数据清洗之 数据增加和删除

数据增加和删除

• 在数据中，直接添加列
• 使用df.insert方法在数据中添加一列
• drop(labels, axis, inplace=True)方法（删除）
  • labels表示删除的数据，axis表示作用轴，inplace=True表示是否对原数据生效
  • axis=0按行操作，axis=1按列操作
• 使用del函数直接删除其中一列

import pandas as pd
import os
import numpy as np

os.getcwd()

'D:\\Jupyter\\notebook\\Python数据清洗实战\\数据'

os.chdir('D:\\Jupyter\\notebook\\Python数据清洗实战\\数据')

df = pd.read_csv('baby_trade_history.csv', encoding='utf-8', dtype={'user_id':str})

df['购买量'] = np.where(df['buy_mount']>3, '高', '低')

df.head(5)

	user_id	auction_id	cat_id	cat1	property	buy_mount	day	购买量
0	786295544	41098319944	50014866	50022520	21458:86755362;13023209:3593274;10984217:21985...	2	20140919	低
1	532110457	17916191097	50011993	28	21458:11399317;1628862:3251296;21475:137325;16...	1	20131011	低
2	249013725	21896936223	50012461	50014815	21458:30992;1628665:92012;1628665:3233938;1628...	1	20131011	低
3	917056007	12515996043	50018831	50014815	21458:15841995;21956:3494076;27000458:59723383...	2	20141023	低
4	444069173	20487688075	50013636	50008168	21458:30992;13658074:3323064;1628665:3233941;1...	1	20141103	低

# 将第二列放在第一列
auction_id = df['auction_id']

del df['auction_id']

df.head(5)

	user_id	cat_id	cat1	property	buy_mount	day	购买量
0	786295544	50014866	50022520	21458:86755362;13023209:3593274;10984217:21985...	2	20140919	低
1	532110457	50011993	28	21458:11399317;1628862:3251296;21475:137325;16...	1	20131011	低
2	249013725	50012461	50014815	21458:30992;1628665:92012;1628665:3233938;1628...	1	20131011	低
3	917056007	50018831	50014815	21458:15841995;21956:3494076;27000458:59723383...	2	20141023	低
4	444069173	50013636	50008168	21458:30992;13658074:3323064;1628665:3233941;1...	1	20141103	低

# 第一个参数：插入位置
# 第二个参数：标签名称
# 第三个参数：数据
df.insert(0, 'auction_id_new', auction_id)

df.head(5)

	auction_id_new	user_id	cat_id	cat1	property	buy_mount	day	购买量
0	41098319944	786295544	50014866	50022520	21458:86755362;13023209:3593274;10984217:21985...	2	20140919	低
1	17916191097	532110457	50011993	28	21458:11399317;1628862:3251296;21475:137325;16...	1	20131011	低
2	21896936223	249013725	50012461	50014815	21458:30992;1628665:92012;1628665:3233938;1628...	1	20131011	低
3	12515996043	917056007	50018831	50014815	21458:15841995;21956:3494076;27000458:59723383...	2	20141023	低
4	20487688075	444069173	50013636	50008168	21458:30992;13658074:3323064;1628665:3233941;1...	1	20141103	低

# 删除两列数据
df.drop(labels=['auction_id_new', '购买量'], axis=1).head(5)

	user_id	cat_id	cat1	property	buy_mount	day
0	786295544	50014866	50022520	21458:86755362;13023209:3593274;10984217:21985...	2	20140919
1	532110457	50011993	28	21458:11399317;1628862:3251296;21475:137325;16...	1	20131011
2	249013725	50012461	50014815	21458:30992;1628665:92012;1628665:3233938;1628...	1	20131011
3	917056007	50018831	50014815	21458:15841995;21956:3494076;27000458:59723383...	2	20141023
4	444069173	50013636	50008168	21458:30992;13658074:3323064;1628665:3233941;1...	1	20141103

