Python sklearn.datasets 模块，load_diabetes() 实例源码

def test_integration_quic_graph_lasso(self, params_in, expected):
        '''
        Just tests inputs/outputs (not validity of result).
        '''
        X = datasets.load_diabetes().data
        ic = QuicGraphLasso(**params_in)
        ic.fit(X)

        result_vec = [
            np.linalg.norm(ic.covariance_),
            np.linalg.norm(ic.precision_),
            np.linalg.norm(ic.opt_),
            np.linalg.norm(ic.duality_gap_),
        ]
        print(result_vec)
        assert_allclose(expected, result_vec, atol=1e-1, rtol=1e-1)

def test_integration_quic_graph_lasso_cv(self, params_in, expected):
        '''
        Just tests inputs/outputs (not validity of result).
        '''
        X = datasets.load_diabetes().data
        ic = QuicGraphLassoCV(**params_in)
        ic.fit(X)

        result_vec = [
            np.linalg.norm(ic.covariance_),
            np.linalg.norm(ic.precision_),
            np.linalg.norm(ic.opt_),
            np.linalg.norm(ic.duality_gap_),
        ]
        if isinstance(ic.lam_, float):
            result_vec.append(ic.lam_)
        elif isinstance(ic.lam_, np.ndarray):
            assert ic.lam_.shape == params_in['lam'].shape

        print(result_vec)
        assert_allclose(expected, result_vec, atol=1e-1, rtol=1e-1)

        assert len(ic.grid_scores) == len(ic.cv_lams_)

def test_integration_quic_graph_lasso_ebic(self, params_in, expected):
        '''
        Just tests inputs/outputs (not validity of result).
        '''
        X = datasets.load_diabetes().data
        ic = QuicGraphLassoEBIC(**params_in)
        ic.fit(X)

        result_vec = [
            np.linalg.norm(ic.covariance_),
            np.linalg.norm(ic.precision_),
        ]
        if isinstance(ic.lam_, float):
            result_vec.append(ic.lam_)
        elif isinstance(ic.lam_, np.ndarray):
            assert ic.lam_.shape == params_in['lam'].shape

        print(result_vec)
        assert_allclose(expected, result_vec, atol=1e-1, rtol=1e-1)

def main():
  diabetes = datasets.load_diabetes()
  diabetes_X = diabetes.data[:, np.newaxis, 2]

  diabetes_X_train = diabetes_X[:-20]
  diabetes_X_test = diabetes_X[-20:]

  diabetes_y_train = diabetes.target[:-20]
  diabetes_y_test = diabetes.target[-20:]

  regr = linear_model.LinearRegression()
  regr.fit(diabetes_X_train, diabetes_y_train)

  print('Coefficients: \n', regr.coef_)
  print("Mean squared error: %.2f" %
        np.mean((regr.predict(diabetes_X_test) - diabetes_y_test)**2))
  print('Variance score: %.2f' % regr.score(diabetes_X_test, diabetes_y_test))

def test_partial_fit():
    data = load_diabetes()
    clf = MLPRegressor(n_epochs=1)

    X, y = data['data'], data['target']

    for _ in range(30):
        clf.partial_fit(X, y)

    y_pred = clf.predict(X)
    assert pearsonr(y_pred, y)[0] > 0.5

def test_embedding_default():
    # Make sure the embedding works by default.
    data = load_diabetes()
    X, y = data['data'], data['target']

    clf = MLPRegressor(n_epochs=1)
    clf.fit(X, y)

    assert clf.transform(X).shape[1] == 256

def test_bayesian_on_diabetes():
    # Test BayesianRidge on diabetes
    raise SkipTest("XFailed Test")
    diabetes = datasets.load_diabetes()
    X, y = diabetes.data, diabetes.target

    clf = BayesianRidge(compute_score=True)

    # Test with more samples than features
    clf.fit(X, y)
    # Test that scores are increasing at each iteration
    assert_array_equal(np.diff(clf.scores_) > 0, True)

    # Test with more features than samples
    X = X[:5, :]
    y = y[:5]
    clf.fit(X, y)
    # Test that scores are increasing at each iteration
    assert_array_equal(np.diff(clf.scores_) > 0, True)

def test_svr():
    # Test Support Vector Regression

    diabetes = datasets.load_diabetes()
    for clf in (svm.NuSVR(kernel='linear', nu=.4, C=1.0),
                svm.NuSVR(kernel='linear', nu=.4, C=10.),
                svm.SVR(kernel='linear', C=10.),
                svm.LinearSVR(C=10.),
                svm.LinearSVR(C=10.),
                ):
        clf.fit(diabetes.data, diabetes.target)
        assert_greater(clf.score(diabetes.data, diabetes.target), 0.02)

