Create app.py

app.py

@@ -0,0 +1,98 @@
+import streamlit as st
+import numpy as np
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+import pickle 
+import joblib
+import pandas as pd
+from sklearn.neighbors import NearestNeighbors
+from sklearn.preprocessing import StandardScaler
+from sklearn.metrics.pairwise import cosine_similarity
+
+# Load the LSTM model
+lstm_model = load_model('lstm_model.h5')
+
+# Load the Tokenizer used during training
+with open('tokenizer.pkl', 'rb') as tokenizer_file:
+    tokenizer = pickle.load(tokenizer_file)
+
+class_mapping = {"Happy": 0, "Sad": 1, "Calm": 2, "Anger": 3}
+numerical_to_label = {v: k for k, v in class_mapping.items()}
+
+# Load the KNN model
+knn_model = joblib.load('knn_model.joblib')
+
+# Load the dataset
+df = pd.read_csv('df1.csv')
+df = df.dropna()
+
+# Preprocess for KNN
+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']]
+audio_features_scaled = StandardScaler().fit_transform(audio_features)
+audio_features_df = pd.DataFrame(audio_features_scaled, columns=audio_feature_columns)
+combined_features = pd.concat([mood_cats, audio_features_df], axis=1)
+
+# Calculate similarity matrix for content-based
+audio_features_scaled_content = StandardScaler().fit_transform(audio_features)
+combined_features_content = pd.concat([mood_cats, pd.DataFrame(audio_features_scaled_content)], axis=1)
+similarity_matrix = cosine_similarity(combined_features_content)
+
+def recommend_cont(song_index, num_recommendations=5):
+    song_similarity = similarity_matrix[song_index]
+    similar_songs = sorted(list(enumerate(song_similarity)), key=lambda x: x[1], reverse=True)[1:num_recommendations+1]
+    recommended_song_indices = [idx for idx, similarity in similar_songs]
+    recommended_songs = df.iloc[recommended_song_indices].copy()
+    recommended_songs['score'] = [similarity for idx, similarity in similar_songs]
+    return recommended_songs
+
+def recommend_knn(query_index, n_recommendations=5):
+    distances, indices = knn_model.kneighbors(combined_features.iloc[query_index].values.reshape(1, -1), n_neighbors=n_recommendations)
+    recommended_songs = df.iloc[indices.flatten()].copy()
+    recommended_songs['score'] = 1 / (1 + distances.flatten())
+    return recommended_songs
+
+def hybrid_recommendation(song_index, top_n=10):
+    content_based_recs = recommend_cont(song_index, top_n)
+    knn_based_recs = recommend_knn(song_index, top_n)
+    combined_recs = pd.concat([content_based_recs, knn_based_recs])
+    hybrid_recs = combined_recs.groupby(combined_recs.index).mean().sort_values(by='score', ascending=False).head(top_n)
+    return hybrid_recs
+
+# Streamlit app
+st.title('Music Recommendation and Emotion Detection')
+
+# Emotion Detection
+st.subheader('Emotion Detection from Song Lyrics')
+user_input = st.text_input('Enter a Text:')
+prediction = None
+
+if st.button('Predict Emotion'):
+    sequence = tokenizer.texts_to_sequences([user_input])
+    padded_sequence = pad_sequences(sequence, maxlen=50)
+    prediction = lstm_model.predict(padded_sequence)
+
+if prediction is not None:
+    for i in range(len(prediction[0])):
+        label = numerical_to_label[i]
+        probability = prediction[0][i]
+        threshold = 0.5
+        if probability > threshold:
+            st.write(f'Predicted Emotion: {label}')
+
+# Music Recommendation
+st.subheader('Music Recommendation')
+song_index_to_recommend = st.number_input('Enter song index:', min_value=0, max_value=len(df)-1, value=0)
+hybrid_recs = hybrid_recommendation(song_index_to_recommend)
+
+st.write("Hybrid Recommendations:")
+if not hybrid_recs.empty:
+    for index in hybrid_recs.index:
+        st.write(f"Song Index: {index}, Title: {df.iloc[index]['track_name']}, Artist: {df.iloc[index]['track_artist']}, Score: {hybrid_recs.loc[index, 'score']}")
+else:
+    st.write("No recommendations found.")