Data is taken from Analytics Vidhya Hackathon. It can be found in the data folder.
Train.csv was used for modeling and feature engineering. Test.csv does not have target values. Hence did not use it for the analysis.
newdf.csv is the dataframe with feature engineered features (huge file, not uploaded). You can view a screenshot of the data below.
EDA and Feature Engineering.ipynb - contains data exploration and addition of new features.
Model.ipynb - Random Forest and XGB models.
Appendix- Other approaches.