python数据分析-pandas相关操作复习1-2

关注

原创最新推荐文章于 2026-10-11 15:59:29 发布 363 阅读 AI 写同款· GEO 优化 ›

利用Python进行数据分析（二）— pandas 2.1数据结构 andas是含有使数据分析工作变得更快更简单的高级数据结构和操作工具。pandas是基于NumPy构建的，让以NumPy为中心的应用变得更加简单。导入pandasPandas主要有两种数据结构：Series和DataFrameSeries是一维标记数组，类似于Python中的列表或数组。它由一组数据和一组与之相关的索引（标签）组成。Series的字符串表现形式为:索引在左边，值在右边。由于没有为数据指定索引，于是会自动创建一个0到N-1(N为数据的长度)的整数型索引。输出将。阅读详情

import pandas as pd
import numpy as np
#read the dataset
data_BM = pd.read_csv("bigmart_data.csv")
#drop the null values 
data_BM = data_BM.dropna(how = "any")
#view the results
data_BM.head()
#out<<
	Item_Identifier	Item_Weight	Item_Fat_Content	Item_Visibility	Item_Type	Item_MRP	Outlet_Identifier	Outlet_Establishment_Year	Outlet_Size	Outlet_Location_Type	Outlet_Type	Item_Outlet_Sales
0	FDA15	9.300	Low Fat	0.016047	Dairy	249.8092	OUT049	1999	Medium	Tier 1	Supermarket Type1	3735.1380
1	DRC01	5.920	Regular	0.019278	Soft Drinks	48.2692	OUT018	2009	Medium	Tier 3	Supermarket Type2	443.4228
2	FDN15	17.500	Low Fat	0.016760	Meat	141.6180	OUT049	1999	Medium	Tier 1	Supermarket Type1	2097.2700
4	NCD19	8.930	Low Fat	0.000000	Household	53.8614	OUT013	1987	High	Tier 3	Supermarket Type1	994.7052
5	FDP36	10.395	Regular	0.000000	Baking Goods	51.4008	OUT018	2009	Medium	Tier 3	Supermarket Type2	556.6088

#sort by year 
sorted_data = data_BM.sort_values(by = 'Outlet_Establishment_Year')
#print sorted data 
sorted_data.head()
#out<<
	Item_Identifier	Item_Weight	Item_Fat_Content	Item_Visibility	Item_Type	Item_MRP	Outlet_Identifier	Outlet_Establishment_Year	Outlet_Size	Outlet_Location_Type	Outlet_Type	Item_Outlet_Sales
2812	FDR60	14.30	Low Fat	0.130307	Baking Goods	75.7328	OUT013	1987	High	Tier 3	Supermarket Type1	617.8624
5938	NCJ06	20.10	Low Fat	0.034624	Household	118.9782	OUT013	1987	High	Tier 3	Supermarket Type1	1549.3166
3867	FDY38	13.60	Regular	0.119077	Dairy	231.2300	OUT013	1987	High	Tier 3	Supermarket Type1	2330.3000
1307	FDB37	20.25	Regular	0.022922	Baking Goods	240.7538	OUT013	1987	High	Tier 3	Supermarket Type1	3364.9532
5930	NCA18	10.10	Low Fat	0.056031	Household	115.1492	OUT013	1987	High	Tier 3	Supermarket Type1	1737.7380

#sort in place and decending order
data_BM.sort_values(by = 'Outlet_Establishment_Year',asending = False,inplace = True )
data_BM.head()
#out<<
	Item_Identifier	Item_Weight	Item_Fat_Content	Item_Visibility	Item_Type	Item_MRP	Outlet_Identifier	Outlet_Establishment_Year	Outlet_Size	Outlet_Location_Type	Outlet_Type	Item_Outlet_Sales
2825	FDL16	12.850	Low Fat	0.169139	Frozen Foods	46.4060	OUT018	2009	Medium	Tier 3	Supermarket Type2	186.4240
6319	FDP58	11.100	Low Fat	0.135693	Snack Foods	220.0482	OUT018	2009	Medium	Tier 3	Supermarket Type2	2628.5784
6347	FDR12	12.600	Regular	0.031663	Baking Goods	173.2764	OUT018	2009	Medium	Tier 3	Supermarket Type2	1030.6584
4274	FDR47	17.850	Low Fat	0.087825	Breads	196.0794	OUT018	2009	Medium	Tier 3	Supermarket Type2	1755.7146
4275	FDJ10	5.095	Regular	0.130031	Snack Foods	142.4838	OUT018	2009	Medium	Tier 3	Supermarket Type2	561.9352

# sort by index 
data_BM.sort_index(inplace = True)
data_BM.head()
#out<<
	Item_Identifier	Item_Weight	Item_Fat_Content	Item_Visibility	Item_Type	Item_MRP	Outlet_Identifier	Outlet_Establishment_Year	Outlet_Size	Outlet_Location_Type	Outlet_Type	Item_Outlet_Sales
0	FDA15	9.300	Low Fat	0.016047	Dairy	249.8092	OUT049	1999	Medium	Tier 1	Supermarket Type1	3735.1380
1	DRC01	5.920	Regular	0.019278	Soft Drinks	48.2692	OUT018	2009	Medium	Tier 3	Supermarket Type2	443.4228
2	FDN15	17.500	Low Fat	0.016760	Meat	141.6180	OUT049	1999	Medium	Tier 1	Supermarket Type1	2097.2700
4	NCD19	8.930	Low Fat	0.000000	Household	53.8614	OUT013	1987	High	Tier 3	Supermarket Type1	994.7052
5	FDP36	10.395	Regular	0.000000	Baking Goods	51.4008	OUT018	2009	Medium	Tier 3	Supermarket Type2	556.6088

