Created
March 24, 2016 08:32
-
-
Save MajorTal/67d54887a729b5e5aa85 to your computer and use it in GitHub Desktop.
This file contains hidden or 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
from numpy.random import choice as random_choice, randint as random_randint, rand | |
MAX_INPUT_LEN = 40 | |
AMOUNT_OF_NOISE = 0.2 / MAX_INPUT_LEN | |
CHARS = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ .") | |
def add_noise_to_string(a_string, amount_of_noise): | |
"""Add some artificial spelling mistakes to the string""" | |
if rand() < amount_of_noise * len(a_string): | |
# Replace a character with a random character | |
random_char_position = random_randint(len(a_string)) | |
a_string = a_string[:random_char_position] + random_choice(CHARS[:-1]) + a_string[random_char_position + 1:] | |
if rand() < amount_of_noise * len(a_string): | |
# Delete a character | |
random_char_position = random_randint(len(a_string)) | |
a_string = a_string[:random_char_position] + a_string[random_char_position + 1:] | |
if len(a_string) < MAX_INPUT_LEN and rand() < amount_of_noise * len(a_string): | |
# Add a random character | |
random_char_position = random_randint(len(a_string)) | |
a_string = a_string[:random_char_position] + random_choice(CHARS[:-1]) + a_string[random_char_position:] | |
if rand() < amount_of_noise * len(a_string): | |
# Transpose 2 characters | |
random_char_position = random_randint(len(a_string) - 1) | |
a_string = (a_string[:random_char_position] + a_string[random_char_position+1] + a_string[random_char_position] + | |
a_string[random_char_position + 2:]) | |
return a_string |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment