ModusMusic / song_matching.py
IshmamF's picture
Upload 5 files
1321ce6
raw history blame
No virus
2.07 kB
import pandas as pd
from sentence_transformers import SentenceTransformer, util
class SongMatcher:
def __init__(self, songs_data_file, model_name="sentence-transformers/all-mpnet-base-v2"):
"""
Initializes the SongMatcher with the songs data file and the SentenceTransformer model.
:param songs_data_file: Path to the CSV file containing songs data
:param model_name: Name of the SentenceTransformer model
"""
self.songs_df = pd.read_csv(songs_data_file)
self.sim_model = SentenceTransformer(model_name)
def match_songs_with_sentiment(self, user_sentiment_label, user_sentiment_score, user_input, score_range=0.00625):
"""
Matches songs from the dataset with the user's sentiment.
:param user_sentiment_label: The sentiment label of the user input
:param user_sentiment_score: The sentiment score of the user input
:param user_input: Text input from the user
:param score_range: Range for filtering songs based on sentiment score
:return: DataFrame of top 5 matched songs
"""
# Filter songs with the same sentiment label
matched_songs = self.songs_df[self.songs_df['sentiment'] == user_sentiment_label]
# Calculate the score range
score_min = max(0, user_sentiment_score - score_range)
score_max = min(1, user_sentiment_score + score_range)
# Further filter songs whose scores fall within the specified range
matched_songs = matched_songs[(matched_songs['score'] >= score_min) & (matched_songs['score'] <= score_max)]
# Compute similarity between user input and song lyrics
input_vector = self.sim_model.encode(user_input)
matched_songs['similarity'] = matched_songs['seq'].apply(lambda x: util.pytorch_cos_sim(self.sim_model.encode(x), input_vector))
# Select the top five songs based on similarity and return
top_5 = matched_songs.nlargest(5, 'similarity')
return top_5[['song', 'artist', 'seq', 'similarity', 'sentiment', 'score']]