Update app.py

app.py

@@ -6,36 +6,51 @@ import pandas as pd
 import numpy as np
 from sklearn.preprocessing import StandardScaler
 
-# Load the emotion prediction model
-emotion_model = load_model('lstm_model.h5')
-
 # Load the tokenizer (ensure it's the one used during training)
 tokenizer = joblib.load('tokenizer.pkl')
 
+# Load the emotion prediction model
+emotion_model = load_model('lstm_model.h5')
+
 # Load the dataset
 df = pd.read_csv('df1.csv')
 df = df.drop(['Unnamed: 0', 'lyrics_filename', 'analysis_url', 'track_href', "type", "id", "uri"], axis=1)
 
-# Load the content-based recommendation module
-recommend_cont_module = joblib.load('recommendation_cont_function.joblib')
+# Preprocess for content-based
+audio_feature_columns = ['danceability', 'energy', 'key', 'loudness', 'mode', 'speechiness',
+       'acousticness', 'instrumentalness', 'liveness', 'valence', 'tempo',
+       'duration_ms', 'time_signature']
 
-# Call the function from the module
-hybrid_recs = recommend_cont_module.recommend_cont(song_index=0)
+audio_features = df[audio_feature_columns]
+mood_cats = df[['mood_cats']]
+mood_cats_df = pd.DataFrame(mood_cats)
 
-# Load the hybrid recommendation function
-hybrid_recommendation = joblib.load('hybrid_recommendation_function.joblib')
+# Normalize audio features for content-based
+scaler_cb = StandardScaler()
+audio_features_scaled_cb = scaler_cb.fit_transform(audio_features)
+audio_features_df_cb = pd.DataFrame(audio_features_scaled_cb, columns=audio_feature_columns)
+combined_features_cb = pd.concat([mood_cats, audio_features_df_cb], axis=1)
 
-# Preprocess for content-based
-audio_features = df[['danceability', 'energy', 'key', 'loudness', 'mode', 'speechiness',
-                     'acousticness', 'instrumentalness', 'liveness', 'valence', 'tempo',
-                     'duration_ms', 'time_signature']]
-mood_cats = df[['mood_cats']]
+# Load the similarity matrix for content-based
+similarity_matrix = np.load('similarity_matrix.npy')
 
-scaler = StandardScaler()
-audio_features_scaled = scaler.fit_transform(audio_features)
-audio_features_df = pd.DataFrame(audio_features_scaled, columns=audio_features.columns)
-mood_cats_df = pd.DataFrame(mood_cats)
-combined_features_content = pd.concat([mood_cats_df, audio_features_df], axis=1)
+# Load the content-based recommendation function
+recommend_cont = joblib.load('recommendation_cont_function.joblib')
+
+# Preprocessing for KNN
+scaler_knn = StandardScaler()
+audio_features_scaled_knn = scaler_knn.fit_transform(audio_features)
+audio_features_df_knn = pd.DataFrame(audio_features_scaled_knn, columns=audio_feature_columns)
+combined_features_knn = pd.concat([mood_cats_df, audio_features_df_knn], axis=1)
+
+# Load the KNN model
+knn = joblib.load('knn_model.joblib')
+
+# Load the KNN recommendation function
+recommend_knn = joblib.load('recommendation_knn_function.joblib')
+
+# Load the hybrid recommendation function
+hybrid_recommendation = joblib.load('hybrid_recommendation_function.joblib')
 
 # Set up the title of the app
 st.title('Emotion and Audio Feature-based Song Recommendation System')
@@ -49,7 +64,7 @@ padded_sequence = pad_sequences(sequence, maxlen=50)
 emotion = emotion_model.predict(padded_sequence).flatten()
 
 # Combine emotion and audio features for recommendation
-combined_features_hybrid = np.concatenate([emotion, query_data[audio_features.columns].values])
+combined_features_hybrid = np.concatenate([emotion, query_data[audio_feature_columns].values])
 
 # Generate recommendations using the hybrid model
 hybrid_recs = hybrid_recommendation(song_index=0)