Given a list of indexes, how do I split a DataFrame on those indexes?

Question

给定一个任意长度的索引列表，例如[6, 12] ，在这些索引上拆分DataFrame的最佳方法是什么，所以最后我有了三个不同的DataFrame？

Answer 1

Here is a more general strategy to deal with non-integer index.

import pandas as pd
import numpy as np

np.random.seed(0)
df = pd.DataFrame(np.random.randn(100, 2), columns=['A', 'B']).set_index('A')

Out[32]: 
              B
A              
 1.7641  0.4002
 0.9787  2.2409
 1.8676 -0.9773
 0.9501 -0.1514
-0.1032  0.4106
 0.1440  1.4543
 0.7610  0.1217
 0.4439  0.3337
 1.4941 -0.2052
 0.3131 -0.8541
-2.5530  0.6536
 0.8644 -0.7422
 2.2698 -1.4544
 0.0458 -0.1872
 1.5328  1.4694
...         ...
 0.9209  0.3187
 0.8568 -0.6510
-1.0342  0.6816
-0.8034 -0.6895
-0.4555  0.0175
-0.3540 -1.3750
-0.6436 -2.2234
 0.6252 -1.6021
-1.1044  0.0522
-0.7396  1.5430
-1.2929  0.2671
-0.0393 -1.1681
 0.5233 -0.1715
 0.7718  0.8235
 2.1632  1.3365

[100 rows x 1 columns]

# say you want -1 and 1 as split point
cutoffs = np.array([-np.inf, -1, 1, np.inf])
df['group_level'] = pd.cut(df.index.values, bins=cutoffs)
# then groupby will give you what you want.
grouped = df.groupby('group_level')

for group_name, group_df in grouped:
    print(group_name)
    print(group_df)

(-inf, -1]
              B group_level
A                          
-2.5530  0.6536  (-inf, -1]
-1.0486 -1.4200  (-inf, -1]
-1.7063  1.9508  (-inf, -1]
-1.2528  0.7775  (-inf, -1]
-1.6139 -0.2127  (-inf, -1]
-1.6302  0.4628  (-inf, -1]
-1.1651  0.9008  (-inf, -1]
-1.0708  1.0545  (-inf, -1]
-1.2705  0.9694  (-inf, -1]
-1.1731  1.9436  (-inf, -1]
-1.4913  0.4394  (-inf, -1]
-1.3159 -0.4616  (-inf, -1]
-1.1475 -0.4378  (-inf, -1]
-1.2254  0.8444  (-inf, -1]
-1.0002 -1.5448  (-inf, -1]
-1.0342  0.6816  (-inf, -1]
-1.1044  0.0522  (-inf, -1]
-1.2929  0.2671  (-inf, -1]
(-1, 1]
              B group_level
A                          
 0.9787  2.2409     (-1, 1]
 0.9501 -0.1514     (-1, 1]
-0.1032  0.4106     (-1, 1]
 0.1440  1.4543     (-1, 1]
 0.7610  0.1217     (-1, 1]
 0.4439  0.3337     (-1, 1]
 0.3131 -0.8541     (-1, 1]
 0.8644 -0.7422     (-1, 1]
 0.0458 -0.1872     (-1, 1]
 0.1549  0.3782     (-1, 1]
-0.8878 -1.9808     (-1, 1]
-0.3479  0.1563     (-1, 1]
-0.3873 -0.3023     (-1, 1]
-0.5097 -0.4381     (-1, 1]
-0.8955  0.3869     (-1, 1]
...         ...         ...
-0.7448 -0.8264     (-1, 1]
-0.0985 -0.6635     (-1, 1]
-0.4980  1.9295     (-1, 1]
 0.9494  0.0876     (-1, 1]
 0.9209  0.3187     (-1, 1]
 0.8568 -0.6510     (-1, 1]
-0.8034 -0.6895     (-1, 1]
-0.4555  0.0175     (-1, 1]
-0.3540 -1.3750     (-1, 1]
-0.6436 -2.2234     (-1, 1]
 0.6252 -1.6021     (-1, 1]
-0.7396  1.5430     (-1, 1]
-0.0393 -1.1681     (-1, 1]
 0.5233 -0.1715     (-1, 1]
 0.7718  0.8235     (-1, 1]

[66 rows x 2 columns]
(1, inf]
             B group_level
A                         
1.7641  0.4002    (1, inf]
1.8676 -0.9773    (1, inf]
1.4941 -0.2052    (1, inf]
2.2698 -1.4544    (1, inf]
1.5328  1.4694    (1, inf]
1.2303  1.2024    (1, inf]
1.1394 -1.2348    (1, inf]
1.4883  1.8959    (1, inf]
1.1788 -0.1799    (1, inf]
1.8832 -1.3478    (1, inf]
1.9229  1.4805    (1, inf]
1.8676  0.9060    (1, inf]
2.3831  0.9445    (1, inf]
1.1266 -1.0799    (1, inf]
1.1880  0.3169    (1, inf]
2.1632  1.3365    (1, inf]