inputSelectExhaustive4reg

Input selection via exhaustive search for regression

Contents

Syntax

Description

[bestSelectedInput, allSelectedInput, allRecogRate, elapsedTime]=inputSelectExhaustive4reg(DS, inputNum, classifier, param, showPlot) performs input selection via exhaustive search.

• Input:
  • DS: dataset
  • inputNum: up to inputNum inputs are selected
  • classifier: classifier for input selection
  • param: parameters for classifier
  • showPlot: 0 for not plotting (default: 1)
• Output:
  • bestSelectedInput: overall selected input index
  • bestRecogRate: recognition rate based on the final selected input
  • allSelectedInput: all selected input during the process
  • allRecogRate: all recognition rate
  • elapseTime: elapsed time

Example

KNNC classifier

ds=prData('iris');
figure; inputSelectExhaustive4reg(ds, inf, 1);

Construct 15 KNN models, each with up to 4 inputs selected from 4 candidates...
modelIndex 1/15: selected={sepal length} => RMSE = 0.508304
modelIndex 2/15: selected={sepal width} => RMSE = 0.738416
modelIndex 3/15: selected={petal length} => RMSE = 0.257325
modelIndex 4/15: selected={petal width} => RMSE = 0.238059
modelIndex 5/15: selected={sepal length, sepal width} => RMSE = 0.427393
modelIndex 6/15: selected={sepal length, petal length} => RMSE = 0.246269
modelIndex 7/15: selected={sepal length, petal width} => RMSE = 0.238053
modelIndex 8/15: selected={sepal width, petal length} => RMSE = 0.256682
modelIndex 9/15: selected={sepal width, petal width} => RMSE = 0.228413
modelIndex 10/15: selected={petal length, petal width} => RMSE = 0.222477
modelIndex 11/15: selected={sepal length, sepal width, petal length} => RMSE = 0.244351
modelIndex 12/15: selected={sepal length, sepal width, petal width} => RMSE = 0.227091
modelIndex 13/15: selected={sepal length, petal length, petal width} => RMSE = 0.215729
modelIndex 14/15: selected={sepal width, petal length, petal width} => RMSE = 0.218177
modelIndex 15/15: selected={sepal length, sepal width, petal length, petal width} => RMSE = 0.215389

Overall min RMSE = 0.215389.
Selected 4 inputs (out of 4): sepal length, sepal width, petal length, petal width

Published with MATLAB® R2020b