Java 为什么ApacheMahout频繁模式minnig算法只返回1个项目集？

我目前正在测试ApacheMahout并行。在实际项目中使用它之前，我从一个简单的代码开始，只是为了确保它能像我期望的那样工作

我没有找到包含代码、数据和输出的完整示例

我目前有一个编译和执行版本（参见下面的java/scala代码），但是返回的频繁模式只包含一个元组（参见下面的示例输出）

这是故意的行为吗？ 我做错了什么

谢谢你的帮助

scala代码：

  import org.apache.mahout.fpm.pfpgrowth.fpgrowth.FPGrowth
  import java.util.HashSet
  import org.apache.mahout.common.iterator.StringRecordIterator
  import org.apache.mahout.common.iterator.FileLineIterable
  import org.apache.mahout.fpm.pfpgrowth.convertors._
  import org.apache.mahout.fpm.pfpgrowth.convertors.integer._
  import org.apache.mahout.fpm.pfpgrowth.convertors.string._
  import org.apache.hadoop.io.SequenceFile.Writer
  import org.apache.mahout.fpm.pfpgrowth.convertors.StatusUpdater
  import org.apache.hadoop.mapred.OutputCollector
  import scala.collection.JavaConversions._
  import java.util.{ List => JList }
  import org.apache.mahout.common.{ Pair => JPair }
  import java.lang.{ Long => JLong }
  import org.apache.hadoop.io.{ Text => JText }

  val minSupport = 5L
  val k: Int = 50
  val fps: FPGrowth[String] = new FPGrowth[String]()

  val milk = "milk"
  val bread = "bread"
  val butter = "butter"
  val bier = "bier"

  val transactionStream: Iterator[JPair[JList[String], JLong]] = Iterator(
    new JPair(List(milk, bread), 10L),
    new JPair(List(butter), 10L),
    new JPair(List(bier), 10L),
    new JPair(List(milk, bread, butter), 5L),
    new JPair(List(milk, bread, bier), 5L),
    new JPair(List(bread), 10L)
  )

  val frequencies: Collection[JPair[String, JLong]] = fps.generateFList(
    transactionStream, minSupport.toInt)

  println("freqList :" + frequencies)

  var returnableFeatures: Collection[String] = List(
    milk, bread, butter, bier)

  var output: OutputCollector[String, JList[JPair[JList[String], JLong]]] = (
    new OutputCollector[String, JList[JPair[JList[String], JLong]]] {
      def collect(x1: String,
                  x2: JList[JPair[JList[String], JLong]]) = {
        println(x1 + ":" +
          x2.map(pair => "[" + pair.getFirst.mkString(",") + "] : " +
            pair.getSecond).mkString("; "))
      }
    }
  )

  val updater: StatusUpdater = new StatusUpdater {
    def update(status: String) = println("updater : " + status)
  }

  fps.generateTopKFrequentPatterns(
    transactionStream,
    frequencies,
    minSupport,
    k,
    null, //returnableFeatures
    output,
    updater)

java代码：

import org.apache.mahout.fpm.pfpgrowth.fpgrowth.*;

import java.io.IOException;
import java.util.*;

import org.apache.mahout.common.iterator.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.integer.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.string.*;

import org.apache.hadoop.mapred.OutputCollector;
import org.apache.mahout.common.*;

import org.apache.hadoop.io.Text;

class FPGrowthDemo {

  public static void main(String[] args) {
    long minSupport = 1L;
    int k = 50;
    FPGrowth<String> fps = new FPGrowth<String>();

    String milk = "milk";
    String bread = "bread";
    String butter = "butter";
    String bier = "bier";

    LinkedList<Pair<List<String>, Long>> data = 
        new LinkedList<Pair<List<String>, Long>>();

    data.add(new Pair(Arrays.asList(milk, bread), 1L));
    data.add(new Pair(Arrays.asList(butter), 1L));
    data.add(new Pair(Arrays.asList(bier), 1L));
    data.add(new Pair(Arrays.asList(milk, bread, butter), 1L));
    data.add(new Pair(Arrays.asList(milk, bread, bier), 1L));
    data.add(new Pair(Arrays.asList(milk, bread), 1L));

    Iterator<Pair<List<String>, Long>> transactions = data.iterator();

    Collection<Pair<String, Long>> frequencies = fps.generateFList(
        transactions, (int) minSupport);

    System.out.println("freqList :" + frequencies);

    Collection<String> returnableFeatures = 
        Arrays.asList(milk, bread, butter, bier);

    OutputCollector<String, List<Pair<List<String>, Long>>> output = 
      new OutputCollector<String, List<Pair<List<String>, Long>>>() {
        @Override
        public void collect(String x1, 
                            List<Pair<List<String>, Long>> listPair)
            throws IOException {
          StringBuffer sb = new StringBuffer();
          sb.append(x1 + ":");
          for (Pair<List<String>, Long> pair : listPair) {
            sb.append("[");
            String sep = "";
            for (String item : pair.getFirst()) {
              sb.append(item + sep);
              sep = ", ";
            }
            sb.append("]:" + pair.getSecond());
          }
          System.out.println("  " + sb.toString());
        }
    };


    StatusUpdater updater = new StatusUpdater() { 
      public void update(String status){
        System.out.println("updater :" + status); 
      }
    };

    try {
    fps.generateTopKFrequentPatterns(
        transactions,
        frequencies,
        minSupport, 
        k,
        null, //returnableFeatures
        output, 
        updater);
    }catch (Exception e){
      e.printStackTrace();
    }

  }
}

import org.apache.mahout.fpm.pfpgrowth.fpgrowth.*;

import java.io.IOException;
import java.util.*;

import org.apache.mahout.common.iterator.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.integer.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.string.*;

import org.apache.hadoop.mapred.OutputCollector;
import org.apache.mahout.common.*;

import org.apache.hadoop.io.Text;

class FPGrowthDemo {

  public static void main(String[] args) {
    long minSupport = 1L;
    int k = 50;
    FPGrowth<String> fps = new FPGrowth<String>();

    String milk = "milk";
    String bread = "bread";
    String butter = "butter";
    String bier = "bier";

    LinkedList<Pair<List<String>, Long>> data = 
        new LinkedList<Pair<List<String>, Long>>();

    data.add(new Pair(Arrays.asList(milk, bread), 1L));
    data.add(new Pair(Arrays.asList(butter), 1L));
    data.add(new Pair(Arrays.asList(bier), 1L));
    data.add(new Pair(Arrays.asList(milk, bread, butter), 1L));
    data.add(new Pair(Arrays.asList(milk, bread, bier), 1L));
    data.add(new Pair(Arrays.asList(milk, bread), 1L));

    // This lines is removed...
    // Iterator<Pair<List<String>, Long>> transactions = data.iterator();

    Collection<Pair<String, Long>> frequencies = fps.generateFList(
        data.iterator(), // use an iterator here...
        (int) minSupport);

    System.out.println("freqList :" + frequencies);

    OutputCollector<String, List<Pair<List<String>, Long>>> output = 
        new OutputCollector<String, List<Pair<List<String>, Long>>>() {

      @Override
      public void collect(String x1, 
                          List<Pair<List<String>, Long>> listPair)
          throws IOException {
        StringBuffer sb = new StringBuffer();
        sb.append(x1 + ":");
        for (Pair<List<String>, Long> pair : listPair) {

          sb.append("[");
          String sep = "";
          for (String item : pair.getFirst()) {
            sb.append(item + sep);
            sep = ", ";
          }
          sb.append("]:" + pair.getSecond());
        }
        System.out.println("  " + sb.toString());
      }
    };

    StatusUpdater updater = new StatusUpdater() {
      public void update(String status) {
        System.out.println("updater :" + status);
      }
    };

    try {
      fps.generateTopKFrequentPatterns(
        // changed here (previously : transactions)
        data.iterator(), // use a "fresh" iterator
        frequencies, 
        minSupport, 
        k, 
        null, 
        output, 
        updater);
    } catch (Exception e) {
      e.printStackTrace();
    }
  }
}

---

代码有缺陷：首先调用事务的迭代器来计算频率，然后再由fp-growth算法调用。问题是，第二个调用将不返回任何值，因为迭代器已到达其末尾

以下是正确的java代码供参考：

import org.apache.mahout.fpm.pfpgrowth.fpgrowth.*;

import java.io.IOException;
import java.util.*;

import org.apache.mahout.common.iterator.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.integer.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.string.*;

import org.apache.hadoop.mapred.OutputCollector;
import org.apache.mahout.common.*;

import org.apache.hadoop.io.Text;

class FPGrowthDemo {

  public static void main(String[] args) {
    long minSupport = 1L;
    int k = 50;
    FPGrowth<String> fps = new FPGrowth<String>();

    String milk = "milk";
    String bread = "bread";
    String butter = "butter";
    String bier = "bier";

    LinkedList<Pair<List<String>, Long>> data = 
        new LinkedList<Pair<List<String>, Long>>();

    data.add(new Pair(Arrays.asList(milk, bread), 1L));
    data.add(new Pair(Arrays.asList(butter), 1L));
    data.add(new Pair(Arrays.asList(bier), 1L));
    data.add(new Pair(Arrays.asList(milk, bread, butter), 1L));
    data.add(new Pair(Arrays.asList(milk, bread, bier), 1L));
    data.add(new Pair(Arrays.asList(milk, bread), 1L));

    Iterator<Pair<List<String>, Long>> transactions = data.iterator();

    Collection<Pair<String, Long>> frequencies = fps.generateFList(
        transactions, (int) minSupport);

    System.out.println("freqList :" + frequencies);

    Collection<String> returnableFeatures = 
        Arrays.asList(milk, bread, butter, bier);

    OutputCollector<String, List<Pair<List<String>, Long>>> output = 
      new OutputCollector<String, List<Pair<List<String>, Long>>>() {
        @Override
        public void collect(String x1, 
                            List<Pair<List<String>, Long>> listPair)
            throws IOException {
          StringBuffer sb = new StringBuffer();
          sb.append(x1 + ":");
          for (Pair<List<String>, Long> pair : listPair) {
            sb.append("[");
            String sep = "";
            for (String item : pair.getFirst()) {
              sb.append(item + sep);
              sep = ", ";
            }
            sb.append("]:" + pair.getSecond());
          }
          System.out.println("  " + sb.toString());
        }
    };


    StatusUpdater updater = new StatusUpdater() { 
      public void update(String status){
        System.out.println("updater :" + status); 
      }
    };

    try {
    fps.generateTopKFrequentPatterns(
        transactions,
        frequencies,
        minSupport, 
        k,
        null, //returnableFeatures
        output, 
        updater);
    }catch (Exception e){
      e.printStackTrace();
    }

  }
}

import org.apache.mahout.fpm.pfpgrowth.fpgrowth.*;

import java.io.IOException;
import java.util.*;

import org.apache.mahout.common.iterator.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.integer.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.string.*;

import org.apache.hadoop.mapred.OutputCollector;
import org.apache.mahout.common.*;

import org.apache.hadoop.io.Text;

class FPGrowthDemo {

  public static void main(String[] args) {
    long minSupport = 1L;
    int k = 50;
    FPGrowth<String> fps = new FPGrowth<String>();

    String milk = "milk";
    String bread = "bread";
    String butter = "butter";
    String bier = "bier";

    LinkedList<Pair<List<String>, Long>> data = 
        new LinkedList<Pair<List<String>, Long>>();

    data.add(new Pair(Arrays.asList(milk, bread), 1L));
    data.add(new Pair(Arrays.asList(butter), 1L));
    data.add(new Pair(Arrays.asList(bier), 1L));
    data.add(new Pair(Arrays.asList(milk, bread, butter), 1L));
    data.add(new Pair(Arrays.asList(milk, bread, bier), 1L));
    data.add(new Pair(Arrays.asList(milk, bread), 1L));

    // This lines is removed...
    // Iterator<Pair<List<String>, Long>> transactions = data.iterator();

    Collection<Pair<String, Long>> frequencies = fps.generateFList(
        data.iterator(), // use an iterator here...
        (int) minSupport);

    System.out.println("freqList :" + frequencies);

    OutputCollector<String, List<Pair<List<String>, Long>>> output = 
        new OutputCollector<String, List<Pair<List<String>, Long>>>() {

      @Override
      public void collect(String x1, 
                          List<Pair<List<String>, Long>> listPair)
          throws IOException {
        StringBuffer sb = new StringBuffer();
        sb.append(x1 + ":");
        for (Pair<List<String>, Long> pair : listPair) {

          sb.append("[");
          String sep = "";
          for (String item : pair.getFirst()) {
            sb.append(item + sep);
            sep = ", ";
          }
          sb.append("]:" + pair.getSecond());
        }
        System.out.println("  " + sb.toString());
      }
    };

    StatusUpdater updater = new StatusUpdater() {
      public void update(String status) {
        System.out.println("updater :" + status);
      }
    };

    try {
      fps.generateTopKFrequentPatterns(
        // changed here (previously : transactions)
        data.iterator(), // use a "fresh" iterator
        frequencies, 
        minSupport, 
        k, 
        null, 
        output, 
        updater);
    } catch (Exception e) {
      e.printStackTrace();
    }
  }
}

import org.apache.mahout.fpm.pfpgrowth.fpgrowth.*；
导入java.io.IOException；
导入java.util.*；
导入org.apache.mahout.common.iterator.*；
导入org.apache.mahout.fpm.pfpgrowth.convertors.*；
导入org.apache.mahout.fpm.pfpgrowth.convertors.integer.*；
导入org.apache.mahout.fpm.pfpgrowth.convertors.string.*；
导入org.apache.hadoop.mapred.OutputCollector；
导入org.apache.mahout.common.*；
导入org.apache.hadoop.io.Text；
类FPGrowthDemo{
公共静态void main（字符串[]args）{
长分钟支持=1L；
int k=50；
FPGrowth fps=新的FPGrowth（）；
String milk=“milk”；
stringbread=“面包”；
String butter=“butter”；
字符串bier=“bier”；
LinkedList数据=
新建LinkedList（）；
添加（新的一对（数组.asList（牛奶，面包），1L））；
添加（新的对（Arrays.asList（butter），1L））；
添加（新对（Arrays.asList（bier），1L））；
添加（新的一对（数组.asList（牛奶，面包，黄油），1L））；
添加（新的一对（数组.asList（牛奶，面包，啤酒），1L））；
添加（新的一对（数组.asList（牛奶，面包），1L））；
//此行已删除。。。
//迭代器事务=data.Iterator（）；
采集频率=fps.generateFList(
data.iterator（），//在此处使用迭代器。。。
（int）minSupport）；
System.out.println（“频率列表：+频率）；
OutputCollector输出=
新的OutputCollector（）{
@凌驾
公共void collect（字符串x1，
列表（列表对）
抛出IOException{
StringBuffer sb=新的StringBuffer（）；
sb.附加（x1+“：”）；
for（对：列表对）{
某人加上（“[”）；
字符串sep=“”；
for（字符串项：pair.getFirst（））{
某人追加（项目+sep）；
sep=“，”；
}
sb.append（“]：”+pair.getSecond（））；
}
System.out.println（“+sb.toString（））；
}
};
StatusUpdater updater=新的StatusUpdater（）{
公共无效更新（字符串状态）{
System.out.println（“更新程序：+状态”）；
}
};
试一试{
fps.generateTopKFrequentPatterns(
//此处更改（以前为：事务）
data.iterator（），//使用“fresh”迭代器
频率，
minSupport，
K
无效的
产出，
更新程序）；
}捕获（例外e）{
e、 printStackTrace（）；
}
}
}

