Make autosklearn/pipeline PEP8 compliant (#826)

* make components/feature_preprocessing PEP8 compliant

* make components/data_preprocessing PEP8 compliant

* make components/classification PEP8 compliant

* make components/regression PEP8 compliant

* make pipeline/* PEP8 compliant

* implement PR review requested changes

Author: gui-miotto

autosklearn/pipeline/base.py

@@ -1,10 +1,9 @@
 from abc import ABCMeta
-from collections import defaultdict
 
 import numpy as np
 from ConfigSpace import Configuration
 from sklearn.pipeline import Pipeline
-from sklearn.utils.validation import check_random_state, check_is_fitted
+from sklearn.utils.validation import check_random_state
 
 from .components.base import AutoSklearnChoice, AutoSklearnComponent
 import autosklearn.pipeline.create_searchspace_util
@@ -226,7 +225,7 @@ def get_hyperparameter_search_space(self, dataset_properties=None):
         return self.config_space
 
     def _get_hyperparameter_search_space(self, include=None, exclude=None,
-                                        dataset_properties=None):
+                                         dataset_properties=None):
         """Return the configuration space for the CASH problem.
 
         This method should be called by the method
@@ -320,8 +319,10 @@ def _get_base_search_space(self, cs, dataset_properties, exclude,
             # if the node isn't a choice we can add it immediately because it
             #  must be active (if it wasn't, np.sum(matches) would be zero
             if not is_choice:
-                cs.add_configuration_space(node_name,
-                    node.get_hyperparameter_search_space(dataset_properties))
+                cs.add_configuration_space(
+                    node_name,
+                    node.get_hyperparameter_search_space(dataset_properties),
+                    )
             # If the node is a choice, we have to figure out which of its
             #  choices are actually legal choices
             else:
@@ -356,7 +357,7 @@ def __repr__(self):
         configuration_string = ''.join(
             ['configuration={\n  ',
              ',\n  '.join(["'%s': %s" % (hp_name, repr(configuration[hp_name]))
-                                         for hp_name in sorted(configuration)]),
+                           for hp_name in sorted(configuration)]),
              '}'])
 
         if len(self.dataset_properties) > 0:
@@ -397,4 +398,3 @@ def get_additional_run_info(self):
         the optimization algorithm.
         """
         return self._additional_run_info
-

autosklearn/pipeline/classification.py

@@ -133,14 +133,11 @@ def predict_proba(self, X, batch_size=None):
                 y = np.zeros((X.shape[0], target.shape[1]),
                              dtype=np.float32)
 
-                for k in range(max(1, int(np.ceil(float(X.shape[0]) /
-                        batch_size)))):
+                for k in range(max(1, int(np.ceil(float(X.shape[0]) / batch_size)))):
                     batch_from = k * batch_size
                     batch_to = min([(k + 1) * batch_size, X.shape[0]])
-                    y[batch_from:batch_to] = \
-                        self.predict_proba(X[batch_from:batch_to],
-                                           batch_size=None).\
-                            astype(np.float32)
+                    pred_prob = self.predict_proba(X[batch_from:batch_to], batch_size=None)
+                    y[batch_from:batch_to] = pred_prob.astype(np.float32)
 
                 return y
 
@@ -161,7 +158,7 @@ def _get_hyperparameter_search_space(self, include=None, exclude=None,
 
         if dataset_properties is None or not isinstance(dataset_properties, dict):
             dataset_properties = dict()
-        if not 'target_type' in dataset_properties:
+        if 'target_type' not in dataset_properties:
             dataset_properties['target_type'] = 'classification'
         if dataset_properties['target_type'] != 'classification':
             dataset_properties['target_type'] = 'classification'
@@ -232,7 +229,7 @@ def _get_hyperparameter_search_space(self, include=None, exclude=None,
                     break
                 except KeyError:
                     break
-                except ValueError as e:
+                except ValueError:
                     # Change the default and try again
                     try:
                         default = possible_default_classifier.pop()

autosklearn/pipeline/components/classification/__init__.py

@@ -1,14 +1,12 @@
 __author__ = 'feurerm'
 
 from collections import OrderedDict
-import copy
 import os
 
 from ..base import AutoSklearnClassificationAlgorithm, find_components, \
     ThirdPartyComponents, AutoSklearnChoice
 from ConfigSpace.configuration_space import ConfigurationSpace
 from ConfigSpace.hyperparameters import CategoricalHyperparameter
-from ConfigSpace.conditions import EqualsCondition
 
 classifier_directory = os.path.split(__file__)[0]
 _classifiers = find_components(__package__,
@@ -61,11 +59,11 @@ def get_available_components(cls, dataset_properties=None,
 
             if entry.get_properties()['handles_classification'] is False:
                 continue
-            if dataset_properties.get('multiclass') is True and entry.get_properties()[
-                'handles_multiclass'] is False:
+            if dataset_properties.get('multiclass') is True and \
+               entry.get_properties()['handles_multiclass'] is False:
                 continue
-            if dataset_properties.get('multilabel') is True and available_comp[name]. \
-                    get_properties()['handles_multilabel'] is False:
+            if dataset_properties.get('multilabel') is True and \
+               available_comp[name].get_properties()['handles_multilabel'] is False:
                 continue
             components_dict[name] = entry
 

autosklearn/pipeline/components/classification/adaboost.py

@@ -3,7 +3,7 @@
     UniformIntegerHyperparameter, CategoricalHyperparameter
 
 from autosklearn.pipeline.components.base import AutoSklearnClassificationAlgorithm
-from autosklearn.pipeline.constants import *
+from autosklearn.pipeline.constants import DENSE, UNSIGNED_DATA, PREDICTIONS, SPARSE
 
