def initialize_nltk_wordnet(self):
"""
Download required NLTK corpora if they have not already been downloaded.
"""
from chatterbot.utils import nltk_download_corpus
nltk_download_corpus('corpora/wordnet')
def initialize_nltk_punkt(self):
"""
Download required NLTK corpora if they have not already been downloaded.
"""
from chatterbot.utils import nltk_download_corpus
nltk_download_corpus('tokenizers/punkt')
def initialize_nltk_punkt(self):
"""
Download required NLTK corpora if they have not already been downloaded.
"""
from chatterbot.utils import nltk_download_corpus
nltk_download_corpus('tokenizers/punkt')
def initialize_nltk_punkt(self):
"""
Download required NLTK punkt corpus if it has not already been downloaded.
"""
from chatterbot.utils import nltk_download_corpus
nltk_download_corpus('punkt')
def initialize_nltk_stopwords(self):
"""
Download required NLTK corpora if they have not already been downloaded.
"""
from chatterbot.utils import nltk_download_corpus
nltk_download_corpus('corpora/stopwords')
def initialize_nltk_stopwords(self):
"""
Download required NLTK stopwords corpus if it has not already been downloaded.
"""
from chatterbot.utils import nltk_download_corpus
nltk_download_corpus('stopwords')
def initialize_nltk_wordnet(self):
"""
Download the NLTK wordnet corpora that is required for this algorithm
to run only if the corpora has not already been downloaded.
"""
from chatterbot.utils import nltk_download_corpus
nltk_download_corpus('corpora/wordnet')
def initialize_nltk_vader_lexicon(self):
"""
Download the NLTK vader lexicon for sentiment analysis
that is required for this algorithm to run.
"""
from chatterbot.utils import nltk_download_corpus
nltk_download_corpus('sentiment/vader_lexicon')
def initialize_nltk_wordnet(self):
"""
Download the NLTK wordnet corpora that is required for this algorithm
to run only if the corpora has not already been downloaded.
"""
from chatterbot.utils import nltk_download_corpus
nltk_download_corpus('corpora/wordnet')
def initialize_nltk_averaged_perceptron_tagger(self):
"""
Download the NLTK averaged perceptron tagger that is required for this algorithm
to run only if the corpora has not already been downloaded.
"""
from chatterbot.utils import nltk_download_corpus
nltk_download_corpus('averaged_perceptron_tagger')
def initialize_nltk_averaged_perceptron_tagger(self):
"""
Download the NLTK averaged perceptron tagger that is required for this algorithm
to run only if the corpora has not already been downloaded.
"""
from chatterbot.utils import nltk_download_corpus
nltk_download_corpus('averaged_perceptron_tagger')
def initialize_nltk_vader_lexicon(self):
"""
Download the NLTK vader lexicon for sentiment analysis
that is required for this algorithm to run.
"""
from chatterbot.utils import nltk_download_corpus
nltk_download_corpus('sentiment/vader_lexicon')
def test_remove_stop_words(self):
from chatterbot.utils import nltk_download_corpus
nltk_download_corpus('stopwords')
tokens = ['this', 'is', 'a', 'test', 'string']
words = utils.remove_stopwords(tokens, 'english')
# This example list of words should end up with only two elements
self.assertEqual(len(words), 2)
self.assertIn('test', list(words))
self.assertIn('string', list(words))
def __init__(self, language='english'):
from chatterbot.utils import nltk_download_corpus
self.punctuation_table = str.maketrans(
dict.fromkeys(string.punctuation))
# Download the stopwords corpus if needed
nltk_download_corpus('stopwords')
# Get list of stopwords from the NLTK corpus
self.stopwords = nltk.corpus.stopwords.words(language)
self.stopwords.append('')
def test_remove_stop_words(self):
from chatterbot.utils import nltk_download_corpus
nltk_download_corpus('stopwords')
tokens = ['this', 'is', 'a', 'test', 'string']
words = utils.remove_stopwords(tokens, 'english')
# This example list of words should end up with only two elements
self.assertEqual(len(words), 2)
self.assertIn('test', list(words))
self.assertIn('string', list(words))
def setUp(self):
from chatterbot.utils import nltk_download_corpus
nltk_download_corpus('stopwords')
nltk_download_corpus('wordnet')
nltk_download_corpus('punkt')
self.adapter = ClosestMeaningAdapter()
# Add a mock storage adapter to the logic adapter
self.adapter.set_chatbot(MockChatBot())
def setUp(self):
super(BestMatchSynsetDistanceTestCase, self).setUp()
from chatterbot.utils import nltk_download_corpus
from chatterbot.comparisons import synset_distance
nltk_download_corpus('stopwords')
nltk_download_corpus('wordnet')
nltk_download_corpus('punkt')
self.adapter = BestMatch(statement_comparison_function=synset_distance)
# Add a mock storage adapter to the logic adapter
self.adapter.set_chatbot(self.chatbot)
def setUp(self):
super(BestMatchSynsetDistanceTestCase, self).setUp()
from chatterbot.utils import nltk_download_corpus
from chatterbot.comparisons import synset_distance
nltk_download_corpus('stopwords')
nltk_download_corpus('wordnet')
nltk_download_corpus('punkt')
self.adapter = BestMatch(
statement_comparison_function=synset_distance
)
# Add a mock storage adapter to the logic adapter
self.adapter.set_chatbot(self.chatbot)
def test_nltk_download_corpus(self):
downloaded = utils.nltk_download_corpus('wordnet')
self.assertTrue(downloaded)
self.skipTest('Test needs to be created')
def initialize_nltk_stopwords(self):
"""
Download required NLTK corpora if they have not already been downloaded.
"""
utils.nltk_download_corpus('corpora/stopwords')
def initialize_nltk_punkt(self):
"""
Download required NLTK corpora if they have not already been downloaded.
"""
utils.nltk_download_corpus('tokenizers/punkt')
def initialize_nltk_vader_lexicon(self):
"""
Download the NLTK vader lexicon for sentiment analysis
that is required for this algorithm to run.
"""
utils.nltk_download_corpus('vader_lexicon')
def test_nltk_download_corpus(self):
downloaded = utils.nltk_download_corpus('wordnet')
self.assertTrue(downloaded)
self.skipTest('Test needs to be created')
def test_nltk_download_corpus(self):
downloaded = utils.nltk_download_corpus('wordnet')
self.assertTrue(downloaded)
def initialize_nltk_stopwords(self):
"""
Download required NLTK stopwords corpus if it has not already been downloaded.
"""
utils.nltk_download_corpus('stopwords')
def initialize_nltk_punkt(self):
"""
Download required NLTK punkt corpus if it has not already been downloaded.
"""
utils.nltk_download_corpus('punkt')
