A project that uses the College scorecard dataset and does some analysis on student debt and other factors.

• Clone the repository.
• The eda folder has eda python notebooks performed by each of us.
• The model foler contains all the models we have tried.
  • gbt_model.ipynb has the code for CatBoost model.
  • xgboost.ipynb has code for the XGBoost model.
  • Download the dataset from https://collegescorecard.ed.gov/data/.
  • Upload it to colab or your compute environment and place the path to it while importing it as a dataframe.
  • Run all the cells and you should be able to see the output.