This would be a great package to have in pypi, especially if it were python3 compatible. Is the project still being actively maintained? Are you looking for a maintainer? I would be happy to help any way I can.

It should be:
Rose S, Engel D, Cramer N, and Cowley, W. Automatic Keyword Extraction from Individual Documents, In: Berry MW, Kogan J, editors. Text Mining: Applications and Theory. Chichester, UK: John Wiley & Sons; 2010. doi: 10.1002/9780470689646.ch1

Nice, But the key word is too long to obtain

It looks like some parts of the code are not able to work with the latest releases of Python.

below code is used in rake.py
sorted_keywords = sorted(keyword_candidates.iteritems(), key=operator.itemgetter(1), reverse=True)

However, iteritems() is no longer supported in python 3, this makes that the code cannot be used in the latest releases of Python.

As described in RAKE paper, section 1.2.3 Adjoining Keywords, is there any function implemented to adjoin the keywords - identifying keywords that contain interior stop words such as "axis of evil"?

Hello,

in rake.py:125, shouldn't

self.__stop_words_pattern = build_stop_word_regex(stoppath) 

be:

self.__stop_words_pattern = build_stop_word_regex(stop_words_path)

?

Dear ,

Can we restrict the Keyword, I mean can we push the list to RAKE and RAKE look for only that ?

Thanks & Regards,
Vinod Nambiar.

Would it be possible to create a tool for using RAKE?

1. input a list of PDFs, of a certain type, or of any type
2. extract text and apply RAKE
3. output keywords for each document, or each type of document
   That way it would be useful to read academic papers

i understand keyword extraction.Kindly explain how it is done using RAKE ?