0.1.2

What's New

Just a quick hotfix.

🐛 Bug Fixes

• (load) Fix a bug where datasets with multiple subsites (e.g. 2024-umcg-hypopharynx-larynx) would cause an error because of a missing maxsplit=2 argument.

0.1.1

What's New

Small features and refactorings.

🚀 Features

• (load) add get_repo() method that fetches remote repository information for a `LyDatasetConfig
• (load) make authentication more flexible
• (utils) put sub-/superlevel inference in its own utility function

0.1.0

What's New

With this release, we make the switch from rapidly evolving 0.0.X versions to something that changes a little more slowly. However, we still consider the library experimental and breaking changes may still occur frequently.

🚀 Features

• (utils) Add often needed enhance function to complete sub-/superlevel involvement and infer maximum likelihood status.

🐛 Bug Fixes

• Avoid KeyError in infer_superlevels

⚙️ Miscellaneous Tasks

• Add link to release 0.0.4

Change

• infer_su(b|per)levels skips inferring involvement of sub-/super LNLs that are already present
• (load) Rename skip_disk to use_github
• (query) Rename in_ to isin for C object

0.0.4

What's New

🚀 Features

• [breaking] Make several helper functions private (e.g., _max_likelihood())
• (utils) Add more shortname columns, like surgery for ("patient", "#", "neck_dissection")
• (load) Allow search for datasets at different locations on disk
• (query) Add C object for easier Q creation
• (query) Add in_ to C object
• (validate) Add transform_to_lyprox function

🐛 Bug Fixes

• (load) Resolve circular import of _repo

📚 Documentation

• Add intersphinx mapping to pandera
• Expand module docstrings
• Update README.md with library examples

🧪 Testing

• Fix failure due to changing order of items in set

Change

• (validate) Add args to renamed validation
• Import useful stuff as top-level
• Make main() funcs private

Remove

• (load) [breaking] load_dataset() not needed, one can just use next(load_datasets())

0.0.3

What's New

🚀 Features

• Add method to infer sublevel involvement #2
• Add method to infer superlevel involvement #2
• (load) Allow loading from different repository and/or reference (tag, commit, ...) #4

🐛 Bug Fixes

• Make align_diagnoses() safer
• Make combine() method work as intended
• (load) Year may be equal to current year, not only smaller

📚 Documentation

• Make accessor method docstring more detailed
• Mention panda's update() in methods

⚙️ Miscellaneous Tasks

• Add documentation link to metadata
• Add changelog
• Remove pyright setting (where from?)
• Ignore B028 ruff rule

0.0.2

Warning

This is still very much experimental. Anything might change at any time.

What's New

🚀 Features

• Add some basic logging
• Add percent and invert to portion

📚 Documentation

• Host documentation on https://lydata.readthedocs.io
• Ensure intersphinx links work

🧪 Testing

• Add doctest to join_datasets()

Change

• Switch to pydantic for dataset definition
• Shorten accessor name to ly

Refac

• Make load funcs/methods clean & consistent

2023 CLB Multisite v2

This updates the previously published dataset due to an error in the diagnostic_consensus column. The data did no actually come with this information, but we assume the diagnosis based on imaging to be negative (i.e., healthy) when no neck dissection was performed. However, due to a bug, it was also set to "healthy", when the pathology after neck dissection reported a healthy LNL. This is obviously wrong and was corrected here.

The full diff can be found here. Note that this also includes many other changes to other datasets since the first release.

0.0.1

First Version 🥳

This marks the first (highly experimental) release of a little Python package for loading, accessing, querying, and validating the datasets in this repo.

If it turns out to be useful, I'll continue to develop this into a mature set of tools that could ultimately deduplicate a lot of code in the lyprox and lyscripts repos.

2021 USZ Oropharynx v2

With this release, we update the previous one about the same dataset.

Note that the data itself remains unchanged, but we spotted a bug in the figures.ipynb that is supposed to reproduce the plots. That bug was fixed with this release.

full diff to previous release (also includes diff to meanwhile added 2021-clb-oropharynx dataset)

2021 USZ Oropharynx

This release contains the detailed patterns of lymphatic progression of 287 patients with squamous cell carcinomas (SCCs) in the oropharynx, treated at the University Hospital Zurich (USZ) between 2013 and 2019.

The archive 2021-usz-oropharynx.zip contains

• a README.md that explains how the dataset was extracted and what it contains
• the data itself as data.csv
• a citation file CITATION.cff that can be used to cite his dataset (one may also cite our Data in Brief article).
• a jupyter notebook figures.ipynb for rendering figures visualizing different aspects of the data
• the folder figures containing the already rendered figures which we also used in our publication for Radiation & Oncology