def get_statements(self):
"""
Returns list of random statements from the API.
"""
from twitter import TwitterError
statements = []
# Generate a random word
random_word = self.random_word(self.random_seed_word, self.lang)
self.logger.info(
u'Requesting 50 random tweets containing the word {}'.format(
random_word))
tweets = self.api.GetSearch(term=random_word, count=50, lang=self.lang)
for tweet in tweets:
statement = Statement(tweet.text)
if tweet.in_reply_to_status_id:
try:
status = self.api.GetStatus(tweet.in_reply_to_status_id)
statement.add_response(Response(status.text))
statements.append(statement)
except TwitterError as error:
self.logger.warning(str(error))
self.logger.info('Adding {} tweets with responses'.format(
len(statements)))
return statements
def train(self, *corpus_paths):
# Allow a list of corpora to be passed instead of arguments
if len(corpus_paths) == 1:
if isinstance(corpus_paths[0], list):
corpus_paths = corpus_paths[0]
# Train the chat bot with each statement and response pair
for corpus_path in corpus_paths:
corpora = self.corpus.load_corpus(corpus_path)
corpus_files = self.corpus.list_corpus_files(corpus_path)
for corpus_count, corpus in enumerate(corpora):
for conversation_count, conversation in enumerate(corpus):
if self.show_training_progress:
utils.print_progress_bar(
str(os.path.basename(corpus_files[corpus_count])) +
' Training', conversation_count + 1, len(corpus))
previous_statement_text = None
for text in conversation:
statement = self.get_or_create(text)
statement.add_tags(corpus.categories)
if previous_statement_text:
statement.add_response(
Response(previous_statement_text))
previous_statement_text = statement.text
self.storage.update(statement)
def learn_response(self, statement, previous_statement):
"""
Learn that the statement provided is a valid response.
"""
from chatter.chatterbot.conversation import Response
if previous_statement:
statement.add_response(Response(previous_statement.text))
self.logger.info('Adding "{}" as a response to "{}"'.format(
statement.text, previous_statement.text))
# Save the statement after selecting a response
self.storage.update(statement)
def deserialize_responses(self, response_list):
"""
Takes the list of response items and returns
the list converted to Response objects.
"""
Statement = self.get_model('statement')
Response = self.get_model('response')
proxy_statement = Statement('')
for response in response_list:
text = response['text']
del response['text']
proxy_statement.add_response(Response(text, **response))
return proxy_statement.in_response_to
def train(self):
import glob
import csv
# Download and extract the Ubuntu dialog corpus if needed
corpus_download_path = self.download(self.data_download_url)
# Extract if the directory doesn not already exists
if not self.is_extracted(self.extracted_data_directory):
self.extract(corpus_download_path)
extracted_corpus_path = os.path.join(self.extracted_data_directory,
'**', '**', '*.tsv')
file_kwargs = {}
# Specify the encoding in Python versions 3 and up
file_kwargs['encoding'] = 'utf-8'
# WARNING: This might fail to read a unicode corpus file in Python 2.x
for file in glob.iglob(extracted_corpus_path):
self.logger.info('Training from: {}'.format(file))
with open(file, 'r', **file_kwargs) as tsv:
reader = csv.reader(tsv, delimiter='\t')
previous_statement_text = None
for row in reader:
if len(row) > 0:
text = row[3]
statement = self.get_or_create(text)
print(text, len(row))
statement.add_extra_data('datetime', row[0])
statement.add_extra_data('speaker', row[1])
if row[2].strip():
statement.add_extra_data('addressing_speaker',
row[2])
if previous_statement_text:
statement.add_response(
Response(previous_statement_text))
previous_statement_text = statement.text
self.storage.update(statement)
def train(self, conversation):
"""
Train the chat bot based on the provided list of
statements that represents a single conversation.
"""
previous_statement_text = None
for conversation_count, text in enumerate(conversation):
if self.show_training_progress:
utils.print_progress_bar('List Trainer',
conversation_count + 1,
len(conversation))
statement = self.get_or_create(text)
if previous_statement_text:
statement.add_response(Response(previous_statement_text))
previous_statement_text = statement.text
self.storage.update(statement)