Easier to read with cream paper, a tint, more contrast or larger text? Choose your colours and text, once, for every page.

Preview

DA 3.3, 3.4: Clusters, groups and places

This is the first page of the lesson. Read it and have a go at the activities. The rest is in the full lesson.

60 minutes

Where should the van wait?

A made-up shop delivers to eight homes. A van can wait at two places. Where should the two places be?

Nobody has labelled the homes "north" or "south". You want the data to show its own groups. Finding groups with no labels is the job of clustering.

Key words

WordWhat it meansExample
Unsupervised learningMachine learning with no right answers given. The computer finds structure itself.Finding groups of homes
ClusterA group of data points that are close or alike.Four homes near the river
ClusteringGrouping data points so that points in one group are alike.Two groups of homes
CentreThe average position of the points in a cluster.The middle of one group
GeospatialData about places on the Earth.Where each customer lives
EnrichAdd useful extra columns to data you already have.Add an area name to each customer
Lookup tableA small table that holds extra facts about one kind of thing.Each district and its area
DatasetA set of data that is ready to be analysed.The customers table
Machine learningA part of AI where a computer finds the rule from examples.Learning from past days

The cells students fill in are left blank in this preview.

By the end of this lesson

Note

I can explain clustering and unsupervised learning, follow a simple clustering method, and enrich a dataset with place data.

Starter: last lesson

Have a go

Starter: last lesson

3 questions
Have a go: your answers are marked here and then forgotten. Sign in if you would like your score kept, and to pick up where you left off.Sign in to keep your score

Your answers are marked here and are not kept. A college account keeps every student’s marks.

No labels, just structure

Unsupervised learning has no right answers to learn from. The computer looks at the data and finds structure on its own.

Clustering is the main kind. It groups points so that each group is alike inside and different from the others. A shop can use it to group customers who buy in similar ways.

How a clustering method works

One well known method has four steps. You choose how many groups you want, here two.

  1. Pick a starting centre for each group.
  2. Give every point to its nearest centre.
  3. Move each centre to the average position of its points.
  4. Repeat steps 2 and 3 until nothing changes.

Check: the order of the steps

Have a go

Check: the order of the steps

3 questions
Have a go: your answers are marked here and then forgotten. Sign in if you would like your score kept, and to pick up where you left off.Sign in to keep your score

Your answers are marked here and are not kept. A college account keeps every student’s marks.

The lesson goes on

11 more parts of this lesson are in the full curriculum, with the tasks, the final check and the labs. A college account gives your students all of it.