Github user jkbradley commented on a diff in the pull request: https://github.com/apache/spark/pull/19746#discussion_r156795068 --- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/VectorSizeHint.scala --- @@ -0,0 +1,188 @@ +/* + * 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.spark.ml.feature + +import org.apache.spark.SparkException +import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.ml.Transformer +import org.apache.spark.ml.attribute.AttributeGroup +import org.apache.spark.ml.linalg.{Vector, VectorUDT} +import org.apache.spark.ml.param.{IntParam, Param, ParamMap, ParamValidators} +import org.apache.spark.ml.param.shared.{HasHandleInvalid, HasInputCol} +import org.apache.spark.ml.util.{DefaultParamsReadable, DefaultParamsWritable, Identifiable} +import org.apache.spark.sql.{Column, DataFrame, Dataset} +import org.apache.spark.sql.functions.{col, udf} +import org.apache.spark.sql.types.StructType + +/** + * :: Experimental :: + * A feature transformer that adds size information to the metadata of a vector column. + * VectorAssembler needs size information for its input columns and cannot be used on streaming + * dataframes without this metadata. + * + */ +@Experimental +@Since("2.3.0") +class VectorSizeHint @Since("2.3.0") (@Since("2.3.0") override val uid: String) + extends Transformer with HasInputCol with HasHandleInvalid with DefaultParamsWritable { + + @Since("2.3.0") + def this() = this(Identifiable.randomUID("vectSizeHint")) + + /** + * The size of Vectors in `inputCol`. + * @group param + */ + @Since("2.3.0") + val size: IntParam = new IntParam( + this, + "size", + "Size of vectors in column.", + {s: Int => s >= 0}) + + /** group getParam */ + @Since("2.3.0") + def getSize: Int = getOrDefault(size) + + /** @group setParam */ + @Since("2.3.0") + def setSize(value: Int): this.type = set(size, value) + + /** @group setParam */ + @Since("2.3.0") + def setInputCol(value: String): this.type = set(inputCol, value) + + /** + * Param for how to handle invalid entries. Invalid vectors include nulls and vectors with the + * wrong size. The options are `skip` (filter out rows with invalid vectors), `error` (throw an + * error) and `keep` (do not check the vector size, and keep all rows). `error` by default. + * @group param + */ + @Since("2.3.0") + override val handleInvalid: Param[String] = new Param[String]( + this, + "handleInvalid", + "How to handle invalid vectors in inputCol. Invalid vectors include nulls and vectors with " + + "the wrong size. The options are skip (filter out rows with invalid vectors), error " + + "(throw an error) and keep (do not check the vector size, and keep all rows). `error` by " + --- End diff -- keep -> optimistic
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org