test and document new twitter wordlists

Former-commit-id: 14cb408100

tests/test.py

@@ -34,6 +34,15 @@ def test_languages():
             assert_greater(word_frequency('lol', new_lang_code), 0)
 
 
+def test_twitter():
+    avail = available_languages('twitter')
+    assert_greater(len(avail), 12)
+
+    for lang in avail:
+        assert_greater(word_frequency('rt', lang, 'twitter'),
+                       word_frequency('rt', lang, 'combined'))
+
+
 def test_defaults():
     eq_(word_frequency('esquivalience', 'en'), 0)
     eq_(word_frequency('esquivalience', 'en', default=1e-6), 1e-6)

wordfreq/__init__.py

@@ -331,9 +331,8 @@ def half_harmonic_mean(a, b):
 def word_frequency(word, lang, wordlist='combined', default=0.):
     """
     Get the frequency of `word` in the language with code `lang`, from the
-    specified `wordlist`. The default (and currently only) wordlist is
-    'combined', built from whichever of these four sources have sufficient
-    data for the language:
+    specified `wordlist`. The default wordlist is 'combined', built from
+    whichever of these four sources have sufficient data for the language:
 
       - Full text of Wikipedia
       - A sample of 72 million tweets collected from Twitter in 2014,
@@ -341,6 +340,9 @@ def word_frequency(word, lang, wordlist='combined', default=0.):
       - Frequencies extracted from OpenSubtitles
       - The Leeds Internet Corpus
 
+    Another available wordlist is 'twitter', which uses only the data from
+    Twitter.
+
     Words that we believe occur at least once per million tokens, based on
     the average of these lists, will appear in the word frequency list.
     If you look up a word that's not in the list, you'll get the `default`