Python linear_model.LassoLarsCV方法代码示例

# 需要导入模块: from sklearn import linear_model [as 别名]
# 或者: from sklearn.linear_model import LassoLarsCV [as 别名]
def test_few_fit_shapes():
    """test_few.py: fit and predict return correct shapes """
    np.random.seed(202)
    # load example data
    boston = load_boston()
    d = pd.DataFrame(data=boston.data)
    print("feature shape:",boston.data.shape)

    learner = FEW(generations=1, population_size=5,
                mutation_rate=0.2, crossover_rate=0.8,
                ml = LassoLarsCV(), min_depth = 1, max_depth = 3,
                sel = 'epsilon_lexicase', tourn_size = 2,
                random_state=0, verbosity=0,
                disable_update_check=False, fit_choice = 'mse')

    score = learner.fit(boston.data[:300], boston.target[:300])
    print("learner:",learner._best_estimator)
    yhat_test = learner.predict(boston.data[300:])
    test_score = learner.score(boston.data[300:],boston.target[300:])
    print("train score:",score,"test score:",test_score,
    "test r2:",r2_score(boston.target[300:],yhat_test))
    assert yhat_test.shape == boston.target[300:].shape 

# 需要导入模块: from sklearn import linear_model [as 别名]
# 或者: from sklearn.linear_model import LassoLarsCV [as 别名]
def test_few_with_parents_weight():
    """test_few.py: few performs without error with parent pressure for selection"""
    np.random.seed(1006987)
    boston = load_boston()
    d = np.column_stack((boston.data,boston.target))
    np.random.shuffle(d)
    features = d[:,0:-1]
    target = d[:,-1]

    print("feature shape:",boston.data.shape)

    learner = FEW(generations=1, population_size=5,
                mutation_rate=1, crossover_rate=1,
                ml = LassoLarsCV(), min_depth = 1, max_depth = 3,
                sel = 'tournament', fit_choice = 'r2',tourn_size = 2, random_state=0, verbosity=0,
                disable_update_check=False, weight_parents=True)

    learner.fit(features[:300], target[:300])
    few_score = learner.score(features[:300], target[:300])
    test_score = learner.score(features[300:],target[300:])

    print("few score:",few_score)
    print("few test score:",test_score) 

# 需要导入模块: from sklearn import linear_model [as 别名]
# 或者: from sklearn.linear_model import LassoLarsCV [as 别名]
def test_lars_cv_max_iter(recwarn):
    warnings.simplefilter('always')
    with np.errstate(divide='raise', invalid='raise'):
        X = diabetes.data
        y = diabetes.target
        rng = np.random.RandomState(42)
        x = rng.randn(len(y))
        X = diabetes.data
        X = np.c_[X, x, x]  # add correlated features
        lars_cv = linear_model.LassoLarsCV(max_iter=5, cv=5)
        lars_cv.fit(X, y)
    # Check that there is no warning in general and no ConvergenceWarning
    # in particular.
    # Materialize the string representation of the warning to get a more
    # informative error message in case of AssertionError.
    recorded_warnings = [str(w) for w in recwarn]
    assert recorded_warnings == [] 

# 需要导入模块: from sklearn import linear_model [as 别名]
# 或者: from sklearn.linear_model import LassoLarsCV [as 别名]
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 

# 需要导入模块: from sklearn import linear_model [as 别名]
# 或者: from sklearn.linear_model import LassoLarsCV [as 别名]
def test_lasso_cv():
    X, y, X_test, y_test = build_dataset()
    max_iter = 150
    clf = LassoCV(n_alphas=10, eps=1e-3, max_iter=max_iter).fit(X, y)
    assert_almost_equal(clf.alpha_, 0.056, 2)

    clf = LassoCV(n_alphas=10, eps=1e-3, max_iter=max_iter, precompute=True)
    clf.fit(X, y)
    assert_almost_equal(clf.alpha_, 0.056, 2)

    # Check that the lars and the coordinate descent implementation
    # select a similar alpha
    lars = LassoLarsCV(normalize=False, max_iter=30).fit(X, y)
    # for this we check that they don't fall in the grid of
    # clf.alphas further than 1
    assert np.abs(np.searchsorted(clf.alphas_[::-1], lars.alpha_) -
                  np.searchsorted(clf.alphas_[::-1], clf.alpha_)) <= 1
    # check that they also give a similar MSE
    mse_lars = interpolate.interp1d(lars.cv_alphas_, lars.mse_path_.T)
    np.testing.assert_approx_equal(mse_lars(clf.alphas_[5]).mean(),
                                   clf.mse_path_[5].mean(), significant=2)

    # test set
    assert_greater(clf.score(X_test, y_test), 0.99) 

# 需要导入模块: from sklearn import linear_model [as 别名]
# 或者: from sklearn.linear_model import LassoLarsCV [as 别名]
def fit_ensemble(x,y):
    fit_type = jhkaggle.jhkaggle_config['FIT_TYPE']
    if 1:
        if fit_type == jhkaggle.const.FIT_TYPE_BINARY_CLASSIFICATION:
            blend = SGDClassifier(loss="log", penalty="elasticnet")  # LogisticRegression()
        else:
            # blend = SGDRegressor()
            #blend = LinearRegression()
            #blend = RandomForestRegressor(n_estimators=10, n_jobs=-1, max_depth=5, criterion='mae')
            blend = LassoLarsCV(normalize=True)
            #blend = ElasticNetCV(normalize=True)
            #blend = LinearRegression(normalize=True)
        blend.fit(x, y)
    else:
        blend = LogisticRegression()
        blend.fit(x, y)


    return blend 

# 需要导入模块: from sklearn import linear_model [as 别名]
# 或者: from sklearn.linear_model import LassoLarsCV [as 别名]
def test_lasso_cv():
    X, y, X_test, y_test = build_dataset()
    max_iter = 150
    clf = LassoCV(n_alphas=10, eps=1e-3, max_iter=max_iter).fit(X, y)
    assert_almost_equal(clf.alpha_, 0.056, 2)

    clf = LassoCV(n_alphas=10, eps=1e-3, max_iter=max_iter, precompute=True)
    clf.fit(X, y)
    assert_almost_equal(clf.alpha_, 0.056, 2)

