Created
June 8, 2018 21:41
-
-
Save kingjr/97d0f942b8b0b62d8378a1c1af3748dd to your computer and use it in GitHub Desktop.
Find simplest google translate request that generate the maximum number of unique words
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
from googletrans import Translator | |
from itertools import product | |
from pandas import DataFrame, read_csv | |
import numpy as np | |
import string | |
import time | |
import os | |
# Get google translator object | |
translator = Translator() | |
if os.path.isfile('results.csv'): | |
print('load...') | |
results = read_csv('results.csv') | |
else: | |
results = DataFrame(columns=('input', 'output', 'size')) | |
# make simple alphabet | |
az = string.ascii_lowercase[:26] | |
n_words = 20 | |
n_letters = 4 | |
# Brute-force search | |
for n_letter in range(n_letters): | |
for chars in product(*[az] * n_letter): | |
input_string = ' '.join([''.join(chars)] * n_words) | |
if input_string in results['input'].values: | |
continue | |
# Deal with Google anti flood policy | |
translated = False | |
while not translated: | |
try: | |
output_string = translator.translate(input_string).text | |
translated = True | |
except ValueError: | |
time.sleep(1) | |
# count number of unique word | |
size = len(np.unique(output_string.split(' '))) | |
results = results.append(dict(input=input_string, | |
output=output_string, | |
size=size), | |
ignore_index=True) | |
disp = results.sort_values(['size', 'output'], ascending=False) | |
print(disp[:10]) | |
# save | |
results.to_csv('results.csv', header=True, index=False, encoding='utf-8') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment