https://github.com/purcellcjp/cryptoclustering

This project applies K-means clustering to group crypto-currencies based on 24 hr and 7 day price changes. In addition, it investigates the impact of dimensionality reduction using Principal Component Analysis (PCA) on clustering outcomes.
https://github.com/purcellcjp/cryptoclustering

clustering cryptocurrency machine-learning pca-analysis unsupervised-learning

Last synced: 6 months ago
JSON representation

This project applies K-means clustering to group crypto-currencies based on 24 hr and 7 day price changes. In addition, it investigates the impact of dimensionality reduction using Principal Component Analysis (PCA) on clustering outcomes.

• Host: GitHub
• URL: https://github.com/purcellcjp/cryptoclustering
• Owner: purcellcjp
• Created: 2024-11-04T16:18:12.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-11-07T19:50:35.000Z (about 1 year ago)
• Last Synced: 2025-02-05T17:12:55.137Z (11 months ago)
• Topics: clustering, cryptocurrency, machine-learning, pca-analysis, unsupervised-learning
• Language: Jupyter Notebook
• Homepage:
• Size: 1.27 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Crypto Clustering

## Overview

In this challenge, you'll use your knowledge of Python and unsupervised learning to predict if cryptocurrencies are affected by 24-hour or 7-day price changes.

## Steps

1. Load the data into a DataFrame.

2. Prepare the data by scaling it using StandardScaler().

3. Find the best value for k using the Scaled DataFrame.

4. Cluster cryptocurrencies with K-means using the original scaled data.

5. Optimize clusters with Principal Component Analysis (PCA)

6. Find the best value for k using the PCA DataFrame.

7. Cluster cryptocurrencies with K-means using the PCA DataFrame.

8. Visualize and compare the results using hvPlot.

## Results

The project includes the following visualizations:

1. Elbow curve for the original data.

![alt text](Images/crypto_elbow_plot.jpg)

 

2. Scatter plot of cryptocurrency clusters based on the original data.

![alt text](Images/crypto_scaled_predictions_scatter_plot.jpg)

3. Elbow curve for the PCA data.

![alt text](Images/pca_crypto_elbow_plot.jpg)

4. Scatter plot of cryptocurrency clusters based on the PCA data.

![alt text](Images/crypto_pca_predictions_scatter_plot.jpg)

## Conclusion

The project analyzes the impact of using fewer features on clustering the data using K-means. Comparing the clustering results of the original data and the PCA data helps to understand the effect of dimensionality reduction on the clustering process.

## Dependencies

- Python

- pandas

- scikit-learn

- hvPlot