采用Ridge（岭回归）重新对三种不同销售方式所影响的销售额展开分析

import numpy as np
import matplotlib as mpl
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import Ridge
from sklearn.model_selection import GridSearchCV

data = pd.read_csv('Advertising.csv')    # TV、Radio、Newspaper、Sales
x = data[['TV', 'Radio', 'Newspaper']]
y = data['Sales']

x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=1, train_size=0.8)
# 同样设定80%的训练样本
# model = Lasso()
model = Ridge()
# 设定Ridge模型
alpha_can = np.logspace(-3, 2, 10)
# Ridge函数需要一个参数值，这里从10的-3次方到10的2次方取十个候选值
np.set_printoptions(suppress=True)
print ('alpha_can = ', alpha_can)

alpha_can =  [  0.001        0.00359381   0.0129155    0.04641589   0.16681005

Ridge_model = GridSearchCV(model, param_grid={'alpha': alpha_can}, cv=5)
# 挨个搜索alpha_can
Ridge_model.fit(x_train, y_train)
# 数据喂给函数
print ('超参数：\n', Ridge_model.best_params_)
# 输出最佳参数

{'alpha': 7.742636826811277}

order = y_test.argsort(axis=0)
y_test = y_test.values[order]
x_test = x_test.values[order, :]
y_hat = Ridge_model.predict(x_test)
mse = np.average((y_hat - np.array(y_test)) ** 2) 
rmse = np.sqrt(mse) 

t = np.arange(len(x_test))
mpl.rcParams['font.sans-serif'] = [u'simHei']
mpl.rcParams['axes.unicode_minus'] = False
plt.figure(facecolor='w')
plt.plot(t, y_test, 'r-', linewidth=2, label=u'真实数据')
plt.plot(t, y_hat, 'g-', linewidth=2, label=u'预测数据')
plt.title(u'线性回归预测销量', fontsize=18)
plt.legend(loc='upper left')
plt.grid(b=True, ls=':')
plt.show()