Python sklearn.svm.LinearSVR() Examples

def meta_model_fit(X_train, y_train, svm_hardness, fit_intercept, number_of_threads, regressor_type="LinearSVR"):
    """
    Trains meta-labeler for predicting number of labels for each user.

    Based on: Tang, L., Rajan, S., & Narayanan, V. K. (2009, April).
              Large scale multi-label classification via metalabeler.
              In Proceedings of the 18th international conference on World wide web (pp. 211-220). ACM.
    """
    if regressor_type == "LinearSVR":
        if X_train.shape[0] > X_train.shape[1]:
            dual = False
        else:
            dual = True

        model = LinearSVR(C=svm_hardness, random_state=0, dual=dual,
                          fit_intercept=fit_intercept)
        y_train_meta = y_train.sum(axis=1)
        model.fit(X_train, y_train_meta)
    else:
        print("Invalid regressor type.")
        raise RuntimeError

    return model 

def test_glm_regressor(self):
        X, y = make_regression(n_features=4, random_state=0)

        lr = LinearRegression()
        lr.fit(X, y)
        lr_coreml = coremltools.converters.sklearn.convert(lr)
        lr_onnx = convert(lr_coreml.get_spec())
        self.assertTrue(lr_onnx is not None)
        dump_data_and_model(X.astype(numpy.float32), lr, lr_onnx, basename="CmlLinearRegression-Dec4")

        svr = LinearSVR()
        svr.fit(X, y)
        svr_coreml = coremltools.converters.sklearn.convert(svr)
        svr_onnx = convert(svr_coreml.get_spec())
        self.assertTrue(svr_onnx is not None)
        dump_data_and_model(X.astype(numpy.float32), svr, svr_onnx, basename="CmlLinearSvr-Dec4") 

def test_svr():
    # Test Support Vector Regression

    diabetes = datasets.load_diabetes()
    for clf in (svm.NuSVR(kernel='linear', nu=.4, C=1.0),
                svm.NuSVR(kernel='linear', nu=.4, C=10.),
                svm.SVR(kernel='linear', C=10.),
                svm.LinearSVR(C=10.),
                svm.LinearSVR(C=10.),
                ):
        clf.fit(diabetes.data, diabetes.target)
        assert_greater(clf.score(diabetes.data, diabetes.target), 0.02)

    # non-regression test; previously, BaseLibSVM would check that
    # len(np.unique(y)) < 2, which must only be done for SVC
    svm.SVR().fit(diabetes.data, np.ones(len(diabetes.data)))
    svm.LinearSVR().fit(diabetes.data, np.ones(len(diabetes.data))) 

def ensure_many_models(self):
        from sklearn.ensemble import GradientBoostingRegressor, RandomForestRegressor
        from sklearn.neural_network import MLPRegressor
        from sklearn.linear_model import ElasticNet, RANSACRegressor, HuberRegressor, PassiveAggressiveRegressor
        from sklearn.neighbors import KNeighborsRegressor
        from sklearn.svm import SVR, LinearSVR

        import warnings
        from sklearn.exceptions import ConvergenceWarning
        warnings.filterwarnings('ignore', category=ConvergenceWarning)

        for learner in [GradientBoostingRegressor, RandomForestRegressor, MLPRegressor,
                        ElasticNet, RANSACRegressor, HuberRegressor, PassiveAggressiveRegressor,
                        KNeighborsRegressor, SVR, LinearSVR]:
            learner = learner()
            learner_name = str(learner).split("(", maxsplit=1)[0]
            with self.subTest("Test fit using {learner}".format(learner=learner_name)):
                model = self.estimator.__class__(learner)
                model.fit(self.data_lin["X"], self.data_lin["a"], self.data_lin["y"])
                self.assertTrue(True)  # Fit did not crash 

def predict_features(self, df_features, df_target, idx=0, C=.1, **kwargs):
        """For one variable, predict its neighbouring nodes.

