From afaed8757bc3daea824a3c2773f8699bdc2364a8 Mon Sep 17 00:00:00 2001 From: Joshua Chin Date: Fri, 17 Jul 2015 14:52:06 -0400 Subject: [PATCH] updated word_frequency docstring --- wordfreq/__init__.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/wordfreq/__init__.py b/wordfreq/__init__.py index a5ac0ec..07daf9f 100644 --- a/wordfreq/__init__.py +++ b/wordfreq/__init__.py @@ -257,6 +257,9 @@ def word_frequency(word, lang, wordlist='combined', minimum=0.): If a word decomposes into multiple tokens, we'll return a smoothed estimate of the word frequency that is no greater than the frequency of any of its individual tokens. + + It should be noted that the current tokenizer does not support + multi-character Chinese terms. """ args = (word, lang, wordlist, minimum) try: