tests TextModel

b4msa/tests/test_texmodel.py

@@ -28,3 +28,12 @@ def test_tweet_iterator():
     for a0, b0 in zip(a, b):
         assert a0['text'] == b0['text']
     os.unlink(fname_gz)
+
+
+def text_texmodel():
+    from b4msa.textmodel import TextModel, tweet_iterator
+    import os
+    fname = os.path.dirname(__file__) + '/text.json'
+    tw = [x for x in tweet_iterator(fname)]
+    text = TextModel([x['text'] for x in tw])
+    assert isinstance(text[tw[0]['text']], list)

b4msa/tests/text.json

@@ -1,4 +1,4 @@
-{"text": "buenos dias b4msa", "klass": "POS"}
+{"text": "buenos dia b4msa", "klass": "POS"}
 {"text": "las vascas me deprimen", "klass": "NEG"}
 {"text": "excelente dia", "klass": "POS"}
 {"text": "la computadora", "klass": "NEU"}

b4msa/textmodel.py

@@ -90,6 +90,7 @@ def expand_qgrams(text, qsize, output):
 OPTION_GROUP = 'group'
 OPTION_DELETE = 'delete'
 
+
 class TextModel:
     def __init__(self,
                  docs,
@@ -98,8 +99,7 @@ def __init__(self,
                  url_option=OPTION_GROUP,
                  lc=True,
                  token_list=[1, 2, 3, 4, 5, 6, 7],
-                 language_dependent=[]
-    ):
+                 language_dependent=[]):
         self.strip_diac = strip_diac
         self.usr_option = usr_option
         self.url_option = url_option