def setUpClass(cls):
#we use the test df
target_files = {
'identifier_infos_path' : 'test_df/Apple Music Activity/Identifier Information.json.zip',
'library_tracks_path' : 'test_df/Apple Music Activity/Apple Music Library Tracks.json.zip',
'library_activity_path': 'test_df/Apple Music Activity/Apple Music Library Activity.json.zip',
'likes_dislikes_path' : 'test_df/Apple Music Activity/Apple Music Likes and Dislikes.csv',
'play_activity_path': 'test_df/Apple Music Activity/Apple Music Play Activity.csv'
}
cls.input_df = Utility.get_df_from_archive('apple_music_analyser/tests/test_df.zip', target_files)
cls.parser = Parser(cls.input_df)
cls.likes_dislikes_df = cls.parser.likes_dislikes_df
cls.play_activity_df = cls.parser.play_activity_df
cls.identifier_infos_df = cls.parser.identifier_infos_df
cls.library_tracks_df = cls.parser.library_tracks_df
cls.library_activity_df = cls.parser.library_activity_df
#we process the df
cls.process = ProcessTracks()
cls.process.process_library_tracks_df(cls.library_tracks_df)
cls.process.process_identifier_df(cls.identifier_infos_df)
cls.process.process_play_df(cls.play_activity_df)
cls.process.process_likes_dislikes_df(cls.likes_dislikes_df)
#we extract the useful objects from the process instance
cls.track_instance_dict = cls.process.track_instance_dict
cls.artist_tracks_titles = cls.process.artist_tracks_titles
cls.genres_list = cls.process.genres_list
cls.items_not_matched = cls.process.items_not_matched
def test_get_df_from_archive_with_target(self):
'''
We test the case where the structure inside the archive is provided as an argument.
This function relies on external package (ZipFile), well covered by tests.
'''
target_files = {
'identifier_infos_path':
'test_df/Apple Music Activity/Identifier Information.json.zip',
'library_tracks_path':
'test_df/Apple Music Activity/Apple Music Library Tracks.json.zip',
'library_activity_path':
'test_df/Apple Music Activity/Apple Music Library Activity.json.zip',
'likes_dislikes_path':
'test_df/Apple Music Activity/Apple Music Likes and Dislikes.csv',
'play_activity_path':
'test_df/Apple Music Activity/Apple Music Play Activity.csv'
}
archive_path = 'apple_music_analyser/tests/test_df.zip'
result = Utility.get_df_from_archive(archive_path, target_files)
self.assertTrue(isinstance(result, dict))
self.assertEqual(len(result), 5)
self.assertEqual(list(result.keys()), [
'identifier_infos_df', 'library_tracks_df', 'library_activity_df',
'likes_dislikes_df', 'play_activity_df'
])
for key in result.keys():
self.assertTrue(isinstance(result[key], pd.DataFrame))
def test_get_df_from_archive_bad_archive(self):
'''
We test the case where the path is wrong
This function relies on external package (ZipFile), well covered by tests.
