BUG Fixes API usage

For newer versions of gensim at least, topics are represented as `(word,
frequency)`.

closes luispedro#21

Author: luispedro

ch04/blei_lda.py

@@ -36,9 +36,9 @@
 # Iterate over all the topics in the model
 for ti in range(model.num_topics):
     words = model.show_topic(ti, 64)
-    tf = sum(f for f, w in words)
+    tf = sum(f for _, f in words)
     with open('topics.txt', 'w') as output:
-        output.write('\n'.join('{}:{}'.format(w, int(1000. * f / tf)) for f, w in words))
+        output.write('\n'.join('{}:{}'.format(w, int(1000. * f / tf)) for w, f in words))
         output.write("\n\n\n")
 
 # We first identify the most discussed topic, i.e., the one with the

ch04/wordcloud.py

@@ -24,8 +24,6 @@ def create_cloud(oname, words,maxsize=120, fontname='Lobster'):
     # gensim returns a weight between 0 and 1 for each word, while pytagcloud
     # expects an integer word count. So, we multiply by a large number and
     # round. For a visualization this is an adequate approximation.
-    # We also need to flip the order as gensim returns (value, word), whilst
-    # pytagcloud expects (word, value):
-    words = [(w,int(v*10000)) for v,w in words]
+    words = [(w,int(v*10000)) for w,v in words]
     tags = make_tags(words, maxsize=maxsize)
     create_tag_image(tags, oname, size=(1800, 1200), fontname=fontname)