https://github.com/joecerniglia/glass_ml2

Historical research using Machine Learning
https://github.com/joecerniglia/glass_ml2

archaeological-science artifacts aviation-accidents glass historical-data imbalanced-learning jupyter-notebook machine-learning-algorithms python3

Last synced: 2 days ago
JSON representation

Historical research using Machine Learning

• Host: GitHub
• URL: https://github.com/joecerniglia/glass_ml2
• Owner: joecerniglia
• Created: 2022-03-21T09:56:27.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2022-12-16T16:02:04.000Z (almost 2 years ago)
• Last Synced: 2024-01-26T10:11:34.390Z (10 months ago)
• Topics: archaeological-science, artifacts, aviation-accidents, glass, historical-data, imbalanced-learning, jupyter-notebook, machine-learning-algorithms, python3
• Language: Jupyter Notebook
• Homepage:
• Size: 18.7 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Machine Learning for the 20th century

I have two main objectives for the Jupyter notebook in this folder: 


1_ Practice maching learning, Python visualizations and Python coding. 


2_ Use data science, specifically Machine Learning (ML) with Python's skikit-learn package, to ascertain whether a small semi-opaque glass container found on the island of Nikumaroro in 2010, and possibly belonging to Amelia Earhart, and a jar of similar vintage in the same size and shape (but not color), found on eBay, can be identified as a container by an ML model fitted to a 1987 glass database. 


The notebook, ML_20th_Century.ipynb, can be viewed in NBViewer here:

https://nbviewer.org/github/joecerniglia/Glass_ML2/blob/main/ML_20th_Century.ipynb

I support the sentiments expressed by The Turing Way:

https://the-turing-way.netlify.app/welcome.html#

Many links to related material and source citations can be found in the notebook 

itself.

Acknowledgements 


I owe what I have learned to date in machine learning to Dr. Jason Brownlee:

https://machinelearningmastery.com/machine-learning-with-python/

My ambition is to add to my knowledge in April 2022 when I take the Machine Learning course at eCornell as part of the Python 360 certificate program, in which I am now enrolled: 

https://ecornell.cornell.edu/certificates/data-science/python-for-data-science/.

Update, December 2022: 


The paper has now been published by the Turing Data Institute here: 


https://alan-turing-institute.github.io/TuringDataStories-fastpages/amelia%20earhart/fred%20noonan/aviation%20mystery/classification/machine%20learning%20in%20social%20sciences/smote/covariate%20drift/random%20forest/2022/10/14/Glass-ML-20th-Century.html