Changelog

Changelog#

All notable changes to this project will be documented in this file.

The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.

[0.2.1]#

Fixed#

  • Compatibility with anndata>=0.12.13 (#240) @eroell

[0.2.0]#

Fixed#

  • Assigning .X to a view of an X-less EHRData (e.g. one created with layers= only) no longer raises TypeError: 'NoneType' object does not support item assignment. The view is now materialised before the assignment, consistent with how AnnData handles other field modifications on views. (#233) @eroell

Modified#

  • infer_feature_types() considers integers from 0, …, n as numeric. It further provides a new argument binary_as, to steer if columns 0/1 should be considered numeric or categorical. (#231) @eroell

[0.1.2]#

Added#

  • from_pandas() with format='long' provides a new keyword argument fill_time_gaps that fills missing timegaps in the common case of integer time steps from 0 to n_timesteps (#229) @eroell

Modified#

  • mimic_2() column censor_flg switched to lifeline’s convention with 1=event, 0=censored, before this dataset loader function had them vice versa since the dataset provides them as such originally. (#227) @sueoglu

Fixed#

  • from_pandas() with format='long' misordered entries in .X/.layers with .obs if the input df was not sorted for the obs id keys, which is now fixed. (#228) @eroell

Documentation#

  • Documentation style polishing (#223) @zethson

[0.1.1]#

Added#

Fixed#

  • Sliceing of EHRData objects fixed when the backing object is an AnnData. (#218) @eroell

Maintenance#

[0.1.0]#

Added#

Fixed#

  • read_h5ad() fixed issues when backed=True. (#199) @eroell

  • read_h5ad() fixed bug when .X is None and harmonize_missing_features is True. (#206) @eroell

  • setup_obs() with observation_table="person_visit_occurrence" now supports multiple visits per patient, creating one row per visit with unique observation IDs, instead of failing with xarray conversion errors with non-unique indices. (#210) @eroell

  • OMOP time interval boundaries now use half-open intervals [start, end) to prevent duplicate measurements at interval boundaries. (#210) @eroell

Maintenance#

  • Support Python3.14 (#194) @Zethson

  • Address FutureWarnings across multiple places (#200) @eroell

  • Enhanced tutorial structure (#208) @eroell

Modified#

  • Dataset generator function ed.dt.ehrdata_blobs now takes n_cat_var and n_categories arguments to generate categorical (integer encoded) time series data (#207) @sueoglu

  • If enrich_var_with_feature_info=True in setup_variables() and setup_interval_variables(), data_table_concept_ids not included within the concept table are now mapped from their respective alternate concept_id included in the concept_relationship table to retrieve the available feature information. (#205) @KilianDahm

  • setup_variables() and setup_interval_variables() with use of "person" now checks birth_datetime for meaningful behaviour and error messages. (#210) @eroell

  • gen_default_config() provides convenience to generate a config directly from an EHRData object, and should be used instead of the previous ehrdata.integrations.vitessce.gen_config. (#211) @eroell

[0.0.10]#

EHRData drops the .R field, and now supports 3D data storage in any slot of .layers. See the Getting started with EHRData tutorial for an introduction to this behaviour. In the future, .X will be enabled soon for 3D data storage as well.

Maintenance#

Fixed#

Modified#

  • EHRData drops the .R field in favor of using .layers for any 3D data arrays (#184) @eroell

  • EHRData’s shape property will always return a 3 dimensional shape. If an EHRData object has flat arrays only, the third dimension will be 1. (#184) @eroell

  • The following functions now take a layer argument: read_csv(), from_pandas(), to_pandas(), setup_variables(), setup_interval_variables(), ehrdata_blobs(), physionet2012(). If it is let to its default, None, the .X field of EHRData is used. Since .X is 2D in this release, in cases with 3D data, the layer argument needs to be used. (#184) @eroell

  • write_zarr() now writes an EHRData specific store encoding, with anndata as a substore. This change allows to use AnnData with its change to consolidated Zarr metadata, and better isolates AnnData’s io. (#185) @eroell

  • read_zarr() is adapted to read the new store encoding, and can also deal with AnnData stores. (#185) @eroell

[0.0.9]#

Maintenance#

  • Use custom logger & remove pydata sparse (#176) @Zethson

  • Replace figshare with scverse S3 (#177) @Zethson

  • Update template to v0.6.0 (#166) @Zethson

Fixed#

  • Fix order of var created in ed.io.omop.setup_variables and ed.io.omop.setup_interval_variables (#179) @eroell

Modified#

  • Rename ed.pl.vitessce.gen_config to ed.integrations.vitessce.gen_config (#181) @eroell

  • Rename ed.tl.omop.EHRDataset to ed.integrations.torch.OMOPEHRDataset (#181) @eroell

[0.0.8]#

Fixed#

  • Update duckdb imports for future (#157) @eroell

Maintenance#

  • Private subset method for EHRData (#160) @eroell

  • Remove omop package dependency (#160) @eroell

[0.0.7]#

Fixed#

  • Fix tests and Getting Started Notebook (#155) @eroell

Maintenance#

  • Update duckdb imports for future (#155) @eroell

[0.0.6]#

Fixed#

  • Cleaned up and updated tutorial notebooks (#140) @agerardy

Added#

[0.0.5]#

Fixed#

  • Initialize EHRData with X and layers (#132) @eroell

Added#

Modified#

  • Rename .t attribute to .tem

[0.0.4]#

Fixed#

  • Zarr version to less than 3

[0.0.3]#

Fixed#

  • Added missing zarr dependency

[0.0.2]#

Added#

  • Expanded documentation

  • Improved OMOP Extraction

  • Support for COO sparse matrices for R

  • A ed.dt.ehrdata_blobs test data generator function

  • Replace -1 encoded missing values with nans in physionet2012 challenge data

Breaking changes#

  • Renamed r to R

[0.0.1] - 2024-11-04#

Added#

  • Initial release

[Unreleased]#

Added#

  • Basic tool, preprocessing and plotting functions

Fixed#

  • tutorial notebooks updated to align with breaking changes