        Args:
            df_features (pandas.DataFrame):
            df_target (pandas.Series):
            idx (int): (optional) for printing purposes
            kwargs (dict): additional options for algorithms
            C (float): Penalty parameter of the error term

        Returns:
            list: scores of each feature relatively to the target
        """
        lsvc = LinearSVR(C=C).fit(df_features.values, np.ravel(df_target.values))

        return np.abs(lsvc.coef_) 

def test_16_linearsvr(self):
        print("\ntest 16 (linear svr with preprocessing)\n")
        X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression()

        model = LinearSVR()
        pipeline_obj = Pipeline([
            ("scaler", MinMaxScaler()),
            ("model", model)
        ])
        pipeline_obj.fit(X,y)
        file_name = 'test16sklearn.pmml'
        
        skl_to_pmml(pipeline_obj, features, target, file_name)
        model_name  = self.adapa_utility.upload_to_zserver(file_name)
        predictions, _ = self.adapa_utility.score_in_zserver(model_name, test_file)
        model_pred = pipeline_obj.predict(X_test)
        self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True) 

def test_15_linearsvr(self):
        print("\ntest 15 (linear svr without preprocessing)\n")
        X, X_test, y, features, target, test_file = self.data_utility.get_data_for_regression()

        model = LinearSVR()
        pipeline_obj = Pipeline([
            ("model", model)
        ])
        pipeline_obj.fit(X,y)
        file_name = 'test15sklearn.pmml'
        
        skl_to_pmml(pipeline_obj, features, target, file_name)
        model_name  = self.adapa_utility.upload_to_zserver(file_name)
        predictions, _ = self.adapa_utility.score_in_zserver(model_name, test_file)
        model_pred = pipeline_obj.predict(X_test)
        self.assertEqual(self.adapa_utility.compare_predictions(predictions, model_pred), True) 

def fit(self, X, y, sample_weight=None, eval_set=None, sample_weight_eval_set=None, **kwargs):
        X = dt.Frame(X)

        orig_cols = list(X.names)

        if self.num_classes >= 2:
            mod = linsvc(random_state=self.random_state, C=self.params["C"], penalty=self.params["penalty"],
                         loss=self.params["loss"], dual=self.params["dual"])
            kf = StratifiedKFold(n_splits=3, shuffle=True, random_state=self.random_state)
            model = CalibratedClassifierCV(base_estimator=mod, method='isotonic', cv=kf)
            lb = LabelEncoder()
            lb.fit(self.labels)
            y = lb.transform(y)
        else:
            model = LinearSVR(epsilon=self.params["epsilon"], C=self.params["C"], loss=self.params["loss"],
                              dual=self.params["dual"], random_state=self.random_state)
        self.means = dict()
        self.standard_scaler = StandardScaler()
        for col in X.names:
            XX = X[:, col]
            self.means[col] = XX.mean1()
            if self.means[col] is None:
                self.means[col] = 0
            XX.replace(None, self.means[col])
            X[:, col] = XX
            assert X[dt.isna(dt.f[col]), col].nrows == 0
        X = X.to_numpy()
        X = self.standard_scaler.fit_transform(X)
        model.fit(X, y, sample_weight=sample_weight)
        importances = np.array([0.0 for k in range(len(orig_cols))])
        if self.num_classes >= 2:
            for classifier in model.calibrated_classifiers_:
                importances += np.array(abs(classifier.base_estimator.get_coeff()))
        else:
            importances += np.array(abs(model.coef_[0]))

        self.set_model_properties(model=model,
                                  features=orig_cols,
                                  importances=importances.tolist(),  # abs(model.coef_[0])
                                  iterations=0) 

def test_linearsvr():
    # check that SVR(kernel='linear') and LinearSVC() give
    # comparable results
    diabetes = datasets.load_diabetes()
    lsvr = svm.LinearSVR(C=1e3).fit(diabetes.data, diabetes.target)
    score1 = lsvr.score(diabetes.data, diabetes.target)

    svr = svm.SVR(kernel='linear', C=1e3).fit(diabetes.data, diabetes.target)
    score2 = svr.score(diabetes.data, diabetes.target)

