Update app.py

Modif pearson vers spearman

app.py

@@ -9,7 +9,8 @@ from sklearn.linear_model import LinearRegression, LogisticRegression
 from sklearn.feature_selection import mutual_info_regression, mutual_info_classif
 from sklearn.metrics import r2_score, accuracy_score
 from sklearn.model_selection import train_test_split
-from scipy.stats import pearsonr
+#from scipy.stats import pearsonr
+from scipy.stats import spearmanr
 
 # ------------------------------------------------------------
 # Configuration Globale
@@ -217,14 +218,19 @@ if df is not None and X is not None and len(X.columns) > 0:
                     "Sens": np.where(coefs > 0, "+", "-")
                 })
                 
+                #if task == "Regression":
+                #    res["Lien direct (Corr)"] = [pearsonr(X_train_proc[:, i], y_train)[0] for i in range(len(feature_names))]
+
                 if task == "Regression":
-                    res["Lien direct (Corr)"] = [pearsonr(X_train_proc[:, i], y_train)[0] for i in range(len(feature_names))]
+                    res["Lien direct (Corr)"] = [spearmanr(X_train_proc[:, i], y_train)[0] for i in range(len(feature_names))]
                 
                 # Normalisation pour Score Synthétique
                 def normalize(s): return (s - s.min()) / (s.max() - s.min() + 1e-10)
                 mi_n = normalize(res["Importance seule (MI)"])
                 poids_n = normalize(res["Poids dans le modèle"])
 
+
+
                 if task == "Regression":
                     corr_n = normalize(res["Lien direct (Corr)"].abs())
                     res["Score synthétique"] = ((mi_n + corr_n) / 2 + poids_n) / 2