Flight fare prediction
Table of Content
- Demo
- Synopsis
- Appendix
- Links
- Directory Tree
- Color Reference
- Features
- Run Locally
- License
- Technology Used
Demo
Synopsis
Flight fare prediction project is based on predicting the price of the flight ticket based on different features, this features includes, the airline in which you might travel, the date of journey, the place from where your journey begins source, the place where you reach destination, the route which you might take to reach your destination, this route also specifies the number of stops the airline stops inbetween the destination , the time for depature, the time of arrival, the time taken for you to travel from the source to the destination, and finally the price for the travel.
So based on the given data,
Independent variable (X) : Airline, Date_of_journey, Source, Destination, Route, Dep_Time, Arrival_Time, Duration, Total_Stops, Additional_Info
Dependent variable (Y) : Price
Based on the given data we can identify this as a regression problem, so we can use various machine learning problems to solve this problems which are as follows:
- Linear regression
- Lasso regression
- Ridge regression
- Decision tree regressor
- Random forest regressor
I have declared this problem with random forest regression, since linear regression model doesn't gave me much accuracy.
Machine learning model : Random forest regressor (sklearn)
Data preprocessing : Pandas
Data visualization : Matplotlib, Seaborn
Web framework : Flask
Model deployment : Heroku platform
Appendix
The requirement for developing this model is present in the requirements.txt file.
The development of the model is present in the main.ipynb file.
The pickle file of the model for deployment is present in flight fare prediction folder.
The flask framework for the web app development is made in the app.py file.
The templates for the framework is done in html and css and the file is located in the templates folder.
Links
-
https://www.kaggle.com/datasets/nikhilmittal/flight-fare-prediction-mh
Dataset link : -
https://github.com/Vedakeerthi/FLIGHT_FARE_PREDICTION
Github link : -
https://flight-fare-prediction-app.herokuapp.com/
Heroku link :
Directory Tree
├── template
│ ├── home.html
├── style
├── css
├── stylesheet.css
├── Procfile
├── README.md
├── Data_Train.xlsx
├── model-gif.gif
├── app.py
├── main.ipynb
|── Flight_fare_prediciton.pkl
├── requirements.txt
Color Reference
Color | Hex |
---|---|
Body of the web page | #6767bd |
Border of the web page | #000000 |
Font color for head, h3 | #ffffff |
Submit button border | #808080 |
Submit button color | #6767bd |
Features
- Live prediction analysis.
- Fullscreen mode supports in mobile, pc.
- Cross platform can be used on multiple operating system.
Run Locally
Clone the project
git clone https://github.com/Vedakeerthi/FLIGHT_FARE_PREDICTION.git
Install dependencies
pip install -r requirements.txt
Start the server
python app.py
Run the app on server by the local link provided