def main(args):
users = pd.read_csv(
USERS_CSV,
sep='::',
engine='python',
usecols=['UserID', 'Gender', 'Age', 'Occupation', 'Zip-code'])
print('{} description of {} users loaded'.format(len(users), max_userid))
movies = pd.read_csv(MOVIES_CSV,
sep='::',
engine='python',
usecols=['movieID', 'Title', 'Genres'])
print('{} descriptions of {} movies loaded'.format(len(movies),
max_movieid))
test_data = pd.read_csv(TEST_CSV, usecols=['UserID', 'MovieID'])
print('{} testing data loaded.'.format(test_data.shape[0]))
trained_model = build_cf_model(max_userid, max_movieid, DIM, isBest=True)
print('Loading model weights...')
trained_model.load_weights(MODEL_WEIGHTS_FILE)
print('Loading model done!!!')
recommendations = pd.read_csv(TEST_CSV, usecols=['TestDataID'])
recommendations['Rating'] = test_data.apply(
lambda x: predict_rating(trained_model, x['UserID'], x['MovieID']),
axis=1)
# print(recommendations)
ensure_dir(args.output)
recommendations.to_csv(args.output,
index=False,
columns=['TestDataID', 'Rating'])
def main(args):
users = pd.read_csv(
USERS_CSV,
sep='::',
engine='python',
usecols=['UserID', 'Gender', 'Age', 'Occupation', 'Zip-code'])
print('{} description of {} users loaded'.format(len(users), max_userid))
movies = pd.read_csv(MOVIES_CSV,
sep='::',
engine='python',
usecols=['movieID', 'Title', 'Genres'])
print('{} descriptions of {} movies loaded'.format(len(movies),
max_movieid))
test_data = pd.read_csv(TEST_CSV, usecols=['UserID', 'MovieID'])
print('{} testing data loaded.'.format(test_data.shape[0]))
trained_model = build_cf_model(max_userid, max_movieid, DIM, isBest=True)
print('Loading model weights...')
trained_model.load_weights(MODEL_WEIGHTS_FILE)
print('Loading model done!!!')
movies_array = movies.as_matrix()
genres_map = {}
for i in range(movies_array.shape[0]):
genre = movies_array[i][2].split('|')[0]
if genre not in genres_map.keys():
genres_map[genre] = [movies_array[i][0] - 1]
else:
genres_map[genre].append(movies_array[i][0] - 1)
# print(genres_map)
movie_emb = np.array(trained_model.layers[3].get_weights()).squeeze()
model = TSNE(n_components=2, random_state=0)
movie_emb = model.fit_transform(movie_emb)
for key in genres_map.keys():
genres_map[key] = movie_emb[genres_map[key]]
# print(key, genres_map[key].shape)
new_genres_map = {}
for c in classes:
new_genres_map[c] = np.ndarray(shape=(0, 2))
for g in c.split('|'):
new_genres_map[c] = np.concatenate(
(new_genres_map[c], genres_map[g]), axis=0)
# print(new_genres_map[c].shape)
draw(new_genres_map, 'graph.png')
def main(args):
ratings = pd.read_csv(args.train, usecols=['UserID', 'MovieID', 'Rating'])
max_userid = ratings['UserID'].drop_duplicates().max()
max_movieid = ratings['MovieID'].drop_duplicates().max()
ratings['User_emb_id'] = ratings['UserID'] - 1
ratings['Movie_emb_id'] = ratings['MovieID'] - 1
print('{} ratings loaded.'.format(ratings.shape[0]))
maximum = {}
maximum['max_userid'] = [max_userid]
maximum['max_movieid'] = [max_movieid]
maximum['dim'] = [DIM]
pd.DataFrame(data=maximum).to_csv(MAX_FILE, index=False)
print('max info save to {}'.format(MAX_FILE))
ratings = ratings.sample(frac=1)
Users = ratings['User_emb_id'].values
print('Users: {}, shape = {}'.format(Users, Users.shape))
Movies = ratings['Movie_emb_id'].values
print('Movies: {}, shape = {}'.format(Movies, Movies.shape))
Ratings = ratings['Rating'].values
print('Ratings: {}, shape = {}'.format(Ratings, Ratings.shape))
model = build_cf_model(max_userid, max_movieid, DIM)
model.compile(loss='mse', optimizer='adamax', metrics=[rmse])
callbacks = [
EarlyStopping('val_rmse', patience=2),
ModelCheckpoint(MODEL_WEIGHTS_FILE, save_best_only=True)
]
history = model.fit([Users, Movies],
Ratings,
epochs=1000,
batch_size=256,
validation_split=.1,
verbose=1,
callbacks=callbacks)