public static void main(String[] args) {
String logFile;
if (args.length != 0) logFile = args[0];
else logFile = "/media/gf/Java/spark-1.4.0-bin-hadoop2.6/README.md";
final SparkConf conf = new SparkConf().setAppName("Simple Application");
final JavaSparkContext sc = new JavaSparkContext(conf);
final JavaRDD<String> logData = sc.textFile(logFile).cache();
final String[] check = getFilterSet();
System.out.println("Start: " + new Date());
for (int i = 0; i < check.length; i++) {
final int post = i;
long count =
logData
.filter(
new Function<String, Boolean>() {
public Boolean call(String s) {
return s.contains(check[post]);
}
})
.count();
System.out.println("Lines with " + check[i] + ": " + count);
}
System.out.println("End: " + new Date());
sc.close();
}
@AfterClass
public static void tearDown() {
if (javaSparkContext != null) {
javaSparkContext.close();
javaSparkContext = null;
}
}
@After
public void tearDown() throws Exception {
if (sc != null) {
sc.stop();
sc.close();
}
}
public static boolean SpatialRangeQuery(
String InputLocation1, String InputLocation2, String OutputLocation) {
SparkConf sparkConfiguration = new SparkConf().setAppName("Group22-RangeQuery");
JavaSparkContext sparkContext = new JavaSparkContext(sparkConfiguration);
boolean result = getRangeQuery(InputLocation1, InputLocation2, OutputLocation, sparkContext);
sparkContext.close();
return result;
}
public static void main(String[] args) {
SparkConf conf = new SparkConf().setAppName("Distinct");
JavaSparkContext sc = new JavaSparkContext(conf);
JavaRDD<Integer> nums =
sc.parallelize(
Arrays.asList(1, 2, 3, 4, 5, 1, 3, 2, 2, 1, 3, 4, 5, 5, 4, 3, 1, 2, 3, 2, 6, 8, 0));
JavaRDD<Integer> distinct = nums.distinct();
System.out.println(StringUtils.join(distinct.collect(), ","));
sc.close();
}
public static void main(String[] args) throws FileNotFoundException {
String path = args[0];
// This is the default 2 line structure for spark programs in java
// The spark.executor.memory can only take the maximum java heapspace set by -Xmx
SparkConf conf =
new SparkConf()
.setMaster("local[" + NUM_THREADS + "]")
.setAppName(Demo.class.getSimpleName())
.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer");
JavaSparkContext sc = new JavaSparkContext(conf);
long start = System.nanoTime();
// if you need both the coordinates and the sequences, use this section of code
// read sequence file and map to PdbId.chainId, SimplePolymerChain pairs
List<Tuple2<String, SimplePolymerChain>> chains =
sc.sequenceFile(path, Text.class, ArrayWritable.class, NUM_THREADS * NUM_TASKS_PER_THREAD)
.sample(false, 0.01, 123)
.mapToPair(
new HadoopToSimpleChainMapper()) // convert input to <pdbId.chainId,
// SimplePolymerChain> pairs
.filter(t -> t._2.isProtein())
.collect();
for (Tuple2<String, SimplePolymerChain> t : chains) {
System.out.println(t._1 + ": " + t._2);
}
// if you need just the coordinates, use this section of code
// read sequence file and map to PdbId.chainId, C-alpha coordinate pairs
List<Tuple2<String, Point3d[]>> coordinates =
sc.sequenceFile(path, Text.class, ArrayWritable.class, NUM_THREADS * NUM_TASKS_PER_THREAD)
.sample(false, 0.01, 123)
.mapToPair(
new HadoopToSimpleChainMapper()) // convert input to <pdbId.chainId, protein
// sequence> pairs
.filter(t -> t._2.isProtein())
.mapToPair(t -> new Tuple2<String, Point3d[]>(t._1, t._2.getCoordinates()))
.collect();
for (Tuple2<String, Point3d[]> t : coordinates) {
System.out.println(t._1 + ": " + Arrays.toString(t._2));
}
sc.close();
System.out.println("Time: " + (System.nanoTime() - start) / 1E9 + " sec.");
}
/**
* @param args Path of the hadoop sequence file
* @throws FileNotFoundException
*/
public static void main(String[] args) throws FileNotFoundException {
String path = args[0];
JavaSparkContext sc = getSparkContext();
// sc is an existing JavaSparkContext.
