fix is_classifier for older xgboost

Author: lopuhin

eli5/sklearn/explain_prediction.py

@@ -1,9 +1,8 @@
-# -*- coding: utf-8 -*-
 from functools import partial
 
 import numpy as np
 import scipy.sparse as sp
-from sklearn.base import BaseEstimator, is_classifier
+from sklearn.base import BaseEstimator
 from sklearn.ensemble import (
     ExtraTreesClassifier,
     ExtraTreesRegressor,
@@ -54,14 +53,15 @@
 from eli5.base_utils import singledispatch
 from eli5.utils import (
     get_target_display_names,
-    get_binary_target_scale_label_id
+    get_binary_target_scale_label_id,
 )
 from eli5.sklearn.utils import (
     add_intercept,
     get_coef,
     get_default_target_names,
     get_X,
     get_X0,
+    is_classifier,
     is_multiclass_classifier,
     is_multitarget_regressor,
     predict_proba,

eli5/sklearn/permutation_importance.py

@@ -1,21 +1,14 @@
-# -*- coding: utf-8 -*-
 from functools import partial
-from typing import List
 
 import numpy as np
 from sklearn.model_selection import check_cv
 from sklearn.utils.metaestimators import available_if
 from sklearn.utils import check_array, check_random_state
-from sklearn.base import (
-    BaseEstimator,
-    MetaEstimatorMixin,
-    clone,
-    is_classifier
-)
+from sklearn.base import BaseEstimator, MetaEstimatorMixin, clone
 from sklearn.metrics import check_scoring
 
 from eli5.permutation_importance import get_score_importances
-from eli5.sklearn.utils import pandas_available
+from eli5.sklearn.utils import pandas_available, is_classifier
 
 if pandas_available:
     import pandas as pd
@@ -157,7 +150,6 @@ class PermutationImportance(BaseEstimator, MetaEstimatorMixin):
     """
     def __init__(self, estimator, scoring=None, n_iter=5, random_state=None,
                  cv='prefit', refit=True):
-        # type: (...) -> None
         if isinstance(cv, str) and cv != "prefit":
             raise ValueError("Invalid cv value: {!r}".format(cv))
         self.refit = refit
@@ -174,8 +166,7 @@ def pd_scorer(model, X, y):
             return base_scorer(model, X, y)
         return pd_scorer
 
-    def fit(self, X, y, groups=None, **fit_params):
-        # type: (...) -> PermutationImportance
+    def fit(self, X, y, groups=None, **fit_params) -> 'PermutationImportance':
         """Compute ``feature_importances_`` attribute and optionally
         fit the base estimator.
 
@@ -224,8 +215,8 @@ def fit(self, X, y, groups=None, **fit_params):
     def _cv_scores_importances(self, X, y, groups=None, **fit_params):
         assert self.cv is not None
         cv = check_cv(self.cv, y, classifier=is_classifier(self.estimator))
-        feature_importances = []  # type: List
-        base_scores = []  # type: List[float]
+        feature_importances: list = []
+        base_scores: list[float] = []
         weights = fit_params.pop('sample_weight', None)
         fold_fit_params = fit_params.copy()
         for train, test in cv.split(X, y, groups):
@@ -249,8 +240,7 @@ def _get_score_importances(self, score_func, X, y):
                                      random_state=self.rng_)
 
     @property
-    def caveats_(self):
-        # type: () -> str
+    def caveats_(self) -> str:
         if self.cv == 'prefit':
             return CAVEATS_PREFIT
         elif self.cv is None:

eli5/sklearn/utils.py

@@ -2,12 +2,30 @@
 
 import numpy as np
 import scipy.sparse as sp
+import sklearn.base
 from sklearn.multiclass import OneVsRestClassifier
 
 from eli5.sklearn.unhashing import invert_hashing_and_fit, handle_hashing_vec
 from eli5._feature_names import FeatureNames
 
 
+def is_classifier(estimator):
+    try:
+        return sklearn.base.is_classifier(estimator)
+    except AttributeError:
+        # old xgboost < 2.0.0 is not compatible with new sklean here
+        try:
+            import xgboost
+        except ImportError:
+            pass
+        else:
+            if isinstance(estimator, xgboost.XGBClassifier):
+                return True
+            elif isinstance(estimator, (xgboost.XGBRanker, xgboost.XGBRegressor)):
+                return False
+        raise
+
+
 def is_multiclass_classifier(clf) -> bool:
     """
     Return True if a classifier is multiclass or False if it is binary.

eli5/utils.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 import numpy as np
 from scipy import sparse as sp