Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/8611#discussion_r39811229
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/regression/AFTSurvivalRegression.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.regression
+
+import scala.collection.mutable
+
+import breeze.linalg.{DenseVector => BDV}
+import breeze.optimize.{CachedDiffFunction, DiffFunction, LBFGS =>
BreezeLBFGS}
+
+import org.apache.spark.{SparkException, Logging}
+import org.apache.spark.annotation.{Since, Experimental}
+import org.apache.spark.ml.{Model, Estimator}
+import org.apache.spark.ml.param._
+import org.apache.spark.ml.param.shared._
+import org.apache.spark.ml.util.{SchemaUtils, Identifiable}
+import org.apache.spark.mllib.linalg.{Vector, Vectors, VectorUDT}
+import org.apache.spark.mllib.linalg.BLAS
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.{Row, DataFrame}
+import org.apache.spark.sql.functions._
+import org.apache.spark.sql.types.{DoubleType, StructType}
+import org.apache.spark.storage.StorageLevel
+
+/**
+ * Params for accelerated failure time (AFT) regression.
+ */
+private[regression] trait AFTSurvivalRegressionParams extends Params
+ with HasFeaturesCol with HasLabelCol with HasPredictionCol with
HasMaxIter
+ with HasTol with HasFitIntercept {
+
+ /**
+ * Param for censored column name.
+ * The value of this column could be 0 or 1.
+ * If the value is 1, it means the event has occurred i.e. uncensored;
otherwise it censored.
--- End diff --
This is confusing. The column name is called `censored` but value `1` means
`uncensored`. I searched for some survival analysis datasets, where "censor" is
commonly used as the column name. See
https://www.umass.edu/statdata/statdata/stat-survival.html. However, in those
datasets, `1` actually means occurred, i.e., uncensored. So my recommendation
would be renaming the param name back to `censorCol` and keep the current doc.
That is `1` for uncensored and `0` for censored. And note that this is to be
consistent with existing datasets.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