    assert_allclose(np.linalg.norm(lsvr.coef_),
                    np.linalg.norm(svr.coef_), 1, 0.0001)
    assert_almost_equal(score1, score2, 2) 

def test_svr_coef_sign():
    # Test that SVR(kernel="linear") has coef_ with the right sign.
    # Non-regression test for #2933.
    X = np.random.RandomState(21).randn(10, 3)
    y = np.random.RandomState(12).randn(10)

    for svr in [svm.SVR(kernel='linear'), svm.NuSVR(kernel='linear'),
                svm.LinearSVR()]:
        svr.fit(X, y)
        assert_array_almost_equal(svr.predict(X),
                                  np.dot(X, svr.coef_.ravel()) + svr.intercept_) 

def test_linearsvx_loss_penalty_deprecations():
    X, y = [[0.0], [1.0]], [0, 1]

    msg = ("loss='%s' has been deprecated in favor of "
           "loss='%s' as of 0.16. Backward compatibility"
           " for the %s will be removed in %s")

    # LinearSVC
    # loss l1 --> hinge
    assert_warns_message(DeprecationWarning,
                         msg % ("l1", "hinge", "loss='l1'", "1.0"),
                         svm.LinearSVC(loss="l1").fit, X, y)

    # loss l2 --> squared_hinge
    assert_warns_message(DeprecationWarning,
                         msg % ("l2", "squared_hinge", "loss='l2'", "1.0"),
                         svm.LinearSVC(loss="l2").fit, X, y)

    # LinearSVR
    # loss l1 --> epsilon_insensitive
    assert_warns_message(DeprecationWarning,
                         msg % ("l1", "epsilon_insensitive", "loss='l1'",
                                "1.0"),
                         svm.LinearSVR(loss="l1").fit, X, y)

    # loss l2 --> squared_epsilon_insensitive
    assert_warns_message(DeprecationWarning,
                         msg % ("l2", "squared_epsilon_insensitive",
                                "loss='l2'", "1.0"),
                         svm.LinearSVR(loss="l2").fit, X, y) 

def test_linearsvr_fit_sampleweight():
    # check correct result when sample_weight is 1
    # check that SVR(kernel='linear') and LinearSVC() give
    # comparable results
    diabetes = datasets.load_diabetes()
    n_samples = len(diabetes.target)
    unit_weight = np.ones(n_samples)
    lsvr = svm.LinearSVR(C=1e3).fit(diabetes.data, diabetes.target,
                                    sample_weight=unit_weight)
    score1 = lsvr.score(diabetes.data, diabetes.target)

    lsvr_no_weight = svm.LinearSVR(C=1e3).fit(diabetes.data, diabetes.target)
    score2 = lsvr_no_weight.score(diabetes.data, diabetes.target)

    assert_allclose(np.linalg.norm(lsvr.coef_),
                    np.linalg.norm(lsvr_no_weight.coef_), 1, 0.0001)
    assert_almost_equal(score1, score2, 2)

    # check that fit(X)  = fit([X1, X2, X3],sample_weight = [n1, n2, n3]) where
    # X = X1 repeated n1 times, X2 repeated n2 times and so forth
    random_state = check_random_state(0)
    random_weight = random_state.randint(0, 10, n_samples)
    lsvr_unflat = svm.LinearSVR(C=1e3).fit(diabetes.data, diabetes.target,
                                           sample_weight=random_weight)
    score3 = lsvr_unflat.score(diabetes.data, diabetes.target,
                               sample_weight=random_weight)

