Add training class for Ubuntu corpus

.gitignore

@@ -21,3 +21,4 @@ docs/_build/
 *.iml
 
 examples/settings.py
+examples/ubuntu_dialogs*

chatterbot/trainers.py

@@ -170,3 +170,29 @@ def train(self):
             statements = self.get_statements()
             for statement in statements:
                 self.storage.update(statement, force=True)
+
+
+class UbuntuCorpusTrainer(Trainer):
+
+    def extract(self, file_path):
+        import tarfile
+
+        self.logger.info('Starting file extraction')
+
+        extracted_directory_path = ''
+
+        def track_progress(members):
+            for member in members:
+                # this will be the current file being extracted
+                yield member
+                print('Extracting {}'.format(member))
+
+        with tarfile.open(file_path) as tar:
+            tar.extractall(members=track_progress(tar))
+
+        self.logger.info('File extraction complete')
+
+        return extracted_directory_path
+
+    def train(self):
+        data_directory = self.extract('C:/Users/Gunther/GitHub/ChatterBot/examples/ubuntu_dialogs.tgz')

examples/ubuntu_corpus_training_example.py

@@ -0,0 +1,23 @@
+from chatterbot import ChatBot
+import logging
+
+
+'''
+This is an example showing how to train a chat bot using the
+Ubuntu Corpus of conversation dialog.
+'''
+
+# Enable info level logging
+logging.basicConfig(level=logging.INFO)
+
+chatbot = ChatBot(
+    'Example Bot',
+    trainer='chatterbot.trainers.UbuntuCorpusTrainer'
+)
+
+# Start by training our bot with the Ubuntu corpus data
+chatbot.train()
+
+# Now let's get a response to a greeting
+response = chatbot.get_response('How are you doing today?')
+print(response)