Data exploration and multilabel classification starter project for the Driven Data competition to how likely individuals are to receive their H1N1 and seasonal flu vaccines. You can find more information about the competition here.
-
exploration.ipynb - Preliminary analysis and data cleaning.
-
main.py - model training, evaluation, implementation and prediction output.
-
Flu Shot data dictionary.pdf - Explanation of all the attributes in the dataset
-
/data/raw - unprocessed data as downloaded from the competition page
-
/data/processed - treated data used for model training
- Clone this repository
- The notebook can be run on Google Colab without the need to install any libraries
- Run main.py on a Python 3 enviroment with all the libraries in the requirements.txt file