人工智能/机器学习房价预测

import pandas as pd

filname = 'D:\\Train_test\\BOSTON_HOUSE.xls'
data = pd.read_excel(filname,header=None)
data.head()

data=data.drop(index=[0,1,2],axis=0)

dataselect=data[[6,11,13,14]]
dataselect=dataselect.rename(columns={6:'RM',11:'PTRATIO',13:'LSTAT',14:'MEDV'})
print(dataselect)

import numpy as np

for col in np.take(dataselect.columns,[0,1,2,3]):
       dataselect[col]/=dataselect[col].max()
dataselect.head()

from sklearn.model_selection import train_test_split
train,test=train_test_split(dataselect.copy(),test_size=0.2)

train_=train[['RM','PTRATIO','LSTAT']]
train_

Train_y=train['MEDV'].values
Train_y

test_=test[['RM','PTRATIO','LSTAT']]
test_