Python sklearn.ensemble.BaggingRegressor() Examples

def test_regression():
    # Check regression for various parameter settings.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data[:50],
                                                        boston.target[:50],
                                                        random_state=rng)
    grid = ParameterGrid({"max_samples": [0.5, 1.0],
                          "max_features": [0.5, 1.0],
                          "bootstrap": [True, False],
                          "bootstrap_features": [True, False]})

    for base_estimator in [None,
                           DummyRegressor(),
                           DecisionTreeRegressor(),
                           KNeighborsRegressor(),
                           SVR(gamma='scale')]:
        for params in grid:
            BaggingRegressor(base_estimator=base_estimator,
                             random_state=rng,
                             **params).fit(X_train, y_train).predict(X_test) 

def test_bootstrap_samples():
    # Test that bootstrapping samples generate non-perfect base estimators.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data,
                                                        boston.target,
                                                        random_state=rng)

    base_estimator = DecisionTreeRegressor().fit(X_train, y_train)

    # without bootstrap, all trees are perfect on the training set
    ensemble = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                max_samples=1.0,
                                bootstrap=False,
                                random_state=rng).fit(X_train, y_train)

    assert_equal(base_estimator.score(X_train, y_train),
                 ensemble.score(X_train, y_train))

    # with bootstrap, trees are no longer perfect on the training set
    ensemble = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                max_samples=1.0,
                                bootstrap=True,
                                random_state=rng).fit(X_train, y_train)

    assert_greater(base_estimator.score(X_train, y_train),
                   ensemble.score(X_train, y_train))

    # check that each sampling correspond to a complete bootstrap resample.
    # the size of each bootstrap should be the same as the input data but
    # the data should be different (checked using the hash of the data).
    ensemble = BaggingRegressor(base_estimator=DummySizeEstimator(),
                                bootstrap=True).fit(X_train, y_train)
    training_hash = []
    for estimator in ensemble.estimators_:
        assert estimator.training_size_ == X_train.shape[0]
        training_hash.append(estimator.training_hash_)
    assert len(set(training_hash)) == len(training_hash) 

def test_bootstrap_features():
    # Test that bootstrapping features may generate duplicate features.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data,
                                                        boston.target,
                                                        random_state=rng)

    ensemble = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                max_features=1.0,
                                bootstrap_features=False,
                                random_state=rng).fit(X_train, y_train)

    for features in ensemble.estimators_features_:
        assert_equal(boston.data.shape[1], np.unique(features).shape[0])

    ensemble = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                max_features=1.0,
                                bootstrap_features=True,
                                random_state=rng).fit(X_train, y_train)

    for features in ensemble.estimators_features_:
        assert_greater(boston.data.shape[1], np.unique(features).shape[0]) 

def test_bootstrap_features():
    # Test that bootstrapping features may generate duplicate features.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data,
                                                        boston.target,
                                                        random_state=rng)

    ensemble = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                max_features=1.0,
                                bootstrap_features=False,
                                random_state=rng).fit(X_train, y_train)

    for features in ensemble.estimators_features_:
        assert_equal(boston.data.shape[1], np.unique(features).shape[0])

    ensemble = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                max_features=1.0,
                                bootstrap_features=True,
                                random_state=rng).fit(X_train, y_train)

    for features in ensemble.estimators_features_:
        assert_greater(boston.data.shape[1], np.unique(features).shape[0]) 

def test_parallel_regression():
    # Check parallel regression.
    rng = check_random_state(0)

    X_train, X_test, y_train, y_test = train_test_split(boston.data,
                                                        boston.target,
                                                        random_state=rng)

    ensemble = BaggingRegressor(DecisionTreeRegressor(),
                                n_jobs=3,
                                random_state=0).fit(X_train, y_train)

    ensemble.set_params(n_jobs=1)
    y1 = ensemble.predict(X_test)
    ensemble.set_params(n_jobs=2)
    y2 = ensemble.predict(X_test)
    assert_array_almost_equal(y1, y2)

    ensemble = BaggingRegressor(DecisionTreeRegressor(),
                                n_jobs=1,
                                random_state=0).fit(X_train, y_train)

    y3 = ensemble.predict(X_test)
    assert_array_almost_equal(y1, y3) 

def test_parallel_regression():
    # Check parallel regression.
    rng = check_random_state(0)

