| AbstractEvaluator |
Abstract base class for evaluator handling weka.core.Instance
objects.
|
| AbstractNearestNeighborBasedEvaluator |
Ancestor for evaluators that use a nearest neighbor search.
|
| AbstractSerializableEvaluator |
Abstract evaluator that can serialize its setup to disk and also load it
from there.
|
| CrossValidatedNeighborHood |
Evaluator that cross-validates the specified classifier on the neighborhood determined for the instance under evaluation.
|
| CrossValidatedPrediction |
Evaluator that (kind of) cross-validates the specified classifier on the neighborhood determined for the instance under evaluation.
A classifier is built on each of the training sets that is generated for the cross-validation.
|
| DistanceToCenter |
Uses the specified nearest neighbor search to determine a neighborhood.
|
| DistanceToClosest |
Uses the specified nearest neighbor search to locate the closest instance in the training data and returns the distance to it.
|
| EnsembleEvaluator |
Builds an ensemble of classifiers on the training data to determine the MAE per classifier, to be used as normalization factor.
At evaluation time, each classifier makes a prediction on the instance and the classification is divided by the normalization factor for this classifier.
|
| FakeEvaluator |
Fake evaluator, outputs random values based on min/max values.
|
| IntervalEstimatorEvaluator |
Stores the interval provided by the interval estimator classifier
|
| MultiClassifierEvaluator |
Multi-classifier based evaluator.
|
| NullEvaluator |
Dummy evaluator, which always return 1.0 as evaluation result.
|
| SavitzkyGolayRange |
This evaluator builds three classifiers:
- on Savitzky-Golay filtered data with no derivative
- on Savitzky-Golay filtered data with first derivative
- on Savitzky-Golay filtered data with second derivative
Each instance under evaluation will be pushed through the three classifiers separately and the range of the three predictions is then output as evaluation result.
|