Github user felixcheung commented on a diff in the pull request:
https://github.com/apache/spark/pull/17170#discussion_r108079970
--- Diff: R/pkg/R/mllib_fpm.R ---
@@ -0,0 +1,148 @@
+#
+# 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.
+#
+
+# mllib_fpm.R: Provides methods for MLlib frequent pattern mining
algorithms integration
+
+#' S4 class that represents a FPGrowthModel
+#'
+#' @param jobj a Java object reference to the backing Scala FPGrowthModel
+#' @export
+#' @note FPGrowthModel since 2.2.0
+setClass("FPGrowthModel", slots = list(jobj = "jobj"))
+
+#' FP-growth
+#'
+#' A parallel FP-growth algorithm to mine frequent itemsets.
+#' For more details, see
+#'
\href{https://spark.apache.org/docs/latest/mllib-frequent-pattern-mining.html#fp-growth}{
+#' FP-growth}.
+#'
+#' @param data A SparkDataFrame for training.
+#' @param minSupport Minimal support level.
+#' @param minConfidence Minimal confidence level.
+#' @param itemsCol Features column name.
+#' @param numPartitions Number of partitions used for fitting.
+#' @param ... additional argument(s) passed to the method.
+#' @return \code{spark.fpGrowth} returns a fitted FPGrowth model.
+#' @rdname spark.fpGrowth
+#' @name spark.fpGrowth
+#' @aliases spark.fpGrowth,SparkDataFrame-method
+#' @export
+#' @examples
+#' \dontrun{
+#' raw_data <- read.df(
+#' "data/mllib/sample_fpgrowth.txt",
+#' source = "csv",
+#' schema = structType(structField("raw_items", "string")))
+#'
+#' data <- selectExpr(raw_data, "split(raw_items, ' ') as items")
+#' model <- spark.fpGrowth(data)
+#'
+#' # Show frequent itemsets
+#' frequent_itemsets <- spark.freqItemsets(model)
+#' showDF(frequent_itemsets)
+#'
+#' # Show association rules
+#' association_rules <- spark.associationRules(model)
+#' showDF(association_rules)
+#'
+#' # Predict on new data
+#' new_itemsets <- data.frame(items = c("t", "t,s"))
+#' new_data <- selectExpr(createDataFrame(new_itemsets), "split(items,
',') as items")
+#' predict(model, new_data)
+#'
+#' # Save and load model
+#' path <- "/path/to/model"
+#' write.ml(model, path)
+#' read.ml(path)
+#'
+#' # Optional arguments
+#' baskets_data <- selectExpr(createDataFrame(itemsets), "split(items,
',') as baskets")
+#' another_model <- spark.fpGrowth(data, minSupport = 0.1, minConfidence =
0.5,
+#' itemsCol = "baskets", numPartitions =
10)
+#' }
+#' @note spark.fpGrowth since 2.2.0
+setMethod("spark.fpGrowth", signature(data = "SparkDataFrame"),
+ function(data, minSupport = 0.3, minConfidence = 0.8,
+ itemsCol = "items", numPartitions = NULL) {
+ if (!is.numeric(minSupport) || minSupport < 0 || minSupport >
1) {
+ stop("minSupport should be a number [0, 1].")
+ }
+ if (!is.numeric(minConfidence) || minConfidence < 0 ||
minConfidence > 1) {
+ stop("minConfidence should be a number [0, 1].")
+ }
+
+ numPartitions <- if (is.null(numPartitions)) NULL else
as.integer(numPartitions)
+ jobj <- callJStatic("org.apache.spark.ml.r.FPGrowthWrapper",
"fit",
+ data@sdf, as.numeric(minSupport),
as.numeric(minConfidence),
+ itemsCol, numPartitions)
+ new("FPGrowthModel", jobj = jobj)
+ })
+
+# Get frequent itemsets.
+
+#' @param object a fitted FPGrowth model.
+#' @return A DataFrame with frequent itemsets.
+#' @rdname spark.fpGrowth
+#' @aliases freqItemsets,FPGrowthModel-method
+#' @export
+#' @note spark.freqItemsets(FPGrowthModel) since 2.2.0
+setMethod("spark.freqItemsets", signature(object = "FPGrowthModel"),
+ function(object) {
+ dataFrame(callJMethod(object@jobj, "freqItemsets"))
+ })
+
+# Get association rules.
+
+#' @return A DataFrame with association rules.
--- End diff --
let's document the list of column like in Python:
https://github.com/apache/spark/pull/17218/files#diff-b6dbf16870bd2cca9b4140df8aebd681R121
for reference, see
https://github.com/apache/spark/blob/master/R/pkg/R/mllib_clustering.R#L249
---
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]