    X_train, X_test, y_train, y_test = train_test_split(boston.data,
                                                        boston.target,
                                                        random_state=rng)

    ensemble = BaggingRegressor(DecisionTreeRegressor(),
                                n_jobs=3,
                                random_state=0).fit(X_train, y_train)

    ensemble.set_params(n_jobs=1)
    y1 = ensemble.predict(X_test)
    ensemble.set_params(n_jobs=2)
    y2 = ensemble.predict(X_test)
    assert_array_almost_equal(y1, y2)

    ensemble = BaggingRegressor(DecisionTreeRegressor(),
                                n_jobs=1,
                                random_state=0).fit(X_train, y_train)

    y3 = ensemble.predict(X_test)
    assert_array_almost_equal(y1, y3) 

def test_regression():
    # Check regression for various parameter settings.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data[:50],
                                                        boston.target[:50],
                                                        random_state=rng)
    grid = ParameterGrid({"max_samples": [0.5, 1.0],
                          "max_features": [0.5, 1.0],
                          "bootstrap": [True, False],
                          "bootstrap_features": [True, False]})

    for base_estimator in [None,
                           DummyRegressor(),
                           DecisionTreeRegressor(),
                           KNeighborsRegressor(),
                           SVR()]:
        for params in grid:
            BaggingRegressor(base_estimator=base_estimator,
                             random_state=rng,
                             **params).fit(X_train, y_train).predict(X_test) 

def test_bootstrap_samples():
    # Test that bootstrapping samples generate non-perfect base estimators.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data,
                                                        boston.target,
                                                        random_state=rng)

    base_estimator = DecisionTreeRegressor().fit(X_train, y_train)

    # without bootstrap, all trees are perfect on the training set
    ensemble = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                max_samples=1.0,
                                bootstrap=False,
                                random_state=rng).fit(X_train, y_train)

    assert_equal(base_estimator.score(X_train, y_train),
                 ensemble.score(X_train, y_train))

    # with bootstrap, trees are no longer perfect on the training set
    ensemble = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                max_samples=1.0,
                                bootstrap=True,
                                random_state=rng).fit(X_train, y_train)

    assert_greater(base_estimator.score(X_train, y_train),
                   ensemble.score(X_train, y_train)) 

def bagging_regressor_best(self, x, y, param_grid=None, assign=True, n_jobs=-1, show=True):
        """
        寻找BaggingRegressor构造器的最优参数
        上层AbuML中bagging_regressor_best函数，直接使用AbuML中的x，y数据调用
        eg：
            bagging_regressor_best无param_grid参数调用：

            from abupy import AbuML, ml
            ttn_abu = AbuML.create_test_more_fiter()
            ttn_abu.bagging_regressor_best()

            bagging_regressor_best有param_grid参数调用：

            param_grid = {'max_samples': np.arange(1, 5), 'n_estimators': np.arange(100, 300, 50)}
            ttn_abu.bagging_regressor_best(param_grid=param_grid, n_jobs=-1)

            out: BaggingRegressor(max_samples=4, n_estimators=250)


        :param x: 训练集x矩阵，numpy矩阵
        :param y: 训练集y序列，numpy序列
        :param param_grid: 最优字典关键字参数，
                        eg：param_grid = {'max_samples': np.arange(1, 5), 'n_estimators': np.arange(100, 300, 50)}
        :param assign: 是否保存实例化后最优参数的学习器对象，默认True
        :param n_jobs: 并行执行的进程任务数量，默认-1, 开启与cpu相同数量的进程数
        :param show: 是否可视化最优参数搜索结果
        :return: 通过最优参数构造的BaggingRegressor对象
        """
        return self._estimators_prarms_best(self.bagging_regressor, x, y, param_grid, assign, n_jobs, show) 

def bagging_regressor(self, assign=True, base_estimator=DecisionTreeRegressor(), **kwargs):
        """
        有监督学习回归器，实例化BaggingRegressor，默认使用：
            BaggingRegressor(base_estimator=base_estimator, n_estimators=200,
                             bootstrap=True, oob_score=True, random_state=1)

