【Scikit-Learn】绘制学习曲线

首先生成相应的数据集（X,Y），然后用线性回归模型去拟合数据集。

这里使用sklearn中的学习曲线函数learning_curve，对于回归问题返回的score是曲线拟合程度指标$R^2$，其最大值为1。$R^2$的值越接近1，说明回归直线对观测值的拟合程度越好。

这里的Y=np.sqrt(X)，使用一次多项式特征会欠拟合，使用3次多项式特征恰好拟合，使用10次多项式特征会过拟合，拟合效果如绘制的学习曲线所示。

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np

n_dots = 200

X = np.linspace(0, 1, n_dots)                   
y = np.sqrt(X) + 0.2*np.random.rand(n_dots) - 0.1;

X = X.reshape(-1, 1)
y = y.reshape(-1, 1)

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LinearRegression

def polynomial_model(degree=1):
    # 生成特征x 的多项式特征。假设有a，b两个特征，那么它的2次多项式为（1,a,b,a^2,ab, b^2）
    polynomial_features = PolynomialFeatures(degree=degree,
                                             include_bias=False)
    linear_regression = LinearRegression()
    pipeline = Pipeline([("polynomial_features", polynomial_features),
                         ("linear_regression", linear_regression)])
    return pipeline

from sklearn.model_selection import learning_curve
from sklearn.model_selection import ShuffleSplit

def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,
                        n_jobs=1, train_sizes=np.linspace(.1, 1.0, 5)):
    """
         train_sizes=np.linspace(.1, 1.0, 5)=array([ 0.1  ,  0.325,  0.55 ,  0.775,  1.   ])，表示训练样本从总数据集中分别取出10%、32.5%、
        55%、77.5%、100%作为子数据集。对当前子数据集，根据cv定好的规则划分为训练集和测试集，然后使用estimator指定的模型计算测试集得分。
       现在是回归问题，因此函数  learning_curve 的score是MSE
    """
    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.shape=(5,10)，test_scores.shape=(5,10)，共有5个子数据集。每个子数据集根据cv随机划分出10组不同的（训练集+测试集）
    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 + 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")
    return plt

# 随机选择20%的数据集作为测试集，80%作为训练集。然后重复10次，共选出10份(训练数据+测试数据)
cv = ShuffleSplit(n_splits=10, test_size=0.2, random_state=0)
titles = ['Learning Curves (Under Fitting)',
          'Learning Curves',
          'Learning Curves (Over Fitting)']
degrees = [1, 3, 10]

plt.figure(figsize=(18, 4), dpi=200)
for i in range(len(degrees)):
    plt.subplot(1, 3, i + 1)
    plot_learning_curve(polynomial_model(degrees[i]), titles[i], X, y, ylim=(0.75, 1.01), cv=cv)

plt.show()