import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
data_url="http://lib.stat.cmu.edu/datasets/boston"
raw_df=pd.read_csv(data_url,sep="\s+",skiprows=22,header=None)
print(raw_df)
data=np.hstack([raw_df.values[::2,:],raw_df.values[1::2,:2]])
target=raw_df.values[1::2,2]
print(data)
print(target)


#拼接特征data和预测目标target
complete_data=np.column_stack([data,target])
columns=["CRIM",'ZN','INDUS','CHAS','NOX','RM','AGE','DIS','RAD','TAX','PTRATIO','B','LSTAT','MEDV']

#创建DataFrame,方便数据分析和特征处理
boston=pd.DataFrame(complete_data,columns=columns)
#显示前5行数据
boston.head()