jisshub/Algerian-Forest-Fires-Prediction

Algerian Forest Fire Predictor Machine Learning Project Explore the Repo » ### About The Project * Using Data Science and Machine learning, we can build a model that takes in the detected fires dataset learns and detects future fires based on certain Weather report. * Building a **Flask App** hosted on **Heroku**. * **Sklearn** for pre-processing and Model Building * Pandas, Numpy, Matplotlib for Data Processing, Data Cleaning, Visualization etc. ### Deployed App LINK TO HEROKU APP ### Dataset Description * I used a dataset on **Algerian Forest Fires from UCI**. The dataset contains a culmination of forest fire observations and data in two regions of Algeria: the Bejaia region and the Sidi Bel-Abbes region. * The timeline of this dataset is from June 2012 to September 2012. In this project, we focused on whether certain weather features could predict forest fires in these regions using few Machine Learning algorithms. ### Attributes Information - Date: (DD/MM/YYYY) Day, - Month: (MM) Month, - Year: (YYYY) Year - Temp: Temparature in Celsius, - RH: Relative Humidity in %, - Wind: Wind Speed in km/h, - Rain: Rainfall in mm, - Fine Fuel Moisture Code(FFMC) index, - Duff Moisture Code(DMC) index, - Drought Code(DC) index, - Initial Spread Index(ISI), - Build Up Index(BUI), - Fire Weather Index(FWI), - Classes: (0) No Fire, (1) Fire ( back to top ) ### Heroku Deployment * Create new repo in Github and push all the data using `Git`. * Install Heroku CLI and login using `heroku login` and setup the app in Heroku Web. * Connect with app `heroku git:remote -a appname` * Push to Heroku using `git push heroku main` ## Technologies Used ### **Tools used** ( back to top ) [VS Code]: code.visualstudio.com [postman]: postman.com [git]: git-scm.com [github]: github.com [heroku]: heroku.com [microsoft_azure]: azure.microsoft.com [python]: python.org …