From d4d7b2f72e95cc7fcd3209434b33dfafb10d2528 Mon Sep 17 00:00:00 2001 From: Rob Speer Date: Tue, 7 Jul 2015 18:18:27 -0400 Subject: [PATCH] fix duplication --- wordfreq/__init__.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/wordfreq/__init__.py b/wordfreq/__init__.py index b10d635..63c4c26 100644 --- a/wordfreq/__init__.py +++ b/wordfreq/__init__.py @@ -230,10 +230,9 @@ def word_frequency(word, lang, wordlist='combined', minimum=0.): - Full text of Wikipedia - A sample of 72 million tweets collected from Twitter in 2014, divided roughly into languages using automatic language detection - - Google Books Syntactic Ngrams 2013 - Frequencies extracted from OpenSubtitles - The Leeds Internet Corpus - - Google Books Ngrams and Google Books Syntactic Ngrams + - Google Books Syntactic Ngrams 2013 Another available wordlist is 'twitter', which uses only the data from Twitter.