    X_flat = np.repeat(diabetes.data, random_weight, axis=0)
    y_flat = np.repeat(diabetes.target, random_weight, axis=0)
    lsvr_flat = svm.LinearSVR(C=1e3).fit(X_flat, y_flat)
    score4 = lsvr_flat.score(X_flat, y_flat)

    assert_almost_equal(score3, score4, 2) 

def test_linearsvr():
    # check that SVR(kernel='linear') and LinearSVC() give
    # comparable results
    diabetes = datasets.load_diabetes()
    lsvr = svm.LinearSVR(C=1e3).fit(diabetes.data, diabetes.target)
    score1 = lsvr.score(diabetes.data, diabetes.target)

    svr = svm.SVR(kernel='linear', C=1e3).fit(diabetes.data, diabetes.target)
    score2 = svr.score(diabetes.data, diabetes.target)

    assert_allclose(np.linalg.norm(lsvr.coef_),
                    np.linalg.norm(svr.coef_), 1, 0.0001)
    assert_almost_equal(score1, score2, 2) 

def test_linearsvr_fit_sampleweight():
    # check correct result when sample_weight is 1
    # check that SVR(kernel='linear') and LinearSVC() give
    # comparable results
    diabetes = datasets.load_diabetes()
    n_samples = len(diabetes.target)
    unit_weight = np.ones(n_samples)
    lsvr = svm.LinearSVR(C=1e3).fit(diabetes.data, diabetes.target,
                                    sample_weight=unit_weight)
    score1 = lsvr.score(diabetes.data, diabetes.target)

    lsvr_no_weight = svm.LinearSVR(C=1e3).fit(diabetes.data, diabetes.target)
    score2 = lsvr_no_weight.score(diabetes.data, diabetes.target)

    assert_allclose(np.linalg.norm(lsvr.coef_),
                    np.linalg.norm(lsvr_no_weight.coef_), 1, 0.0001)
    assert_almost_equal(score1, score2, 2)

    # check that fit(X)  = fit([X1, X2, X3],sample_weight = [n1, n2, n3]) where
    # X = X1 repeated n1 times, X2 repeated n2 times and so forth
    random_state = check_random_state(0)
    random_weight = random_state.randint(0, 10, n_samples)
    lsvr_unflat = svm.LinearSVR(C=1e3).fit(diabetes.data, diabetes.target,
                                           sample_weight=random_weight)
    score3 = lsvr_unflat.score(diabetes.data, diabetes.target,
                               sample_weight=random_weight)

    X_flat = np.repeat(diabetes.data, random_weight, axis=0)
    y_flat = np.repeat(diabetes.target, random_weight, axis=0)
    lsvr_flat = svm.LinearSVR(C=1e3).fit(X_flat, y_flat)
    score4 = lsvr_flat.score(X_flat, y_flat)

    assert_almost_equal(score3, score4, 2) 

def test_model_linear_svr_bool(self):
        model, X = fit_regression_model(LinearSVR(), is_bool=True)
        model_onnx = convert_sklearn(
            model, "linear SVR",
            [("input", BooleanTensorType([None, X.shape[1]]))])
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X,
            model,
            model_onnx,
            basename="SklearnLinearSVRBool",
            allow_failure="StrictVersion("
            "onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

def test_model_linear_svr_int(self):
        model, X = fit_regression_model(LinearSVR(), is_int=True)
        model_onnx = convert_sklearn(
            model, "linear SVR",
            [("input", Int64TensorType([None, X.shape[1]]))])
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X,
            model,
            model_onnx,
            basename="SklearnLinearSvrInt-Dec4",
            allow_failure="StrictVersion("
            "onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

def test_model_linear_svr(self):
        model, X = fit_regression_model(LinearSVR())
        model_onnx = convert_sklearn(
            model, "linear SVR",
            [("input", FloatTensorType([None, X.shape[1]]))])
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X,
            model,
            model_onnx,
            basename="SklearnLinearSvr-Dec4",
            allow_failure="StrictVersion("
            "onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

def test_linearsvx_loss_penalty_deprecations():
    X, y = [[0.0], [1.0]], [0, 1]

    msg = ("loss='%s' has been deprecated in favor of "
           "loss='%s' as of 0.16. Backward compatibility"
           " for the %s will be removed in %s")

    # LinearSVC
    # loss l1 --> hinge
    assert_warns_message(DeprecationWarning,
                         msg % ("l1", "hinge", "loss='l1'", "1.0"),
                         svm.LinearSVC(loss="l1").fit, X, y)

