001/*
002 * Copyright (c) 2015-2020, Oracle and/or its affiliates. All rights reserved.
003 *
004 * Licensed under the Apache License, Version 2.0 (the "License");
005 * you may not use this file except in compliance with the License.
006 * You may obtain a copy of the License at
007 *
008 *     http://www.apache.org/licenses/LICENSE-2.0
009 *
010 * Unless required by applicable law or agreed to in writing, software
011 * distributed under the License is distributed on an "AS IS" BASIS,
012 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express implied.
013 * See the License for the specific language governing permissions and
014 * limitations under the License.
015 */
016
017package org.tribuo.sequence;
018
019import com.oracle.labs.mlrg.olcut.config.Configurable;
020import com.oracle.labs.mlrg.olcut.provenance.Provenancable;
021import com.oracle.labs.mlrg.olcut.provenance.Provenance;
022import org.tribuo.Output;
023import org.tribuo.provenance.TrainerProvenance;
024
025import java.util.Collections;
026import java.util.Map;
027
028/**
029 * An interface for things that can train sequence prediction models.
030 */
031public interface SequenceTrainer<T extends Output<T>> extends Configurable, Provenancable<TrainerProvenance> {
032    
033    /**
034     * Trains a sequence prediction model using the examples in the given data set.
035     * @param examples the data set containing the examples.
036     * @return a prediction model that can be used to predict values for new examples.
037     */
038    default public SequenceModel<T> train(SequenceDataset<T> examples) {
039        return train(examples, Collections.emptyMap());
040    }
041
042    /**
043     * Trains a sequence prediction model using the examples in the given data set.
044     * @param examples the data set containing the examples.
045     * @param runProvenance Training run specific provenance (e.g., fold number).
046     * @return a predictive model that can be used to generate predictions for new examples.
047     */
048    public SequenceModel<T> train(SequenceDataset<T> examples, Map<String, Provenance> runProvenance);
049
050    /**
051     * Returns the number of times the train method has been invoked.
052     * @return The number of times train has been invoked.
053     */
054    public int getInvocationCount();
055}