[
https://issues.apache.org/jira/browse/SPARK-19827?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16719069#comment-16719069
]
ASF GitHub Bot commented on SPARK-19827:
----------------------------------------
srowen closed pull request #23292: [SPARK-19827][R][FOLLOWUP] spark.ml R API
for PIC
URL: https://github.com/apache/spark/pull/23292
This is a PR merged from a forked repository.
As GitHub hides the original diff on merge, it is displayed below for
the sake of provenance:
As this is a foreign pull request (from a fork), the diff is supplied
below (as it won't show otherwise due to GitHub magic):
diff --git a/R/pkg/R/mllib_clustering.R b/R/pkg/R/mllib_clustering.R
index 7d9dcebfe70d3..9b32b71d34fef 100644
--- a/R/pkg/R/mllib_clustering.R
+++ b/R/pkg/R/mllib_clustering.R
@@ -621,11 +621,10 @@ setMethod("write.ml", signature(object = "LDAModel", path
= "character"),
#'
#' A scalable graph clustering algorithm. Users can call
\code{spark.assignClusters} to
#' return a cluster assignment for each input vertex.
-#'
-# Run the PIC algorithm and returns a cluster assignment for each input
vertex.
+#' Run the PIC algorithm and returns a cluster assignment for each input
vertex.
#' @param data a SparkDataFrame.
#' @param k the number of clusters to create.
-#' @param initMode the initialization algorithm.
+#' @param initMode the initialization algorithm; "random" or "degree"
#' @param maxIter the maximum number of iterations.
#' @param sourceCol the name of the input column for source vertex IDs.
#' @param destinationCol the name of the input column for destination vertex
IDs
@@ -633,18 +632,16 @@ setMethod("write.ml", signature(object = "LDAModel", path
= "character"),
#' we treat all instance weights as 1.0.
#' @param ... additional argument(s) passed to the method.
#' @return A dataset that contains columns of vertex id and the corresponding
cluster for the id.
-#' The schema of it will be:
-#' \code{id: Long}
-#' \code{cluster: Int}
+#' The schema of it will be: \code{id: integer}, \code{cluster:
integer}
#' @rdname spark.powerIterationClustering
-#' @aliases
assignClusters,PowerIterationClustering-method,SparkDataFrame-method
+#' @aliases spark.assignClusters,SparkDataFrame-method
#' @examples
#' \dontrun{
#' df <- createDataFrame(list(list(0L, 1L, 1.0), list(0L, 2L, 1.0),
#' list(1L, 2L, 1.0), list(3L, 4L, 1.0),
#' list(4L, 0L, 0.1)),
#' schema = c("src", "dst", "weight"))
-#' clusters <- spark.assignClusters(df, initMode="degree", weightCol="weight")
+#' clusters <- spark.assignClusters(df, initMode = "degree", weightCol =
"weight")
#' showDF(clusters)
#' }
#' @note spark.assignClusters(SparkDataFrame) since 3.0.0
@@ -652,7 +649,7 @@ setMethod("spark.assignClusters",
signature(data = "SparkDataFrame"),
function(data, k = 2L, initMode = c("random", "degree"), maxIter =
20L,
sourceCol = "src", destinationCol = "dst", weightCol = NULL) {
- if (!is.numeric(k) || k < 1) {
+ if (!is.integer(k) || k < 1) {
stop("k should be a number with value >= 1.")
}
if (!is.integer(maxIter) || maxIter <= 0) {
diff --git a/R/pkg/R/mllib_fpm.R b/R/pkg/R/mllib_fpm.R
index c248e9ec9be94..0cc7a16c302dc 100644
--- a/R/pkg/R/mllib_fpm.R
+++ b/R/pkg/R/mllib_fpm.R
@@ -183,8 +183,8 @@ setMethod("write.ml", signature(object = "FPGrowthModel",
path = "character"),
#' @return A complete set of frequent sequential patterns in the input
sequences of itemsets.
#' The returned \code{SparkDataFrame} contains columns of sequence and
corresponding
#' frequency. The schema of it will be:
-#' \code{sequence: ArrayType(ArrayType(T))} (T is the item type)
-#' \code{freq: Long}
+#' \code{sequence: ArrayType(ArrayType(T))}, \code{freq: integer}
+#' where T is the item type
#' @rdname spark.prefixSpan
#' @aliases findFrequentSequentialPatterns,PrefixSpan,SparkDataFrame-method
#' @examples
diff --git a/examples/src/main/r/ml/powerIterationClustering.R
b/examples/src/main/r/ml/powerIterationClustering.R
index ba43037106d14..3530d88e50509 100644
--- a/examples/src/main/r/ml/powerIterationClustering.R
+++ b/examples/src/main/r/ml/powerIterationClustering.R
@@ -30,7 +30,8 @@ df <- createDataFrame(list(list(0L, 1L, 1.0), list(0L, 2L,
1.0),
list(4L, 0L, 0.1)),
schema = c("src", "dst", "weight"))
# assign clusters
-clusters <- spark.assignClusters(df, k=2L, maxIter=20L, initMode="degree",
weightCol="weight")
+clusters <- spark.assignClusters(df, k = 2L, maxIter = 20L,
+ initMode = "degree", weightCol = "weight")
showDF(arrange(clusters, clusters$id))
# $example off$
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
> spark.ml R API for PIC
> ----------------------
>
> Key: SPARK-19827
> URL: https://issues.apache.org/jira/browse/SPARK-19827
> Project: Spark
> Issue Type: Sub-task
> Components: ML, SparkR
> Affects Versions: 2.1.0
> Reporter: Felix Cheung
> Assignee: Huaxin Gao
> Priority: Major
> Fix For: 3.0.0
>
>
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
