[
https://issues.apache.org/jira/browse/SPARK-23166?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16336157#comment-16336157
]
Apache Spark commented on SPARK-23166:
--------------------------------------
User 'ymazari' has created a pull request for this issue:
https://github.com/apache/spark/pull/20366
> Add maxDF Parameter to CountVectorizer
> --------------------------------------
>
> Key: SPARK-23166
> URL: https://issues.apache.org/jira/browse/SPARK-23166
> Project: Spark
> Issue Type: Improvement
> Components: ML
> Affects Versions: 2.2.1
> Reporter: Yacine Mazari
> Priority: Minor
>
> 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|http://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.CountVectorizer.html],
> max_df.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
