Inspire-Mubas/Malawi-IDSR-COVID-19-Synthetic-DataSet

A synthetic dataset for the fields in the Integrated Disease Surveillance and Response form used in Malawi to record Covid19 cases and tests Malawi IDSR Covid-19 Synthetic DataSet Contents of the dataset archive: Version 2.0 contains several datasets: - with 100 records (Malawi_IDSR_Covid19SyntheticDataSet_v10_100.csv) - with 1,000 records (Malawi_IDSR_Covid19SyntheticDataSet_v10_1000.csv) - with 10,000 records (Malawi_IDSR_Covid19SyntheticDataSet_v10_10000.csv) - with 100,000 records (Malawi_IDSR_Covid19SyntheticDataSet_v10_1ht.csv) The main difference from v1.0 is that there is an additional field called REPR_ID representing the ID for the MOH employyee recording a case using the IDSR form. Each facility is assigned a set number of health professionals, between 3 and 10, who can record cases. In v1.0 each case (row) was generated by a random case recorded, hence in principle you had as many health professionals as cases which is not realistic. Version 1.0 containing 1. Dataset description and methodology: Documentation for the Malawi IDSR COVID-19 Synthetic DataSet (v1.0).pdf 2. Dataset in csv format: Malawi_IDSR_Covid19SyntheticDataSet_v10.csv: the dataset congtains 10,000 rows 3. File with Categories Used for Variables: Categories.csv Copyright Policy: Creative Commons Attribution-NonCommercial 4.0 International Public License Institution: Malawi University of Business and Applied Sciences, A. Taylor Grant: IDRC Global South AI4COVID Program