pandas5:DataFrame的链接concat，合并merge与删除drop

灰太狼 2023-02-26 12:23 53阅读 0赞

# 1.链接，concat #

## 1.1行链接 ##

import pandas as pd

df1 = pd.read_csv('./data/concat_1.csv')
    print(df1)
    df2 = pd.read_csv('./data/concat_2.csv')
    print(df2)
    df3 = pd.read_csv('./data/concat_3.csv')
    print(df3)

A   B   C   D
    0  a0  b0  c0  d0
    1  a1  b1  c1  d1
    2  a2  b2  c2  d2
    3  a3  b3  c3  d3
        A   B   C   D
    0  a4  b4  c4  d4
    1  a5  b5  c5  d5
    2  a6  b6  c6  d6
    3  a7  b7  c7  d7
         A    B    C    D
    0   a8   b8   c8   d8
    1   a9   b9   c9   d9
    2  a10  b10  c10  d10
    3  a11  b11  c11  d11

row_concat = pd.concat([df1, df2, df3])
    print(row_concat)

A    B    C    D
    0   a0   b0   c0   d0
    1   a1   b1   c1   d1
    2   a2   b2   c2   d2
    3   a3   b3   c3   d3
    0   a4   b4   c4   d4
    1   a5   b5   c5   d5
    2   a6   b6   c6   d6
    3   a7   b7   c7   d7
    0   a8   b8   c8   d8
    1   a9   b9   c9   d9
    2  a10  b10  c10  d10
    3  a11  b11  c11  d11

print(row_concat.iloc[4,])
    print(row_concat.iloc[4:6,])

A    a4
    B    b4
    C    c4
    D    d4
    Name: 0, dtype: object
        A   B   C   D
    0  a4  b4  c4  d4
    1  a5  b5  c5  d5

new_row_series = pd.Series(['n1','n2','n3','n4'])
    print(new_row_series)

0    n1
    1    n2
    2    n3
    3    n4
    dtype: object

print(pd.concat([df1, new_row_series]))

A    B    C    D    0
    0   a0   b0   c0   d0  NaN
    1   a1   b1   c1   d1  NaN
    2   a2   b2   c2   d2  NaN
    3   a3   b3   c3   d3  NaN
    0  NaN  NaN  NaN  NaN   n1
    1  NaN  NaN  NaN  NaN   n2
    2  NaN  NaN  NaN  NaN   n3
    3  NaN  NaN  NaN  NaN   n4

new_row_df = pd.DataFrame([['n1','n2','n3','n4']],
                             columns=['A','B','C','D'])
    print(new_row_df)

A   B   C   D
    0  n1  n2  n3  n4

print(pd.concat([df1,new_row_df]))
    print(pd.concat([df1,new_row_df],ignore_index=True))

A   B   C   D
    0  a0  b0  c0  d0
    1  a1  b1  c1  d1
    2  a2  b2  c2  d2
    3  a3  b3  c3  d3
    0  n1  n2  n3  n4
        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  n1  n2  n3  n4

## 1.2列拼接 ##

df1 = pd.read_csv('./data/concat_1.csv')
    print(df1)
    df2 = pd.read_csv('./data/concat_2.csv')
    print(df2)
    df3 = pd.read_csv('./data/concat_3.csv')
    print(df3)

col_concat = pd.concat([df1, df2, df3],axis=1)
    print(col_concat)

A   B   C   D   A   B   C   D    A    B    C    D
    0  a0  b0  c0  d0  a4  b4  c4  d4   a8   b8   c8   d8
    1  a1  b1  c1  d1  a5  b5  c5  d5   a9   b9   c9   d9
    2  a2  b2  c2  d2  a6  b6  c6  d6  a10  b10  c10  d10
    3  a3  b3  c3  d3  a7  b7  c7  d7  a11  b11  c11  d11

print(col_concat['B'])

B   B    B
    0  b0  b4   b8
    1  b1  b5   b9
    2  b2  b6  b10
    3  b3  b7  b11

# ADD NEW COL
    col_concat['new_col_list'] = ['n1','n2','n3','n4']
    print(col_concat)

A   B   C   D   A   B   C   D    A    B    C    D new_col_list
    0  a0  b0  c0  d0  a4  b4  c4  d4   a8   b8   c8   d8           n1
    1  a1  b1  c1  d1  a5  b5  c5  d5   a9   b9   c9   d9           n2
    2  a2  b2  c2  d2  a6  b6  c6  d6  a10  b10  c10  d10           n3
    3  a3  b3  c3  d3  a7  b7  c7  d7  a11  b11  c11  d11           n4

