feat(application): integrate measured-load ingestion training and planner source

2026-10-02 21:00:05 +00:00
parent 44362e4bf5
commit fc024fcfba
96 changed files with 8933 additions and 0 deletions
@@ -0,0 +1,121 @@
+import datetime
+import numpy as np
+import pandas as pd
+from sklearn.ensemble import HistGradientBoostingRegressor
+from sklearn.inspection import permutation_importance
+
+from methods.common import load_model, save_model
+
+FORECAST_ID = 22
+FEATURES = ["temp_c", "hour_cos", "load_24h_ago", "load_7d_ago", "energy_24h_rolling", "weekday"]
+
+
+def _feature_frame(df):
+    out = df.copy()
+    if "temp_c" not in out.columns:
+        out["temp_c"] = 15.0
+    out["temp_c"] = pd.to_numeric(out["temp_c"], errors="coerce").ffill().bfill().fillna(15.0)
+    out["hour_float"] = out.index.hour + out.index.minute / 60.0
+    out["hour_cos"] = np.cos(2 * np.pi * out["hour_float"] / 24.0)
+    out["weekday"] = out.index.weekday
+    if "Hausverbrauch" in out.columns:
+        out["load_24h_ago"] = out["Hausverbrauch"].shift(288)
+        out["load_7d_ago"] = out["Hausverbrauch"].shift(2016)
+        out["energy_5m_kwh"] = out["Hausverbrauch"] * (5 / 60) / 1000
+        out["energy_24h_rolling"] = out["energy_5m_kwh"].shift(1).rolling(window=288).sum()
+        out = out.drop(columns=["energy_5m_kwh"])
+    return out
+
+
+def _history_value(history, recent, reference, ts):
+    for frame in (history, recent, reference):
+        if frame is not None and not frame.empty and ts in frame.index and "Hausverbrauch" in frame.columns:
+            value = frame.at[ts, "Hausverbrauch"]
+            if pd.notna(value):
+                return float(value)
+    return None
+
+
+def train(data_obj):
+    aid = data_obj["config"]["anlagen_id"]
+    df = _feature_frame(data_obj.get("df_load_training", data_obj["df_hist"]).copy())
+    if "Hausverbrauch" not in df.columns:
+        return {"trained": False, "reason": "Hausverbrauch fehlt"}
+    df = df.dropna(subset=FEATURES + ["Hausverbrauch"])
+    if len(df) < 288:
+        return {"trained": False, "reason": "zu wenig Daten", "samples": int(len(df))}
+
+    last_day = df.index.max().normalize()
+    train_df = df[df.index < last_day]
+    test_df = df[(df.index >= last_day) & (df.index < last_day + datetime.timedelta(days=1))]
+    score = None
+    importance = {}
+    if len(train_df) >= 288 and len(test_df) >= 12:
+        eval_model = HistGradientBoostingRegressor(max_iter=2500, max_depth=25, learning_rate=0.01, min_samples_leaf=1, random_state=42)
+        eval_model.fit(train_df[FEATURES], train_df["Hausverbrauch"])
+        score = float(eval_model.score(test_df[FEATURES], test_df["Hausverbrauch"]))
+        print(f"[var_22] R2 Hausverbrauch letzter kompletter Tag: {score:.3f}")
+        try:
+            perm = permutation_importance(eval_model, test_df[FEATURES], test_df["Hausverbrauch"], n_repeats=10, random_state=42)
+            order = perm.importances_mean.argsort()[::-1]
+            importance = {FEATURES[i]: float(perm.importances_mean[i]) for i in order}
+            print("[var_22] Feature-Wichtigkeit Hausverbrauch:")
+            for name, val in importance.items():
+                print(f"  {name}: {val:.4f}")
+        except Exception as exc:
+            print(f"[var_22] permutation_importance nicht berechnet: {exc}")
+
+    model = HistGradientBoostingRegressor(max_iter=2500, max_depth=25, learning_rate=0.01, min_samples_leaf=1, random_state=42)
+    model.fit(df[FEATURES], df["Hausverbrauch"])
+    path = save_model(aid, FORECAST_ID, {"model": model, "features": FEATURES, "r2_last_day": score, "importance": importance})
+    return {"trained": True, "samples": int(len(df)), "features": FEATURES, "r2_last_day": score, "path": path}
+
+
+def predict(data_obj):
+    aid = data_obj["config"]["anlagen_id"]
+    artifact = load_model(aid, FORECAST_ID)
+    model = artifact["model"] if artifact and "model" in artifact else None
+    try:
+        score = float(artifact.get("r2_last_day")) if artifact and artifact.get("r2_last_day") is not None else 0.0
+    except (TypeError, ValueError):
+        score = 0.0
+    model_weight = min(0.35, max(0.0, score) * 0.35) if np.isfinite(score) else 0.0
+    hist = data_obj["df_hist"].copy()
+    recent = data_obj.get("df_recent_raw", pd.DataFrame())
+    reference = data_obj.get("df_load_training", pd.DataFrame())
+    fut = data_obj["df_fut"]
+    res = {}
+    for t in fut.index:
+        t_24 = t - datetime.timedelta(days=1)
+        t_7d = t - datetime.timedelta(days=7)
+        load_7d = _history_value(hist, recent, reference, t_7d)
+        load_24 = _history_value(hist, recent, reference, t_24)
+        if load_24 is None:
+            load_24 = load_7d if load_7d is not None else 0.0
+        if load_7d is None:
+            load_7d = load_24
+        ref_end = t - datetime.timedelta(days=7)
+        ref_start = ref_end - datetime.timedelta(days=1)
+        if not reference.empty and "Hausverbrauch" in reference.columns:
+            window = reference.loc[ref_start:ref_end - datetime.timedelta(minutes=5), "Hausverbrauch"]
+        else:
+            window = pd.Series(dtype=float)
+        if window.empty and "Hausverbrauch" in recent.columns:
+            window = recent.loc[t - datetime.timedelta(days=1):t - datetime.timedelta(minutes=5), "Hausverbrauch"]
+        roll_energy = float((window.sum() * 5 / 60) / 1000.0) if not window.empty else 0.0
+        row = pd.DataFrame([[
+            float(fut.at[t, "temp_c"]),
+            float(fut.at[t, "hour_cos"]),
+            load_24,
+            load_7d,
+            roll_energy,
+            int(fut.at[t, "weekday"]),
+        ]], columns=FEATURES)
+        profile = max(0.0, (0.65 * load_24) + (0.35 * load_7d))
+        pred = profile
+        if model is not None and model_weight > 0.0:
+            model_pred = max(0.0, float(model.predict(row)[0]))
+            pred = ((1.0 - model_weight) * profile) + (model_weight * model_pred)
+        res[t] = pred
+        hist.loc[t, "Hausverbrauch"] = pred
+    return res