代码有缺陷：首先调用事务的迭代器来计算频率，然后由fp-growth算法再次调用。问题是，第二个调用将不返回任何值，因为迭代器已到达其末尾

以下是正确的java代码供参考：

import org.apache.mahout.fpm.pfpgrowth.fpgrowth.*;

import java.io.IOException;
import java.util.*;

import org.apache.mahout.common.iterator.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.integer.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.string.*;

import org.apache.hadoop.mapred.OutputCollector;
import org.apache.mahout.common.*;

import org.apache.hadoop.io.Text;

class FPGrowthDemo {

  public static void main(String[] args) {
    long minSupport = 1L;
    int k = 50;
    FPGrowth<String> fps = new FPGrowth<String>();

    String milk = "milk";
    String bread = "bread";
    String butter = "butter";
    String bier = "bier";

    LinkedList<Pair<List<String>, Long>> data = 
        new LinkedList<Pair<List<String>, Long>>();

    data.add(new Pair(Arrays.asList(milk, bread), 1L));
    data.add(new Pair(Arrays.asList(butter), 1L));
    data.add(new Pair(Arrays.asList(bier), 1L));
    data.add(new Pair(Arrays.asList(milk, bread, butter), 1L));
    data.add(new Pair(Arrays.asList(milk, bread, bier), 1L));
    data.add(new Pair(Arrays.asList(milk, bread), 1L));

    Iterator<Pair<List<String>, Long>> transactions = data.iterator();

    Collection<Pair<String, Long>> frequencies = fps.generateFList(
        transactions, (int) minSupport);

    System.out.println("freqList :" + frequencies);

    Collection<String> returnableFeatures = 
        Arrays.asList(milk, bread, butter, bier);

    OutputCollector<String, List<Pair<List<String>, Long>>> output = 
      new OutputCollector<String, List<Pair<List<String>, Long>>>() {
        @Override
        public void collect(String x1, 
                            List<Pair<List<String>, Long>> listPair)
            throws IOException {
          StringBuffer sb = new StringBuffer();
          sb.append(x1 + ":");
          for (Pair<List<String>, Long> pair : listPair) {
            sb.append("[");
            String sep = "";
            for (String item : pair.getFirst()) {
              sb.append(item + sep);
              sep = ", ";
            }
            sb.append("]:" + pair.getSecond());
          }
          System.out.println("  " + sb.toString());
        }
    };


    StatusUpdater updater = new StatusUpdater() { 
      public void update(String status){
        System.out.println("updater :" + status); 
      }
    };

    try {
    fps.generateTopKFrequentPatterns(
        transactions,
        frequencies,
        minSupport, 
        k,
        null, //returnableFeatures
        output, 
        updater);
    }catch (Exception e){
      e.printStackTrace();
    }

  }
}

import org.apache.mahout.fpm.pfpgrowth.fpgrowth.*;

import java.io.IOException;
import java.util.*;

import org.apache.mahout.common.iterator.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.integer.*;
import org.apache.mahout.fpm.pfpgrowth.convertors.string.*;

import org.apache.hadoop.mapred.OutputCollector;
import org.apache.mahout.common.*;

import org.apache.hadoop.io.Text;

class FPGrowthDemo {

  public static void main(String[] args) {
    long minSupport = 1L;
    int k = 50;
    FPGrowth<String> fps = new FPGrowth<String>();

    String milk = "milk";
    String bread = "bread";
    String butter = "butter";
    String bier = "bier";

    LinkedList<Pair<List<String>, Long>> data = 
        new LinkedList<Pair<List<String>, Long>>();

    data.add(new Pair(Arrays.asList(milk, bread), 1L));
    data.add(new Pair(Arrays.asList(butter), 1L));
    data.add(new Pair(Arrays.asList(bier), 1L));
    data.add(new Pair(Arrays.asList(milk, bread, butter), 1L));
    data.add(new Pair(Arrays.asList(milk, bread, bier), 1L));
    data.add(new Pair(Arrays.asList(milk, bread), 1L));

