إنشاء تضمينات لملفات الصوت والبيانات الوصفية للأغاني

import pandas as pd
metadata_file_path="/content/drive/MyDrive/vector-databases-course/music-recommendation-system/dataset/reduced_80_fer2013_music_dataset_with_youtube_URLS.csv"
# Loading metadata into DataFrame
metadata_df = pd.read_csv(metadata_file_path)
# Extracting relevant numeric attribute and creating textual description using them
metadata_df['textual_description'] = metadata_df.apply(
    lambda row: f"The song {row['song_name']} has a danceability of {row['danceability']}, "
                f"energy of {row['energy']}, "
                f"loudness of {row['loudness']}, "
                f"speechiness of {row['speechiness']}, "
                f"acousticness of {row['acousticness']}, "
                f"instrumentalness of {row['instrumentalness']}, "
                f"liveness of {row['liveness']}, "
                f"valence of {row['valence']}, "
                f"tempo of {row['tempo']}",
    axis=1
)
# Saving the updated DataFrame with the textual descriptions for each song back to the CSV file
metadata_df.to_csv(metadata_file_path, index=False)
print("The 'textual_description' column has been added to the CSV file.")

# Define special tokens for numeric attributes
SPECIAL_TOKENS = {
    '[DANCEABILITY]': 'danceability',
    '[SPEECHINESS]': 'speechiness',
    '[ENERGY]': 'energy',
    '[LOUDNESS]': 'loudness',
    '[ACOUSTICNESS]': 'acousticness',
    '[INSTRUMENTALNESS]': 'instrumentalness',
    '[LIVENESS]': 'liveness',
    '[VALENCE]': 'valence',
    '[TEMPO]': 'tempo'
}
# Tokenize using custom special tokens
def tokenize_with_special_tokens(text):
    for token, attribute in SPECIAL_TOKENS.items():
        text = text.replace(attribute, token)
    return text
# Apply tokenization to create input for BERT
metadata_df['textual_description_with_Special_Tokens'] = metadata_df['textual_description'].apply(tokenize_with_special_tokens)