Python sklearn.linear_model.LassoLarsIC() Examples

def test_LassoCV(self, criterion):
        diabetes = datasets.load_diabetes()
        X = diabetes.data
        y = diabetes.target

        X = pp.normalize(X)

        df = pdml.ModelFrame(diabetes)
        df.data = df.data.pp.normalize()

        mod1 = lm.LassoLarsIC(criterion=criterion)
        mod1.fit(X, y)

        mod2 = df.lm.LassoLarsIC(criterion=criterion)
        df.fit(mod2)
        self.assertAlmostEqual(mod1.alpha_, mod2.alpha_)

        expected = mod1.predict(X)
        predicted = df.predict(mod2)
        self.assertIsInstance(predicted, pdml.ModelSeries)
        self.assert_numpy_array_almost_equal(predicted.values, expected) 

def test_lasso_lars_ic():
    # Test the LassoLarsIC object by checking that
    # - some good features are selected.
    # - alpha_bic > alpha_aic
    # - n_nonzero_bic < n_nonzero_aic
    lars_bic = linear_model.LassoLarsIC('bic')
    lars_aic = linear_model.LassoLarsIC('aic')
    rng = np.random.RandomState(42)
    X = diabetes.data
    X = np.c_[X, rng.randn(X.shape[0], 5)]  # add 5 bad features
    lars_bic.fit(X, y)
    lars_aic.fit(X, y)
    nonzero_bic = np.where(lars_bic.coef_)[0]
    nonzero_aic = np.where(lars_aic.coef_)[0]
    assert_greater(lars_bic.alpha_, lars_aic.alpha_)
    assert_less(len(nonzero_bic), len(nonzero_aic))
    assert_less(np.max(nonzero_bic), diabetes.data.shape[1])

    # test error on unknown IC
    lars_broken = linear_model.LassoLarsIC('<unknown>')
    assert_raises(ValueError, lars_broken.fit, X, y) 

def test_estimatorclasses_positive_constraint():
    # testing the transmissibility for the positive option of all estimator
    # classes in this same function here
    default_parameter = {'fit_intercept': False}

    estimator_parameter_map = {'LassoLars': {'alpha': 0.1},
                               'LassoLarsCV': {},
                               'LassoLarsIC': {}}
    for estname in estimator_parameter_map:
        params = default_parameter.copy()
        params.update(estimator_parameter_map[estname])
        estimator = getattr(linear_model, estname)(positive=False, **params)
        estimator.fit(X, y)
        assert estimator.coef_.min() < 0
        estimator = getattr(linear_model, estname)(positive=True, **params)
        estimator.fit(X, y)
        assert min(estimator.coef_) >= 0 

def test_lasso_lars_ic():
    # Test the LassoLarsIC object by checking that
    # - some good features are selected.
    # - alpha_bic > alpha_aic
    # - n_nonzero_bic < n_nonzero_aic
    lars_bic = linear_model.LassoLarsIC('bic')
    lars_aic = linear_model.LassoLarsIC('aic')
    rng = np.random.RandomState(42)
    X = diabetes.data
    y = diabetes.target
    X = np.c_[X, rng.randn(X.shape[0], 5)]  # add 5 bad features
    lars_bic.fit(X, y)
    lars_aic.fit(X, y)
    nonzero_bic = np.where(lars_bic.coef_)[0]
    nonzero_aic = np.where(lars_aic.coef_)[0]
    assert_greater(lars_bic.alpha_, lars_aic.alpha_)
    assert_less(len(nonzero_bic), len(nonzero_aic))
    assert_less(np.max(nonzero_bic), diabetes.data.shape[1])

    # test error on unknown IC
    lars_broken = linear_model.LassoLarsIC('<unknown>')
    assert_raises(ValueError, lars_broken.fit, X, y) 

def test_lasso_lars_copyX_behaviour(copy_X):
    """
    Test that user input regarding copy_X is not being overridden (it was until
    at least version 0.21)

    """
    lasso_lars = LassoLarsIC(copy_X=copy_X, precompute=False)
    rng = np.random.RandomState(0)
    X = rng.normal(0, 1, (100, 5))
    X_copy = X.copy()
    y = X[:, 2]
    lasso_lars.fit(X, y)
    assert copy_X == np.array_equal(X, X_copy) 

def test_lasso_lars_fit_copyX_behaviour(copy_X):
    """
    Test that user input to .fit for copy_X overrides default __init__ value

    """
    lasso_lars = LassoLarsIC(precompute=False)
    rng = np.random.RandomState(0)
    X = rng.normal(0, 1, (100, 5))
    X_copy = X.copy()
    y = X[:, 2]
    lasso_lars.fit(X, y, copy_X=copy_X)
    assert copy_X == np.array_equal(X, X_copy) 

def test_model_lasso_lars_ic(self):
        model, X = fit_regression_model(linear_model.LassoLarsIC())
        model_onnx = convert_sklearn(
            model, "lasso lars cv",
            [("input", FloatTensorType([None, X.shape[1]]))])
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X,
            model,
            model_onnx,
            basename="SklearnLassoLarsIC-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 test_lars_precompute():
    # Check for different values of precompute
    X, y = diabetes.data, diabetes.target
    G = np.dot(X.T, X)
    for classifier in [linear_model.Lars, linear_model.LarsCV,
                       linear_model.LassoLarsIC]:
        clf = classifier(precompute=G)
        output_1 = ignore_warnings(clf.fit)(X, y).coef_
        for precompute in [True, False, 'auto', None]:
            clf = classifier(precompute=precompute)
            output_2 = clf.fit(X, y).coef_
            assert_array_almost_equal(output_1, output_2, decimal=8)