import pandas as pd
d=pd.read_csv('D:/pandas活用/pandas_for_everyone-master/data/acs_ny.csv')
print(d.columns)
print('@'*66)
print(d.head())
以下对FamilyIncome 进行分箱操作:
#其中指定要进行分箱操作的列,指定收入在范围为0-150000的为0,150000到收入的最大值范围之间的为1,标签labels使用列表传入值,也可以指定字符串作为标签
d['income_15w']=pd.cut(d['FamilyIncome'],[0,150000,d['FamilyIncome'].max()],labels=[0,1])
print(d.info())
print(d['income_15w'].value_counts())