Skip to content
 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

32 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Cultural classifier

Cultural classifier is an application using the ML model to distinguish between two archaeological cultures (specifically epigravettian and epiaurignacian) that are hard to classify with the conventional classification approach that relies on analysing the stone tool industry.

  • machine learning for classification purposes in archaeology
  • practical usage of the Logistic regression model as a complement for classifying stone industry, trained model and all data are available here
  • all archaeological sites are represented by using interactive maps

Watch the video about cultural classifier or checkout the app

You can watch the video here

You can checkout the app here

Getting Started

Prerequisites

pip (package manager)
python 3.6 (and newer versions)

Installation

  1. Clone the repo
    git clone https://github.com/hampet1/moodtracker.git
    
  2. Install packages
    pip install -r requirements.txt
    
  3. Set up config
    * set FLASK_ENV=development
    * set FLASK_APP=main
    
  4. Run server
    flask run
    

Usage

Classifier distinguishes between two very simalar archaeological cultures in terms of material culture. The input data (attributes) includes geospacial data related to the archaeological sites, the output is one of the archaeological cultures. For more information regarding input data please checkout the guideline.

For more info please checkout the website about project

More resources

The scientific paper which backs up the whole idea of applyingthe machine learning model for classification purposes in such fields as archeology is available here

Known issues (work in progress)

It's absolutely crucial to collect more data regarding these archaeologically hard to determine cultures in order to fully understand the potential of this quite new approach. At this stage the amount of data is not sufficient, that's why we should take this project for the time being with a grain of salt.

Acknowledgment

All data was collected by associate professors Zdenka Neruda and Petr Neruda, under the patronage of the Anthropos Institute.

License

Distributed under the MIT License.

Contact

Petr Hamrozi - hamrozipetr@outlook.com

About

classifier

Resources

Code of conduct

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages