Benchmarking timing performance Keyword Extraction between regex (regex module) and flashtext

flashtext_regex_timing_keyword_extraction_regex_module.py

#!/bin/python
from flashtext.keyword import KeywordProcessor
import random
import string
import regex
import time

def get_word_of_length(str_length):
    # generate a random word of given length
    return ''.join(random.choice(string.ascii_lowercase) for _ in range(str_length))

# generate a list of 100K words of randomly chosen size
all_words = [get_word_of_length(random.choice([3, 4, 5, 6, 7, 8])) for i in range(100000)]

print('Count  | FlashText | Regex    ')
print('-------------------------------')
for keywords_length in range(0, 20001, 1000):
    # chose 5000 terms and create a string to search in.
    all_words_chosen = random.sample(all_words, 5000)
    story = ' '.join(all_words_chosen)

    # get unique keywords from the list of words generated.
    unique_keywords_sublist = list(set(random.sample(all_words, keywords_length)))

    # compile regex
    compiled_re = regex.compile('|'.join([r'\b' + keyword + r'\b' for keyword in unique_keywords_sublist]))

    # add keywords to flashtext
    keyword_processor = KeywordProcessor()
    keyword_processor.add_keywords_from_list(unique_keywords_sublist)

    # time the modules
    start = time.time()
    _ = keyword_processor.extract_keywords(story)
    mid = time.time()
    _ = compiled_re.findall(story)
    end = time.time()
    # print output
    print(str(keywords_length).ljust(6), '|',
          "{0:.5f}".format(mid - start).ljust(9), '|',
          "{0:.5f}".format(end - mid).ljust(9), '|',)

# Count  | FlashText | Regex    
# -------------------------------
# 0      | 0.01503   | 0.00451   |
# 1000   | 0.01770   | 0.11515   |
# 2000   | 0.02162   | 0.28438   |
# 3000   | 0.02005   | 0.40018   |
# 4000   | 0.01825   | 0.40201   |
# 5000   | 0.02166   | 0.47453   |
# 6000   | 0.02271   | 0.61018   |
# 7000   | 0.01948   | 0.63136   |
# 8000   | 0.01917   | 0.71915   |
# 9000   | 0.01952   | 1.05328   |
# 10000  | 0.01971   | 1.34943   |
# 11000  | 0.01991   | 1.17387   |
# 12000  | 0.02020   | 1.63653   |
# 13000  | 0.02274   | 2.18791   |
# 14000  | 0.02174   | 2.82363   |
# 15000  | 0.02084   | 1.87638   |
# 16000  | 0.02172   | 2.01723   |
# 17000  | 0.02102   | 2.04743   |
# 18000  | 0.02119   | 2.99934   |
# 19000  | 0.02240   | 3.16921   |
# 20000  | 0.02227   | 3.75960   |