Skip to content

This is a repository which i used to meddle with various ML configurations in order to tackle the Kaggle Classification Competition named : "Ghouls, Goblins, and Ghosts... Boo!"

License

Notifications You must be signed in to change notification settings

rempakos/Kaggle-MonsterClassification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

image

Kaggle-MonsterClassification Repository for "Ghouls, Goblins, and Ghosts... Boo!" competition.

Welcome to my repository for the Kaggle competition "Ghouls, Goblins, and Ghosts... Boo!". This repository contains the code and analysis for the competition, aiming to predict the type of creature (ghost, ghoul, or goblin) based on provided features.

The competition is closed but archived and can be found in this link -> https://www.kaggle.com/competitions/ghouls-goblins-and-ghosts-boo/data

Competition Description

The "Ghouls, Goblins, and Ghosts... Boo!" Kaggle competition challenges participants to develop a machine learning model that accurately classifies creatures into one of three categories: ghost, ghoul, or goblin. The competition provides a labeled training dataset and an unlabeled test dataset for evaluation.

Repository Contents

This repository contains the necessary code and resources to tackle the competition. The exact file structure may vary depending on the organization of the code. Please refer to the repository files and their documentation for further details.

The algorithms used are:

  1. KNN
  2. MLP
  3. Naive-Bayes
  4. SVM

Getting Started

To utilize the code and resources in this repository, follow the instructions below:

  1. Clone the repository to your local machine.

  2. Install the required dependencies as specified in the provided documentation or requirements file.

  3. Review the code and analysis files to understand the implementation details and explore different approaches used.

  4. Use the code and resources as a reference for your own implementation, adapting and modifying them to suit your needs.

    Note: A boxplot, a colored countplot and a pairplot are used to evaluate performance further.

License

The code in this repository is licensed under the appropriate license. Please refer to the repository's license file for more information.

This was a very fun problem for me to engage into as i learned about various ML models such as those mentioned above!Much obliged to the Kaggle Community.

About

This is a repository which i used to meddle with various ML configurations in order to tackle the Kaggle Classification Competition named : "Ghouls, Goblins, and Ghosts... Boo!"

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages