Python learning_curve.learning_curve方法代码示例

# 需要导入模块: from sklearn import learning_curve [as 别名]
# 或者: from sklearn.learning_curve import learning_curve [as 别名]
def test_learning_curve():
    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)
    with warnings.catch_warnings(record=True) as w:
        train_sizes, train_scores, test_scores = learning_curve(
            estimator, X, y, cv=3, train_sizes=np.linspace(0.1, 1.0, 10))
    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)) 

# 需要导入模块: from sklearn import learning_curve [as 别名]
# 或者: from sklearn.learning_curve 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 learning_curve [as 别名]
# 或者: from sklearn.learning_curve 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(n_iter=1, 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 learning_curve [as 别名]
# 或者: from sklearn.learning_curve import learning_curve [as 别名]
def plot_learning_curve(loss_train_record, loss_valid_record):
    plt.figure()
    plt.plot(loss_train_record, label='train')
    plt.plot(loss_valid_record, c='r', label='validation')
    plt.ylabel("RMSE")
    plt.legend(loc='upper left', frameon=False)
    plt.savefig("data/learning_curve.png") 

# 需要导入模块: from sklearn import learning_curve [as 别名]
# 或者: from sklearn.learning_curve import learning_curve [as 别名]
def plot_learning_curve(self):
        print " + Plotting learning curve (this will take some time)...",
 
        (X_train, y_train) = self._train_data

        plt.figure()
        plt.title("Learning curve (%s)" % self._learner)
        plt.xlabel("Training examples")
        plt.ylabel("Score")
        train_sizes, train_scores, test_scores = learning_curve(
                                                    self._clf[self._learner],
                                                    X_train, y_train,
                                                    cv=5)
        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()
  
        print "done."
                         
    # Plot the ROC curve that results from each of our classifiers 

# 需要导入模块: from sklearn import learning_curve [as 别名]
# 或者: from sklearn.learning_curve 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)):
    if os.name == 'nt':
        n_jobs = 1
    else:
        n_jobs = -1
    plt.figure()
    plt.title(title)
    if ylim is not None:
        plt.ylim(*ylim)
    plt.xlabel("?????")
    plt.ylabel("???")
    train_sizes, train_scores, test_scores = learning_curve(
        estimator, X, y, cv=cv, n_jobs=n_jobs,
        scoring='accuracy', 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="???")
    plt.plot(train_sizes, test_scores_mean, 'o-', color="g",
             label="?????????")

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

# ??? 

# 需要导入模块: from sklearn import learning_curve [as 别名]
# 或者: from sklearn.learning_curve import learning_curve [as 别名]
def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,
                        n_jobs=1, train_sizes=np.linspace(.1, 1.0, 5)):
    from sklearn.learning_curve import learning_curve
    
    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 learning_curve [as 别名]
# 或者: from sklearn.learning_curve import learning_curve [as 别名]
def GenerateLearningCurve(estimator, X, y):
    # generate learning curve data
    #todo: edit parameters
    num_resources = -1 #engage all available CPUs and GPUs
    train_sizes, train_scores, test_scores = learning_curve(estimator=estimator, X=X, y=y, train_sizes= np.linspace(0.1, 1.0, 10), cv=10, n_jobs=num_resources, scoring='mean_squared_error')
    train_mean = np.mean(train_scores, axis = 1)
    train_std = np.std(train_scores, axis=1)
    test_mean = np.mean(test_scores, axis=1)
    test_std = np.std(test_scores, axis=1)
    PlotLearningCurve(train_sizes, train_mean, train_std, test_mean, test_std) 

# 需要导入模块: from sklearn import learning_curve [as 别名]
# 或者: from sklearn.learning_curve import learning_curve [as 别名]
def test_learning_curve():

    digits = load_digits()
    X,y=digits.data,digits.target

    train_sizes=np.linspace(0.1,1.0,endpoint=True,dtype='float')
    abs_trains_sizes,train_scores, test_scores = learning_curve(LinearSVC(),
            X, y,cv=10, scoring="accuracy",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)

    fig=plt.figure()
    ax=fig.add_subplot(1,1,1)

    ax.plot(abs_trains_sizes, train_scores_mean, label="Training Accuracy", color="r")
    ax.fill_between(abs_trains_sizes, train_scores_mean - train_scores_std,
                     train_scores_mean + train_scores_std, alpha=0.2, color="r")
    ax.plot(abs_trains_sizes, test_scores_mean, label="Testing Accuracy", color="g")
    ax.fill_between(abs_trains_sizes, test_scores_mean - test_scores_std,
                     test_scores_mean + test_scores_std, alpha=0.2, color="g")

    ax.set_title("Learning Curve with LinearSVC")
    ax.set_xlabel("Sample Nums")
    ax.set_ylabel("Score")
    ax.set_ylim(0,1.1)
    ax.legend(loc='best')
    plt.show() 

# 需要导入模块: from sklearn import learning_curve [as 别名]
# 或者: from sklearn.learning_curve 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 learning_curve [as 别名]
# 或者: from sklearn.learning_curve 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 learning_curve [as 别名]
# 或者: from sklearn.learning_curve 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)
    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))
    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 learning_curve [as 别名]
# 或者: from sklearn.learning_curve 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 learning_curve [as 别名]
# 或者: from sklearn.learning_curve 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 learning_curve [as 别名]
# 或者: from sklearn.learning_curve 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=30, n_folds=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))