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_filter_last_x_days_recordings(self):
top_artist_limit = 1
top_artist_df = candidate_sets.get_top_artists(self.mapped_listens_df, top_artist_limit, [])
_, candidate_set_df = candidate_sets.get_top_artist_candidate_set(
top_artist_df, self.recordings_df, self.users_df, self.mapped_listens_subset
)
df = candidate_sets.filter_last_x_days_recordings(candidate_set_df, self.mapped_listens_subset)
user_name = [row.user_name for row in df.collect()]
self.assertEqual(sorted(user_name), ['rob', 'vansika_1'])
received_recording_mbid = sorted([row.recording_mbid for row in df.collect()])
expected_recording_mbid = sorted(
["sf5a56f4-1f83-4681-b319-70a734d0d047", "sf5a56f4-1f83-4681-b319-70a734d0d047"]
)
self.assertEqual(expected_recording_mbid, received_recording_mbid)