        通过**kwargs即关键字参数透传BaggingRegressor，即:
            BaggingRegressor(**kwargs)

        :param base_estimator: 默认使用DecisionTreeRegressor()
        :param assign: 是否保存实例后的BaggingRegressor对象，默认True，self.reg = reg
        :param kwargs: 有参数情况下初始化: BaggingRegressor(**kwargs)
                       无参数情况下初始化: BaggingRegressor(base_estimator=base_estimator, reg_core, n_estimators=200,
                                                          bootstrap=True, oob_score=True, random_state=1)
        :return: 实例化的BaggingRegressor对象
        """
        if kwargs is not None and len(kwargs) > 0:
            if 'base_estimator' not in kwargs:
                kwargs['base_estimator'] = base_estimator
            reg = BaggingRegressor(**kwargs)
        else:
            reg = BaggingRegressor(base_estimator=base_estimator, n_estimators=200,
                                   bootstrap=True, oob_score=True, random_state=1)

        if assign:
            self.reg = reg
        return reg 

def test_objectmapper(self):
        df = pdml.ModelFrame([])
        self.assertIs(df.ensemble.AdaBoostClassifier,
                      ensemble.AdaBoostClassifier)
        self.assertIs(df.ensemble.AdaBoostRegressor,
                      ensemble.AdaBoostRegressor)
        self.assertIs(df.ensemble.BaggingClassifier,
                      ensemble.BaggingClassifier)
        self.assertIs(df.ensemble.BaggingRegressor,
                      ensemble.BaggingRegressor)
        self.assertIs(df.ensemble.ExtraTreesClassifier,
                      ensemble.ExtraTreesClassifier)
        self.assertIs(df.ensemble.ExtraTreesRegressor,
                      ensemble.ExtraTreesRegressor)

        self.assertIs(df.ensemble.GradientBoostingClassifier,
                      ensemble.GradientBoostingClassifier)
        self.assertIs(df.ensemble.GradientBoostingRegressor,
                      ensemble.GradientBoostingRegressor)

        self.assertIs(df.ensemble.IsolationForest,
                      ensemble.IsolationForest)

        self.assertIs(df.ensemble.RandomForestClassifier,
                      ensemble.RandomForestClassifier)
        self.assertIs(df.ensemble.RandomTreesEmbedding,
                      ensemble.RandomTreesEmbedding)
        self.assertIs(df.ensemble.RandomForestRegressor,
                      ensemble.RandomForestRegressor)

        self.assertIs(df.ensemble.VotingClassifier,
                      ensemble.VotingClassifier) 

def get_ensemble_models():
    rf = RandomForestRegressor(
        n_estimators=51, min_samples_leaf=5, min_samples_split=3, random_state=42,
        n_jobs=int(0.8*n_cores))
    bag = BaggingRegressor(n_estimators=51, random_state=42, n_jobs=int(0.8*n_cores))
    extra = ExtraTreesRegressor(n_estimators=71, random_state=42, n_jobs=int(0.8*n_cores))
    ada = AdaBoostRegressor(random_state=42)
    grad = GradientBoostingRegressor(n_estimators=101, random_state=42)
    classifier_list = [rf, bag, extra, ada, grad]
    classifier_name_list = ['Random Forests', 'Bagging',
                            'Extra Trees', 'AdaBoost', 'Gradient Boost']
    return classifier_list, classifier_name_list 

def __init__(self, cols=None, predictors=None, base_estimator=None,
                 n_estimators=10, max_samples=1.0, max_features=1.0,
                 bootstrap=True, bootstrap_features=False, n_jobs=1,
                 random_state=None, verbose=0, tmp_fill=-999., as_df=True):

        super(BaggedRegressorImputer, self).__init__(
            imputer_class=BaggingRegressor, cols=cols, predictors=predictors,
            base_estimator=base_estimator, n_estimators=n_estimators,
            max_samples=max_samples, max_features=max_features,
            bootstrap=bootstrap, bootstrap_features=bootstrap_features,
            n_jobs=n_jobs, random_state=random_state, verbose=verbose,
            tmp_fill=tmp_fill, as_df=as_df) 

