Bloom Filter in MapReduce - hadoop

I have to use bloom filter in the reduce side join algorithm to filter one of my input, but I have a problem with the function readFields that de-serialise the input stream of a distributed cache (bloom filter) into a bloom filter.
public class BloomJoin {
//function map : input transaction.txt
public static class TransactionJoin extends
Mapper<LongWritable, Text, Text, Text> {
private Text CID=new Text();
private Text outValue=new Text();
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
String record[] = line.split(",", -1);
CID.set(record[1]);
outValue.set("A"+value);
context.write(CID, outValue);
}
}
//function map : input customer.txt
public static class CustomerJoinMapper extends
Mapper<LongWritable, Text, Text, Text> {
private Text outkey=new Text();
private Text outvalue = new Text();
private BloomFilter bfilter = new BloomFilter();
public void setup(Context context) throws IOException {
URI[] files = DistributedCache
.getCacheFiles(context.getConfiguration());
// if the files in the distributed cache are set
if (files != null) {
System.out.println("Reading Bloom filter from: "
+ files[0].getPath());
// Open local file for read.
DataInputStream strm = new DataInputStream(new FileInputStream(
files[0].toString()));
bfilter.readFields(strm);
strm.close();
// Read into our Bloom filter.
} else {
throw new IOException(
"Bloom filter file not set in the DistributedCache.");
}
};
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
String record[] = line.split(",", -1);
outkey.set(record[0]);
if (bfilter.membershipTest(new Key(outkey.getBytes()))) {
outvalue.set("B"+value);
context.write(outkey, outvalue);
}
}
}
//function reducer: join customer with transaction
public static class JoinReducer extends
Reducer<Text, Text, Text, Text> {
private ArrayList<Text> listA = new ArrayList<Text>();
private ArrayList<Text> listB = new ArrayList<Text>();
#Override
public void reduce(Text key, Iterable<Text> values, Context context)
throws IOException, InterruptedException {
listA.clear();
listB.clear();
for (Text t : values) {
if (t.charAt(0) == 'A') {
listA.add(new Text(t.toString().substring(1)));
System.out.println("liste A: "+listA);
} else /* if (t.charAt('0') == 'B') */{
listB.add(new Text(t.toString().substring(1)));
System.out.println("listeB :"+listB);
}
}
executeJoinLogic(context);
}
private void executeJoinLogic(Context context) throws IOException,
InterruptedException {
if (!listA.isEmpty() && !listB.isEmpty()) {
for (Text A : listB) {
for (Text B : listA) {
context.write(A, B);
System.out.println("A="+A+",B="+B);
}
}
}
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
Path bloompath=new Path("/user/biadmin/ezzaki/bloomfilter/output/part-00000");
DistributedCache.addCacheFile(bloompath.toUri(),conf);
Job job = new Job(conf, "Bloom Join");
job.setJarByClass(BloomJoin.class);
String[] otherArgs = new GenericOptionsParser(conf, args)
.getRemainingArgs();
if (otherArgs.length != 3) {
System.err
.println("ReduceSideJoin <Transaction data> <Customer data> <out> ");
System.exit(1);
}
MultipleInputs.addInputPath(job, new Path(otherArgs[0]),
TextInputFormat.class,TransactionJoin.class);
MultipleInputs.addInputPath(job, new Path(otherArgs[1]),
TextInputFormat.class, CustomerJoinMapper.class);
job.setReducerClass(JoinReducer.class);
FileOutputFormat.setOutputPath(job, new Path(otherArgs[2]));
//job.setMapOutputKeyClass(Text.class);
//job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
System.exit(job.waitForCompletion(true) ? 0 : 3);
}
}
How can I solve this problem?

Can you try changing
URI[] files = DistributedCache.getCacheFiles(context.getConfiguration());
to
Path[] cacheFilePaths = DistributedCache.getLocalCacheFiles(conf);
for (Path cacheFilePath : cacheFilePaths) {
DataInputStream fileInputStream = fs.open(cacheFilePath);
}
bloomFilter.readFields(fileInputStream);
fileInputStream.close();
Also, I think you are using Map side join and not Reduce side since you are using the Distributed cache in Mapper.

