def test_get_top_artist_candidate_set(self):
mapped_listens_df = utils.read_files_from_HDFS(
self.mapped_listens_path)
recordings_df = create_dataframes.get_recordings_df(
mapped_listens_df, {})
users = create_dataframes.get_users_dataframe(mapped_listens_df, {})
mapped_listens_subset = utils.read_files_from_HDFS(
self.mapped_listens_subset_path)
top_artist_limit = 1
top_artist_df = candidate_sets.get_top_artists(mapped_listens_subset,
top_artist_limit, [])
top_artist_candidate_set_df, top_artist_candidate_set_df_html = candidate_sets.get_top_artist_candidate_set(
top_artist_df, recordings_df, users, mapped_listens_subset)
cols = ['recording_id', 'user_id', 'user_name']
self.assertListEqual(sorted(cols),
sorted(top_artist_candidate_set_df.columns))
self.assertEqual(top_artist_candidate_set_df.count(), 3)
cols = [
'top_artist_credit_id', 'top_artist_name', 'mb_artist_credit_id',
'mb_artist_credit_mbids', 'mb_recording_mbid',
'msb_artist_credit_name_matchable', 'msb_recording_name_matchable',
'recording_id', 'user_name', 'user_id'
]
self.assertListEqual(sorted(cols),
sorted(top_artist_candidate_set_df_html.columns))
self.assertEqual(top_artist_candidate_set_df_html.count(), 3)
def test_filter_last_x_days_recordings(self):
mapped_listens_df = utils.read_files_from_HDFS(
self.mapped_listens_path)
mapped_listens_subset = utils.read_files_from_HDFS(
self.mapped_listens_subset_path)
recordings_df = create_dataframes.get_recordings_df(
mapped_listens_df, {})
users = create_dataframes.get_users_dataframe(mapped_listens_df, {})
mapped_listens_subset = utils.read_files_from_HDFS(
self.mapped_listens_subset_path)
top_artist_limit = 1
top_artist_df = candidate_sets.get_top_artists(mapped_listens_subset,
top_artist_limit, [])
_, candidate_set_df = candidate_sets.get_top_artist_candidate_set(
top_artist_df, recordings_df, users, mapped_listens_subset)
df = candidate_sets.filter_last_x_days_recordings(
candidate_set_df, mapped_listens_subset)
user_name = [row.user_name for row in df.collect()]
self.assertEqual(sorted(user_name), ['rob', 'rob', 'vansika_1'])
received_recording_mbid = sorted(
[row.mb_recording_mbid for row in df.collect()])
expected_recording_mbid = sorted([
"sf5a56f4-1f83-4681-b319-70a734d0d047",
"af5a56f4-1f83-4681-b319-70a734d0d047",
"sf5a56f4-1f83-4681-b319-70a734d0d047"
])
self.assertEqual(expected_recording_mbid, received_recording_mbid)
def test_get_recordings_dataframe(self):
metadata = {}
mapped_listens = utils.read_files_from_HDFS(RECOMMENDATION_RECORDING_MAPPED_LISTENS)
recordings_df = create_dataframes.get_recordings_df(mapped_listens, metadata, RECOMMENDATION_RECORDINGS_DATAFRAME)
self.assertEqual(recordings_df.count(), 20)
self.assertCountEqual(['artist_credit_id', 'recording_id', 'recording_mbid'], recordings_df.columns)
self.assertEqual(metadata['recordings_count'], 20)
status = utils.path_exists(RECOMMENDATION_RECORDINGS_DATAFRAME)
self.assertTrue(status)
def test_get_recordings_dataframe(self):
metadata = {}
mapped_listens = utils.read_files_from_HDFS(self.mapped_listens_path)
recordings_df = create_dataframes.get_recordings_df(mapped_listens, metadata)
self.assertEqual(recordings_df.count(), 3)
self.assertListEqual(sorted(self.get_recordings_df().columns), sorted(recordings_df.columns))
self.assertEqual(metadata['recordings_count'], 3)
status = utils.path_exists(path.RECORDINGS_DATAFRAME_PATH)
self.assertTrue(status)
def test_save_playcounts_df(self):
metadata = {}
mapped_listens = utils.read_files_from_HDFS(RECOMMENDATION_RECORDING_MAPPED_LISTENS)
users_df = create_dataframes.get_users_dataframe(mapped_listens, {}, RECOMMENDATION_RECORDING_USERS_DATAFRAME)
recordings_df = create_dataframes.get_recordings_df(mapped_listens, {}, RECOMMENDATION_RECORDINGS_DATAFRAME)
listens_df = create_dataframes.get_listens_df(mapped_listens, {})
create_dataframes.save_playcounts_df(listens_df, recordings_df, users_df, metadata, RECOMMENDATION_RECORDING_PLAYCOUNTS_DATAFRAME)
