画学习曲线的方法

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

from sklearn.model_selection import ShuffleSplit 
from sklearn.model_selection import learning_curve
from sklearn.neighbors import KNeighborsClassifier

#加载数据
data=pd.read_csv(r"D:\Desktop\data\59024 scikit-learn机器学习源码_20181031\code\datasets\pima-indians-diabetes\diabetes.csv")

#from common.utils import plot_learning_curve
def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,
                        n_jobs=1, train_sizes=np.linspace(.1, 1.0, 5)):
    plt.figure()
    plt.title(title)
    if ylim is not None:
        plt.ylim(*ylim)
    plt.xlabel("Training examples")
    plt.ylabel("Score")
    train_sizes, train_scores, test_scores = learning_curve(
        estimator, X, y, cv=cv, n_jobs=n_jobs, 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()# 生成网格
    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.legend(loc="best")#添加图例
    return plt

X=data.iloc[:,0:8]
y=data.iloc[:,-1]#pandas对象加iloc，数组不用加
knn=KNeighborsClassifier(n_neighbors=2)

cv=ShuffleSplit(n_splits=10,test_size=0.2,random_state=0)
plt.figure(figsize=(16,10),dpi=200)
plot_learning_curve(knn,"Learn Curve for KNN Diabetes",X,y,ylim=(0.0,1.01),cv=cv)

 

 学习曲线说明：

 横坐标表示训练样本的数量，纵坐标表示准确率

1：观察左上图，训练集准确率与验证集准确率收敛，但是两者收敛后的准确率远小于我们的期望准确率（上面那条红线），所以由图可得该模型属于欠拟合-高偏差（underfitting）问题。由于欠拟合，所以我们需要增加模型的复杂度，比如，增加特征、增加树的深度、减小正则项等等，此时再增加数据量是不起作用的。

    2：观察右上图，训练集准确率高于期望值，验证集则低于期望值，两者之间有很大的间距，误差很大，对于新的数据集模型适应性较差，所以由图可得该模型属于过拟合-高方差（overfitting）问题。由于过拟合，所以我们降低模型的复杂度，比如减小树的深度、增大分裂节点样本数、增大样本数、减少特征数等等。

    3：一个比较理想的学习曲线图应当是：低偏差、低方差，即收敛且误差小。