给定数据集insurance.csv,该数据集记录的是投保人相关的历史数据

1)加载数据集并做数据清洗

2)划分训练集和测试集,并生成模型

3)模型验证,绘制折线图比较预测值和真实值,并计算MSE

4)假设投保人信息如下:

person={'age':[35],'sex':1,'bmi':[31],'children':[2],'smoker':[1],'region':[2],'bmismoker':[1],'charges':[0]}

预测该投保人的医疗费用并输出

import numpy as np
import pandas as pd
from sklearn.metrics import mean_absolute_error
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression,SGDRegressor
from sklearn.datasets import load_boston
from sklearn.preprocessing import MinMaxScaler
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False
data=pd.read_csv("data/insurance.csv")
print(data)
#特征处理（非数字转换为数字，使用map,apply函数）
data["sex"]=data["sex"].map({"male":1,"female":0})
data["smoker"]=data["smoker"].map({"yes":1,"no":0})
print(data["region"].value_counts())
data["region"]=data["region"].map({"southwest":1,"southeast":2,"northwest":3,"northeast":4})
print(data.corr())
def change(x):
    if x["bmi"]>30 and x["smoker"]==1:
        return 1
    else:
        return 0
data.insert(6,"bmismoker",data.apply(lambda x:change(x),axis=1))
#将数据标准化或者归一化
#数据集划分
scaler=MinMaxScaler()
data=scaler.fit_transform(data)
x=data[:,-1]
y=data[:,-1]
print(x)
x_train,x_test,y_train,y_test=train_test_split(x,y,random_state=22,test_size=0.2)
#模型训练
model=LinearRegression()
model.fit(x_train,y_train)#模型生成
#模型评估，计算mse的取值
y_pred=model.predict(x_test)
mse=mean_absolute_error(y_test,y_pred)
#模型得分：
print(model.score(x_test,y_test))
#均方误差:
print(mse)
#对新数据做预测
person={'age':[35],'sex':1,'bmi':[31],'children':[2],'smoker':[1],'region':[2],'bmismoker':[1],'charges':[0]}
person_df=pd.DataFrame(person)
#新数据要和训练集相同规格的标准化或归一化
person_chuli=scaler.transform(person_df)#不能重新fit,必须使用前面的scaler对象
person_pred=model.predict(person_chuli[:,:-1])
person_chuli[0,6]=person_pred
#进行反归一化获取真实值
fan=scaler.inverse_transform(person_chuli)
print(fan[0,6])