File size: 2,756 Bytes
edc4276
01e4bba
 
c4d5407
 
 
6868cdb
401d1a7
d69f584
3f56ca4
c4d5407
a4492f7
 
 
6868cdb
3f56ca4
6868cdb
c4d5407
a4492f7
 
 
 
3f56ca4
a4492f7
 
 
edc4276
a4492f7
 
 
 
 
edc4276
a4492f7
 
6868cdb
a4492f7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6868cdb
3f56ca4
 
577a126
3f56ca4
 
577a126
3f56ca4
 
6868cdb
3f56ca4
577a126
3f56ca4
a4492f7
577a126
3f56ca4
 
1f9b2ed
3f56ca4
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
import streamlit as st
from tensorflow.keras.models import load_model
from tensorflow.keras.preprocessing.sequence import pad_sequences
import joblib
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')

# 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)

# 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)

# 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 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')

# Get data from index 0
query_data = df.iloc[0]

# 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()

# Combine emotion and audio features for recommendation
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)

st.write("Emotion Detected:", emotion[0])
st.header('Recommended Songs (Hybrid)')
st.write(hybrid_recs)