def __init__(self, options):
        self.handle_options(options)
        params = options.get('params', {})
        out_params = convert_params(
            params,
            floats=['max_samples', 'max_features'],
            bools=['bootstrap', 'bootstrap_features', 'oob_score', 'warm_start'],
            ints=['n_estimators'],
        )

        self.estimator = _BaggingRegressor(**out_params) 

def setClf(self):
#         min_samples_split = 3
        self.clf = BaggingRegressor(n_estimators = 100, max_samples =0.5, max_features =0.5, verbose = 100)
        return 

def test_oob_score_regression():
    # Check that oob prediction is a good estimation of the generalization
    # error.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data,
                                                        boston.target,
                                                        random_state=rng)

    clf = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                           n_estimators=50,
                           bootstrap=True,
                           oob_score=True,
                           random_state=rng).fit(X_train, y_train)

    test_score = clf.score(X_test, y_test)

    assert_less(abs(test_score - clf.oob_score_), 0.1)

    # Test with few estimators
    assert_warns(UserWarning,
                 BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                  n_estimators=1,
                                  bootstrap=True,
                                  oob_score=True,
                                  random_state=rng).fit,
                 X_train,
                 y_train) 

def __init__(self, info, verbose=True, debug_mode=False):
        self.label_num=info['label_num']
        self.target_num=info['target_num']
        self.task = info['task']
        self.metric = info['metric']
        self.postprocessor = None
        #self.postprocessor = MultiLabelEnsemble(LogisticRegression(), balance=True) # To calibrate proba
        self.postprocessor = MultiLabelEnsemble(LogisticRegression(), balance=False) # To calibrate proba
        if debug_mode>=2:
            self.name = "RandomPredictor"
            self.model = RandomPredictor(self.target_num)
            self.predict_method = self.model.predict_proba 
            return
        if info['task']=='regression':
            if info['is_sparse']==True:
                self.name = "BaggingRidgeRegressor"
                self.model = BaggingRegressor(base_estimator=Ridge(), n_estimators=1, verbose=verbose) # unfortunately, no warm start...
            else:
                self.name = "GradientBoostingRegressor"
                self.model = GradientBoostingRegressor(n_estimators=1, verbose=verbose, warm_start = True)
            self.predict_method = self.model.predict # Always predict probabilities
        else:
            if info['has_categorical']: # Out of lazziness, we do not convert categorical variables...
                self.name = "RandomForestClassifier"
                self.model = RandomForestClassifier(n_estimators=1, verbose=verbose) # unfortunately, no warm start...
            elif info['is_sparse']:                
                self.name = "BaggingNBClassifier"
                self.model = BaggingClassifier(base_estimator=BernoulliNB(), n_estimators=1, verbose=verbose) # unfortunately, no warm start...                          
            else:
                self.name = "GradientBoostingClassifier"
                self.model = eval(self.name + "(n_estimators=1, verbose=" + str(verbose) + ", min_samples_split=10, random_state=1, warm_start = True)")
            if info['task']=='multilabel.classification':
                self.model = MultiLabelEnsemble(self.model)
            self.predict_method = self.model.predict_proba 

def fit(self):
        """Scale data and train the model with the indicated algorithm.

        Do not forget to tune the hyperparameters.

        Parameters
        ----------
        algorithm : String,
            "KernelRidge", "SVM", "LinearRegression", "Lasso", "ElasticNet", "NeuralNet", "BaggingNeuralNet", default = "SVM"

        """
        self.X_scaler.fit(self.X_train)
        self.Y_scaler.fit(self.y_train)

        # scaling the data in all cases, it may not be used during the fit later
        self.X_train_sc = self.X_scaler.transform(self.X_train)
        self.y_train_sc = self.Y_scaler.transform(self.y_train)

        self.X_test_sc = self.X_scaler.transform(self.X_test)
        self.y_test_sc = self.Y_scaler.transform(self.y_test)

        if self.algorithm == "KernelRidge":
            clf_kr = KernelRidge(kernel=self.user_kernel)
            self.model = sklearn.model_selection.GridSearchCV(clf_kr, cv=5, param_grid=self.param_kr)

