Find the nearest bridge between groups

One nearby pair connects otherwise spread-out groups

Two groups of sensor response times can be close through only one pair. Botie needs the single-linkage distance used to consider their merger.

BOTIE

For groups [0, 8] and [9, 20], which pair determines single linkage?

The inputs we are comparing

First group's response times

Separated groups

Touching through one pair

Second group's response times

Separated groups

Touching through one pair

Result for separated groups

Choose an explanation to test

The two group means, because clustering always compares centres8 and 9, because their cross-group distance is smallest0 and 20, because their distance covers the full span

The closest responses sit inside the sorted groups

This check uses the pieces from “Find the closest cross-group pair”.

BOTIE

The two groups now contain unequal numbers of response times. Predict their single-linkage distance by considering cross-group pairs.

First group's response times: 01
14
29
Second group's response times: 05
112

What result should your machine produce for this case?

Use a number, text, or an array matching the requested result. For a matrix, put each row in brackets. Saving your prediction runs your current construction on these inputs and checks the earlier examples too.

Build a construction in the workspace above first. This case will test those pieces.

How could replacing minimum with maximum change a sequence of merges, even if every pairwise distance stayed the same?

Your notes for later. These stay with this journey.

A linkage definition determines what 'close groups' means before an agglomerative method chooses its merges.

This workshop calculates one linkage comparison in one dimension. A complete agglomerative algorithm repeatedly chooses and records merges.

Work through the Python challenges →

Continue the courseDensity-Based Clustering →

← k-Means Clustering