zhipeng93 commented on code in PR #141: URL: https://github.com/apache/flink-ml/pull/141#discussion_r947400349
########## flink-ml-lib/src/main/java/org/apache/flink/ml/feature/hashingtf/HashingTF.java: ########## @@ -0,0 +1,193 @@ +/* + * 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.hashingtf; + +import org.apache.flink.api.common.functions.MapFunction; +import org.apache.flink.api.java.typeutils.RowTypeInfo; +import org.apache.flink.ml.api.Transformer; +import org.apache.flink.ml.common.datastream.TableUtils; +import org.apache.flink.ml.linalg.Vectors; +import org.apache.flink.ml.linalg.typeinfo.VectorTypeInfo; +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.streaming.api.datastream.DataStream; +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.table.catalog.ResolvedSchema; +import org.apache.flink.types.Row; +import org.apache.flink.util.Preconditions; + +import org.apache.commons.lang3.ArrayUtils; + +import java.io.IOException; +import java.util.Arrays; +import java.util.HashMap; +import java.util.Map; + +import static org.apache.flink.shaded.guava30.com.google.common.hash.Hashing.murmur3_32; + +/** + * A Transformer that maps a sequence of terms(strings, numbers, booleans) to a sparse vector with a + * specified dimension using the hashing trick. + * + * <p>If multiple features are projected into the same column, the output values are accumulated by + * default. Users could also enforce all non-zero output values as 1 by setting {@link + * HashingTFParams#BINARY} as true. + * + * <p>For the hashing trick, see https://en.wikipedia.org/wiki/Feature_hashing for details. + */ +public class HashingTF implements Transformer<HashingTF>, HashingTFParams<HashingTF> { + private final Map<Param<?>, Object> paramMap = new HashMap<>(); + + private static final org.apache.flink.shaded.guava30.com.google.common.hash.HashFunction + HASH_FUNC = murmur3_32(0); Review Comment: I think it is just a personal choice. So I will just keep using 0 as the seed here. -- 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: issues-unsubscr...@flink.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
