數據分箱技術Binning

• 數據分箱技術Binning
• • 引入相關庫
  • 數據獲取
  • 數據分箱

數據分箱技術Binning

引入相關庫

import numpy as np import pandas as pd from pandas import Series,DataFrame

數據獲取

產生一些考試的成績分數，一共20個數據在25到100之間

score_list=np.random.randint(25,100,size=20) score_list array([66, 40, 32, 55, 81, 91, 49, 57, 36, 96, 83, 55, 98, 38, 36, 82, 71,39, 73, 60])

數據分箱

把0-59作為不及格，60-70作為ok，70-80作為良好，80-100作為優秀，定義一個list作為數據的取值范圍

bins=[0,59,70,80,100]

通過cut方法，第一個參數為對哪個數據做分箱，第二個參數作為分箱的范圍

pd.cut(score_list,bins) [(59, 70], (0, 59], (0, 59], (0, 59], (80, 100], ..., (80, 100], (70, 80], (0, 59], (70, 80], (59, 70]] Length: 20 Categories (4, interval[int64]): [(0, 59] < (59, 70] < (70, 80] < (80, 100]] score_cat=pd.cut(score_list,bins)

統計每個分數段人數的結果

pd.value_counts(score_cat) (0, 59] 10 (80, 100] 6 (70, 80] 2 (59, 70] 2 dtype: int64

創建一個空的DataFrame

df=DataFrame()

把‘score’這一列用score_list賦值

df['score']=score_list df score012345678910111213141516171819

66
40
32
55
81
91
49
57
36
96
83
55
98
38
36
82
71
39
73
60

通過rands生成隨機的20個字符串，作為學生的姓名

df['student']=[pd.util.testing.rands(3) for i in range(20)] df scorestudent012345678910111213141516171819

66	mDG
40	pCe
32	Iuv
55	sWt
81	eaR
91	5Gw
49	8Xc
57	Tu2
36	IRS
96	VQU
83	lsc
55	nek
98	cFQ
38	ZeB
36	Lfi
82	jYv
71	x6q
39	t9I
73	CJg
60	hF4

把DataFrame的score作cut

pd.cut(df['score'],bins) 0 (59, 70] 1 (0, 59] 2 (0, 59] 3 (0, 59] 4 (80, 100] 5 (80, 100] 6 (0, 59] 7 (0, 59] 8 (0, 59] 9 (80, 100] 10 (80, 100] 11 (0, 59] 12 (80, 100] 13 (0, 59] 14 (0, 59] 15 (80, 100] 16 (70, 80] 17 (0, 59] 18 (70, 80] 19 (59, 70] Name: score, dtype: category Categories (4, interval[int64]): [(0, 59] < (59, 70] < (70, 80] < (80, 100]]

把做完cut的Categorie賦給DataFrame的‘Categories’

df['Categories ']=pd.cut(df['score'],bins) df scorestudentCategories012345678910111213141516171819

66	mDG	(59, 70]
40	pCe	(0, 59]
32	Iuv	(0, 59]
55	sWt	(0, 59]
81	eaR	(80, 100]
91	5Gw	(80, 100]
49	8Xc	(0, 59]
57	Tu2	(0, 59]
36	IRS	(0, 59]
96	VQU	(80, 100]
83	lsc	(80, 100]
55	nek	(0, 59]
98	cFQ	(80, 100]
38	ZeB	(0, 59]
36	Lfi	(0, 59]
82	jYv	(80, 100]
71	x6q	(70, 80]
39	t9I	(0, 59]
73	CJg	(70, 80]
60	hF4	(59, 70]

定義一個list，作為labels方法的參數，通過標簽的方法，把Categories標志出來，更適合人的閱讀

df['Categories ']=pd.cut(df['score'],bins,labels=['Low','OK','Good','Great']) df scorestudentCategories012345678910111213141516171819

66	mDG	OK
40	pCe	Low
32	Iuv	Low
55	sWt	Low
81	eaR	Great
91	5Gw	Great
49	8Xc	Low
57	Tu2	Low
36	IRS	Low
96	VQU	Great
83	lsc	Great
55	nek	Low
98	cFQ	Great
38	ZeB	Low
36	Lfi	Low
82	jYv	Great
71	x6q	Good
39	t9I	Low
73	CJg	Good
60	hF4	OK

總結

以上是生活随笔為你收集整理的数据分箱技术Binning的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。