assert len(pub.sent) == 1
|
||||
notify.evaluate(r, _fc(0.20), state, pub, now=NOW)
|
||||
assert len(pub.sent) == 2 and "easing" in pub.sent[1].title
|
||||
|
||||
|
||||
def test_heuristic_forecast_ignored(pub):
|
||||
state = notify.InMemoryState()
|
||||
fc = [
|
||||
{
|
||||
"station_code": "P.1",
|
||||
"horizon_hours": 24,
|
||||
"p_warning": 0.9,
|
||||
"source": "heuristic",
|
||||
}
|
||||
]
|
||||
notify.evaluate([_reading("P.1", 2.0)], fc, state, pub, now=NOW)
|
||||
assert pub.sent == []
|
||||
|
||||
|
||||
def test_stale_feed_and_recovery(pub):
|
||||
state = notify.InMemoryState()
|
||||
notify.evaluate(
|
||||
[_reading("P.1", 1.6, "2026-09-24T12:00:00")], [], state, pub, now=NOW
|
||||
)
|
||||
assert pub.sent == []
|
||||
later = NOW + datetime.timedelta(hours=4)
|
||||
notify.evaluate(
|
||||
[_reading("P.1", 1.6, "2026-09-24T12:00:00")], [], state, pub, now=later
|
||||
)
|
||||
assert topics(pub) == ["ping-status"] and "stale" in pub.sent[0].title
|
||||
notify.evaluate(
|
||||
[_reading("P.1", 1.6, "2026-09-24T12:00:00")],
|
||||
[],
|
||||
state,
|
||||
pub,
|
||||
now=later + datetime.timedelta(hours=1),
|
||||
)
|
||||
assert len(pub.sent) == 1 # still stale, no repeat
|
||||
notify.evaluate(
|
||||
[_reading("P.1", 1.6, "2026-09-24T17:00:00")],
|
||||
[],
|
||||
state,
|
||||
pub,
|
||||
now=later + datetime.timedelta(hours=1),
|
||||
)
|
||||
assert len(pub.sent) == 2 and "recovered" in pub.sent[1].title
|
||||
|
||||
|
||||
def test_capacity_guard_blocks_stale_threshold(pub):
|
||||
"""P.77 2026-09: 3.02 m >= 2.85 m 'warning' at 22 % capacity -> not a flood."""
|
||||
state = notify.InMemoryState()
|
||||
r = {
|
||||
"station_code": "P.77",
|
||||
"water_level": 4.40,
|
||||
"timestamp": "2026-09-24T12:00:00",
|
||||
"discharge_percent": 10.3,
|
||||
}
|
||||
notify.evaluate([r], [], state, pub, now=NOW)
|
||||
assert pub.sent == [] and state.get("level:P.77") is None
|
||||
# same level with capacity agreeing -> alert
|
||||
r["discharge_percent"] = 82.0
|
||||
notify.evaluate([r], [], state, pub, now=NOW)
|
||||
assert topics(pub) == ["ping-p77-warning", "ping-warning"]
|
||||
|
||||
|
||||
def test_capacity_guard_exempts_p1_and_missing_pct(pub):
|
||||
state = notify.InMemoryState()
|
||||
notify.evaluate(
|
||||
[
|
||||
{
|
||||
"station_code": "P.1",
|
||||
"water_level": 3.75,
|
||||
"timestamp": "2026-09-24T12:00:00",
|
||||
"discharge_percent": 40.0,
|
||||
}
|
||||
],
|
||||
[],
|
||||
state,
|
||||
pub,
|
||||
now=NOW,
|
||||
)
|
||||
assert topics(pub) == ["ping-p1-warning", "ping-warning"]
|
||||
pub.sent.clear()
|
||||
notify.evaluate(
|
||||
[
|
||||
{
|
||||
"station_code": "P.103",
|
||||
"water_level": 6.0,
|
||||
"timestamp": "2026-09-24T12:00:00",
|
||||
}
|
||||
],
|
||||
[],
|
||||
state,
|
||||
pub,
|
||||
now=NOW,
|
||||
)
|
||||
assert topics(pub) == ["ping-p103-warning", "ping-warning"]
|
||||
|
||||
|
||||
def test_capacity_guard_does_not_block_clearing(pub):
|
||||
"""Guard applies only to the clear->alert edge; the all-clear always goes out."""
|
||||
state = notify.InMemoryState()
|
||||
r = {
|
||||
"station_code": "P.67",
|
||||
"water_level": 2.6,
|
||||
"timestamp": "2026-09-24T12:00:00",
|
||||
"discharge_percent": 90.0,
|
||||
}
|
||||
notify.evaluate([r], [], state, pub, now=NOW)
|
||||
assert len(pub.sent) == 2
|
||||
r.update(water_level=2.2, discharge_percent=30.0)
|
||||
notify.evaluate([r], [], state, pub, now=NOW)
|
||||
assert "back to normal" in pub.sent[2].title
|
||||
|
||||
|
||||
def test_state_survives_restart_via_sql(tmp_path, pub):
|
||||
from sqlalchemy import create_engine
|
||||
|
||||
eng = create_engine(f"sqlite:///{tmp_path / 'n.db'}")
|
||||
state = notify.NotificationState(eng, "sqlite")
|
||||
notify.evaluate([_reading("P.1", 3.8)], [], state, pub, now=NOW)
|
||||
assert len(pub.sent) == 2
|
||||
# "restart": new state object on the same DB, same reading -> nothing re-sent
|
||||
state2 = notify.NotificationState(eng, "sqlite")
|
||||
notify.evaluate([_reading("P.1", 3.8)], [], state2, pub, now=NOW)
|
||||
assert len(pub.sent) == 2
|
||||
|
||||
|
||||
def test_publish_failure_does_not_advance_state():
|
||||
"""If ntfy is down the transition must be retried next cycle, not lost."""
|
||||
|
||||
class Down(notify.NtfyPublisher):
|
||||
def __init__(self):
|
||||
super().__init__("http://ntfy.test")
|
||||
self.calls = 0
|
||||
|
||||
def publish(self, n):
|
||||
self.calls += 1
|
||||
return False
|
||||
|
||||
pub = Down()
|
||||
state = notify.InMemoryState()
|
||||
notify.evaluate([_reading("P.1", 3.8)], [], state, pub, now=NOW)
|
||||
assert pub.calls == 2 and state.get("level:P.1") is None
|
||||
# next cycle, ntfy back: the crossing is delivered
|
||||
good = FakePublisher()
|
||||
notify.evaluate([_reading("P.1", 3.8)], [], state, good, now=NOW)
|
||||
assert topics(good) == ["ping-p1-warning", "ping-warning"]
|
||||
assert state.get("level:P.1") == "warning"
|
||||
Reference in New Issue
Block a user