Flight Delay Prediction

Execution steps:

1. Upload the following dataset to the google drive link
2. Open the following Colab link and mount the google drive. Then, provide the dataset location in the cell where spark reads the csv data.Colab link
3. This program stores the processed data back in the drive. Note the folder/file path.
4. Now, Open the following to run the Linear Regression Model by replacing the read csv path with the processed data folder path URL
5. Next, Open the following to run the Random Forest Model by replacing the read csv path with the processed data folder path URL
6. Then, Open the following to run the Gradient Boosted Tree Model by replacing the read csv path with the processed data folder path.url
7. Finally, you can also execute the following code to evaluate Gradient Boosted Tree Model for various system metrics url
8. Test data will be run automatically for each model and graph is displayed at end. Note: We used multiple colab notebooks as it would be easy to evaluate each model individually.