You can use a Bloom Filter from here:
https://github.com/odnoklassniki/apache-cassandra/blob/master/src/java/org/apache/cassandra/utils/BloomFilter.java
It goes with dedicated serializer:
https://github.com/odnoklassniki/apache-cassandra/blob/master/src/java/org/apache/cassandra/utils/BloomFilterSerializer.java
You can serialize like this:
Path file = new Path(bloomFilterPath);
FileSystem hdfs = file.getFileSystem(context.getConfiguration());
OutputStream os = hdfs.create(file);
BloomFilterSerializer serializer = new BloomFilterSerializer();
serializer.serialize(bloomFilter, new DataOutputStream(os));
And deserialize:
InputStream is = getInputStreamFromHdfs(context, bloomFilterPath);
Path path = new Path(bloomFilterPath);
InputStream is = path.getFileSystem(context.getConfiguration()).open(path);
BloomFilterSerializer serializer = new BloomFilterSerializer();
BloomFilter bloomFilter = serializer.deserialize(
new DataInputStream(new BufferedInputStream(is)));

Related

How to remove r-00000 extention from reducer output in mapreduce

I am able to rename my reducer output file correctly but r-00000 is still persisting .
I have used MultipleOutputs in my reducer class .
Here is details of the that .Not sure what am i missing or what extra i have to do?
public class MyReducer extends Reducer<NullWritable, Text, NullWritable, Text> {
private Logger logger = Logger.getLogger(MyReducer.class);
private MultipleOutputs<NullWritable, Text> multipleOutputs;
String strName = "";
public void setup(Context context) {
logger.info("Inside Reducer.");
multipleOutputs = new MultipleOutputs<NullWritable, Text>(context);
}
#Override
public void reduce(NullWritable Key, Iterable<Text> values, Context context)
throws IOException, InterruptedException {
for (Text value : values) {
final String valueStr = value.toString();
StringBuilder sb = new StringBuilder();
sb.append(strArrvalueStr[0] + "|!|");
multipleOutputs.write(NullWritable.get(), new Text(sb.toString()),strName);
}
}
public void cleanup(Context context) throws IOException,
InterruptedException {
multipleOutputs.close();
}
}
I was able to do it explicitly after my job finishes and thats ok for me.No delay in the job
if (b){
DateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd-HHmm");
Calendar cal = Calendar.getInstance();
String strDate=dateFormat.format(cal.getTime());
FileSystem hdfs = FileSystem.get(getConf());
FileStatus fs[] = hdfs.listStatus(new Path(args[1]));
if (fs != null){
for (FileStatus aFile : fs) {
if (!aFile.isDir()) {
hdfs.rename(aFile.getPath(), new Path(aFile.getPath().toString()+".txt"));
}
}
}
}
A more suitable approach to the problem would be changing the OutputFormat.
For eg :- If you are using TextOutputFormatClass, just get the source code of the TextOutputFormat class and modify the below method to get the proper filename (without r-00000). We need to then set the modified output format in the driver.
public synchronized static String getUniqueFile(TaskAttemptContext context, String name, String extension) {
/*TaskID taskId = context.getTaskAttemptID().getTaskID();
int partition = taskId.getId();*/
StringBuilder result = new StringBuilder();
result.append(name);
/*
* result.append('-');
* result.append(TaskID.getRepresentingCharacter(taskId.getTaskType()));
* result.append('-'); result.append(NUMBER_FORMAT.format(partition));
* result.append(extension);
*/
return result.toString();
}
So whatever name is passed through the multiple outputs, filename will be created according to it.

