Python sklearn.linear_model 模块，LassoLarsCV() 实例源码

def train_lassolars_model(train_x, train_y, predict_x):
    print_title("LassoLars Regressor")
    reg = linear_model.LassoLarsCV(
        cv=10, n_jobs=3, max_iter=2000, normalize=False)
    reg.fit(train_x, train_y)
    print("alphas and cv_alphas: {0} and {1}".format(
        reg.alphas_.shape, reg.cv_alphas_.shape))
    print("alphas[%d]: %s" % (len(reg.cv_alphas_), reg.cv_alphas_))
    print("mse shape: {0}".format(reg.cv_mse_path_.shape))
    # print("mse: %s" % np.mean(_mse, axis=0))
    # print("mse: %s" % np.mean(_mse, axis=1))
    # index = np.where(reg.alphas_ == reg.alpha_)
    # print("itemindex: %s" % index)
    index = np.where(reg.cv_alphas_ == reg.alpha_)
    _mse_v = np.mean(reg.cv_mse_path_[index, :])
    print("mse value: %f" % _mse_v)

    print("best alpha: %f" % reg.alpha_)
    best_alpha = reg.alpha_
    reg = linear_model.LassoLars(alpha=best_alpha)
    reg.fit(train_x, train_y)
    n_nonzeros = (reg.coef_ != 0).sum()
    print("Non-zeros coef: %d" % n_nonzeros)
    predict_y = reg.predict(predict_x)
    return {'y': predict_y, "coef": reg.coef_}

def test_get_errors_param(self):
        """
        Test known models we can get the cv errors for alpha selection
        """

        # Test original CV models
        for model in (RidgeCV, LassoCV, LassoLarsCV, ElasticNetCV):
            try:
                model = AlphaSelection(model())

                X, y = make_regression()
                model.fit(X, y)

                errors = model._find_errors_param()
                self.assertTrue(len(errors) > 0)
            except YellowbrickValueError:
                self.fail("could not find errors on {}".format(model.name))

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

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)

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.cv_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)

def test_regressor_cv(self):
        """
        Ensure only "CV" regressors are allowed
        """

        for model in (SVR, Ridge, Lasso, LassoLars, ElasticNet):
            with self.assertRaises(YellowbrickTypeError):
                alphas = AlphaSelection(model())

        for model in (RidgeCV, LassoCV, LassoLarsCV, ElasticNetCV):
            try:
                alphas = AlphaSelection(model())
            except YellowbrickTypeError:
                self.fail("could not instantiate RegressorCV on alpha selection")

def test_get_alphas_param_lassolars(self):
        """
        Assert that we can get alphas from lasso lars.
        """
        X, y = make_regression()
        model = AlphaSelection(LassoLarsCV())
        model.fit(X, y)
        try:
            malphas = model._find_alphas_param()
            self.assertTrue(len(malphas) > 0)
        except YellowbrickValueError:
            self.fail("could not find alphas on {}".format(model.name))

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)

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

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_

def lasso_regr(wine_set):

    pred = wine_set[["density", 'alcohol', 'sulphates', 'pH', 'volatile_acidity', 'chlorides', 'fixed_acidity',
                    'citric_acid', 'residual_sugar', 'free_sulfur_dioxide', 'total_sulfur_dioxide']]
    predictors = pred.copy()
    targets = wine_set.quality

    # standardize predictors to have mean=0 and sd=1
    predictors = pd.DataFrame(preprocessing.scale(predictors))
    predictors.columns = pred.columns
    # print(predictors.head())

    # split into training and testing sets
    pred_train, pred_test, tar_train, tar_test = train_test_split(predictors, targets, test_size=.3, random_state=123)

    # specify the lasso regression model
    model = LassoLarsCV(cv=10, precompute=False).fit(pred_train, tar_train)

    print('Predictors and their regression coefficients:')
    d = dict(zip(predictors.columns, model.coef_))
    for k in d:
        print(k, ':', d[k])

    # plot coefficient progression
    m_log_alphas = -np.log10(model.alphas_)
    # ax = plt.gca()
    plt.plot(m_log_alphas, model.coef_path_.T)
    print('\nAlpha:', model.alpha_)
    plt.axvline(-np.log10(model.alpha_), linestyle="dashed", color='k', label='alpha CV')
    plt.ylabel("Regression coefficients")
    plt.xlabel("-log(alpha)")
    plt.title('Regression coefficients progression for Lasso paths')
    plt.show()

    # plot mean squared error for each fold
    m_log_alphascv = -np.log10(model.cv_alphas_)
    plt.plot(m_log_alphascv, model.cv_mse_path_, ':')
    plt.plot(m_log_alphascv, model.cv_mse_path_.mean(axis=-1), 'k', label='Average across the folds', linewidth=2)
    plt.legend()
    plt.xlabel('-log(alpha)')
    plt.ylabel('Mean squared error')
    plt.title('Mean squared error on each fold')
    plt.show()

    # Mean squared error from training and test data
    train_error = mean_squared_error(tar_train, model.predict(pred_train))
    test_error = mean_squared_error(tar_test, model.predict(pred_test))
    print('\nMean squared error for training data:', train_error)
    print('Mean squared error for test data:', test_error)

    rsquared_train = model.score(pred_train, tar_train)
    rsquared_test = model.score(pred_test, tar_test)
    print('\nR-square for training data:', rsquared_train)
    print('R-square for test data:', rsquared_test)
#
# print('----------------Lasso Regression------------------------')
# call(lasso_regr)


# ______________________________K-Means Cluster Analysis_________________