Translate a dataframe column

Self Learning
1

Hey!

I want to translate a dataframe column into english. This column contains at each row a list of words. I tried the following :

from googletrans import Translator

translator = Translator() 
df.col=df.col.apply(lambda x: translator.translate(x, dest='en'))

But this part never ends, and when it stops I get the error read out of time. What am I doing wrong?

Thank you in advance!

2

Hello Marianthi,

To translate a dataframe column containing lists of words in Python, you can use the Google Cloud Translate API. Here’s an example code :

from google.cloud import translate_v2
import pandas as pd

# create a translation client
translate_client = translate_v2.Client()

# read in your dataframe
df = pd.read_csv(path)

# define the target language for translation (in this case, English)
target_language = 'en'

# define a function to apply to each row of the column, translating the list of words

def translate_list(row):

    # join the list of words into a single string
    words_string = ' '.join(row[column_to_translate])

    # translate the string to the target language
    translated_text = translate_client.translate(words_string, target_language=target_language)

    # split the translated text back into a list of words
    translated_words = translated_text['translatedText'].split()

    return translated_words

# define the column containing the lists of words you want to translate
column_to_translate = 'your_column_name'

# apply the translation function to the column
df['translated_column'] = df.apply(translate_list, axis=1)

Yohan

1 Like
3

I have installed google-cloud by :
pip install google-cloud

but I still get the following error :

image
image1575×747 71.4 KB

What does this mean? How can I fix this error?

Thank you in advance!

4

To use the Google Cloud Translation API to translate text in Python, you will need to follow these general steps:

  1. Set up a Google Cloud account and create a new project.
  2. Enable the Cloud Translation API and generate API credentials (a service account key) for your project.
  3. Install the google-cloud-translate Python package using pip: pip install google-cloud-translate
  4. Set the environment variable GOOGLE_APPLICATION_CREDENTIALS to the path of your API credentials file.

Thus, you must click on the following link and follow the steps above.

5

Is this the only way to translate some elements of the dataframe? Is this payable?
Does the googletrans library not work?

6

Could you explain to me further how the step 4 works exactly? Shall I add a new file .env with

GOOGLE_APPLICATION_CREDENTIALS = '...'

and then in the main python file I write the following ?

import os
from dotenv import load_dotenv
load_dotenv()
api_key = os.getenv("GOOGLE_APPLICATION_CREDENTIALS")

or what am I supposed to do?

7

Certainly, I can explain step 4 in more detail.

  1. First, you need to create a service account in your Google Cloud Console. To do this, navigate to the IAM & Admin page and click on « Service accounts ». Then, click on « Create Service Account » and follow the prompts to create a new service account with the appropriate permissions to access the Cloud Vision API.

  2. After you have created the service account, you need to create a key for the account. Click on the service account you just created, then click on « Keys » and « Add Key ». Choose « JSON » as the key type and click « Create ».

  3. This will download a JSON file containing your service account key.

GOOGLE_APPLICATION_CREDENTIALS= "your_path_json_key"

import os
from dotenv import load_dotenv

# Load environment variables from .env file
load_dotenv()

# Set the path to the JSON key file in the GOOGLE_APPLICATION_CREDENTIALS environment variable
os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = os.getenv('GOOGLE_APPLICATION_CREDENTIALS')

With these steps completed, your Python code should now be able to authenticate with the Cloud Vision API.

Yohan