python分箱统计个数_python中如何对一列数据进行分箱，分成个数比较均匀的几组样本，然后统计各组内的某个比率进行计算绘图。...

需求：我想等频分箱，就是比如一个score有不同的分数，先按照分数升序排列，排列后按照人数的分位数进行分箱，最终实现下图效果

数据下载链接网址https://bbs.pinggu.org/forum.php?mod=viewthread&tid=9485342&extra=

解答：#------------------------------------------------------------

#导入数据

#--------------------------------------------------------------

import pandas as pd

import numpy as np

data1=pd.read_excel("D:\\forver.xlsx")

#计算分位数 0.2。。。，设定分箱区间

qq=data1["score1"].quantile([0.2,0.4,0.6,0.8])

min1=data1["score1"].min()

max1=data1["score1"].max()

intervel=[0]+list(qq)+[max1]

#对变量进行排序

data1.sort_values(by="score1",ascending=True,inplace=True)

#对相关变量进行分箱

data1["score1分箱l"]=pd.cut(data1.score1,intervel)

data1["score1分箱"]=pd.cut(data1.score1,intervel,labels=[1,2,3,4,5])

#---------------------------------------------------------------

# 准备画图用数据

#-----------------------------------------------------------------

#统计各箱包含的样本个数

#计算各箱的bad%

#说明target取值为1则为bad，0为good

score1各箱人数=data1["score1分箱l"].value_counts()

score1各箱人数.sort_index(inplace=True)

score1badcount=data1[data1["target"]==1]["score1分箱l"].value_counts()

score1goodcount=data1[data1["target"]==0]["score1分箱l"].value_counts()

#将几个指标按照索引进行横向合并

picdata=pd.concat([score1各箱人数,score1badcount,score1goodcount],axis=1)

picdata.columns=["score1各箱人数","score1badcount","score1goodcount"]

#计算各箱的bad%

picdata["badper"]=picdata["score1badcount"]/picdata["score1各箱人数"]

#

#---------------------------------------------------------------

# 画图

#-------------------------------------------------------------------

xticklabel=[]

for i in range(len(intervel)-1):

print(i)

tt=str(int(intervel[i]))+"-"+str(int(intervel[i+1]))

print(tt)

xticklabel.append(tt)

import matplotlib.pyplot as plt

#解决中文乱码问题

plt.rcParams['font.sans-serif'] = ['Simhei']

fig,ax1=plt.subplots()

ax1.bar(xticklabel,picdata["score1各箱人数"],label="坏人数",color='r',width=0.6)

ax1.bar(xticklabel,picdata["score1goodcount"],label="好人数",color='b',width=0.6)

ax1.set_ylim([0,300]) # y轴边界

ax1.legend(loc=2)

ax2=ax1.twinx()

ax2.plot(np.arange(5),picdata["badper"],'r',label="bad百分比")

ax2.set_ylim([0,1]) # y轴边界

ax2.legend(loc=1)

ax1.set_xticklabels(xticklabel,fontsize=20,rotation=45)

fig.suptitle(u'score1的情况',fontsize=15)