https://github.com/kizman-23/unsupervised_models

https://github.com/kizman-23/unsupervised_models

Last synced: 23 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/kizman-23/unsupervised_models
• Owner: KizMan-23
• Created: 2024-08-18T17:10:53.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-12-11T19:05:41.000Z (about 1 month ago)
• Last Synced: 2024-12-11T20:19:16.009Z (about 1 month ago)
• Language: Jupyter Notebook
• Size: 1.11 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
Unsupervised_Models is a repository for models trained using unsupervised techniques.

unsupervised model is a machine learning technique in which the data are not pre-labelled but the algorithm identifies patterns, 

relationships underlining the data and they are grouped according to those similarities

[Clusters](https://github.com/KizMan-23/unsupervised_models/blob/main/clusters.ipynb) is a project that showcases the underlining algorithm of different cluster techniques such as KMeans Clustering, Agglomerative Clustering, Hierrachical Clustering

[KMean Clustering](kmeans.ipynb) this is re-purposing of the Kmeans algorithm from scratch using artists' track performance dataset. This project gives an internal understanding of kmeans algorithm and how it functions to find pattern

within datasets and group items into clusters of similar relationships

![kmeans](https://github.com/user-attachments/assets/c8e558bb-5812-4aa3-9164-62c3276d6648)

Visualising the movements of centroids until it converges

![kmean viz](https://github.com/user-attachments/assets/3619270a-06d4-4828-855f-c495cfd45bfe)