playcounts_df = utils.read_files_from_HDFS(RECOMMENDATION_RECORDING_PLAYCOUNTS_DATAFRAME)
self.assertEqual(playcounts_df.count(), 20)
self.assertListEqual(['spark_user_id', 'recording_id', 'count'], playcounts_df.columns)
self.assertEqual(metadata['playcounts_count'], 20)
def test_save_playcounts_df(self):
metadata = {}
mapped_listens = utils.read_files_from_HDFS(self.mapped_listens_path)
users_df = create_dataframes.get_users_dataframe(mapped_listens, {})
recordings_df = create_dataframes.get_recordings_df(mapped_listens, {})
listens_df = create_dataframes.get_listens_df(mapped_listens, {})
create_dataframes.save_playcounts_df(listens_df, recordings_df, users_df, metadata)
playcounts_df = utils.read_files_from_HDFS(path.PLAYCOUNTS_DATAFRAME_PATH)
self.assertEqual(playcounts_df.count(), 5)
self.assertListEqual(['user_id', 'recording_id', 'count'], playcounts_df.columns)
self.assertEqual(metadata['playcounts_count'], playcounts_df.count())
def setUpClass(cls):
super(CandidateSetsTestClass, cls).setUpClass()
cls.mapped_listens_df = listenbrainz_spark \
.session \
.read \
.parquet("file://" + os.path.join(TEST_DATA_PATH, 'mapped_listens_candidate_sets.parquet')) \
.where("recording_mbid IS NOT NULL")
to_date = datetime(2019, 1, 21, tzinfo=timezone.utc)
from_date = stats.offset_days(to_date, 4)
cls.mapped_listens_subset = candidate_sets.get_listens_to_fetch_top_artists(
cls.mapped_listens_df, from_date, to_date)
cls.recordings_df = create_dataframes.get_recordings_df(
cls.mapped_listens_df, {}, RECOMMENDATION_RECORDINGS_DATAFRAME)
cls.users_df = create_dataframes.get_users_dataframe(
cls.mapped_listens_df, {},
RECOMMENDATION_RECORDING_USERS_DATAFRAME)
def test_save_playcounts_df(self):
metadata = {}
mapped_listens = utils.read_files_from_HDFS(self.mapped_listens_path)
users_df = create_dataframes.get_users_dataframe(
mapped_listens, {}, self.users_path)
recordings_df = create_dataframes.get_recordings_df(
mapped_listens, {}, self.recordings_path)
listens_df = create_dataframes.get_listens_df(mapped_listens, {})
threshold = 0
create_dataframes.save_playcounts_df(listens_df, recordings_df,
users_df, threshold, metadata,
self.playcounts_path)
playcounts_df = utils.read_files_from_HDFS(
path.RECOMMENDATION_RECORDING_PLAYCOUNTS_DATAFRAME)
self.assertEqual(playcounts_df.count(), 5)
self.assertListEqual(['user_id', 'recording_id', 'count'],
playcounts_df.columns)
self.assertEqual(metadata['playcounts_count'], playcounts_df.count())
def test_get_similar_artist_candidate_set_df(self):
mapped_listens_df = utils.read_files_from_HDFS(
self.mapped_listens_path)
recordings_df = create_dataframes.get_recordings_df(
mapped_listens_df, {}, self.recordings_path)
users = create_dataframes.get_users_dataframe(mapped_listens_df, {},
self.users_path)
mapped_listens_subset = utils.read_files_from_HDFS(
self.mapped_listens_subset_path)
df = utils.create_dataframe(Row(similar_artist_credit_id=2,
similar_artist_name='martinkemp',
user_name='rob'),
schema=None)
similar_artist_df = df.union(
utils.create_dataframe(Row(similar_artist_credit_id=2,
similar_artist_name='martinkemp',
user_name='vansika_1'),
schema=None))
similar_artist_candidate_set_df, similar_artist_candidate_set_df_html = candidate_sets.get_similar_artist_candidate_set(
similar_artist_df, recordings_df, users, mapped_listens_subset)
cols = ['recording_id', 'user_id', 'user_name']
self.assertListEqual(sorted(cols),
sorted(similar_artist_candidate_set_df.columns))
self.assertEqual(similar_artist_candidate_set_df.count(), 2)
cols = [
'similar_artist_credit_id', 'similar_artist_name',
'mb_artist_credit_id', 'mb_artist_credit_mbids',
'mb_recording_mbid', 'msb_artist_credit_name_matchable',
'msb_recording_name_matchable', 'recording_id', 'user_name',
'user_id'
]
self.assertListEqual(
sorted(cols), sorted(similar_artist_candidate_set_df_html.columns))
self.assertEqual(similar_artist_candidate_set_df_html.count(), 2)
