Python string replacement efficiency

Question

I have a list of ~ 50,000 lines (captions) and a list of 150 words to remove from these headers if found. My code is still below. The end result should be a list of 50,000 lines, with all copies of 150 words deleted. I would like to know the most efficient (effective) way to do this. My code seems to work, albeit very slowly.

excludes = GetExcludes()
titles = GetTitles()
titles_alpha = []
titles_excl = []
for k in range(len(titles)):
    #remove all non-alphanumeric characters 
    s = re.sub('[^0-9a-zA-Z]+', ' ',titles[k])

    #remove extra white space
    s = re.sub( '\s+', ' ', s).strip()

    #lowercase
    s = s.lower()

    titles_alpha.append(s)
    #remove any excluded words


    for i in range (len(excludes)):
        titles_excl.append(titles_alpha[k].replace(excludes[i],''))

print titles_excl

Answer 1

Most of the regular expression service resources are compiled by regular expressions. You must move the regex compilation from the loop.

This should give you a significant improvement:

pattern1 = re.compile('[^0-9a-zA-Z]+')
pattern2 = re.compile('\s+')
for k in range(len(titles)):
    #remove all non-alphanumeric characters 
    s = re.sub(pattern1,' ',titles[k])

    #remove extra white space
    s = re.sub(pattern2,' ', s).strip()

wordlist.txt :

import re
def noncompiled():
    with open("wordlist.txt",'r') as f:
        titles = f.readlines()
    titles = ["".join([title,nonalpha]) for title in titles for nonalpha in "!@#$%"]
    for k in range(len(titles)):
        #remove all non-alphanumeric characters 
        s = re.sub('[^0-9a-zA-Z]+', ' ',titles[k])

        #remove extra white space
        s = re.sub( '\s+', ' ', s).strip()

def compiled():
    with open("wordlist.txt",'r') as f:
        titles = f.readlines()
    titles = ["".join([title,nonalpha]) for title in titles for nonalpha in "!@#$%"]
    pattern1=re.compile('[^0-9a-zA-Z]+')
    pattern2 = re.compile( '\s+')
    for k in range(len(titles)):
        #remove all non-alphanumeric characters 
        s = pattern1.sub('',titles[k])

        #remove extra white space
        s = pattern2.sub('', s)



In [2]: %timeit noncompiled()
1 loops, best of 3: 292 ms per loop

In [3]: %timeit compiled()
10 loops, best of 3: 176 ms per loop

" " , , @zsquare, , , , , .

def with_excludes():
    with open("wordlist.txt",'r') as f:
        titles = f.readlines()
    titles = ["".join([title,nonalpha]) for title in titles for nonalpha in "!@#$%"]
    pattern1=re.compile('[^0-9a-zA-Z]+')
    pattern2 = re.compile( '\s+')
    excludes = ["shit","poo","ass","love","boo","ch"]
    excludes_regex = re.compile('|'.join(excludes))
    for k in range(len(titles)):
        #remove all non-alphanumeric characters 
        s = pattern1.sub('',titles[k])

        #remove extra white space
        s = pattern2.sub('', s)
        #remove bad words
        s = pattern2.sub('', s)
In [2]: %timeit with_excludes()
1 loops, best of 3: 251 ms per loop

, :

def master():
    with open("wordlist.txt",'r') as f:
        titles = f.readlines()
    titles = ["".join([title,nonalpha]) for title in titles for nonalpha in "!@#$%"]
    excludes = ["shit","poo","ass","love","boo","ch"]
    nonalpha='[^0-9a-zA-Z]+'
    whitespace='\s+'
    badwords = '|'.join(excludes)
    master_regex=re.compile('|'.join([nonalpha,whitespace,badwords]))

    for k in range(len(titles)):
        #remove all non-alphanumeric characters 
        s = master_regex.sub('',titles[k])
In [2]: %timeit master()
10 loops, best of 3: 148 ms per loop

, python:

    result = [master_regex.sub('',item) for item in titles]


In [4]: %timeit list_comp()
10 loops, best of 3: 139 ms per loop

. :

def baseline():
    with open("wordlist.txt",'r') as f:
        titles = f.readlines()
    titles = ["".join([title,nonalpha]) for title in titles for nonalpha in "!@#$%"]

In [2]: %timeit baseline()
10 loops, best of 3: 24.8 ms per loop

Answer 2

.

- :

excludes_regex = re.compile('|'.join(excludes))
titles_excl = []
for title in titles:
    titles_excl.append(excludes_regex.sub('', title))