Added subroutine to run an NLTK Stemmer (sloria#149)

* Added subroutine to run an NLTK Stemmer

* Added NLTK Stemmer + test functions

* Added NLTK Stemmer + tests

* Fixed NLTK Stemmer

Author: nikulshr

tests/test_blob.py

@@ -101,6 +101,10 @@ def test_lemmatize(self):
         wl = tb.WordList(["cat", "dogs", "oxen"])
         assert_equal(wl.lemmatize(), tb.WordList(['cat', 'dog', 'ox']))
 
+    def test_stem(self): #only PorterStemmer tested
+        wl = tb.WordList(["cat", "dogs", "oxen"])
+        assert_equal(wl.stem(), tb.WordList(['cat', 'dog', 'oxen']))
+
     def test_upper(self):
         wl = tb.WordList(self.words)
         assert_equal(wl.upper(), tb.WordList([w.upper() for w in self.words]))
@@ -914,6 +918,14 @@ def test_lemma(self):
         w = tb.Word("went", "VBD");
         assert_equal(w.lemma, "go")
 
+    def test_stem(self): #only PorterStemmer tested
+        w = tb.Word("cars")
+        assert_equal(w.stem(), "car")
+        w = tb.Word("wolves")
+        assert_equal(w.stem(), "wolv")
+        w = tb.Word("went")
+        assert_equal(w.stem(), "went")
+
     def test_synsets(self):
         w = tb.Word("car")
         assert_true(isinstance(w.synsets, (list, tuple)))

textblob/blob.py

@@ -148,6 +148,19 @@ def lemmatize(self, pos=None):
         lemmatizer = nltk.stem.WordNetLemmatizer()
         return lemmatizer.lemmatize(self.string, pos)
 
+    PorterStemmer = nltk.stem.porter.PorterStemmer()
+    LancasterStemmer = nltk.stem.lancaster.LancasterStemmer()
+    SnowballStemmer = nltk.stem.snowball.SnowballStemmer("english")
+
+    #added 'stemmer' on lines of lemmatizer
+    #based on nltk
+    def stem(self, stemmer=PorterStemmer):
+        """Stem a word using various NLTK stemmers. (Default: Porter Stemmer)
+
+        .. versionadded:: 0.12.0
+        """
+        return stemmer.stem(self.string)
+
     @cached_property
     def synsets(self):
         """The list of Synset objects for this Word.