sklearn不同数量的训练集在测试集上的表现的曲线刻画

def plot_learning_curve(estimator,X,y,cv=5,train_sizes=[0.1,0.3,0.5,0.7,0.8,0.9]):

    """

    描述：对于不同数量的训练样本的估计器的验证和训练评分

    param estimator:object|

    param X:shape=[n_samples,n_feature]

    param y:shape=[n_samples,]

    param cv:int

    param train_size:list of float

    """

    import matplotlib.pyplot as plt
　　 from sklearn.model_selection import learning_curve

    plt.figure()

    plt.title("learning curves")

    plt.xlabel("Training examples")

    plt.ylabel("Score")

    train_sizes, train_scores, test_scores = learning_curve(estimator=estimator,

                                                            X=X,

                                                            y=y,

                                                            cv=cv,

                                                            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,

                     y1=train_scores_mean-train_scores_std,

                     y2=train_scores_mean+train_scores_std,

                     alpha=0.1,

                     color="r")

    plt.fill_between(train_sizes,

                     y1=test_scores_mean-test_scores_std,

                     y2=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="testing score")

    plt.legend(loc="best")

    plt.show()

plot_learning_curve(estimator=SVC(),X=X,y=y,cv=5,train_sizes=[0.1,0.3,0.5,0.7,0.8,0.9])