Formatting (#68)

Fix most flake/lint errors and ignore a few others

Signed-off-by: abigailt <abigailt@il.ibm.com>

apt/__init__.py

@@ -6,4 +6,4 @@ from apt import anonymization
 from apt import minimization
 from apt import utils
 
-__version__ = "0.1.0"
+__version__ = "0.1.0"

apt/anonymization/anonymizer.py

@@ -68,7 +68,7 @@ class Anonymize:
 
         if dataset.features_names is not None:
             self.features_names = dataset.features_names
-        else: # if no names provided, use numbers instead
+        else:  # if no names provided, use numbers instead
             self.features_names = self.features
 
         if not set(self.quasi_identifiers).issubset(set(self.features_names)):

apt/minimization/minimizer.py

@@ -16,7 +16,7 @@ from sklearn.utils.validation import check_is_fitted
 from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
 from sklearn.model_selection import train_test_split
 
-from apt.utils.datasets import ArrayDataset, Data, DATA_PANDAS_NUMPY_TYPE
+from apt.utils.datasets import ArrayDataset, DATA_PANDAS_NUMPY_TYPE
 from apt.utils.models import Model, SklearnRegressor, ModelOutputType, SklearnClassifier
 
 
@@ -268,14 +268,14 @@ class GeneralizeToRepresentative(BaseEstimator, MetaEstimatorMixin, TransformerM
             if self.encoder is None:
                 numeric_features = [f for f in self._features if f not in self.categorical_features]
                 numeric_transformer = Pipeline(
-                        steps=[('imputer', SimpleImputer(strategy='constant', fill_value=0))]
+                    steps=[('imputer', SimpleImputer(strategy='constant', fill_value=0))]
                 )
                 categorical_transformer = OneHotEncoder(handle_unknown="ignore", sparse=False)
                 self.encoder = ColumnTransformer(
-                        transformers=[
-                            ("num", numeric_transformer, numeric_features),
-                            ("cat", categorical_transformer, self.categorical_features),
-                        ]
+                    transformers=[
+                        ("num", numeric_transformer, numeric_features),
+                        ("cat", categorical_transformer, self.categorical_features),
+                    ]
                 )
                 self.encoder.fit(x)
 
@@ -345,7 +345,6 @@ class GeneralizeToRepresentative(BaseEstimator, MetaEstimatorMixin, TransformerM
                         print('Pruned tree to level: %d, new relative accuracy: %f' % (level, accuracy))
                         level += 1
 
-
             # if accuracy below threshold, improve accuracy by removing features from generalization
             elif accuracy < self.target_accuracy:
                 print('Improving accuracy')
@@ -599,8 +598,8 @@ class GeneralizeToRepresentative(BaseEstimator, MetaEstimatorMixin, TransformerM
                             new_cell['ranges'][feature]['end'] = right_cell['ranges'][feature]['start']
                         for feature in left_cell['categories'].keys():
                             new_cell['categories'][feature] = \
-                                list(set(left_cell['categories'][feature]) |
-                                     set(right_cell['categories'][feature]))
+                                list(set(left_cell['categories'][feature])
+                                     | set(right_cell['categories'][feature]))
                         for feature in left_cell['untouched']:
                             if feature in right_cell['untouched']:
                                 new_cell['untouched'].append(feature)
@@ -707,8 +706,8 @@ class GeneralizeToRepresentative(BaseEstimator, MetaEstimatorMixin, TransformerM
             for feature in self._features:
                 # if feature has a representative value in the cell and should not be left untouched,
                 # take the representative value
-                if feature in cells[i]['representative'] and ('untouched' not in cells[i] or
-                                                              feature not in cells[i]['untouched']):
+                if feature in cells[i]['representative'] \
+                        and ('untouched' not in cells[i] or feature not in cells[i]['untouched']):
                     representatives.loc[i, feature] = cells[i]['representative'][feature]
                 # else, drop the feature (removes from representatives columns that do not have a
                 # representative value or should remain untouched)

apt/utils/dataset_utils.py

@@ -24,7 +24,7 @@ def _load_iris(test_set_size: float = 0.3):
 