# 用Series添加一列
    col_concat['new_col_series'] = pd.Series(['n1','n2','n3','n4'])
    print(col_concat)

A   B   C   D   A   B   C   D    A    B    C    D new_col_list  \
    0  a0  b0  c0  d0  a4  b4  c4  d4   a8   b8   c8   d8           n1   
    1  a1  b1  c1  d1  a5  b5  c5  d5   a9   b9   c9   d9           n2   
    2  a2  b2  c2  d2  a6  b6  c6  d6  a10  b10  c10  d10           n3   
    3  a3  b3  c3  d3  a7  b7  c7  d7  a11  b11  c11  d11           n4   
    
      new_col_series  
    0             n1  
    1             n2  
    2             n3  
    3             n4

col_concat = pd.concat([df1,df2,df3],axis=1,ignore_index=True)
    print(col_concat)

0   1   2   3   4   5   6   7    8    9    10   11
    0  a0  b0  c0  d0  a4  b4  c4  d4   a8   b8   c8   d8
    1  a1  b1  c1  d1  a5  b5  c5  d5   a9   b9   c9   d9
    2  a2  b2  c2  d2  a6  b6  c6  d6  a10  b10  c10  d10
    3  a3  b3  c3  d3  a7  b7  c7  d7  a11  b11  c11  d11

print(col_concat[2])

0    c0
    1    c1
    2    c2
    3    c3
    Name: 2, dtype: object

print(col_concat[2][1])

print(col_concat[1:3])

0   1   2   3   4   5   6   7    8    9    10   11
    1  a1  b1  c1  d1  a5  b5  c5  d5   a9   b9   c9   d9
    2  a2  b2  c2  d2  a6  b6  c6  d6  a10  b10  c10  d10

# 拥有不同列的data_frame
    df1 = pd.read_csv('./data/concat_1.csv')
    df2 = pd.read_csv('./data/concat_2.csv')
    df3 = pd.read_csv('./data/concat_3.csv')

df1.columns = ['A','B','C','D']
    df2.columns = ['E','F','G','H']
    df3.columns = ['A','C','F','H']

print(df1)
    print(df2)
    print(df3)

A   B   C   D
    0  a0  b0  c0  d0
    1  a1  b1  c1  d1
    2  a2  b2  c2  d2
    3  a3  b3  c3  d3
        E   F   G   H
    0  a4  b4  c4  d4
    1  a5  b5  c5  d5
    2  a6  b6  c6  d6
    3  a7  b7  c7  d7
         A    C    F    H
    0   a8   b8   c8   d8
    1   a9   b9   c9   d9
    2  a10  b10  c10  d10
    3  a11  b11  c11  d11

col_concat = pd.concat([df1,df2,df3])
    print(col_concat)

A    B    C    D    E    F    G    H
    0   a0   b0   c0   d0  NaN  NaN  NaN  NaN
    1   a1   b1   c1   d1  NaN  NaN  NaN  NaN
    2   a2   b2   c2   d2  NaN  NaN  NaN  NaN
    3   a3   b3   c3   d3  NaN  NaN  NaN  NaN
    0  NaN  NaN  NaN  NaN   a4   b4   c4   d4
    1  NaN  NaN  NaN  NaN   a5   b5   c5   d5
    2  NaN  NaN  NaN  NaN   a6   b6   c6   d6
    3  NaN  NaN  NaN  NaN   a7   b7   c7   d7
    0   a8  NaN   b8  NaN  NaN   c8  NaN   d8
    1   a9  NaN   b9  NaN  NaN   c9  NaN   d9
    2  a10  NaN  b10  NaN  NaN  c10  NaN  d10
    3  a11  NaN  b11  NaN  NaN  c11  NaN  d11
    
    
    /home/leon/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:1: FutureWarning: Sorting because non-concatenation axis is not aligned. A future version
    of pandas will change to not sort by default.
    
    To accept the future behavior, pass 'sort=False'.
    
    To retain the current behavior and silence the warning, pass 'sort=True'.
    
      """Entry point for launching an IPython kernel.

# 2合并,merge #

关系型数据库中的两个表之间的链接

# table1.field1 table.field2
    # select table1.field1,table2.field2
    # where table1.field1 = table2.field
    
    # 1. one vs one
    # 2. more vs one 
    # 3. more vs more

import pandas as pd

person = pd.read_csv('./data/survey_person.csv')
    site = pd.read_csv('./data/survey_site.csv')
    survey = pd.read_csv('./data/survey_survey.csv')
    visited = pd.read_csv('./data/survey_visited.csv')

print(person)
    print(site)
    print(survey)
    print(visited)

