对DataFrame中的数据进行按区间切分进行分组

import pandas as pd

#设置切分区域
listBins = [0, 10, 20, 30, 40, 50, 60, 1000000]

#设置切分后对应标签
listLabels = ['0_10','11_20','21_30','31_40','41_50','51_60','61及以上']

#利用pd.cut进行数据离散化切分
"""
pandas.cut(x,bins,right=True,labels=None,retbins=False,precision=3,include_lowest=False)
x:需要切分的数据
bins:切分区域
labels:对应标签,用标记来代替返回的bins,若不在该序列中,则返回NaN
retbins:是否包含右端点,默认False,不包含
precision:精度
include_lowest:是否包含左端点,默认False,不包含
"""
df['fenzu'] = pd.cut(df['data'], bins=listBins, labels=listLabels, include_lowest=True)

猜你喜欢

转载自blog.csdn.net/longwei92/article/details/82899604