def load_test_data(self, sessions_df):
data_df = read_from_csv(self.task_core.test_data_file, self.task_core.n_seed
#, max_rows=50000
)
cache_file = os.path.join(self.task_core.cache_dir, 'features_test_' + str(len(data_df.index)) + '.p')
if os.path.isfile(cache_file):
print('Loading test features from file')
x = DataSet.load_from_file(cache_file)
else:
x = ds_from_df(data_df, sessions_df, True)
print('saving test features to file')
DataSet.save_to_file(x, cache_file)
return x
def load_train_data(self, sessions_df):
data_df = read_from_csv(self.task_core.data_file, self.task_core.n_seed
#, max_rows=50000
)
cache_file = os.path.join(self.task_core.cache_dir, 'features_train_' + str(len(data_df.index)) + '.p')
if os.path.isfile(cache_file):
print('Loading train features from file')
x = DataSet.load_from_file(cache_file)
else:
x = ds_from_df(data_df, sessions_df, False)
print('saving train features to file')
DataSet.save_to_file(x, cache_file)
labels = data_df['country_destination'].values
y = le_.transform(labels)
return x, y
