if __name__ == "__main__":
#chunks = file_io.read_lastfm_user_art_file("data/userid-timestamp-artid-artname-traid-traname.tsv")
chunks = file_io.read_lastfm_user_art_file("data/test_shorter.tsv")
# read songs
vectorizer = FeatureHasher()
pre = Preprocessor(chunks, vectorizer)
songs = pre.read_songs(20)
print(songs)
# reset file reader
#chunks = file_io.read_lastfm_user_art_file("data/tmp.tsv")
#pre.reset_file_reader(chunks)
# read user song mapping
pre.read_user_songs(1000)
# convert to user-song matrix
X = pre.get_user_song_matrix()
start_time = time.time()
clf = KNeighborsClassifier(n_neighbors=1)
clf.fit(X, list(range(X.shape[0])))
print(clf.predict(pre.user_song_dict["user_000001"]))
print("training and predict using {0}".format(time.time() - start_time))
#song_content = [ (artist,song) for (artist,song) in zip(list(songs['artname']), list(songs['traname']))]
# temporary song_list
song_content = [('Underworld', 'Boy, Boy, Boy'),
('Underworld', 'Crocodile'),
('Led Zeppelin', 'Stairway to heaven'),
if __name__ == "__main__":
start_time = time.time()
np.set_printoptions(threshold=np.nan)
vectorizer = DictVectorizer()
# reset file reader
chunks = file_io.read_lastfm_user_art_file("data/halfid_20%_train.tsv")
valid_songs = [] # don't filter with valid songs
valid_songs = file_io.get_all_valid_songs('data/song_word2vec_whole_truncate_60000_new.csv')
pre = Preprocessor(chunks, vectorizer, valid_songs)
pre.reset_file_reader(chunks)
# read user song mapping
pre.read_user_songs(3000000)
# convert to user-song matrix
X = pre.get_user_song_matrix()
print("non zeros: {0}".format(X.count_nonzero()))
print("pre-processed in {0:.2f} sec".format(time.time() - start_time))
#cluster_cf.cluster_usr(X, k=5)
print("non zeros: {0}".format(X.count_nonzero()))
pred = recommendation.predict_by_user(X)
#pred = recommendation.predict_by_factorize(X)
recommended = recommendation.recommend_all(X, pred, masked=False)
recommend_numbers = 5
songs = pre.get_songs_by_indices(recommended, recommend_numbers)
print("user 1 top recommended songs: {0}".format(songs[0]))
print("predict in {0:.2f} sec".format(time.time() - start_time))