Python sklearn.linear_model.Lars() Examples

def test_multitarget():
    # Assure that estimators receiving multidimensional y do the right thing
    Y = np.vstack([y, y ** 2]).T
    n_targets = Y.shape[1]
    estimators = [
        linear_model.LassoLars(),
        linear_model.Lars(),
        # regression test for gh-1615
        linear_model.LassoLars(fit_intercept=False),
        linear_model.Lars(fit_intercept=False),
    ]

    for estimator in estimators:
        estimator.fit(X, Y)
        Y_pred = estimator.predict(X)
        alphas, active, coef, path = (estimator.alphas_, estimator.active_,
                                      estimator.coef_, estimator.coef_path_)
        for k in range(n_targets):
            estimator.fit(X, Y[:, k])
            y_pred = estimator.predict(X)
            assert_array_almost_equal(alphas[k], estimator.alphas_)
            assert_array_almost_equal(active[k], estimator.active_)
            assert_array_almost_equal(coef[k], estimator.coef_)
            assert_array_almost_equal(path[k], estimator.coef_path_)
            assert_array_almost_equal(Y_pred[:, k], y_pred) 

def get_model(PARAMS):
    '''Get model according to parameters'''
    model_dict = {
        'LinearRegression': LinearRegression(),
        'Ridge': Ridge(),
        'Lars': Lars(),
        'ARDRegression': ARDRegression()

    }
    if not model_dict.get(PARAMS['model_name']):
        LOG.exception('Not supported model!')
        exit(1)

    model = model_dict[PARAMS['model_name']]
    model.normalize = bool(PARAMS['normalize'])

    return model 

def test_lars_lstsq():
    # Test that Lars gives least square solution at the end
    # of the path
    X1 = 3 * X  # use un-normalized dataset
    clf = linear_model.LassoLars(alpha=0.)
    clf.fit(X1, y)
    # Avoid FutureWarning about default value change when numpy >= 1.14
    rcond = None if LooseVersion(np.__version__) >= '1.14' else -1
    coef_lstsq = np.linalg.lstsq(X1, y, rcond=rcond)[0]
    assert_array_almost_equal(clf.coef_, coef_lstsq) 

def test_multitarget():
    # Assure that estimators receiving multidimensional y do the right thing
    X = diabetes.data
    Y = np.vstack([diabetes.target, diabetes.target ** 2]).T
    n_targets = Y.shape[1]
    estimators = [
        linear_model.LassoLars(),
        linear_model.Lars(),
        # regression test for gh-1615
        linear_model.LassoLars(fit_intercept=False),
        linear_model.Lars(fit_intercept=False),
    ]

    for estimator in estimators:
        estimator.fit(X, Y)
        Y_pred = estimator.predict(X)
        alphas, active, coef, path = (estimator.alphas_, estimator.active_,
                                      estimator.coef_, estimator.coef_path_)
        for k in range(n_targets):
            estimator.fit(X, Y[:, k])
            y_pred = estimator.predict(X)
            assert_array_almost_equal(alphas[k], estimator.alphas_)
            assert_array_almost_equal(active[k], estimator.active_)
            assert_array_almost_equal(coef[k], estimator.coef_)
            assert_array_almost_equal(path[k], estimator.coef_path_)
            assert_array_almost_equal(Y_pred[:, k], y_pred) 

def test_lars_n_nonzero_coefs(verbose=False):
    lars = linear_model.Lars(n_nonzero_coefs=6, verbose=verbose)
    lars.fit(X, y)
    assert_equal(len(lars.coef_.nonzero()[0]), 6)
    # The path should be of length 6 + 1 in a Lars going down to 6
    # non-zero coefs
    assert_equal(len(lars.alphas_), 7) 

def test_lasso_lars_vs_lasso_cd_ill_conditioned2():
    # Create an ill-conditioned situation in which the LARS has to go
    # far in the path to converge, and check that LARS and coordinate
    # descent give the same answers
    # Note it used to be the case that Lars had to use the drop for good
    # strategy for this but this is no longer the case with the
    # equality_tolerance checks
    X = [[1e20, 1e20, 0],
         [-1e-32, 0, 0],
         [1, 1, 1]]
    y = [10, 10, 1]
    alpha = .0001

