Created
January 31, 2022 05:34
-
-
Save pszemraj/302a7d1a9bcf69ffc0e4137dfaca758a to your computer and use it in GitHub Desktop.
how to use the rpunct pip package to repunctuate grammar (after CPU fix implemented)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
usage example: | |
from scratch.rpunct.rpunct import RestorePuncts | |
rpunct_fixer = RestorePuncts() | |
bot_resp = repunctuate_grammar( | |
original_text, rpunct_obj=rpunct_fixer, verbose=True | |
) | |
""" | |
def repunctuate_grammar(input_text, rpunct_obj, verbose=False): | |
""" | |
repunctuate_grammar - uses the rpunct module to repunctuate a string after stripping all existing punctuation | |
Args: | |
input_text (str): [string to be repunctuated] | |
rpunct_obj (rpunct.RPunct): [rpunct object] | |
verbose (bool, optional): [whether to print the output of the rpunct module]. Defaults to False. | |
Returns: | |
[str]: [repunctuated string] | |
""" | |
if verbose: | |
print(f"repunctuating:\n\t{input_text}") | |
# strip all punctuation on the input text, except for apostrophes | |
input_text = re.sub(r"[^\w\s\']", "", input_text) | |
st = time.perf_counter() | |
ptext = rpunct_obj.punctuate(input_text, lang="en") | |
rt = time.perf_counter() - st | |
if verbose: | |
print(f"the new string is:\n\t{ptext}") | |
print("repunctuation took {} seconds".format(rt)) | |
return ptext |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment