[ci][python] updated pep8 to pycodestyle (#1358)

* updated pep8 to pycodestyle

* fixed E722 do not use bare 'except'

* fixed W605 invalid escape sequence '\*'

* fixed W504 line break after binary operator

* ignore W605 invalid escape sequence '\*' in nuget builder

* made pycodestyle happy

.appveyor.yml

@@ -30,7 +30,7 @@ install:
   - ps: $env:LGB_VER = (Get-Content VERSION.txt).trim()
   - conda config --set always_yes yes --set changeps1 no
   - conda update -q conda
-  - conda create -q -n test-env python=%PYTHON_VERSION% numpy nose scipy scikit-learn pandas matplotlib pep8 pytest
+  - conda create -q -n test-env python=%PYTHON_VERSION% numpy nose scipy scikit-learn pandas matplotlib pytest
   - activate test-env
 
 build_script:

.travis/test.sh

@@ -50,8 +50,8 @@ if [[ ${TASK} == "check-docs" ]]; then
 fi
 
 if [[ ${TASK} == "pylint" ]]; then
-    conda install pep8
-    pep8 --ignore=E501 --exclude=./compute,./docs . || exit -1
+    conda install pycodestyle
+    pycodestyle --ignore=E501,W503 --exclude=./compute,./docs,./.nuget . || exit -1
     exit 0
 fi
 

examples/python-guide/advanced_example.py

@@ -8,7 +8,7 @@ from sklearn.metrics import mean_squared_error
 
 try:
     import cPickle as pickle
-except:
+except BaseException:
     import pickle
 
 # load or create your dataset

python-package/lightgbm/basic.py

@@ -438,7 +438,7 @@ class _InnerPredictor(object):
         elif isinstance(data, list):
             try:
                 data = np.array(data)
-            except:
+            except BaseException:
                 raise ValueError('Cannot convert data list to numpy array.')
             preds, nrow = self.__pred_for_np2d(data, num_iteration,
                                                predict_type)
@@ -446,7 +446,7 @@ class _InnerPredictor(object):
             try:
                 warnings.warn('Converting data to scipy sparse matrix.')
                 csr = scipy.sparse.csr_matrix(data)
-            except:
+            except BaseException:
                 raise TypeError('Cannot predict data for type {}'.format(type(data).__name__))
             preds, nrow = self.__pred_for_csr(csr, num_iteration,
                                               predict_type)
@@ -712,7 +712,7 @@ class Dataset(object):
             try:
                 csr = scipy.sparse.csr_matrix(data)
                 self.__init_from_csr(csr, params_str, ref_dataset)
-            except:
+            except BaseException:
                 raise TypeError('Cannot initialize Dataset from {}'.format(type(data).__name__))
         if label is not None:
             self.set_label(label)

python-package/lightgbm/sklearn.py

@@ -197,7 +197,7 @@ class LGBMModel(_LGBMModelBase):
 
             Note
             ----
-            \*\*kwargs is not supported in sklearn, it may cause unexpected issues.
+            \\*\\*kwargs is not supported in sklearn, it may cause unexpected issues.
 
         Attributes
         ----------
@@ -618,12 +618,12 @@ class LGBMRegressor(LGBMModel, _LGBMRegressorBase):
         return self
 
     base_doc = LGBMModel.fit.__doc__
-    fit.__doc__ = (base_doc[:base_doc.find('eval_class_weight :')] +
-                   base_doc[base_doc.find('eval_init_score :'):])
+    fit.__doc__ = (base_doc[:base_doc.find('eval_class_weight :')]
+                   + base_doc[base_doc.find('eval_init_score :'):])
     base_doc = fit.__doc__
-    fit.__doc__ = (base_doc[:base_doc.find('eval_metric :')] +
-                   'eval_metric : string, list of strings, callable or None, optional (default="l2")\n' +
-                   base_doc[base_doc.find('            If string, it should be a built-in evaluation metric to use.'):])
+    fit.__doc__ = (base_doc[:base_doc.find('eval_metric :')]
+                   + 'eval_metric : string, list of strings, callable or None, optional (default="l2")\n'
+                   + base_doc[base_doc.find('            If string, it should be a built-in evaluation metric to use.'):])
 
 
 class LGBMClassifier(LGBMModel, _LGBMClassifierBase):
@@ -679,9 +679,9 @@ class LGBMClassifier(LGBMModel, _LGBMClassifierBase):
         return self
 
     base_doc = LGBMModel.fit.__doc__
-    fit.__doc__ = (base_doc[:base_doc.find('eval_metric :')] +
-                   'eval_metric : string, list of strings, callable or None, optional (default="logloss")\n' +
-                   base_doc[base_doc.find('            If string, it should be a built-in evaluation metric to use.'):])
+    fit.__doc__ = (base_doc[:base_doc.find('eval_metric :')]
+                   + 'eval_metric : string, list of strings, callable or None, optional (default="logloss")\n'
+                   + base_doc[base_doc.find('            If string, it should be a built-in evaluation metric to use.'):])
 
     def predict(self, X, raw_score=False, num_iteration=0):
         class_probs = self.predict_proba(X, raw_score, num_iteration)
@@ -773,12 +773,12 @@ class LGBMRanker(LGBMModel):
         return self
 
     base_doc = LGBMModel.fit.__doc__
-    fit.__doc__ = (base_doc[:base_doc.find('eval_class_weight :')] +
-                   base_doc[base_doc.find('eval_init_score :'):])
+    fit.__doc__ = (base_doc[:base_doc.find('eval_class_weight :')]
+                   + base_doc[base_doc.find('eval_init_score :'):])
     base_doc = fit.__doc__
-    fit.__doc__ = (base_doc[:base_doc.find('eval_metric :')] +
-                   'eval_metric : string, list of strings, callable or None, optional (default="ndcg")\n' +
-                   base_doc[base_doc.find('            If string, it should be a built-in evaluation metric to use.'):base_doc.find('early_stopping_rounds :')] +
-                   'eval_at : list of int, optional (default=[1])\n'
-                   '            The evaluation positions of NDCG.\n' +
-                   base_doc[base_doc.find('        early_stopping_rounds :'):])
+    fit.__doc__ = (base_doc[:base_doc.find('eval_metric :')]
+                   + 'eval_metric : string, list of strings, callable or None, optional (default="ndcg")\n'
+                   + base_doc[base_doc.find('            If string, it should be a built-in evaluation metric to use.'):base_doc.find('early_stopping_rounds :')]
+                   + 'eval_at : list of int, optional (default=[1])\n'
+                     '            The evaluation positions of NDCG.\n'
+                   + base_doc[base_doc.find('        early_stopping_rounds :'):])

tests/python_package_test/test_engine.py

@@ -626,13 +626,11 @@ class TestEngine(unittest.TestCase):
         x2_negatively_correlated_with_y = np.random.random(size=number_of_dpoints)
         x = np.column_stack((x1_positively_correlated_with_y, x2_negatively_correlated_with_y))
         zs = np.random.normal(loc=0.0, scale=0.01, size=number_of_dpoints)
-        y = (
-            5 * x1_positively_correlated_with_y +
-            np.sin(10 * np.pi * x1_positively_correlated_with_y) -
-            5 * x2_negatively_correlated_with_y -
-            np.cos(10 * np.pi * x2_negatively_correlated_with_y) +
-            zs
-        )
+        y = (5 * x1_positively_correlated_with_y
+             + np.sin(10 * np.pi * x1_positively_correlated_with_y)
+             - 5 * x2_negatively_correlated_with_y
+             - np.cos(10 * np.pi * x2_negatively_correlated_with_y)
+             + zs)
         trainset = lgb.Dataset(x, label=y)
         params = {
             'min_data': 20,