test weighwords

xtas/tasks/cluster.py

@@ -202,7 +202,7 @@ def parsimonious_wordcloud(docs, w=.5, k=10):
     Parameters
     ----------
     docs : list
-        List of documents.
+        List of documents. Each document should be a list of terms.
 
     w : float
         Weight assigned to the document terms when fitting individual models,

xtas/tests/test_cluster.py

@@ -0,0 +1,19 @@
+import numbers
+
+from nose.tools import assert_equal, assert_true
+
+from xtas.tasks.cluster import parsimonious_wordcloud
+
+
+def test_parsimonious_wordcloud():
+    docs = map(lambda s: s.split(),
+               [["an apple a day keeps the doctor away"],
+                ["orange is the new black"],
+                ["comparing apples and oranges"]])
+    lm = parsimonious_wordcloud(docs, k=4)
+    assert_equal(3, len(lm))
+    for x in lm:
+        assert_equal(4, len(x))
+        term, weight = x
+        assert_true(isinstance(term, basestring))
+        assert_true(isinstance(weight, numbers.Real))