Can we consider regression tree (fine/ medium/coarse) present in regression learner app as classification and regression tree (CART)?
16 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Manas Saha
el 24 de Jul. de 2023
Comentada: Manas Saha
el 18 de Ag. de 2023
The screen shot of the regression tree (fine/medium/coarse) present in regression learner app is shown in the attachment for easy reference.
Here classification and regression tree (CART) means classification and regression tree algorithm mentioned in the research paper titled "A classification and regression tree algorithm for heart disease modeling and prediction" by Ozcan and Peker.
The research paper is also attached as reference.
Respuesta aceptada
Drew
el 15 de Ag. de 2023
The short answer is yes.
- Quoting from https://www.mathworks.com/help/stats/choose-regression-model-options.html, "The Regression Learner app uses the fitrtree function to train regression trees."
- Quoting from https://www.mathworks.com/help/stats/fitrtree.html, the default fitrtree PredictorSelection uses "Standard CART"
MATLAB's built-in decision tree implementation uses the Classification and Regression Trees (CART) algorithm. The fitctree function is used for building decision trees for classification tasks, and the fitrtree function is used for building decision trees for regression tasks. These functions use the CART algorithm, which involves Gini impurity for classification tasks and mean squared error for regression tasks to determine the best splits for building the tree.
For more info, and available variations on the default standard CART algorithms, see:
- https://www.mathworks.com/help/stats/fitrtree.html
- https://www.mathworks.com/help/stats/fitctree.html
- https://www.mathworks.com/help/stats/improving-classification-trees-and-regression-trees.html#bvgp2zo-1
0 comentarios
Más respuestas (0)
Ver también
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!