Python sklearn.linear_model.HuberRegressor() Examples

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 fit(candidate_data, reference_data):
    ''' Tries a variety of robust fitting methods in what is considered
    descending order of how good the fits are with this type of data set
    (found empirically).

    :param list candidate_data: A 1D list or array representing only the image
                                data of the candidate band
    :param list reference_data: A 1D list or array representing only the image
                                data of the reference band

    :returns: A gain and an offset (tuple of floats)
    '''
    try:
        logging.debug('Robust: Trying HuberRegressor with epsilon 1.01')
        gain, offset = _huber_regressor(
            candidate_data, reference_data, 1.01)
    except:
        try:
            logging.debug('Robust: Trying HuberRegressor with epsilon 1.05')
            gain, offset = _huber_regressor(
                candidate_data, reference_data, 1.05)
        except:
            try:
                logging.debug('Robust: Trying HuberRegressor with epsilon 1.1')
                gain, offset = _huber_regressor(
                    candidate_data, reference_data, 1.1)
            except:
                try:
                    logging.debug('Robust: Trying HuberRegressor with epsilon '
                                 '1.35')
                    gain, offset = _huber_regressor(
                        candidate_data, reference_data, 1.35)
                except:
                    logging.debug('Robust: Trying RANSAC')
                    gain, offset = _ransac_regressor(
                        candidate_data, reference_data)
    return gain, offset 

def _huber_regressor(candidate_data, reference_data, epsilon, max_iter=10000):
    model = linear_model.HuberRegressor(epsilon=epsilon, max_iter=max_iter)
    model.fit(numpy.array([[c] for c in candidate_data]),
              numpy.array(reference_data))
    gain = model.coef_
    offset = model.intercept_

    return gain, offset 

def getModels():
    result = []
    result.append("LinearRegression")
    result.append("BayesianRidge")
    result.append("ARDRegression")
    result.append("ElasticNet")
    result.append("HuberRegressor")
    result.append("Lasso")
    result.append("LassoLars")
    result.append("Rigid")
    result.append("SGDRegressor")
    result.append("SVR")
    result.append("MLPClassifier")
    result.append("KNeighborsClassifier")
    result.append("SVC")
    result.append("GaussianProcessClassifier")
    result.append("DecisionTreeClassifier")
    result.append("RandomForestClassifier")
    result.append("AdaBoostClassifier")
    result.append("GaussianNB")
    result.append("LogisticRegression")
    result.append("QuadraticDiscriminantAnalysis")
    return result 

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_model_huber_regressor(self):
        model, X = fit_regression_model(linear_model.HuberRegressor())
        model_onnx = convert_sklearn(
            model, "huber regressor",
            [("input", FloatTensorType([None, X.shape[1]]))])
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X,
            model,
            model_onnx,
            basename="SklearnHuberRegressor-Dec4",
            allow_failure="StrictVersion("
            "onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

def test_objectmapper(self):
        df = pdml.ModelFrame([])
        self.assertIs(df.linear_model.ARDRegression, lm.ARDRegression)
        self.assertIs(df.linear_model.BayesianRidge, lm.BayesianRidge)
        self.assertIs(df.linear_model.ElasticNet, lm.ElasticNet)
        self.assertIs(df.linear_model.ElasticNetCV, lm.ElasticNetCV)

        self.assertIs(df.linear_model.HuberRegressor, lm.HuberRegressor)

        self.assertIs(df.linear_model.Lars, lm.Lars)
        self.assertIs(df.linear_model.LarsCV, lm.LarsCV)
        self.assertIs(df.linear_model.Lasso, lm.Lasso)
        self.assertIs(df.linear_model.LassoCV, lm.LassoCV)
        self.assertIs(df.linear_model.LassoLars, lm.LassoLars)
        self.assertIs(df.linear_model.LassoLarsCV, lm.LassoLarsCV)
        self.assertIs(df.linear_model.LassoLarsIC, lm.LassoLarsIC)

