This repository contains scripts for preprocessing files on Brazilian mortality by city I collected and preprocessed in order to facilitate manipulation by the data community.
- Import files
- Extract from file header the year of reference
- Extract the IBGE city code
- Convert objects to numeric (this dataset contains columns where the decimal separator is period or comma)
- Rename columns according to ICD10 (please refer to https://icd.codes/icd10cm)
- Export a CSV at
output_mortality/brazil_city_mortality_<year>.csv
Run Dataprep Notebook.ipynb (instruction on notebook).
NOTE
This data pipeline was tested only with files from 2010 to 2018. It might not work on previous data.
I update this data on Kaggle monthly. Get it: https://www.kaggle.com/jairofreitas/brazilian-universal-health-care-data