SQLContext sqlContext = new org.apache.spark.sql.SQLContext(sc);
sqlContext.setConf("spark.sql.parquet.compression.codec", "snappy");
sqlContext.setConf("spark.sql.parquet.filterPushdown", "true");
long start = System.nanoTime();
// read sequence file and map
JavaRDD<Row> rowRDD =
sc.sequenceFile(path, Text.class, Text.class)
// .sample(false, 0.01, 123)
.mapToPair(t -> new Tuple2<String, String>(t._1.toString(), t._2.toString()))
.groupByKey()
.map(new HadoopToParqRow())
.cache();
List<StructField> fields =
new ArrayList<StructField>(); // create data fields of features for the DataFrame
fields.add(DataTypes.createStructField("index", DataTypes.StringType, false));
fields.add(DataTypes.createStructField("chainId1", DataTypes.StringType, false));
fields.add(DataTypes.createStructField("chainId2", DataTypes.StringType, false));
fields.add(DataTypes.createStructField("Rnum1", DataTypes.StringType, false));
fields.add(DataTypes.createStructField("Rnum2", DataTypes.StringType, false));
fields.add(DataTypes.createStructField("Ins1", DataTypes.StringType, false));
fields.add(DataTypes.createStructField("Ins2", DataTypes.StringType, false));
fields.add(DataTypes.createStructField("res1", DataTypes.StringType, false));
fields.add(DataTypes.createStructField("res2", DataTypes.StringType, false));
fields.add(DataTypes.createStructField("atom1", DataTypes.StringType, false));
fields.add(DataTypes.createStructField("atom2", DataTypes.StringType, false));
fields.add(DataTypes.createStructField("element1", DataTypes.StringType, false));
fields.add(DataTypes.createStructField("element2", DataTypes.StringType, false));
fields.add(DataTypes.createStructField("distance", DataTypes.IntegerType, false));
fields.add(
DataTypes.createStructField(
"pdbId", DataTypes.createArrayType(DataTypes.StringType), false));
StructType schema = DataTypes.createStructType(fields);
// Apply the schema to the RDD.
DataFrame dataFrame = sqlContext.createDataFrame(rowRDD, schema);
dataFrame
.coalesce(1)
.write()
.mode(SaveMode.Overwrite)
.partitionBy("index")
.parquet("/Users/hina/Data/ExampleFiles/seq.parquet");
sc.close();
System.out.println("Time: " + (System.nanoTime() - start) / 1E9 + " sec.");
}
private static void trainAdaBoost() {
int imgSize = 24;
int T = 300;
// String root = "/home/hadoop/ProgramDatas/MLStudy/FaceDection/";
String root = "E:/TestDatas/MLStudy/FaceDection/";
String dataFile = root + "train_data.txt";
String modelFile = root + "adaboost_model.txt";
String sparkAppName = "Viola-Jones Train";
String sparkMaster = "spark://localhost:7077";
int sparkCores = 60;
String sparkJars = "/home/hadoop/violajones.jar";
checkMemoryInfo();
System.out.println("initing feature templates...");
List<FeatureTemplate> templates = FeatureTemplate.initFeaTemplates();
System.out.println("initing features...");
List<HaarLikeFeature> features = HaarLikeFeature.initFeatures(imgSize, imgSize, templates);
System.out.println("loading train datas...");
List<IntegralImage> trainDatas = FileUtils.loadTrainDatas(dataFile, imgSize, imgSize);
Collections.shuffle(trainDatas);
SparkConf sparkConf =
new SparkConf()
.setMaster(sparkMaster)
.setAppName(sparkAppName)
.set("spark.executor.memory", "2g");
JavaSparkContext sc = new JavaSparkContext(sparkConf);
sc.addJar(sparkJars);
sc.setLogLevel("WARN");
System.out.println("training adaboost...");
AdaBoost adaBoost = new AdaBoost(trainDatas, features);
Map<HaarLikeFeature, Double> classifiers = adaBoost.train(sc, sparkCores, T);
