Python metrics.make_scorer方法代码示例

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import make_scorer [as 别名]
def test_cross_val_score_with_score_func_regression():
    X, y = make_regression(n_samples=30, n_features=20, n_informative=5,
                           random_state=0)
    reg = Ridge()

    # Default score of the Ridge regression estimator
    scores = cross_val_score(reg, X, y, cv=5)
    assert_array_almost_equal(scores, [0.94, 0.97, 0.97, 0.99, 0.92], 2)

    # R2 score (aka. determination coefficient) - should be the
    # same as the default estimator score
    r2_scores = cross_val_score(reg, X, y, scoring="r2", cv=5)
    assert_array_almost_equal(r2_scores, [0.94, 0.97, 0.97, 0.99, 0.92], 2)

    # Mean squared error; this is a loss function, so "scores" are negative
    neg_mse_scores = cross_val_score(reg, X, y, cv=5,
                                     scoring="neg_mean_squared_error")
    expected_neg_mse = np.array([-763.07, -553.16, -274.38, -273.26, -1681.99])
    assert_array_almost_equal(neg_mse_scores, expected_neg_mse, 2)

    # Explained variance
    scoring = make_scorer(explained_variance_score)
    ev_scores = cross_val_score(reg, X, y, cv=5, scoring=scoring)
    assert_array_almost_equal(ev_scores, [0.94, 0.97, 0.97, 0.99, 0.92], 2) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import make_scorer [as 别名]
def test_grid_search_cv_results_multimetric():
    X, y = make_classification(n_samples=50, n_features=4, random_state=42)

    n_splits = 3
    params = [dict(kernel=['rbf', ], C=[1, 10], gamma=[0.1, 1]),
              dict(kernel=['poly', ], degree=[1, 2])]

    for iid in (False, True):
        grid_searches = []
        for scoring in ({'accuracy': make_scorer(accuracy_score),
                         'recall': make_scorer(recall_score)},
                        'accuracy', 'recall'):
            grid_search = GridSearchCV(SVC(gamma='scale'), cv=n_splits,
                                       iid=iid, param_grid=params,
                                       scoring=scoring, refit=False)
            grid_search.fit(X, y)
            assert_equal(grid_search.iid, iid)
            grid_searches.append(grid_search)

        compare_cv_results_multimetric_with_single(*grid_searches, iid=iid) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import make_scorer [as 别名]
def apply_gridsearch(self,model):
        """
        apply grid search on ml algorithm to specified parameters
        returns updated best score and parameters
        """
        # check if custom evalution function is specified
        if callable(self.params_cv['scoring']):
            scoring = make_scorer(self.params_cv['scoring'],greater_is_better=self._greater_is_better)
        else:
            scoring = self.params_cv['scoring']
        
        gsearch = GridSearchCV(estimator=model,param_grid=self.get_params_tune(),scoring=scoring,
                               iid=self.params_cv['iid'],cv=self.params_cv['cv_folds'],n_jobs=self.params_cv['n_jobs'])
        gsearch.fit(self.X,self.y)
        
        # update best model if best_score is improved
        if (gsearch.best_score_ * self._score_mult) > (self.best_score * self._score_mult):
            self.best_model = clone(gsearch.best_estimator_)
            self.best_score = gsearch.best_score_
        
        # update tuned parameters with optimal values
        for key,value in gsearch.best_params_.items():
            self._params[key] = value
        self._temp_score = gsearch.best_score_
        return self 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import make_scorer [as 别名]
def mae_cv(self, cv):
        """
        This method performs cross-validation over median absolute error.
        
        Parameters
        ----------
        * cv : integer
          The number of cross validation folds to perform

        Returns
        -------
        Returns a scores of the k-fold median absolute error.
        """

        mae = metrics.make_scorer(metrics.median_absolute_error)
        result = cross_validate(self.reg, self.X,
                                self.y, cv=cv,
                                scoring=(mae))
        return self.get_test_score(result) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import make_scorer [as 别名]
def mse_cv(self, cv):
        """
        This method performs cross-validation over mean squared error.
        
