LICENSE
MANIFEST.in
README.md
requirements.txt
setup.py
dataprep/VERSION
dataprep/__init__.py
dataprep/__main__.py
dataprep/config.py
dataprep/dirutils.py
dataprep/fileutils.py
dataprep/logging.yaml
dataprep/noneng.py
dataprep/parse_projects.py
dataprep/prepconfig.py
dataprep/stemming.py
dataprep/to_repr.py
dataprep/util.py
dataprep/vocab.py
dataprep/api/__init__.py
dataprep/api/common.py
dataprep/api/corpus.py
dataprep/api/text.py
dataprep/bpepkg/__init__.py
dataprep/bpepkg/bpe_config.py
dataprep/bpepkg/bpe_encode.py
dataprep/bpepkg/bpe_learn.py
dataprep/bpepkg/cache.py
dataprep/bpepkg/merge.py
dataprep/bpepkg/wild_bpe.py
dataprep/cli/__init__.py
dataprep/cli/impl.py
dataprep/cli/spec.py
dataprep/cli/vocab.py
dataprep/data/bpe/case/0/merges.txt
dataprep/data/bpe/case/10k/merges.txt
dataprep/data/bpe/case/1k/merges.txt
dataprep/data/bpe/case/5k/merges.txt
dataprep/data/bpe/nocase/0/merges.txt
dataprep/data/bpe/nocase/10k/merges.txt
dataprep/data/bpe/nocase/1k/merges.txt
dataprep/data/bpe/nocase/5k/merges.txt
dataprep/infrastructure/__init__.py
dataprep/infrastructure/bpelearner.py
dataprep/infrastructure/bperegistry.py
dataprep/infrastructure/dataset.py
dataprep/infrastructure/stages.py
dataprep/infrastructure/vocabloader.py
dataprep/parse/__init__.py
dataprep/parse/core.py
dataprep/parse/matchers.py
dataprep/parse/subtokens.py
dataprep/parse/model/__init__.py
dataprep/parse/model/containers.py
dataprep/parse/model/core.py
dataprep/parse/model/metadata.py
dataprep/parse/model/noneng.py
dataprep/parse/model/numeric.py
dataprep/parse/model/placeholders.py
dataprep/parse/model/whitespace.py
dataprep/parse/model/word.py
dataprep/preprocess/__init__.py
dataprep/preprocess/core.py
giganticode_dataprep.egg-info/PKG-INFO
giganticode_dataprep.egg-info/SOURCES.txt
giganticode_dataprep.egg-info/dependency_links.txt
giganticode_dataprep.egg-info/entry_points.txt
giganticode_dataprep.egg-info/not-zip-safe
giganticode_dataprep.egg-info/requires.txt
giganticode_dataprep.egg-info/top_level.txt
tests/__init__.py
tests/api_b2b.py
tests/subword_separation.py
tests/to_repr.py
tests/util.py
tests/api/__init__.py
tests/api/corpus.py
tests/bpepkg/__init__.py
tests/bpepkg/bpe_config.py
tests/bpepkg/bpe_learn.py
tests/bpepkg/merge.py
tests/bpepkg/wild_bpe.py
tests/bpepkg/wild_bpe_performance.py
tests/cli/__init__.py
tests/cli/spec.py
tests/installation/__init__.py
tests/installation/bpelearner.py
tests/installation/bperegistry.py
tests/installation/dataset.py
tests/parse/__init__.py
tests/parse/core.py
tests/parse/subtokens.py