LICENSE
README.md
pyproject.toml
setup.cfg
setup.py
nlpta/__init__.py
nlpta/cleaning.py
nlpta/embeddings.py
nlpta.egg-info/PKG-INFO
nlpta.egg-info/SOURCES.txt
nlpta.egg-info/dependency_links.txt
nlpta.egg-info/top_level.txt
nlpta/datasets/__init__.py
nlpta/datasets/datasets.py
nlpta/features/__init__.py
nlpta/features/bow.py
nlpta/features/tfidf.py
nlpta/models/__init__.py
nlpta/models/embeddings.py
nlpta/morphology/__init__.py
nlpta/morphology/affixes.py
nlpta/morphology/confidence.py
nlpta/morphology/detection.py
nlpta/ngrams/__init__.py
nlpta/ngrams/ngrams.py
nlpta/normalization/__init__.py
nlpta/normalization/characters.py
nlpta/normalization/numerals.py
nlpta/normalization/pipeline.py
nlpta/normalization/punctuation.py
nlpta/normalization/whitespace.py
nlpta/preprocessing/__init__.py
nlpta/preprocessing/cleaning.py
nlpta/preprocessing/stopwords.py
nlpta/preprocessing/tokenization.py
nlpta/segmentation/__init__.py
nlpta/segmentation/sentence_splitter.py
nlpta/stopwords/__init__.py
nlpta/stopwords/amharic.py
nlpta/stopwords/english.py
nlpta/stopwords/stopword_filter.py
nlpta/tokenization/__init__.py
nlpta/tokenization/pipeline.py
nlpta/tokenization/sentence_tokenizer.py
nlpta/tokenization/sentences.py
nlpta/tokenization/tokenizer.py
nlpta/tokenization/word_tokenizer.py
nlpta/tokenization/words.py
tests/__init__.py
tests/test_datasets.py
tests/test_embeddings.py
tests/test_exports.py
tests/test_features.py
tests/test_ngrams.py
tests/test_preprocessing.py
tests/test_stopwords.py
tests/test_tokenization.py