Squashed commit of the following:

commit d53818644e
Author: olasaadi <92303887+olasaadi@users.noreply.github.com>
Date:   Mon Mar 7 20:12:55 2022 +0200

    Build the dt on all features anon (#23)

    * add param to build the DT on all features and not just on QI
    * one-hot encoding only for categorical features

commit c47819a031
Author: abigailt <abigailt@il.ibm.com>
Date:   Wed Feb 23 19:40:11 2022 +0200

    Update docs

commit 7e2ce7fe96
Merge: 7fbd1e4 752871d
Author: abigailt <abigailt@il.ibm.com>
Date:   Wed Feb 23 19:26:44 2022 +0200

    Merge remote-tracking branch 'origin/main' into main

commit 7fbd1e4b90
Author: abigailt <abigailt@il.ibm.com>
Date:   Wed Feb 23 19:22:54 2022 +0200

    Update version and docs

commit 752871dd0c
Author: olasaadi <92303887+olasaadi@users.noreply.github.com>
Date:   Wed Feb 23 14:57:12 2022 +0200

    add minimization notebook (#22)

    * add german credit notebook to showcase new features (minimize only some features and categorical features)

    * add notebook to show minimization data on a regression problem

apt/anonymization/anonymizer.py

@@ -3,6 +3,9 @@ import pandas as pd
 from scipy.spatial import distance
 from collections import Counter
 
+from sklearn.compose import ColumnTransformer
+from sklearn.impute import SimpleImputer
+from sklearn.pipeline import Pipeline
 from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
 from sklearn.preprocessing import OneHotEncoder
 from apt.utils.datasets import ArrayDataset, DATA_PANDAS_NUMPY_TYPE
@@ -15,28 +18,38 @@ class Anonymize:
     Class for performing tailored, model-guided anonymization of training datasets for ML models.
 
     Based on the implementation described in: https://arxiv.org/abs/2007.13086
+    Parameters
+    ----------
+    k : int
+        The privacy parameter that determines the number of records that will be indistinguishable from each
+        other (when looking at the quasi identifiers). Should be at least 2.
+    quasi_identifiers : np.ndarray or list
+        The features that need to be minimized in case of pandas data, and indexes of features
+        in case of numpy data.
+    categorical_features : list, optional
+        The list of categorical features (should only be supplied when passing data as a
+        pandas dataframe.
+    is_regression : Bool, optional
+        Whether the model is a regression model or not (if False, assumes
+        a classification model). Default is False.
+    train_only_QI : Bool, optional
+        The required method to train data set for anonymization. Default is
+        to train the tree on all features.
     """
 
     def __init__(self, k: int, quasi_identifiers: Union[np.ndarray, list], categorical_features: Optional[list] = None,
-                 is_regression=False):
-        """
-        :param k: The privacy parameter that determines the number of records that will be indistinguishable from each
-                  other (when looking at the quasi identifiers). Should be at least 2.
-        :param quasi_identifiers: The features that need to be minimized. It can be a list of feature names (strings) if
-                  dataset.feature_names is set, otherwise a list of indexes (integers).
-        :param categorical_features: The list of categorical features. It can be a list of feature names (strings) if
-                  dataset.feature_names is set, otherwise a list of indexes (integers).
-        :param is_regression: Boolean param indicates that is is a regression problem.
-        """
+                 is_regression=False, train_only_QI=False):
         if k < 2:
             raise ValueError("k should be a positive integer with a value of 2 or higher")
         if quasi_identifiers is None or len(quasi_identifiers) < 1:
             raise ValueError("The list of quasi-identifiers cannot be empty")
+
         self.k = k
         self.quasi_identifiers = quasi_identifiers
         self.categorical_features = categorical_features
         self.is_regression = is_regression
         self.features_names = None
+        self.train_only_QI = train_only_QI
 
     def anonymize(self, dataset: ArrayDataset) -> DATA_PANDAS_NUMPY_TYPE:
         """
@@ -72,7 +85,10 @@ class Anonymize:
     def _anonymize(self, x, y):
         if x.shape[0] != y.shape[0]:
             raise ValueError("x and y should have same number of rows")
-        x_anonymizer_train = x[:, self.quasi_identifiers]
+        x_anonymizer_train = x
+        if self.train_only_QI:
+            # build DT just on QI features
+            x_anonymizer_train = x[:, self.quasi_identifiers]
         if x.dtype.kind not in 'iufc':
             if not self.categorical_features:
                 raise ValueError('when supplying an array with non-numeric data, categorical_features must be defined')
@@ -151,6 +167,21 @@ class Anonymize:
         return x
 
     def _modify_categorical_features(self, x):
-        encoder = OneHotEncoder()
-        one_hot_encoded = encoder.fit_transform(x)
-        return one_hot_encoded
+        # prepare data for DT
+        used_features = self.features
+        if self.train_only_QI:
+            used_features = self.quasi_identifiers
+        numeric_features = [f for f in x.columns if f in used_features and f not in self.categorical_features]
+        categorical_features = [f for f in self.categorical_features if f in used_features]
+        numeric_transformer = Pipeline(
+            steps=[('imputer', SimpleImputer(strategy='constant', fill_value=0))]
+        )
+        categorical_transformer = OneHotEncoder(handle_unknown="ignore", sparse=False)
+        preprocessor = ColumnTransformer(
+            transformers=[
+                ("num", numeric_transformer, numeric_features),
+                ("cat", categorical_transformer, categorical_features),
+            ]
+        )
+        encoded = preprocessor.fit_transform(x)
+        return encoded