Created
July 29, 2025 09:55
-
-
Save karpanGit/992f1fd6aa630137271a341054e46901 to your computer and use it in GitHub Desktop.
understand pandas groupby/apply arguments group_keys and include_groups
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import pandas as pd | |
| df = pd.DataFrame( | |
| { | |
| "A": ["foo", "bar", "foo", "bar", "foo", "bar", "foo", "foo"], | |
| "B": ["one", "one", "two", "three", "two", "two", "one", "three"], | |
| "C": np.random.randn(8), | |
| "D": np.random.randn(8), | |
| } | |
| ) | |
| df.groupby('A', group_keys=True).apply(lambda x: x, include_groups=True) # group_keys matters when using apply | |
| # A B C D | |
| # A | |
| # bar 1 bar one -1.583891 -1.708604 | |
| # 3 bar three 0.352257 -0.088550 | |
| # 5 bar two 0.857819 -0.480496 | |
| # foo 0 foo one -0.290060 0.856008 | |
| # 2 foo two 1.192185 -0.243608 | |
| # 4 foo two 0.772302 -0.791737 | |
| # 6 foo one -0.446585 1.177601 | |
| # 7 foo three -1.776370 1.541010 | |
| df.groupby('A', group_keys=True).apply(lambda x: x, include_groups=False) | |
| # B C D | |
| # A | |
| # bar 1 one -1.583891 -1.708604 | |
| # 3 three 0.352257 -0.088550 | |
| # 5 two 0.857819 -0.480496 | |
| # foo 0 one -0.290060 0.856008 | |
| # 2 two 1.192185 -0.243608 | |
| # 4 two 0.772302 -0.791737 | |
| # 6 one -0.446585 1.177601 | |
| # 7 three -1.776370 1.541010 | |
| df.groupby('A', group_keys=False).apply(lambda x: x, include_groups=True) | |
| # A B C D | |
| # 0 foo one -0.290060 0.856008 | |
| # 1 bar one -1.583891 -1.708604 | |
| # 2 foo two 1.192185 -0.243608 | |
| # 3 bar three 0.352257 -0.088550 | |
| # 4 foo two 0.772302 -0.791737 | |
| # 5 bar two 0.857819 -0.480496 | |
| # 6 foo one -0.446585 1.177601 | |
| # 7 foo three -1.776370 1.541010 | |
| df.groupby('A', group_keys=False).apply(lambda x: x, include_groups=False) | |
| # B C D | |
| # 0 one -0.290060 0.856008 | |
| # 1 one -1.583891 -1.708604 | |
| # 2 two 1.192185 -0.243608 | |
| # 3 three 0.352257 -0.088550 | |
| # 4 two 0.772302 -0.791737 | |
| # 5 two 0.857819 -0.480496 | |
| # 6 one -0.446585 1.177601 | |
| # 7 three -1.776370 1.541010 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment