Skip to content

I have built a simple web app that predicts the price of flights based on inputs such as Departure date and time, Source and destination, etc. The model is trained on "Random Forest Regressor" and deployed using "Streamlit" on Heroku. The accuracy of the model was found out to be 95% on the train data and about 80% on the test data.

License

Notifications You must be signed in to change notification settings

sarthakkmishraa/Flight-Price-Prediction-With-Deployment

Repository files navigation

Flight Price Prediction with deployment

I have built a simple web app model which predicts the price of flight given the departure time , arrival time , date of journey , airline etc !

This was a fun project as the dataset which I had was categorical and to convert that into meaningful and mapping numerical values took me some time !

The accuracy on test data is 80 % and for the train data it goes to 95 %

I have also included the dataset (air_train.xlsx and air_test.xlsx) , the jupyter notebook(main code) file and the pickle file !

Demo Link

Deployment.

Heroku

Frontend and Backend -- Streamlit

Steps to follow after cloning :

1.place the pickle file in the same directory

2.Run the ipynb file

3. Use streamlit and heroku for the deployment

Any issue or requirement if necessary , you can raise a request !

Thank you !

About

I have built a simple web app that predicts the price of flights based on inputs such as Departure date and time, Source and destination, etc. The model is trained on "Random Forest Regressor" and deployed using "Streamlit" on Heroku. The accuracy of the model was found out to be 95% on the train data and about 80% on the test data.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published