ident   personal    family
    0      dyer    William      Dyer
    1        pb      Frank   Pabodie
    2      lake   Anderson      Lake
    3       roe  Valentina   Roerich
    4  danforth      Frank  Danforth
        name    lat    long
    0   DR-1 -49.85 -128.57
    1   DR-3 -47.15 -126.72
    2  MSK-4 -48.87 -123.40
        taken person quant  reading
    0     619   dyer   rad     9.82
    1     619   dyer   sal     0.13
    2     622   dyer   rad     7.80
    3     622   dyer   sal     0.09
    4     734     pb   rad     8.41
    5     734   lake   sal     0.05
    6     734     pb  temp   -21.50
    7     735     pb   rad     7.22
    8     735    NaN   sal     0.06
    9     735    NaN  temp   -26.00
    10    751     pb   rad     4.35
    11    751     pb  temp   -18.50
    12    751   lake   sal     0.10
    13    752   lake   rad     2.19
    14    752   lake   sal     0.09
    15    752   lake  temp   -16.00
    16    752    roe   sal    41.60
    17    837   lake   rad     1.46
    18    837   lake   sal     0.21
    19    837    roe   sal    22.50
    20    844    roe   rad    11.25
       ident   site       dated
    0    619   DR-1  1927-02-08
    1    622   DR-1  1927-02-10
    2    734   DR-3  1939-01-07
    3    735   DR-3  1930-01-12
    4    751   DR-3  1930-02-26
    5    752   DR-3         NaN
    6    837  MSK-4  1932-01-14
    7    844   DR-1  1932-03-22

visited_subset = visited.loc[[0,2],]
    print(visited_subset)

ident  site       dated
    0    619  DR-1  1927-02-08
    2    734  DR-3  1939-01-07

# one to one
    print(site)
    print(visited_subset)

name    lat    long
    0   DR-1 -49.85 -128.57
    1   DR-3 -47.15 -126.72
    2  MSK-4 -48.87 -123.40
       ident  site       dated
    0    619  DR-1  1927-02-08
    2    734  DR-3  1939-01-07

merge1 = site.merge(visited_subset,left_on = 'name',right_on='site')
    print(merge1)

name    lat    long  ident  site       dated
    0  DR-1 -49.85 -128.57    619  DR-1  1927-02-08
    1  DR-3 -47.15 -126.72    734  DR-3  1939-01-07

## merge多对一 ##

print(site)
    print(visited)

name    lat    long
    0   DR-1 -49.85 -128.57
    1   DR-3 -47.15 -126.72
    2  MSK-4 -48.87 -123.40
       ident   site       dated
    0    619   DR-1  1927-02-08
    1    622   DR-1  1927-02-10
    2    734   DR-3  1939-01-07
    3    735   DR-3  1930-01-12
    4    751   DR-3  1930-02-26
    5    752   DR-3         NaN
    6    837  MSK-4  1932-01-14
    7    844   DR-1  1932-03-22

merge2 = site.merge(visited,left_on = 'name',right_on='site')
    print(merge2)

name    lat    long  ident   site       dated
    0   DR-1 -49.85 -128.57    619   DR-1  1927-02-08
    1   DR-1 -49.85 -128.57    622   DR-1  1927-02-10
    2   DR-1 -49.85 -128.57    844   DR-1  1932-03-22
    3   DR-3 -47.15 -126.72    734   DR-3  1939-01-07
    4   DR-3 -47.15 -126.72    735   DR-3  1930-01-12
    5   DR-3 -47.15 -126.72    751   DR-3  1930-02-26
    6   DR-3 -47.15 -126.72    752   DR-3         NaN
    7  MSK-4 -48.87 -123.40    837  MSK-4  1932-01-14

## merge多对多 ##

print(person)
    print(survey)

ident   personal    family
    0      dyer    William      Dyer
    1        pb      Frank   Pabodie
    2      lake   Anderson      Lake
    3       roe  Valentina   Roerich
    4  danforth      Frank  Danforth
        taken person quant  reading
    0     619   dyer   rad     9.82
    1     619   dyer   sal     0.13
    2     622   dyer   rad     7.80
    3     622   dyer   sal     0.09
    4     734     pb   rad     8.41
    5     734   lake   sal     0.05
    6     734     pb  temp   -21.50
    7     735     pb   rad     7.22
    8     735    NaN   sal     0.06
    9     735    NaN  temp   -26.00
    10    751     pb   rad     4.35
    11    751     pb  temp   -18.50
    12    751   lake   sal     0.10
    13    752   lake   rad     2.19
    14    752   lake   sal     0.09
    15    752   lake  temp   -16.00
    16    752    roe   sal    41.60
    17    837   lake   rad     1.46
    18    837   lake   sal     0.21
    19    837    roe   sal    22.50
    20    844    roe   rad    11.25

merge3 = person.merge(survey,left_on = 'ident',right_on='person')
    print(merge3)

