power_prediction.py 文件源码

def plot_learning_curve(estimator, title, X, y,
                        ylim=None, cv=None, scoring=None,
                        n_jobs=1, train_sizes=np.linspace(0.1, 1.0, 5)):
    """
    Generate a simple plot of the test and training learning curve

    Parameters
    ----------
    estimator: object type that implements the "fit" and "predict" methods.
    title: string; title for the chart.
    X: traning vector, shape (n_samples, n_features)
    y: target, shape (n_samples,)
    ylim: tuple, shape (ymin, ymax)
          Defines minimum and maximum yvalues plotted.
    cv: int, cross-validation generator or an iterable
        Determines the cross-validation splitting strategy.
        Possible inputs for cv are:
          - None, to use the dafault 3-fold cross-validation
          - Interger, to specify the number of folds
          - An object to be used as a cross-validation generator
    """
    from sklearn.model_selection 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, scoring=scoring)
    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")
    return plt,train_sizes