System.out.println("exporting model...");
List<String> model = new ArrayList<String>();
for (Entry<HaarLikeFeature, Double> item : classifiers.entrySet()) {
model.add(item.getKey().toStringWithWeight(item.getValue()));
}
FileUtils.exportFile(modelFile, model);
System.out.println("viola jones training success!");
sc.close();
}
private static void trainCascadeAdaBoost() {
int imgSize = 30;
double eachDR = 0.99, eachFAR = 0.5, finalFAR = 0;
String root = "/home/hadoop/ProgramDatas/MLStudy/FaceDection/";
// String root = "E:/TestDatas/MLStudy/FaceDection/";
String dataFile = root + "train_data_2.txt";
String modelFile = root + "CascadeAdaboost_model.txt";
String misclassificationFile = root + "mis_classifications.txt";
String sparkAppName = "Viola-Jones Train";
String sparkMaster = "spark://localhost:7077";
int sparkCores = 60;
String sparkJars = "/home/hadoop/violajones.jar";
checkMemoryInfo();
System.out.println("initing feature templates...");
List<FeatureTemplate> templates = FeatureTemplate.initFeaTemplates();
System.out.println("initing features...");
List<HaarLikeFeature> features = HaarLikeFeature.initFeatures(imgSize, imgSize, templates);
System.out.println("loading train datas...");
Map<Integer, List<IntegralImage>> trainDatas =
FileUtils.loadTrainDatasSeparate(dataFile, imgSize, imgSize);
List<IntegralImage> posDatas = trainDatas.get(1);
List<IntegralImage> negDatas = trainDatas.get(0);
SparkConf sparkConf =
new SparkConf()
.setMaster(sparkMaster)
.setAppName(sparkAppName)
.set("spark.executor.memory", "3g");
JavaSparkContext sc = new JavaSparkContext(sparkConf);
sc.addJar(sparkJars);
sc.setLogLevel("WARN");
System.out.println("training cascade adaboost...");
CascadeAdaBoost cascade = new CascadeAdaBoost(posDatas, negDatas, features);
CascadeClassifier classifier =
cascade.train(sc, sparkCores, eachDR, eachFAR, finalFAR, modelFile, misclassificationFile);
System.out.println("exporting model...");
FileUtils.exportFile(modelFile, classifier.exportModel());
sc.close();
}
public static void main(String[] args) {
// Create a Spark Context.
SparkConf conf = new SparkConf().setAppName("Activity").set("spark.eventLog.enabled", "true");
;
JavaSparkContext sc = new JavaSparkContext(conf);
JavaStreamingContext jssc = new JavaStreamingContext(sc, STREAM_INTERVAL);
String TOPIC = "activityevent";
String zkQuorum = "localhost:2181";
String group = "1";
Map<String, Integer> topicMap = new HashMap<String, Integer>();
topicMap.put(TOPIC, 1);
JavaPairReceiverInputDStream<String, String> messages =
KafkaUtils.createStream(jssc, zkQuorum, group, topicMap);
// messages.print();
JavaDStream<String> activitydatastream =
messages.map(
new Function<Tuple2<String, String>, String>() {
@Override
public String call(Tuple2<String, String> tuple2) {
return tuple2._2();
}
});
final Long teamWindowDurationMs = Durations.minutes(1).milliseconds();
JavaDStream<Activity> ActivityEntryDStream = activitydatastream.map(Activity::parseFromLine);
JavaPairDStream<WithTimestamp<String>, Double> ActivityWindowDStream =
ActivityEntryDStream.mapToPair(
windows ->
new Tuple2<>(
WithTimestamp.create(
windows.getActivity(),
// Apply Fixed Window by rounding the timestamp down to the nearest
// multiple of the window size
(convertMillsecs(windows.getTimestamp()) / teamWindowDurationMs)
* teamWindowDurationMs),
windows.getXaxis()))
.reduceByKey(SUM_REDUCER);
ActivityWindowDStream.print();
jssc.start();