 
 class AdaboostClassifier(AutoSklearnClassificationAlgorithm):
@@ -76,4 +76,3 @@ def get_hyperparameter_search_space(dataset_properties=None):
 
         cs.add_hyperparameters([n_estimators, learning_rate, algorithm, max_depth])
         return cs
-

autosklearn/pipeline/components/classification/bernoulli_nb.py

@@ -7,7 +7,7 @@
 from autosklearn.pipeline.components.base import (
     AutoSklearnClassificationAlgorithm,
 )
-from autosklearn.pipeline.constants import *
+from autosklearn.pipeline.constants import DENSE, UNSIGNED_DATA, PREDICTIONS, SPARSE
 from autosklearn.util.common import check_for_bool
 
 
@@ -60,7 +60,7 @@ def get_properties(dataset_properties=None):
     @staticmethod
     def get_hyperparameter_search_space(dataset_properties=None):
         cs = ConfigurationSpace()
-        
+
         # the smoothing parameter is a non-negative float
         # I will limit it to 1000 and put it on a logarithmic scale. (SF)
         # Please adjust that, if you know a proper range, this is just a guess.
@@ -72,5 +72,5 @@ def get_hyperparameter_search_space(dataset_properties=None):
                                               default_value="True")
 
         cs.add_hyperparameters([alpha, fit_prior])
-        
+
         return cs

autosklearn/pipeline/components/classification/decision_tree.py

@@ -7,7 +7,7 @@
 
 from autosklearn.pipeline.components.base import \
     AutoSklearnClassificationAlgorithm
-from autosklearn.pipeline.constants import *
+from autosklearn.pipeline.constants import DENSE, UNSIGNED_DATA, PREDICTIONS, SPARSE
 from autosklearn.pipeline.implementations.util import convert_multioutput_multiclass_to_multilabel
 from autosklearn.util.common import check_none
 

autosklearn/pipeline/components/classification/extra_trees.py

@@ -1,15 +1,12 @@
-import numpy as np
-
 from ConfigSpace.configuration_space import ConfigurationSpace
 from ConfigSpace.hyperparameters import UniformFloatHyperparameter, \
-    UniformIntegerHyperparameter, CategoricalHyperparameter, \
-    UnParametrizedHyperparameter, Constant
+    UniformIntegerHyperparameter, CategoricalHyperparameter, UnParametrizedHyperparameter
 
 from autosklearn.pipeline.components.base import (
     AutoSklearnClassificationAlgorithm,
     IterativeComponentWithSampleWeight,
 )
-from autosklearn.pipeline.constants import *
+from autosklearn.pipeline.constants import DENSE, UNSIGNED_DATA, PREDICTIONS, SPARSE
 from autosklearn.pipeline.implementations.util import convert_multioutput_multiclass_to_multilabel
 from autosklearn.util.common import check_for_bool, check_none
 

autosklearn/pipeline/components/classification/gaussian_nb.py

@@ -5,7 +5,7 @@
 from autosklearn.pipeline.components.base import (
     AutoSklearnClassificationAlgorithm,
 )
-from autosklearn.pipeline.constants import *
+from autosklearn.pipeline.constants import DENSE, UNSIGNED_DATA, PREDICTIONS
 
 
 class GaussianNB(AutoSklearnClassificationAlgorithm):
@@ -57,4 +57,3 @@ def get_properties(dataset_properties=None):
     def get_hyperparameter_search_space(dataset_properties=None):
         cs = ConfigurationSpace()
         return cs
-

autosklearn/pipeline/components/classification/gradient_boosting.py

@@ -10,7 +10,7 @@
     AutoSklearnClassificationAlgorithm,
     IterativeComponent,
 )
-from autosklearn.pipeline.constants import *
+from autosklearn.pipeline.constants import DENSE, UNSIGNED_DATA, PREDICTIONS
 from autosklearn.util.common import check_none
 
 
@@ -121,7 +121,9 @@ def iterative_fit(self, X, y, n_iter=2, refit=False):
 
         self.estimator.fit(X, y)
 
-        if self.estimator.max_iter >= self.max_iter or self.estimator.max_iter > self.estimator.n_iter_:
+        if self.estimator.max_iter >= self.max_iter \
+           or self.estimator.max_iter > self.estimator.n_iter_:
+
             self.fully_fit_ = True
 
         return self
@@ -195,4 +197,3 @@ def get_hyperparameter_search_space(dataset_properties=None):
         cs.add_conditions([n_iter_no_change_cond, validation_fraction_cond])
 
         return cs
-

autosklearn/pipeline/components/classification/k_nearest_neighbors.py

@@ -1,9 +1,8 @@
 from ConfigSpace.configuration_space import ConfigurationSpace
-from ConfigSpace.hyperparameters import CategoricalHyperparameter, \
-    Constant, UniformIntegerHyperparameter
+from ConfigSpace.hyperparameters import CategoricalHyperparameter, UniformIntegerHyperparameter
 
 from autosklearn.pipeline.components.base import AutoSklearnClassificationAlgorithm
-from autosklearn.pipeline.constants import *
+from autosklearn.pipeline.constants import DENSE, UNSIGNED_DATA, PREDICTIONS, SPARSE
 
 
 class KNearestNeighborsClassifier(AutoSklearnClassificationAlgorithm):