Created
September 20, 2019 08:42
-
-
Save MSWon/cce57027fff3275846e728ae5dfebf35 to your computer and use it in GitHub Desktop.
shuffling word's character order
This file contains 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
import random | |
import numpy as np | |
class shuffle(): | |
def __init__(self): | |
np.random.seed(1234) | |
def shuffle_string(self, string): | |
chars = list(string) | |
random.shuffle(chars) | |
return ''.join(chars) | |
def garble_word(self, word): | |
shuffle_rate = (len(word) // 4) + 1 | |
# No operation needed on sufficiently small words | |
# (Also, main algorithm requires word length >= 2) | |
if len(word) <= 3: | |
return word | |
# Split word into first & last letter, and middle letters | |
first, mid, last = word[0:shuffle_rate], word[shuffle_rate:-shuffle_rate], word[-shuffle_rate:] | |
return first + self.shuffle_string(mid) + last | |
def shuffle_corpus(self, corpus, vocabulary, shuffle_rate=2): | |
np.random.seed(1234) | |
for sent in corpus: | |
index = [i for i in range(len(sent)) if sent[i] in vocabulary] | |
r_list = np.random.choice(index, len(index)//shuffle_rate , replace = False) | |
for j in r_list: | |
sent[j] = self.garble_word(sent[j]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment