Python 根据日期将数据一分为二

我想按年份将我的数据分成两半。因此，在我下面的样本数据中，我需要得到两个独立的数据框，一个是每年前50%的数据框，另一个是另一半的数据框。附加条件是，50%需要以“LG”列为基础

有人能帮我吗

样本数据：

import pandas as pd
import numpy as np

df = pd.DataFrame(
    {'LG' : ('AR1', 'AR1', 'AR1', 'AR1', 'AR1', 'AR1', 'PO1',  'PO1', 'AR1', 'AR1', 'PO1', 'PO1'),
     'Date': ('2011-1-1', '2011-3-1',  '2011-4-1', '2011-2-1', '2012-1-1', '2012-2-1', '2012-1-1', '2012-2-1', '2013-1-1', '2013-2-1', '2013-1-1', '2013-2-1'),
     'Year': (2011, 2011, 2011, 2011, 2012, 2012, 2012, 2012, 2013, 2013, 2013, 2013)})

pd.to_datetime(df['Date'])

         Date   LG  Year
0  2011-01-01  AR1  2011
1  2011-03-01  AR1  2011
2  2011-04-01  AR1  2011
3  2011-02-01  AR1  2011
4  2012-01-01  AR1  2012
5  2012-02-01  AR1  2012
6  2012-01-01  PO1  2012
7  2012-02-01  PO1  2012
8  2013-01-01  AR1  2013
9  2013-02-01  AR1  2013
10 2013-01-01  PO1  2013
11 2013-02-01  PO1  2013

# group by 'Year' and 'LG'
idx = ['Year', 'LG']

# build a grouper
group_by = df.groupby(idx, as_index=False)

# need frame to re-expand the group size
df1 = df.set_index(idx)
df1['g_size'] = group_by.size()

# find the rows in the top half of respective group
top_half = (group_by.cumcount() / df1.g_size.values).values < 0.5

# build new data frames
top = df.loc[top_half]
bot = df.loc[~top_half]

print(df)
print('-- top')
print(top)
print('-- bot')
print(bot)
print('--')

        Date   LG  Year
0   2011-1-1  AR1  2011
1   2011-3-1  AR1  2011
2   2011-4-1  AR1  2011
3   2011-2-1  AR1  2011
4   2012-1-1  AR1  2012
5   2012-2-1  AR1  2012
6   2012-1-1  PO1  2012
7   2012-2-1  PO1  2012
8   2013-1-1  AR1  2013
9   2013-2-1  AR1  2013
10  2013-1-1  PO1  2013
11  2013-2-1  PO1  2013
-- top
   Year   LG      Date
0  2011  AR1  2011-1-1
1  2011  AR1  2011-2-1
2  2012  AR1  2012-1-1
3  2012  PO1  2012-1-1
4  2013  AR1  2013-1-1
5  2013  PO1  2013-1-1
-- bot
   Year   LG      Date
0  2011  AR1  2011-3-1
1  2011  AR1  2011-4-1
2  2012  AR1  2012-2-1
3  2012  PO1  2012-2-1
4  2013  AR1  2013-2-1
5  2013  PO1  2013-2-1

df = pd.DataFrame({
    'LG': ('AR1', 'AR1', 'AR1', 'AR1', 'AR1', 'AR1',
           'PO1', 'PO1', 'AR1', 'AR1', 'PO1', 'PO1'),
    'Date': ('2011-1-1', '2011-3-1', '2011-4-1', '2011-2-1', '2012-1-1',
             '2012-2-1', '2012-1-1', '2012-2-1', '2013-1-1', '2013-2-1',
             '2013-1-1', '2013-2-1'),
    'Year': (2011, 2011, 2011, 2011, 2012, 2012, 2012, 2012, 2013,
             2013, 2013, 2013)
})
pd.to_datetime(df['Date'])

df:

import pandas as pd
import numpy as np

df = pd.DataFrame(
    {'LG' : ('AR1', 'AR1', 'AR1', 'AR1', 'AR1', 'AR1', 'PO1',  'PO1', 'AR1', 'AR1', 'PO1', 'PO1'),
     'Date': ('2011-1-1', '2011-3-1',  '2011-4-1', '2011-2-1', '2012-1-1', '2012-2-1', '2012-1-1', '2012-2-1', '2013-1-1', '2013-2-1', '2013-1-1', '2013-2-1'),
     'Year': (2011, 2011, 2011, 2011, 2012, 2012, 2012, 2012, 2013, 2013, 2013, 2013)})

pd.to_datetime(df['Date'])

         Date   LG  Year
0  2011-01-01  AR1  2011
1  2011-03-01  AR1  2011
2  2011-04-01  AR1  2011
3  2011-02-01  AR1  2011
4  2012-01-01  AR1  2012
5  2012-02-01  AR1  2012
6  2012-01-01  PO1  2012
7  2012-02-01  PO1  2012
8  2013-01-01  AR1  2013
9  2013-02-01  AR1  2013
10 2013-01-01  PO1  2013
11 2013-02-01  PO1  2013

# group by 'Year' and 'LG'
idx = ['Year', 'LG']

# build a grouper
group_by = df.groupby(idx, as_index=False)

# need frame to re-expand the group size
df1 = df.set_index(idx)
df1['g_size'] = group_by.size()

# find the rows in the top half of respective group
top_half = (group_by.cumcount() / df1.g_size.values).values < 0.5

# build new data frames
top = df.loc[top_half]
bot = df.loc[~top_half]

print(df)
print('-- top')
print(top)
print('-- bot')
print(bot)
print('--')

        Date   LG  Year
0   2011-1-1  AR1  2011
1   2011-3-1  AR1  2011
2   2011-4-1  AR1  2011
3   2011-2-1  AR1  2011
4   2012-1-1  AR1  2012
5   2012-2-1  AR1  2012
6   2012-1-1  PO1  2012
7   2012-2-1  PO1  2012
8   2013-1-1  AR1  2013
9   2013-2-1  AR1  2013
10  2013-1-1  PO1  2013
11  2013-2-1  PO1  2013
-- top
   Year   LG      Date
0  2011  AR1  2011-1-1
1  2011  AR1  2011-2-1
2  2012  AR1  2012-1-1
3  2012  PO1  2012-1-1
4  2013  AR1  2013-1-1
5  2013  PO1  2013-1-1
-- bot
   Year   LG      Date
0  2011  AR1  2011-3-1
1  2011  AR1  2011-4-1
2  2012  AR1  2012-2-1
3  2012  PO1  2012-2-1
4  2013  AR1  2013-2-1
5  2013  PO1  2013-2-1

df = pd.DataFrame({
    'LG': ('AR1', 'AR1', 'AR1', 'AR1', 'AR1', 'AR1',
           'PO1', 'PO1', 'AR1', 'AR1', 'PO1', 'PO1'),
    'Date': ('2011-1-1', '2011-3-1', '2011-4-1', '2011-2-1', '2012-1-1',
             '2012-2-1', '2012-1-1', '2012-2-1', '2013-1-1', '2013-2-1',
             '2013-1-1', '2013-2-1'),
    'Year': (2011, 2011, 2011, 2011, 2012, 2012, 2012, 2012, 2013,
             2013, 2013, 2013)
})
pd.to_datetime(df['Date'])

---

在对

年份

和

LG

进行分组后，将框架一分为二。基本思想是在组中找到小于组大小50%的位置

代码：

import pandas as pd
import numpy as np

df = pd.DataFrame(
    {'LG' : ('AR1', 'AR1', 'AR1', 'AR1', 'AR1', 'AR1', 'PO1',  'PO1', 'AR1', 'AR1', 'PO1', 'PO1'),
     'Date': ('2011-1-1', '2011-3-1',  '2011-4-1', '2011-2-1', '2012-1-1', '2012-2-1', '2012-1-1', '2012-2-1', '2013-1-1', '2013-2-1', '2013-1-1', '2013-2-1'),
     'Year': (2011, 2011, 2011, 2011, 2012, 2012, 2012, 2012, 2013, 2013, 2013, 2013)})

pd.to_datetime(df['Date'])

         Date   LG  Year
0  2011-01-01  AR1  2011
1  2011-03-01  AR1  2011
2  2011-04-01  AR1  2011
3  2011-02-01  AR1  2011
4  2012-01-01  AR1  2012
5  2012-02-01  AR1  2012
6  2012-01-01  PO1  2012
7  2012-02-01  PO1  2012
8  2013-01-01  AR1  2013
9  2013-02-01  AR1  2013
10 2013-01-01  PO1  2013
11 2013-02-01  PO1  2013

# group by 'Year' and 'LG'
idx = ['Year', 'LG']

# build a grouper
group_by = df.groupby(idx, as_index=False)

# need frame to re-expand the group size
df1 = df.set_index(idx)
df1['g_size'] = group_by.size()

# find the rows in the top half of respective group
top_half = (group_by.cumcount() / df1.g_size.values).values < 0.5

# build new data frames
top = df.loc[top_half]
bot = df.loc[~top_half]

print(df)
print('-- top')
print(top)
print('-- bot')
print(bot)
print('--')

