Example for preprocessing.dictmapper.DictMapper and meta.outlier_classifier.OutlierClassifier

sklego/meta/outlier_classifier.py

@@ -23,6 +23,30 @@ class OutlierClassifier(BaseEstimator, ClassifierMixin):
         The fitted underlying outlier detection model.
     classes_ : array-like of shape (2,)
         Classes used for prediction (0 or 1)
+
+    Example
+    -------
+    ```py
+    from sklearn.ensemble import IsolationForest
+    from sklego.meta.outlier_classifier import OutlierClassifier
+
+    X = [[0], [0.5], [-1], [99]]
+    y = [0, 0, 0, 1]
+
+    isolation_forest = IsolationForest()
+
+    outlier_clf = OutlierClassifier(isolation_forest)
+    _ = outlier_clf.fit(X, y)
+
+    preds = outlier_clf.predict([[100], [-0.5], [0.5], [1]])
+    # array[1. 0. 0. 0.]
+
+    proba_preds = outlier_clf.predict_proba([[100], [-0.5], [0.5], [1]])
+    # [[0.34946567 0.65053433]
+    #  [0.79707913 0.20292087]
+    #  [0.80275406 0.19724594]
+    #  [0.80275406 0.19724594]]
+    ```
     """
 
     def __init__(self, model):
@@ -52,33 +76,6 @@ def fit(self, X, y=None):
         ValueError
             - If the underlying model is not an outlier detection model.
             - If the underlying model does not have a `decision_function` method.
-
-        Example
-        -------
-        ```py
-        from sklearn.ensemble import IsolationForest
-        from sklego.meta.outlier_classifier import OutlierClassifier
-
-        X = [[0], [0.5], [-1], [99]]
-        y = [[0], [0], [0], [1]]
-
-        isolation_forest = IsolationForest()
-        isolation_forest.fit(X)
-        detector_preds = isolation_forest.predict(X)
-        # array[ 1  1  1 -1]
-
-        outlier_clf = OutlierClassifier(isolation_forest)
-        _ = outlier_clf.fit(X, y)
-
-        preds = outlier_clf.predict([[100], [-0.5], [0.5], [1]])
-        # array[1. 0. 0. 0.]
-
-        proba_preds = outlier_clf.predict_proba([[100], [-0.5], [0.5], [1]])
-        # [[0.34946567 0.65053433]
-        #  [0.79707913 0.20292087]
-        #  [0.80275406 0.19724594]
-        #  [0.80275406 0.19724594]]
-        ```
         """
         X, y = check_X_y(X, y, estimator=self)
         if not self._is_outlier_model():

sklego/model_selection.py

@@ -260,7 +260,7 @@ def KlusterFoldValidation(**kwargs):
 class ClusterFoldValidation:
     """Cross validator that creates folds based on provided cluster method.
     This ensures that data points in the same cluster are not split across different folds.
-    
+
     !!! info "New in version 0.9.0"
 
     Parameters

sklego/preprocessing/dictmapper.py

@@ -23,6 +23,34 @@ class DictMapper(TransformerMixin, BaseEstimator):
         Number of features seen during `fit`.
     dim_ : int
         Deprecated, please use `n_features_in_` instead.
+
+    Example
+    -------
+    ```py
+    import pandas as pd
+    from sklego.preprocessing.dictmapper import DictMapper
+    from sklearn.compose import ColumnTransformer
+
+    X = pd.DataFrame({
+        "city_pop": ["Amsterdam", "Leiden", "Utrecht", "None", "Haarlem"]
+    })
+
+    mapper = {
+    "Amsterdam": 1_181_817,
+    "Leiden": 130_181,
+    "Utrecht": 367_984,
+    "Haarlem": 165_396,
+    }
+
+    ct = ColumnTransformer([("dictmapper", DictMapper(mapper, 0), ["city_pop"])])
+    X_trans = ct.fit_transform(X)
+    X_trans
+    # array([[1181817],
+    #        [ 130181],
+    #        [ 367984],
+    #        [      0],
+    #        [ 165396]])
+    ```
     """
 
     def __init__(self, mapper, default):
@@ -43,41 +71,6 @@ def fit(self, X, y=None):
         -------
         self : DictMapper
             The fitted transformer.
-
-        Example
-        -------
-        ```py
-        import pandas as pd
-        from sklego.preprocessing.dictmapper import DictMapper
-
-        X = pd.DataFrame({
-            "city": ["Amsterdam", "Leiden", "Utrecht", "Amsterdam", "Haarlem"],
-            "university": ["uva", "lei", "uu", "vu", "none"]
-        })
-
-        mapper = {
-
-            #population
-
-            "Amsterdam": 1_181_817,
-            "Leiden": 130_181,
-            "Utrecht": 367_984,
-            "Haarlem": 165_396,
-
-            #ranking
-
-            "uva": 64,
-            "lei": 214,
-            "uu": 117,
-            "vu": 105
-        }
-
-        dict_mapper = DictMapper(mapper, 0)
-        _ = dict_mapper.fit(X)
-
-        dict_mapper.n_features_in_
-        # 2
-        ```
         """
         X = check_array(
             X,
@@ -107,47 +100,6 @@ def transform(self, X):
         ------
         ValueError
             If the number of columns from `X` differs from the number of columns when fitting.
-
-        Example
-        -------
-        ```py
-        import pandas as pd
-        from sklego.preprocessing.dictmapper import DictMapper
-
-        X = pd.DataFrame({
-            "city": ["Amsterdam", "Leiden", "Utrecht", "Amsterdam", "Haarlem"],
-            "university": ["uva", "lei", "uu", "vu", "none"]
-        })
-
-        mapper = {
-
-            #population
-
-            "Amsterdam": 1_181_817,
-            "Leiden": 130_181,
-            "Utrecht": 367_984,
-            "Haarlem": 165_396,
-
-            #ranking
-
-            "uva": 64,
-            "lei": 214,
-            "uu": 117,
-            "vu": 105
-        }
-
-        dict_mapper = DictMapper(mapper, 0)
-        _ = dict_mapper.fit(X)
-
-        X_trans = dict_mapper.transform(X)
-        X_trans
-        # array([[1181817,      64],
-        #        [ 130181,     214],
-        #        [ 367984,     117],
-        #        [1181817,     105],
-        #        [ 165396,       0]])
-
-        ```
         """
         check_is_fitted(self, ["n_features_in_"])
         X = check_array(