def pennTreeBank(self, text):
"""
Tokenization using the Penn Tree Bank Tokenizer
Parameters
----------
arg1 : list
A list of strings where each string is a single sentence
Returns
-------
list
A list of lists where each sub-list is a sequence of tokens
"""
tokenizedText = []
if isinstance(text, list):
for sentence in text:
if isinstance(sentence, str):
tokenizedText_ = TreebankWordTokenizer().tokenize(sentence)
for word in tokenizedText_:
if word in punctuations:
# remove any unwanted punctuation symbols which have been calssified as tokens
# was not getting unwanted spaces with punkt so that part has been ignored
tokenizedText_.remove(word)
tokenizedText.append(tokenizedText_)
else:
print("Warning")
print("Sentences are not in the form of strings")
return 0
else:
print("Warning")
print("Argument not in the form of a list.")
return 0
return tokenizedText
def pennTreeBank(self, text):
"""
Tokenization using the Penn Tree Bank Tokenizer
Parameters
----------
arg1 : list
A list of strings where each string is a single sentence
Returns
-------
list
A list of lists where each sub-list is a sequence of tokens
"""
tokenizedText = []
for sent in text:
# tokenize sentence using tree bank algorithm
tokens = TreebankWordTokenizer().tokenize(sent)
for W in tokens:
# in this case there won't be any empty words or spaces so just remove punctuations if any
if W in ['?', ':', '!', '.', ',', ';']:
tokens.remove(W)
tokenizedText.append(tokens)
return tokenizedText
