博客

一、岭回归 Ridge

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

from sklearn.model_selection import train_test_split

df = pd.read_csv(‘d:/3_film.csv’)

X = df.iloc[:,1:4]

y = df.filmnum

X = np.array(X.values)

y = np.array(y.values)

x_train,x_test,y_train,y_test = train_test_split(X,y,test_size = 0.25,random_state = 1)

from sklearn import linear_model

#λ为0.1

ridge = linear_model.Ridge(alpha = 0.1)

ridge.fit(x_train,y_train)

print(‘求解系数为：’+str(ridge.coef_))

print(‘求解截距项为:’+str(ridge.intercept_))

y_pre = ridge.predict(x_test)

print(y_pre)

plt.figure(figsize=(10,6)) #设置图片大小

t = np.arange(0,len(x_test),1) #x轴

plt.plot(t,y_pre,‘b’,linewidth = 2,label = ‘predict’)

plt.plot(t,y_test,‘r’,linewidth = 2,label = ‘test’)

plt.legend()

plt.show()

from sklearn import metrics

from sklearn.metrics import r2_score

print(‘R2拟合度为:’+str(r2_score(y_test,y_pre)))

print(‘MAE误差为:’+str(metrics.mean_absolute_error(y_test,y_pre)))

print(‘MSE误差为:’+str(metrics.mean_squared_error(y_test,y_pre)))

print(‘RMSE误差为’+str(np.sqrt(metrics.mean_squared_error(y_test,y_pre))))

二、Lasso回归

lasso = linear_model.Lasso(alpha = 0.1)

lasso.fit(x_train,y_train)

print(‘参数：’,lasso.coef_)

print(‘截距：’,lasso.intercept_)

y_hat = lasso.predict(x_test)

plt.figure(figsize=(10,6))

t = np.arange(len(y_hat))

plt.plot(t,y_test,‘g’,linewidth=2,label=‘test’)

plt.plot(t,y_hat,‘r’,linewidth=2,label=‘predict’)

plt.legend()

plt.show()

from sklearn.linear_model import LinearRegression

lr = LinearRegression()

lr.fit(x_train,y_train)

y_pre1 = lr.predict(x_test)