rebo16v commented on code in PR #48347: URL: https://github.com/apache/spark/pull/48347#discussion_r1808201204
########## mllib/src/main/scala/org/apache/spark/ml/feature/TargetEncoder.scala: ########## @@ -0,0 +1,447 @@ +/* + * 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.NominalAttribute +import org.apache.spark.ml.param._ +import org.apache.spark.ml.param.shared._ +import org.apache.spark.ml.util._ +import org.apache.spark.sql.{Column, DataFrame, Dataset, Row} +import org.apache.spark.sql.functions._ +import org.apache.spark.sql.types._ + +/** Private trait for params and common methods for TargetEncoder and TargetEncoderModel */ +private[ml] trait TargetEncoderBase extends Params with HasLabelCol + with HasInputCol with HasInputCols with HasOutputCol with HasOutputCols with HasHandleInvalid { + + /** + * Param for how to handle invalid data during transform(). + * Options are 'keep' (invalid data presented as an extra categorical feature) or + * 'error' (throw an error). + * Note that this Param is only used during transform; during fitting, invalid data + * will result in an error. + * Default: "error" + * @group param + */ + @Since("4.0.0") + override val handleInvalid: Param[String] = new Param[String](this, "handleInvalid", + "How to handle invalid data during transform(). " + + "Options are 'keep' (invalid data presented as an extra categorical feature) " + + "or error (throw an error). Note that this Param is only used during transform; " + + "during fitting, invalid data will result in an error.", + ParamValidators.inArray(TargetEncoder.supportedHandleInvalids)) + + setDefault(handleInvalid -> TargetEncoder.ERROR_INVALID) + + @Since("4.0.0") + val targetType: Param[String] = new Param[String](this, "targetType", + "How to handle invalid data during transform(). " + + "Options are 'keep' (invalid data presented as an extra categorical feature) " + Review Comment: Ups! Fixed for targetType & smoothing ########## mllib/src/main/scala/org/apache/spark/ml/feature/TargetEncoder.scala: ########## @@ -0,0 +1,447 @@ +/* + * 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.NominalAttribute +import org.apache.spark.ml.param._ +import org.apache.spark.ml.param.shared._ +import org.apache.spark.ml.util._ +import org.apache.spark.sql.{Column, DataFrame, Dataset, Row} +import org.apache.spark.sql.functions._ +import org.apache.spark.sql.types._ + +/** Private trait for params and common methods for TargetEncoder and TargetEncoderModel */ +private[ml] trait TargetEncoderBase extends Params with HasLabelCol + with HasInputCol with HasInputCols with HasOutputCol with HasOutputCols with HasHandleInvalid { + + /** + * Param for how to handle invalid data during transform(). + * Options are 'keep' (invalid data presented as an extra categorical feature) or + * 'error' (throw an error). + * Note that this Param is only used during transform; during fitting, invalid data + * will result in an error. + * Default: "error" + * @group param + */ + @Since("4.0.0") + override val handleInvalid: Param[String] = new Param[String](this, "handleInvalid", + "How to handle invalid data during transform(). " + + "Options are 'keep' (invalid data presented as an extra categorical feature) " + + "or error (throw an error). Note that this Param is only used during transform; " + Review Comment: done -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