jssc.awaitTermination();
// jssc.close();
sc.stop();
sc.close();
}
public static void main(String[] args) {
SparkConf conf = new SparkConf().setAppName("Example_2_2").setMaster("local[2]");
JavaSparkContext sc = new JavaSparkContext(conf);
JavaRDD<String> lines = sc.parallelize(Arrays.asList("hello world", "hi"));
JavaRDD<String> words =
lines.flatMap(
new FlatMapFunction<String, String>() {
public Iterable<String> call(String line) {
return Arrays.asList(line.split(" "));
}
});
String first = words.first();
System.out.println(first);
sc.close();
}
public static void main(String[] args) {
SparkConf conf = new SparkConf().setMaster("local").setAppName("My App");
JavaSparkContext sc = new JavaSparkContext(conf);
JavaRDD<String> lines = sc.textFile("src/main/resources/data.txt");
@SuppressWarnings("serial")
JavaRDD<String> words =
lines.flatMap(
new FlatMapFunction<String, String>() {
@Override
public Iterable<String> call(String s) {
return Arrays.asList(s.split(" "));
}
});
@SuppressWarnings("serial")
JavaPairRDD<String, Integer> ones =
words.mapToPair(
new PairFunction<String, String, Integer>() {
@Override
public Tuple2<String, Integer> call(String s) {
return new Tuple2<String, Integer>(s, 1);
}
});
@SuppressWarnings("serial")
JavaPairRDD<String, Integer> counts =
ones.reduceByKey(
new Function2<Integer, Integer, Integer>() {
@Override
public Integer call(Integer i1, Integer i2) {
return i1 + i2;
}
});
List<Tuple2<String, Integer>> output = counts.collect();
for (Tuple2<?, ?> tuple : output) {
System.out.println(tuple._1() + "-> " + tuple._2());
}
sc.close();
}
public static void main(String[] args) {
SparkConf sparkconf =
new SparkConf()
.setAppName("Simple Application")
.setMaster("spark://1.245.77.10:7077")
.set(
"spark.driver.extraClassPath",
"E:/installprogram/spark-1.5.2-bin-hadoop2.4/libthirdparty/*")
.set(
"spark.executor.extraClassPath",
"E:/installprogram/spark-1.5.2-bin-hadoop2.4/libthirdparty/*")
.set("fs.default.name", "file:///");
JavaSparkContext sc = new JavaSparkContext(sparkconf);
Configuration hadoopConfig = sc.hadoopConfiguration();
hadoopConfig.set("fs.hdfs.impl", org.apache.hadoop.hdfs.DistributedFileSystem.class.getName());
hadoopConfig.set("fs.file.impl", org.apache.hadoop.fs.LocalFileSystem.class.getName());
// sc.addJar("e:/installprogram/spark-1.5.2-bin-hadoop2.4/libthirdparty/jmatrw-0.2.jar");
// sc.addJar("e:/installprogram/spark-1.5.2-bin-hadoop2.4/libthirdparty/jmatrw4spark-0.2.jar");
/*JavaRDD<Double> matrdd2 = sc.parallelize(Arrays.asList(1.0, 3.0, 2.0));
System.out.println("Start counting parallelize...");
long values = matrdd2.count();
System.out.println("Value count of parallelize is " + values);*/
JavaPairRDD<Long, Double> matrdd =
sc.newAPIHadoopFile(
"e:/tmp/vecRow03_x256.mat",
JMATFileInputFormat.class,
Long.class,
Double.class,
hadoopConfig);
System.out.println("Start job...");
long values = matrdd.count();
System.out.println("Value count of hadoop is " + values);
sc.stop();
sc.close();
}
public static void main(String[] args) {
String master = args.length > 0 ? args[0] : "local[4]";
JavaSparkContext sc = new JavaSparkContext(master, SparkSumByFold.class.getSimpleName());
JavaRDD<Integer> oddNos = sc.parallelize(Arrays.asList(1, 3, 5, 3, 7, 7, 9, 1));
JavaRDD<Integer> evenNos = sc.parallelize(Arrays.asList(2, 4, 2, 2, 2, 6, 0, 4));
JavaRDD<Integer> allNos = oddNos.union(evenNos);
System.out.println("printing all nos.");
// print the all nos.