        Date   LG  Year
0   2011-1-1  AR1  2011
1   2011-3-1  AR1  2011
2   2011-4-1  AR1  2011
3   2011-2-1  AR1  2011
4   2012-1-1  AR1  2012
5   2012-2-1  AR1  2012
6   2012-1-1  PO1  2012
7   2012-2-1  PO1  2012
8   2013-1-1  AR1  2013
9   2013-2-1  AR1  2013
10  2013-1-1  PO1  2013
11  2013-2-1  PO1  2013
-- top
   Year   LG      Date
0  2011  AR1  2011-1-1
1  2011  AR1  2011-2-1
2  2012  AR1  2012-1-1
3  2012  PO1  2012-1-1
4  2013  AR1  2013-1-1
5  2013  PO1  2013-1-1
-- bot
   Year   LG      Date
0  2011  AR1  2011-3-1
1  2011  AR1  2011-4-1
2  2012  AR1  2012-2-1
3  2012  PO1  2012-2-1
4  2013  AR1  2013-2-1
5  2013  PO1  2013-2-1

df = pd.DataFrame({
    'LG': ('AR1', 'AR1', 'AR1', 'AR1', 'AR1', 'AR1',
           'PO1', 'PO1', 'AR1', 'AR1', 'PO1', 'PO1'),
    'Date': ('2011-1-1', '2011-3-1', '2011-4-1', '2011-2-1', '2012-1-1',
             '2012-2-1', '2012-1-1', '2012-2-1', '2013-1-1', '2013-2-1',
             '2013-1-1', '2013-2-1'),
    'Year': (2011, 2011, 2011, 2011, 2012, 2012, 2012, 2012, 2013,
             2013, 2013, 2013)
})
pd.to_datetime(df['Date'])

排序结果：

import pandas as pd
import numpy as np

df = pd.DataFrame(
    {'LG' : ('AR1', 'AR1', 'AR1', 'AR1', 'AR1', 'AR1', 'PO1',  'PO1', 'AR1', 'AR1', 'PO1', 'PO1'),
     'Date': ('2011-1-1', '2011-3-1',  '2011-4-1', '2011-2-1', '2012-1-1', '2012-2-1', '2012-1-1', '2012-2-1', '2013-1-1', '2013-2-1', '2013-1-1', '2013-2-1'),
     'Year': (2011, 2011, 2011, 2011, 2012, 2012, 2012, 2012, 2013, 2013, 2013, 2013)})

pd.to_datetime(df['Date'])

         Date   LG  Year
0  2011-01-01  AR1  2011
1  2011-03-01  AR1  2011
2  2011-04-01  AR1  2011
3  2011-02-01  AR1  2011
4  2012-01-01  AR1  2012
5  2012-02-01  AR1  2012
6  2012-01-01  PO1  2012
7  2012-02-01  PO1  2012
8  2013-01-01  AR1  2013
9  2013-02-01  AR1  2013
10 2013-01-01  PO1  2013
11 2013-02-01  PO1  2013

# group by 'Year' and 'LG'
idx = ['Year', 'LG']

# build a grouper
group_by = df.groupby(idx, as_index=False)

# need frame to re-expand the group size
df1 = df.set_index(idx)
df1['g_size'] = group_by.size()

# find the rows in the top half of respective group
top_half = (group_by.cumcount() / df1.g_size.values).values < 0.5

# build new data frames
top = df.loc[top_half]
bot = df.loc[~top_half]

print(df)
print('-- top')
print(top)
print('-- bot')
print(bot)
print('--')

        Date   LG  Year
0   2011-1-1  AR1  2011
1   2011-3-1  AR1  2011
2   2011-4-1  AR1  2011
3   2011-2-1  AR1  2011
4   2012-1-1  AR1  2012
5   2012-2-1  AR1  2012
6   2012-1-1  PO1  2012
7   2012-2-1  PO1  2012
8   2013-1-1  AR1  2013
9   2013-2-1  AR1  2013
10  2013-1-1  PO1  2013
11  2013-2-1  PO1  2013
-- top
   Year   LG      Date
0  2011  AR1  2011-1-1
1  2011  AR1  2011-2-1
2  2012  AR1  2012-1-1
3  2012  PO1  2012-1-1
4  2013  AR1  2013-1-1
5  2013  PO1  2013-1-1
-- bot
   Year   LG      Date
0  2011  AR1  2011-3-1
1  2011  AR1  2011-4-1
2  2012  AR1  2012-2-1
3  2012  PO1  2012-2-1
4  2013  AR1  2013-2-1
5  2013  PO1  2013-2-1

df = pd.DataFrame({
    'LG': ('AR1', 'AR1', 'AR1', 'AR1', 'AR1', 'AR1',
           'PO1', 'PO1', 'AR1', 'AR1', 'PO1', 'PO1'),
    'Date': ('2011-1-1', '2011-3-1', '2011-4-1', '2011-2-1', '2012-1-1',
             '2012-2-1', '2012-1-1', '2012-2-1', '2013-1-1', '2013-2-1',
             '2013-1-1', '2013-2-1'),
    'Year': (2011, 2011, 2011, 2011, 2012, 2012, 2012, 2012, 2013,
             2013, 2013, 2013)
})
pd.to_datetime(df['Date'])

