JSON ETL

spotify-wrapped.py

# path to your folder with all endsong json files
path = ''
# path where excel files will be saved to
output_path = ''

files = [os.path.join(path, f) for f in os.listdir(path)
         if os.path.isfile(os.path.join(path, f)) and f.endswith('.json')]
data_frames = [pd.read_json(file).astype({col: 'float64' for col in pd.read_json(file)
                                          .select_dtypes(include='bool').columns}) for file in files]
data = pd.concat([pd.read_json(file) for file in files])

# filter out streams less than 30 seconds
filtered_data = data[data['ms_played'] >= 30000].reset_index(drop=True)
# drop rows that do not have a URI
filtered_data = filtered_data[filtered_data['spotify_track_uri'].notnull()]