Presentation
This dataset is the default configuration used in the bioclean()
function. Each row corresponds to a given biological concept
and a given unit
and the columns contain various informations.
Configuration
This default configuration is based on statistical summaries of AP-HP's biological measurements.
It can be generated from the create_config_from_stats function.
To list all available configurations, use list_all_configs().
Structure and usage
Internally, the dataset is returned by calling the function get_biology_config()
:
from eds_scikit.resources import registry
df = registry.get("data", function_name="get_biology_config")()
Use your own data.
The simplest way to generate your own configuration file is to use the create_config_from_stats function. Simply provide a name via the config_name
parameter:
from eds_scikit.biology.utils.config import create_config_from_stats
...
create_config_from_stats(..., config_name="my_custom_config", ...)
You can now provide this config_name
to every function that accepts it, especially the bioclean()
function.