2.Merging dataframes-concat()

#import requied dictionary
import pandas as pd

# create dummy data
df1 = pd.DataFrame({'A': ['A0', 'A1', 'A2', 'A3'],
                     'B': ['B0', 'B1', 'B2', 'B3'],
                     'C': ['C0', 'C1', 'C2', 'C3'],
                     'D': ['D0', 'D1', 'D2', 'D3']},
                    index=[0, 1, 2, 3])
 

df2 = pd.DataFrame({'A': ['A4', 'A5', 'A6', 'A7'],
                     'B': ['B4', 'B5', 'B6', 'B7'],
                     'C': ['C4', 'C5', 'C6', 'C7'],
                     'D': ['D4', 'D5', 'D6', 'D7']},
                    index=[4, 5, 6, 7])
 

df3 = pd.DataFrame({'A': ['A8', 'A9', 'A10', 'A11'],
                     'B': ['B8', 'B9', 'B10', 'B11'],
                     'C': ['C8', 'C9', 'C10', 'C11'],
                     'D': ['D8', 'D9', 'D10', 'D11']},
                    index=[8, 9, 10, 11])

#combine dataframes 
result = pd.concat([df2,df2,df3])
result
#out<<
	A	B	C	D
0	A0	B0	C0	D0
1	A1	B1	C1	D1
2	A2	B2	C2	D2
3	A3	B3	C3	D3
4	A4	B4	C4	D4
5	A5	B5	C5	D5
6	A6	B6	C6	D6
7	A7	B7	C7	D7
8	A8	B8	C8	D8
9	A9	B9	C9	D9
10	A10	B10	C10	D10
11	A11	B11	C11	D11

#combine dataframes with key
reult1 = pd.concat([df1,df2,df3],keys = ['x','y','z'])
result1
#out<<
		A	B	C	D
x	0	A0	B0	C0	D0
1	A1	B1	C1	D1
2	A2	B2	C2	D2
3	A3	B3	C3	D3
y	4	A4	B4	C4	D4
5	A5	B5	C5	D5
6	A6	B6	C6	D6
7	A7	B7	C7	D7
z	8	A8	B8	C8	D8
9	A9	B9	C9	D9
10	A10	B10	C10	D10
11	A11	B11	C11	D11

#get dataframe by key
result1.loc['x'] 
#location
#out<<
A	B	C	D
0	A0	B0	C0	D0
1	A1	B1	C1	D1
2	A2	B2	C2	D2
3	A3	B3	C3	D3

df4 = pd.DataFrame({'B': ['B2', 'B3', 'B6', 'B7'],
                        'D': ['D2', 'D3', 'D6', 'D7'],
                        'F': ['F2', 'F3', 'F6', 'F7']},
                       index=[2, 3, 6, 7])

result = pd.concat([df1,df4],axis = 1,sort =False)
result
#out<<
A	B	C	D	B	D	F
0	A0	B0	C0	D0	NaN	NaN	NaN
1	A1	B1	C1	D1	NaN	NaN	NaN
2	A2	B2	C2	D2	B2	D2	F2
3	A3	B3	C3	D3	B3	D3	F3
6	NaN	NaN	NaN	NaN	B6	D6	F6
7	NaN	NaN	NaN	NaN	B7	D7	F7

result = pd.concat([df1,df4],axis = 0,sort = False)
result
#out<<
A	B	C	D	F
0	A0	B0	C0	D0	NaN
1	A1	B1	C1	D1	NaN
2	A2	B2	C2	D2	NaN
3	A3	B3	C3	D3	NaN
2	NaN	B2	NaN	D2	F2
3	NaN	B3	NaN	D3	F3
6	NaN	B6	NaN	D6	F6
7	NaN	B7	NaN	D7	F7

result = pd.concat([df1,df4],axis = 1,sort = True)
result
#out<<
A	B	C	D	B	D	F
0	A0	B0	C0	D0	NaN	NaN	NaN
1	A1	B1	C1	D1	NaN	NaN	NaN
2	A2	B2	C2	D2	B2	D2	F2
3	A3	B3	C3	D3	B3	D3	F3
6	NaN	NaN	NaN	NaN	B6	D6	F6
7	NaN	NaN	NaN	NaN	B7	D7	F7

result = pd.concat([df1, df4], axis=1, join='inner')
result
#交集
#out<<
	A	B	C	D	B	D	F
2	A2	B2	C2	D2	B2	D2	F2
3	A3	B3	C3	D3	B3	D3	F3

result = pd.concat([df1, df4], axis=1, join_axes=[df1.index])
result
#并集
#out<<
A	B	C	D	B	D	F
0	A0	B0	C0	D0	NaN	NaN	NaN
1	A1	B1	C1	D1	NaN	NaN	NaN
2	A2	B2	C2	D2	B2	D2	F2
3	A3	B3	C3	D3	B3	D3	F3