     # Split training and test sets
     x_train, x_test, y_train, y_test = model_selection.train_test_split(data, labels, test_size=test_set_size,
-                                                                                random_state=18, stratify=labels)
+                                                                        random_state=18, stratify=labels)
 
     return (x_train, y_train), (x_test, y_test)
 
@@ -94,9 +94,6 @@ def get_german_credit_dataset_pd(test_set: float = 0.3):
     x_test = test.drop(["label"], axis=1)
     y_test = test.loc[:, "label"]
 
-    categorical_features = ["Existing_checking_account", "Credit_history", "Purpose", "Savings_account",
-                            "Present_employment_since", "Personal_status_sex", "debtors", "Property",
-                            "Other_installment_plans", "Housing", "Job"]
     x_train.reset_index(drop=True, inplace=True)
     y_train.reset_index(drop=True, inplace=True)
     x_test.reset_index(drop=True, inplace=True)

apt/utils/models/keras_model.py

@@ -1,11 +1,9 @@
 from typing import Optional
 
 import numpy as np
-from sklearn.preprocessing import OneHotEncoder
 
 import tensorflow as tf
 from tensorflow import keras
-tf.compat.v1.disable_eager_execution()
 
 from sklearn.metrics import mean_squared_error
 
@@ -16,6 +14,8 @@ from art.utils import check_and_transform_label_format
 from art.estimators.classification.keras import KerasClassifier as ArtKerasClassifier
 from art.estimators.regression.keras import KerasRegressor as ArtKerasRegressor
 
+tf.compat.v1.disable_eager_execution()
+
 
 class KerasModel(Model):
     """
@@ -23,7 +23,6 @@ class KerasModel(Model):
     """
 
 
-
 class KerasClassifier(KerasModel):
     """
     Wrapper class for keras classification models.

apt/utils/models/model.py

@@ -1,5 +1,5 @@
 from abc import ABCMeta, abstractmethod
-from typing import Any, Optional, Callable, Tuple, Union
+from typing import Any, Optional, Callable, Tuple, Union, TYPE_CHECKING
 from enum import Enum, auto
 import numpy as np
 
@@ -7,6 +7,9 @@ from apt.utils.datasets import Dataset, Data, OUTPUT_DATA_ARRAY_TYPE
 from art.estimators.classification import BlackBoxClassifier
 from art.utils import check_and_transform_label_format
 
+if TYPE_CHECKING:
+    import torch
+
 
 class ModelOutputType(Enum):
     CLASSIFIER_PROBABILITIES = auto()  # vector of probabilities

apt/utils/models/pytorch_model.py

@@ -8,7 +8,7 @@ import numpy as np
 import torch
 from torch.utils.data import DataLoader, TensorDataset
 
-from art.utils import check_and_transform_label_format, logger
+from art.utils import check_and_transform_label_format
 from apt.utils.datasets.datasets import PytorchData
 from apt.utils.models import Model, ModelOutputType
 from apt.utils.datasets import OUTPUT_DATA_ARRAY_TYPE

apt/utils/models/sklearn_model.py

@@ -1,6 +1,5 @@
 from typing import Optional
 
-from sklearn.preprocessing import OneHotEncoder
 from sklearn.base import BaseEstimator
 
 from apt.utils.models import Model, ModelOutputType, get_nb_classes, check_correct_model_output

apt/utils/models/xgboost_model.py

@@ -38,7 +38,7 @@ class XGBoostClassifier(XGBoostModel):
     :type unlimited_queries: boolean, optional
     """
     def __init__(self, model: XGBClassifier, output_type: ModelOutputType, input_shape: Tuple[int, ...],
-                 nb_classes: int,black_box_access: Optional[bool] = True,
+                 nb_classes: int, black_box_access: Optional[bool] = True,
                  unlimited_queries: Optional[bool] = True, **kwargs):
         super().__init__(model, output_type, black_box_access, unlimited_queries, **kwargs)
         self._art_model = ArtXGBoostClassifier(model, nb_features=input_shape[0], nb_classes=nb_classes)