pandas 0.20.1
numpy 1.12.1
scikit-learn 0.19.0
statsmodel 0.8.0
- Folder Data contains train.csv and test.csv
- eda_plots.py is used for EDA and identifying outliers
- Final Model_Tweedie Regression.py is used for final modelling process in which Tweedie regression is used as a ML model.
- Final Submission Tweedie.csv is the final submission of predictions on test dataset.
A Note on Tweedie
Tweedie Distribution: Definition and Examples
Tweedie distribution