8000 DOC explain how to use custom edge bins in KBinsDiscretizer by Todaime · Pull Request #18972 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content

DOC explain how to use custom edge bins in KBinsDiscretizer #18972

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 15 commits into from
Dec 15, 2020
Merged

DOC explain how to use custom edge bins in KBinsDiscretizer #18972

Changes from all commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
fb5307e
Fixes ##18498
Dec 6, 2020
5fbc66e
Doc for the use of FunctionTransformer with pandas.cut for custom bin…
Dec 6, 2020
940c57d
Fix typo
Dec 6, 2020
9c3c9b3
Fix ... error
Dec 6, 2020
61de436
Second fix
Dec 6, 2020
608864e
fix pandas import
Dec 6, 2020
980f145
fix pandas import
Dec 6, 2020
15cdeaa
fix return values
Dec 6, 2020
110f681
fix return values
Dec 6, 2020
56c455e
fix return values
Dec 6, 2020
de662be
Fix typo
Dec 11, 2020
e2da3ee
Update doc/modules/preprocessing.rst
Dec 15, 2020
28ac063
Update doc/modules/preprocessing.rst
Dec 15, 2020
5885066
Update doc/modules/preprocessing.rst
Dec 15, 2020
001b5fe
Update doc/modules/preprocessing.rst
Dec 15, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 16 additions & 0 deletions doc/modules/preprocessing.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -667,6 +667,22 @@ constant-width bins. The 'quantile' strategy uses the quantiles values to have
equally populated bins in each feature. The 'kmeans' strategy defines bins based
on a k-means clustering procedure performed on each feature independently.

Be aware that one can specify custom bins by passing a callable defining the
discretization strategy to :class:`~sklearn.preprocessing.FunctionTransformer`.
For instance, we can use the Pandas function :func:`pandas.cut`::

>>> import pandas as pd
>>> import numpy as np
>>> bins = [0, 1, 13, 20, 60, np.inf]
>>> labels = ['infant', 'kid', 'teen', 'adult', 'senior citizen']
>>> transformer = preprocessing.FunctionTransformer(
... pd.cut, kw_args={'bins': bins, 'labels': labels, 'retbins': False}
... )
>>> X = np.array([0.2, 2, 15, 25, 97])
>>> transformer.fit_transform(X)
['infant', 'kid', 'teen', 'adult', 'senior citizen']
Categories (5, object): ['infant' < 'kid' < 'teen' < 'adult' < 'senior citizen']

.. topic:: Examples:

* :ref:`sphx_glr_auto_examples_preprocessing_plot_discretization.py`
Expand Down
0