import numpy as np
import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_boston
from sklearn.datasets import load_iris
np.set_printoptions(precision=2)
鸢尾花数据集(一元)
iris=load_iris()
X,y=iris.data[:,2].reshape(-1,1),iris.data[:,3]
lr=LinearRegression()
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.25,random_state=0)
lr.fit(X_train,y_train)
print('模型权重:',lr.coef_)
print('截距:',lr.intercept_)
y_hat=lr.predict(X_test)
print('实际值:',y_train[:5])
print('预测值',y_hat[:5])
y_hat=lr.predict(X_test)
print('训练集R^2:',lr.score(X_train,y_train))
print('测试集R^2:',lr.score(X_test,y_test))
import matplotlib.pyplot as plt
plt.rcParams["font.family"] = "SimHei"
plt.rcParams["axes.unicode_minus"]=False
plt.rcParams['font.size']=15
plt.figure(figsize=(10,6))
plt.scatter(X_train,y_train,c='orange',label='训练集')
plt.scatter(X_test,y_test,c='g',marker='D',label='测试集')
plt.plot(X,lr.predict(X),'r-')
plt.legend()
plt.xlabel('花瓣长度')
plt.ylabel('花瓣宽度')
plt.figure(figsize=(15,6))
plt.plot(y_test,label='真实值',color='r',marker='o')
plt.plot(y_hat,label='预测值',ls='--',color='g',marker='o')
plt.xlabel('测试集数据序号')
plt.ylabel('数据集')
plt.legend()
波士顿房价数据集(多元)
boston=load_boston()
X,y=boston.data,boston.target
df=pd.DataFrame(np.concatenate([X,y.reshape(-1,1)],axis=1),
columns=boston.feature_names.tolist()+['MEDV'])
df.head()
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.25,random_state=0)
lr=LinearRegression()
lr.fit(X_train,y_train)
print('模型权重:',lr.coef_)
print('截距:',lr.intercept_)
y_hat=lr.predict(X_test)
print('训练集R^2:',lr.score(X_train,y_train))
print('测试集R^2:',lr.score(X_test,y_test))
使用投放广告(X)与收入(y)
df=pd.read_csv('./Advertising.csv',index_col=0)
x=df.iloc[:,0:-1]
y=df.iloc[:,-1]
x_train, x_test, y_train, y_test = train_test_split(x, y,test_size=0.2, random_state=0)
lr=LinearRegression()
lr.fit(x_train,y_train)
print(lr.predict(x_test))
print("训练集R^2:", lr.score(x_train, y_train))
print("测试集R^2:", lr.score(x_test, y_test))