Polyglot-Based Word Frequency Calculator

  • Share this:

Code introduction


This function uses the Polyglot library to calculate the frequency of words in a given text and returns a dictionary containing words and their frequencies. It first downloads the necessary models for the specified language, then creates a Polyglot Text object, and finally retrieves the word frequencies from it.


Technology Stack : Polyglot, Text, downloader, embeddings2.en, ner2.en

Code Type : Function

Code Difficulty : Intermediate


                
                    
def random_word_frequency(text, language='en'):
    from polyglot.text import Text
    from polyglot.downloader import downloader

    # Download necessary models for the specified language
    downloader.download('embeddings2.en')
    downloader.download('ner2.en')

    # Create a Polyglot Text object
    polyglot_text = Text(text, hint_language_code=language)

    # Get the word frequencies
    word_freqs = polyglot_text.words.by_freq()

    # Return the frequencies as a dictionary
    return dict(word_freqs)