challenging-america-word-ga.../utils.py
2022-04-11 00:20:54 +02:00

34 lines
801 B
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

import pandas as pd
import regex as re
from csv import QUOTE_NONE
ENCODING = "utf-8"
REP = re.compile(r"[{}\[\]\&%^$*#\(\)@\t\n0123456789]+")
REM = re.compile(r"'s|[\-]\\n|\-\\n|\p{P}")
def read_csv(fname):
return pd.read_csv(
fname,
sep="\t",
on_bad_lines='skip',
header=None,
quoting=QUOTE_NONE,
encoding=ENCODING
)
def clean_text(text):
res = str(text).lower().strip()
res = res.replace("", "'")
res = REM.sub("", res)
res = REP.sub(" ", res)
res = res.replace("'s", " is")
res = res.replace("'ll", " will")
res = res.replace("won't", "will not")
res = res.replace("isn't", "is not")
res = res.replace("aren't", "are not")
res = res.replace("'ve'", "have")
return res.replace("'m", " am")