GitHub user ymazari opened a pull request:
https://github.com/apache/spark/pull/20367
[SPARK-23166][ML] Add maxDF Parameter to CountVectorizer
## What changes were proposed in this pull request?
Currently, the CountVectorizer has a minDF parameter.
It might be useful to also have a maxDF parameter.
It will be used as a threshold for filtering all the terms that occur very
frequently in a text corpus, because they are not very informative or could
even be stop-words.
This is analogous to scikit-learn, CountVectorizer, max_df.
## How was this patch tested?
Unit tests.
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/ymazari/spark SPARK-23166
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/spark/pull/20367.patch
To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:
This closes #20367
----
commit f9eb543ea2c9f9c1d4c96db112a4e14a9c1beb11
Author: Yacine Mazari <y.mazari@...>
Date: 2018-01-23T19:11:52Z
[SPARK-23166][ML] Add maxDF Parameter to CountVectorizer
----
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