        elif self.algorithm == "SVM":
            clf_svm = SVR(kernel=self.user_kernel)
            self.model = sklearn.model_selection.GridSearchCV(clf_svm, cv=5, param_grid=self.param_svm)

        elif self.algorithm == "Lasso":
            clf_lasso = sklearn.linear_model.Lasso(alpha=0.1,random_state=self.rand_state)
            self.model = sklearn.model_selection.GridSearchCV(clf_lasso, cv=5,
                                                              param_grid=dict(alpha=np.logspace(-5,5,30)))

        elif self.algorithm == "ElasticNet":
            clf_ElasticNet = sklearn.linear_model.ElasticNet(alpha=0.1, l1_ratio=0.5,random_state=self.rand_state)
            self.model = sklearn.model_selection.GridSearchCV(clf_ElasticNet,cv=5,
                                                              param_grid=dict(alpha=np.logspace(-5,5,30)))

        elif self.algorithm == "LinearRegression":
            self.model = sklearn.linear_model.LinearRegression()

        elif self.algorithm == "NeuralNet":
            self.model = MLPRegressor(**self.param_neurons)
        elif self.algorithm == "BaggingNeuralNet":
            nn_m = MLPRegressor(**self.param_neurons)

            self.model = BaggingRegressor(base_estimator = nn_m, **self.param_bag)

        if self.scaling == True:
            self.model.fit(self.X_train_sc, self.y_train_sc.reshape(-1,))
            predict_train_sc = self.model.predict(self.X_train_sc)
            self.prediction_train = self.Y_scaler.inverse_transform(predict_train_sc.reshape(-1,1))
            predict_test_sc = self.model.predict(self.X_test_sc)
            self.prediction_test = self.Y_scaler.inverse_transform(predict_test_sc.reshape(-1,1))
        else:
            self.model.fit(self.X_train, self.y_train.reshape(-1,))
            self.prediction_train = self.model.predict(self.X_train)
            self.prediction_test = self.model.predict(self.X_test) 

def test_bagging_regressor_with_missing_inputs():
    # Check that BaggingRegressor can accept X with missing/infinite data
    X = np.array([
        [1, 3, 5],
        [2, None, 6],
        [2, np.nan, 6],
        [2, np.inf, 6],
        [2, np.NINF, 6],
    ])
    y_values = [
        np.array([2, 3, 3, 3, 3]),
        np.array([
            [2, 1, 9],
            [3, 6, 8],
            [3, 6, 8],
            [3, 6, 8],
            [3, 6, 8],
        ])
    ]
    for y in y_values:
        regressor = DecisionTreeRegressor()
        pipeline = make_pipeline(
            FunctionTransformer(replace, validate=False),
            regressor
        )
        pipeline.fit(X, y).predict(X)
        bagging_regressor = BaggingRegressor(pipeline)
        y_hat = bagging_regressor.fit(X, y).predict(X)
        assert_equal(y.shape, y_hat.shape)

        # Verify that exceptions can be raised by wrapper regressor
        regressor = DecisionTreeRegressor()
        pipeline = make_pipeline(regressor)
        assert_raises(ValueError, pipeline.fit, X, y)
        bagging_regressor = BaggingRegressor(pipeline)
        assert_raises(ValueError, bagging_regressor.fit, X, y) 

def test_oob_score_regression():
    # Check that oob prediction is a good estimation of the generalization
    # error.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data,
                                                        boston.target,
                                                        random_state=rng)

    clf = BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                           n_estimators=50,
                           bootstrap=True,
                           oob_score=True,
                           random_state=rng).fit(X_train, y_train)

    test_score = clf.score(X_test, y_test)

    assert_less(abs(test_score - clf.oob_score_), 0.1)

    # Test with few estimators
    assert_warns(UserWarning,
                 BaggingRegressor(base_estimator=DecisionTreeRegressor(),
                                  n_estimators=1,
                                  bootstrap=True,
                                  oob_score=True,
                                  random_state=rng).fit,
                 X_train,
                 y_train) 

def test_base_estimator():
    # Check base_estimator and its default values.
    rng = check_random_state(0)

    # Classification
    X_train, X_test, y_train, y_test = train_test_split(iris.data,
                                                        iris.target,
                                                        random_state=rng)

    ensemble = BaggingClassifier(None,
                                 n_jobs=3,
                                 random_state=0).fit(X_train, y_train)

    assert_true(isinstance(ensemble.base_estimator_, DecisionTreeClassifier))

    ensemble = BaggingClassifier(DecisionTreeClassifier(),
                                 n_jobs=3,
                                 random_state=0).fit(X_train, y_train)

    assert_true(isinstance(ensemble.base_estimator_, DecisionTreeClassifier))

    ensemble = BaggingClassifier(Perceptron(tol=1e-3),
                                 n_jobs=3,
                                 random_state=0).fit(X_train, y_train)

    assert_true(isinstance(ensemble.base_estimator_, Perceptron))

    # Regression
    X_train, X_test, y_train, y_test = train_test_split(boston.data,
                                                        boston.target,
                                                        random_state=rng)

    ensemble = BaggingRegressor(None,
                                n_jobs=3,
                                random_state=0).fit(X_train, y_train)

    assert_true(isinstance(ensemble.base_estimator_, DecisionTreeRegressor))

    ensemble = BaggingRegressor(DecisionTreeRegressor(),
                                n_jobs=3,
                                random_state=0).fit(X_train, y_train)

    assert_true(isinstance(ensemble.base_estimator_, DecisionTreeRegressor))

    ensemble = BaggingRegressor(SVR(),
                                n_jobs=3,
                                random_state=0).fit(X_train, y_train)
    assert_true(isinstance(ensemble.base_estimator_, SVR)) 

def test_sparse_regression():
    # Check regression for various parameter settings on sparse input.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data[:50],
                                                        boston.target[:50],
                                                        random_state=rng)

    class CustomSVR(SVR):
        """SVC variant that records the nature of the training set"""

        def fit(self, X, y):
            super(CustomSVR, self).fit(X, y)
            self.data_type_ = type(X)
            return self

    parameter_sets = [
        {"max_samples": 0.5,
         "max_features": 2,
         "bootstrap": True,
         "bootstrap_features": True},
        {"max_samples": 1.0,
         "max_features": 4,
         "bootstrap": True,
         "bootstrap_features": True},
        {"max_features": 2,
         "bootstrap": False,
         "bootstrap_features": True},
        {"max_samples": 0.5,
         "bootstrap": True,
         "bootstrap_features": False},
    ]

    for sparse_format in [csc_matrix, csr_matrix]:
        X_train_sparse = sparse_format(X_train)
        X_test_sparse = sparse_format(X_test)
        for params in parameter_sets:

            # Trained on sparse format
            sparse_classifier = BaggingRegressor(
                base_estimator=CustomSVR(),
                random_state=1,
                **params
            ).fit(X_train_sparse, y_train)
            sparse_results = sparse_classifier.predict(X_test_sparse)

            # Trained on dense format
            dense_results = BaggingRegressor(
                base_estimator=CustomSVR(),
                random_state=1,
                **params
            ).fit(X_train, y_train).predict(X_test)

            sparse_type = type(X_train_sparse)
            types = [i.data_type_ for i in sparse_classifier.estimators_]

            assert_array_equal(sparse_results, dense_results)
            assert all([t == sparse_type for t in types])
            assert_array_equal(sparse_results, dense_results) 

def lets_try(train, labels):
    results = {}

    def test_model(clf):
        cv = KFold(n_splits=5, shuffle=True, random_state=45)
        r2 = make_scorer(r2_score)
        r2_val_score = cross_val_score(clf, train, labels, cv=cv, scoring=r2)
        scores = [r2_val_score.mean()]
        return scores

    clf = linear_model.LinearRegression()
    results["Linear"] = test_model(clf)

    clf = linear_model.Ridge()
    results["Ridge"] = test_model(clf)

    clf = linear_model.BayesianRidge()
    results["Bayesian Ridge"] = test_model(clf)

    clf = linear_model.HuberRegressor()
    results["Hubber"] = test_model(clf)

    clf = linear_model.Lasso(alpha=1e-4)
    results["Lasso"] = test_model(clf)

    clf = BaggingRegressor()
    results["Bagging"] = test_model(clf)

    clf = RandomForestRegressor()
    results["RandomForest"] = test_model(clf)

