The goal of this project is to predict the hospitalization times given the MIMIC-III dataset on hospitalization events. The data includes information about the patient, ICU, medical exams that were performed and their results, among other variables.
This notebook presents an exploratory data analysis using Seaborn, model creation and evaluation using Keras with a TensorFlow backend. It was created to run on a PySpark cluster, which, in our case, was deployed on Google Cloud.