jiangxin369 commented on code in PR #174: URL: https://github.com/apache/flink-ml/pull/174#discussion_r1028792920
########## flink-ml-lib/src/main/java/org/apache/flink/ml/feature/countvectorizer/CountVectorizer.java: ########## @@ -0,0 +1,218 @@ +/* + * 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.countvectorizer; + +import org.apache.flink.api.common.functions.AggregateFunction; +import org.apache.flink.api.common.functions.MapFunction; +import org.apache.flink.api.java.tuple.Tuple2; +import org.apache.flink.ml.api.Estimator; +import org.apache.flink.ml.common.datastream.DataStreamUtils; +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.types.Row; +import org.apache.flink.util.Preconditions; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.stream.Collectors; + +/** + * {@link CountVectorizer} aims to help convert a collection of text documents to vectors of token + * counts. When an a-priori dictionary is not available, {@link CountVectorizer} can be used as an + * estimator to extract the vocabulary, and generates a {@link CountVectorizerModel}. The model + * produces sparse representations for the documents over the vocabulary, which can then be passed + * to other algorithms like LDA. Review Comment: * The JavaDoc often provides a description of the Estimator and starts with "An Estimator which", while the markdown starts with "CountVectorizer is an algorithm that ". * I'll remove the `@link`. -- 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
