xuyang1706 commented on a change in pull request #9184: [FLINK-13339][ml] Add an implementation of pipeline's api URL: https://github.com/apache/flink/pull/9184#discussion_r328494978
########## File path: flink-ml-parent/flink-ml-lib/src/main/java/org/apache/flink/ml/common/AlgoOperator.java ########## @@ -0,0 +1,156 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, + * software distributed under the License is distributed on an + * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY + * KIND, either express or implied. See the License for the + * specific language governing permissions and limitations + * under the License. + */ + +package org.apache.flink.ml.common; + +import org.apache.flink.api.common.typeinfo.TypeInformation; +import org.apache.flink.ml.api.misc.param.Params; +import org.apache.flink.ml.api.misc.param.WithParams; +import org.apache.flink.ml.batchoperator.source.TableSourceBatchOp; +import org.apache.flink.ml.params.shared.HasMLEnvironmentId; +import org.apache.flink.ml.streamoperator.source.TableSourceStreamOp; +import org.apache.flink.table.api.Table; +import org.apache.flink.table.api.TableSchema; +import org.apache.flink.table.api.internal.TableImpl; +import org.apache.flink.table.api.java.StreamTableEnvironment; + +import java.io.Serializable; + +/** + * Base class for algorithm operators. + * + * <p>Hold a Table as its output. + * + * @param <T> The class type of the {@link AlgoOperator} implementation itself + */ +public abstract class AlgoOperator<T extends AlgoOperator <T>> + implements WithParams<T>, HasMLEnvironmentId<T>, Serializable { + + /** + * Params for algorithms. + */ + private Params params; + + /** + * The table held by operator. + */ + private Table output = null; + + /** + * The side outputs of operator that be similar to the stream's side outputs. + */ + private Table[] sideOutputs = null; + + /** + * Construct the operator with empty Params. + */ + protected AlgoOperator() { Review comment: In later PRs, these APIs will be used and tested. For how using this constructor, I'd like to give an example. SplitBatchOp is widely used in ML data pre-preprossing, which splits one dataset input 2 dataset: training set and validation set. It is very convenient for us to write code like this: new SplitBatchOp().setSplitRatio(0.9) For output field. The AlgoOperator may have one or more result tables, in most cases, it has only one result. The output is the main operation result table, and the other results are kept in the sideOutputs. For example, 2 AlgoOperators: AlgoA and AlgoB, AlgoB takes the AlgoA’s results as its inputs, we can write the code like this: AlgoB.linkFrom(AlgoA) AlgoA.getOutput() provides the main result of AlgoA, and AlgoA.getSideOutputs() provides the other results of AlgoA. AlgoB will take the AlgoA’s results as its inputs by calling AlgoA.getOutput() and AlgoA.getSideOutputs(). ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