        self.assertIs(df.linear_model.LinearRegression, lm.LinearRegression)
        self.assertIs(df.linear_model.LogisticRegression, lm.LogisticRegression)
        self.assertIs(df.linear_model.LogisticRegressionCV, lm.LogisticRegressionCV)
        self.assertIs(df.linear_model.MultiTaskLasso, lm.MultiTaskLasso)
        self.assertIs(df.linear_model.MultiTaskElasticNet, lm.MultiTaskElasticNet)
        self.assertIs(df.linear_model.MultiTaskLassoCV, lm.MultiTaskLassoCV)
        self.assertIs(df.linear_model.MultiTaskElasticNetCV, lm.MultiTaskElasticNetCV)

        self.assertIs(df.linear_model.OrthogonalMatchingPursuit, lm.OrthogonalMatchingPursuit)
        self.assertIs(df.linear_model.OrthogonalMatchingPursuitCV, lm.OrthogonalMatchingPursuitCV)
        self.assertIs(df.linear_model.PassiveAggressiveClassifier, lm.PassiveAggressiveClassifier)
        self.assertIs(df.linear_model.PassiveAggressiveRegressor, lm.PassiveAggressiveRegressor)

        self.assertIs(df.linear_model.Perceptron, lm.Perceptron)
        self.assertIs(df.linear_model.RandomizedLasso, lm.RandomizedLasso)
        self.assertIs(df.linear_model.RandomizedLogisticRegression, lm.RandomizedLogisticRegression)
        self.assertIs(df.linear_model.RANSACRegressor, lm.RANSACRegressor)
        self.assertIs(df.linear_model.Ridge, lm.Ridge)
        self.assertIs(df.linear_model.RidgeClassifier, lm.RidgeClassifier)
        self.assertIs(df.linear_model.RidgeClassifierCV, lm.RidgeClassifierCV)
        self.assertIs(df.linear_model.RidgeCV, lm.RidgeCV)
        self.assertIs(df.linear_model.SGDClassifier, lm.SGDClassifier)
        self.assertIs(df.linear_model.SGDRegressor, lm.SGDRegressor)
        self.assertIs(df.linear_model.TheilSenRegressor, lm.TheilSenRegressor) 

def getSKLearnModel(modelName):
    if modelName == 'LinearRegression':
        model = linear_model.LinearRegression()
    elif modelName == 'BayesianRidge':
        model = linear_model.BayesianRidge()
    elif modelName == 'ARDRegression':
        model = linear_model.ARDRegression()
    elif modelName == 'ElasticNet':
        model = linear_model.ElasticNet()
    elif modelName == 'HuberRegressor':
        model = linear_model.HuberRegressor()
    elif modelName == 'Lasso':
        model = linear_model.Lasso()
    elif modelName == 'LassoLars':
        model = linear_model.LassoLars()
    elif modelName == 'Rigid':
        model = linear_model.Ridge()
    elif modelName == 'SGDRegressor':
        model = linear_model.SGDRegressor()
    elif modelName == 'SVR':
        model = SVR()
    elif modelName=='MLPClassifier':
        model = MLPClassifier()
    elif modelName=='KNeighborsClassifier':
        model = KNeighborsClassifier()
    elif modelName=='SVC':
        model = SVC()
    elif modelName=='GaussianProcessClassifier':
        model = GaussianProcessClassifier()
    elif modelName=='DecisionTreeClassifier':
        model = DecisionTreeClassifier()
    elif modelName=='RandomForestClassifier':
        model = RandomForestClassifier()
    elif modelName=='AdaBoostClassifier':
        model = AdaBoostClassifier()
    elif modelName=='GaussianNB':
        model = GaussianNB()
    elif modelName=='LogisticRegression':
        model = linear_model.LogisticRegression()
    elif modelName=='QuadraticDiscriminantAnalysis':
        model = QuadraticDiscriminantAnalysis()

    return model 

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_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)