Getting bad escape error in regex for python

Viewed 17

I am writing code to clean a very large data set of arrest records. I have been using regex to do this.

really confused and I couldn't really figure out anything from other questions. Also tried to run it in pythonanywhere and it still did not work

i tried importing regex as re but i got this error

e-packages\regex\regex.py", line 546, in _compile
    raise error(caught_exception.msg, caught_exception.pattern,
regex._regex_core.error: missing < at position 9 

    #arresttrasnfo
import pandas as pd
import xlsxwriter
import re
#take single line of arrest data all garbled turn it into county - date of arrest and crime or code (as best as possible)


def countiesfunc(locdata):
    d1 = "(\((.*?)\))" # catches stuff in parentheses
    red1 = re.compile(d1)
    counties = []
    for item in locdata:
        search = (red1.search(item))
        if search == None:
                  counties.append("No County Given or Failed to Parse County")
        else:
            counties.append(search)
    return counties
        

def datesfunc(timedata):
    d1 = '((\d|\d\d)(\/|\.)(\d|\d\d)(\/|\.)(\d\d|\d))' #inclusive date pattern
    red1 = re.compile(d1)

    dates = []

    for item in timedata:
        search = (red1.search(item))
        if search == None:
                  dates.append("Failed to Parse Date")
        else:
            dates.append(search)

    return dates
def crimesfunc(crimedata):
    d1 = "(\-\s\P\L(.*?)\,)|(\/(.*?)\-)|(\d\s(.*?)\-)" #inclusive formula to catch all crimes 
    red1 = re.compile(d1)

    crimes = []

    for item in crimedata:
        search = (red1.search(item))
        if search == None:
                  crimes.append("Failed to Parse Date")
        else:
            crimes.append(search)
    

def ziptodf(data,dates,counties,crimes):
    mapped = zip(data,dates,counties,crimes)
    resultdf = pd.DataFrame(mapped, columns = ['ACTN_CONDITN','Arrest Date','Counties',"Crime"])
    resultdf.to_excel("results.xlsx",engine = 'xlsxwriter')
    print('DataFrame is written to Excel File successfully.')

def main():
    df = pd.read_csv('arrestinfo.csv')
    data = df['ACTN_CONDITN'].tolist()
    counties = countiesfunc(data)
    crimes = crimesfunc(data)
    dates = datesfunc(data)
    ziptodf(data,dates,counties,crimes)
main()

I keep getting this error re.error: bad escape \P at position 5

0 Answers
Related