Fix typo

nltk/classify/textcat.py

@@ -18,7 +18,7 @@
 be identified-then compares using a distance measure.
 
 Language n-grams are provided by the "An Crubadan"
-project. A corpus reader was created seperately to read
+project. A corpus reader was created separately to read
 those files.
 
 For details regarding the algorithm, see:

nltk/parse/malt.py

@@ -329,7 +329,7 @@ def train_from_file(self, conll_file, verbose=False):
 
 if __name__ == '__main__':
     '''
-    A demostration function to show how NLTK users can use the malt parser API.
+    A demonstration function to show how NLTK users can use the malt parser API.
 
     >>> from nltk import pos_tag
     >>> assert 'MALT_PARSER' in os.environ, str(

nltk/stem/cistem.py

@@ -33,7 +33,7 @@ class Cistem(StemmerI):
     is thrice as fast as the Snowball stemmer for German while being about as fast
     as most other stemmers.
 
-    case_insensitive is a a boolean specifiying if case-insensitive stemming
+    case_insensitive is a a boolean specifying if case-insensitive stemming
     should be used. Case insensitivity improves performance only if words in the
     text may be incorrectly upper case. For all-lowercase and correctly cased
     text, best performance is achieved by setting case_insensitive for false.

nltk/stem/porter.py

@@ -75,7 +75,7 @@ class PorterStemmer(StemmerI):
     For the best stemming, you should use the default NLTK_EXTENSIONS
     version. However, if you need to get the same results as either the
     original algorithm or one of Martin Porter's hosted versions for
-    compability with an existing implementation or dataset, you can use
+    compatibility with an existing implementation or dataset, you can use
     one of the other modes instead.
     """
 

nltk/test/corpus.doctest

@@ -1216,7 +1216,7 @@ definitions of these data access methods wherever possible.
 
 At a high level, corpora can be divided into three basic types:
 
-- A *token corpus* contains information about specific occurences of
+- A *token corpus* contains information about specific occurrences of
   language use (or linguistic tokens), such as dialogues or written
   texts.  Examples of token corpora are collections of written text
   and collections of speech.

nltk/twitter/common.py

@@ -115,7 +115,7 @@ def json2csv(
     are 'id_str' for the tweetID and 'text' for the text of the tweet. See\
     <https://dev.twitter.com/overview/api/tweets> for a full list of fields.\
     e. g.: ['id_str'], ['id', 'text', 'favorite_count', 'retweet_count']\
-    Additonally, it allows IDs from other Twitter objects, e. g.,\
+    Additionally, it allows IDs from other Twitter objects, e. g.,\
     ['id', 'text', 'user.id', 'user.followers_count', 'user.friends_count']
 
     :param error: Behaviour for encoding errors, see\

nltk/twitter/twitterclient.py

@@ -199,7 +199,7 @@ def search_tweets(
         Call the REST API ``'search/tweets'`` endpoint with some plausible
         defaults. See `the Twitter search documentation
         <https://dev.twitter.com/rest/public/search>`_ for more information
-        about admissable search parameters.
+        about admissible search parameters.
 
         :param str keywords: A list of query terms to search for, written as\
         a comma-separated string