Skip to content
Snippets Groups Projects
Commit da797f58 authored by Mohamed Sebabti's avatar Mohamed Sebabti
Browse files

predictsup0

parent 352d262d
No related branches found
No related tags found
No related merge requests found
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' !")
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment