class CorpusUtilsTestCase(TestCase):
def setUp(self):
self.corpus = Corpus()
def test_get_file_path(self):
"""
Test that a dotted path is properly converted to a file address.
"""
path = self.corpus.get_file_path("chatterbot.corpus.english")
self.assertIn(
os.path.join("chatterbot", "corpus", "data", "english"),
path
)
def test_read_corpus(self):
corpus_path = os.path.join(
self.corpus.data_directory,
"english", "conversations.json"
)
data = self.corpus.read_corpus(corpus_path)
self.assertIn("conversations", data)
def test_load_corpus(self):
corpus = self.corpus.load_corpus("chatterbot.corpus.english.greetings")
self.assertEqual(len(corpus), 1)
self.assertIn(["Hi", "Hello"], corpus[0])
def test_load_corpus_general(self):
corpus = self.corpus.load_corpus("chatterbot.corpus.english")
self.assertEqual(len(corpus), 2)
self.assertIn(["Hi", "Hello"], corpus[1])
class CorpusUtilsTestCase(TestCase):
def setUp(self):
self.corpus = Corpus()
def test_get_file_path(self):
"""
Test that a dotted path is properly converted to a file address.
"""
path = self.corpus.get_file_path('chatterbot.corpus.english')
self.assertIn(os.path.join('chatterbot', 'corpus', 'data', 'english'),
path)
def test_read_corpus(self):
corpus_path = os.path.join(self.corpus.data_directory, 'english',
'conversations.json')
data = self.corpus.read_corpus(corpus_path)
self.assertIn('conversations', data)
def test_list_english_corpus_files(self):
data_files = self.corpus.list_corpus_files('chatterbot.corpus.english')
self.assertGreaterEqual(len(data_files), 3)
self.assertIn('.json', data_files[0])
def test_load_corpus(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.english.greetings')
self.assertEqual(len(corpus), 1)
self.assertIn(['Hi', 'Hello'], corpus[0])
def test_load_corpus_general(self):
corpus = self.corpus.load_corpus("chatterbot.corpus.english")
self.assertEqual(len(corpus), 3)
self.assertIn(['Hi', 'Hello'], corpus[1])
class CorpusUtilsTestCase(TestCase):
def setUp(self):
self.corpus = Corpus()
def test_get_file_path(self):
"""
Test that a dotted path is properly converted to a file address.
"""
path = self.corpus.get_file_path("chatterbot.corpus.english")
self.assertIn(
os.path.join("chatterbot", "corpus", "data", "english"),
path
)
def test_read_corpus(self):
corpus_path = os.path.join(
self.corpus.data_directory,
"english", "conversations.json"
)
data = self.corpus.read_corpus(corpus_path)
self.assertIn("conversations", data)
def test_load_corpus(self):
corpus = self.corpus.load_corpus("chatterbot.corpus.english.greetings")
self.assertEqual(len(corpus), 1)
self.assertIn(["Hi", "Hello"], corpus[0])
def test_load_corpus_general(self):
corpus = self.corpus.load_corpus("chatterbot.corpus.english")
self.assertEqual(len(corpus), 3)
self.assertIn(["Hi", "Hello"], corpus[1])
class ChatterBotCorpusTrainer(Trainer):
"""
Allows the chat bot to be trained using data from the
ChatterBot dialog corpus.
"""
def __init__(self, chatbot, **kwargs):
super().__init__(chatbot, **kwargs)
from chatterbot.corpus import Corpus
self.corpus = Corpus()
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 = Statement(
text=text,
in_response_to=previous_statement_text,
conversation='training')
_statement.add_tags(*corpus.categories)
statement = self.get_preprocessed_statement(_statement)
previous_statement_text = statement.text
self.chatbot.storage.create(
text=statement.text,
in_response_to=statement.in_response_to,
conversation=statement.conversation,
tags=statement.tags)
def get_language_data(self , language):
"""
Load language-specific data
"""
from chatterbot.corpus import Corpus
corpus = Corpus()
math_words_data_file_path = corpus.get_file_path('chatterbot.corpus.{}.math_words'.format(language) ,
extension='json')
try:
with open(math_words_data_file_path) as data:
return json.load(data)
except IOError:
raise self.UnrecognizedLanguageException(
'A math_words data file was not found for `{}` at `{}`.'.format(language , math_words_data_file_path))
class newCorpusTrainer(trainers.Trainer):
def __init__(self, storage, **kwargs):
super(newCorpusTrainer, self).__init__(storage, **kwargs)
from chatterbot.corpus import Corpus
self.corpus = Corpus()
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):
print_progress_bar(
str(os.path.basename(corpus_files[corpus_count])) +
" Training", conversation_count + 1, len(corpus))
previous_statement_line = []
statement_line = []
for line in conversation:
for text in line:
statement = self.get_or_create(text)
statement.add_tags(corpus.categories)
statement_line.append(statement.text)
if previous_statement_line != []:
for previous_statement_text in previous_statement_line:
statement.add_response(
Response(previous_statement_text))
self.storage.update(statement)
previous_statement_line = statement_line
statement_line = []
class CorpusUtilsTestCase(TestCase):
def setUp(self):
self.corpus = Corpus()
def test_get_file_path(self):
"""
Test that a dotted path is properly converted to a file address.
"""
path = self.corpus.get_file_path('chatterbot.corpus.english')
self.assertIn(
os.path.join('chatterbot', 'corpus', 'data', 'english'),
path
)
def test_read_english_corpus(self):
corpus_path = os.path.join(
self.corpus.data_directory,
'english', 'conversations.corpus.json'
)
data = self.corpus.read_corpus(corpus_path)
self.assertIn('conversations', data)
def test_list_english_corpus_files(self):
data_files = self.corpus.list_corpus_files('chatterbot.corpus.english')
self.assertGreaterEqual(len(data_files), 3)
self.assertIn('.json', data_files[0])
def test_load_corpus(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.english.greetings')
self.assertEqual(len(corpus), 1)
self.assertIn(['Hi', 'Hello'], corpus[0])
def test_load_corpus_english(self):
corpus = self.corpus.load_corpus("chatterbot.corpus.english")
self.assertEqual(len(corpus), 3)
self.assertIn(['Hi', 'Hello'], corpus[1])
def get_language_data(self, language):
"""
Load language-specific data
"""
from chatterbot.corpus import Corpus
corpus = Corpus()
math_words_data_file_path = corpus.get_file_path(
'chatterbot.corpus.{}.math_words'.format(language),
extension='json'
)
try:
with open(math_words_data_file_path) as data:
return json.load(data)
except IOError:
raise self.UnrecognizedLanguageException(
'A math_words data file was not found for `{}` at `{}`.'.format(
language, math_words_data_file_path
)
)
def setUp(self):
self.corpus = Corpus()
def __init__(self, chatbot, **kwargs):
super().__init__(chatbot, **kwargs)
from chatterbot.corpus import Corpus
self.corpus = Corpus()
class CorpusLoadingTestCase(TestCase):
def setUp(self):
self.corpus = Corpus()
def test_load_corpus_chinese(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.chinese')
self.assertTrue(len(corpus))
def test_load_corpus_english(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.english')
self.assertTrue(len(corpus))
def test_load_corpus_english_greetings(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.english.greetings')
self.assertEqual(len(corpus), 1)
self.assertIn(['Hi', 'Hello'], corpus[0])
def test_load_corpus_french(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.french')
self.assertTrue(len(corpus))
def test_load_corpus_german(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.german')
self.assertTrue(len(corpus))
def test_load_corpus_hindi(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.hindi')
self.assertTrue(len(corpus))
def test_load_corpus_indonesia(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.indonesia')
self.assertTrue(len(corpus))
def test_load_corpus_italian(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.italian')
self.assertTrue(len(corpus))
def test_load_corpus_marathi(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.marathi')
self.assertTrue(len(corpus))
def test_load_corpus_portuguese(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.portuguese')
self.assertTrue(len(corpus))
def test_load_corpus_russian(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.russian')
self.assertTrue(len(corpus))
def test_load_corpus_spanish(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.spanish')
self.assertTrue(len(corpus))
def test_load_corpus_telugu(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.telugu')
self.assertTrue(len(corpus))
def test_get_file_path(self):
"""
Test that a dotted path is properly converted to a file address.
"""
import os
path = self.corpus.get_file_path('chatterbot.corpus.english')
self.assertIn(
os.path.join('chatterbot_corpus', 'data', 'english'),
path
)
def __init__(self, storage, **kwargs):
self.kwargs = kwargs
self.storage = storage
self.corpus = Corpus()
class CorpusLoadingTestCase(TestCase):
def setUp(self):
self.corpus = Corpus()
def test_load_corpus_chinese(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.chinese')
self.assertTrue(len(corpus))
def test_load_corpus_english(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.english')
self.assertTrue(len(corpus))
def test_load_corpus_english_greetings(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.english.greetings')
self.assertEqual(len(corpus), 1)
self.assertIn(['Hi', 'Hello'], corpus[0])
def test_load_corpus_french(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.french')
self.assertTrue(len(corpus))
def test_load_corpus_german(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.german')
self.assertTrue(len(corpus))
def test_load_corpus_hindi(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.hindi')
self.assertTrue(len(corpus))
def test_load_corpus_indonesia(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.indonesia')
self.assertTrue(len(corpus))
def test_load_corpus_italian(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.italian')
self.assertTrue(len(corpus))
def test_load_corpus_marathi(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.marathi')
self.assertTrue(len(corpus))
def test_load_corpus_portuguese(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.portuguese')
self.assertTrue(len(corpus))
def test_load_corpus_russian(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.russian')
self.assertTrue(len(corpus))
def test_load_corpus_spanish(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.spanish')
self.assertTrue(len(corpus))
def test_load_corpus_telugu(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.telugu')
self.assertTrue(len(corpus))
def test_get_file_path(self):
"""
Test that a dotted path is properly converted to a file address.
"""
import os
path = self.corpus.get_file_path('chatterbot.corpus.english')
self.assertIn(
os.path.join('chatterbot_corpus', 'data', 'english'),
path
)
def __init__(self, storage, **kwargs):
super(newCorpusTrainer, self).__init__(storage, **kwargs)
from chatterbot.corpus import Corpus
self.corpus = Corpus()
class CorpusLoadingTestCase(TestCase):
def setUp(self):
self.corpus = Corpus()
def test_load_corpus_chinese(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.chinese')
self.assertTrue(len(corpus))
def test_load_corpus_english(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.english')
self.assertTrue(len(corpus))
def test_load_corpus_french(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.french')
self.assertTrue(len(corpus))
def test_load_corpus_german(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.german')
self.assertTrue(len(corpus))
def test_load_corpus_hindi(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.hindi')
self.assertTrue(len(corpus))
def test_load_corpus_indonesia(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.indonesia')
self.assertTrue(len(corpus))
def test_load_corpus_italian(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.italian')
self.assertTrue(len(corpus))
def test_load_corpus_marathi(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.marathi')
self.assertTrue(len(corpus))
def test_load_corpus_portuguese(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.portuguese')
self.assertTrue(len(corpus))
def test_load_corpus_russian(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.russian')
self.assertTrue(len(corpus))
def test_load_corpus_spanish(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.spanish')
self.assertTrue(len(corpus))
def test_load_corpus_telugu(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.telugu')
self.assertTrue(len(corpus))
def setUp(self):
self.corpus = Corpus()
class CorpusLoadingTestCase(TestCase):
def setUp(self):
self.corpus = Corpus()
def test_load_corpus_chinese(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.chinese')
self.assertTrue(len(corpus))
def test_load_corpus_english(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.english')
self.assertTrue(len(corpus))
def test_load_corpus_french(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.french')
self.assertTrue(len(corpus))
def test_load_corpus_german(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.german')
self.assertTrue(len(corpus))
def test_load_corpus_hindi(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.hindi')
self.assertTrue(len(corpus))
def test_load_corpus_indonesia(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.indonesia')
self.assertTrue(len(corpus))
def test_load_corpus_italian(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.italian')
self.assertTrue(len(corpus))
def test_load_corpus_marathi(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.marathi')
self.assertTrue(len(corpus))
def test_load_corpus_portuguese(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.portuguese')
self.assertTrue(len(corpus))
def test_load_corpus_russian(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.russian')
self.assertTrue(len(corpus))
def test_load_corpus_spanish(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.spanish')
self.assertTrue(len(corpus))
def test_load_corpus_telugu(self):
corpus = self.corpus.load_corpus('chatterbot.corpus.telugu')
self.assertTrue(len(corpus))
