Databricks Project: Spark, Python, Creating Model for Health Outcomes

Job ID: 31068717

Budget: $30 – $250 CAD

URL: https://community.cloud.databricks.com/?o=1218499441415280#notebook/930055990842418/command/930055990842440

You would work along the lines as seen in the URL. You would use the same dataset from Kaggle. You would do data prep, some visualization, run ML models (including regression, logistic regression and others that are sensible). You should be using different parameters and predictor variables than in the URL. The model you build to predict strokes should be superior to what is in the URL. Lastly, you need to provide some comments that clearly explain your choices and interpret the stastical summaries.

You should be importing this notebook and working from it, but improving it, doing different visualizations.

This MUST be done in Databricks. You must have strong familiarity with Databricks in order to meet the deadline.

I would want it retuned by the end of the business day, which is approximately in the next 16 hours.