scikit-learn · thomasjpfan · Jul 5, 2019 · Jul 5, 2019 · Jul 5, 2019 · Jul 5, 2019
diff --git a/doc/whats_new/v0.22.rst b/doc/whats_new/v0.22.rst
@@ -80,6 +80,9 @@ Changelog
   plot model scalability (see learning_curve example).
   :pr:`13938` by :user:`Hadrien Reboul <H4dr1en>`.
 
+- |Efficiency| Multimetric scoring now caches predictions to avoid repeated 		
+  calls. :pr:`14261` by `Thomas Fan`_.
+
 :mod:`sklearn.pipeline`
 .......................
 

diff --git a/sklearn/ensemble/voting.py b/sklearn/ensemble/voting.py
@@ -337,6 +337,10 @@ def predict_proba(self):
         """
         return self._predict_proba
 
+    @predict_proba.setter
+    def predict_proba(self, func):
+        self._predict_proba = func
+
     def transform(self, X):
         """Return class labels or probabilities for X for each estimator.
 

diff --git a/sklearn/linear_model/stochastic_gradient.py b/sklearn/linear_model/stochastic_gradient.py
@@ -988,6 +988,10 @@ def predict_proba(self):
         self._check_proba()
         return self._predict_proba
 
+    @predict_proba.setter
+    def predict_proba(self, func):
+        self._predict_proba = func
+
     def _predict_proba(self, X):
         check_is_fitted(self, "t_")
 
@@ -1056,6 +1060,10 @@ def predict_log_proba(self):
         self._check_proba()
         return self._predict_log_proba
 
+    @predict_log_proba.setter
+    def predict_log_proba(self, func):
+        self._predict_log_proba = func
+
     def _predict_log_proba(self, X):
         return np.log(self.predict_proba(X))
 

diff --git a/sklearn/model_selection/_validation.py b/sklearn/model_selection/_validation.py
@@ -14,6 +14,8 @@
 import numbers
 import time
 from traceback import format_exception_only
+from contextlib import contextmanager
+from functools import partial
 
 import numpy as np
 import scipy.sparse as sp
@@ -24,7 +26,8 @@
                      _message_with_time)
 from ..utils.validation import _is_arraylike, _num_samples
 from ..utils.metaestimators import _safe_split
-from ..metrics.scorer import check_scoring, _check_multimetric_scoring
+from ..metrics.scorer import (check_scoring, _check_multimetric_scoring,
+                              _BaseScorer)
 from ..exceptions import FitFailedWarning
 from ._split import check_cv
 from ..preprocessing import LabelEncoder
@@ -596,15 +599,43 @@ def _score(estimator, X_test, y_test, scorer, is_multimetric=False):
     return score
 
 
+@contextmanager
+def _cache_estimator(estimator):
+
+    def _call_func(X, *args, name=None, func=None, cache=None, **kwargs):
+        try:
+            return cache[name, id(X)]
+        except KeyError:
+            result = func(X, *args, **kwargs)
+            cache[name, id(X)] = result
+            return result
+
+    cache = {}
+    names = ['predict', 'predict_proba', 'decision_function', 'score']
+    cache_funcs = {name: getattr(estimator, name) for name in names if
+                   hasattr(estimator, name)}
+
+    # patch methods
+    for name, func in cache_funcs.items():
+        setattr(estimator, name,
+                partial(_call_func, name=name, func=func, cache=cache))
+    yield estimator
+
+    # place methods back
+    for name, func in cache_funcs.items():
+        setattr(estimator, name, func)
+
+
 def _multimetric_score(estimator, X_test, y_test, scorers):
     """Return a dict of score for multimetric scoring"""
     scores = {}
 
     for name, scorer in scorers.items():
-        if y_test is None:
-            score = scorer(estimator, X_test)
-        else:
-            score = scorer(estimator, X_test, y_test)
+        with _cache_estimator(estimator) as cached_estimator:
+            if y_test is None:
+                score = scorer(cached_estimator, X_test)
+            else:
+                score = scorer(cached_estimator, X_test, y_test)
 
         if hasattr(score, 'item'):
             try:

diff --git a/sklearn/model_selection/tests/test_validation.py b/sklearn/model_selection/tests/test_validation.py
@@ -5,6 +5,7 @@
 import tempfile
 import os
 from time import sleep
+from unittest.mock import Mock
 
 import pytest
 import numpy as np
@@ -76,7 +77,7 @@
 
 from sklearn.model_selection.tests.common import OneTimeSplitter
 from sklearn.model_selection import GridSearchCV
-
+from sklearn.model_selection._validation import _cache_estimator
 
 try:
     WindowsError
@@ -1718,3 +1719,22 @@ def two_params_scorer(estimator, X_test):
     fit_and_score_args = [None, None, None, two_params_scorer]
     assert_raise_message(ValueError, error_message,
                          _score, *fit_and_score_args)
+
+
+@pytest.mark.parametrize('func_name',
+                         ['predict', 'predict_proba',
+                          'decision_function', 'score'])
+def test_cached_estimator(func_name):
+    mock_est = Mock()
+    mock_func = getattr(mock_est, func_name)
+    mock_func.return_value = 42
+    X = np.array([[1]])
+
+    with _cache_estimator(mock_est) as cached_est:
+        # call func twice
+        func = getattr(cached_est, func_name)
+        assert func(X) == 42
+        assert func(X) == 42
+
+        # only called once
+        assert mock_func.call_count == 1
diff --git a/sklearn/neighbors/lof.py b/sklearn/neighbors/lof.py
@@ -296,6 +296,10 @@ def predict(self):
 
         return self._predict
 
+ 
F438
   @predict.setter
+    def predict(self, func):
+        self._predict = func
+
     def _predict(self, X=None):
         """Predict the labels (1 inlier, -1 outlier) of X according to LOF.
 
@@ -363,6 +367,10 @@ def decision_function(self):
 
         return self._decision_function
 
+    @decision_function.setter
+    def decision_function(self, func):
+        self._decision_function = func
+
     def _decision_function(self, X):
         """Shifted opposite of the Local Outlier Factor of X.
 

diff --git a/sklearn/neural_network/multilayer_perceptron.py b/sklearn/neural_network/multilayer_perceptron.py
@@ -664,6 +664,10 @@ def partial_fit(self):
                                  % self.solver)
         return self._partial_fit
 
+    @partial_fit.setter
+    def partial_fit(self, func):
+        self._partial_fit = func
+
     def _partial_fit(self, X, y):
         return self._fit(X, y, incremental=True)
 
@@ -1040,6 +1044,10 @@ def partial_fit(self):
                                  % self.solver)
         return self._partial_fit
 
+    @partial_fit.setter
+    def partial_fit(self, func):
+        self._partial_fit = func
+
     def _partial_fit(self, X, y, classes=None):
         if _check_partial_fit_first_call(self, classes):
             self._label_binarizer = LabelBinarizer()

diff --git a/sklearn/svm/base.py b/sklearn/svm/base.py
@@ -614,6 +614,10 @@ def predict_proba(self):
         self._check_proba()
         return self._predict_proba
 
+    @predict_proba.setter
+    def predict_proba(self, func):
+        self._predict_proba = func
+
     def _predict_proba(self, X):
         X = self._validate_for_predict(X)
         if self.probA_.size == 0 or self.probB_.size == 0:
@@ -653,6 +657,10 @@ def predict_log_proba(self):
         self._check_proba()
         return self._predict_log_proba
 
+    @predict_log_proba.setter
+    def predict_log_proba(self, func):
+        self._predict_log_proba = func
+
     def _predict_log_proba(self, X):
         return np.log(self.predict_proba(X))