GOATS/translate_data.py
2024-06-03 22:36:02 +02:00

29 lines
1.1 KiB
Python

import os
import pandas as pd
import requests
def translate_text(text, target_language='en'):
url = 'https://translate.googleapis.com/translate_a/single?client=gtx&sl=auto&tl={}&dt=t&q={}'.format(target_language, text)
response = requests.get(url)
if response.status_code == 200:
translated_text = response.json()[0][0][0]
return translated_text
else:
return text # Zwracamy oryginalny tekst w razie problemów z tłumaczeniem
data_directory = 'data'
translated_data_directory = 'translated_data'
os.makedirs(translated_data_directory, exist_ok=True)
for file_name in os.listdir(data_directory):
if file_name.endswith('.tsv'):
file_path = os.path.join(data_directory, file_name)
df = pd.read_csv(file_path, sep='\t')
# Tłumaczymy kolumnę 'value' na angielski
df['value_en'] = df['value'].apply(lambda x: translate_text(x, 'en'))
# Zapisujemy przetłumaczone dane do nowego pliku TSV
translated_file_path = os.path.join(translated_data_directory, file_name)
df.to_csv(translated_file_path, index=False, sep='\t')