updated on: 7th September 2021

A sleek CLI app for KMeans Clustering

Made with ♥ in India

KMeansExample

Whats new?

• Bar Plot Visualization of number of points in each cluster
• Pie Plot Visualization of Weightage of Clusters in overall

Table of Contents

• Introduction
• Getting Started
• Usage
• TODOs
• ChangeLog
• Preview
• License

Introduction

KMeansExample is a simple implementation of the K Means clustering Algorithm in Python.

Features

• Accurate division of clusters
• Graphic preview of clusters
• Naming of clusters
• Making Predictions
• Bar Chart of number of points per cluster
• Pie Chart of Cluster Weightage

Getting Started

Requirements

KMeansExample Requires these bare-minimum things to work:

• python 3.x - Python 3 and above
• matplotlib for previewing the data . If not installed

$ pip install matplotlib

Installation

KMeansExample doesn’t need to be installed, just run main.py without parameters.

$ python3 main.py

Usage

$ python3 main.py
 **
 Welcome to KMeansExample.
 **

A GUI prompt will open to let you choose a csv file

$ python3 main.py
 **
 Welcome to KMeansExample.
 **

Working on student records at data/test.csv  ..



  * (1) for Previewing the records
  * (2) for Proceeding with training
  * (3) for Exiting the predictor
Enter action:

hereafter, the menu interface will guide you.

TODOs

• Add more functionalities

ChangeLog

• See CHANGELOG

Preview for students.csv

• Prediction Tool

  Enter action: 4
  Enter Student's Attendance: 85
  Enter Student's Marks: 90
  Probability for Cluster 1: 77.36%
  Probability for Cluster 2: 61.99%
  Probability for Cluster 3: 93.16%
  Probability for Cluster 4: 67.50%

• Rich plotting of Clusters
  

• Bar Chart Representation
  

• Pie Chart Representation
  

• Raw Data Records
  

License

• See LICENSE

Syed Nasim, 2021