文章作者：Tyan 博客：noahsnail.com | | 简书
本文主要介绍scikit-learn中的交叉验证。
Demo import numpy as np import matplotlib.pyplot as plt from sklearn.datasets import load_digits from sklearn.cross_validation import train_test_split from sklearn.svm import SVC from sklearn.learning_curve import learning_curve from sklearn.model_selection import cross_val_score # 加载数据集 digits = load_digits() X = digits.data y = digits.target # 用SVM进行学习并记录loss train_sizes, train_loss, test_loss = learning_curve(SVC(gamma = 0.001), X, y, cv = 10, scoring = 'neg_mean_squared_error', train_sizes = [0.1, 0.25, 0.5, 0.75, 1]) # 训练误差均值 train_loss_mean = -np.mean(train_loss, axis = 1) # 测试误差均值 test_loss_mean = -np.mean(test_loss, axis = 1) # 绘制误差曲线 plt.plot(train_sizes, train_loss_mean, 'o-', color = 'r', label = 'Training') plt.plot(train_sizes, test_loss_mean, 'o-', color = 'g', label = 'Cross-Validation') plt.xlabel('Training data size') plt.ylabel('Loss') plt.legend(loc = 'best') plt.show() 结果)
