Emi Griffith
7aaad17603
climate.py repeated the same four mechanical patterns:
- the Open-Meteo daily params dict (3x) -> _om_daily_params(cell, **window)
- the doy attach line (6x) -> _with_doy
- makedirs + drop-doy + zstd to_parquet (3x) -> _write_cache
- the identical _to_frame/_nasa_to_frame tail (feels-like, valid-day
filter, doy) -> _finalize_frame
grading.py encoded the tier tables twice — TEMP_BANDS/RAIN_BANDS plus the
hand-aligned _TEMP_LADDER/_RAIN_LADDER ('kept aligned' by comment). The
ladders are now derived from the bands (_ladder_from; verified
byte-identical to the old tables before landing), so tier boundaries have
exactly one definition. grade_range's inline dry-streak walk is replaced
with the existing dry_streaks(); its per-(doy,var) sample cache now also
memoizes the window mask per doy instead of recomputing it once per
metric (9x per day-of-year).
New tests pin the refactor: _to_frame schema/day-filter/missing-series
tolerance, the combined feels-like side selection, NASA unit conversions
and fill-sentinel handling, _om_daily_params windows, and _write_cache
stripping the derived doy column.
82 lines
3.4 KiB
Python
82 lines
3.4 KiB
Python
"""The source→frame mappings and cache-write path (pure parts of climate.py —
|
|
no network)."""
|
|
import numpy as np
|
|
import pandas as pd
|
|
|
|
import climate
|
|
|
|
|
|
def _om_daily(n=3):
|
|
"""A minimal Open-Meteo daily response."""
|
|
return {
|
|
"time": [f"2026-06-{d:02d}" for d in range(1, n + 1)],
|
|
"temperature_2m_max": [80.0, 90.0, None],
|
|
"temperature_2m_min": [60.0, 70.0, 55.0],
|
|
"precipitation_sum": [0.0, 0.25, 0.1],
|
|
"wind_speed_10m_max": [10.0, 20.0, 5.0],
|
|
"wind_gusts_10m_max": [15.0, 30.0, 8.0],
|
|
"apparent_temperature_max": [82.0, 95.0, 70.0],
|
|
"apparent_temperature_min": [58.0, 68.0, 50.0],
|
|
"relative_humidity_2m_mean": [50.0, 60.0, 70.0],
|
|
}
|
|
|
|
|
|
def test_to_frame_schema_and_day_filter():
|
|
df = climate._to_frame(_om_daily())
|
|
# The None tmax day is dropped: a usable climate day needs a real high/low.
|
|
assert len(df) == 2
|
|
assert df["doy"].dtype == np.int16
|
|
assert set(df.columns) == {"date", "tmax", "tmin", "precip", "wind", "gust",
|
|
"humid", "fmax", "fmin", "feels", "doy"}
|
|
|
|
|
|
def test_to_frame_tolerates_missing_series():
|
|
daily = _om_daily()
|
|
del daily["wind_gusts_10m_max"], daily["relative_humidity_2m_mean"]
|
|
df = climate._to_frame(daily)
|
|
assert df["gust"].isna().all() and df["humid"].isna().all()
|
|
assert df["tmax"].notna().all() # required series unaffected
|
|
|
|
|
|
def test_combined_feels_picks_the_extreme_side():
|
|
df = climate._to_frame(_om_daily())
|
|
# Day 2: fmax 95 is 30 past the 65°F comfort point vs fmin 68 only 3 below —
|
|
# the hot side wins; both days here are hot-side days.
|
|
assert df.loc[df["date"] == "2026-06-02", "feels"].item() == 95.0
|
|
|
|
|
|
def test_nasa_to_frame_converts_units_and_fills():
|
|
param = {
|
|
"T2M_MAX": {"20260601": 30.0, "20260602": -999.0}, # °C; -999 = missing
|
|
"T2M_MIN": {"20260601": 20.0, "20260602": 15.0},
|
|
"PRECTOTCORR": {"20260601": 25.4, "20260602": 0.0}, # mm
|
|
"WS10M_MAX": {"20260601": 10.0, "20260602": 5.0}, # m/s
|
|
"RH2M": {"20260601": 50.0, "20260602": 60.0},
|
|
}
|
|
df = climate._nasa_to_frame(param)
|
|
assert len(df) == 1 # the missing-tmax day dropped
|
|
row = df.iloc[0]
|
|
assert row["tmax"] == 86.0 # 30°C
|
|
assert row["precip"] == 1.0 # 25.4mm = 1in
|
|
assert round(row["wind"], 1) == 22.4 # 10 m/s in mph
|
|
assert np.isnan(row["gust"]) # POWER has no gusts
|
|
assert row["fmax"] > row["tmax"] # ≥80°F: the NWS heat index applies
|
|
|
|
|
|
def test_om_daily_params_carries_the_window():
|
|
cell = {"center_lat": 47.6, "center_lon": -122.3}
|
|
p = climate._om_daily_params(cell, start_date="2026-01-01", end_date="2026-02-01")
|
|
assert p["latitude"] == 47.6 and p["daily"] == climate.DAILY_VARS
|
|
assert p["temperature_unit"] == "fahrenheit"
|
|
assert p["start_date"] == "2026-01-01" and p["end_date"] == "2026-02-01"
|
|
p2 = climate._om_daily_params(cell, past_days=25, forecast_days=8)
|
|
assert p2["past_days"] == 25 and "start_date" not in p2
|
|
|
|
|
|
def test_write_cache_strips_the_derived_doy(tmp_path):
|
|
df = climate._to_frame(_om_daily())
|
|
path = str(tmp_path / "cell.parquet")
|
|
climate._write_cache(df, path)
|
|
stored = pd.read_parquet(path)
|
|
assert "doy" not in stored.columns
|
|
assert len(stored) == len(df)
|