From 6f4a4084b013c7c115cc481b2afb58266f12ea9a Mon Sep 17 00:00:00 2001 From: "GRT67@open" <32413040+hrukkudyr@users.noreply.github.com> Date: Fri, 7 Jul 2023 09:05:35 +0100 Subject: [PATCH] Update tutorial.md to use edited svg image Change transparent svg to a png with white background so that image is viable in dark view mode --- .../statistics/tutorials/clustering_machinelearning/tutorial.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/topics/statistics/tutorials/clustering_machinelearning/tutorial.md b/topics/statistics/tutorials/clustering_machinelearning/tutorial.md index ac653c8e9aea6a..0c1812ffb06129 100644 --- a/topics/statistics/tutorials/clustering_machinelearning/tutorial.md +++ b/topics/statistics/tutorials/clustering_machinelearning/tutorial.md @@ -74,7 +74,7 @@ Many clustering algorithms use distance measures to determine the similarity or The choice of a distance measure is crucial in clustering. It defines how the similarity of two elements `(x, y)` is calculated as it influences the shape of the clusters. The classical distance measures are [euclidean](https://en.wikipedia.org/wiki/Euclidean_distance) and [manhattan](https://en.wikipedia.org/wiki/Taxicab_geometry) distances. For the most common clustering algorithms, the default distance measure is euclidean. If the euclidean distance is chosen, then observations having high magnitudes of their respective features will be clustered together. The same holds for the observations having low magnitudes of their respective features. In Figure 3, we group the cells using euclidean distance and their distance matrix. -![Distances](images/raceid_distance.svg "Euclidean distance between three points (R, P, V) across three features (G1, G2, G3)") +![Distances](images/raceid_distance.png "Euclidean distance between three points (R, P, V) across three features (G1, G2, G3)") >