线性回归——预测保险费用操作手册（5.3学习）

#导入库  任务1——加载数据及进行预处理
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

df=pd.read_csv('./data/insurance.csv')
df.head()

df.shape

df.info()

2.数据的清洗和转换

#将性别'female'——0；'male'-1替换
df['sex'].unique()

df['sex'].replace({'female':0,'male':1},inplace=True)
df.head()

#df['smoker']中'yes'——1，'no'——0替换
df['smoker'].unique()
df['smoker'].replace({'yes':1,'no':0},inplace=True)
df.head()

df['region']中'southwest’，'southeast'，'northwest','northeast'分别对应1、2、3、4数据的清洗和转换

df['region'].unique()

dict_region={'southwest':1,'southeast':2,'northwest':3,'northeast':4}

df['region']=df['region'].map(dict_re