Python model_selection.learning_curve方法代码示例

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import learning_curve [as 别名]
def test_learning_curve_verbose():
    X, y = make_classification(n_samples=30, n_features=1, n_informative=1,
                               n_redundant=0, n_classes=2,
                               n_clusters_per_class=1, random_state=0)
    estimator = MockImprovingEstimator(20)

    old_stdout = sys.stdout
    sys.stdout = StringIO()
    try:
        train_sizes, train_scores, test_scores = \
            learning_curve(estimator, X, y, cv=3, verbose=1)
    finally:
        out = sys.stdout.getvalue()
        sys.stdout.close()
        sys.stdout = old_stdout

    assert("[learning_curve]" in out) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import learning_curve [as 别名]
def test_learning_curve_batch_and_incremental_learning_are_equal():
    X, y = make_classification(n_samples=30, n_features=1, n_informative=1,
                               n_redundant=0, n_classes=2,
                               n_clusters_per_class=1, random_state=0)
    train_sizes = np.linspace(0.2, 1.0, 5)
    estimator = PassiveAggressiveClassifier(max_iter=1, tol=None,
                                            shuffle=False)

    train_sizes_inc, train_scores_inc, test_scores_inc = \
        learning_curve(
            estimator, X, y, train_sizes=train_sizes,
            cv=3, exploit_incremental_learning=True)
    train_sizes_batch, train_scores_batch, test_scores_batch = \
        learning_curve(
            estimator, X, y, cv=3, train_sizes=train_sizes,
            exploit_incremental_learning=False)

    assert_array_equal(train_sizes_inc, train_sizes_batch)
    assert_array_almost_equal(train_scores_inc.mean(axis=1),
                              train_scores_batch.mean(axis=1))
    assert_array_almost_equal(test_scores_inc.mean(axis=1),
                              test_scores_batch.mean(axis=1)) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import learning_curve [as 别名]
def test_learning_curve_with_boolean_indices():
    X, y = make_classification(n_samples=30, n_features=1, n_informative=1,
                               n_redundant=0, n_classes=2,
                               n_clusters_per_class=1, random_state=0)
    estimator = MockImprovingEstimator(20)
    cv = KFold(n_splits=3)
    train_sizes, train_scores, test_scores = learning_curve(
        estimator, X, y, cv=cv, train_sizes=np.linspace(0.1, 1.0, 10))
    assert_array_equal(train_sizes, np.linspace(2, 20, 10))
    assert_array_almost_equal(train_scores.mean(axis=1),
                              np.linspace(1.9, 1.0, 10))
    assert_array_almost_equal(test_scores.mean(axis=1),
                              np.linspace(0.1, 1.0, 10))


# 0.23. warning about tol not having its correct default value. 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import learning_curve [as 别名]
def learning_curve(self, graphs, targets,
                       cv=5, n_steps=10, start_fraction=0.1):
        """learning_curve."""
        graphs, targets = paired_shuffle(graphs, targets)
        x = self.transform(graphs)
        train_sizes = np.linspace(start_fraction, 1.0, n_steps)
        scoring = 'roc_auc'
        train_sizes, train_scores, test_scores = learning_curve(
            self.model, x, targets,
            cv=cv, train_sizes=train_sizes,
            scoring=scoring)
        return train_sizes, train_scores, test_scores 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import learning_curve [as 别名]
def __calc_learning_curve(self, algorithm):
        estimator = algorithm.estimator
        train_sizes, train_scores, test_scores = learning_curve(
            estimator,
            self.data.X,
            self.data.y,
            cv=self.cv,
            scoring=self.scoring,
            n_jobs=self.n_jobs)  # parallel run in cross validation
        train_scores_mean = np.mean(train_scores, axis=1)
        test_scores_mean = np.mean(test_scores, axis=1)

        return {'x': train_sizes, 'y_train': train_scores_mean,
                'y_cv': test_scores_mean} 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import learning_curve [as 别名]
def test_learning_curve():
    n_samples = 30
    n_splits = 3
    X, y = make_classification(n_samples=n_samples, n_features=1,
                               n_informative=1, n_redundant=0, n_classes=2,
                               n_clusters_per_class=1, random_state=0)
    estimator = MockImprovingEstimator(n_samples * ((n_splits - 1) / n_splits))
    for shuffle_train in [False, True]:
        with warnings.catch_warnings(record=True) as w:
            train_sizes, train_scores, test_scores = learning_curve(
                estimator, X, y, cv=KFold(n_splits=n_splits),
                train_sizes=np.linspace(0.1, 1.0, 10),
                shuffle=shuffle_train)
        if len(w) > 0:
            raise RuntimeError("Unexpected warning: %r" % w[0].message)
        assert_equal(train_scores.shape, (10, 3))
        assert_equal(test_scores.shape, (10, 3))
        assert_array_equal(train_sizes, np.linspace(2, 20, 10))
        assert_array_almost_equal(train_scores.mean(axis=1),
                                  np.linspace(1.9, 1.0, 10))
        assert_array_almost_equal(test_scores.mean(axis=1),
                                  np.linspace(0.1, 1.0, 10))

        # Test a custom cv splitter that can iterate only once
        with warnings.catch_warnings(record=True) as w:
            train_sizes2, train_scores2, test_scores2 = learning_curve(
                estimator, X, y,
                cv=OneTimeSplitter(n_splits=n_splits, n_samples=n_samples),
                train_sizes=np.linspace(0.1, 1.0, 10),
                shuffle=shuffle_train)
        if len(w) > 0:
            raise RuntimeError("Unexpected warning: %r" % w[0].message)
        assert_array_almost_equal(train_scores2, train_scores)
        assert_array_almost_equal(test_scores2, test_scores) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import learning_curve [as 别名]
def test_learning_curve_unsupervised():
    X, _ = make_classification(n_samples=30, n_features=1, n_informative=1,
                               n_redundant=0, n_classes=2,
                               n_clusters_per_class=1, random_state=0)
    estimator = MockImprovingEstimator(20)
    train_sizes, train_scores, test_scores = learning_curve(
        estimator, X, y=None, cv=3, train_sizes=np.linspace(0.1, 1.0, 10))
    assert_array_equal(train_sizes, np.linspace(2, 20, 10))
    assert_array_almost_equal(train_scores.mean(axis=1),
                              np.linspace(1.9, 1.0, 10))
    assert_array_almost_equal(test_scores.mean(axis=1),
                              np.linspace(0.1, 1.0, 10)) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import learning_curve [as 别名]
def test_learning_curve_incremental_learning_not_possible():
    X, y = make_classification(n_samples=2, n_features=1, n_informative=1,
                               n_redundant=0, n_classes=2,
                               n_clusters_per_class=1, random_state=0)
    # The mockup does not have partial_fit()
    estimator = MockImprovingEstimator(1)
    assert_raises(ValueError, learning_curve, estimator, X, y,
