[ci] [python-package] enforce flake8 checks (fixes #5566)

.ci/test.sh

@@ -76,13 +76,16 @@ if [[ $TASK == "lint" ]]; then
  conda install -q -y -n $CONDA_ENV \
  cmakelint \
  cpplint \
+ flake8 \
  isort \
  mypy \
- pycodestyle \
  pydocstyle \
  "r-lintr>=3.0"
- echo "Linting Python code"
- pycodestyle --ignore=E501,W503 --exclude=./.nuget,./external_libs . || exit -1
+ echo "Linting Pythone code"
+ flake8 \
+ --ignore=E501,W503 \
+ --exclude=./.nuget,./external_libs,./python-package/build \
+ . || exit -1
  pydocstyle --convention=numpy --add-ignore=D105 --match-dir="^(?!^external_libs|test|example).*" --match="(?!^test_|setup).*\.py" . || exit -1
  isort . --check-only || exit -1
  mypy --ignore-missing-imports python-package/ || true

docs/conf.py

@@ -105,7 +105,7 @@ def run(self) -> List:
  'scipy.sparse',
 ]
 try:
- import sklearn
+ import sklearn # noqa: F401
 except ImportError:
  autodoc_mock_imports.append('sklearn')
 # hide type hints in API docs

python-package/lightgbm/compat.py

@@ -36,14 +36,14 @@ def __init__(self, *args, **kwargs):
 
 """matplotlib"""
 try:
- import matplotlib
+ import matplotlib # noqa: F401
  MATPLOTLIB_INSTALLED = True
 except ImportError:
  MATPLOTLIB_INSTALLED = False
 
 """graphviz"""
 try:
- import graphviz
+ import graphviz # noqa: F401
  GRAPHVIZ_INSTALLED = True
 except ImportError:
  GRAPHVIZ_INSTALLED = False

python-package/setup.py

@@ -96,7 +96,7 @@ def silent_call(cmd: List[str], raise_error: bool = False, error_msg: str = '')
  with open(LOG_PATH, "ab") as log:
  subprocess.check_call(cmd, stderr=log, stdout=log)
  return 0
- except Exception as err:
+ except Exception:
  if raise_error:
  raise Exception("\n".join((error_msg, LOG_NOTICE)))
  return 1

tests/distributed/_test_distributed.py

@@ -4,7 +4,7 @@
 import subprocess
 from concurrent.futures import ThreadPoolExecutor
 from pathlib import Path
-from typing import Any, Dict, Generator, List
+from typing import Any, Dict, Generator, List, Optional
 
 import numpy as np
 import pytest
@@ -106,7 +106,7 @@ def _write_data(self, partitions: List[np.ndarray]) -> None:
  for i, partition in enumerate(partitions):
  np.savetxt(str(TESTS_DIR / f'train{i}.txt'), partition, delimiter=',')
 
- def fit(self, partitions: List[np.ndarray], train_config: Dict = {}) -> None:
+ def fit(self, partitions: List[np.ndarray], train_config: Optional[Dict] = None) -> None:
  """Run the distributed training process on a single machine.
 
  For each worker i:
@@ -117,6 +117,7 @@ def fit(self, partitions: List[np.ndarray], train_config: Dict = {}) -> None:
  5. The trained model is saved as model{i}.txt. Each model file only differs in data and local_listen_port.
  The whole training set is saved as train.txt.
  """
+ train_config = train_config or {}
  self.train_config = copy.deepcopy(self.default_train_config)
  self.train_config.update(train_config)
  self.n_workers = self.train_config['num_machines']

tests/python_package_test/test_callback.py

@@ -3,7 +3,7 @@
 
 import lightgbm as lgb
 
-from .utils import SERIALIZERS, pickle_and_unpickle_object, pickle_obj, unpickle_obj
+from .utils import SERIALIZERS, pickle_and_unpickle_object
 
 
 def reset_feature_fraction(boosting_round):

tests/python_package_test/test_dask.py

@@ -1724,7 +1724,7 @@ def test_dask_methods_and_sklearn_equivalents_have_similar_signatures(methods):
 
 @pytest.mark.parametrize('task', tasks)
 def test_training_succeeds_when_data_is_dataframe_and_label_is_column_array(task, cluster):
- with Client(cluster) as client:
+ with Client(cluster):
  _, _, _, _, dX, dy, dw, dg = _create_data(
  objective=task,
  output='dataframe',
@@ -1803,7 +1803,7 @@ def _tested_estimators():
 @pytest.mark.parametrize("estimator", _tested_estimators())
 @pytest.mark.parametrize("check", sklearn_checks_to_run())
 def test_sklearn_integration(estimator, check, cluster):
- with Client(cluster) as client:
+ with Client(cluster):
  estimator.set_params(local_listen_port=18000, time_out=5)
  name = type(estimator).__name__
  check(name, estimator)

tests/python_package_test/test_engine.py

@@ -2903,7 +2903,7 @@ def test_forced_split_feature_indices(tmp_path):
  "forcedsplits_filename": tmp_split_file
  }
  with pytest.raises(lgb.basic.LightGBMError, match="Forced splits file includes feature index"):
- bst = lgb.train(params, lgb_train)
+ lgb.train(params, lgb_train)
 
 
 def test_forced_bins():

tests/python_package_test/test_sklearn.py

@@ -446,7 +446,9 @@ def test_clone_and_property():
 
  gbm_clone = clone(gbm)
  assert isinstance(gbm.booster_, lgb.Booster)
+ assert isinstance(gbm_clone.booster_, lgb.Booster)
  assert isinstance(gbm.feature_importances_, np.ndarray)
+ assert isinstance(gbm_clone.feature_importances_, np.ndarray)
 
  X, y = load_digits(n_class=2, return_X_y=True)
  clf = lgb.LGBMClassifier(n_estimators=10, verbose=-1)