給定交易資料集，FP增長的第一步是計算專案頻率並識別頻繁專案。與為同樣目的設計的類似Apriori的演算法不同，FP增長的第二步使用字尾樹（FP-tree）結構來編碼事務，而不會顯式生成候選集，生成的代價通常很高。第二步之後，可以從FP樹中提取頻繁項集。
import org.apache.spark.sql.SparkSession
import org.apache.spark.mllib.fpm.FPGrowth
import org.apache.spark.rdd.RDD
val spark = SparkSession
.builder()
.appName("Spark SQL basic example")
.config("spark.some.config.option", "some-value")
.getOrCreate()
// For implicit conversions like converting RDDs to DataFrames
import spark.implicits._
val data = List(
"1,2,5",
"1,2,3,5",
"1,2").toDF("items")
data: org.apache.spark.sql.DataFrame = [items: string]
// 注意每行，頭部和尾部的[中括號
data.rdd.map { s => s.toString() }.collect().take(3)
res20: Array[String] = Array([1,2,5], [1,2,3,5], [1,2])
val transactions: RDD[Array[String]] = data.rdd.map {
s =>
val str = s.toString().drop(1).dropRight(1)
str.trim().split(",")
}
val fpg = new FPGrowth().setMinSupport(0.5).setNumPartitions(8)
val model = fpg.run(transactions)
/* model.freqItemsets.collect().foreach { itemset =>
println(itemset.items.mkString("[", ",", "]") + ", " + itemset.freq)
}*/
val freqItemSets = model.freqItemsets.map { itemset =>
val items = itemset.items.mkString(",")
val freq = itemset.freq
(items, freq)
}.toDF("items", "freq")
freqItemSets: org.apache.spark.sql.DataFrame = [items: string, freq: bigint]
freqItemSets.show
+-----+----+
|items|freq|
+-----+----+
| 1| 3|
| 2| 3|
| 2,1| 3|
| 5| 2|
| 5,2| 2|
|5,2,1| 2|
| 5,1| 2|
+-----+----+
val minConfidence = 0.6
minConfidence: Double = 0.6
/*model.generateAssociationRules(minConfidence).collect().foreach { rule =>
println(
rule.antecedent.mkString("[", ",", "]")
+ " => " + rule.consequent.mkString("[", ",", "]")
+ ", " + rule.confidence)
}*/
// 根據置信度生成關聯規則
val Rules = model.generateAssociationRules(minConfidence)
Rules: org.apache.spark.rdd.RDD[org.apache.spark.mllib.fpm.AssociationRules.Rule[String]] = MapPartitionsRDD[129] at filter at AssociationRules.scala:80
val df = Rules.map { s =>
val L = s.antecedent.mkString(",")
val R = s.consequent.mkString(",")
val confidence = s.confidence
(L, R, confidence)
}.toDF("left_collect", "right_collect", "confidence")
df: org.apache.spark.sql.DataFrame = [left_collect: string, right_collect: string ... 1 more field]
df.show
+------------+-------------+------------------+
|left_collect|right_collect| confidence|
+------------+-------------+------------------+
| 2| 5|0.6666666666666666|
| 2| 1| 1.0|
| 5,2| 1| 1.0|
| 5| 2| 1.0|
| 5| 1| 1.0|
| 1| 5|0.6666666666666666|
| 1| 2| 1.0|
| 2,1| 5|0.6666666666666666|
| 5,1| 2| 1.0|
+------------+-------------+------------------+