Pandas高阶篇五(数据的拆分与分割)

数据的拆分

pandas返回的是一个特殊的Categorical对象。 你可以将其看做一组表 示面元名称的字符串。 实际上,它含有一个表示 不同分类名称的levels数组以及一个为年龄数据进行标号的labels属性。
跟“区间”的数学符号 一样,圆括号表示开端,而方括号则表示闭端(包括)。 哪边是闭端可以通过right.
也可以自定义label名称。

代码演示如下：

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]
#将所有的ages进行分组
bins = [18,25,35,60,100]
#使用pandas中的cut对年龄数据进行分组
cats = pd.cut(ages,bins)
cats
#打印结果：
[(18, 25], (18, 25], (18, 25], (25, 35], (18, 25], ..., (25, 35], (60, 100], (35, 60], (35, 60], (25, 35]]
Length: 12
Categories (4, interval[int64]): [(18, 25] < (25, 35] < (35, 60] < (60, 100]]

#调用pd.value_counts方法统计每个区间的人数
pd.value_counts(cats)
#打印结果：
(18, 25]     5
(35, 60]     3
(25, 35]     3
(60, 100]    1
dtype: int64

#显示第几个区间index值
cats.codes
#打印结果：
array([0, 0, 0, 1, 0, 0, 2, 1, 3, 2, 2, 1], dtype=int8)

#为分类出来的每一组年龄加上标签
group_names = ["Youth","YouthAdult","MiddleAged","Senior"]
personType = pd.cut(ages,bins,labels=group_names)
personType
#打印结果：
[Youth, Youth, Youth, YouthAdult, Youth, ..., YouthAdult, Senior, MiddleAged, MiddleAged, YouthAdult]
Length: 12
Categories (4, object): [Youth < YouthAdult < MiddleAged < Senior]

#用一个直方图简单的展示
plt.hist(personType)

打印结果：

对比qcut和cut用法

data = np.random.randn(100)   #服从正态分布
result = pd.qcut(data,4) #qcut会将100个数据进行排序，然后再将data数据均分成四组
result
#打印结果：
[(-2.912, -0.647], (-0.647, 0.218], (-2.912, -0.647], (0.218, 0.744], (-0.647, 0.218], ..., (-2.912, -0.647], (0.218, 0.744], (0.218, 0.744], (0.744, 2.57], (-0.647, 0.218]]
Length: 100
Categories (4, interval[float64]): [(-2.912, -0.647] < (-0.647, 0.218] < (0.218, 0.744] < (0.744, 2.57]]

#统计落在每个区间的元素个数
pd.value_counts(result) 
#打印结果：
(0.744, 2.57]       25
(0.218, 0.744]      25
(-0.647, 0.218]     25
(-2.912, -0.647]    25
dtype: int64

data
#打印结果：
array([-0.81944393, -0.47827597, -1.09209466,  0.65593818, -0.33765443,
        1.62557458,  0.3194351 ,  2.57005046,  1.41407812,  0.99061237,
        0.38456894, -1.89477296, -0.17753136, -1.43995942,  0.29287511,
        0.49614109, -0.42212434,  0.47653863,  0.27854401, -1.2910386 ,
        0.44532622,  2.15824034,  1.4430415 , -1.06147851,  1.68223286,
       -1.13871536,  0.57685232, -0.32090836,  0.77133685, -0.18020109,
       -1.31381356,  0.95240515, -0.78690992, -1.11867563,  1.14199622,
       -0.14897499, -0.41965931, -0.03576476,  0.77007272, -0.32632594,
        0.06267203, -1.44471277,  0.18464705,  0.02437242,  0.43143395,
       -0.60205938,  0.67788094, -0.17743486, -1.13475686, -2.91085367,
        0.62727327, -0.17854275, -0.88260309,  0.85683197, -2.49055636,
        0.86906019, -0.78107309,  0.6875342 ,  0.34721684, -0.10699128,
        0.40549062,  1.76385094,  1.17304214, -1.19093869, -0.37709317,
       -0.44977869,  1.09737126, -0.20524537, -1.11885991, -0.96239911,
        0.53720485,  0.79086801,  0.61237678,  0.34413715,  0.63984259,
        0.72957858,  1.11031023, -0.3926265 ,  1.76136485, -1.28750533,
        1.94702292, -2.43255566,  0.73515991,  1.94887473,  1.57655946,
       -1.40915724,  0.09215286,  0.50873343,  0.18692116, -1.05886742,
        0.2932763 ,  1.75318424,  1.4303616 , -1.45832408, -0.26121468,
       -2.04321697,  0.55099437,  0.24997625,  1.26154715,  0.07230284])

#qcut : 跟cut一样也可以自定义分位数（0到1之间的数值，包括端点）
result = pd.qcut(data,[0,0.1,0.5,0.9,1])
result
#打印结果：
[(-1.293, 0.218], (-1.293, 0.218], (-1.293, 0.218], (0.218, 1.456], (-1.293, 0.218], ..., (-2.912, -1.293], (0.218, 1.456], (0.218, 1.456], (0.218, 1.456], (-1.293, 0.218]]
Length: 100
Categories (4, interval[float64]): [(-2.912, -1.293] < (-1.293, 0.218] < (0.218, 1.456] < (1.456, 2.57]]

#统计落在每个区间的元素个数
pd.value_counts(result) 
#打印结果：
(0.218, 1.456]      40
(-1.293, 0.218]     40
(1.456, 2.57]       10
(-2.912, -1.293]    10
dtype: int64

#如果分位数的差值的和小于1的情况
result = pd.qcut(data,[0,0.1,0.3,0.75])
pd.value_counts(result)
#打印结果：
(-0.401, 0.744]     45
(-1.293, -0.401]    20
(-2.912, -1.293]    10
dtype: int64

#cut函数分割一组数据
data = np.random.rand(20)
data
#打印结果：
array([0.47895253, 0.28414843, 0.36634132, 0.35300655, 0.15481243,
       0.46266364, 0.34585777, 0.81500546, 0.47044936, 0.72463485,
       0.33547231, 0.19937734, 0.90590714, 0.64994955, 0.39107997,
       0.67691253, 0.13468209, 0.22932333, 0.19109326, 0.39903587])

#用cut函数将一组数据分割成n份
#cut函数分割的方式：数据里的（最大值-最小值）/n=每个区间的间距
#利用数据中最大值和最小值的差除以分组数作为每一组数据的区间范围的差值
result = pd.cut(data,4,precision=2)  #precision保留小数点的有效位数
result
#打印结果：
[(0.33, 0.52], (0.13, 0.33], (0.33, 0.52], (0.33, 0.52], (0.13, 0.33], ..., (0.52, 0.71], (0.13, 0.33], (0.13, 0.33], (0.13, 0.33], (0.33, 0.52]]
Length: 20
Categories (4, interval[float64]): [(0.13, 0.33] < (0.33, 0.52] < (0.52, 0.71] < (0.71, 0.91]]

#统计落在每个区间的元素个数
pd.value_counts(result) 
(0.33, 0.52]    9
(0.13, 0.33]    6
(0.71, 0.91]    3
(0.52, 0.71]    2
dtype: int64