    # non-regression test; previously, BaseLibSVM would check that
    # len(np.unique(y)) < 2, which must only be done for SVC
    svm.SVR().fit(diabetes.data, np.ones(len(diabetes.data)))
    svm.LinearSVR().fit(diabetes.data, np.ones(len(diabetes.data)))

def test_integration_quic_graph_lasso_fun(self, params_in, expected):
        '''
        Just tests inputs/outputs (not validity of result).
        '''
        X = datasets.load_diabetes().data
        lam = 0.5
        if 'lam' in params_in:
            lam = params_in['lam']
            del params_in['lam']

        S = np.corrcoef(X, rowvar=False)
        if 'init_method' in params_in:
            if params_in['init_method'] == 'cov':
                S = np.cov(X, rowvar=False)

            del params_in['init_method']

        precision_, covariance_, opt_, cpu_time_, iters_, duality_gap_ =\
            quic(S, lam, **params_in)

        result_vec = [
            np.linalg.norm(covariance_),
            np.linalg.norm(precision_),
            np.linalg.norm(opt_),
            np.linalg.norm(duality_gap_),
        ]
        print(result_vec)
        assert_allclose(expected, result_vec, atol=1e-1, rtol=1e-1)

def test_invalid_method(self):
        '''
        Test behavior of invalid inputs.
        '''
        X = datasets.load_diabetes().data
        ic = QuicGraphLasso(method='unknownmethod')
        assert_raises(NotImplementedError, ic.fit, X)

def read_training(self):
        return datasets.load_diabetes()

def main(dataset_size, test_proportion):
    diabetes = load_diabetes()
    X = diabetes.data[:dataset_size]
    y = diabetes.target[:dataset_size]

    fig, ax_list = plt.subplots(3, 1, figsize=(8, 6))
    plot_errors_by_lambda(X, y, test_proportion=test_proportion, regression_class=Ridge, ax=ax_list[0])
    plot_errors_by_lambda(X, y, test_proportion=test_proportion, regression_class=Lasso, ax=ax_list[1])
    plot_errors_by_lambda(X, y, test_proportion=test_proportion, regression_class=LinearRegression, ax=ax_list[2])

    plt.tight_layout()
    plt.show()

def get_sample_dataset(dataset_properties):
    """Returns sample dataset

    Args:
        dataset_properties (dict): Dictionary corresponding to the properties of the dataset
            used to verify the estimator and metric generators.

    Returns:
        X (array-like): Features array

        y (array-like): Labels array

        splits (iterator): This is an iterator that returns train test splits for
            cross-validation purposes on ``X`` and ``y``.
    """
    kwargs = dataset_properties.copy()
    data_type = kwargs.pop('type')
    if data_type == 'multiclass':
        try:
            X, y = datasets.make_classification(random_state=8, **kwargs)
            splits = model_selection.StratifiedKFold(n_splits=2, random_state=8).split(X, y)
        except Exception as e:
            raise exceptions.UserError(repr(e))
    elif data_type == 'iris':
        X, y = datasets.load_iris(return_X_y=True)
        splits = model_selection.StratifiedKFold(n_splits=2, random_state=8).split(X, y)
    elif data_type == 'mnist':
        X, y = datasets.load_digits(return_X_y=True)
        splits = model_selection.StratifiedKFold(n_splits=2, random_state=8).split(X, y)
    elif data_type == 'breast_cancer':
        X, y = datasets.load_breast_cancer(return_X_y=True)
        splits = model_selection.StratifiedKFold(n_splits=2, random_state=8).split(X, y)
    elif data_type == 'boston':
        X, y = datasets.load_boston(return_X_y=True)
        splits = model_selection.KFold(n_splits=2, random_state=8).split(X)
    elif data_type == 'diabetes':
        X, y = datasets.load_diabetes(return_X_y=True)
        splits = model_selection.KFold(n_splits=2, random_state=8).split(X)
    else:
        raise exceptions.UserError('Unknown dataset type {}'.format(dataset_properties['type']))
    return X, y, splits

def test_replicability():
    """Make sure running fit twice in a row finds the same parameters."""
    diabetes = load_diabetes()
    X_diabetes, y_diabetes = diabetes.data, diabetes.target
    ind = np.arange(X_diabetes.shape[0])
    rng = np.random.RandomState(0)
    rng.shuffle(ind)
    X_diabetes, y_diabetes = X_diabetes[ind], y_diabetes[ind]

