Merge branch 'master' into hotfix/report_demo

requirements.dev.txt

@@ -25,7 +25,7 @@ nbsphinx==0.8.8
 sphinx_material==0.0.35
 pytest>=6.2.5
 pytest-cov>=2.8.1
-scikit-learn>=1.0.1,<1.4
+scikit-learn>=1.4.0
 xgboost>=1.0.0
 nbformat>4.2.0
 numba>=0.53.1

setup.py

@@ -32,7 +32,7 @@
     "dash-table>=5.0.0",
     "nbformat>4.2.0",
     "numba>=0.53.1",
-    "scikit-learn>=1.0.1,<1.4",
+    "scikit-learn>=1.4.0",
     "category_encoders>=2.6.0",
     "scipy>=0.19.1",
 ]

shapash/explainer/smart_explainer.py

@@ -240,7 +240,14 @@ def __init__(
         self.features_imp = None
 
     def compile(
-        self, x, contributions=None, y_pred=None, y_target=None, additional_data=None, additional_features_dict=None
+        self,
+        x,
+        contributions=None,
+        y_pred=None,
+        proba_values=None,
+        y_target=None,
+        additional_data=None,
+        additional_features_dict=None,
     ):
         """
         The compile method is the first step to understand model and
@@ -266,6 +273,11 @@ def compile(
             This is an interesting parameter for more explicit outputs.
             Shapash lets users define their own predict,
             as they may wish to set their own threshold (classification)
+        proba_values : pandas.Series or pandas.DataFrame, optional (default: None)
+            Probability values (1 column only).
+            The index must be identical to the index of x_init.
+            This is an interesting parameter for more explicit outputs.
+            Shapash lets users define their own probability values
         y_target : pandas.Series or pandas.DataFrame, optional (default: None)
             Target values (1 column only).
             The index must be identical to the index of x_init.
@@ -291,6 +303,13 @@ def compile(
         x_init = inverse_transform(self.x_encoded, self.preprocessing)
         self.x_init = handle_categorical_missing(x_init)
         self.y_pred = check_y(self.x_init, y_pred, y_name="y_pred")
+        if (self.y_pred is None) and (hasattr(self.model, "predict")):
+            self.predict()
+
+        self.proba_values = check_y(self.x_init, proba_values, y_name="proba_values")
+        if (self._case == "classification") and (self.proba_values is None) and (hasattr(self.model, "predict_proba")):
+            self.predict_proba()
+
         self.y_target = check_y(self.x_init, y_target, y_name="y_target")
         self.prediction_error = predict_error(self.y_target, self.y_pred, self._case)
 
@@ -405,6 +424,7 @@ def define_style(self, palette_name=None, colors_dict=None):
     def add(
         self,
         y_pred=None,
+        proba_values=None,
         y_target=None,
         label_dict=None,
         features_dict=None,
@@ -423,6 +443,9 @@ def add(
         y_pred : pandas.Series, optional (default: None)
             Prediction values (1 column only).
             The index must be identical to the index of x_init.
+        proba_values : pandas.Series, optional (default: None)
+            Probability values (1 column only).
+            The index must be identical to the index of x_init.
         label_dict: dict, optional (default: None)
             Dictionary mapping integer labels to domain names.
         features_dict: dict, optional (default: None)
@@ -446,6 +469,8 @@ def add(
             self.y_pred = check_y(self.x_init, y_pred, y_name="y_pred")
             if hasattr(self, "y_target"):
                 self.prediction_error = predict_error(self.y_target, self.y_pred, self._case)
+        if proba_values is not None:
+            self.proba_values = check_y(self.x_init, proba_values, y_name="proba_values")
         if y_target is not None:
             self.y_target = check_y(self.x_init, y_target, y_name="y_target")
             if hasattr(self, "y_pred"):
@@ -895,7 +920,7 @@ def to_pandas(
         )
         # Matching with y_pred
         if proba:
-            self.predict_proba() if proba else None
+            self.predict_proba()
             proba_values = self.proba_values
         else:
             proba_values = None
@@ -1006,8 +1031,6 @@ def init_app(self, settings: dict = None):
             Possible settings (dict keys) are 'rows', 'points', 'violin', 'features'
             Values should be positive ints
         """
-        if self.y_pred is None:
-            self.predict()
         self.smartapp = SmartApp(self, settings)
 
     def run_app(
@@ -1046,8 +1069,6 @@ def run_app(
 
         if title_story is not None:
             self.title_story = title_story
-        if self.y_pred is None:
-            self.predict()
         if hasattr(self, "_case"):
             self.smartapp = SmartApp(self, settings)
             if host is None:

