Machine learning, penguins and explanatory data visualisations

dataviz

annotations

machine learning

ggplot2

tidyverse

tidyTuesday

An annotated data visualisation to illustrate the decision-tree model classification of penguins into species based on their flipper and bill lengths

Published

July 29, 2020

For this week’s 🐧#TidyTuesday I chanced upon clusters in the data and decided to apply some machine learning skills to get a decision tree and illustrate the outcomes:

✅ accuracy (misclassified = triangle)
✅ decision nodes (- - -)
✅ notable outlier

A scatterplot showing penguin flipper lengths (x axis) and bill lengths (y axis), coloured by species; the clusters neatly identify the three different species in the dataset. The visualisation is clearly annotated with dashed lines showing the decision nodes; any misclassified penguins are a triangle shape rather than a dot.

Code: https://github.com/cararthompson/tidytuesdays

Here’s the making of!

Video

Reuse

https://creativecommons.org/licenses/by/4.0/

Citation

For attribution, please cite this work as:

“Machine Learning, Penguins and Explanatory Data Visualisations.” 2020. July 29, 2020. https://www.cararthompson.com/posts/2020-07-29-tidy-tuesday.