srowen commented on a change in pull request #24777: [SPARK-16692][ML][Python] add MultilabelClassificationEvaluator URL: https://github.com/apache/spark/pull/24777#discussion_r292415667
########## File path: mllib/src/main/scala/org/apache/spark/ml/evaluation/MultilabelClassificationEvaluator.scala ########## @@ -0,0 +1,137 @@ +/* + * 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.evaluation + +import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.ml.param._ +import org.apache.spark.ml.param.shared._ +import org.apache.spark.ml.util._ +import org.apache.spark.mllib.evaluation.MultilabelMetrics +import org.apache.spark.sql.Dataset +import org.apache.spark.sql.functions._ +import org.apache.spark.sql.types._ + + +/** + * :: Experimental :: + * Evaluator for multi-label classification, which expects two input + * columns: prediction and label. + */ +@Since("3.0.0") +@Experimental +class MultilabelClassificationEvaluator (override val uid: String) + extends Evaluator with HasPredictionCol with HasLabelCol + with DefaultParamsWritable { + + import MultilabelClassificationEvaluator.supportedMetricNames + + def this() = this(Identifiable.randomUID("mlcEval")) + + /** + * param for metric name in evaluation (supports `"f1Measure"` (default), `"subsetAccuracy"`, + * `"accuracy"`, `"hammingLoss"`, `"precision"`, `"recall"`, `"precisionByLabel"`, + * `"recallByLabel"`, `"f1MeasureByLabel"`, `"microPrecision"`, `"microRecall"`, + * `"microF1Measure"`) + * @group param + */ + final val metricName: Param[String] = { + val allowedParams = ParamValidators.inArray(supportedMetricNames) + new Param(this, "metricName", "metric name in evaluation " + + s"${supportedMetricNames.mkString("(", "|", ")")}", allowedParams) + } + + /** @group getParam */ + def getMetricName: String = $(metricName) + + /** @group setParam */ + def setMetricName(value: String): this.type = set(metricName, value) + + setDefault(metricName -> "f1Measure") + + final val label: DoubleParam = new DoubleParam(this, "label", + "The label whose metric will be computed in precisionByLabel|recallByLabel|" + + "f1MeasureByLabel. Must be >= 0. The default value is 0.", + ParamValidators.gtEq(0.0)) + + /** @group getParam */ + def getLabel: Double = $(label) + + /** @group setParam */ + def setLabel(value: Double): this.type = set(label, value) Review comment: Sounds good to me, just anything to distinguish its purpose. I suppose we say `labelCol` specifies the _class_ that the instance is labeled with, and `metricClass` chooses the _class_ to use when evaluating the 1 vs all metric. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