                  exploit_incremental_learning=True) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import learning_curve [as 别名]
def test_learning_curve_incremental_learning():
    X, y = make_classification(n_samples=30, n_features=1, n_informative=1,
                               n_redundant=0, n_classes=2,
                               n_clusters_per_class=1, random_state=0)
    estimator = MockIncrementalImprovingEstimator(20)
    for shuffle_train in [False, True]:
        train_sizes, train_scores, test_scores = learning_curve(
            estimator, X, y, cv=3, exploit_incremental_learning=True,
            train_sizes=np.linspace(0.1, 1.0, 10), shuffle=shuffle_train)
        assert_array_equal(train_sizes, np.linspace(2, 20, 10))
        assert_array_almost_equal(train_scores.mean(axis=1),
                                  np.linspace(1.9, 1.0, 10))
        assert_array_almost_equal(test_scores.mean(axis=1),
                                  np.linspace(0.1, 1.0, 10)) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import learning_curve [as 别名]
def test_learning_curve_n_sample_range_out_of_bounds():
    X, y = make_classification(n_samples=30, n_features=1, n_informative=1,
                               n_redundant=0, n_classes=2,
                               n_clusters_per_class=1, random_state=0)
    estimator = MockImprovingEstimator(20)
    assert_raises(ValueError, learning_curve, estimator, X, y, cv=3,
                  train_sizes=[0, 1])
    assert_raises(ValueError, learning_curve, estimator, X, y, cv=3,
                  train_sizes=[0.0, 1.0])
    assert_raises(ValueError, learning_curve, estimator, X, y, cv=3,
                  train_sizes=[0.1, 1.1])
    assert_raises(ValueError, learning_curve, estimator, X, y, cv=3,
                  train_sizes=[0, 20])
    assert_raises(ValueError, learning_curve, estimator, X, y, cv=3,
                  train_sizes=[1, 21]) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import learning_curve [as 别名]
def test_learning_curve_remove_duplicate_sample_sizes():
    X, y = make_classification(n_samples=3, n_features=1, n_informative=1,
                               n_redundant=0, n_classes=2,
                               n_clusters_per_class=1, random_state=0)
    estimator = MockImprovingEstimator(2)
    train_sizes, _, _ = assert_warns(
        RuntimeWarning, learning_curve, estimator, X, y, cv=3,
        train_sizes=np.linspace(0.33, 1.0, 3))
    assert_array_equal(train_sizes, [1, 2]) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import learning_curve [as 别名]
def test_learning_curve_with_shuffle():
    # Following test case was designed this way to verify the code
    # changes made in pull request: #7506.
    X = np.array([[1, 2], [3, 4], [5, 6], [7, 8], [11, 12], [13, 14], [15, 16],
                 [17, 18], [19, 20], [7, 8], [9, 10], [11, 12], [13, 14],
                 [15, 16], [17, 18]])
    y = np.array([1, 1, 1, 2, 3, 4, 1, 1, 2, 3, 4, 1, 2, 3, 4])
    groups = np.array([1, 1, 1, 1, 1, 1, 3, 3, 3, 3, 3, 4, 4, 4, 4])
    # Splits on these groups fail without shuffle as the first iteration
    # of the learning curve doesn't contain label 4 in the training set.
    estimator = PassiveAggressiveClassifier(max_iter=5, tol=None,
                                            shuffle=False)

