[Pandas] 数据迭代
df
![[Pandas] 数据迭代_第1张图片](http://img.e-com-net.com/image/info8/0f2527eb859c4d23bf23419dc97630a4.jpg)
1.迭代Series
Series本身是一个可迭代的对象，可直接对Series使用for语句来遍历它的值
import pandas as pd
df = pd.DataFrame([['liver','E',89,21,24,64],
['Arry','C',36,37,37,57],
['Ack','A',57,60,18,84],
['Eorge','C',93,96,71,78],
['Oah','D',65,49,61,86]
],
columns = ['name','team','Q1','Q2','Q3','Q4'])
# 迭代指定的列
for i in df.name:
print(i)
# 效果和上面相同
# df.name.values返回array结构数据可用于迭代
for i in df.name.values:
print(i)
# 输出结果:
# liver
# Arry
# Ack
# Eorge
# Oah迭代索引和指定的多列，使用python内置的zip函数将其打包为可迭代的zip对象
import pandas as pd
df = pd.DataFrame([['liver','E',89,21,24,64],
['Arry','C',36,37,37,57],
['Ack','A',57,60,18,84],
['Eorge','C',93,96,71,78],
['Oah','D',65,49,61,86]
],
columns = ['name','team','Q1','Q2','Q3','Q4'])
# 迭代索引和指定的两列
for i, n, q in zip(df.index, df.name, df.Q1):
print(i, n, q)
# 输出结果:
# 0 liver 89
# 1 Arry 36
# 2 Ack 57
# 3 Eorge 93
# 4 Oah 652. df.iterrows()
df.iterrows()生成一个可迭代对象，将DataFrame行作为(索引，行数据)组成的Series数据对进行迭代。在for语句中需要两个变量来承接数据:一个为索引变量，即使索引在迭代中不会使用(这种情况可用useless作为变量名);另一个为数据变量，读取具体列时，可以使用字典的方法和对象属性的方法
df.iterrows()是最常用、最方便的按行迭代方法
import pandas as pd
df = pd.DataFrame([['liver','E',89,21,24,64],
['Arry','C',36,37,37,57],
['Ack','A',57,60,18,84],
['Eorge','C',93,96,71,78],
['Oah','D',65,49,61,86]
],
columns = ['name','team','Q1','Q2','Q3','Q4'])
# 迭代,使用name,Q1数据
for index, row in df.iterrows():
print(index, row['name'], row.Q1)
# 输出结果:
# 0 liver 89
# 1 Arry 36
# 2 Ack 57
# 3 Eorge 93
# 4 Oah 653 df.itertuples()
df.itertuples()生成一个namedtuples类型数据，name默认名为Pandas，可以在参数中指定
与df.iterrows()相比,df.itertuples()运行速度会更快一些，推荐在数据量庞大的情况下优先使用
import pandas as pd
df = pd.DataFrame([['liver','E',89,21,24,64],
['Arry','C',36,37,37,57],
['Ack','A',57,60,18,84],
['Eorge','C',93,96,71,78],
['Oah','D',65,49,61,86]
],
columns = ['name','team','Q1','Q2','Q3','Q4'])
for row in df.itertuples():
print(row)
# 输出结果:
# Pandas(Index=0, name='liver', team='E', Q1=89, Q2=21, Q3=24, Q4=64)
# Pandas(Index=1, name='Arry', team='C', Q1=36, Q2=37, Q3=37, Q4=57)
# Pandas(Index=2, name='Ack', team='A', Q1=57, Q2=60, Q3=18, Q4=84)
# Pandas(Index=3, name='Eorge', team='C', Q1=93, Q2=96, Q3=71, Q4=78)
# Pandas(Index=4, name='Oah', team='D', Q1=65, Q2=49, Q3=61, Q4=86)以下是一些使用方法示例:
import pandas as pd
df = pd.DataFrame([['liver','E',89,21,24,64],
['Arry','C',36,37,37,57],
['Ack','A',57,60,18,84],
['Eorge','C',93,96,71,78],
['Oah','D',65,49,61,86]
],
columns = ['name','team','Q1','Q2','Q3','Q4'])
# 不包含索引数据
for row in df.itertuples(index=False):
print(row)
# Pandas(name='liver', team='E', Q1=89, Q2=21, Q3=24, Q4=64)
# Pandas(name='Arry', team='C', Q1=36, Q2=37, Q3=37, Q4=57)
# Pandas(name='Ack', team='A', Q1=57, Q2=60, Q3=18, Q4=84)
# Pandas(name='Eorge', team='C', Q1=93, Q2=96, Q3=71, Q4=78)
# Pandas(name='Oah', team='D', Q1=65, Q2=49, Q3=61, Q4=86)
# 自定义name
# namedtuples
for row in df.itertuples(index=False, name='Hudas'):
