模型状态评估：绘制学习曲线

原：https://www.zybuluo.com/hanxiaoyang/note/545131#plot-learning-curve

from sklearn.svm import LinearSVC
from sklearn.learning_curve import learning_curve
#绘制学习曲线，以确定模型的状况
def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,
                        train_sizes=np.linspace(.1, 1.0, 5)):
    """
    画出data在某模型上的learning curve.
    参数解释
    ----------
    estimator : 你用的分类器。
    title : 表格的标题。
    X : 输入的feature，numpy类型
    y : 输入的target vector
    ylim : tuple格式的(ymin, ymax), 设定图像中纵坐标的最低点和最高点
    cv : 做cross-validation的时候，数据分成的份数，其中一份作为cv集，其余n-1份作为training(默认为3份)
    """
    plt.figure()
    train_sizes, train_scores, test_scores = learning_curve(
        estimator, X, y, cv=5, n_jobs=1, 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.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.xlabel("Training examples")
    plt.ylabel("Score")
    plt.legend(loc="best")
    plt.grid("on") 
    if ylim:
        plt.ylim(ylim)
    plt.title(title)
    plt.show()
#少样本的情况情况下绘出学习曲线
plot_learning_curve(LinearSVC(C=10.0), "LinearSVC(C=10.0)",
                    X, y, ylim=(0.8, 1.01),
                    train_sizes=np.linspace(.05, 0.2, 5))