    cv = GroupKFold(n_splits=2)
    train_sizes_batch, train_scores_batch, test_scores_batch = learning_curve(
        estimator, X, y, cv=cv, n_jobs=1, train_sizes=np.linspace(0.3, 1.0, 3),
        groups=groups, shuffle=True, random_state=2)
    assert_array_almost_equal(train_scores_batch.mean(axis=1),
                              np.array([0.75, 0.3, 0.36111111]))
    assert_array_almost_equal(test_scores_batch.mean(axis=1),
                              np.array([0.36111111, 0.25, 0.25]))
    assert_raises(ValueError, learning_curve, estimator, X, y, cv=cv, n_jobs=1,
                  train_sizes=np.linspace(0.3, 1.0, 3), groups=groups,
                  error_score='raise')

    train_sizes_inc, train_scores_inc, test_scores_inc = learning_curve(
        estimator, X, y, cv=cv, n_jobs=1, train_sizes=np.linspace(0.3, 1.0, 3),
        groups=groups, shuffle=True, random_state=2,
        exploit_incremental_learning=True)
    assert_array_almost_equal(train_scores_inc.mean(axis=1),
                              train_scores_batch.mean(axis=1))
    assert_array_almost_equal(test_scores_inc.mean(axis=1),
                              test_scores_batch.mean(axis=1)) 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import learning_curve [as 别名]
def plot_learning_curve(self, estimator, title, X, y, ylim=None, cv=None,
                            n_jobs=None, train_sizes=np.linspace(.1, 1.0, 5)):
        # From https://scikit-learn.org/stable/auto_examples/model_selection/plot_learning_curve.html
        print('Drawing curve, depending on your datasets size, this may take several minutes to several hours.')
        plt.figure()
        plt.title(title)
        if ylim is not None:
            plt.ylim(*ylim)
        plt.xlabel("Training examples")
        plt.ylabel("Score")
        train_sizes, train_scores, test_scores = learning_curve(
            estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_sizes)
        train_scores_mean = np.mean(train_scores, axis=1)
        train_scores_std = np.std(train_scores, axis=1)
        test_scores_mean = np.mean(test_scores, axis=1)
        test_scores_std = np.std(test_scores, axis=1)
        plt.grid()
        plt.fill_between(train_sizes, train_scores_mean - train_scores_std,
                         train_scores_mean + train_scores_std, alpha=0.1,
                         color="r")
        plt.fill_between(train_sizes, test_scores_mean - test_scores_std,
                         test_scores_mean + test_scores_std, alpha=0.1, color="g")
        plt.plot(train_sizes, train_scores_mean, 'o-', color="r",
                 label="Training score")
        plt.plot(train_sizes, test_scores_mean, 'o-', color="g",
                 label="Cross-validation score")
        plt.legend(loc="best")
        plt.show() 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import learning_curve [as 别名]
def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,
                        train_sizes=np.linspace(.1, 1.0, 5), n_jobs=1, figure_path=None):
    plt.figure()
    plt.title(title)
    if ylim is not None:
        plt.ylim(*ylim)
    plt.xlabel("Training examples")
    plt.ylabel("Score")
    train_sizes, train_scores, test_scores = learning_curve(
        estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_sizes)
    train_scores_mean = np.mean(train_scores, axis=1)
    train_scores_std = np.std(train_scores, axis=1)
    test_scores_mean = np.mean(test_scores, axis=1)
    test_scores_std = np.std(test_scores, axis=1)
    plt.grid()

    plt.fill_between(train_sizes, train_scores_mean - train_scores_std,
                     train_scores_mean + train_scores_std, alpha=0.1,
                     color="r")
    plt.fill_between(train_sizes, test_scores_mean - test_scores_std,
                     test_scores_mean + test_scores_std, alpha=0.1, color="g")
    plt.plot(train_sizes, train_scores_mean, 'o-', color="r",
             label="Training score")
    plt.plot(train_sizes, test_scores_mean, 'o-', color="g",
             label="Cross-validation score")

    plt.legend(loc="best")
    plt.savefig(figure_path)
    return plt 

# 需要导入模块: from sklearn import model_selection [as 别名]
# 或者: from sklearn.model_selection import learning_curve [as 别名]
def _set_description(self, dfe):
        importances = pd.Series(self.model.feature_importances_, index=dfe.get_features().columns).sort_values(ascending=False)

        y = dfe.df[dfe.target]
        X = dfe.df.drop(dfe.target, axis=1)
        train_sizes, train_scores, test_scores = learning_curve(self.model, X, y, n_jobs=self.n_jobs)
        train_scores_mean = np.mean(train_scores, axis=1)
        train_scores_std = np.std(train_scores, axis=1)
        test_scores_mean = np.mean(test_scores, axis=1)
        test_scores_std = np.std(test_scores, axis=1)
            
        pic = ImageFile.create()
        with pic.plot() as plt_fig:
            plt, fig = plt_fig
            fig.set_figwidth(12)
            plt.subplot(121)
            importances.plot(kind="bar")

            ax2 = plt.subplot(122)
            ax2.fill_between(train_sizes, train_scores_mean - train_scores_std,
                train_scores_mean + train_scores_std, alpha=0.1,color="r")
            ax2.fill_between(train_sizes, test_scores_mean - test_scores_std,
                test_scores_mean + test_scores_std, alpha=0.1, color="g")
            ax2.plot(train_sizes, train_scores_mean, "o-", color="r", label="学習精度" if self.lang == "ja" else "Training score")
            ax2.plot(train_sizes, test_scores_mean, 'o-', color="g", label="評価精度" if self.lang == "ja" else "Cross-validation score")
            ax2.set_xlabel("学習データ量(行数)" if self.lang == "ja" else "data records")
            ax2.set_ylabel("精度" if self.lang == "ja" else "accuracy")
            ax2.set_ylim(0, 1)
            ax2.legend(loc="best")
        
        params = (self.score, self.model.__class__.__name__)
        self.description = {
            "ja": Description("モデルの精度は{:.3f}です(利用モデル:{})。各項目の貢献度は図のようになっています。".format(*params), pic),
            "en": Description("The model accuracy is {:.3f}(model is {}). The contributions of each features are here.".format(*params), pic)
        }