        Parameters
        ----------
        * cv : integer
          The number of cross validation folds to perform

        Returns
        -------
        Returns a scores of the k-fold mean squared error.
        """
        mse = metrics.make_scorer(metrics.mean_squared_error)
        result = cross_validate(self.reg, self.X,
                                self.y, cv=cv,
                                scoring=(mse))
        return self.get_test_score(result) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import make_scorer [as 别名]
def tse_cv(self, cv):
        """
        This method performs cross-validation over trimean squared error.
        
        Parameters
        ----------
        * cv : integer
          The number of cross validation folds to perform

        Returns
        -------
        Returns a scores of the k-fold trimean squared error.
        """
        tse = metrics.make_scorer(self.trimean_squared_error)
        result = cross_validate(self.reg, self.X,
                                self.y, cv=cv,
                                scoring=(tse))
        return self.get_test_score(result) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import make_scorer [as 别名]
def tae_cv(self, cv):
        """
        This method performs cross-validation over trimean absolute error.
        
        Parameters
        ----------
        * cv : integer
          The number of cross validation folds to perform

        Returns
        -------
        Returns a scores of the k-fold trimean absolute error.
        """
        tse = metrics.make_scorer(self.trimean_absolute_error)
        result = cross_validate(self.reg, self.X,
                                self.y, cv=cv,
                                scoring=(tse))
        return self.get_test_score(result) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import make_scorer [as 别名]
def test_with_make_scorer_accuracy_score(
            self, net_cls, module_cls, scoring_cls, train_split, data,
    ):
        net = net_cls(
            module_cls,
            callbacks=[scoring_cls(make_scorer(accuracy_score))],
            batch_size=1,
            max_epochs=2,
            train_split=train_split,
        )
        net.fit(*data)

        score_epochs = net.history[:, 'accuracy_score']
        assert np.allclose(score_epochs, [0, 0])

        score_batches = net.history[:, 'batches', :, 'accuracy_score']
        assert np.allclose(score_batches, [[0, 0], [0, 0]]) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import make_scorer [as 别名]
def convert_sklearn_metric_function(scoring):
    """If ``scoring`` is a sklearn metric function, convert it to a
    sklearn scorer and return it. Otherwise, return ``scoring`` unchanged."""
    if callable(scoring):
        module = getattr(scoring, '__module__', None)

        # those are scoring objects returned by make_scorer starting
        # from sklearn 0.22
        scorer_names = ('_PredictScorer', '_ProbaScorer', '_ThresholdScorer')
        if (
                hasattr(module, 'startswith') and
                module.startswith('sklearn.metrics.') and
                not module.startswith('sklearn.metrics.scorer') and
                not module.startswith('sklearn.metrics.tests.') and
                not scoring.__class__.__name__ in scorer_names
        ):
            return make_scorer(scoring)
    return scoring 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import make_scorer [as 别名]
def test_with_gridsearchcv3_auto(self):
        from sklearn.model_selection import GridSearchCV
        from sklearn.datasets import load_iris
        from sklearn.metrics import accuracy_score, make_scorer
        lr = LogisticRegression()
        from sklearn.pipeline import Pipeline
        scikit_pipeline = Pipeline([(Nystroem().name(), Nystroem()), (lr.name(), LogisticRegression())])
        all_parameters = get_grid_search_parameter_grids(Nystroem()>>lr, num_samples=1)
        # otherwise the test takes too long
        parameters = random.sample(all_parameters, 2)
        with warnings.catch_warnings():
            warnings.simplefilter("ignore")