    def objective_function(coef):
        return (1. / (2. * len(X)) * linalg.norm(y - np.dot(X, coef)) ** 2
                + alpha * linalg.norm(coef, 1))

    lars = linear_model.LassoLars(alpha=alpha, normalize=False)
    assert_warns(ConvergenceWarning, lars.fit, X, y)
    lars_coef_ = lars.coef_
    lars_obj = objective_function(lars_coef_)

    coord_descent = linear_model.Lasso(alpha=alpha, tol=1e-4, normalize=False)
    cd_coef_ = coord_descent.fit(X, y).coef_
    cd_obj = objective_function(cd_coef_)

    assert_less(lars_obj, cd_obj * (1. + 1e-8)) 

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) 

def test_lasso_gives_lstsq_solution():
    # Test that Lars Lasso gives least square solution at the end
    # of the path
    alphas_, active, coef_path_ = linear_model.lars_path(X, y, method="lasso")
    coef_lstsq = np.linalg.lstsq(X, y)[0]
    assert_array_almost_equal(coef_lstsq, coef_path_[:, -1]) 

def test_lars_lstsq():
    # Test that Lars gives least square solution at the end
    # of the path
    X1 = 3 * diabetes.data  # use un-normalized dataset
    clf = linear_model.LassoLars(alpha=0.)
    clf.fit(X1, y)
    coef_lstsq = np.linalg.lstsq(X1, y)[0]
    assert_array_almost_equal(clf.coef_, coef_lstsq) 

def test_simple():
    # Principle of Lars is to keep covariances tied and decreasing

    # also test verbose output
    from sklearn.externals.six.moves import cStringIO as StringIO
    import sys
    old_stdout = sys.stdout
    try:
        sys.stdout = StringIO()

        alphas_, active, coef_path_ = linear_model.lars_path(
            diabetes.data, diabetes.target, method="lar", verbose=10)

        sys.stdout = old_stdout

        for (i, coef_) in enumerate(coef_path_.T):
            res = y - np.dot(X, coef_)
            cov = np.dot(X.T, res)
            C = np.max(abs(cov))
            eps = 1e-3
            ocur = len(cov[C - eps < abs(cov)])
            if i < X.shape[1]:
                assert_true(ocur == i + 1)
            else:
                # no more than max_pred variables can go into the active set
                assert_true(ocur == X.shape[1])
    finally:
        sys.stdout = old_stdout 

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_model_lars(self):
        model, X = fit_regression_model(linear_model.Lars())
        model_onnx = convert_sklearn(
            model, "lars",
            [("input", FloatTensorType([None, X.shape[1]]))])
        self.assertIsNotNone(model_onnx)
        dump_data_and_model(
            X,
            model,
            model_onnx,
            basename="SklearnLars-Dec4",
            allow_failure="StrictVersion("
            "onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

def _create_regressor(self):
        if self.mode == 'default':
            return Lars()
        if self.mode == 'lasso':
            return LassoLars(alpha=self.alpha)
        raise ValueError('Unexpected mode ' + self.mode + '. Expected "default" or "lasso"') 

def test_lars_add_features():
    # assure that at least some features get added if necessary
    # test for 6d2b4c
    # Hilbert matrix
    n = 5
    H = 1. / (np.arange(1, n + 1) + np.arange(n)[:, np.newaxis])
    clf = linear_model.Lars(fit_intercept=False).fit(
        H, np.arange(n))
    assert np.all(np.isfinite(clf.coef_)) 

def test_lasso_lars_vs_lasso_cd_ill_conditioned2():
    # Create an ill-conditioned situation in which the LARS has to go
    # far in the path to converge, and check that LARS and coordinate
    # descent give the same answers
    # Note it used to be the case that Lars had to use the drop for good
    # strategy for this but this is no longer the case with the
    # equality_tolerance checks
    X = [[1e20, 1e20, 0],
         [-1e-32, 0, 0],
         [1, 1, 1]]
    y = [10, 10, 1]
    alpha = .0001

    def objective_function(coef):
        return (1. / (2. * len(X)) * linalg.norm(y - np.dot(X, coef)) ** 2
                + alpha * linalg.norm(coef, 1))

