nepalikit 1.0

A Nepali language processing library

NepaliKit

NepaliKit is a Python library for natural language processing tasks in the Nepali language.

Installation

You can install NepaliKit using pip:

.. code-block:: bash

pip install NepaliKit

Features

NepaliKit provides the following features:

• Tokenization: Tokenize Nepali text using the SentencePiece tokenizer.
• Preprocessing: Clean and preprocess Nepali text data, including removing HTML tags, special characters, and other cleaning tasks.
• Stopword Management: Load, add, and remove stopwords from Nepali text.
• Sentence Operations: Segment Nepali text into sentences based on punctuation marks.
• SentencePiece Model Training: Train custom SentencePiece models for Nepali text data.
• Utility Functions: Various utility functions for text processing and manipulation.
• Integration with PyTorch: Utilities for integrating with PyTorch for machine learning tasks.

Usage

Tokenization Example

from NepaliKit.tokenization import SentencePieceTokenizer

text = "नमस्ते, के छ खबर?"
tokenizer = SentencePieceTokenizer()
tokens = tokenizer.tokenize(text)
print(tokens)

Preprocessing Example

from NepaliKit.preprocessing import remove_html_tags, remove_special_characters

text = "<p>नमस्ते, के छ खबर?</p>"
clean_text = remove_html_tags(text)
clean_text = remove_special_characters(clean_text)
print(clean_text)

Stopword Example

from NepaliKit.manage_stopwords import load_stopwords, add_stopword, remove_stopword

stopwords = load_stopwords('/path/to/stopword/directory')
add_stopword('नयाँ_स्टापवर्ड')
remove_stopword('कुनै_स्टापवर्ड')

License

This project is licensed under the MIT License.

Author

• Prabhash Kumar Jha
• Email: [e-mail]