spark mllib 频繁项 FPGrowth

末蓝、 2022-08-20 14:26 180阅读 0赞

package org.apache.spark.examples.mllib;  
  
  
// $example on$  
import java.util.Arrays;  
import java.util.List;  
  
  
import org.apache.spark.api.java.JavaRDD;  
import org.apache.spark.api.java.JavaSparkContext;  
// $example off$  
import org.apache.spark.api.java.function.Function;  
// $example on$  
import org.apache.spark.mllib.fpm.AssociationRules;  
import org.apache.spark.mllib.fpm.FPGrowth;  
import org.apache.spark.mllib.fpm.FPGrowthModel;  
// $example off$  
  
  
import org.apache.spark.SparkConf;  
  
  
public class JavaSimpleFPGrowth \{  
  
  
  public static void main(String\[\] args) \{  
    SparkConf conf = new SparkConf().setAppName("FP-growth Example");  
    JavaSparkContext sc = new JavaSparkContext(conf);  
  
  
    // $example on$  
    JavaRDD<String> data = sc.textFile("data/mllib/sample\_fpgrowth.txt");  
  
  
    JavaRDD<List<String>> transactions = data.map(  
      new Function<String, List<String>>() \{  
        public List<String> call(String line) \{  
          String\[\] parts = line.split(" ");  
          return Arrays.asList(parts);  
        \}  
      \}  
    );  
  
  
    FPGrowth fpg = new FPGrowth()  
      .setMinSupport(0.2)  
      .setNumPartitions(10);  
    FPGrowthModel<String> model = fpg.run(transactions);  
  
  
    for (FPGrowth.FreqItemset<String> itemset: model.freqItemsets().toJavaRDD().collect()) \{  
      System.out.println("\[" + itemset.javaItems() + "\], " + itemset.freq());  
    \}  
  
  
    double minConfidence = 0.8;  
    for (AssociationRules.Rule<String> rule  
      : model.generateAssociationRules(minConfidence).toJavaRDD().collect()) \{  
      System.out.println(  
        rule.javaAntecedent() + " => " + rule.javaConsequent() + ", " + rule.confidence());  
    \}  
    // $example off$  
  
  
    sc.stop();  
  \}  
\}