from pandas import Series,DataFrame
import pandas as pd
import numpy as np
from numpy import nan as NA
from matplotlib import pyplot as plt
ages = [20,22,25,27,21,23,37,31,61,45,41,32]
#將所有的ages進(jìn)行分組
bins = [18,25,35,60,100]
#使用pandas中的cut對年齡數(shù)據(jù)進(jìn)行分組
cats = pd.cut(ages,bins)
#print(cats)
#調(diào)用pd.value_counts方法統(tǒng)計每個區(qū)間的個數(shù)
number=pd.value_counts(cats)
#print(pd.value_counts(cats))
#顯示第幾個區(qū)間index值
index=pd.cut(ages,bins).codes
#print(index)
#為分類出來的每一組年齡加上標(biāo)簽
group_names = ["Youth","YouthAdult","MiddleAged","Senior"]
personType=pd.cut(ages,bins,labels=group_names)
#print(personType)
plt.hist(personType)
#plt.show()
#cut和qcut的用法
data=[1,2,3,4,5,6,7,8,9,10]
result=pd.qcut(data,4)
print(' ',result)##qcut會將10個數(shù)據(jù)進(jìn)行排序，然后再將data數(shù)據(jù)均分成四組
#統(tǒng)計落在每個區(qū)間的元素個數(shù)
print('dasdasdasdasdas:  ',pd.value_counts(result))
#qcut : 跟cut一樣也可以自定義分位數(shù)（0到1之間的數(shù)值，包括端點）
results=pd.qcut(data,[0,0.1,0.5,0.9,1])
print('results:  ',results)

import numpy as np
import pandas as pd
data = np.random.rand(20)
print(data)
#用cut函數(shù)將一組數(shù)據(jù)分割成n份
#cut函數(shù)分割的方式：數(shù)據(jù)里的（最大值-最小值）/n=每個區(qū)間的間距
#利用數(shù)據(jù)中最大值和最小值的差除以分組數(shù)作為每一組數(shù)據(jù)的區(qū)間范圍的差值
result = pd.cut(data,4,precision=2) #precision保留小數(shù)點的有效位數(shù)
print(result)
res_data=pd.value_counts(result)
print(res_data)