Repository: spark Updated Branches: refs/heads/master eaac60a1e -> 70bcc9d5a
[SPARK-22993][ML] Clarify HasCheckpointInterval param doc ## What changes were proposed in this pull request? Add a note to the `HasCheckpointInterval` parameter doc that clarifies that this setting is ignored when no checkpoint directory has been set on the spark context. ## How was this patch tested? No tests necessary, just a doc update. Author: sethah <[email protected]> Closes #20188 from sethah/als_checkpoint_doc. Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/70bcc9d5 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/70bcc9d5 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/70bcc9d5 Branch: refs/heads/master Commit: 70bcc9d5ae33d6669bb5c97db29087ccead770fb Parents: eaac60a Author: sethah <[email protected]> Authored: Tue Jan 9 23:32:47 2018 -0800 Committer: Felix Cheung <[email protected]> Committed: Tue Jan 9 23:32:47 2018 -0800 ---------------------------------------------------------------------- R/pkg/R/mllib_recommendation.R | 2 ++ R/pkg/R/mllib_tree.R | 6 ++++++ .../org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala | 4 +++- .../scala/org/apache/spark/ml/param/shared/sharedParams.scala | 4 ++-- python/pyspark/ml/param/_shared_params_code_gen.py | 5 +++-- python/pyspark/ml/param/shared.py | 4 ++-- 6 files changed, 18 insertions(+), 7 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/70bcc9d5/R/pkg/R/mllib_recommendation.R ---------------------------------------------------------------------- diff --git a/R/pkg/R/mllib_recommendation.R b/R/pkg/R/mllib_recommendation.R index fa79424..5441c4a 100644 --- a/R/pkg/R/mllib_recommendation.R +++ b/R/pkg/R/mllib_recommendation.R @@ -48,6 +48,8 @@ setClass("ALSModel", representation(jobj = "jobj")) #' @param numUserBlocks number of user blocks used to parallelize computation (> 0). #' @param numItemBlocks number of item blocks used to parallelize computation (> 0). #' @param checkpointInterval number of checkpoint intervals (>= 1) or disable checkpoint (-1). +#' Note: this setting will be ignored if the checkpoint directory is not +#' set. #' @param ... additional argument(s) passed to the method. #' @return \code{spark.als} returns a fitted ALS model. #' @rdname spark.als http://git-wip-us.apache.org/repos/asf/spark/blob/70bcc9d5/R/pkg/R/mllib_tree.R ---------------------------------------------------------------------- diff --git a/R/pkg/R/mllib_tree.R b/R/pkg/R/mllib_tree.R index 89a58bf..4e5ddf2 100644 --- a/R/pkg/R/mllib_tree.R +++ b/R/pkg/R/mllib_tree.R @@ -161,6 +161,8 @@ print.summary.decisionTree <- function(x) { #' >= 1. #' @param minInfoGain Minimum information gain for a split to be considered at a tree node. #' @param checkpointInterval Param for set checkpoint interval (>= 1) or disable checkpoint (-1). +#' Note: this setting will be ignored if the checkpoint directory is not +#' set. #' @param maxMemoryInMB Maximum memory in MB allocated to histogram aggregation. #' @param cacheNodeIds If FALSE, the algorithm will pass trees to executors to match instances with #' nodes. If TRUE, the algorithm will cache node IDs for each instance. Caching @@ -382,6 +384,8 @@ setMethod("write.ml", signature(object = "GBTClassificationModel", path = "chara #' @param minInstancesPerNode Minimum number of instances each child must have after split. #' @param minInfoGain Minimum information gain for a split to be considered at a tree node. #' @param checkpointInterval Param for set checkpoint interval (>= 1) or disable checkpoint (-1). +#' Note: this setting will be ignored if the checkpoint directory is not +#' set. #' @param maxMemoryInMB Maximum memory in MB allocated to histogram aggregation. #' @param cacheNodeIds If FALSE, the algorithm will pass trees to executors to match instances with #' nodes. If TRUE, the algorithm will cache node IDs for each instance. Caching @@ -595,6 +599,8 @@ setMethod("write.ml", signature(object = "RandomForestClassificationModel", path #' @param minInstancesPerNode Minimum number of instances each child must have after split. #' @param minInfoGain Minimum information gain for a split to be considered at a tree node. #' @param checkpointInterval Param for set checkpoint interval (>= 1) or disable checkpoint (-1). +#' Note: this setting will be ignored if the checkpoint directory is not +#' set. #' @param maxMemoryInMB Maximum memory in MB allocated to histogram aggregation. #' @param cacheNodeIds If FALSE, the algorithm will pass trees to executors to match instances with #' nodes. If TRUE, the algorithm will cache node IDs for each instance. Caching http://git-wip-us.apache.org/repos/asf/spark/blob/70bcc9d5/mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala b/mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala index a5d57a1..6ad44af 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala @@ -63,7 +63,9 @@ private[shared] object SharedParamsCodeGen { ParamDesc[Array[String]]("outputCols", "output column names"), ParamDesc[Int]("checkpointInterval", "set checkpoint interval (>= 1) or " + "disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed " + - "every 10 iterations", isValid = "(interval: Int) => interval == -1 || interval >= 1"), + "every 10 iterations. Note: this setting will be ignored if the checkpoint directory " + + "is not set in the SparkContext", + isValid = "(interval: Int) => interval == -1 || interval >= 1"), ParamDesc[Boolean]("fitIntercept", "whether to fit an intercept term", Some("true")), ParamDesc[String]("handleInvalid", "how to handle invalid entries. Options are skip (which " + "will filter out rows with bad values), or error (which will throw an error). More " + http://git-wip-us.apache.org/repos/asf/spark/blob/70bcc9d5/mllib/src/main/scala/org/apache/spark/ml/param/shared/sharedParams.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/ml/param/shared/sharedParams.scala b/mllib/src/main/scala/org/apache/spark/ml/param/shared/sharedParams.scala index 13425da..be8b2f2 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/param/shared/sharedParams.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/param/shared/sharedParams.scala @@ -282,10 +282,10 @@ trait HasOutputCols extends Params { trait HasCheckpointInterval extends Params { /** - * Param for set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations. + * Param for set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations. Note: this setting will be ignored if the checkpoint directory is not set in the SparkContext. * @group param */ - final val checkpointInterval: IntParam = new IntParam(this, "checkpointInterval", "set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations", (interval: Int) => interval == -1 || interval >= 1) + final val checkpointInterval: IntParam = new IntParam(this, "checkpointInterval", "set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations. Note: this setting will be ignored if the checkpoint directory is not set in the SparkContext", (interval: Int) => interval == -1 || interval >= 1) /** @group getParam */ final def getCheckpointInterval: Int = $(checkpointInterval) http://git-wip-us.apache.org/repos/asf/spark/blob/70bcc9d5/python/pyspark/ml/param/_shared_params_code_gen.py ---------------------------------------------------------------------- diff --git a/python/pyspark/ml/param/_shared_params_code_gen.py b/python/pyspark/ml/param/_shared_params_code_gen.py index d55d209..1d0f60a 100644 --- a/python/pyspark/ml/param/_shared_params_code_gen.py +++ b/python/pyspark/ml/param/_shared_params_code_gen.py @@ -121,8 +121,9 @@ if __name__ == "__main__": ("outputCol", "output column name.", "self.uid + '__output'", "TypeConverters.toString"), ("numFeatures", "number of features.", None, "TypeConverters.toInt"), ("checkpointInterval", "set checkpoint interval (>= 1) or disable checkpoint (-1). " + - "E.g. 10 means that the cache will get checkpointed every 10 iterations.", None, - "TypeConverters.toInt"), + "E.g. 10 means that the cache will get checkpointed every 10 iterations. Note: " + + "this setting will be ignored if the checkpoint directory is not set in the SparkContext.", + None, "TypeConverters.toInt"), ("seed", "random seed.", "hash(type(self).__name__)", "TypeConverters.toInt"), ("tol", "the convergence tolerance for iterative algorithms (>= 0).", None, "TypeConverters.toFloat"), http://git-wip-us.apache.org/repos/asf/spark/blob/70bcc9d5/python/pyspark/ml/param/shared.py ---------------------------------------------------------------------- diff --git a/python/pyspark/ml/param/shared.py b/python/pyspark/ml/param/shared.py index e5c5ddf..813f7a5 100644 --- a/python/pyspark/ml/param/shared.py +++ b/python/pyspark/ml/param/shared.py @@ -281,10 +281,10 @@ class HasNumFeatures(Params): class HasCheckpointInterval(Params): """ - Mixin for param checkpointInterval: set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations. + Mixin for param checkpointInterval: set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations. Note: this setting will be ignored if the checkpoint directory is not set in the SparkContext. """ - checkpointInterval = Param(Params._dummy(), "checkpointInterval", "set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations.", typeConverter=TypeConverters.toInt) + checkpointInterval = Param(Params._dummy(), "checkpointInterval", "set checkpoint interval (>= 1) or disable checkpoint (-1). E.g. 10 means that the cache will get checkpointed every 10 iterations. Note: this setting will be ignored if the checkpoint directory is not set in the SparkContext.", typeConverter=TypeConverters.toInt) def __init__(self): super(HasCheckpointInterval, self).__init__() --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
