Customize TFIDF Stop Words

[ericchaucl]

I'm now trying to use the TFIDF algorithm and use the parameter "stop_words=english".

Where are the stop_words defined and how can I customize it? Thanks!

[ericchaucl · Accepted solution]

Thanks for the advise. Finally I can find it!

It's in the path:
$SPLUNK HOME\etc\apps\Splunk_SA_Scientific_Python_windows_x86_64\bin\windows_x86_64\Lib\site-packages\sklearn\feature_extraction\stop_words.py

[parkz]

Is there a similar file path for Linux Splunk app?

[cmerriman]

If you go through the splunk docs for the algoriths, they bring you to the scikit-learn that houses the documentation. if you go through that enough, you can land on this page. https://github.com/scikit-learn/scikit-learn/blob/ef5cb84a805efbe4bb06516670a9b8c690992bd7/sklearn/f...