jharvey09 / Cookies_Crumble_but_CryptoCurrency_Clusters

In this project, the tools used are unsupervised learning (K-Means Clustering) accompanied by 3-D HVPlot visualizations to group cryptocurrencies by feature

Cookies Crumble but CryptoCurrency Clusters

Background:

In this project, I will be using tools such as unsupervised learning and Amazon SageMaker to initiate clustering cryptocurrencies and to create plots that will present the results.

Table Of Contents:

Tasks

Steps

Reducing Dimensions Using PCA

Clustering Cryptocurrencies Using K-Means

Data Visualization

Tasks:

1. Data PreProcessing: Prepare data for dimension reduction with PCA and clustering using K-Means
2. Reducing Data Dimensions Using PCA: Reducing data dimensions using the PCA algorithm from sklearn
3. Clustering Cryptocurrencies Using K-Means: Predict clusters using the cryptocurrencies data using the KMeans algorithm from sklearn.
4. Visualizing Results: Create plots and data tables to present the results

Steps:

Loading and PreProcessing Data:

1. Load data, create DataFrame w/neccessary coulmns

2. Remove rows with cryptocurrencies that don't have any coins mined

3. Drop the "CoinName" column, it wont be used in the clustering algorithm

Reducing Dimensions Using PCA:

1. Reduce dimensions to 3 principal components. Then load into DataFrame w/principle components data

Clustering Cryptocurrencies Using K-Means:

1. Finding the best value for K using the Elbow Curve, using the inertia model
2. Initialized the K-Means model, fit the K-Means model, create a DataFrame including predicted clusters & cryptocurrencies features

Data Visualization:

Table of Cryptocurrencies:

Scatter Plot of Cryptocurrencies: