7.1 kmeans configure

20211121

The kmeans package is Python based and utilises the system application ffmpeg for generating a video of the algorithm in action. Python libraries utilised include numpy, matplotlib, pandas, and scikit-learn. On a Ubuntu system the first three can be system installed as python3-numpy, python3-matplotlib, and python3-pandas. The scikit-learn library can be installed from PyPI. For MacOS they can all be installed from PyPI.

ml configure kmeans

Output will be something like:

*** The following required system packages are already installed:
  ffmpeg

*** The following required system packages are already installed:
  python3-numpy python3-matplotlib python3-pandas

*** The following required pip packages are already installed:
  scikit-learn

*** Downloading required files ...

To view the model's README:

ml readme kmeans

Python and support files are downloaded from GitHub as specified in the MLHUB.yaml file.

meta:
  name         : kmeans
  title        : An animation demonstration for the kmeans clustering
  keywords     : python, visualisation, clustering
  languages    : py
  license      : gpl3
  author       : Gefei Shan, Anita Williams
  url          : https://github.com/acwkayon/kmeans
dependencies:
  system:
    - ffmpeg
  python3:
    - numpy
    - matplotlib
    - pandas
  pip3:
    - scikit-learn
    - plotnine
  files:
    - README.md
    - demo.py
    - train.py
    - predict.py
    - utils.py
    - iris.csv
commands:
  demo : Demonstrate the model capabilities in one easy session.
  train : Training the kmeans model on a given csv data file.
  predict : Label the dataset with a provided model file (csv for cluster centres).
  normalise : Remap numeric input csv columns using z-score.
  visualise : Generate static plot of the final clustering.

---

Your donation will support ongoing availability and give you access to the PDF version of this book. Desktop Survival Guides include Data Science, GNU/Linux, and MLHub. Books available on Amazon include Data Mining with Rattle and Essentials of Data Science. Popular open source software includes rattle, wajig, and mlhub. Hosted by Togaware, a pioneer of free and open source software since 1984. Copyright © 1995-2022 Graham.Williams@togaware.com Creative Commons Attribution-ShareAlike 4.0