Update app.py

app.py

@@ -44,7 +44,7 @@ def hybrid_recommendation(song_index):
     audio_features_df = pd.DataFrame(audio_features_scaled_knn, columns=audio_features_knn.columns)
     # Combine mood and audio features
     combined_features = pd.concat([mood_cats_df, audio_features_df], axis=1)
-    
+
     # Predict using the KNN model
     knn_recommendations = knn_model.kneighbors(combined_features, n_neighbors=5, return_distance=False)[0]
 
@@ -57,12 +57,11 @@ def hybrid_recommendation(song_index):
     features_for_similarity = df[['danceability', 'energy', 'key', 'loudness', 'mode', 'speechiness',
                                   'acousticness', 'instrumentalness', 'liveness', 'valence', 'tempo',
                                   'duration_ms', 'time_signature']].values
-    scaler = StandardScaler()
-    audio_features_scaled = scaler.fit_transform(features_for_similarity)
+    scaler_cb = StandardScaler()
+    audio_features_scaled_cb = scaler_cb.fit_transform(features_for_similarity)
     # Combine mood and audio features
-    combined_features = pd.concat([emotion_category, pd.DataFrame(audio_features_scaled)], axis=1)
-
-    cosine_similarities = cosine_similarity(combined_features)
+    combined_features_cb = np.concatenate([np.array([emotion_category]), audio_features_scaled_cb])
+    cosine_similarities = cosine_similarity([combined_features_cb])
 
     # Combine recommendations from both models
     combined_indices = np.argsort(-np.concatenate([knn_recommendations, cosine_similarities]))