Merge pull request #912 from longdt219/fix_CI_Errors

Fix errors shown in CI

nltk/classify/senna.py

@@ -27,19 +27,17 @@ The input is:
 - List of the operations needed to be performed.
 - (optionally) the encoding of the input data (default:utf-8)
 
+    >>> from __future__ import unicode_literals
     >>> from nltk.classify import Senna
     >>> pipeline = Senna('/usr/share/senna-v2.0', ['pos', 'chk', 'ner'])
-    >>> sent = 'Düsseldorf is an international business center'.split()
-    >>> pipeline.tag(sent)
-    [{'word': 'D\xfcsseldorf', 'chk': 'B-NP', 'ner': 'B-PER', 'pos': 'NNP'},
-    {'word': 'is', 'chk': 'B-VP', 'ner': 'O', 'pos': 'VBZ'},
-    {'word': 'an', 'chk': 'B-NP', 'ner': 'O', 'pos': 'DT'},
-    {'word': 'international', 'chk': 'I-NP', 'ner': 'O', 'pos': 'JJ'},
-    {'word': 'business', 'chk': 'I-NP', 'ner': 'O', 'pos': 'NN'},
-    {'word': 'center', 'chk': 'I-NP', 'ner': 'O','pos': 'NN'}]
+    >>> sent = 'Dusseldorf is an international business center'.split()
+    >>> [(token['word'], token['chk'], token['ner'], token['pos']) for token in pipeline.tag(sent)]
+    [('Dusseldorf', 'B-NP', 'B-LOC', 'NNP'), ('is', 'B-VP', 'O', 'VBZ'), ('an', 'B-NP', 'O', 'DT'), 
+    ('international', 'I-NP', 'O', 'JJ'), ('business', 'I-NP', 'O', 'NN'), ('center', 'I-NP', 'O', 'NN')]
 """
 
 
+from __future__ import unicode_literals
 from os import path, sep, environ
 from subprocess import Popen, PIPE
 from platform import architecture, system

nltk/parse/chart.py

@@ -1313,7 +1313,7 @@ class ChartParser(ParserI):
         # Width, for printing trace edges.
         trace_edge_width = self._trace_chart_width // (chart.num_leaves() + 1)
         if trace: print(chart.pretty_format_leaves(trace_edge_width))
-
+        
         if self._use_agenda:
             # Use an agenda-based algorithm.
             for axiom in self._axioms:
@@ -1628,8 +1628,9 @@ def demo(choice=None,
         print()
         cp = ChartParser(grammar, strategies[strategy][1], trace=trace)
         t = time.time()
-        parses = cp.parse_all(tokens)
         chart = cp.chart_parse(tokens)
+        parses = list(chart.parses(grammar.start()))
+        
         times[strategies[strategy][0]] = time.time()-t
         print("Nr edges in chart:", len(chart.edges()))
         if numparses:

nltk/tag/crf.py

@@ -24,7 +24,7 @@ class CRFTagger(TaggerI):
     """
     A module for POS tagging using CRFSuite https://pypi.python.org/pypi/python-crfsuite
     
-    >>> from nltk.tag.crfsuite import CRFTagger
+    >>> from nltk.tag.crf import CRFTagger
     >>> ct = CRFTagger()
  
     >>> train_data = [[('University','Noun'), ('is','Verb'), ('a','Det'), ('good','Adj'), ('place','Noun')],