    # loss l2 --> squared_hinge
    assert_warns_message(DeprecationWarning,
                         msg % ("l2", "squared_hinge", "loss='l2'", "1.0"),
                         svm.LinearSVC(loss="l2").fit, X, y)

    # LinearSVR
    # loss l1 --> epsilon_insensitive
    assert_warns_message(DeprecationWarning,
                         msg % ("l1", "epsilon_insensitive", "loss='l1'",
                                "1.0"),
                         svm.LinearSVR(loss="l1").fit, X, y)

    # loss l2 --> squared_epsilon_insensitive
    assert_warns_message(DeprecationWarning,
                         msg % ("l2", "squared_epsilon_insensitive",
                                "loss='l2'", "1.0"),
                         svm.LinearSVR(loss="l2").fit, X, y) 

def ensure_many_models(self):
        from sklearn.ensemble import GradientBoostingRegressor, RandomForestRegressor
        from sklearn.neural_network import MLPRegressor
        from sklearn.linear_model import ElasticNet, RANSACRegressor, HuberRegressor, PassiveAggressiveRegressor
        from sklearn.neighbors import KNeighborsRegressor
        from sklearn.svm import SVR, LinearSVR

        from sklearn.ensemble import GradientBoostingClassifier, RandomForestClassifier
        from sklearn.neural_network import MLPClassifier
        from sklearn.neighbors import KNeighborsClassifier

        from sklearn.exceptions import ConvergenceWarning
        warnings.filterwarnings('ignore', category=ConvergenceWarning)

        data = self.create_uninformative_ox_dataset()
        for propensity_learner in [GradientBoostingClassifier(n_estimators=10),
                                   RandomForestClassifier(n_estimators=100),
                                   MLPClassifier(hidden_layer_sizes=(5,)),
                                   KNeighborsClassifier(n_neighbors=20)]:
            weight_model = IPW(propensity_learner)
            propensity_learner_name = str(propensity_learner).split("(", maxsplit=1)[0]
            for outcome_learner in [GradientBoostingRegressor(n_estimators=10), RandomForestRegressor(n_estimators=10),
                                    MLPRegressor(hidden_layer_sizes=(5,)),
                                    ElasticNet(), RANSACRegressor(), HuberRegressor(), PassiveAggressiveRegressor(),
                                    KNeighborsRegressor(), SVR(), LinearSVR()]:
                outcome_learner_name = str(outcome_learner).split("(", maxsplit=1)[0]
                outcome_model = Standardization(outcome_learner)

                with self.subTest("Test fit & predict using {} & {}".format(propensity_learner_name,
                                                                            outcome_learner_name)):
                    model = self.estimator.__class__(outcome_model, weight_model)
                    model.fit(data["X"], data["a"], data["y"], refit_weight_model=False)
                    model.estimate_individual_outcome(data["X"], data["a"])
                    self.assertTrue(True)  # Fit did not crash 

def test_linear_svm_convergence_warnings():
    # Test that warnings are raised if model does not converge

    lsvc = svm.LinearSVC(random_state=0, max_iter=2)
    assert_warns(ConvergenceWarning, lsvc.fit, X, Y)
    assert_equal(lsvc.n_iter_, 2)

    lsvr = svm.LinearSVR(random_state=0, max_iter=2)
    assert_warns(ConvergenceWarning, lsvr.fit, iris.data, iris.target)
    assert_equal(lsvr.n_iter_, 2) 

def test_svr():
    # Test Support Vector Regression

    diabetes = datasets.load_diabetes()
    for clf in (svm.NuSVR(kernel='linear', nu=.4, C=1.0),
                svm.NuSVR(kernel='linear', nu=.4, C=10.),
                svm.SVR(kernel='linear', C=10.),
                svm.LinearSVR(C=10.),
                svm.LinearSVR(C=10.),
                ):
        clf.fit(diabetes.data, diabetes.target)
        assert_greater(clf.score(diabetes.data, diabetes.target), 0.02)

    # non-regression test; previously, BaseLibSVM would check that
    # len(np.unique(y)) < 2, which must only be done for SVC
    svm.SVR(gamma='scale').fit(diabetes.data, np.ones(len(diabetes.data)))
    svm.LinearSVR().fit(diabetes.data, np.ones(len(diabetes.data))) 

def load_default(self, machine_list='basic'):
        """
        Loads 4 different scikit-learn regressors by default. The advanced list adds more machines. 

