OMOP Teva - Quick use
This tutorial demonstrates how the OMOP teva module can be quickly used to generate OMOP tables dashboard.
Simply apply generate_omop_teva function after loading the data. It will create a directory with one HTML per OMOP table.
Avoid Jupyter Notebook
Koalas framework with high volumetry processing in Jupyter Notebook might cause computationnal delay and memory issues. Prefer spark-submit script to run OMOP Teva.
Loading dataset
from eds_scikit.io.hive import HiveData
data = HiveData(
spark_session=spark,
database_name="project_xxxxxxxx",
tables_to_load=[
"care_site",
"visit_occurrence",
"concept",
"concept_relationship",
"note",
"procedure_occurrence",
"condition_occurrence",
"drug_exposure_prescription",
"drug_exposure_administration",
],
)
from eds_scikit.plot import generate_omop_teva
start_date, end_date = "2021-01-01", "2021-12-01"
generate_omop_teva(data=data, start_date=start_date, end_date=end_date)
In this example condition_source_value is splited between diabetic and non-diabetic conditions.
You can modify dashboard configuration by importing eds_scikit.plot.default_omop_teva_config and customizing it. See next section for details on how to do it.