测试数据：

import pandas as pd
import numpy as np

df = pd.DataFrame(
    {'LG' : ('AR1', 'AR1', 'AR1', 'AR1', 'AR1', 'AR1', 'PO1',  'PO1', 'AR1', 'AR1', 'PO1', 'PO1'),
     'Date': ('2011-1-1', '2011-3-1',  '2011-4-1', '2011-2-1', '2012-1-1', '2012-2-1', '2012-1-1', '2012-2-1', '2013-1-1', '2013-2-1', '2013-1-1', '2013-2-1'),
     'Year': (2011, 2011, 2011, 2011, 2012, 2012, 2012, 2012, 2013, 2013, 2013, 2013)})

pd.to_datetime(df['Date'])

         Date   LG  Year
0  2011-01-01  AR1  2011
1  2011-03-01  AR1  2011
2  2011-04-01  AR1  2011
3  2011-02-01  AR1  2011
4  2012-01-01  AR1  2012
5  2012-02-01  AR1  2012
6  2012-01-01  PO1  2012
7  2012-02-01  PO1  2012
8  2013-01-01  AR1  2013
9  2013-02-01  AR1  2013
10 2013-01-01  PO1  2013
11 2013-02-01  PO1  2013

# group by 'Year' and 'LG'
idx = ['Year', 'LG']

# build a grouper
group_by = df.groupby(idx, as_index=False)

# need frame to re-expand the group size
df1 = df.set_index(idx)
df1['g_size'] = group_by.size()

# find the rows in the top half of respective group
top_half = (group_by.cumcount() / df1.g_size.values).values < 0.5

# build new data frames
top = df.loc[top_half]
bot = df.loc[~top_half]

print(df)
print('-- top')
print(top)
print('-- bot')
print(bot)
print('--')

        Date   LG  Year
0   2011-1-1  AR1  2011
1   2011-3-1  AR1  2011
2   2011-4-1  AR1  2011
3   2011-2-1  AR1  2011
4   2012-1-1  AR1  2012
5   2012-2-1  AR1  2012
6   2012-1-1  PO1  2012
7   2012-2-1  PO1  2012
8   2013-1-1  AR1  2013
9   2013-2-1  AR1  2013
10  2013-1-1  PO1  2013
11  2013-2-1  PO1  2013
-- top
   Year   LG      Date
0  2011  AR1  2011-1-1
1  2011  AR1  2011-2-1
2  2012  AR1  2012-1-1
3  2012  PO1  2012-1-1
4  2013  AR1  2013-1-1
5  2013  PO1  2013-1-1
-- bot
   Year   LG      Date
0  2011  AR1  2011-3-1
1  2011  AR1  2011-4-1
2  2012  AR1  2012-2-1
3  2012  PO1  2012-2-1
4  2013  AR1  2013-2-1
5  2013  PO1  2013-2-1

df = pd.DataFrame({
    'LG': ('AR1', 'AR1', 'AR1', 'AR1', 'AR1', 'AR1',
           'PO1', 'PO1', 'AR1', 'AR1', 'PO1', 'PO1'),
    'Date': ('2011-1-1', '2011-3-1', '2011-4-1', '2011-2-1', '2012-1-1',
             '2012-2-1', '2012-1-1', '2012-2-1', '2013-1-1', '2013-2-1',
             '2013-1-1', '2013-2-1'),
    'Year': (2011, 2011, 2011, 2011, 2012, 2012, 2012, 2012, 2013,
             2013, 2013, 2013)
})
pd.to_datetime(df['Date'])

---

df['Date'].apply（pd.to_datetime）

是一种缓慢的表达方式

pd.to_datetime（df['Date']）

。根据您的注释进行编辑谢谢，不过只有一期。2011年的AR1未正确拆分。2011-2-1在“底部”组，2011-3-1在“顶部”组。为什么？哦，你想把它分类？您没有显示任何示例输出，因此我没有假设。让我做点什么…是的，我的错。我指的是前50%的年份是日期，而不是如图所示的列。谢谢，那看起来怎么样？