Update app.py

app.py

@@ -4,6 +4,7 @@ from tensorflow.keras.preprocessing.sequence import pad_sequences
 import joblib
 import pandas as pd
 import numpy as np
+from sklearn.metrics.pairwise import cosine_similarity
 
 # Check if scikit-learn is installed
 try:
@@ -19,15 +20,14 @@ emotion_model = load_model('lstm_model.h5')
 try:
     recommender_model = joblib.load('knn_model.pkl')
 except Exception as e:
-    st.error(f"Error loading model: {e}")
+    st.error(f"Error loading KNN model: {e}")
 
 # Load the tokenizer (ensure it's the one used during training)
 tokenizer = joblib.load('tokenizer.pkl')  # Correct the path
 
 # Load the dataset and preprocess
 df = pd.read_csv('df1.csv')  
-#df = df.dropna()
-df = df.drop(['Unnamed: 0', 'lyrics_filename',  'analysis_url', 'track_href', "type", "id", "uri"], axis=1)
+df = df.drop(['Unnamed: 0', 'lyrics_filename', 'analysis_url', 'track_href', "type", "id", "uri"], axis=1)
 
 # Set up the title of the app
 st.title('Emotion and Audio Feature-based Song Recommendation System')
@@ -39,26 +39,34 @@ lyrics = st.text_area("Input the lyrics of the song here:")
 # Input fields for audio features
 st.header('Enter Audio Features')
 audio_features = []
-#df = df.drop([ 'track_artist', 'track_name','Unnamed: 0', 'lyrics_filename',  'analysis_url', 'track_href', "type", "id", "uri"] axis=1)
-for feature_name in df.columns:
+
+# Display only relevant columns for audio features
+audio_feature_columns = ['danceability', 'energy', 'key', 'loudness', 'mode', 'speechiness', 'acousticness',
+                         'instrumentalness', 'liveness', 'valence', 'tempo']
+
+for feature_name in audio_feature_columns:
     feature = st.number_input(f"Enter value for {feature_name}:", step=0.01)
     audio_features.append(feature)
 
 # Predict and Recommend button
 if st.button('Predict Emotion and Recommend Songs'):
     if lyrics and all(audio_features):
+        # Process the lyrics
         sequence = tokenizer.texts_to_sequences([lyrics])
         padded_sequence = pad_sequences(sequence, maxlen=128)
         emotion = emotion_model.predict(padded_sequence).flatten()
 
+        # Combine emotion and audio features for recommendation
         combined_features = np.concatenate([emotion, audio_features])
 
-        distances, indices = recommender_model.kneighbors([combined_features], n_neighbors=5)
-        recommended_songs = df.iloc[indices.flatten()]
+        # Generate recommendations using the KNN model
+        knn_distances, knn_indices = recommender_model.kneighbors([combined_features], n_neighbors=5)
+        knn_recommended_songs = df.iloc[knn_indices.flatten()]
 
         st.write("Emotion Detected:", emotion[0])
-        st.header('Recommended Songs')
-        for _, song in recommended_songs.iterrows():
+        st.header('Recommended Songs (KNN)')
+        for _, song in knn_recommended_songs.iterrows():
             st.write(song)
+
     else:
         st.error("Please fill in all the fields.")