Réorganisation

docs/05 - Corrélations binaires avancées/scripts/plot_lagged_correlations.py

@@ -0,0 +1,64 @@
+# scripts/plot_lagged_correlations.py
+from __future__ import annotations
+
+from pathlib import Path
+import sys
+
+
+PROJECT_ROOT = Path(__file__).resolve().parents[3]
+if str(PROJECT_ROOT) not in sys.path:
+    sys.path.insert(0, str(PROJECT_ROOT))
+
+from meteo.dataset import load_raw_csv
+from meteo.variables import VARIABLES_BY_KEY
+from meteo.analysis import compute_lagged_correlation
+from meteo.plots import plot_lagged_correlation
+from meteo.correlation_presets import DEFAULT_LAGGED_PAIRS
+
+
+CSV_PATH = Path("data/weather_minutely.csv")
+DOC_DIR = Path(__file__).resolve().parent.parent
+OUTPUT_DIR = DOC_DIR / "figures" / "lagged_correlations"
+
+
+def main() -> None:
+    if not CSV_PATH.exists():
+        print(f"⚠ Fichier introuvable : {CSV_PATH}")
+        return
+
+    df = load_raw_csv(CSV_PATH)
+    print(f"Dataset minuté chargé : {CSV_PATH}")
+    print(f"  Lignes   : {len(df)}")
+    print(f"  Colonnes : {list(df.columns)}")
+    print()
+
+    for key_x, key_y in DEFAULT_LAGGED_PAIRS:
+        var_x = VARIABLES_BY_KEY[key_x]
+        var_y = VARIABLES_BY_KEY[key_y]
+
+        print(f"→ Corrélation décalée : {var_x.key} → {var_y.key}")
+
+        lag_df = compute_lagged_correlation(
+            df=df,
+            var_x=var_x,
+            var_y=var_y,
+            max_lag_minutes=360,   # ± 6 heures
+            step_minutes=10,       # pas de 10 minutes
+            method="pearson",
+        )
+
+        filename = f"lagcorr_{var_x.key}_to_{var_y.key}.png"
+        output_path = OUTPUT_DIR / filename
+
+        plot_lagged_correlation(
+            lag_df=lag_df,
+            var_x=var_x,
+            var_y=var_y,
+            output_path=output_path,
+        )
+
+    print("✔ Graphiques de corrélation décalée générés.")
+
+
+if __name__ == "__main__":
+    main()

docs/05 - Corrélations binaires avancées/scripts/plot_rolling_correlation_heatmap.py

@@ -0,0 +1,65 @@
+# scripts/plot_rolling_correlation_heatmap.py
+from __future__ import annotations
+
+from pathlib import Path
+import sys
+
+
+PROJECT_ROOT = Path(__file__).resolve().parents[3]
+if str(PROJECT_ROOT) not in sys.path:
+    sys.path.insert(0, str(PROJECT_ROOT))
+
+from meteo.dataset import load_raw_csv
+from meteo.variables import VARIABLES_BY_KEY
+from meteo.analysis import compute_rolling_correlations_for_pairs
+from meteo.plots import plot_rolling_correlation_heatmap
+from meteo.correlation_presets import DEFAULT_ROLLING_PAIRS
+
+
+CSV_PATH = Path("data/weather_minutely.csv")
+DOC_DIR = Path(__file__).resolve().parent.parent
+OUTPUT_PATH = DOC_DIR / "figures" / "rolling_correlations" / "rolling_correlation_heatmap.png"
+
+WINDOW_MINUTES = 180  # 3 heures pour observer les tendances synoptiques
+STEP_MINUTES = 30     # on n'échantillonne qu'un point sur 30 minutes
+
+
+def main() -> None:
+    if not CSV_PATH.exists():
+        print(f"⚠ Fichier introuvable : {CSV_PATH}")
+        return
+
+    df = load_raw_csv(CSV_PATH)
+    print(f"Dataset minuté chargé : {CSV_PATH}")
+    print(f"  Lignes   : {len(df)}")
+    print(f"  Colonnes : {list(df.columns)}")
+    print()
+
+    pairs = [(VARIABLES_BY_KEY[a], VARIABLES_BY_KEY[b]) for a, b in DEFAULT_ROLLING_PAIRS]
+
+    rolling_df = compute_rolling_correlations_for_pairs(
+        df=df,
+        pairs=pairs,
+        window_minutes=WINDOW_MINUTES,
+        min_valid_fraction=0.7,
+        step_minutes=STEP_MINUTES,
+        method="pearson",
+    )
+
+    if rolling_df.empty:
+        print("⚠ Impossible de calculer les corrélations glissantes (données insuffisantes).")
+        return
+
+    output_path = plot_rolling_correlation_heatmap(
+        rolling_corr=rolling_df,
+        output_path=OUTPUT_PATH,
+        cmap="coolwarm",
+        vmin=-1.0,
+        vmax=1.0,
+    )
+
+    print(f"✔ Heatmap de corrélations glissantes enregistrée : {output_path}")
+
+
+if __name__ == "__main__":
+    main()