Github user zhengruifeng commented on a diff in the pull request: https://github.com/apache/spark/pull/19527#discussion_r147950931 --- Diff: mllib/src/main/scala/org/apache/spark/ml/feature/OneHotEncoderEstimator.scala --- @@ -0,0 +1,462 @@ +/* + * 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.hadoop.fs.Path + +import org.apache.spark.SparkException +import org.apache.spark.annotation.Since +import org.apache.spark.ml.{Estimator, Model} +import org.apache.spark.ml.attribute._ +import org.apache.spark.ml.linalg.Vectors +import org.apache.spark.ml.param._ +import org.apache.spark.ml.param.shared.{HasHandleInvalid, HasInputCols, HasOutputCols} +import org.apache.spark.ml.util._ +import org.apache.spark.sql.{DataFrame, Dataset} +import org.apache.spark.sql.expressions.UserDefinedFunction +import org.apache.spark.sql.functions.{col, lit, udf} +import org.apache.spark.sql.types.{DoubleType, NumericType, StructField, StructType} + +/** Private trait for params and common methods for OneHotEncoderEstimator and OneHotEncoderModel */ +private[ml] trait OneHotEncoderBase extends Params with HasHandleInvalid + with HasInputCols with HasOutputCols { + + /** + * Param for how to handle invalid data. + * Options are 'keep' (invalid data produces a vector of zeros) or 'error' (throw an error). + * Default: "error" + * @group param + */ + @Since("2.3.0") + override val handleInvalid: Param[String] = new Param[String](this, "handleInvalid", + "How to handle invalid data " + + "Options are 'keep' (invalid data produces a vector of zeros) or error (throw an error).", + ParamValidators.inArray(OneHotEncoderEstimator.supportedHandleInvalids)) + + setDefault(handleInvalid, OneHotEncoderEstimator.ERROR_INVALID) + + /** + * Whether to drop the last category in the encoded vector (default: true) + * @group param + */ + @Since("2.3.0") + final val dropLast: BooleanParam = + new BooleanParam(this, "dropLast", "whether to drop the last category") + setDefault(dropLast -> true) + + /** @group getParam */ + @Since("2.3.0") + def getDropLast: Boolean = $(dropLast) + + protected def checkParamsValidity(schema: StructType): Unit = { + val inputColNames = $(inputCols) + val outputColNames = $(outputCols) + val existingFields = schema.fields + + require(inputColNames.length == outputColNames.length, --- End diff -- it's better to add a checking for duplicated columns, like what `Imputer` and `Interaction` do, IMO
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org