ident   personal   family  taken person quant  reading
    0   dyer    William     Dyer    619   dyer   rad     9.82
    1   dyer    William     Dyer    619   dyer   sal     0.13
    2   dyer    William     Dyer    622   dyer   rad     7.80
    3   dyer    William     Dyer    622   dyer   sal     0.09
    4     pb      Frank  Pabodie    734     pb   rad     8.41
    5     pb      Frank  Pabodie    734     pb  temp   -21.50
    6     pb      Frank  Pabodie    735     pb   rad     7.22
    7     pb      Frank  Pabodie    751     pb   rad     4.35
    8     pb      Frank  Pabodie    751     pb  temp   -18.50
    9   lake   Anderson     Lake    734   lake   sal     0.05
    10  lake   Anderson     Lake    751   lake   sal     0.10
    11  lake   Anderson     Lake    752   lake   rad     2.19
    12  lake   Anderson     Lake    752   lake   sal     0.09
    13  lake   Anderson     Lake    752   lake  temp   -16.00
    14  lake   Anderson     Lake    837   lake   rad     1.46
    15  lake   Anderson     Lake    837   lake   sal     0.21
    16   roe  Valentina  Roerich    752    roe   sal    41.60
    17   roe  Valentina  Roerich    837    roe   sal    22.50
    18   roe  Valentina  Roerich    844    roe   rad    11.25

# 3.删除drop #

import pandas as pd
    df = pd.read_csv('./data/survey_visited.csv')
    print(df)

## 2.1删除行 ##

### 删除单行 ###

df2=df.drop(labels=0)   # axis默认等于0，即按行删除，这里表示按行删除第0行
    print(df2)

ident   site       dated
    1    622   DR-1  1927-02-10
    2    734   DR-3  1939-01-07
    3    735   DR-3  1930-01-12
    4    751   DR-3  1930-02-26
    5    752   DR-3         NaN
    6    837  MSK-4  1932-01-14
    7    844   DR-1  1932-03-22

### 删除多行 ###

df3=df.drop(labels=[1,3],axis=0)   # axis=0 表示按行删除，删除第1行和第3行
    print(df)
    print(df3)

ident   site       dated
    0    619   DR-1  1927-02-08
    1    622   DR-1  1927-02-10
    2    734   DR-3  1939-01-07
    3    735   DR-3  1930-01-12
    4    751   DR-3  1930-02-26
    5    752   DR-3         NaN
    6    837  MSK-4  1932-01-14
    7    844   DR-1  1932-03-22
       ident   site       dated
    0    619   DR-1  1927-02-08
    2    734   DR-3  1939-01-07
    4    751   DR-3  1930-02-26
    5    752   DR-3         NaN
    6    837  MSK-4  1932-01-14
    7    844   DR-1  1932-03-22

**要删除连续的多行可以用range(),删除连续的多列不能用此方法**

df4=df.drop(labels=range(1,3),axis=0)   # axis=0 表示按行删除，删除索引值是第1行至第3行的正行数据
    print(df4)

ident   site       dated
    0    619   DR-1  1927-02-08
    3    735   DR-3  1930-01-12
    4    751   DR-3  1930-02-26
    5    752   DR-3         NaN
    6    837  MSK-4  1932-01-14
    7    844   DR-1  1932-03-22

## 2.2删除列 ##

### 删除单列 ###

df5=df.drop(labels='site',axis=1)  # axis=1 表示按列删除，删除gender列
    print(df)
    print(df5)

ident   site       dated
    0    619   DR-1  1927-02-08
    1    622   DR-1  1927-02-10
    2    734   DR-3  1939-01-07
    3    735   DR-3  1930-01-12
    4    751   DR-3  1930-02-26
    5    752   DR-3         NaN
    6    837  MSK-4  1932-01-14
    7    844   DR-1  1932-03-22
       ident       dated
    0    619  1927-02-08
    1    622  1927-02-10
    2    734  1939-01-07
    3    735  1930-01-12
    4    751  1930-02-26
    5    752         NaN
    6    837  1932-01-14
    7    844  1932-03-22

### 删除指定的某几列 ###

df6=df.drop(labels=['ident',"site"],axis=1)  # axis=1 表示按列删除，删除gender、age列
    print(df)
    print(df6)

ident   site       dated
    0    619   DR-1  1927-02-08
    1    622   DR-1  1927-02-10
    2    734   DR-3  1939-01-07
    3    735   DR-3  1930-01-12
    4    751   DR-3  1930-02-26
    5    752   DR-3         NaN
    6    837  MSK-4  1932-01-14
    7    844   DR-1  1932-03-22
            dated
    0  1927-02-08
    1  1927-02-10
    2  1939-01-07
    3  1930-01-12
    4  1930-02-26
    5         NaN
    6  1932-01-14
    7  1932-03-22