func testEmbeddedFeaturesFiltering(numBaseModels, maxTreeHeight int, train_dataset, test_dataset *mlearn.DataSet) (
[]testEmbeddedFeaturesFilteringResult, float64) {
fmt.Println("training adaboost classifier with embedded features filtering ...")
cartTrainer := adaboost.NewCARTClassifierTrainer(train_dataset,
adaboost.CARTClassifierTrainOptions{MaxDepth: int(maxTreeHeight), MinElementsInLeaf: 10, EnableEmbeddedFeaturesRanking: true})
adaboostTrainer := adaboost.NewAdaboostClassifierTrainer(cartTrainer)
classifier := adaboostTrainer.TrainClassifier(train_dataset,
adaboost.AdaboostClassifierTrainOptions{MaxEstimators: numBaseModels, EnableEmbeddedFeaturesRanking: true})
ranked_features := adaboostTrainer.GetRankedFeatures()
fmt.Println("predicting ...")
predictions := make([]int, len(test_dataset.Classes))
for i := range predictions {
predictions[i] = classifier.PredictProbe(test_dataset.GetSample(i))
}
precision, recall, ref_f1 := mlearn.PrecisionRecallF1(predictions, test_dataset.Classes, test_dataset.ClassesNum)
fmt.Printf("reference precision: %.3v recall: %.3v f1: %.3v \n\n", precision, recall, ref_f1)
var test_results []testEmbeddedFeaturesFilteringResult
for j := 10; j < test_dataset.FeaturesNum; j++ {
fmt.Printf("now training again using only %v of selected features ...\n", j)
selected_features := ranked_features[:j]
fmt.Println("selected features are: ")
fmt.Println(selected_features)
train_data_subset := &mlearn.DataSet{}
test_data_subset := &mlearn.DataSet{}
*train_data_subset = *train_dataset
*test_data_subset = *test_dataset
train_data_subset.SubsetFeatures(selected_features)
test_data_subset.SubsetFeatures(selected_features)
fmt.Println()
cartTrainer = adaboost.NewCARTClassifierTrainer(train_data_subset,
adaboost.CARTClassifierTrainOptions{MaxDepth: int(maxTreeHeight), MinElementsInLeaf: 10})
adaboostTrainer = adaboost.NewAdaboostClassifierTrainer(cartTrainer)
classifier = adaboostTrainer.TrainClassifier(train_data_subset,
adaboost.AdaboostClassifierTrainOptions{MaxEstimators: numBaseModels})
fmt.Println("predicting ...")
predictions = make([]int, len(test_data_subset.Classes))
for i := range predictions {
predictions[i] = classifier.PredictProbe(test_data_subset.GetSample(i))
}
precision, recall, f1 := mlearn.PrecisionRecallF1(predictions, test_dataset.Classes, test_dataset.ClassesNum)
fmt.Printf("precision: %.3v recall: %.3v f1: %.3v \n", precision, recall, f1)
test_results = append(test_results, testEmbeddedFeaturesFilteringResult{FeaturesCount: j, F1: f1})
}
return test_results, ref_f1
}
func testCARTClassifier(train_dataset, test_dataset *mlearn.DataSet) {
fmt.Println("testing CART classifier itself ...")
cartTrainer := adaboost.NewCARTClassifierTrainer(train_dataset,
adaboost.CARTClassifierTrainOptions{MaxDepth: 0, MinElementsInLeaf: 1})
classifier := cartTrainer.TrainClassifier(train_dataset)
predictions := make([]int, len(test_dataset.Classes))
for i := range predictions {
predictions[i] = classifier.PredictProbe(test_dataset.GetSample(i))
}
precision, recall, f1 := mlearn.PrecisionRecallF1(predictions, test_dataset.Classes, test_dataset.ClassesNum)
// here we expect f1 == 1.0
fmt.Printf("precision: %.3v recall: %.3v f1: %.3v \n\n", precision, recall, f1)
}
func testAdaboostClassifier(numBaseModels, maxTreeHeight, minLeafItems int, train_dataset, test_dataset *mlearn.DataSet) {
fmt.Println("training adaboost classifier over CART trees ...")
cartTrainer := adaboost.NewCARTClassifierTrainer(train_dataset,
adaboost.CARTClassifierTrainOptions{MaxDepth: maxTreeHeight, MinElementsInLeaf: minLeafItems})
adaboostTrainer := adaboost.NewAdaboostClassifierTrainer(cartTrainer)
classifier := adaboostTrainer.TrainClassifier(train_dataset,
adaboost.AdaboostClassifierTrainOptions{MaxEstimators: numBaseModels})
fmt.Println("predicting ...")
predictions := make([]int, len(test_dataset.Classes))
for i := range predictions {
predictions[i] = classifier.PredictProbe(test_dataset.GetSample(i))
}
precision, recall, f1 := mlearn.PrecisionRecallF1(predictions, test_dataset.Classes, test_dataset.ClassesNum)
fmt.Printf("\nprecision: %.3v recall: %.3v f1: %.3v \n", precision, recall, f1)
}