zhipeng93 commented on a change in pull request #73: URL: https://github.com/apache/flink-ml/pull/73#discussion_r834164536
########## File path: flink-ml-lib/src/main/java/org/apache/flink/ml/feature/standardscaler/StandardScaler.java ########## @@ -0,0 +1,290 @@ +/* + * 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.standardscaler; + +import org.apache.flink.api.common.state.ListState; +import org.apache.flink.api.common.state.ListStateDescriptor; +import org.apache.flink.api.common.typeinfo.BasicTypeInfo; +import org.apache.flink.api.common.typeinfo.TypeInformation; +import org.apache.flink.api.java.tuple.Tuple3; +import org.apache.flink.api.java.typeutils.TupleTypeInfo; +import org.apache.flink.iteration.operator.OperatorStateUtils; +import org.apache.flink.ml.api.Estimator; +import org.apache.flink.ml.linalg.BLAS; +import org.apache.flink.ml.linalg.DenseVector; +import org.apache.flink.ml.linalg.Vector; +import org.apache.flink.ml.linalg.Vectors; +import org.apache.flink.ml.param.Param; +import org.apache.flink.ml.util.ParamUtils; +import org.apache.flink.ml.util.ReadWriteUtils; +import org.apache.flink.runtime.state.StateInitializationContext; +import org.apache.flink.runtime.state.StateSnapshotContext; +import org.apache.flink.streaming.api.datastream.DataStream; +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; +import org.apache.flink.streaming.api.operators.AbstractStreamOperator; +import org.apache.flink.streaming.api.operators.BoundedOneInput; +import org.apache.flink.streaming.api.operators.OneInputStreamOperator; +import org.apache.flink.streaming.runtime.streamrecord.StreamRecord; +import org.apache.flink.table.api.Table; +import org.apache.flink.table.api.bridge.java.StreamTableEnvironment; +import org.apache.flink.table.api.internal.TableImpl; +import org.apache.flink.types.Row; +import org.apache.flink.util.Preconditions; + +import java.io.IOException; +import java.util.HashMap; +import java.util.Map; + +/** + * An Estimator which implements the standard scaling algorithm. + * + * <p>Standardization is a common requirement for machine learning training because they may behave + * badly if the individual features of a input do not look like standard normally distributed data + * (e.g. Gaussian with 0 mean and unit variance). + * + * <p>This estimator standardizes the input features by removing the mean and scaling each dimension + * to unit variance. + */ +public class StandardScaler + implements Estimator<StandardScaler, StandardScalerModel>, + StandardScalerParams<StandardScaler> { + private final Map<Param<?>, Object> paramMap = new HashMap<>(); + + public StandardScaler() { + ParamUtils.initializeMapWithDefaultValues(paramMap, this); + } + + @Override + public StandardScalerModel fit(Table... inputs) { + Preconditions.checkArgument(inputs.length == 1); + StreamTableEnvironment tEnv = + (StreamTableEnvironment) ((TableImpl) inputs[0]).getTableEnvironment(); + DataStream<Tuple3<DenseVector, DenseVector, Long>> sumAndSquaredSumAndWeight = + tEnv.toDataStream(inputs[0]) + .transform( + "computeMeta", + new TupleTypeInfo<>( + TypeInformation.of(DenseVector.class), + TypeInformation.of(DenseVector.class), + BasicTypeInfo.LONG_TYPE_INFO), + new ComputeMeta(getFeaturesCol())); Review comment: Good point. My concern is that using`windowAll/window` may lead to a large memory consumption. As I understand, window operations need to cache the data in state. (Please correct me if I am wrong... -- 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]
