.gitignore
LICENSE
README.md
config.json
pyproject.toml
.github/workflows/python-package.yml
.github/workflows/python-publish.yml
dataQuest/__init__.py
dataQuest/filter_articles.py
dataQuest/generate_output.py
dataQuest/settings.py
dataQuest/utils.py
dataQuest.egg-info/PKG-INFO
dataQuest.egg-info/SOURCES.txt
dataQuest.egg-info/dependency_links.txt
dataQuest.egg-info/entry_points.txt
dataQuest.egg-info/requires.txt
dataQuest.egg-info/top_level.txt
dataQuest/article_final_selection/__init__.py
dataQuest/article_final_selection/article_selector.py
dataQuest/article_final_selection/process_article.py
dataQuest/article_final_selection/process_articles.py
dataQuest/filter/__init__.py
dataQuest/filter/delpher_kranten.py
dataQuest/filter/document.py
dataQuest/filter/document_filter.py
dataQuest/filter/input_file.py
dataQuest/models/base.py
dataQuest/models/tfidf.py
dataQuest/output_generator/text_formater.py
dataQuest/preprocessor/__init__.py
dataQuest/preprocessor/parser.py
dataQuest/preprocessor/text_cleaner.py
dataQuest/temporal_categorization/__init__.py
dataQuest/temporal_categorization/timestamped_data.py
docs/.gitkeep
example/config.json
example/getting_started.ipynb
example/data/KRANTEN_KBPERS01_000002100.json.gz
example/data/KRANTEN_KBPERS01_000002200.json.gz
example/data/KRANTEN_KBPERS01_000003100.json.gz
results/.gitkeep
scripts/convert_input_files.py
scripts/filter_articles.sh
tests/.gitkeep