Skip to content

This repository contains the final project for Applied Machine Learning, where we built and evaluated predictive models to assess the risk of bird strikes on aircraft. The project explores various machine learning techniques to classify incidents and determine whether they resulted in aircraft damage.

License

Notifications You must be signed in to change notification settings

shaikaasim67/Predicting-Bird-Strikes

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 

Repository files navigation

Predicting-Bird-Strikes

This repository contains the final project for Applied Machine Learning, where we built and evaluated predictive models to assess the risk of bird strikes on aircraft. The project explores various machine learning techniques to classify incidents and determine whether they resulted in aircraft damage. This README provides details on the dataset and data preprocessing and about the model used for this classification project in FinalProject.ipynb.

Project Overview: The goal of this project is to predict [Target variable] using a classification machine learning model trained on the Birds_Strike.csv. The dataset is collected from FAA (Federal Aviation Administration) during 2000-2011.

Several models have been explored by tuning hyper parameters and changing data processing, and evaluated based on test accuracy, AUC- ROC, precision and recall.

Data Overview: The project uses the Birds_Strike.csv dataset containing 25559 examples with 25 features. Modified dataset and used 10 features that are important and required to classify the target variable.

Link to the Dataset: https://wildlife.faa.gov/search The modified Dataset is uploaded in the Zip folder as Bird Strike.csv.

Link to access the code : https://jupyter.org/try-jupyter/lab/index.html?path=FinalProject.ipynb Download all the Dataset, and upload it in the Jupyter Notebook.

Run Each Cell: Execute each cell in the notebook to perform all data preprocessing, model training and evaluation. Download all the required libraries.

About

This repository contains the final project for Applied Machine Learning, where we built and evaluated predictive models to assess the risk of bird strikes on aircraft. The project explores various machine learning techniques to classify incidents and determine whether they resulted in aircraft damage.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published