How to construct a regression tree

1 view (last 30 days)
Salad Box
Salad Box on 8 Jan 2019
Edited: Stephen23 on 9 Jan 2019
Hi,
As I was trying to understand the matlab example on the documentation page for constructing a regression tree https://uk.mathworks.com/help/stats/regressiontree-class.html, below is the example.
>> load carsmall;
>> whos
Name Size Bytes Class Attributes
Acceleration 100x1 800 double
Cylinders 100x1 800 double
Displacement 100x1 800 double
Horsepower 100x1 800 double
MPG 100x1 800 double
Mfg 100x13 2600 char
Model 100x33 6600 char
Model_Year 100x1 800 double
Origin 100x7 1400 char
Weight 100x1 800 double
>> tree = fitrtree([Weight, Cylinders],MPG,...
'categoricalpredictors',2,'MinParentSize',20,...
'PredictorNames',{'W','C'})
tree =
RegressionTree
PredictorNames: {'W' 'C'}
ResponseName: 'Y'
CategoricalPredictors: 2
ResponseTransform: 'none'
NumObservations: 94
Properties, Methods
>> mileage4K = predict(tree,[4000 4; 4000 6; 4000 8])
mileage4K =
19.2778
19.2778
14.3889
I wonder how the mileage is predicted while there is no variable in 'carsmall' named mileage.
  3 Comments
Salad Box
Salad Box on 9 Jan 2019
Edited: Salad Box on 9 Jan 2019
Yes you are right. Someone who constructed 'fitrtree' documentation webpage has comfirmed that the varialbe 'MPG' is the variable 'mileage'. But as someone living in the UK, mileage means the total miles a car has been driven.
Thanks for answering!
Star Strider
Star Strider on 9 Jan 2019
My pleasure!
As Winston Churchill noted, the U.S. and the U.K. are ‘two nations divided by a common language’.

Sign in to comment.

Answers (0)

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!