莫烦sklearn学习自修第九天【过拟合问题处理】

1. 过拟合问题可以通过调整机器学习的参数来完成，比如sklearn中通过调节gamma参数，将训练损失和测试损失降到最低

2. 代码实现（显示gamma参数对训练损失和测试损失的影响）

from __future__ import print_function
from sklearn.learning_curve import  validation_curve
from sklearn.datasets import load_digits
from sklearn.svm import SVC
import matplotlib.pyplot as plt
import numpy as np

digits = load_digits()
X = digits.data
y = digits.target
param_range = np.logspace(-6, -2.3, 5)
train_loss, test_loss = validation_curve(
        SVC(), X, y, param_name='gamma', param_range=param_range, cv=10,
        scoring='mean_squared_error')
train_loss_mean = -np.mean(train_loss, axis=1)
test_loss_mean = -np.mean(test_loss, axis=1)

plt.plot(param_range, train_loss_mean, 'o-', color="r",
             label="Training")
plt.plot(param_range, test_loss_mean, 'o-', color="g",
             label="Cross-validation")

plt.xlabel("gamma")
plt.ylabel("Loss")
plt.legend(loc="best")
plt.show()