    clf = AdaBoostRegressor()
    results["AdaBoost"] = test_model(clf)

    clf = svm.SVR()
    results["SVM RBF"] = test_model(clf)

    clf = svm.SVR(kernel="linear")
    results["SVM Linear"] = test_model(clf)

    results = pd.DataFrame.from_dict(results, orient='index')
    results.columns = ["R Square Score"]
    # results = results.sort(columns=["R Square Score"], ascending=False)
    results.plot(kind="bar", title="Model Scores")
    axes = plt.gca()
    axes.set_ylim([0.5, 1])
    return results 

def test_base_estimator():
    # Check base_estimator and its default values.
    rng = check_random_state(0)

    # Classification
    X_train, X_test, y_train, y_test = train_test_split(iris.data,
                                                        iris.target,
                                                        random_state=rng)

    ensemble = BaggingClassifier(None,
                                 n_jobs=3,
                                 random_state=0).fit(X_train, y_train)

    assert isinstance(ensemble.base_estimator_, DecisionTreeClassifier)

    ensemble = BaggingClassifier(DecisionTreeClassifier(),
                                 n_jobs=3,
                                 random_state=0).fit(X_train, y_train)

    assert isinstance(ensemble.base_estimator_, DecisionTreeClassifier)

    ensemble = BaggingClassifier(Perceptron(tol=1e-3),
                                 n_jobs=3,
                                 random_state=0).fit(X_train, y_train)

    assert isinstance(ensemble.base_estimator_, Perceptron)

    # Regression
    X_train, X_test, y_train, y_test = train_test_split(boston.data,
                                                        boston.target,
                                                        random_state=rng)

    ensemble = BaggingRegressor(None,
                                n_jobs=3,
                                random_state=0).fit(X_train, y_train)

    assert isinstance(ensemble.base_estimator_, DecisionTreeRegressor)

    ensemble = BaggingRegressor(DecisionTreeRegressor(),
                                n_jobs=3,
                                random_state=0).fit(X_train, y_train)

    assert isinstance(ensemble.base_estimator_, DecisionTreeRegressor)

    ensemble = BaggingRegressor(SVR(gamma='scale'),
                                n_jobs=3,
                                random_state=0).fit(X_train, y_train)
    assert isinstance(ensemble.base_estimator_, SVR) 

def test_sparse_regression():
    # Check regression for various parameter settings on sparse input.
    rng = check_random_state(0)
    X_train, X_test, y_train, y_test = train_test_split(boston.data[:50],
                                                        boston.target[:50],
                                                        random_state=rng)

    class CustomSVR(SVR):
        """SVC variant that records the nature of the training set"""

        def fit(self, X, y):
            super().fit(X, y)
            self.data_type_ = type(X)
            return self

    parameter_sets = [
        {"max_samples": 0.5,
         "max_features": 2,
         "bootstrap": True,
         "bootstrap_features": True},
        {"max_samples": 1.0,
         "max_features": 4,
         "bootstrap": True,
         "bootstrap_features": True},
        {"max_features": 2,
         "bootstrap": False,
         "bootstrap_features": True},
        {"max_samples": 0.5,
         "bootstrap": True,
         "bootstrap_features": False},
    ]

    for sparse_format in [csc_matrix, csr_matrix]:
        X_train_sparse = sparse_format(X_train)
        X_test_sparse = sparse_format(X_test)
        for params in parameter_sets:

            # Trained on sparse format
            sparse_classifier = BaggingRegressor(
                base_estimator=CustomSVR(gamma='scale'),
                random_state=1,
                **params
            ).fit(X_train_sparse, y_train)
            sparse_results = sparse_classifier.predict(X_test_sparse)

            # Trained on dense format
            dense_results = BaggingRegressor(
                base_estimator=CustomSVR(gamma='scale'),
                random_state=1,
                **params
            ).fit(X_train, y_train).predict(X_test)

            sparse_type = type(X_train_sparse)
            types = [i.data_type_ for i in sparse_classifier.estimators_]

            assert_array_almost_equal(sparse_results, dense_results)
            assert all([t == sparse_type for t in types])
            assert_array_almost_equal(sparse_results, dense_results)