数据挖掘-3.建模调参

绘制学习率曲线与验证曲线

learning_curve :param ::train_size
fill_between

def plot_learning_curve(estimator,title, X, y, ylim=None, cv=None, n_jobs=1, 
                        train_size = np.linspace(.1,1.0,5)):
    plt.figure()
    plt.title(title)
    if ylim is not None:
        plt.ylim(*ylim)
    plt.xlabel('Training example')
    plt.ylabel('score')

    train_sizes, train_scores, test_scores = learning_curve(estimator, X, y, cv=cv, 
                                                           n_jobs = n_jobs,
                                                           train_sizes = train_size, 
                                                           scoring = make_scorer(mean_absolute_error))
    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 + test_scores_std, alpha=.1, color='r')
    plt.fill_between(train_sizes,test_scores_mean - test_scores_std,
                    test_scores_mean + test_scores_std, alpha=.1, color='g')
    plt.plot(train_sizes,train_scores_mean, 'o-', color='r', label='train_mean')
    plt.plot(train_sizes,test_scores_mean, 'o-', color='g', label='val_mean')

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