    // This lines is removed...
    // Iterator<Pair<List<String>, Long>> transactions = data.iterator();

    Collection<Pair<String, Long>> frequencies = fps.generateFList(
        data.iterator(), // use an iterator here...
        (int) minSupport);

    System.out.println("freqList :" + frequencies);

    OutputCollector<String, List<Pair<List<String>, Long>>> output = 
        new OutputCollector<String, List<Pair<List<String>, Long>>>() {

      @Override
      public void collect(String x1, 
                          List<Pair<List<String>, Long>> listPair)
          throws IOException {
        StringBuffer sb = new StringBuffer();
        sb.append(x1 + ":");
        for (Pair<List<String>, Long> pair : listPair) {

          sb.append("[");
          String sep = "";
          for (String item : pair.getFirst()) {
            sb.append(item + sep);
            sep = ", ";
          }
          sb.append("]:" + pair.getSecond());
        }
        System.out.println("  " + sb.toString());
      }
    };

    StatusUpdater updater = new StatusUpdater() {
      public void update(String status) {
        System.out.println("updater :" + status);
      }
    };

    try {
      fps.generateTopKFrequentPatterns(
        // changed here (previously : transactions)
        data.iterator(), // use a "fresh" iterator
        frequencies, 
        minSupport, 
        k, 
        null, 
        output, 
        updater);
    } catch (Exception e) {
      e.printStackTrace();
    }
  }
}

import org.apache.mahout.fpm.pfpgrowth.fpgrowth.*；
导入java.io.IOException；
导入java.util.*；
导入org.apache.mahout.common.iterator.*；
导入org.apache.mahout.fpm.pfpgrowth.convertors.*；
导入org.apache.mahout.fpm.pfpgrowth.convertors.integer.*；
导入org.apache.mahout.fpm.pfpgrowth.convertors.string.*；
导入org.apache.hadoop.mapred.OutputCollector；
导入org.apache.mahout.common.*；
导入org.apache.hadoop.io.Text；
类FPGrowthDemo{
公共静态void main（字符串[]args）{
长分钟支持=1L；
int k=50；
FPGrowth fps=新的FPGrowth（）；
String milk=“milk”；
stringbread=“面包”；
String butter=“butter”；
字符串bier=“bier”；
LinkedList数据=
新建LinkedList（）；
添加（新的一对（数组.asList（牛奶，面包），1L））；
添加（新的对（Arrays.asList（butter），1L））；
添加（新对（Arrays.asList（bier），1L））；
添加（新的一对（数组.asList（牛奶，面包，黄油），1L））；
添加（新的一对（数组.asList（牛奶，面包，啤酒），1L））；
添加（新的一对（数组.asList（牛奶，面包），1L））；
//此行已删除。。。
//迭代器事务=data.Iterator（）；
采集频率=fps.generateFList(
data.iterator（），//在此处使用迭代器。。。
（int）minSupport）；
System.out.println（“频率列表：+频率）；
OutputCollector输出=
新的OutputCollector（）{
@凌驾
公共void collect（字符串x1，
列表（列表对）
抛出IOException{
StringBuffer sb=新的StringBuffer（）；
sb.附加（x1+“：”）；
for（对：列表对）{
某人加上（“[”）；
字符串sep=“”；
for（字符串项：pair.getFirst（））{
某人追加（项目+sep）；
sep=“，”；
}
sb.append（“]：”+pair.getSecond（））；
}
System.out.println（“+sb.toString（））；
}
};
StatusUpdater updater=新的StatusUpdater（）{
公共无效更新（字符串状态）{
System.out.println（“更新程序：+状态”）；
}
};
试一试{
fps.generateTopKFrequentPatterns(
//此处更改（以前为：事务）
data.iterator（），//使用“fresh”迭代器
频率，
minSupport，
K
无效的
产出，