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)) |
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
0.41 KB | |
def edits1(word): | |
splits = [(word[:i], word[i:]) for i in range(len(word) + 1)] | |
deletes = [a + b[1:] for a, b in splits if b] | |
transposes = [a + b[1] + b[0] + b[2:] for a, b in splits if len(b)>1] | |
replaces = [a + c + b[1:] for a, b in splits for c in alphabet if b] | |
inserts = [a + c + b for a, b in splits for c in alphabet] | |
return set(deletes + transposes + replaces + inserts) |