Update app.py

app.py

@@ -6,74 +6,85 @@ import pandas as pd
 import numpy as np
 from sklearn.preprocessing import StandardScaler
 
-# Load the tokenizer (ensure it's the one used during training)
-tokenizer = joblib.load('tokenizer.pkl')
+def load_models():
+    # 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 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 dataset
+    df = pd.read_csv('df1.csv')
+    df = df.drop(['Unnamed: 0', 'lyrics_filename', 'analysis_url', 'track_href', "type", "id", "uri"], axis=1)
 
-# Preprocess for content-based
-audio_feature_columns = ['danceability', 'energy', 'key', 'loudness', 'mode', 'speechiness',
-       'acousticness', 'instrumentalness', 'liveness', 'valence', 'tempo',
-       'duration_ms', 'time_signature']
+    # Preprocess for content-based
+    audio_feature_columns = ['danceability', 'energy', 'key', 'loudness', 'mode', 'speechiness',
+           'acousticness', 'instrumentalness', 'liveness', 'valence', 'tempo',
+           'duration_ms', 'time_signature']
 
-audio_features = df[audio_feature_columns]
-mood_cats = df[['mood_cats']]
-mood_cats_df = pd.DataFrame(mood_cats)
+    audio_features = df[audio_feature_columns]
+    mood_cats = df[['mood_cats']]
+    mood_cats_df = pd.DataFrame(mood_cats)
 
-# 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)
+    # 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)
 
-# Load the similarity matrix for content-based
-similarity_matrix = np.load('similarity_matrix.npy')
+    # Load the similarity matrix for content-based
+    similarity_matrix = np.load('similarity_matrix.npy')
 
-# Load the content-based recommendation function
-recommend_cont = joblib.load('recommendation_cont_function.joblib')
+    # 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)
+    # 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 model
+    knn = joblib.load('knn_model.joblib')
 
-# Load the KNN recommendation function
-recommend_knn = joblib.load('recommendation_knn_function.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')
+    # 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')
+    return tokenizer, emotion_model, df, audio_feature_columns, combined_features_cb, similarity_matrix, recommend_cont, mood_cats_df, audio_features_df_knn, combined_features_knn, knn, recommend_knn, hybrid_recommendation
 
-# Get data from index 0
-query_data = df.iloc[0]
+def main():
+    # Set up the title of the app
+    st.title('Emotion and Audio Feature-based Song Recommendation System')
 
-# Process the lyrics
-sequence = tokenizer.texts_to_sequences([query_data['lyrics']])
-padded_sequence = pad_sequences(sequence, maxlen=50)
-emotion = emotion_model.predict(padded_sequence).flatten()
+    # Load models and data
+    tokenizer, emotion_model, df, audio_feature_columns, combined_features_cb, similarity_matrix, recommend_cont, mood_cats_df, audio_features_df_knn, combined_features_knn, knn, recommend_knn, hybrid_recommendation = load_models()
 
-# Mapping emotion predictions to encoded categories
-emotion_mapping = {0: 'happy', 1: 'sad', 2: 'calm', 3: 'anger'}
-encoded_emotion = np.argmax(emotion)  
-emotion_category = emotion_mapping[encoded_emotion]
+    # Get data from index 0
+    query_data = df.iloc[0]
 
-# Combine emotion and audio features for recommendation
-combined_features_hybrid = np.concatenate([encoded_emotion, query_data[audio_feature_columns].values])
+    # Process the lyrics
+    sequence = tokenizer.texts_to_sequences([query_data['lyrics']])
+    padded_sequence = pad_sequences(sequence, maxlen=50)
+    emotion = emotion_model.predict(padded_sequence).flatten()
 
-# Generate recommendations using the hybrid model
-hybrid_recs = hybrid_recommendation(song_index=0)
+    # Mapping emotion predictions to encoded categories
+    emotion_mapping = {0: 'happy', 1: 'sad', 2: 'calm', 3: 'anger'}
+    encoded_emotion = np.argmax(emotion)  
+    emotion_category = emotion_mapping[encoded_emotion]
+
+    # Combine emotion and audio features for recommendation
+    combined_features_hybrid = np.concatenate([encoded_emotion, query_data[audio_feature_columns].values])
+
+    # Generate recommendations using the hybrid model
+    hybrid_recs = hybrid_recommendation(song_index=0)
+
+    st.write("Emotion Detected:", emotion[0])
+    st.header('Recommended Songs (Hybrid)')
+    st.write(hybrid_recs)
+
+if __name__ == '__main__':
+    main()
 
-st.write("Emotion Detected:", emotion[0])
-st.header('Recommended Songs (Hybrid)')
-st.write(hybrid_recs)