    lars = linear_model.LassoLars(alpha=alpha, normalize=False)
    assert_warns(ConvergenceWarning, lars.fit, X, y)
    lars_coef_ = lars.coef_
    lars_obj = objective_function(lars_coef_)

    coord_descent = linear_model.Lasso(alpha=alpha, tol=1e-4, normalize=False)
    cd_coef_ = coord_descent.fit(X, y).coef_
    cd_obj = objective_function(cd_coef_)

    assert_less(lars_obj, cd_obj * (1. + 1e-8)) 

def test_lasso_gives_lstsq_solution():
    # Test that Lars Lasso gives least square solution at the end
    # of the path
    _, _, coef_path_ = linear_model.lars_path(X, y, method='lasso')
    coef_lstsq = np.linalg.lstsq(X, y)[0]
    assert_array_almost_equal(coef_lstsq, coef_path_[:, -1]) 

def test_simple():
    # Principle of Lars is to keep covariances tied and decreasing

    # also test verbose output
    from io import StringIO
    import sys
    old_stdout = sys.stdout
    try:
        sys.stdout = StringIO()

        _, _, coef_path_ = linear_model.lars_path(
            X, y, method='lar', verbose=10)

        sys.stdout = old_stdout

        for i, coef_ in enumerate(coef_path_.T):
            res = y - np.dot(X, coef_)
            cov = np.dot(X.T, res)
            C = np.max(abs(cov))
            eps = 1e-3
            ocur = len(cov[C - eps < abs(cov)])
            if i < X.shape[1]:
                assert ocur == i + 1
            else:
                # no more than max_pred variables can go into the active set
                assert ocur == X.shape[1]
    finally:
        sys.stdout = old_stdout 

def mcfs(X, n_selected_features, **kwargs):
    """
    This function implements unsupervised feature selection for multi-cluster data.

    Input
    -----
    X: {numpy array}, shape (n_samples, n_features)
        input data
    n_selected_features: {int}
        number of features to select
    kwargs: {dictionary}
        W: {sparse matrix}, shape (n_samples, n_samples)
            affinity matrix
        n_clusters: {int}
            number of clusters (default is 5)

    Output
    ------
    W: {numpy array}, shape(n_features, n_clusters)
        feature weight matrix

    Reference
    ---------
    Cai, Deng et al. "Unsupervised Feature Selection for Multi-Cluster Data." KDD 2010.
    """

    # use the default affinity matrix
    if 'W' not in kwargs:
        W = construct_W(X)
    else:
        W = kwargs['W']
    # default number of clusters is 5
    if 'n_clusters' not in kwargs:
        n_clusters = 5
    else:
        n_clusters = kwargs['n_clusters']

    # solve the generalized eigen-decomposition problem and get the top K
    # eigen-vectors with respect to the smallest eigenvalues
    W = W.toarray()
    W = (W + W.T) / 2
    W_norm = np.diag(np.sqrt(1 / W.sum(1)))
    W = np.dot(W_norm, np.dot(W, W_norm))
    WT = W.T
    W[W < WT] = WT[W < WT]
    eigen_value, ul = scipy.linalg.eigh(a=W)
    Y = np.dot(W_norm, ul[:, -1*n_clusters-1:-1])

    # solve K L1-regularized regression problem using LARs algorithm with cardinality constraint being d
    n_sample, n_feature = X.shape
    W = np.zeros((n_feature, n_clusters))
    for i in range(n_clusters):
        clf = linear_model.Lars(n_nonzero_coefs=n_selected_features)
        clf.fit(X, Y[:, i])
        W[:, i] = clf.coef_
    return W 

def test_lasso_lars_vs_lasso_cd_positive():
    # Test that LassoLars and Lasso using coordinate descent give the
    # same results when using the positive option

    # This test is basically a copy of the above with additional positive
    # option. However for the middle part, the comparison of coefficient values
    # for a range of alphas, we had to make an adaptations. See below.

    # not normalized data
    X = 3 * diabetes.data

    alphas, _, lasso_path = linear_model.lars_path(X, y, method='lasso',
                                                   positive=True)
    lasso_cd = linear_model.Lasso(fit_intercept=False, tol=1e-8, positive=True)
    for c, a in zip(lasso_path.T, alphas):
        if a == 0:
            continue
        lasso_cd.alpha = a
        lasso_cd.fit(X, y)
        error = linalg.norm(c - lasso_cd.coef_)
        assert_less(error, 0.01)

    # The range of alphas chosen for coefficient comparison here is restricted
    # as compared with the above test without the positive option. This is due
    # to the circumstance that the Lars-Lasso algorithm does not converge to
    # the least-squares-solution for small alphas, see 'Least Angle Regression'
    # by Efron et al 2004. The coefficients are typically in congruence up to
    # the smallest alpha reached by the Lars-Lasso algorithm and start to
    # diverge thereafter.  See
    # https://gist.github.com/michigraber/7e7d7c75eca694c7a6ff

    for alpha in np.linspace(6e-1, 1 - 1e-2, 20):
        clf1 = linear_model.LassoLars(fit_intercept=False, alpha=alpha,
                                      normalize=False, positive=True).fit(X, y)
        clf2 = linear_model.Lasso(fit_intercept=False, alpha=alpha, tol=1e-8,
                                  normalize=False, positive=True).fit(X, y)
        err = linalg.norm(clf1.coef_ - clf2.coef_)
        assert_less(err, 1e-3)

    # normalized data
    X = diabetes.data
    alphas, _, lasso_path = linear_model.lars_path(X, y, method='lasso',
                                                   positive=True)
    lasso_cd = linear_model.Lasso(fit_intercept=False, normalize=True,
                                  tol=1e-8, positive=True)
    for c, a in zip(lasso_path.T[:-1], alphas[:-1]):  # don't include alpha=0
        lasso_cd.alpha = a
        lasso_cd.fit(X, y)
        error = linalg.norm(c - lasso_cd.coef_)
        assert_less(error, 0.01) 

def test_lasso_lars_vs_lasso_cd_positive(verbose=False):
    # Test that LassoLars and Lasso using coordinate descent give the
    # same results when using the positive option

    # This test is basically a copy of the above with additional positive
    # option. However for the middle part, the comparison of coefficient values
    # for a range of alphas, we had to make an adaptations. See below.

    # not normalized data
    X = 3 * diabetes.data

    alphas, _, lasso_path = linear_model.lars_path(X, y, method='lasso',
                                                   positive=True)
    lasso_cd = linear_model.Lasso(fit_intercept=False, tol=1e-8, positive=True)
    for c, a in zip(lasso_path.T, alphas):
        if a == 0:
            continue
        lasso_cd.alpha = a
        lasso_cd.fit(X, y)
        error = linalg.norm(c - lasso_cd.coef_)
        assert_less(error, 0.01)

    # The range of alphas chosen for coefficient comparison here is restricted
    # as compared with the above test without the positive option. This is due
    # to the circumstance that the Lars-Lasso algorithm does not converge to
    # the least-squares-solution for small alphas, see 'Least Angle Regression'
    # by Efron et al 2004. The coefficients are typically in congruence up to
    # the smallest alpha reached by the Lars-Lasso algorithm and start to
    # diverge thereafter.  See
    # https://gist.github.com/michigraber/7e7d7c75eca694c7a6ff

    for alpha in np.linspace(6e-1, 1 - 1e-2, 20):
        clf1 = linear_model.LassoLars(fit_intercept=False, alpha=alpha,
                                      normalize=False, positive=True).fit(X, y)
        clf2 = linear_model.Lasso(fit_intercept=False, alpha=alpha, tol=1e-8,
                                  normalize=False, positive=True).fit(X, y)
        err = linalg.norm(clf1.coef_ - clf2.coef_)
        assert_less(err, 1e-3)

    # normalized data
    X = diabetes.data
    alphas, _, lasso_path = linear_model.lars_path(X, y, method='lasso',
                                                   positive=True)
    lasso_cd = linear_model.Lasso(fit_intercept=False, normalize=True,
                                  tol=1e-8, positive=True)
    for c, a in zip(lasso_path.T[:-1], alphas[:-1]):  # don't include alpha=0
        lasso_cd.alpha = a
        lasso_cd.fit(X, y)
        error = linalg.norm(c - lasso_cd.coef_)
        assert_less(error, 0.01)