Merge pull request #9 from sheetal-158/master

changed to python 3.0
xiaohuiyan · Mar 29, 2017 · a29cf8c · a29cf8c
2 parents 95b33f7 + ff4feb3
commit a29cf8c
Show file tree

Hide file tree

Showing 2 changed files with 20 additions and 20 deletions.
diff --git a/script/indexDocs.py b/script/indexDocs.py
@@ -6,37 +6,37 @@
 w2id = {}
 
 def indexFile(pt, res_pt):
-    print 'index file: ', pt
+    print('index file: '+str(pt))
     wf = open(res_pt, 'w')
     for l in open(pt):
         ws = l.strip().split()
         for w in ws:
-            if not w2id.has_key(w):
+            if w not in w2id:
                 w2id[w] = len(w2id)
 
-        wids = [w2id[w] for w in ws]        
-        print >>wf, ' '.join(map(str, wids))
-
-    print 'write file: ', res_pt
+        wids = [w2id[w] for w in ws]  
+        print(' '.join(map(str, wids)), file=wf)
+         
+    print('write file: '+str(res_pt))
 
 
 def write_w2id(res_pt):
-    print 'write:', res_pt
+    print('write:'+str(res_pt))
     wf = open(res_pt, 'w')
     for w, wid in sorted(w2id.items(), key=lambda d:d[1]):
-        print >>wf, '%d\t%s' % (wid, w)
+        print('%d\t%s' % (wid, w), file=wf)
 
 if __name__ == '__main__':
     if len(sys.argv) < 4:
-        print 'Usage: python %s <doc_pt> <dwid_pt> <voca_pt>' % sys.argv[0]
-        print '\tdoc_pt    input docs to be indexed, each line is a doc with the format "word word ..."'
-        print '\tdwid_pt   output docs after indexing, each line is a doc with the format "wordId wordId ..."'
-        print '\tvoca_pt   output vocabulary file, each line is a word with the format "wordId    word"' 
+        print('Usage: python %s <doc_pt> <dwid_pt> <voca_pt>' % sys.argv[0])
+        print('\tdoc_pt    input docs to be indexed, each line is a doc with the format "word word ..."')
+        print('\tdwid_pt   output docs after indexing, each line is a doc with the format "wordId wordId..."')
+        print('\tvoca_pt   output vocabulary file, each line is a word with the format "wordId    word"')
         exit(1)
 
     doc_pt = sys.argv[1]
     dwid_pt = sys.argv[2]
     voca_pt = sys.argv[3]
     indexFile(doc_pt, dwid_pt)
-    print 'n(w)=', len(w2id)
+    print('n(w)='+str(len(w2id)))
     write_w2id(voca_pt)
diff --git a/script/topicDisplay.py b/script/topicDisplay.py
@@ -30,24 +30,24 @@ def dispTopics(pt, voca, pz):
         topics.append((pz[k], tmps))
         k += 1
 
-    print 'p(z)\t\tTop words'
+    print('p(z)\t\tTop words')
     for pz, s in sorted(topics, reverse=True):
-        print '%f\t%s' % (pz, s)
+        print('%f\t%s' % (pz, s))
 
 if __name__ == '__main__':
     if len(sys.argv) < 4:
-        print 'Usage: python %s <model_dir> <K> <voca_pt>' % sys.argv[0]
-        print '\tmodel_dir    the output dir of BTM'
-        print '\tK    the number of topics'
-        print '\tvoca_pt    the vocabulary file'
+        print('Usage: python %s <model_dir> <K> <voca_pt>' % sys.argv[0])
+        print('\tmodel_dir    the output dir of BTM')
+        print('\tK    the number of topics')
+        print('\tvoca_pt    the vocabulary file')
         exit(1)
 
     model_dir = sys.argv[1]
     K = int(sys.argv[2])
     voca_pt = sys.argv[3]
     voca = read_voca(voca_pt)    
     W = len(voca)
-    print 'K:%d, n(W):%d' % (K, W)
+    print('K:%d, n(W):%d' % (K, W))
 
     pz_pt = model_dir + 'k%d.pz' % K
     pz = read_pz(pz_pt)