        Parameters
        ----------
        machine_list: optional, list of strings
            List of default machine names to be loaded.
        Returns
        -------
        self : returns an instance of self.
        """

        if machine_list == 'basic':
            machine_list = ['tree', 'ridge', 'random_forest', 'svm']
        if machine_list == 'advanced':
            machine_list=['lasso', 'tree', 'ridge', 'random_forest', 'svm', 'bayesian_ridge', 'sgd']

        self.estimators_ = {}
        for machine in machine_list:
            try:
                if machine == 'lasso':
                    self.estimators_['lasso'] = linear_model.LassoCV(random_state=self.random_state).fit(self.X_k_, self.y_k_)
                if machine == 'tree':
                    self.estimators_['tree'] = DecisionTreeRegressor(random_state=self.random_state).fit(self.X_k_, self.y_k_)
                if machine == 'ridge':
                    self.estimators_['ridge'] = linear_model.RidgeCV().fit(self.X_k_, self.y_k_)
                if machine == 'random_forest':
                    self.estimators_['random_forest'] = RandomForestRegressor(random_state=self.random_state).fit(self.X_k_, self.y_k_)
                if machine == 'svm':
                    self.estimators_['svm'] = LinearSVR(random_state=self.random_state).fit(self.X_k_, self.y_k_)
                if machine == 'sgd':
                    self.estimators_['sgd'] = linear_model.SGDRegressor(random_state=self.random_state).fit(self.X_k_, self.y_k_)
                if machine == 'bayesian_ridge':
                    self.estimators_['bayesian_ridge'] = linear_model.BayesianRidge().fit(self.X_k_, self.y_k_)
            except ValueError:
                continue
        return self 

def test_linear_svr_evaluation(self):
        """
        Check that the evaluation results are the same in scikit learn and coremltools
        """
        ARGS = [
            {},
            {"C": 0.5, "epsilon": 0.25},
            {"dual": False, "loss": "squared_epsilon_insensitive"},
            {"tol": 0.005},
            {"fit_intercept": False},
            {"intercept_scaling": 1.5},
        ]

        input_names = self.scikit_data.feature_names
        df = pd.DataFrame(self.scikit_data.data, columns=input_names)

        for cur_args in ARGS:
            print(cur_args)
            cur_model = LinearSVR(**cur_args)
            cur_model.fit(self.scikit_data["data"], self.scikit_data["target"])
            spec = convert(cur_model, input_names, "target")

            df["prediction"] = cur_model.predict(self.scikit_data.data)

            metrics = evaluate_regressor(spec, df)
            self.assertAlmostEquals(metrics["max_error"], 0) 

def convert(model, features, target):
    """Convert a LinearSVR model to the protobuf spec.
    Parameters
    ----------
    model: LinearSVR
        A trained LinearSVR model.

    feature_names: [str]
        Name of the input columns.

    target: str
        Name of the output column.

    Returns
    -------
    model_spec: An object of type Model_pb.
        Protobuf representation of the model
    """
    if not (_HAS_SKLEARN):
        raise RuntimeError(
            "scikit-learn not found. scikit-learn conversion API is disabled."
        )