Hadoop and Custom Writable Issue

I am using Hadoop 2.7 and I have got an issue when using a custom Writable "TextPair" (page 104 of the Definitive Guide). Basically, my program works fine when I am using just Text whereas it outputs "test.TextTuple#3b86249a test.TextTuple#63cd18fd" when using the TextPair.
Please, Any idea of what is wrong with my code (below)?
============
Mapper1:
public class KWMapper extends Mapper<LongWritable, Text, TextTuple, TextTuple> {
#Override
public void map(LongWritable k, Text v, Mapper.Context c) throws IOException, InterruptedException {
String keywordRelRecord[] = v.toString().split(",");
String subTopicID = keywordRelRecord[0];
String paperID = keywordRelRecord[1];
//set the KEY
TextTuple key = new TextTuple();
key.setNaturalKey(new Text(subTopicID));
key.setSecondaryKey(new Text("K"));
//set the VALUE
TextTuple value = new TextTuple();
value.setNaturalKey(new Text(paperID));
value.setSecondaryKey(new Text("K"));
c.write(key, value);
}
Mapper2:
public class TDMapper extends Mapper<LongWritable, Text, TextTuple, TextTuple> {
#Override
public void map(LongWritable k, Text v, Mapper.Context c) throws IOException, InterruptedException {
String topicRecord[] = v.toString().split(",");
String superTopicID = topicRecord[0];
String subTopicID = topicRecord[1].substring(1, topicRecord[1].length() - 1);
TextTuple key = new TextTuple();
key.setNaturalKey(new Text(subTopicID));
key.setSecondaryKey(new Text("T"));
TextTuple value = new TextTuple();
value.setNaturalKey(new Text(superTopicID));
value.setSecondaryKey(new Text("T"));
c.write(key, value);
}
REDUCER :
public class TDKRReducer extends Reducer<TextTuple, TextTuple, Text, Text>{
public void reduce(TextTuple k, Iterable<TextTuple> values, Reducer.Context c) throws IOException, InterruptedException{
for (TextTuple val : values) {
c.write(k.getNaturalKey(), val.getNaturalKey());
}
}
}
DRIVER:
public class TDDriver {
public static void main(String args[]) throws IOException, InterruptedException, ClassNotFoundException {
// This class support the user for the configuration of the execution;
Configuration confStage1 = new Configuration();
Job job1 = new Job(confStage1, "TopDecKeywordRel");
// Setting the driver class
job1.setJarByClass(TDDriver.class);
// Setting the input Files and processing them using the corresponding mapper class
MultipleInputs.addInputPath(job1, new Path(args[0]), TextInputFormat.class, TDMapper.class);
MultipleInputs.addInputPath(job1, new Path(args[1]), TextInputFormat.class, KWMapper.class);
job1.setMapOutputKeyClass(TextTuple.class);
job1.setMapOutputValueClass(TextTuple.class);
// Setting the Reducer Class;
job1.setReducerClass(TDKRReducer.class);
// Setting the output class for the Key-value pairs
job1.setOutputKeyClass(Text.class);
job1.setOutputValueClass(Text.class);
// Setting the output file
Path outputPA = new Path(args[2]);
FileOutputFormat.setOutputPath(job1, outputPA);
// Submitting the Job Monitoring the execution of the Job
System.exit(job1.waitForCompletion(true) ? 0 : 1);
//conf.setPartitionerClass(CustomPartitioner.class);
}
}
CUSTOM VARIABLE
public class TextTuple implements Writable, WritableComparable<TextTuple> {
private Text naturalKey;
private Text secondaryKey;
public TextTuple() {
this.naturalKey = new Text();
this.secondaryKey = new Text();
}
public void setNaturalKey(Text naturalKey) {
this.naturalKey = naturalKey;
}
public void setSecondaryKey(Text secondaryKey) {
this.secondaryKey = secondaryKey;
}
public Text getNaturalKey() {
return naturalKey;
}
public Text getSecondaryKey() {
return secondaryKey;
}
#Override
public void write(DataOutput out) throws IOException {
naturalKey.write(out);
secondaryKey.write(out);
}
#Override
public void readFields(DataInput in) throws IOException {
naturalKey.readFields(in);
secondaryKey.readFields(in);
}
//This comparator controls the sort order of the keys.
#Override
public int compareTo(TextTuple o) {
// comparing the naturalKey
int compareValue = this.naturalKey.compareTo(o.naturalKey);
if (compareValue == 0) {
compareValue = this.secondaryKey.compareTo(o.secondaryKey);
}
return -1 * compareValue;
}
}

