diff --git a/spotify-popularity-prediction-v2/recup_predict_sup0.py b/spotify-popularity-prediction-v2/recup_predict_sup0.py
new file mode 100644
index 0000000000000000000000000000000000000000..833a094fb0b1844a71e2e085affeaf7bb56ec59c
--- /dev/null
+++ b/spotify-popularity-prediction-v2/recup_predict_sup0.py
@@ -0,0 +1,45 @@
+import numpy as np
+import pandas as pd
+import pickle
+from sklearn.preprocessing import StandardScaler
+
+# 📂 Charger le dataset complet (avec les IDs)
+df = pd.read_csv("data_sup_0popularity.csv")
+
+# 📂 Charger le modèle et le scaler
+with open("random_forest_model_sup0.pkl", "rb") as model_file:
+    rf = pickle.load(model_file)
+
+with open("scaler_sup0.pkl", "rb") as scaler_file:
+    scaler = pickle.load(scaler_file)
+
+# ✅ Vérifier que les features attendues sont bien présentes
+expected_features = ['year', 'acousticness', 'danceability', 'energy', 'explicit',
+                     'instrumentalness', 'key', 'liveness', 'loudness', 'mode',
+                     'speechiness', 'tempo', 'valence', 'nb_caracteres_sans_espaces',
+                     'nb_artistes', 'featuring', 'duree_minute', 'categorie_annee', 'categorie_tempo']
+
+# ⚠️ Vérifier si des colonnes sont manquantes
+missing_features = [col for col in expected_features if col not in df.columns]
+if missing_features:
+    raise ValueError(f"⚠️ Il manque ces colonnes dans le dataset : {missing_features}")
+
+# 📝 Garder uniquement les colonnes nécessaires (ID + Features)
+df_features = df[['id'] + expected_features]
+
+# 🎯 Extraire les features
+X = df_features[expected_features]
+
+# 📏 Appliquer le scaler sur les features
+X_scaled = scaler.transform(X)
+
+# 🔮 Faire les prédictions
+df_features["predictions"] = rf.predict(X_scaled)
+
+# 📊 Afficher les 10 premières lignes
+print(df_features.head(10))
+
+# 💾 Sauvegarder le DataFrame avec les prédictions en CSV
+df_features.to_csv("predictions_sup0.csv", index=False)
+
+print("\n✅ Prédictions sauvegardées dans 'predictions_sup0.csv' !")