Files
grabowski ba781465a9
CI/CD Pipeline - Northern Thailand Ping River Monitor / Test Suite (3.11) (push) Failing after 25s
CI/CD Pipeline - Northern Thailand Ping River Monitor / Build Docker Image (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Integration Test with Services (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Deploy to Staging (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Deploy to Production (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Performance Test (push) Skipped
CI/CD Pipeline - Northern Thailand Ping River Monitor / Code Quality (push) Successful in 12s
Documentation / Generate API Documentation (push) Successful in 8s
Documentation / Build Sphinx Documentation (push) Successful in 15s
CI/CD Pipeline - Northern Thailand Ping River Monitor / Cleanup (push) Successful in 1s
Documentation / Documentation Summary (push) Successful in 2s
Documentation / Validate Documentation (push) Failing after 7s
feat: in-memory HII gap-fill in the ML data loader
load_measurements() (DB path) patches missing station-hours from the
hii_waterlevel mirror telemetry: exact mirrors (P.1/P.103/P.20/P.4A/P.67/
P.75/P.82/P.84/P.92) plus bias-corrected P.81 (+9,340 h). Per-station
MSL->gauge offset is derived from >=168 h of series overlap, which
reproduces the published offsets for exact mirrors and absorbs P.81's
bias; P.76/P.77/P.85/P.87 HII twins are different physical sensors and
stay excluded. Training and serving share the loader, so both sides see
identical filled series; water_measurements is never written.
2026-08-13 10:29:54 +07:00

125 lines
4.5 KiB
Python

"""Tests for the in-memory HII gap-fill in the ML data loader."""
import datetime
import numpy as np
import pandas as pd
import pytest
from src.hii_collector import HiiStore
from src.ml.data import fill_from_hii
START = datetime.datetime(2024, 9, 1, 0, 0)
def _hours(n, offset=0):
return [START + datetime.timedelta(hours=offset + i) for i in range(n)]
def _base_frame(code="P.20", n=200, level=2.0):
return pd.DataFrame(
{
"timestamp": _hours(n),
"station_code": code,
"water_level": level,
"discharge": 100.0,
}
)
@pytest.fixture
def hii_db(tmp_path):
"""SQLite DB with hii_* tables; returns (db_url, store)."""
db_url = f"sqlite:///{tmp_path}/hii_fill.db"
store = HiiStore(db_url, "sqlite")
assert store.connect()
return db_url, store
def _seed_mirror(store, station_id, rid_code, hours, wl_msl, discharge=250.0):
from sqlalchemy import text
with store.engine.begin() as conn:
conn.execute(
text("INSERT INTO hii_wl_stations (id, rid_code) VALUES (:i, :c)"),
{"i": station_id, "c": rid_code},
)
conn.execute(
text(
"INSERT INTO hii_waterlevel (station_id, timestamp, wl_msl, discharge) "
"VALUES (:i, :t, :w, :d)"
),
[
{"i": station_id, "t": t, "w": w, "d": discharge}
for t, w in zip(hours, wl_msl)
],
)
class TestFillFromHii:
def test_exact_mirror_fills_missing_hours(self, hii_db):
db_url, store = hii_db
base = _base_frame("P.20", n=200, level=2.0)
# Mirror covers the base window plus 48 extra hours, at MSL offset +300
_seed_mirror(store, 1, "P.20", _hours(248), [302.0] * 248)
filled = fill_from_hii(base, db_url, min_overlap_hours=168)
p20 = filled[filled["station_code"] == "P.20"]
assert len(p20) == 248
new_rows = p20[p20["timestamp"] >= START + datetime.timedelta(hours=200)]
assert len(new_rows) == 48
# MSL converted back to gauge datum via the overlap-derived offset
assert new_rows["water_level"].round(6).eq(2.0).all()
# Exact mirrors copy discharge
assert new_rows["discharge"].eq(250.0).all()
def test_p81_bias_corrected_without_discharge(self, hii_db):
db_url, store = hii_db
base = _base_frame("P.81", n=200, level=1.5)
# Biased mirror: offset 310.2 (not a published offset — derived only)
_seed_mirror(store, 2, "P.81", _hours(230), [311.7] * 230)
filled = fill_from_hii(base, db_url, min_overlap_hours=168)
p81 = filled[filled["station_code"] == "P.81"]
new_rows = p81[p81["timestamp"] >= START + datetime.timedelta(hours=200)]
assert len(new_rows) == 30
assert new_rows["water_level"].round(6).eq(1.5).all()
assert new_rows["discharge"].isna().all()
def test_insufficient_overlap_skips_station(self, hii_db):
db_url, store = hii_db
base = _base_frame("P.20", n=50) # only 50 shared hours
_seed_mirror(store, 1, "P.20", _hours(100), [302.0] * 100)
filled = fill_from_hii(base, db_url, min_overlap_hours=168)
assert len(filled) == len(base)
def test_nan_level_rows_are_replaced(self, hii_db):
db_url, store = hii_db
base = _base_frame("P.20", n=200, level=2.0)
base.loc[10, "water_level"] = np.nan
_seed_mirror(store, 1, "P.20", _hours(200), [302.5] * 200)
filled = fill_from_hii(base, db_url, min_overlap_hours=168)
p20 = filled[filled["station_code"] == "P.20"]
assert len(p20) == 200 # no duplicate hour
replaced = p20[p20["timestamp"] == START + datetime.timedelta(hours=10)]
assert replaced["water_level"].round(6).eq(2.0).all()
def test_never_merged_station_untouched(self, hii_db):
db_url, store = hii_db
base = _base_frame("P.76", n=200, level=1.0)
_seed_mirror(store, 3, "P.76", _hours(300), [301.0] * 300)
filled = fill_from_hii(base, db_url, min_overlap_hours=1)
assert len(filled) == len(base) # P.76 not in HII_FILL_STATIONS
def test_missing_tables_degrade_gracefully(self, tmp_path):
base = _base_frame("P.20")
filled = fill_from_hii(base, f"sqlite:///{tmp_path}/empty.db")
assert filled.equals(base)
def test_no_station_overlap_returns_input(self, hii_db):
db_url, _ = hii_db
base = _base_frame("P.5") # not fillable
assert fill_from_hii(base, db_url).equals(base)