Attempting to fix slow NaiveBayes

Three changes:

1) basic_extractor can accept a list of strings as well as a list of
('word','label') tuples.

2) BaseClassifier now has an instance variable _word_set which is a set
of tokens seen by the classifier.

1+2) BaseClassifier.extract_features passes _word_set to extractor
rather than the training set.

3)  NLTKClassifier.update adds new words to the _word_set.

Author: emmyzero

textblob/classifiers.py

@@ -76,9 +76,15 @@ def basic_extractor(document, train_set):
 
     :param document: The text to extract features from. Can be a string or an iterable.
     :param list train_set: Training data set, a list of tuples of the form
-        ``(words, label)``.
+        ``(words, label)`` OR an iterable of strings.
     """
-    word_features = _get_words_from_dataset(train_set)
+    el_zero = iter(train_set).next() #Infer input from first element.
+    if isinstance(el_zero, tuple):
+        word_features = _get_words_from_dataset(train_set)
+    elif isinstance(el_zero, str):
+        word_features = train_set
+    else:
+        raise ValueError('train_set is proabably malformed.')
     tokens = _get_document_tokens(document)
     features = dict(((u'contains({0})'.format(word), (word in tokens))
                                             for word in word_features))
@@ -123,6 +129,7 @@ def __init__(self, train_set, feature_extractor=basic_extractor, format=None, **
             self.train_set = self._read_data(train_set, format)
         else:  # train_set is a list of tuples
             self.train_set = train_set
+        self._word_set = _get_words_from_dataset(train_set) #Keep a hidden set of unique words.
         self.train_features = None
 
     def _read_data(self, dataset, format=None):
@@ -166,7 +173,7 @@ def extract_features(self, text):
         '''
         # Feature extractor may take one or two arguments
         try:
-            return self.feature_extractor(text, self.train_set)
+            return self.feature_extractor(text, self._word_set)
         except (TypeError, AttributeError):
             return self.feature_extractor(text)
 
@@ -260,6 +267,7 @@ def update(self, new_data, *args, **kwargs):
             ``(text, label)``.
         """
         self.train_set += new_data
+        self._word_set.update(_get_words_from_dataset(new_data))
         self.train_features = [(self.extract_features(d), c)
                                 for d, c in self.train_set]
         try: