NaiveBayesMain.java
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
public class NaiveBayesMain
{
public static void main(String[] args) throws Exception
{
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
FileSystem fs = FileSystem.get(conf);
Path path_train, path_temp, path_test, path_out;
if(otherArgs.length != 5)
{
System.err.println("Usage: NaiveBayesMain <dfs_path> <conf> <train> <test> <out>");
System.exit(2);
}
conf.set("conf", otherArgs[0] + "/" +otherArgs[1]);
conf.set("train", otherArgs[0] + "/" +otherArgs[2]);
conf.set("test", otherArgs[0] + "/" +otherArgs[3]);
conf.set("output", otherArgs[0] + "/" +otherArgs[4]);
put2HDFS(otherArgs[1], otherArgs[0] + "/" + otherArgs[1], conf);
put2HDFS(otherArgs[2], otherArgs[0] + "/" + otherArgs[2], conf);
put2HDFS(otherArgs[3], otherArgs[0] + "/" + otherArgs[3], conf);
path_train = new Path(otherArgs[0] + "/" + otherArgs[2]);
path_temp = new Path(otherArgs[0] + "/" + otherArgs[2] + ".train");
path_test = new Path(otherArgs[0] + "/" +otherArgs[3]);
path_out = new Path(otherArgs[0] + "/" + otherArgs[4]);
{
Job job_train = new Job(conf, "naive bayse training");
job_train.setJarByClass(NaiveBayesMain.class);
job_train.setMapperClass(NaiveBayesTrain.TrainMapper.class);
job_train.setCombinerClass(NaiveBayesTrain.TrainReducer.class);
job_train.setReducerClass(NaiveBayesTrain.TrainReducer.class);
job_train.setOutputKeyClass(Text.class);
job_train.setOutputValueClass(IntWritable.class);
FileInputFormat.setInputPaths(job_train, path_train);
if(fs.exists(path_temp))
fs.delete(path_temp, true);
FileOutputFormat.setOutputPath(job_train, path_temp);
if(job_train.waitForCompletion(true) == false)
System.exit(1);
conf.set("train_result", otherArgs[0] + "/" +otherArgs[2] + ".train");
}
{
Job job_test = new Job(conf, "naive bayse testing");
job_test.setJarByClass(NaiveBayesTest.class);
job_test.setMapperClass(NaiveBayesTest.TestMapper.class);
job_test.setOutputKeyClass(Text.class);
job_test.setOutputValueClass(Text.class);
FileInputFormat.setInputPaths(job_test, path_test);
if(fs.exists(path_out))
fs.delete(path_out, true);
FileOutputFormat.setOutputPath(job_test, path_out);
if(job_test.waitForCompletion(true) == false)
System.exit(1);
fs.delete(path_temp, true);
}
getFromHDFS(otherArgs[0] + "/" + otherArgs[4], ".", conf);
fs.close();
System.exit(0);
}
public static void put2HDFS(String src, String dst, Configuration conf) throws Exception
{
Path dstPath = new Path(dst);
FileSystem hdfs = dstPath.getFileSystem(conf);
hdfs.copyFromLocalFile(false, true, new Path(src), new Path(dst));
}
public static void getFromHDFS(String src, String dst, Configuration conf) throws Exception
{
Path dstPath = new Path(dst);
FileSystem lfs = dstPath.getFileSystem(conf);
String temp[] = src.split("/");
Path ptemp = new Path(temp[temp.length-1]);
if(lfs.exists(ptemp));
lfs.delete(ptemp, true);
lfs.copyToLocalFile(true, new Path(src), dstPath);
}
}
NaiveBayesTrain.java
import java.util.Scanner;
import java.io.IOException;
import java.util.ArrayList;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
public class NaiveBayesTrain
{
public static class TrainMapper
extends Mapper<Object, Text, Text, IntWritable>
{
public NaiveBayesConf nBConf;
private final static IntWritable one = new IntWritable(1);
private Text word;
public void setup(Context context)
{
try{
nBConf = new NaiveBayesConf();
Configuration conf = context.getConfiguration();
nBConf.ReadNaiveBayesConf(conf.get("conf"), conf);
}
catch(Exception ex)
{
ex.printStackTrace();
System.exit(1);
}
System.out.println("setup");
}
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException
{
Scanner scan = new Scanner(value.toString());
String str, vals[], temp;
int i;
word = new Text();
while(scan.hasNextLine())
{
str = scan.nextLine();
vals = str.split(" ");
word.set(vals[0]);
context.write(word, one);
for(i = 1; i<vals.length; i++)
{
word = new Text();
temp = vals[0] + "#" + nBConf.proNames.get(i-1);
temp += "#" + vals[i];
word.set(temp);
context.write(word, one);
}
}
}
}
public static class TrainReducer
extends Reducer<Text,IntWritable,Text,IntWritable>
{
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable<IntWritable> values,
Context context) throws IOException, InterruptedException
{
int sum = 0;
for (IntWritable val : values)
{
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}
}
NaiveBayesTest.java
import java.util.Scanner;
import java.io.IOException;
import java.util.HashMap;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
public class NaiveBayesTest
{
public static class TestMapper
extends Mapper<Object, Text, Text, Text>
{
public NaiveBayesConf nBConf;
public NaiveBayesTrainData nBTData;
public void setup(Context context)
{
try{
Configuration conf = context.getConfiguration();
nBConf = new NaiveBayesConf();
nBConf.ReadNaiveBayesConf(conf.get("conf"), conf);
nBTData = new NaiveBayesTrainData();
nBTData.getData(conf.get("train_result"), conf);
}
catch(Exception ex)
{
ex.printStackTrace();
System.exit(1);
}
}
public void map(Object key, Text value, Context context)
throws IOException, InterruptedException
{
Scanner scan = new Scanner(value.toString());
String str, vals[], temp;
int i,j,k,fxyi,fyi,fyij,maxf,idx;
Text id;
Text cls;
while(scan.hasNextLine())
{
str = scan.nextLine();
vals = str.split(" ");
maxf = -100;
idx = -1;
for(i = 0; i<nBConf.class_num; i++)
{
fxyi = 1;
String cl = nBConf.classNames.get(i);
Integer integer = nBTData.freq.get(cl);
if(integer == null)
fyi = 0;
else
fyi = integer.intValue();
for(j = 1; j<vals.length; j++)
{
temp = cl + "#" + nBConf.proNames.get(j-1) + "#" + vals[j];
integer = nBTData.freq.get(temp);
if(integer == null)
fyij = 0;
else
fyij = integer.intValue();
fxyi = fxyi*fyij;
}
if(fyi*fxyi > maxf)
{
maxf = fyi*fxyi;
idx = i;
}
}
id = new Text(vals[0]);
cls = new Text(nBConf.classNames.get(idx));
context.write(id, cls);
}
}
}
}
NaiveBayesConf.java
import java.util.ArrayList;
import java.util.Scanner;
import java.io.File;
import java.io.FileNotFoundException;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.conf.Configuration;
public class NaiveBayesConf
{
public int dimen;
public int class_num;
public ArrayList<String> classNames;
public ArrayList<String> proNames;
public ArrayList<Integer> proRanges;
public NaiveBayesConf()
{
dimen = class_num = 0;
classNames = new ArrayList<String>();
proNames = new ArrayList<String>();
proRanges = new ArrayList<Integer>();
}
public void ReadNaiveBayesConf(String file, Configuration conf) throws Exception
{
Path conf_path = new Path(file);
FileSystem hdfs = conf_path.getFileSystem(conf);
FSDataInputStream fsdt = hdfs.open(conf_path);
Scanner scan = new Scanner(fsdt);
String str = scan.nextLine();
String[] vals = str.split(" ");
class_num = Integer.parseInt(vals[0]);
int i;
for(i = 1; i<vals.length; i++)
{
classNames.add(vals[i]);
}
str = scan.nextLine();
vals = str.split(" ");
dimen = Integer.parseInt(vals[0]);
for(i = 1; i<vals.length; i+=2)
{
proNames.add(vals[i]);
proRanges.add(new Integer(vals[i+1]));
}
fsdt.close();
scan.close();
}
}
NaiveBayesTrainData.java
import java.util.ArrayList;
import java.util.Scanner;
import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.io.File;
import java.io.IOException;
import java.io.FileNotFoundException;
import java.util.HashMap;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileStatus;
//功能:读取指定路径下输出文件"part-..."并添加到HashMap
public class NaiveBayesTrainData
{
public HashMap<String, Integer> freq;
public NaiveBayesTrainData()
{
freq = new HashMap<String, Integer>();
}
public void getData(String file, Configuration conf) throws IOException
{
int i;
Path data_path = new Path(file);
Path file_path;
String temp[], line;
FileSystem hdfs = data_path.getFileSystem(conf);
FileStatus[] status = hdfs.listStatus(data_path);
for(i = 0; i<status.length; i++)
{
file_path = status[i].getPath();
if(hdfs.getFileStatus(file_path).isDir() == true)
continue;
line = file_path.toString();
temp = line.split("/");
if(temp[temp.length-1].substring(0,5).equals("part-") == false)
continue;
System.err.println(line);
FSDataInputStream fin = hdfs.open(file_path);
InputStreamReader inr = new InputStreamReader(fin);
BufferedReader bfr = new BufferedReader(inr);
while((line = bfr.readLine()) != null)
{
String res[] = line.split("\t");
freq.put(res[0], new Integer(res[1]));
System.out.println(line);
}
bfr.close();
inr.close();
fin.close();
}
}
}
NBayes.conf
4 cl1 cl2 cl3 cl4
3 p1 12 p2 16 p3 17
NBayes.train
cl1 5 6 7
cl2 3 8 4
cl1 2 5 2
cl3 7 8 7
cl4 3 8 2
cl4 9 2 7
cl2 1 8 5
cl5 2 9 4
cl3 10 3 4
cl1 4 5 6
cl3 4 6 7
NBayes.test
1 5 6 7
2 1 8 5
3 2 9 4
4 10 3 4
5 4 5 6
6 3 8 4
7 2 5 2
8 7 8 7
9 3 8 2
10 9 2 7
11 4 6 7
train-map-output.txt
trainmapinput:cl1 5 6 7
trainmapoutput:<cl1,1>
trainmapoutput:<cl1#p1#5,1>
trainmapoutput:<cl1#p2#6,1>
trainmapoutput:<cl1#p3#7,1>
trainmapinput:cl2 3 8 4
trainmapoutput:<cl2,1>
trainmapoutput:<cl2#p1#3,1>
trainmapoutput:<cl2#p2#8,1>
trainmapoutput:<cl2#p3#4,1>
trainmapinput:cl1 2 5 2
trainmapoutput:<cl1,1>
trainmapoutput:<cl1#p1#2,1>
trainmapoutput:<cl1#p2#5,1>
trainmapoutput:<cl1#p3#2,1>
trainmapinput:cl3 7 8 7
trainmapoutput:<cl3,1>
trainmapoutput:<cl3#p1#7,1>
trainmapoutput:<cl3#p2#8,1>
trainmapoutput:<cl3#p3#7,1>
trainmapinput:cl4 3 8 2
trainmapoutput:<cl4,1>
trainmapoutput:<cl4#p1#3,1>
trainmapoutput:<cl4#p2#8,1>
trainmapoutput:<cl4#p3#2,1>
trainmapinput:cl4 9 2 7
trainmapoutput:<cl4,1>
trainmapoutput:<cl4#p1#9,1>
trainmapoutput:<cl4#p2#2,1>
trainmapoutput:<cl4#p3#7,1>
trainmapinput:cl2 1 8 5
trainmapoutput:<cl2,1>
trainmapoutput:<cl2#p1#1,1>
trainmapoutput:<cl2#p2#8,1>
trainmapoutput:<cl2#p3#5,1>
trainmapinput:cl5 2 9 4
trainmapoutput:<cl5,1>
trainmapoutput:<cl5#p1#2,1>
trainmapoutput:<cl5#p2#9,1>
trainmapoutput:<cl5#p3#4,1>
trainmapinput:cl3 10 3 4
trainmapoutput:<cl3,1>
trainmapoutput:<cl3#p1#10,1>
trainmapoutput:<cl3#p2#3,1>
trainmapoutput:<cl3#p3#4,1>
trainmapinput:cl1 4 5 6
trainmapoutput:<cl1,1>
trainmapoutput:<cl1#p1#4,1>
trainmapoutput:<cl1#p2#5,1>
trainmapoutput:<cl1#p3#6,1>
trainmapinput:cl3 4 6 7
trainmapoutput:<cl3,1>
trainmapoutput:<cl3#p1#4,1>
trainmapoutput:<cl3#p2#6,1>
trainmapoutput:<cl3#p3#7,1>
train-reduce-output.txt
cl1 3
cl1#p1#2 1
cl1#p1#4 1
cl1#p1#5 1
cl1#p2#5 2
cl1#p2#6 1
cl1#p3#2 1
cl1#p3#6 1
cl1#p3#7 1
cl2 2
cl2#p1#1 1
cl2#p1#3 1
cl2#p2#8 2
cl2#p3#4 1
cl2#p3#5 1
cl3 3
cl3#p1#10 1
cl3#p1#4 1
cl3#p1#7 1
cl3#p2#3 1
cl3#p2#6 1
cl3#p2#8 1
cl3#p3#4 1
cl3#p3#7 2
cl4 2
cl4#p1#3 1
cl4#p1#9 1
cl4#p2#2 1
cl4#p2#8 1
cl4#p3#2 1
cl4#p3#7 1
cl5 1
cl5#p1#2 1
cl5#p2#9 1
cl5#p3#4 1
test-mapreduce-output.txt
1 cl1
10 cl4
11 cl3
2 cl2
3 cl1
4 cl3
5 cl1
6 cl2
7 cl1
8 cl3
9 cl4