# 再次查看df，发现刚才删除数据仍然存在
# 因为没有对原数据生效 
df.head(5)

	auction_id_new	user_id	cat_id	cat1	property	buy_mount	day	购买量
0	41098319944	786295544	50014866	50022520	21458:86755362;13023209:3593274;10984217:21985...	2	20140919	低
1	17916191097	532110457	50011993	28	21458:11399317;1628862:3251296;21475:137325;16...	1	20131011	低
2	21896936223	249013725	50012461	50014815	21458:30992;1628665:92012;1628665:3233938;1628...	1	20131011	低
3	12515996043	917056007	50018831	50014815	21458:15841995;21956:3494076;27000458:59723383...	2	20141023	低
4	20487688075	444069173	50013636	50008168	21458:30992;13658074:3323064;1628665:3233941;1...	1	20141103	低

df.drop(labels=['auction_id_new', '购买量'], axis=1, inplace=True)

---------------------------------------------------------------------------

KeyError                                  Traceback (most recent call last)

<ipython-input-30-acf2a75acaf3> in <module>
----> 1 df.drop(labels=['auction_id_new', '购买量'], axis=1, inplace=True)


D:\Anaconda3\lib\site-packages\pandas\core\frame.py in drop(self, labels, axis, index, columns, level, inplace, errors)
   3938                                            index=index, columns=columns,
   3939                                            level=level, inplace=inplace,
-> 3940                                            errors=errors)
   3941 
   3942     @rewrite_axis_style_signature('mapper', [('copy', True),


D:\Anaconda3\lib\site-packages\pandas\core\generic.py in drop(self, labels, axis, index, columns, level, inplace, errors)
   3778         for axis, labels in axes.items():
   3779             if labels is not None:
-> 3780                 obj = obj._drop_axis(labels, axis, level=level, errors=errors)
   3781 
   3782         if inplace:


D:\Anaconda3\lib\site-packages\pandas\core\generic.py in _drop_axis(self, labels, axis, level, errors)
   3810                 new_axis = axis.drop(labels, level=level, errors=errors)
   3811             else:
-> 3812                 new_axis = axis.drop(labels, errors=errors)
   3813             result = self.reindex(**{axis_name: new_axis})
   3814 


D:\Anaconda3\lib\site-packages\pandas\core\indexes\base.py in drop(self, labels, errors)
   4963             if errors != 'ignore':
   4964                 raise KeyError(
-> 4965                     '{} not found in axis'.format(labels[mask]))
   4966             indexer = indexer[~mask]
   4967         return self.delete(indexer)


KeyError: "['auction_id_new' '购买量'] not found in axis"

df.head(5)

	user_id	cat_id	cat1	property	buy_mount	day
0	786295544	50014866	50022520	21458:86755362;13023209:3593274;10984217:21985...	2	20140919
1	532110457	50011993	28	21458:11399317;1628862:3251296;21475:137325;16...	1	20131011
2	249013725	50012461	50014815	21458:30992;1628665:92012;1628665:3233938;1628...	1	20131011
3	917056007	50018831	50014815	21458:15841995;21956:3494076;27000458:59723383...	2	20141023
4	444069173	50013636	50008168	21458:30992;13658074:3323064;1628665:3233941;1...	1	20141103

# 删除标签为3，4数据
df.drop(labels=[3,4], axis=0, inplace=True)

df.head(5)

	user_id	cat_id	cat1	property	buy_mount	day
0	786295544	50014866	50022520	21458:86755362;13023209:3593274;10984217:21985...	2	20140919
1	532110457	50011993	28	21458:11399317;1628862:3251296;21475:137325;16...	1	20131011
2	249013725	50012461	50014815	21458:30992;1628665:92012;1628665:3233938;1628...	1	20131011
5	152298847	121394024	50008168	21458:3408353;13023209:727117752;22009:2741771...	1	20141103
6	513441334	50010557	50008168	25935:21991;1628665:29784;22019:34731;22019:20...	1	20121212

df.drop(labels=range(0,3), axis=0, inplace=True)

df.head(5)

	user_id	cat_id	cat1	property	buy_mount	day
5	152298847	121394024	50008168	21458:3408353;13023209:727117752;22009:2741771...	1	20141103
6	513441334	50010557	50008168	25935:21991;1628665:29784;22019:34731;22019:20...	1	20121212
7	297411659	50010542	50008168	21458:60020529;25935:31381;1633959:27247291;16...	1	20121212
8	82830661	50013874	28	21458:11580;21475:137325	1	20121101
9	475046636	203527	28	22724:40168;22729:40278;21458:21817;2770200:24...	1	20121101