# Chronological evaluation and training-set error normalization.
# Input preparation and model fitting are described in the case methods.

train_dates, val_dates, test_dates = all_dates[:20], all_dates[20:27], all_dates[27:]
full = merged.inverter_count.eq(expected_inverters)
weather_valid = np.isfinite(merged[["IRRADIATION", "AMBIENT_TEMPERATURE", "MODULE_TEMPERATURE"]].to_numpy()).all(axis=1)
daylight = merged.IRRADIATION.gt(0.01)
clean = merged.loc[full & weather_valid & daylight].copy().sort_values("DATE_TIME")
clean["date"] = clean.DATE_TIME.dt.date
train = clean.loc[clean.date.isin(train_dates)].copy()
val = clean.loc[clean.date.isin(val_dates)].copy()
test = clean.loc[clean.date.isin(test_dates)].copy()
assert train.DATE_TIME.max() < val.DATE_TIME.min() < test.DATE_TIME.min()
assert not set(train.date) & set(test.date)
if min(len(train), len(val), len(test)) < 30:
    raise ValueError("Insufficient retained observations in a time partition")
xtrain, xval = features(train), features(val)
ytrain, yval = train.AC_POWER.to_numpy(), val.AC_POWER.to_numpy()
scale = float(np.quantile(ytrain, 0.95))

def metrics(y, pred, scale):
    return {"mae_reported_kw": float(np.mean(np.abs(y-pred))),
            "rmse_reported_kw": float(np.sqrt(np.mean((y-pred)**2))),
            "nmae_percent_train_p95": float(100*np.mean(np.abs(y-pred))/scale)}