Github user srowen commented on a diff in the pull request: https://github.com/apache/spark/pull/22236#discussion_r212833449 --- Diff: mllib/src/main/scala/org/apache/spark/ml/fpm/FPGrowth.scala --- @@ -338,7 +355,16 @@ object FPGrowthModel extends MLReadable[FPGrowthModel] { val metadata = DefaultParamsReader.loadMetadata(path, sc, className) val dataPath = new Path(path, "data").toString val frequentItems = sparkSession.read.parquet(dataPath) - val model = new FPGrowthModel(metadata.uid, frequentItems) + val itemSupportPath = new Path(path, "itemSupport") + val fs = FileSystem.get(sc.hadoopConfiguration) + val itemSupport = if (fs.exists(itemSupportPath)) { + sparkSession.read.parquet(itemSupportPath.toString).rdd.collect().map { --- End diff -- How about `collectAsMap` here?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org