print(row)
# Hudas(name='liver', team='E', Q1=89, Q2=21, Q3=24, Q4=64)
# Hudas(name='Arry', team='C', Q1=36, Q2=37, Q3=37, Q4=57)
# Hudas(name='Ack', team='A', Q1=57, Q2=60, Q3=18, Q4=84)
# Hudas(name='Eorge', team='C', Q1=93, Q2=96, Q3=71, Q4=78)
# Hudas(name='Oah', team='D', Q1=65, Q2=49, Q3=61, Q4=86)
# 使用数据
for row in df.itertuples():
print(row.Index, row.name)
# 0 liver
# 1 Arry
# 2 Ack
# 3 Eorge
# 4 Oah
4 df.items()
df.items()和df.iteritems()功能相同，它迭代时返回一个(列名，本列的Series结构数据),实现对列的迭代
如果需要对Series的数据再进行迭代，可嵌套for循环
import pandas as pd
df = pd.DataFrame([['liver','E',89,21,24,64],
['Arry','C',36,37,37,57],
['Ack','A',57,60,18,84],
['Eorge','C',93,96,71,78],
['Oah','D',65,49,61,86]
],
columns = ['name','team','Q1','Q2','Q3','Q4'])
# Series取前三个
for label, ser in df.items():
print(label)
print(ser[:3], end='\n\n')
# 输出结果:------------------------------------------------------------------------------
name
0 liver
1 Arry
2 Ack
Name: name, dtype: object
team
0 E
1 C
2 A
Name: team, dtype: object
Q1
0 89
1 36
2 57
Name: Q1, dtype: int64
Q2
0 21
1 37
2 60
Name: Q2, dtype: int64
Q3
0 24
1 37
2 18
Name: Q3, dtype: int64
Q4
0 64
1 57
2 84
Name: Q4, dtype: int64
#----------------------------------------------------------------------------------------5 按列迭代
除了df.items()，如需要迭代一个DataFrame的列，可以直接对DataFrame迭代，会循环得到列名
import pandas as pd
df = pd.DataFrame([['liver','E',89,21,24,64],
['Arry','C',36,37,37,57],
['Ack','A',57,60,18,84],
['Eorge','C',93,96,71,78],
['Oah','D',65,49,61,86]
],
columns = ['name','team','Q1','Q2','Q3','Q4'])
# 直接对DataFrame迭代
for column in df:
print(column)
# 输出结果:
# name
# team
# Q1
# Q2
# Q3
# Q4
# 再利用df[列名]的方法迭代列
# 依次取出每个列
for column in df:
print(df[column])
# 输出结果:------------------------------------------------------------------------------
0 liver
1 Arry
2 Ack
3 Eorge
4 Oah
Name: name, dtype: object
0 E
1 C
2 A
3 C
4 D
Name: team, dtype: object
0 89
1 36
2 57
3 93
4 65
Name: Q1, dtype: int64
0 21
1 37
2 60
3 96
4 49
Name: Q2, dtype: int64
0 24
1 37
2 18
3 71
4 61
Name: Q3, dtype: int64
0 64
1 57
2 84
3 78
4 86
Name: Q4, dtype: int64
#----------------------------------------------------------------------------------------
# 可对每个列的内容进行迭代:
for column in df:
for i in df[column]:
print(i)
# 输出结果:------------------------------------------------------------------------------
liver
Arry
Ack
Eorge
Oah
E
C
A
C
D
89
36
57
93
65
21
37
60
96
49
24
37
18
71
61
64
57
84
78
86
#----------------------------------------------------------------------------------------
# 可以迭代指定列
for i in df.name:
print(i)
# 输出结果:
# liver
# Arry
# Ack
# Eorge
# Oah
# 只迭代想要的列
l = ['name','Q1']
cols = df.columns.intersection(l)
for col in cols:
print(col)
# 输出结果:
# name
# Q1