zhipeng93 commented on code in PR #160: URL: https://github.com/apache/flink-ml/pull/160#discussion_r1015050760
########## flink-ml-examples/src/main/java/org/apache/flink/ml/examples/feature/RandomSplitterExample.java: ########## @@ -0,0 +1,65 @@ +/* + * 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.examples.feature; + +import org.apache.flink.ml.feature.randomsplitter.RandomSplitter; +import org.apache.flink.streaming.api.datastream.DataStream; +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; +import org.apache.flink.table.api.Table; +import org.apache.flink.table.api.bridge.java.StreamTableEnvironment; +import org.apache.flink.types.Row; +import org.apache.flink.util.CloseableIterator; + +/** Simple program that creates a RandomSplitter instance and uses it for data splitting. */ +public class RandomSplitterExample { + public static void main(String[] args) { + StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment(); + StreamTableEnvironment tEnv = StreamTableEnvironment.create(env); + + // Generates input data. + DataStream<Row> inputStream = + env.fromElements( + Row.of(1, 10, 0), + Row.of(1, 10, 0), + Row.of(1, 10, 0), + Row.of(4, 10, 0), + Row.of(5, 10, 0), + Row.of(6, 10, 0), + Row.of(7, 10, 0), + Row.of(10, 10, 0), + Row.of(13, 10, 3)); + Table inputTable = tEnv.fromDataStream(inputStream).as("input"); + + // Creates a Splitter object and initializes its parameters. Review Comment: nit: RandomSplitter ########## docs/content/docs/operators/feature/randomsplitter.md: ########## @@ -0,0 +1,147 @@ +--- +title: "RandomSplitter" +weight: 1 +type: docs +aliases: +- /operators/feature/randomsplitter.html +--- + +<!-- +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. +--> + +## RandomSplitter + +An AlgoOperator which splits a table into N tables according to the given weights. + +### Parameters + +| Key | Default | Type | Required | Description | +|:--------|:-------------|:---------|:---------|:-------------------------------| +| weights | `[1.0, 1.0]` | Double[] | no | The weights of data splitting. | + +### Examples + +{{< tabs examples >}} + +{{< tab "Java">}} + +```java +import org.apache.flink.ml.feature.randomsplitter.RandomSplitter; +import org.apache.flink.streaming.api.datastream.DataStream; +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; +import org.apache.flink.table.api.Table; +import org.apache.flink.table.api.bridge.java.StreamTableEnvironment; +import org.apache.flink.types.Row; +import org.apache.flink.util.CloseableIterator; + +/** Simple program that creates a RandomSplitter instance and uses it for data splitting. */ +public class RandomSplitterExample { + public static void main(String[] args) { + StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment(); + StreamTableEnvironment tEnv = StreamTableEnvironment.create(env); + + // Generates input data. + DataStream<Row> inputStream = + env.fromElements( + Row.of(1, 10, 0), + Row.of(1, 10, 0), + Row.of(1, 10, 0), + Row.of(4, 10, 0), + Row.of(5, 10, 0), + Row.of(6, 10, 0), + Row.of(7, 10, 0), + Row.of(10, 10, 0), + Row.of(13, 10, 3)); + Table inputTable = tEnv.fromDataStream(inputStream).as("input"); + + // Creates a RandomSplitter object and initializes its parameters. + RandomSplitter splitter = new RandomSplitter().setWeights(4.0, 6.0); + + // Uses the Splitter to split inputData. Review Comment: nit: RandomSplitter ########## flink-ml-lib/src/test/java/org/apache/flink/ml/feature/RandomSplitterTest.java: ########## @@ -0,0 +1,147 @@ +/* + * 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.feature; + +import org.apache.flink.api.common.restartstrategy.RestartStrategies; +import org.apache.flink.configuration.Configuration; +import org.apache.flink.ml.feature.randomsplitter.RandomSplitter; +import org.apache.flink.ml.util.TestUtils; +import org.apache.flink.streaming.api.datastream.DataStreamSource; +import org.apache.flink.streaming.api.environment.ExecutionCheckpointingOptions; +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; +import org.apache.flink.table.api.Table; +import org.apache.flink.table.api.bridge.java.StreamTableEnvironment; +import org.apache.flink.test.util.AbstractTestBase; +import org.apache.flink.types.Row; + +import org.apache.commons.collections.IteratorUtils; +import org.junit.Before; +import org.junit.Rule; +import org.junit.Test; +import org.junit.rules.TemporaryFolder; + +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Comparator; +import java.util.List; + +import static