    clf = MLPRegressor(keep_prob=0.9, random_state=42, n_epochs=100)
    target = y_diabetes
    # Just predict on the training set, for simplicity.
    pred1 = clf.fit(X_diabetes, target).predict(X_diabetes)
    pred2 = clf.fit(X_diabetes, target).predict(X_diabetes)
    assert_array_almost_equal(pred1, pred2)

def test_embedding_no_layers():
    # Make sure the embedding works with no layers.
    data = load_diabetes()
    X, y = data['data'], data['target']

    clf = MLPRegressor(n_epochs=1, hidden_units=[])
    clf.fit(X, y)

    assert clf.transform(X).shape[1] == 1

def test_embedding_specific_layer():
    # Make sure the embedding works with no layers.
    data = load_diabetes()
    X, y = data['data'], data['target']

    clf = MLPRegressor(
        n_epochs=1,
        hidden_units=(256, 8, 256),
        transform_layer_index=1)
    clf.fit(X, y)

    assert clf.transform(X).shape[1] == 8

def load_data_regression():
    '''
    load the date set for regression (diabetes)
    :return: train_data, test_data, train_value, test_value
    '''
    diabetes = datasets.load_diabetes()
    return cross_validation.train_test_split(diabetes.data,diabetes.target,
    test_size=0.25,random_state=0)

def load_data_regression():
    '''
    load the diabetes data for regression
    :return: train_data, test_data, train_value, test_value
    '''
    diabetes = datasets.load_diabetes()
    return cross_validation.train_test_split(diabetes.data,diabetes.target,
    test_size=0.25,random_state=0)

def load_data_regression():
    '''
    load the diabetes for regression
    :return: train_data, test_data, train_value, test_value
    '''
    diabetes = datasets.load_diabetes()
    return cross_validation.train_test_split(diabetes.data,diabetes.target,
    test_size=0.25,random_state=0)

def load_data():

    diabetes = datasets.load_diabetes()
    return cross_validation.train_test_split(diabetes.data,diabetes.target,
        test_size=0.25,random_state=0)

def load_data():
    '''
    load for the dataset
    return:
            1 array for the regression problem.
            train_data, test_data, train_value, test_value
    '''

    diabetes = datasets.load_diabetes()
    return cross_validation.train_test_split(diabetes.data,diabetes.target,
        test_size=0.25,random_state=0)

def load_data():
    '''
    load for the dataset
        return:
                1 array for the regression problem.
                train_data, test_data, train_value, test_value
    '''
    diabetes = datasets.load_diabetes()
    return cross_validation.train_test_split(diabetes.data,diabetes.target,
        test_size=0.25,random_state=0)

def load_data_regression():
    '''
    load dataset for regression
    :return: train_data,test_data, train_target, test_target
    '''
    diabetes = datasets.load_diabetes()
    return cross_validation.train_test_split(diabetes.data,diabetes.target,
        test_size=0.25,random_state=0)

def load_data_regression():
    '''
    load dataset for regression
    :return: train_data,test_data, train_target, test_target
    '''
    diabetes = datasets.load_diabetes()
    return cross_validation.train_test_split(diabetes.data,diabetes.target,
        test_size=0.25,random_state=0)

def test_regression_scorers():
    # Test regression scorers.
    diabetes = load_diabetes()
    X, y = diabetes.data, diabetes.target
    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
    clf = Ridge()
    clf.fit(X_train, y_train)
    score1 = get_scorer('r2')(clf, X_test, y_test)
    score2 = r2_score(y_test, clf.predict(X_test))
    assert_almost_equal(score1, score2)

def test_load_diabetes():
    res = load_diabetes()
    assert_equal(res.data.shape, (442, 10))
    assert_true(res.target.size, 442)

def test_linearsvr():
    # check that SVR(kernel='linear') and LinearSVC() give
    # comparable results
    diabetes = datasets.load_diabetes()
    lsvr = svm.LinearSVR(C=1e3).fit(diabetes.data, diabetes.target)
    score1 = lsvr.score(diabetes.data, diabetes.target)

    svr = svm.SVR(kernel='linear', C=1e3).fit(diabetes.data, diabetes.target)
    score2 = svr.score(diabetes.data, diabetes.target)

    assert np.linalg.norm(lsvr.coef_ - svr.coef_) / np.linalg.norm(svr.coef_) < .1
    assert np.abs(score1 - score2) < 0.1