Hadoop Mapreduce: Custom Input Format

I have a file with data having text and "^" in between:
SOME TEXT^GOES HERE^
AND A FEW^MORE
GOES HERE
I am writing a custom input format to delimit the rows using "^" character. i.e The output of the mapper should be like:
SOME TEXT
GOES HERE
AND A FEW
MORE GOES HERE
I have written a written a custom input format which extends FileInputFormat and also written a custom record reader that extends RecordReader. Code for my custom record reader is given below. I dont know how to proceed with this code. Having trouble with the nextKeyValue() method in the WHILE loop part. How should I read the data from a split and generate my custom key-value? I am using all new mapreduce package instead of the old mapred package.
public class MyRecordReader extends RecordReader<LongWritable, Text>
{
long start, current, end;
Text value;
LongWritable key;
LineReader reader;
FileSplit split;
Path path;
FileSystem fs;
FSDataInputStream in;
Configuration conf;
#Override
public void initialize(InputSplit inputSplit, TaskAttemptContext cont) throws IOException, InterruptedException
{
conf = cont.getConfiguration();
split = (FileSplit)inputSplit;
path = split.getPath();
fs = path.getFileSystem(conf);
in = fs.open(path);
reader = new LineReader(in, conf);
start = split.getStart();
current = start;
end = split.getLength() + start;
}
#Override
public boolean nextKeyValue() throws IOException
{
if(key==null)
key = new LongWritable();
key.set(current);
if(value==null)
value = new Text();
long readSize = 0;
while(current<end)
{
Text tmpText = new Text();
readSize = read //here how should i read data from the split, and generate key-value?
if(readSize==0)
break;
current+=readSize;
}
if(readSize==0)
{
key = null;
value = null;
return false;
}
return true;
}
#Override
public float getProgress() throws IOException
{
}
#Override
public LongWritable getCurrentKey() throws IOException
{
}
#Override
public Text getCurrentValue() throws IOException
{
}
#Override
public void close() throws IOException
{
}
}
There is no need to implement that yourself. You can simply set the configuration value textinputformat.record.delimiter to be the circumflex character.
conf.set("textinputformat.record.delimiter", "^");
This should work fine with the normal TextInputFormat.

Distributed cache not working

I am storing a small amount of data (few MBs) in a distributed cache and using that to perform anti join with two big files. For few lines of data in cache , the functionality is working fine, but when the cache is having more data in production it's not able to do the job but its not throwing any error as well. Just that only few records (around 20%) are getting joined and others are just getting ignored. So is there any upper limit of number of records that can be stored in the distributed cache? Why its working for some of the records and ignoring the rest? Any suggestion will be extremely helpful.
Bellow is my code
public class MyMapper extends Mapper<LongWritable, Text, Text, TextPair> {
Text albumKey = new Text();
Text photoKey = new Text();
private HashSet<String> photoDeleted = new HashSet<String>();
private HashSet<String> albDeleted = new HashSet<String>();
Text interKey = new Text();
private TextPair interValue = new TextPair();
private static final Logger LOGGER = Logger.getLogger(SharedStreamsSlMapper.class);
protected void setup(Context context) throws IOException, InterruptedException {
int count=0;
Path[] cacheFiles = DistributedCache.getLocalCacheFiles(context.getConfiguration());
System.out.println(cacheFiles.length);
LOGGER.info(cacheFiles+"****");
try {
if (cacheFiles != null && cacheFiles.length > 0) {
for (Path path : cacheFiles) {
String line;
String[] tokens;
BufferedReader joinReader = new BufferedReader(new FileReader(path.toString()));
System.out.println(path.toString());
// BufferedReader joinReader = new BufferedReader(new FileReader("/Users/Kunal_Basak/Desktop/ss_test/dsitCache/part-m-00000"));
try {
while ((line = joinReader.readLine()) != null) {
count++;
tokens = line.split(SSConstants.TAB, 2);
if(tokens.length<2){
System.out.println("WL");
continue;
}
if (tokens[0].equals("P")) {
photoDeleted.add(tokens[1]);
}
else if (tokens[0].equals("A")) {
albDeleted.add(tokens[1]);
}
}
}
finally {
joinReader.close();
}
}
}
}
catch (IOException e) {
System.out.println("Exception reading DistributedCache: " + e);
}
System.out.println(count);
System.out.println("albdeleted *****"+albDeleted.size());
System.out.println("photo deleted *****"+photoDeleted.size());
LOGGER.info("albdeleted *****"+albDeleted.size());
LOGGER.info("albdeleted *****"+albDeleted.size());
}
public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
try{
//my mapper code
}
}
}
According to this blog article:
The local.cache.size parameter controls the size of the
DistributedCache.
By default, it’s set to 10 GB.
So if you have more than 10GB in the cache, that may be your problem.

Example for running mapreduce on hdfs files and storing reducer results in hbase table

