Github user jkbradley commented on a diff in the pull request: https://github.com/apache/spark/pull/15435#discussion_r134627545 --- Diff: mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala --- @@ -1324,90 +1354,147 @@ private[ml] class MultiClassSummarizer extends Serializable { } /** - * Abstraction for multinomial Logistic Regression Training results. - * Currently, the training summary ignores the training weights except - * for the objective trace. - */ -sealed trait LogisticRegressionTrainingSummary extends LogisticRegressionSummary { - - /** objective function (scaled loss + regularization) at each iteration. */ - def objectiveHistory: Array[Double] - - /** Number of training iterations until termination */ - def totalIterations: Int = objectiveHistory.length - -} - -/** - * Abstraction for Logistic Regression Results for a given model. + * Abstraction for logistic regression results for a given model. */ sealed trait LogisticRegressionSummary extends Serializable { /** * Dataframe output by the model's `transform` method. */ + @Since("1.5.0") def predictions: DataFrame /** Field in "predictions" which gives the probability of each class as a vector. */ + @Since("1.5.0") def probabilityCol: String + /** Field in "predictions" which gives the prediction of each class. */ + @Since("2.3.0") + def predictionCol: String + /** Field in "predictions" which gives the true label of each instance (if available). */ + @Since("1.5.0") def labelCol: String /** Field in "predictions" which gives the features of each instance as a vector. */ + @Since("1.6.0") def featuresCol: String + @transient private val multiclassMetrics = { + new MulticlassMetrics( + predictions.select( + col(predictionCol), + col(labelCol).cast(DoubleType)) + .rdd.map { case Row(prediction: Double, label: Double) => (prediction, label) }) + } + + /** + * Returns the sequence of labels in ascending order --- End diff -- Clarify: "Returns the sequence of labels in ascending order. This order matches the order used in metrics which are specified as arrays over labels, e.g., truePositiveRateByLabel."
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org