added basic documentation for sentiwordnet

nltk/corpus/reader/sentiwordnet.py

@@ -17,13 +17,28 @@ For details about SentiWordNet see:
 http://sentiwordnet.isti.cnr.it/
 
     >>> from nltk.corpus import sentiwordnet as swn
-
+    >>> print(swn.senti_synset('breakdown.n.03'))
+    <breakdown.n.03: PosScore=0.0 NegScore=0.25>
+    >>> list(swn.senti_synsets('slow'))
+    [SentiSynset('decelerate.v.01'), SentiSynset('slow.v.02'),\
+    SentiSynset('slow.v.03'), SentiSynset('slow.a.01'),\
+    SentiSynset('slow.a.02'), SentiSynset('slow.a.04'),\
+    SentiSynset('slowly.r.01'), SentiSynset('behind.r.03')]
+    >>> happy = swn.senti_synsets('happy', 'a')
+    >>> happy0 = list(happy)[0]
+    >>> happy0.pos_score()
+    0.875
+    >>> happy0.neg_score()
+    0.0
+    >>> happy0.obj_score()
+    0.125
 """
 
 import re
-
+from nltk.compat import python_2_unicode_compatible
 from nltk.corpus.reader import CorpusReader
 
+@python_2_unicode_compatible
 class SentiWordNetCorpusReader(CorpusReader):
     def __init__(self, root, fileids, encoding='utf-8'):
         """
@@ -34,10 +49,10 @@ class SentiWordNetCorpusReader(CorpusReader):
                                                   encoding=encoding)
         if len(self._fileids) != 1:
             raise ValueError('Exactly one file must be specified')
-        self.db = {}
-        self.parse_src_file()
+        self._db = {}
+        self._parse_src_file()
 
-    def parse_src_file(self):
+    def _parse_src_file(self):
         lines = self.open(self._fileids[0]).read().splitlines()
         lines = filter((lambda x : not re.search(r"^\s*#", x)), lines)
         for i, line in enumerate(lines):
@@ -48,12 +63,12 @@ class SentiWordNetCorpusReader(CorpusReader):
                 raise ValueError('Line %s formatted incorrectly: %s\n' % (i, line))
             if pos and offset:
                 offset = int(offset)
-                self.db[(pos, offset)] = (float(pos_score), float(neg_score))
+                self._db[(pos, offset)] = (float(pos_score), float(neg_score))
 
     def senti_synset(self, *vals):        
         from nltk.corpus import wordnet as wn
-        if tuple(vals) in self.db:
-            pos_score, neg_score = self.db[tuple(vals)]
+        if tuple(vals) in self._db:
+            pos_score, neg_score = self._db[tuple(vals)]
             pos, offset = vals
             synset = wn._synset_from_pos_and_offset(pos, offset)
             return SentiSynset(pos_score, neg_score, synset)
@@ -61,8 +76,8 @@ class SentiWordNetCorpusReader(CorpusReader):
             synset = wn.synset(vals[0])
             pos = synset.pos()
             offset = synset.offset()
-            if (pos, offset) in self.db:
-                pos_score, neg_score = self.db[(pos, offset)]
+            if (pos, offset) in self._db:
+                pos_score, neg_score = self._db[(pos, offset)]
                 return SentiSynset(pos_score, neg_score, synset)
             else:
                 return None
@@ -78,28 +93,42 @@ class SentiWordNetCorpusReader(CorpusReader):
 
     def all_senti_synsets(self):
         from nltk.corpus import wordnet as wn
-        for key, fields in self.db.items():
+        for key, fields in self._db.items():
             pos, offset = key
             pos_score, neg_score = fields
             synset = wn._synset_from_pos_and_offset(pos, offset)
             yield SentiSynset(pos_score, neg_score, synset)
 
 
+@python_2_unicode_compatible
 class SentiSynset(object):
     def __init__(self, pos_score, neg_score, synset):
-        self.pos_score = pos_score
-        self.neg_score = neg_score
-        self.obj_score = 1.0 - (self.pos_score + self.neg_score)
+        self._pos_score = pos_score
+        self._neg_score = neg_score
+        self._obj_score = 1.0 - (self._pos_score + self._neg_score)
         self.synset = synset
 
+    def pos_score(self):
+        return self._pos_score
+
+    def neg_score(self):
+        return self._neg_score
+
+    def obj_score(self):
+        return self._obj_score
+
     def __str__(self):
         """Prints just the Pos/Neg scores for now."""
-        s = ""
-        s += self.synset.name() + "\t"
-        s += "PosScore: %s\t" % self.pos_score
-        s += "NegScore: %s" % self.neg_score
+        s = "<"
+        s += self.synset.name() + ": "
+        s += "PosScore=%s " % self._pos_score
+        s += "NegScore=%s" % self._neg_score
+        s += ">"
         return s
 
     def __repr__(self):
         return "Senti" + repr(self.synset)
                     
+if __name__ == "__main__":
+    import doctest
+    doctest.testmod(optionflags=doctest.NORMALIZE_WHITESPACE)

nltk/test/corpus.doctest

@@ -479,6 +479,11 @@ PropBank
 
 Please see the separate PropBank howto.
 
+SentiWordNet
+============
+
+Please see the separate SentiWordNet howto.
+
 Categorized Corpora
 ===================
 

nltk/test/sentiwordnet.doctest

+.. Copyright (C) 2001-2014 NLTK Project
+.. For license information, see LICENSE.TXT
+
+======================
+SentiWordNet Interface
+======================
+
+SentiWordNet can be imported like this:
+
+    >>> from nltk.corpus import sentiwordnet as swn
+
+------------
+SentiSynsets
+------------
+
+    >>> breakdown = swn.senti_synset('breakdown.n.03')
+    >>> print(breakdown)
+    <breakdown.n.03: PosScore=0.0 NegScore=0.25>
+    >>> breakdown.pos_score()
+    0.0
+    >>> breakdown.neg_score()
+    0.25
+    >>> breakdown.obj_score()
+    0.75
+
+
+------
+Lookup
+------
+
+    >>> list(swn.senti_synsets('slow'))
+    [SentiSynset('decelerate.v.01'), SentiSynset('slow.v.02'),\
+    SentiSynset('slow.v.03'), SentiSynset('slow.a.01'),\
+    SentiSynset('slow.a.02'), SentiSynset('slow.a.04'),\
+    SentiSynset('slowly.r.01'), SentiSynset('behind.r.03')]
+
+    >>> happy = swn.senti_synsets('happy', 'a')
+
+    >>> all = swn.all_senti_synsets()