shapash/explainer/smart_plotter.py

@@ -949,9 +949,7 @@ def local_pred(self, index, label=None):
         float: Predict or predict_proba value
         """
         if self.explainer._case == "classification":
-            if hasattr(self.explainer.model, "predict_proba"):
-                if not hasattr(self.explainer, "proba_values"):
-                    self.explainer.predict_proba()
+            if self.explainer.proba_values is not None:
                 value = self.explainer.proba_values.iloc[:, [label]].loc[index].values[0]
             else:
                 value = None
@@ -1237,9 +1235,7 @@ def contribution_plot(
                 col_value = self.explainer._classes[label_num]
             subtitle = f"Response: <b>{label_value}</b>"
             # predict proba Color scale
-            if proba and hasattr(self.explainer.model, "predict_proba"):
-                if not hasattr(self.explainer, "proba_values"):
-                    self.explainer.predict_proba()
+            if proba and self.explainer.proba_values is not None:
                 proba_values = self.explainer.proba_values.iloc[:, [label_num]]
                 if not hasattr(self, "pred_colorscale"):
                     self.pred_colorscale = {}
@@ -3209,12 +3205,7 @@ def _prediction_classification_plot(
 
         label_num, _, label_value = self.explainer.check_label_name(label)
         # predict proba Color scale
-        if hasattr(self.explainer.model, "predict_proba"):
-            if not hasattr(self.explainer, "proba_values"):
-                self.explainer.predict_proba()
-            if hasattr(self.explainer.model, "predict"):
-                if not hasattr(self.explainer, "y_pred") or self.explainer.y_pred is None:
-                    self.explainer.predict()
+        if self.explainer.proba_values is not None:
             # Assign proba values of the target
             df_proba_target = self.explainer.proba_values.copy()
             df_proba_target["proba_target"] = df_proba_target.iloc[:, label_num]
@@ -3333,9 +3324,6 @@ def _prediction_regression_plot(
         fig = go.Figure()
 
         subtitle = None
-        if self.explainer.y_pred is None:
-            if hasattr(self.explainer.model, "predict"):
-                self.explainer.predict()
         prediction_error = self.explainer.prediction_error
         if prediction_error is not None:
             if (self.explainer.y_target == 0).any()[0]:

shapash/utils/columntransformer_backend.py

@@ -4,6 +4,7 @@
 
 import numpy as np
 import pandas as pd
+from sklearn.preprocessing import FunctionTransformer
 
 from shapash.utils.category_encoder_backend import (
     category_encoder_binary,
@@ -91,7 +92,7 @@ def inv_transform_ct(x_in, encoding):
 
             # columns not encode
             elif name_encoding == "remainder":
-                if ct_encoding == "passthrough":
+                if isinstance(ct_encoding, FunctionTransformer):
                     nb_col = len(col_encoding)
                     frame = x_in.iloc[:, init : init + nb_col]
                 else:
@@ -249,7 +250,7 @@ def calc_inv_contrib_ct(x_contrib, encoding, agg_columns):
                     init += nb_col
 
             elif name_encoding == "remainder":
-                if ct_encoding == "passthrough":
+                if isinstance(ct_encoding, FunctionTransformer):
                     nb_col = len(col_encoding)
                     frame = x_contrib.iloc[:, init : init + nb_col]
                     rst = pd.concat([rst, frame], axis=1)
@@ -366,7 +367,9 @@ def get_feature_names(column_transformer):
         List of returned features names when ColumnTransformer is applied.
     """
     feature_names = []
-    l_transformers = list(column_transformer._iter(fitted=True))
+    l_transformers = list(
+        column_transformer._iter(fitted=True, column_as_labels=False, skip_drop=True, skip_empty_columns=True)
+    )
 
     for name, trans, column, _ in l_transformers:
         feature_names.extend(get_names(name, trans, column, column_transformer))
@@ -463,11 +466,8 @@ def get_col_mapping_ct(encoder, x_encoded):
             else:
                 raise NotImplementedError(f"Estimator not supported : {estimator}")
 