Can somebody give one good example link for mapreduce with Hbase? My requirement is run mapreduce on hdfs file and store reducer output to hbase table. Mapper input will be hdfs file and output will be Text,IntWritable key value pairs. Reducers output will be Put object ie add reducer Iterable IntWritable values and store in hbase table.
Here is the code which will solve your problem
Driver
HBaseConfiguration conf = HBaseConfiguration.create();
Job job = new Job(conf,"JOB_NAME");
job.setJarByClass(yourclass.class);
job.setMapperClass(yourMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Intwritable.class);
FileInputFormat.setInputPaths(job, new Path(inputPath));
TableMapReduceUtil.initTableReducerJob(TABLE,
yourReducer.class, job);
job.setReducerClass(yourReducer.class);
job.waitForCompletion(true);
Mapper&Reducer
class yourMapper extends Mapper<LongWritable, Text, Text,IntWritable> {
//#overide map()
}
class yourReducer
extends
TableReducer<Text, IntWritable,
ImmutableBytesWritable>
{
//#override rdeuce()
}
**Ckeck the bellow code that works fine for me with Phoenix Hbase and map reduce **
This program will read data from Hbase table and inset result in to another table after map-reduce job .
Table :-> STOCK ,STOCK_STATS
StockComputationJob.java
public static class StockMapper extends Mapper<NullWritable, StockWritable, Text , DoubleWritable> {
private Text stock = new Text();
private DoubleWritable price = new DoubleWritable ();
#Override
protected void map(NullWritable key, StockWritable stockWritable, Context context) throws IOException, InterruptedException {
double[] recordings = stockWritable.getRecordings();
final String stockName = stockWritable.getStockName();
System.out.println("Map-"+recordings);
double maxPrice = Double.MIN_VALUE;
for(double recording : recordings) {
System.out.println("M-"+key+"-"+recording);
if(maxPrice < recording) {
maxPrice = recording;
}
}
System.out.println(stockName+"--"+maxPrice);
stock.set(stockName);
price.set(maxPrice);
context.write(stock,price);
}
}
public static void main(String[] args) throws Exception {
final Configuration conf = new Configuration();
HBaseConfiguration.addHbaseResources(conf);
conf.set(HConstants.ZOOKEEPER_QUORUM, zkUrl);
final Job job = Job.getInstance(conf, "stock-stats-job");
// We can either specify a selectQuery or ignore it when we would like to retrieve all the columns
final String selectQuery = "SELECT STOCK_NAME,RECORDING_YEAR,RECORDINGS_QUARTER FROM STOCK ";
// StockWritable is the DBWritable class that enables us to process the Result of the above query
PhoenixMapReduceUtil.setInput(job,StockWritable.class,"STOCK",selectQuery);
// Set the target Phoenix table and the columns
PhoenixMapReduceUtil.setOutput(job, "STOCK_STATS", "STOCK_NAME,MAX_RECORDING");
job.setMapperClass(StockMapper.class);
job.setReducerClass(StockReducer.class);
job.setOutputFormatClass(PhoenixOutputFormat.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(DoubleWritable.class);
job.setOutputKeyClass(NullWritable.class);
job.setOutputValueClass(StockWritable.class);
TableMapReduceUtil.addDependencyJars(job);
job.waitForCompletion(true);
}
}
StockReducer.java
public class StockReducer extends Reducer<Text, DoubleWritable, NullWritable , StockWritable> {
protected void reduce(Text key, Iterable<DoubleWritable> recordings, Context context) throws IOException, InterruptedException {
double maxPrice = Double.MIN_VALUE;
System.out.println(recordings);
for(DoubleWritable recording : recordings) {
System.out.println("R-"+key+"-"+recording);
if(maxPrice < recording.get()) {
maxPrice = recording.get();
}
}
final StockWritable stock = new StockWritable();
stock.setStockName(key.toString());
stock.setMaxPrice(maxPrice);
System.out.println(key+"--"+maxPrice);
context.write(NullWritable.get(),stock);
}
}
StockWritable.java
public class StockWritable implements DBWritable,Writable {
private String stockName;
private int year;
private double[] recordings;
private double maxPrice;
public void readFields(DataInput input) throws IOException {
}
public void write(DataOutput output) throws IOException {
}
public void readFields(ResultSet rs) throws SQLException {
stockName = rs.getString("STOCK_NAME");
setYear(rs.getInt("RECORDING_YEAR"));
final Array recordingsArray = rs.getArray("RECORDINGS_QUARTER");
setRecordings((double[])recordingsArray.getArray());
}
public void write(PreparedStatement pstmt) throws SQLException {
pstmt.setString(1, stockName);
pstmt.setDouble(2, maxPrice);
}
public int getYear() {
return year;
}
public void setYear(int year) {
this.year = year;
}
public double[] getRecordings() {
return recordings;
}
public void setRecordings(double[] recordings) {
this.recordings = recordings;
}
public double getMaxPrice() {
return maxPrice;
}
public void setMaxPrice(double maxPrice) {
this.maxPrice = maxPrice;
}
public String getStockName() {
return stockName;
}
public void setStockName(String stockName) {
this.stockName = stockName;
}
}

Resources