Main Content

Find Change Points

Find abrupt changes in data in the Live Editor

Since R2019b

Description

The Find Change Points task lets you interactively find abrupt changes in the mean, variance, or slope and intercept of data. The task automatically generates MATLAB® code for your live script.

Using this task, you can:

  • Specify the change point type and locate the change points in data in a workspace variable.

  • Adjust the number of detected change points.

  • Visualize change point locations and the segments of data between them.

Related Functions

Find Change Points generates code that uses the ischange function.

Find Change Points task in the Live Editor

Open the Task

To add the Find Change Points task to a live script in the MATLAB Editor:

  • On the Live Editor tab, select Task > Find Change Points.

  • In a code block in the script, type a relevant keyword, such as change, find, variance, or linear. Select Find Change Points from the suggested command completions. For some keywords, the task automatically updates one or more corresponding parameters.

Examples

expand all

Interactively find abrupt changes in the slope and intercept of data using the Find Change Points task in the Live Editor.

Create a vector of noisy data. Create a plot to visualize the data.

data = [zeros(1,100) 1:100 99:-1:50  50*ones(1,250)] + 10*rand(1,500);
plot(1:500,data)

Open the Find Change Points task in the Live Editor. To find abrupt changes in the slope and intercept of the vector, select data as the input data.

In the Specify parameters section of the task, in the Type of change field, specify the change detection method as Linear. To reduce the number of change points detected due to noise, increase the change point threshold to 100. Alternatively, you can specify the maximum number of change points to detect.

To view the segments between change points more clearly, remove the input data from the plot by clearing the Input data field in the Display results section.

Live Task

Related Examples

Parameters

expand all

This task operates on input data contained in a vector, table, or timetable. The data can be of type single or double.

For table or timetable input data, to clean all variables of type single or double, select All supported variables. To choose which single or double variables to clean, select Specified variables.

Specify the method for detecting changes in the input data as one of these options.

Method

Description

mean

Find abrupt changes in the mean of the data.

variance

Find abrupt changes in the variance of the data.

linear

Find abrupt changes in the slope and intercept of the data.

Version History

Introduced in R2019b

expand all