    # Check that the lars and the coordinate descent implementation
    # select a similar alpha
    lars = LassoLarsCV(normalize=False, max_iter=30).fit(X, y)
    # for this we check that they don't fall in the grid of
    # clf.alphas further than 1
    assert_true(np.abs(
        np.searchsorted(clf.alphas_[::-1], lars.alpha_) -
        np.searchsorted(clf.alphas_[::-1], clf.alpha_)) <= 1)
    # check that they also give a similar MSE
    mse_lars = interpolate.interp1d(lars.cv_alphas_, lars.mse_path_.T)
    np.testing.assert_approx_equal(mse_lars(clf.alphas_[5]).mean(),
                                   clf.mse_path_[5].mean(), significant=2)

    # test set
    assert_greater(clf.score(X_test, y_test), 0.99) 

# 需要导入模块: from sklearn import linear_model [as 别名]
# 或者: from sklearn.linear_model import LassoLarsCV [as 别名]
def test_few_at_least_as_good_as_default():
    """test_few.py: few performs at least as well as the default ML """
    np.random.seed(1006987)
    boston = load_boston()
    d = np.column_stack((boston.data,boston.target))
    np.random.shuffle(d)
    features = d[:,0:-1]
    target = d[:,-1]

    print("feature shape:",boston.data.shape)

    learner = FEW(generations=1, population_size=5,
                ml = LassoLarsCV(), min_depth = 1, max_depth = 3,
                sel = 'tournament')

    learner.fit(features[:300], target[:300])
    few_score = learner.score(features[:300], target[:300])
    few_test_score = learner.score(features[300:],target[300:])

    lasso = LassoLarsCV()
    lasso.fit(features[:300], target[:300])
    lasso_score = lasso.score(features[:300], target[:300])
    lasso_test_score = lasso.score(features[300:],target[300:])
    print("few score:",few_score,"lasso score:",lasso_score)
    print("few test score:",few_test_score,"lasso test score:",
          lasso_test_score)
    assert round(few_score,8) >= round(lasso_score,8)

    print("lasso coefficients:",lasso.coef_)

    # assert False 

# 需要导入模块: from sklearn import linear_model [as 别名]
# 或者: from sklearn.linear_model import LassoLarsCV [as 别名]
def test_lars_cv():
    # Test the LassoLarsCV object by checking that the optimal alpha
    # increases as the number of samples increases.
    # This property is not actually guaranteed in general and is just a
    # property of the given dataset, with the given steps chosen.
    old_alpha = 0
    lars_cv = linear_model.LassoLarsCV()
    for length in (400, 200, 100):
        X = diabetes.data[:length]
        y = diabetes.target[:length]
        lars_cv.fit(X, y)
        np.testing.assert_array_less(old_alpha, lars_cv.alpha_)
        old_alpha = lars_cv.alpha_
    assert not hasattr(lars_cv, 'n_nonzero_coefs') 

# 需要导入模块: from sklearn import linear_model [as 别名]
# 或者: from sklearn.linear_model import LassoLarsCV [as 别名]
def _fit_model(x, y, names, operators, **kw):
    steps = [("trafo", LibTrafo(names, operators)), ("lasso", LassoLarsCV(**kw))]
    model = Pipeline(steps).fit(x, y)
    return model, model.score(x, y) 

# 需要导入模块: from sklearn import linear_model [as 别名]
# 或者: from sklearn.linear_model import LassoLarsCV [as 别名]
def test_model_lasso_lars_cv(self):
        model, X = fit_regression_model(linear_model.LassoLarsCV())
        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="SklearnLassoLarsCV-Dec4",
            allow_failure="StrictVersion("
            "onnxruntime.__version__)"
            "<= StrictVersion('0.2.1')",
        ) 

# 需要导入模块: from sklearn import linear_model [as 别名]
# 或者: from sklearn.linear_model import LassoLarsCV [as 别名]
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) 

# 需要导入模块: from sklearn import linear_model [as 别名]
# 或者: from sklearn.linear_model import LassoLarsCV [as 别名]
def test_lars_cv():
    # Test the LassoLarsCV object by checking that the optimal alpha
    # increases as the number of samples increases.
    # This property is not actually guaranteed in general and is just a
    # property of the given dataset, with the given steps chosen.
    old_alpha = 0
    lars_cv = linear_model.LassoLarsCV()
    for length in (400, 200, 100):
        X = diabetes.data[:length]
        y = diabetes.target[:length]
        lars_cv.fit(X, y)
        np.testing.assert_array_less(old_alpha, lars_cv.alpha_)
        old_alpha = lars_cv.alpha_
    assert_false(hasattr(lars_cv, 'n_nonzero_coefs')) 

# 需要导入模块: from sklearn import linear_model [as 别名]
# 或者: from sklearn.linear_model import LassoLarsCV [as 别名]
def test_lars_cv_max_iter():
    with warnings.catch_warnings(record=True) as w:
        X = diabetes.data
        y = diabetes.target
        rng = np.random.RandomState(42)
        x = rng.randn(len(y))
        X = np.c_[X, x, x]  # add correlated features
        lars_cv = linear_model.LassoLarsCV(max_iter=5)
        lars_cv.fit(X, y)
    assert_true(len(w) == 0)