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

tests/test_anonymizer.py

@@ -1,5 +1,8 @@
 import pytest
 import numpy as np
+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
 
@@ -19,7 +22,7 @@ def test_anonymize_ndarray_iris():
 
     k = 10
     QI = [0, 2]
-    anonymizer = Anonymize(k, QI)
+    anonymizer = Anonymize(k, QI, train_only_QI=True)
     anon = anonymizer.anonymize(ArrayDataset(x_train, pred))
     assert(len(np.unique(anon[:, QI], axis=0)) < len(np.unique(x_train[:, QI], axis=0)))
     _, counts_elements = np.unique(anon[:, QI], return_counts=True)
@@ -29,18 +32,31 @@ def test_anonymize_ndarray_iris():
 
 def test_anonymize_pandas_adult():
     (x_train, y_train), _ = get_adult_dataset()
-    encoded = OneHotEncoder().fit_transform(x_train)
-    model = DecisionTreeClassifier()
-    model.fit(encoded, y_train)
-    pred = model.predict(encoded)
 
     k = 100
-    features = ['age', 'workclass', 'education-num', 'marital-status', 'occupation', 'relationship', 'race', 'sex',
-                'capital-gain', 'capital-loss', 'hours-per-week', 'native-country']
+    features = ['age', 'workclass', 'education-num', 'marital-status', 'occupation',
+                'relationship', 'race', 'sex', 'capital-gain', 'capital-loss', 'hours-per-week', 'native-country']
     QI = ['age', 'workclass', 'education-num', 'marital-status', 'occupation', 'relationship', 'race', 'sex',
           'native-country']
     categorical_features = ['workclass', 'marital-status', 'occupation', 'relationship', 'race', 'sex',
                             'native-country']
+    # prepare data for DT
+    numeric_features = [f for f in features if f not in categorical_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_train)
+    model = DecisionTreeClassifier()
+    model.fit(encoded, y_train)
+    pred = model.predict(encoded)
+
     anonymizer = Anonymize(k, QI, categorical_features=categorical_features)
     anon = anonymizer.anonymize(ArrayDataset(x_train, pred, features))
 
@@ -50,17 +66,30 @@ def test_anonymize_pandas_adult():
 
 def test_anonymize_pandas_nursery():
     (x_train, y_train), _ = get_nursery_dataset()
-    features = ["parents", "has_nurs", "form", "children", "housing", "finance", "social", "health"]
     x_train = x_train.astype(str)
-    encoded = OneHotEncoder().fit_transform(x_train)
+
+    k = 100
+    features = ["parents", "has_nurs", "form", "children", "housing", "finance", "social", "health"]
+    QI = ["finance", "social", "health"]
+    categorical_features = ["parents", "has_nurs", "form", "housing", "finance", "social", "health", 'children']
+    # prepare data for DT
+    numeric_features = [f for f in features if f not in categorical_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_train)
     model = DecisionTreeClassifier()
     model.fit(encoded, y_train)
     pred = model.predict(encoded)
 
-    k = 100
-    QI = ["finance", "social", "health"]
-    categorical_features = ["parents", "has_nurs", "form", "housing", "finance", "social", "health", 'children']
-    anonymizer = Anonymize(k, QI, categorical_features=categorical_features)
+    anonymizer = Anonymize(k, QI, categorical_features=categorical_features, train_only_QI=True)
     anon = anonymizer.anonymize(ArrayDataset(x_train, pred))
 
     assert(anon.loc[:, QI].drop_duplicates().shape[0] < x_train.loc[:, QI].drop_duplicates().shape[0])
@@ -78,7 +107,7 @@ def test_regression():
     pred = model.predict(x_train)
     k = 10
     QI = [0, 2, 5, 8]
-    anonymizer = Anonymize(k, QI, is_regression=True)
+    anonymizer = Anonymize(k, QI, is_regression=True, train_only_QI=True)
     anon = anonymizer.anonymize(ArrayDataset(x_train, pred))
     print('Base model accuracy (R2 score): ', model.score(x_test, y_test))
     model.fit(anon, y_train)