org.junit.Assert.assertArrayEquals; +import static org.junit.Assert.assertEquals; + +/** Tests {@link RandomSplitter}. */ +public class RandomSplitterTest extends AbstractTestBase { + @Rule public final TemporaryFolder tempFolder = new TemporaryFolder(); + private StreamExecutionEnvironment env; + private StreamTableEnvironment tEnv; + + @Before + public void before() { + Configuration config = new Configuration(); + config.set(ExecutionCheckpointingOptions.ENABLE_CHECKPOINTS_AFTER_TASKS_FINISH, true); + + env = StreamExecutionEnvironment.getExecutionEnvironment(config); + env.setParallelism(1); + env.enableCheckpointing(100); + env.setRestartStrategy(RestartStrategies.noRestart()); + + tEnv = StreamTableEnvironment.create(env); + } + + private Table getTable(int size) { + DataStreamSource<Long> dataStream = env.fromSequence(0L, size); + return tEnv.fromDataStream(dataStream); + } + + @Test + public void testParam() { + RandomSplitter splitter = new RandomSplitter(); + splitter.setWeights(0.3, 0.4); + assertArrayEquals(new Double[] {0.3, 0.4}, splitter.getWeights()); + } + + @Test + public void testOutputSchema() { + Table tempTable = + tEnv.fromDataStream(env.fromElements(Row.of("", ""))) + .as("test_input", "dummy_input"); + + RandomSplitter splitter = new RandomSplitter().setWeights(0.5, 0.1); + Table[] output = splitter.transform(tempTable); + assertEquals(2, output.length); + for (Table table : output) { + assertEquals( + Arrays.asList("test_input", "dummy_input"), + table.getResolvedSchema().getColumnNames()); + } + } + + @Test + public void testWeights() throws Exception { + Table data = getTable(1000); + RandomSplitter splitter = new RandomSplitter().setWeights(2.0, 1.0, 2.0); + Table[] output = splitter.transform(data); + + List<Row> result0 = IteratorUtils.toList(tEnv.toDataStream(output[0]).executeAndCollect()); + List<Row> result1 = IteratorUtils.toList(tEnv.toDataStream(output[1]).executeAndCollect()); + List<Row> result2 = IteratorUtils.toList(tEnv.toDataStream(output[2]).executeAndCollect()); + assertEquals(result0.size() / 400.0, 1.0, 0.1); + assertEquals(result1.size() / 200.0, 1.0, 0.1); + assertEquals(result2.size() / 400.0, 1.0, 0.1); + verifyResultTables(data, output); + } + + @Test + public void testSaveLoadAndTransform() throws Exception { + Table data = getTable(2000); + RandomSplitter randomSplitter = new RandomSplitter().setWeights(4.0, 6.0); + + RandomSplitter splitterLoad = + TestUtils.saveAndReload( + tEnv, randomSplitter, TEMPORARY_FOLDER.newFolder().getAbsolutePath()); + + Table[] output = splitterLoad.transform(data); + List<Row> result0 = IteratorUtils.toList(tEnv.toDataStream(output[0]).executeAndCollect()); + List<Row> result1 = IteratorUtils.toList(tEnv.toDataStream(output[1]).executeAndCollect()); + assertEquals(result0.size() / 800.0, 1.0, 0.1); + assertEquals(result1.size() / 1200.0, 1.0, 0.1); + verifyResultTables(data, output); + } + + Comparator<Row> comparator = Review Comment: Is this still necessary? ########## flink-ml-examples/src/main/java/org/apache/flink/ml/examples/feature/RandomSplitterExample.java: ########## @@ -0,0 +1,65 @@ +/* + * 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.examples.feature; + +import org.apache.flink.ml.feature.randomsplitter.RandomSplitter; +import org.apache.flink.streaming.api.datastream.DataStream; +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; +import org.apache.flink.table.api.Table; +import org.apache.flink.table.api.bridge.java.StreamTableEnvironment; +import org.apache.flink.types.Row; +import org.apache.flink.util.CloseableIterator; + +/** Simple program that creates a RandomSplitter instance and uses it for data splitting. */ +public class RandomSplitterExample { + public static void main(String[] args) { + StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment(); + StreamTableEnvironment tEnv = StreamTableEnvironment.create(env); + + // Generates input data. + DataStream<Row> inputStream = + env.fromElements( + Row.of(1, 10, 0), + Row.of(1, 10, 0), + Row.of(1, 10, 0), + Row.of(4, 10, 0), + Row.of(5, 10, 0), + Row.of(6, 10, 0), + Row.of(7, 10, 0), + Row.of(10, 10, 0), + Row.of(13, 10, 3)); + Table inputTable = tEnv.fromDataStream(inputStream).as("input"); + + // Creates a Splitter object and initializes its parameters. + RandomSplitter splitter = new RandomSplitter().setWeights(4.0, 6.0); + + // Uses the Splitter to split inputData. Review Comment: nit: RandomSplitter -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