            clf = GridSearchCV(scikit_pipeline, parameters, cv=2, scoring=make_scorer(accuracy_score))
            iris = load_iris()
            clf.fit(iris.data, iris.target)
            predicted = clf.predict(iris.data) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import make_scorer [as 别名]
def test_with_randomizedsearchcv(self):
        from sklearn.model_selection import RandomizedSearchCV
        from sklearn.datasets import load_iris
        from sklearn.metrics import accuracy_score, make_scorer
        from scipy.stats.distributions import uniform
        import numpy as np
        lr = LogisticRegression()
        parameters = {'solver':('liblinear', 'lbfgs'), 'penalty':['l2']}
        ranges, cat_idx = lr.get_param_ranges()
        min_C, max_C, default_C = ranges['C']
        # specify parameters and distributions to sample from
        #the loguniform distribution needs to be taken care of properly
        param_dist = {"solver": ranges['solver'],
                      "C": uniform(min_C, np.log(max_C))}
        # run randomized search
        n_iter_search = 5
        with warnings.catch_warnings():
            warnings.simplefilter("ignore")
            random_search = RandomizedSearchCV(
                lr, param_distributions=param_dist, n_iter=n_iter_search, cv=5,
                scoring=make_scorer(accuracy_score))
            iris = load_iris()
            random_search.fit(iris.data, iris.target) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import make_scorer [as 别名]
def test_clone_operator_choice(self):
        from sklearn.model_selection import cross_val_score
        from sklearn.metrics import accuracy_score, make_scorer
        from sklearn.base import clone
        from sklearn.datasets import load_iris
        iris = load_iris()
        X, y = iris.data, iris.target

        lr = LogisticRegression()
        trainable = PCA() >> lr 
        trainable_wrapper = make_sklearn_compat(trainable)
        trainable2 = clone(trainable_wrapper)
        with warnings.catch_warnings():
            warnings.simplefilter("ignore")
            result = cross_val_score(trainable_wrapper, X, y,
                                     scoring=make_scorer(accuracy_score), cv=2)
            result2 = cross_val_score(trainable2, X, y,
                                      scoring=make_scorer(accuracy_score), cv=2)
        for i in range(len(result)):
            self.assertEqual(result[i], result2[i]) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import make_scorer [as 别名]
def test_with_gridsearchcv_auto_wrapped_pipe1(self):
        from sklearn.datasets import load_iris
        from sklearn.metrics import accuracy_score, make_scorer
  
        lr = LogisticRegression()
        pca = PCA()
        trainable = pca >> lr

        with warnings.catch_warnings():
            warnings.simplefilter("ignore")
            from lale.lib.lale import GridSearchCV
            clf = GridSearchCV(
                estimator=trainable, lale_num_samples=1, lale_num_grids=1,
                cv=2, scoring=make_scorer(accuracy_score))
            iris = load_iris()
            clf.fit(iris.data, iris.target) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import make_scorer [as 别名]
def backtest(data_set_path,n_test_split):

    X,y = prepare_data(data_set_path,as_retention=False)

    tscv = TimeSeriesSplit(n_splits=n_test_split)

    lift_scorer = make_scorer(calc_lift, needs_proba=True)
    score_models = {'lift': lift_scorer, 'AUC': 'roc_auc'}

    retain_reg = LogisticRegression(penalty='l1', solver='liblinear', fit_intercept=True)

    gsearch = GridSearchCV(estimator=retain_reg,scoring=score_models, cv=tscv, verbose=1,
                           return_train_score=False,  param_grid={'C' : [1]}, refit='AUC')

    gsearch.fit(X,y)
    result_df = pd.DataFrame(gsearch.cv_results_)

    save_path = data_set_path.replace('.csv', '_backtest.csv')
    result_df.to_csv(save_path, index=False)
    print('Saved test scores to ' + save_path) 

# 需要导入模块: from sklearn import metrics [as 别名]
# 或者: from sklearn.metrics import make_scorer [as 别名]
def crossvalidate_churn_model(self,model_code,groups=True):
        X,y = self.prepare_xy(groups)
        params = self.cv_params(model_code)
        model = self.model_instance(model_code)
        tscv = TimeSeriesSplit(n_splits=3)
        lift_scorer = make_scorer(top_decile_lift,needs_proba=True)
        score_models = {'lift_scorer' : lift_scorer, 'AUC' : 'roc_auc'}
        gsearch = GridSearchCV(estimator=model, param_grid=params, scoring=score_models, cv=tscv, n_jobs=8,verbose=5,
                               return_train_score=True,refit='AUC')


        gsearch.fit(X, y)
        result_df = pd.DataFrame(gsearch.cv_results_)
        if len(params)>1:
            result_df.sort_values('mean_test_AUC',ascending=False,inplace=True)


        save_file_name = model_code + '_CV'
        save_path = self.save_path(save_file_name, subdir=self.grouping_correlation_subdir(groups))

        result_df.to_csv(save_path)
        print('Saved result to ' + save_path)
        return result_df