Joel Therrien
a5fe856857
Changed the covariates to be more clever with how they produce the different splits. In the future (not yet implemented) a clever GroupDifferentiator could update the current score calculation based just on how many rows moved from one hand to the other. There were a few other changes as well; TreeTrainer#growTree now accepts a Random as a parameter which is used throughout the entire growing process. This means it's now theoretically possible to grow trees using a seed, so that results can be fully reproducible.
47 lines
1.4 KiB
Java
47 lines
1.4 KiB
Java
package ca.joeltherrien.randomforest;
|
|
|
|
import ca.joeltherrien.randomforest.covariates.Covariate;
|
|
import lombok.Getter;
|
|
import lombok.RequiredArgsConstructor;
|
|
|
|
import java.io.Serializable;
|
|
import java.util.HashMap;
|
|
import java.util.List;
|
|
import java.util.Map;
|
|
|
|
@RequiredArgsConstructor
|
|
public class CovariateRow implements Serializable {
|
|
|
|
private final Covariate.Value[] valueArray;
|
|
|
|
@Getter
|
|
private final int id;
|
|
|
|
public <V> Covariate.Value<V> getCovariateValue(Covariate<V> covariate){
|
|
return valueArray[covariate.getIndex()];
|
|
}
|
|
|
|
@Override
|
|
public String toString(){
|
|
return "CovariateRow " + this.id;
|
|
}
|
|
|
|
public static CovariateRow createSimple(Map<String, String> simpleMap, List<Covariate> covariateList, int id){
|
|
final Covariate.Value[] valueArray = new Covariate.Value[covariateList.size()];
|
|
final Map<String, Covariate> covariateMap = new HashMap<>();
|
|
|
|
covariateList.forEach(covariate -> covariateMap.put(covariate.getName(), covariate));
|
|
|
|
simpleMap.forEach((name, valueStr) -> {
|
|
final Covariate covariate = covariateMap.get(name);
|
|
|
|
if(covariate != null){ // happens often in tests where we experiment with adding / removing covariates
|
|
valueArray[covariate.getIndex()] = covariate.createValue(valueStr);
|
|
}
|
|
|
|
});
|
|
|
|
return new CovariateRow(valueArray, id);
|
|
}
|
|
|
|
}
|