def split_only_sequential(self, URM, URM_df):
helper = Helper()
sequential_playlists = helper.get_target_playlists_list()[:5000]
selected_playlists = np.array([])
self.target_playlists = sequential_playlists
grouped = URM_df.groupby(
'playlist_id', as_index=True).apply(lambda x: list(x['track_id']))
relevant_items = defaultdict(list)
for playlist_id in sequential_playlists:
# Tracks = lista delle tracks prese dalla URM
tracks = np.array(grouped[playlist_id])
to_be_removed = int(len(tracks) * 0.2)
# Torna le #to_be_removed tracks ordinate sequenzialmente. e le toglie dalla lista delle tracks
to_be_removed_tracks = helper.get_sorted_tracks_in_playlist(
playlist_id)[-to_be_removed:]
for track in to_be_removed_tracks:
relevant_items[playlist_id].append(track)
tracks = np.delete(tracks, np.where(tracks == track))
grouped[playlist_id] = tracks
all_tracks = self.tracks_df["track_id"].unique()
matrix = MultiLabelBinarizer(classes=all_tracks,
sparse_output=True).fit_transform(grouped)
self.URM_train = matrix.tocsr()
self.URM_train = self.URM_train.astype(np.float64)
self.dict_test = relevant_items
def split_sequential(self, URM, URM_df):
segment = 1
# splitting URM in test set e train set
selected_playlists = np.array([])
available_playlists = np.arange(URM.shape[0])
target_analyzer = TargetAnalyzer()
#Gets distribution of only last 5000 playlists
dist = target_analyzer.get_distribution_array_only_last(segment)
helper = Helper()
target_playlists = helper.get_target_playlists_list()[:5000]
#n_target = np.sum(dist) - len(target_playlists)
# Removing from the cluster distribution the len of the sequential target
for playlist_id in target_playlists:
playlist_id = int(playlist_id)
available_playlists = np.delete(
available_playlists,
np.where(available_playlists == playlist_id))
selected_playlists = np.append(selected_playlists, playlist_id)
#target_len = len(URM[playlist_id].data)
#dist[target_len] -= 1
print("Clustering with segment = " + str(segment))
for key in tqdm(range(len(dist))):
while dist[key] != 0:
random_index = randint(0, len(available_playlists) - 1)
playlist_id = available_playlists[random_index]
target_segment = int(0.8 * len(URM[playlist_id].data))
if target_segment == key:
available_playlists = np.delete(
available_playlists,
np.where(available_playlists == playlist_id))
selected_playlists = np.append(selected_playlists,
playlist_id)
dist[key] -= 1
self.target_playlists = selected_playlists.astype(int)
grouped = URM_df.groupby(
'playlist_id', as_index=True).apply(lambda x: list(x['track_id']))
relevant_items = defaultdict(list)
for playlist_id in selected_playlists:
#Tracks = lista delle tracks prese dalla URM
tracks = np.array(grouped[playlist_id])
if playlist_id in target_playlists:
to_be_removed = int(len(tracks) * 0.2)
#Torna le #to_be_removed tracks ordinate sequenzialmente. e le toglie dalla lista delle tracks
to_be_removed_tracks = helper.get_sorted_tracks_in_playlist(
playlist_id)[-to_be_removed:]
for track in to_be_removed_tracks:
relevant_items[playlist_id].append(track)
tracks = np.delete(tracks, np.where(tracks == track))
else:
to_be_removed = int(len(tracks) * 0.2)
for i in range(to_be_removed):
index = randint(0, len(tracks) - 1)
removed_track = tracks[index]
relevant_items[playlist_id].append(removed_track)
tracks = np.delete(tracks, index)
grouped[playlist_id] = tracks
all_tracks = self.tracks_df["track_id"].unique()
matrix = MultiLabelBinarizer(classes=all_tracks,
sparse_output=True).fit_transform(grouped)
self.URM_train = matrix.tocsr()
self.URM_train = self.URM_train.astype(np.float64)
self.dict_test = relevant_items
