urm_col = sps.csc_matrix(urm)
top_p = np.zeros(urm.shape[1])
rec = []
eurm1 = sps.lil_matrix(urm.shape)
eurm2 = sps.lil_matrix(urm.shape)
print(eurm1.shape)
pids = dr.get_test_pids(cat=2)
pids_all = dr.get_test_pids()
# TopPop Album
# ucm_album = dr.get_ucm_albums().tocsc()
# album_dic = dr.get_track_to_album_dict()
# TopPop Artist
ucm_album = dr.get_ucm_albums().tocsc()
artists_dic = dr.get_track_to_artist_dict()
album_to_tracks = load_obj(name="album_tracks_dict_offline",
path=ROOT_DIR + "/boosts/")
tracks_to_album = load_obj(name="artist_tracks_dict_offline",
path=ROOT_DIR + "/boosts/")
for row in tqdm(pids, desc="part1"):
track_ind = urm.indices[urm.indptr[row]:urm.indptr[row + 1]][0]
# TopPop Album
album = artists_dic[track_ind]
playlists = ucm_album.indices[ucm_album.indptr[album]:ucm_album.
indptr[album + 1]]
top = urm[playlists].sum(axis=0).A1.astype(np.int32)
from utils.post_processing import *
from personal.Tommaso.NLP.NLP import NLP
from utils.definitions import *
# Datareader
dr = Datareader(mode='online', only_load=True)
#ev = Evaluator(dr)
# Dataframe with interactions
df_train = dr.get_df_train_interactions()
df_test = dr.get_df_test_interactions()
df = pd.concat([df_train, df_test], axis=0, join='outer')
playlists = df['pid'].as_matrix()
tracks = df['tid'].as_matrix()
dictionary = dr.get_track_to_artist_dict()
pids = list(dr.get_train_pids()) + list(dr.get_test_pids())
# URM
urm = dr.get_urm()
urm = urm[pids]
print(urm.shape)
print('artists...')
artists = [dictionary[t] for t in tracks]
print('ucm...')
ucm = sparse.csr_matrix((np.ones(len(playlists)), (playlists, artists)),
shape=(1049361, len(dr.get_artists())))
ucm = ucm.tocsr()