'''
archive_path = None
result = Utility.get_df_from_archive(archive_path)
self.assertEqual(result, {})
def setUp(self):
target_files = {
'identifier_infos_path' : 'test_df/Apple Music Activity/Identifier Information.json.zip',
'library_tracks_path' : 'test_df/Apple Music Activity/Apple Music Library Tracks.json.zip',
'library_activity_path': 'test_df/Apple Music Activity/Apple Music Library Activity.json.zip',
'likes_dislikes_path' : 'test_df/Apple Music Activity/Apple Music Likes and Dislikes.csv',
'play_activity_path': 'test_df/Apple Music Activity/Apple Music Play Activity.csv'
}
self.input_df = Utility.get_df_from_archive('apple_music_analyser/tests/test_df.zip', target_files)
self.df_visualization = VisualizationDataframe(self.input_df)
def setUp(self):
target_files = {
'identifier_infos_path' : 'test_df/Apple Music Activity/Identifier Information.json.zip',
'library_tracks_path' : 'test_df/Apple Music Activity/Apple Music Library Tracks.json.zip',
'library_activity_path': 'test_df/Apple Music Activity/Apple Music Library Activity.json.zip',
'likes_dislikes_path' : 'test_df/Apple Music Activity/Apple Music Likes and Dislikes.csv',
'play_activity_path': 'test_df/Apple Music Activity/Apple Music Play Activity.csv'
}
self.input_df = Utility.get_df_from_archive('apple_music_analyser/tests/test_df.zip', target_files)
self.parser = Parser(self.input_df)
self.likes_dislikes_df = self.parser.likes_dislikes_df
self.play_activity_df = self.parser.play_activity_df
self.identifier_infos_df = self.parser.identifier_infos_df
self.library_tracks_df = self.parser.library_tracks_df
self.library_activity_df = self.parser.library_activity_df
self.process = ProcessTracks()
self.track_instance = Track(self.process.increment)
def test_init_Parser(self):
target_files = {
'identifier_infos_path':
'test_df/Apple Music Activity/Identifier Information.json.zip',
'library_tracks_path':
'test_df/Apple Music Activity/Apple Music Library Tracks.json.zip',
'library_activity_path':
'test_df/Apple Music Activity/Apple Music Library Activity.json.zip',
'likes_dislikes_path':
'test_df/Apple Music Activity/Apple Music Likes and Dislikes.csv',
'play_activity_path':
'test_df/Apple Music Activity/Apple Music Play Activity.csv'
}
input_df = Utility.get_df_from_archive(
'apple_music_analyser/tests/test_df.zip', target_files)
shape_input_likes_dislikes_df = input_df['likes_dislikes_df'].shape
shape_input_play_activity_df = input_df['play_activity_df'].shape
shape_input_identifier_infos_df = input_df['identifier_infos_df'].shape
shape_input_library_tracks_df = input_df['library_tracks_df'].shape
shape_input_library_activity_df = input_df['library_activity_df'].shape
result = Parser(input_df)
self.assertTrue(isinstance(result.likes_dislikes_df, pd.DataFrame))
self.assertEqual(result.likes_dislikes_df.shape,
(shape_input_likes_dislikes_df[0],
shape_input_likes_dislikes_df[1] + 2))
self.assertTrue(isinstance(result.play_activity_df, pd.DataFrame))
self.assertEqual(result.play_activity_df.shape,
(shape_input_play_activity_df[0] - 1,
shape_input_play_activity_df[1] - 14))
self.assertTrue(isinstance(result.identifier_infos_df, pd.DataFrame))
self.assertEqual(result.identifier_infos_df.shape,
(shape_input_identifier_infos_df[0],
shape_input_identifier_infos_df[1]))
self.assertTrue(isinstance(result.library_tracks_df, pd.DataFrame))
self.assertEqual(result.library_tracks_df.shape,
(shape_input_library_tracks_df[0],
shape_input_library_tracks_df[1] - 34))
self.assertTrue(isinstance(result.library_activity_df, pd.DataFrame))
self.assertEqual(result.library_activity_df.shape,
(shape_input_library_activity_df[0],
shape_input_library_activity_df[1] + 8))
###########################################################################################################################
# we assume you have an instance of the visualization dataframe class saved in the same folder under the name 'viz_df_instance.pkl'
viz_df_instance = Utility.load_from_pickle('viz_df_instance.pkl')
# SAVE A PICKLE
###########################################################################################################################
# get the input file - see starter_code.py for more details
path_to_archive = '../apple_music_analyser/tests/test_df.zip'
target_files = {
'identifier_infos_path':
'test_df/Apple Music Activity/Identifier Information.json.zip',
'library_tracks_path':
'test_df/Apple Music Activity/Apple Music Library Tracks.json.zip',
'library_activity_path':
'test_df/Apple Music Activity/Apple Music Library Activity.json.zip',
'likes_dislikes_path':
'test_df/Apple Music Activity/Apple Music Likes and Dislikes.csv',
'play_activity_path':
'test_df/Apple Music Activity/Apple Music Play Activity.csv'
}
input_df = Utility.get_df_from_archive(path_to_archive, target_files)
# create an instance of the visualization dataframe class
viz_df_instance = VisualizationDataframe(input_df)
# save the instance
Utility.save_to_pickle(viz_df_instance, 'viz_df_instance.pkl')