Stopwords API

Overview

Manage and filter Nepali stopwords (340+ curated words).

Functions

get_stopwords()

Get the current stopword list.

from nepalikit.manage_stopwords import get_stopwords

stopwords = get_stopwords()
print(len(stopwords))  # 340

is_stopword(word)

Check if a word is a stopword.

from nepalikit.manage_stopwords import is_stopword

is_stopword("र")       # True
is_stopword("नेपाल")   # False

add_stopwords(words)

Add custom stopwords.

from nepalikit.manage_stopwords import add_stopwords, is_stopword

add_stopwords(["नेपाल", "काठमाडौं"])
is_stopword("नेपाल")  # True

remove_custom_stopwords(words)

Remove words from custom stopwords (cannot remove defaults).

from nepalikit.manage_stopwords import remove_custom_stopwords

remove_custom_stopwords(["नेपाल"])

remove_stopwords_from_text(text, stopwords=None)

Remove stopwords from text.

from nepalikit.manage_stopwords import remove_stopwords_from_text

filtered = remove_stopwords_from_text("म घर जाँदै छु")
print(filtered)  # "घर जाँदै"

# With custom stopwords
filtered = remove_stopwords_from_text("म घर जाँदै छु", stopwords=["घर"])
print(filtered)  # "म जाँदै छु"

load_stopwords(folder_path)

Load stopwords from text files (legacy API).

from nepalikit.manage_stopwords import load_stopwords

stopwords = load_stopwords("/path/to/stopwords/")
print(stopwords)