基于MapReduce的Apriori算法代码及其使用.docx

package com;import java.io.IOException;import java.text.DateFormat;import java.text.SimpleDateFormat;import java.util.Date;import java.util.StringTokenizer;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.conf.Configured;import org.apache.hadoop.fs.FileSystem;import org.apache.hadoop.fs.Path;import org.apache.hadoop.util.Tool;import org.apache.hadoop.util.ToolRunner;import org.apache.hadoop.io.IntWritable;import org.apache.hadoop.io.LongWritable;import org.apache.hadoop.io.Text;import org.apache.hadoop.mapreduce.Job;import org.apache.hadoop.mapreduce.Mapper;import org.apache.hadoop.mapreduce.Reducer;import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;public class Apriori extends Configured implements Tool {enum Counter {LINESKIP, // 出错的行}public static class MAP extendsMapperLongWritable, Text, Text, IntWritable {@Overridepublic void map(LongWritable key, Text value, Context context)throws IOException, InterruptedException {// 输入的一行预处理文本StringTokenizer itr = new StringTokenizer(value.toString());String[] values = new String[2];int i = 0;while (itr.hasMoreTokens()) {values[i] = itr.nextToken();i++;}if (values[0].length() 0 values[1].length() 0) {String dd[] = values[1].split(,);System.out.println(values[1] + , + dd.length);int[] result;String output = ;for (int j = 1; j dd.length; j++) {Combination c = new Combination(j + 1, dd.length);while ((result = c.next()) != null) {for (i = 0; i result.length; i++) {// System.out.print(result+);//output += dd[result] + ,;//System.out.print(d[i]+ );output += dd[result[i]] + ,;}// System.out.println();context.write(new Text(output.substring(0, output.length()-1)), new IntWritable(1));result = null;output = ;}}}}}public static class REDUCE extendsReducerText, IntWritable, Text, IntWritable {@Overridepublic void reduce(Text key, IterableIntWritable values,Context context) throws IOException, InterruptedException {int CNT = 0;for (IntWri