-        elif estimator == "passthrough":
-            try:
-                features_out = encoder.feature_names_in_[features]
-            except Exception:
-                features_out = encoder._feature_names_in[features]  # for oldest sklearn version
+        elif isinstance(estimator, FunctionTransformer):
+            features_out = encoder.feature_names_in_[features]
             for f_name in features_out:
                 dict_col_mapping[f_name] = [x_encoded.columns.to_list()[idx_encoded]]
                 idx_encoded += 1

shapash/utils/transform.py

@@ -1,10 +1,12 @@
 """
 Transform Module
 """
+
 import re
 
 import numpy as np
 import pandas as pd
+from sklearn.preprocessing import FunctionTransformer
 
 from shapash.utils.category_encoder_backend import (
     get_col_mapping_ce,
@@ -185,7 +187,7 @@ def check_transformers(list_encoding):
                 if (str(type(ct_encoding)) not in supported_sklearn) and (
                     str(type(ct_encoding)) not in supported_category_encoder
                 ):
-                    if str(type(ct_encoding)) != "<class 'str'>":
+                    if not isinstance(ct_encoding, str) and not isinstance(ct_encoding, FunctionTransformer):
                         raise ValueError("One of the encoders used in ColumnTransformers isn't supported.")
 
         elif str(type(enc)) in supported_category_encoder:

tests/unit_tests/explainer/test_smart_plotter.py

@@ -108,6 +108,7 @@ def setUp(self):
         self.smart_explainer._case, self.smart_explainer._classes = check_model(model)
         self.smart_explainer.state = MultiDecorator(SmartState())
         self.smart_explainer.y_pred = None
+        self.smart_explainer.proba_values = None
         self.smart_explainer.features_desc = dict(self.x_init.nunique())
         self.smart_explainer.features_compacity = self.features_compacity
 
@@ -863,7 +864,7 @@ def test_contribution_plot_8(self):
         xpl.model = model
         np_hv = [f"Id: {x}<br />Predict: {y}" for x, y in zip(xpl.x_init.index, xpl.y_pred.iloc[:, 0].tolist())]
         np_hv.sort()
-        output = xpl.plot.contribution_plot(col)
+        output = xpl.plot.contribution_plot(col, proba=False)
         annot_list = []
         for data_plot in output.data:
             annot_list.extend(data_plot.hovertext.tolist())
@@ -895,7 +896,7 @@ def test_contribution_plot_9(self):
         model = lambda: None
         model.classes_ = np.array([0, 1])
         xpl.model = model
-        output = xpl.plot.contribution_plot(col, max_points=39)
+        output = xpl.plot.contribution_plot(col, max_points=39, proba=False)
         assert len(output.data) == 4
         for elem in output.data:
             assert elem.type == "violin"
@@ -1266,6 +1267,9 @@ def test_features_importance_4(self):
 
     def test_local_pred_1(self):
         xpl = self.smart_explainer
+        xpl.proba_values = pd.DataFrame(
+            data=np.array([[0.4, 0.6], [0.3, 0.7]]), columns=["class_1", "class_2"], index=xpl.x_encoded.index.values
+        )
         output = xpl.plot.local_pred("person_A", label=0)
         assert isinstance(output, float)
 

tests/unit_tests/utils/test_columntransformer_backend.py

@@ -1,6 +1,7 @@
 """
 Unit test of Inverse Transform
 """
+
 import unittest
 
 import catboost as cb
@@ -959,25 +960,25 @@ def test_get_names_1(self):
         enc_4.fit(train)
 
         feature_names_1 = []
-        l_transformers = list(enc_1._iter(fitted=True))
+        l_transformers = list(enc_1._iter(fitted=True, column_as_labels=False, skip_drop=True, skip_empty_columns=True))
 
         for name, trans, column, _ in l_transformers:
             feature_names_1.extend(get_names(name, trans, column, enc_1))
 
         feature_names_2 = []
-        l_transformers = list(enc_2._iter(fitted=True))
+        l_transformers = list(enc_2._iter(fitted=True, column_as_labels=False, skip_drop=True, skip_empty_columns=True))
 
         for name, trans, column, _ in l_transformers:
             feature_names_2.extend(get_names(name, trans, column, enc_2))
 
         feature_names_3 = []
-        l_transformers = list(enc_3._iter(fitted=True))
+        l_transformers = list(enc_3._iter(fitted=True, column_as_labels=False, skip_drop=True, skip_empty_columns=True))
 
         for name, trans, column, _ in l_transformers:
             feature_names_3.extend(get_names(name, trans, column, enc_3))
 
         feature_names_4 = []
-        l_transformers = list(enc_4._iter(fitted=True))
+        l_transformers = list(enc_4._iter(fitted=True, column_as_labels=False, skip_drop=True, skip_empty_columns=True))
 
         for name, trans, column, _ in l_transformers:
             feature_names_4.extend(get_names(name, trans, column, enc_4))