Use trained classifier to predict target values for new samples.
Use trained estimator to predict target values for new samples. These will
typically be unseen samples, e.g., test data (derived manually or from
split_table) or samples with unknown values, but can theoretically be any
samples present in a feature table that contain overlapping features with
the feature table used to train the estimator.
Parameters
- table : FeatureTable[Frequency]
- Feature table containing all features that should be used for target
prediction.
- sample_estimator : SampleEstimator[Classifier]
- Sample classifier trained with fit_classifier.
Returns
- predictions : SampleData[ClassifierPredictions]
- Predicted target values for each input sample.