def fit(self, ratings_df):
with elapsed_time('total fit'):
for model in self.models:
model.fit(ratings_df)
x, y = get_xy(ratings_df)
with elapsed_time('get blend predictions'):
blend_predictions = self.get_blend_predictions(x)
user_groups = x.groupby('userId')
movie_groups = x.groupby('movieId')
supports = []
for _, row in x.iterrows():
user_id = row['userId']
movie_id = row['movieId']
user_support = len(user_groups.get_group(user_id))
movie_support = len(movie_groups.get_group(movie_id))
support = min(user_support, movie_support)
supports.append(support)
# print Counter(supports)
self.regression.fit(blend_predictions, y)
print 'linear regression coefficients: %s, intercept: %.3f' % (
self.regression.coef_, self.regression.intercept_)
def fit(self, ratings_df):
with elapsed_time('fit'):
self.baseline_model.fit(ratings_df)
ratings_df = self.baseline_model.create_modified_ratings(ratings_df)
unique_movie_ids = np.array(sorted(ratings_df['movieId'].unique()))
for _, row in ratings_df.iterrows():
movie_id = row['movieId']
user_id = row['userId']
rating = row['rating']
self.ratings_by_movie[movie_id][user_id] = rating
self.ratings_by_user[user_id][movie_id] = rating
for movie_id in unique_movie_ids:
self.raters_by_movie[movie_id] = set(self.ratings_by_movie[movie_id].keys())
for movie_index_1, movie_id_1 in enumerate(unique_movie_ids):
for movie_index_2 in xrange(movie_index_1 + 1, len(unique_movie_ids)):
movie_id_2 = unique_movie_ids[movie_index_2]
similarity = self.calculate_similarity(movie_id_1, movie_id_2)
movie_pair = (movie_id_1, movie_id_2)
self.movie_similarity[movie_pair] = similarity
# self.movie_aij[movie_pair] = aij
return self
def main():
ratings_df = read_ratings_df_with_timestamp('ml-latest-small/ratings.csv')
# ratings_df = read_ratings_df('ml-latest-small/ratings_5_pct.csv')
with elapsed_time('build model'):
score_model(ratings_df,
model_f=UserSimilarityModel,
model_name='user similarity model')
def fit(self, ratings_df):
with elapsed_time('effects init'):
_, y_train = get_xy(ratings_df)
self.y_mean = y_train.mean()
movie_ratings = ratings_df.groupby('movieId')['rating']
self.user_groups = ratings_df.groupby('userId')
self.movie_effects = self.calculate_movie_effects(movie_ratings)
self.user_effects = self.calculate_user_effects(self.user_groups)
return self
def main():
common.verify_output_dir(TMP_DIR)
out = get_output_filename()
command = "arecord -d 0 -c 2 -f S16_LE -r 44100 -t wav -D copy | oggenc -o %s -" % out
print color(command, 'cyan')
print color("Press CTRL+C to stop the recording process.", 'green')
start = time.time()
os.system(command)
end = time.time()
print color( common.elapsed_time(end, start), 'yellow' )
print color("Size of the output file: %s bytes." % common.numberToPrettyString(os.path.getsize(out)), 'yellow')
print color("If you want to listen to the recorded file, execute the following command:", 'green')
print color("mplayer %s" % out, 'cyan')
def main():
common.verify_output_dir(TMP_DIR)
out = get_output_filename()
command = "arecord -d 0 -c 2 -f S16_LE -r 44100 -t wav -D copy | oggenc -o %s -" % out
print color(command, 'cyan')
print color("Press CTRL+C to stop the recording process.", 'green')
start = time.time()
os.system(command)
end = time.time()
print color(common.elapsed_time(end, start), 'yellow')
print color(
"Size of the output file: %s bytes." %
common.numberToPrettyString(os.path.getsize(out)), 'yellow')
print color(
"If you want to listen to the recorded file, execute the following command:",
'green')
print color("mplayer %s" % out, 'cyan')
def build_model(ratings_df):
train_scores = []
test_scores = []
train_rmse_scores = []
test_rmse_scores = []
n_iter = 1
# model = BaselineTotalMeanModel()
# model = BaselineMeansModel(user_weight=0.5)
# model = BaselineEffectsModel(movie_lambda=5.0, user_lambda=20.0)
model = UserSimilarityModel(movie_lambda=5.0, user_lambda=20.0)
for _ in xrange(n_iter):
train_ratings_df, test_ratings_df = train_test_split(ratings_df)
model = model.fit(train_ratings_df)
x_train, y_train = get_xy(train_ratings_df)
x_test, y_test = get_xy(test_ratings_df)
with elapsed_time('scoring'):
y_train_pred = model.predict(x_train)
y_test_pred = model.predict(x_test)
train_score = r2_score(y_train, y_train_pred)
test_score = r2_score(y_test, y_test_pred)
train_rmse = root_mean_squared_error(y_train, y_train_pred)
test_rmse = root_mean_squared_error(y_test, y_test_pred)
train_scores.append(train_score)
test_scores.append(test_score)
train_rmse_scores.append(train_rmse)
test_rmse_scores.append(test_rmse)
print 'mean train score: %.4f, std: %.4f' % (np.mean(train_scores),
np.std(train_scores))
print 'mean test score: %.4f, std: %.4f' % (np.mean(test_scores),
np.std(test_scores))
print
print 'mean train rmse: %.4f, std: %.4f' % (np.mean(train_rmse_scores),
np.std(train_rmse_scores))
print 'mean test rmse: %.4f, std: %.4f' % (np.mean(test_rmse_scores),
np.std(test_rmse_scores))
def read_ratings_df(file_name):
with elapsed_time('loaded csv'):
ratings_df = pd.read_csv(file_name)
return ratings_df
def read_ratings_df_with_timestamp(file_name):
with elapsed_time('loaded csv'):
ratings_df = pd.read_csv(file_name,
parse_dates=['timestamp'],
date_parser=date_parse)
return ratings_df
