sklearn之validationcurve

 通过validation_curve画出训练图,找到最合适的参数范围和参数

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
from sklearn.model_selection 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

#建立参数测试集
param_range = np.logspace(-6, -2.3, 5)

#使用validation_curve找出模型对参数的影响,
# param_name是要评估的参数,param_range是选用的参数
train_loss, test_loss = validation_curve(
    SVC(), X, y, param_name='gamma', param_range=param_range, cv=10, scoring='mean_squared_error')


#平均每一轮的平均方差
train_loss_mean = -np.mean(train_loss, axis=1)
test_loss_mean = -np.mean(test_loss, axis=1)

#可视化图形
plt.plot(param_range, train_loss_mean, 'o-', color="r",
         label="Training")
plt.plot(param_range, test_loss_mean, 'o-', color="b",
        label="Cross-validation")

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