学习曲线

机器学习 learning curve

学习曲线用去判断模型学习过程中是否存在过拟合，如果在训练集和测试集上差距很大，则存在了过拟合现象

import numpy as np
import matplotlib.pyplot as plt
from sklearn.learning_curve import learning_curve


def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None, n_jobs=1, 
                        train_sizes=np.linspace(.7, 1., 20), verbose=0, plot=True):

    train_sizes, train_scores, test_scores = learning_curve(
        estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_sizes, verbose=verbose)

    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)

    if plot:
        plt.figure()
        plt.title(title)
        if ylim is not None:
            plt.ylim(*ylim)
        plt.xlabel(u"训练样本数")
        plt.ylabel(u"得分")
        plt.gca().invert_yaxis()
        plt.grid()

        plt.fill_between(train_sizes, train_scores_mean - train_scores_std, train_scores_mean + train_scores_std, 
                         alpha=0.1, color="b")
        plt.fill_between(train_sizes, test_scores_mean - test_scores_std, test_scores_mean + test_scores_std, 
                         alpha=0.1, color="r")
        plt.plot(train_sizes, train_scores_mean, 'o-', color="b", label=u"trainning")
        plt.plot(train_sizes, test_scores_mean, 'o-', color="r", label=u"cross validate")

        plt.legend(loc="best")

        plt.draw()
        plt.gca().invert_yaxis()
        plt.show()

    midpoint = ((train_scores_mean[-1] + train_scores_std[-1]) + (test_scores_mean[-1] - test_scores_std[-1])) / 2
    diff = (train_scores_mean[-1] + train_scores_std[-1]) - (test_scores_mean[-1] - test_scores_std[-1])
    return midpoint, diff
plot_learning_curve(clf, u"learning curve", X, y)