diff --git a/app.py b/app.py
index 04aedb24d021cb846006d38dec988ff2716e73ed..935a508946168fb8311b56ae5056eeb58c4bc727 100644
--- a/app.py
+++ b/app.py
@@ -2,6 +2,7 @@ from flask import Flask, request, jsonify, render_template
 import pickle
 import pandas as pd
 from sklearn.preprocessing import StandardScaler
+import numpy as np
 
 app = Flask(__name__)
 
@@ -24,7 +25,7 @@ def predict():
     input_data_scaled = scaler.fit_transform(input_data)
 
     # Prédiction
-    predictions = rf.predict(input_data_scaled)
+    predictions = np.round(rf.predict(input_data_scaled),4)
 
     return jsonify({'predictions': predictions.tolist()})
 
diff --git a/ml_binairefinal.py b/ml_binairefinal.py
index c355b6ed4d6aaa0503781678d4f92be1352cf028..0688e9ed318f280dd16008fe2999bfcbf278f8aa 100644
--- a/ml_binairefinal.py
+++ b/ml_binairefinal.py
@@ -29,7 +29,7 @@ def train_random_forest(df):
     X_test_scaled = scaler.transform(X_test)
 
     # 4️⃣ Initialisation du modèle avec les hyperparamètres optimisés
-    rf = RandomForestClassifier(n_estimators=200, max_depth=None, criterion="gini")
+    rf = RandomForestClassifier(n_estimators=200, max_depth=None, criterion="gini",class_weight='balanced')
     
     # 5️⃣ Entraînement du modèle
     rf.fit(X_train_scaled, y_train)
@@ -72,4 +72,6 @@ def get_independent_variables(df):
     return independent_variables
 
 # Obtenir la liste des variables indépendantes
-independent_variables = get_independent_variables(df)
\ No newline at end of file
+independent_variables = get_independent_variables(df)
+
+print(df['popularity_2'].value_counts())
\ No newline at end of file
diff --git a/mlsup0final.py b/mlsup0final.py
index c4b60104aab69bcc110af65eee50ee309b589888..d430629ab13a422ec4386b6e597e77ad6f57ea76 100644
--- a/mlsup0final.py
+++ b/mlsup0final.py
@@ -31,6 +31,10 @@ def train_random_forest(df):
     rf = RandomForestRegressor(n_estimators=200, max_depth=20, min_samples_split=2, random_state=42)
     rf.fit(X_train_scaled, y_train)
 
+     # Sauvegarder le modèle
+    with open('random_forest_model_sup.pkl', 'wb') as model_file:
+        pickle.dump(rf, model_file)
+
     # 5️⃣ Prédiction sur les données de test
     y_pred = rf.predict(X_test_scaled)
 
diff --git a/random_forest_model.pkl b/random_forest_model.pkl
index 53681515e3a7abfedbdbcc78e0c9bb4dbeeb691a..348339307c70b4af2bf48bbebfc2613bc6cc61b8 100644
Binary files a/random_forest_model.pkl and b/random_forest_model.pkl differ