def test_processor(feature_size, chunksize):
"""Tests FileProcessor.
:param feature_size: int, size of feature vector.
:param chunksize: int, FileProcessor chunk size.
"""
sep = '\t'
n_rows = 50
feature = 3
with TemporaryDirectory() as dir:
input_path = os.path.join(dir, 'data.tsv')
output_path = os.path.join(dir, 'data_proc.tsv')
data, feature_values = generate_data(n_rows=n_rows,
feature=feature,
feature_size=feature_size,
seed=42)
data.to_csv(input_path, sep=sep, index=False)
reader_params = {
'chunksize': chunksize,
'sep': sep,
}
transformers = (
Standardizer,
MaxIndex,
MaxFeatureAbsMeanDiff,
)
processor = FileProcessor(transformers, reader_params=reader_params)
processor.train(input_path)
processor.process(input_path, output_path)
processed = pd.read_csv(output_path, sep=sep)
# check feature_{i}_stand_{index}
expected_stand = (feature_values -
feature_values.mean(axis=0)) / feature_values.std(axis=0,
ddof=1)
stand = processed.filter(regex=f'feature_{feature}_stand_[0-9]+')
assert np.allclose(expected_stand, stand)
assert np.allclose(stand.mean(axis=0), 0)
assert np.allclose(stand.std(axis=0, ddof=1), 1)
# check max_feature_{i}_index
expected_max = feature_values.max(axis=1)
max_index = processed[f'max_feature_{feature}_index'].values
max_mask = (max_index.reshape(
(-1, 1)) == np.arange(feature_values.shape[1]).reshape((1, -1)))
fact_max = feature_values[max_mask]
assert np.allclose(expected_max, fact_max)
# check max_feature_{i}_abs_mean_diff
expected_max_mean = np.broadcast_to(feature_values.mean(axis=0),
shape=max_mask.shape)[max_mask]
expected_abs_mean_diff = np.abs(expected_max - expected_max_mean)
abs_mean_diff = processed[f'max_feature_{feature}_abs_mean_diff']
assert np.allclose(expected_abs_mean_diff, abs_mean_diff)
header = True
for seed in tqdm(range(100), desc='generating data'):
data, _ = generate_data(
n_rows=100_000,
feature=feature,
feature_size=512,
seed=seed
)
data.to_csv(
input_path,
sep=sep,
index=False,
mode='a',
header=header
)
header = False
reader_params = {
'chunksize': 10_000,
'sep': sep,
}
transformers = (
Standardizer,
MaxIndex,
MaxFeatureAbsMeanDiff,
)
processor = FileProcessor(transformers, reader_params=reader_params)
processor.train(input_path)
processor.process(input_path, output_path)
parser.add_argument(
'-o', '--output',
default=os.path.join(DATA_DIR, OUTPUT_FILE),
help='Path to file, where processed data will be stored.',
)
parser.add_argument(
'-c', '--chunk_size',
default=128,
help='Rows to process at a time.',
)
args = parser.parse_args()
if __name__ == '__main__':
train_path = args.train
test_path = args.input
output_path = args.output
reader_params = {
'chunksize': args.chunk_size,
'sep': SEPARATOR,
}
transformers = (
Standardizer,
MaxIndex,
MaxFeatureAbsMeanDiff,
)
processor = FileProcessor(transformers, reader_params=reader_params)
processor.train(train_path)
processor.process(test_path, output_path)
