python 画学习曲线的方法

Posted 2021-05-09

from matplotlib import pyplot as plt
from matplotlib.font_manager import FontProperties
font = FontProperties(fname=r"c:\windows\fonts\simsun.ttc", size=14)    # 解决windows环境下画图汉字乱码问题
from sklearn.learning_curve import learning_curve
from sklearn.metrics import make_scorer, mean_absolute_error    # 评分函数
'''
- 用sklearn的learning_curve得到training_score和cv_score，使用matplotlib画出learning curve
- 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None为3份)
@scoring : 评分函数，可以通过sklearn.metrics中的评分函数指定
@n_jobs : 并行的的任务数(默认1)
'''
def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None, scoring=None, n_jobs=1, 
                        train_sizes=np.linspace(.05, 1., 20), verbose=0, plot=True):
    train_sizes, train_scores, test_scores = learning_curve(
        estimator, X, y, cv=cv, scoring=scoring, n_jobs=n_jobs, train_sizes=train_sizes, verbose=verbose)
    '''
    返回值解释
    ------------
    train_sizes：指定的train_sizes大小的数组，shape为(n_ticks, ).
    train_scores：训练集上的得分，shape为(n_ticks, n_cv_folds)，n_cv_folds为cv的份数，默认为3
    test_scores： 测试集上的得分
    '''
    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,fontproperties=font)
        if ylim is not None:
            plt.ylim(*ylim)
        plt.xlabel(u"训练样本数",fontproperties=font)
        plt.ylabel(u"得分",fontproperties=font)
        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=r"score of training set")
        plt.plot(train_sizes, test_scores_mean, 'o-', color="r", label=r'score of cv set')

        plt.legend(loc="best")
        #plt.ion()
        plt.draw()
        plt.show()
        plt.gca().invert_yaxis()
        #time.sleep(1)

    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
    
'''使用'''
#mean_absolute_error_score = make_scorer(mean_absolute_error)
#plot_learning_curve(model, u"学习曲线", X_train, Y_train[:,i],scoring=mean_absolute_error_score)