| """Build the supervised table: weather up to day t -> log(turbidity FNU) at day t+h. |
| |
| Features only use information up to day t (no future weather), so inference needs no |
| weather forecast. Caveat: training weather is ERA5 / wave reanalysis, while live use |
| feeds the real-time Open-Meteo analysis, a small distribution shift. |
| """ |
| import numpy as np, pandas as pd |
| from pathlib import Path |
| from spots import SPOTS |
|
|
| HORIZONS = (1, 2, 3) |
|
|
|
|
| def daily_weather(name, data=Path("data")): |
| return daily_weather_from_hourly(pd.read_parquet(data / f"wx_{name}.parquet")) |
|
|
|
|
| def daily_weather_from_hourly(w): |
| w = w.set_index("time").sort_index() |
| w["wave_energy"] = w["wave_height"] ** 2 * w["wave_period"] |
| d = pd.DataFrame({ |
| "hs_max": w["wave_height"].resample("D").max(), |
| "hs_mean": w["wave_height"].resample("D").mean(), |
| "tp_mean": w["wave_period"].resample("D").mean(), |
| "wave_e": w["wave_energy"].resample("D").mean(), |
| "wind": w["wind_speed_10m"].resample("D").mean(), |
| "wind_max": w["wind_speed_10m"].resample("D").max(), |
| "rain": w["precipitation"].resample("D").sum(), |
| }) |
| for c, wins in (("hs_max", (2, 3, 7)), ("wave_e", (3, 7)), ("rain", (3, 7)), ("wind", (3,))): |
| for k in wins: |
| d[f"{c}_r{k}"] = d[c].rolling(k, min_periods=1).mean() |
| return d |
|
|
|
|
| def build(h, data=Path("data")): |
| rows = [] |
| for i, (name, (lat, lon, reg)) in enumerate(SPOTS.items()): |
| p = data / f"hr_{name}.parquet" |
| if not p.exists() or not (data / f"wx_{name}.parquet").exists(): |
| continue |
| hr = pd.read_parquet(p).set_index("date") |
| hr = hr[hr["valid_frac"] > 0.2] |
| kd = hr["tur"].groupby(level=0).mean().clip(lower=0.01) |
| wx = daily_weather(name, data) |
| idx = pd.date_range("2020-01-02", "2026-08-25") |
| kdf = np.log(kd.reindex(idx)) |
| df = wx.reindex(idx).copy() |
| df["y"] = kdf.shift(-h) |
| |
| last = kdf.ffill() |
| age = kdf.notna().astype(int).groupby(kdf.notna().cumsum()).cumcount() |
| df["last_kd"] = last |
| df["last_age"] = age |
| df["doy_sin"] = np.sin(2 * np.pi * idx.dayofyear / 365.25) |
| df["doy_cos"] = np.cos(2 * np.pi * idx.dayofyear / 365.25) |
| df["lat"], df["lon"], df["spot"] = lat, lon, i |
| df["date"] = idx |
| rows.append(df) |
| out = pd.concat(rows).dropna(subset=["y", "last_kd"]) |
| return out.reset_index(drop=True) |
|
|
|
|
| def split(df): |
| t = df["date"] |
| return (df[t < "2025-01-01"], df[(t >= "2025-01-01") & (t < "2026-01-01")], df[t >= "2026-01-01"]) |
|
|