    # Check the scikit learn model
    _sklearn_util.check_expected_type(model, _LinearSVR)
    _sklearn_util.check_fitted(model, lambda m: hasattr(m, "coef_"))

    return _MLModel(_linear_regression._convert(model, features, target)) 

def test_sklearn_21(self):
        df = pd.read_csv('nyoka/tests/auto-mpg.csv')
        X = df.drop(['mpg', 'car name'], axis=1)
        y = df['mpg']

        features = X.columns
        target = 'mpg'
        f_name = "linearsvr_pmml.pmml"

        model = LinearSVR()
        pipeline_obj = Pipeline([
            ('model', model)
        ])

        pipeline_obj.fit(X, y)
        skl_to_pmml(pipeline_obj, features, target, f_name)
        pmml_obj = pml.parse(f_name, True)

        # 1
        self.assertEqual(os.path.isfile(f_name), True)

        # 2
        self.assertEqual("{:.16f}".format(model.intercept_[0]),
                         "{:.16f}".format(pmml_obj.RegressionModel[0].RegressionTable[0].intercept))

        # 3
        reg_tab = pmml_obj.RegressionModel[0].RegressionTable[0].NumericPredictor
        for model_val, pmml_val in zip(model.coef_, reg_tab):
            self.assertEqual("{:.16f}".format(model_val), "{:.16f}".format(pmml_val.coefficient)) 

def test_validate_sklearn_linarsvr_models_regression(self):
        model = LinearSVR()
        pipe = Pipeline([
            ('model',model)
        ])
        pipe.fit(self.X_reg, self.y_reg)
        file_name = 'linearsvr_model_regression.pmml'
        skl_to_pmml(pipe, self.features_reg, 'target',file_name)
        self.assertEqual(self.schema.is_valid(file_name), True) 

def test_many_models(self):
        from sklearn.ensemble import GradientBoostingRegressor, RandomForestRegressor
        from sklearn.neural_network import MLPRegressor
        from sklearn.linear_model import ElasticNet, RANSACRegressor, HuberRegressor, PassiveAggressiveRegressor
        from sklearn.neighbors import KNeighborsRegressor
        from sklearn.svm import SVR, LinearSVR

        from sklearn.ensemble import GradientBoostingClassifier, RandomForestClassifier
        from sklearn.neural_network import MLPClassifier
        from sklearn.neighbors import KNeighborsClassifier

        from sklearn.exceptions import ConvergenceWarning
        warnings.filterwarnings('ignore', category=ConvergenceWarning)

        data = self.create_uninformative_ox_dataset()

        for propensity_learner in [GradientBoostingClassifier(n_estimators=10),
                                   RandomForestClassifier(n_estimators=100),
                                   MLPClassifier(hidden_layer_sizes=(5,)),
                                   KNeighborsClassifier(n_neighbors=20)]:
            weight_model = IPW(propensity_learner)
            propensity_learner_name = str(propensity_learner).split("(", maxsplit=1)[0]
            for outcome_learner in [GradientBoostingRegressor(n_estimators=10),
                                    RandomForestRegressor(n_estimators=10),
                                    RANSACRegressor(), HuberRegressor(), SVR(), LinearSVR()]:
                outcome_learner_name = str(outcome_learner).split("(", maxsplit=1)[0]
                outcome_model = Standardization(outcome_learner)

                with self.subTest("Test fit using {} & {}".format(propensity_learner_name, outcome_learner_name)):
                    model = self.estimator.__class__(outcome_model, weight_model)
                    model.fit(data["X"], data["a"], data["y"], refit_weight_model=False)
                    self.assertTrue(True)  # Fit did not crash

            for outcome_learner in [MLPRegressor(hidden_layer_sizes=(5,)), ElasticNet(),
                                    PassiveAggressiveRegressor(), KNeighborsRegressor()]:
                outcome_learner_name = str(outcome_learner).split("(", maxsplit=1)[0]
                outcome_model = Standardization(outcome_learner)

                with self.subTest("Test fit using {} & {}".format(propensity_learner_name, outcome_learner_name)):
                    model = self.estimator.__class__(outcome_model, weight_model)
                    with self.assertRaises(TypeError):
                        # Joffe forces learning with sample_weights,
                        # not all ML models support that and so calling should fail
                        model.fit(data["X"], data["a"], data["y"], refit_weight_model=False)