ehrapy
ehrapy copied to clipboard
theislab
Electronic Health Record Analysis with Python.
### Description of feature - [ ] Quality control - [ ] normalization - [ ] encoding -> #650 - [ ] [...]
### Description of feature I looked a bit into sparse encoding. One-hot encoding being the most important: 1. scikit-learn's one-hot encoding supports a `sparse_output` parameter that should return a CSR...
### Description of feature I noticed that many messages produced by the logger are extremely long and take too much space when analyzing something in a Jupyter notebook. It really...
We already offer a CLI, but didn't add any functions of the API as commands yet. This is required to write neat Nextflow/Snakemake pipelines eventually.
### Description of feature As soon as @xinyuejohn knows more - [ ] MIMIC-IV sample - [ ] MIMIC-III full - [ ] MIMIC-IV full
There's quite a few of them, especially when the tests are executed. Let's collect them: ``` /home/zeth/PycharmProjects/ehrapy/ehrapy/preprocessing/encoding/_encode.py:324: FutureWarning: X.dtype being converted to np.float32 from object. In the next version of...
### Description of feature Hey! Some minor adjustments in the Docstrings might enhance user friendliness. As a word of caution, it appears that a `:` in the first line of...
### Description of feature By Karsten: We should ensure that we only impute into the future with past values. Think that this must be on patient by patient case
Probably something that we should try at some point... conda-forge I guess
**Is your feature request related to a problem? Please describe.** Currently, when using caching, we cannot write some datatypes like booleans in `obs` for example. Workarounds are implemented currently and...