allNos.foreach(
new VoidFunction<Integer>() {
@Override
public void call(Integer t) throws Exception {
System.out.println(t);
}
});
sc.close();
}
public static void main(String[] args) throws FileNotFoundException {
if (args.length <= 0) {
System.out.println(
"We require input file path, output file path and number of partitions argument to proceed further.");
System.out.println(
"Usage: java FarthestPair <input file path> <output file path> <noOfPartitions>");
System.exit(0);
}
String inputFile = args[0];
SparkConf conf = new SparkConf().setAppName("Group6-FarthestPair");
JavaSparkContext sc = new JavaSparkContext(conf);
// Read file as RDD
JavaRDD<String> inputData = sc.textFile(inputFile);
// JavaRDD<Coordinate> coordinates = inputData.mapPartitions(parseData);
// Map each String in the file as a coordinate object
JavaRDD<Coordinate> coordinates = inputData.map(parseData); // .repartition(noOfPartitions);
// Map to a tuple to sort the Points
JavaPairRDD<Coordinate, Boolean> pointTupleRDD =
coordinates.mapToPair(new CoordinatePairFunction());
// Sort the points
JavaPairRDD<Coordinate, Boolean> sortedPointTupleRDD =
pointTupleRDD.sortByKey(new CoordinateComparator());
// Map to points RDD
JavaRDD<Coordinate> finalSortedPointRDD =
sortedPointTupleRDD.map(new TupleToCoordinateMapFunction());
// Convert sorted collection to RDD
// Perform Convex hull operation on individual partition
JavaRDD<Coordinate> localHull = finalSortedPointRDD.mapPartitions(new hull());
// Repartition to 1 partition in order to apply 'convex hull' on all the Coordinate objects
// obtained from individual partitions
JavaRDD<Coordinate> calculatedHull = localHull.coalesce(1).cache();
// Perform Convex hull operation
JavaRDD<Coordinate> globalHull = calculatedHull.mapPartitions(new hull()).distinct();
JavaPairRDD<Coordinate, Coordinate> allCoordinateTuples = globalHull.cartesian(globalHull);
System.out.println("Total cart: " + allCoordinateTuples.collect().size());
JavaRDD<Pair> pairsRDD =
allCoordinateTuples.map(
new Function<Tuple2<Coordinate, Coordinate>, Pair>() {
public Pair call(Tuple2<Coordinate, Coordinate> tuple) throws Exception {
// TODO Auto-generated method stub
Coordinate pointA = tuple._1();
Coordinate pointB = tuple._2();
Pair a = new Pair(pointA, pointB);
return a;
}
});
JavaRDD<Pair> pairs =
allCoordinateTuples.mapPartitions(
new FlatMapFunction<Iterator<Tuple2<Coordinate, Coordinate>>, Pair>() {
/** */
private static final long serialVersionUID = 1L;
public Iterable<Pair> call(Iterator<Tuple2<Coordinate, Coordinate>> tuples)
throws Exception {
// TODO Auto-generated method stub
List<Pair> pairsFromTuples = new ArrayList<Pair>();
// Pair singlePair = new Pair();
Tuple2<Coordinate, Coordinate> tuple;
while (tuples.hasNext()) {
tuple = tuples.next();
// singlePair.A = tuples.next()._1;
// singlePair.B = tuples.next()._2;
Pair singlePair = new Pair(tuple._1(), tuple._2());
pairsFromTuples.add(singlePair);
}
return pairsFromTuples;
}
});
JavaRDD<Integer> x =
pairsRDD.mapPartitions(
new FlatMapFunction<Iterator<Pair>, Integer>() {
public Iterable<Integer> call(Iterator<Pair> arg0) throws Exception {
// TODO Auto-generated method stub
ArrayList<Integer> x = new ArrayList<Integer>();
x.add(1);
return x;
}
});
System.out.println("Num of partitions: " + x.collect());
JavaRDD<Integer> y =
pairs.mapPartitions(
new FlatMapFunction<Iterator<Pair>, Integer>() {
public Iterable<Integer> call(Iterator<Pair> arg0) throws Exception {
// TODO Auto-generated method stub
ArrayList<Integer> x = new ArrayList<Integer>();
x.add(1);
return x;
}
});
System.out.println("Num of partitions charan: " + y.collect());
Pair minDistPair =
pairs.reduce(
new Function2<Pair, Pair, Pair>() {
/** */
private static final long serialVersionUID = 1L;
public Pair call(Pair a, Pair b) throws Exception {
// TODO Auto-generated method stub
return (a.distanceLength > b.distanceLength ? a : b);
}
});
// System.out.println(minDistPair);
Coordinate closestpointA = minDistPair.A;
Coordinate closestpointB = minDistPair.B;
List<Coordinate> closestPoints = new ArrayList<Coordinate>();
closestPoints.add(closestpointA);
closestPoints.add(closestpointB);
JavaRDD<Coordinate> closestRDD = sc.parallelize(closestPoints);
// Map to a tuple to sort the Points
JavaPairRDD<Coordinate, Boolean> coordinateTupleRDD =
closestRDD.mapToPair(new CoordinatePairFunction());
// Sort the points
JavaPairRDD<Coordinate, Boolean> sortedCoordinateTupleRDD =
coordinateTupleRDD.sortByKey(new CoordinateComparator());
// Map to points RDD
JavaRDD<Coordinate> finalSortedCoordinateRDD =
sortedCoordinateTupleRDD.map(new TupleToCoordinateMapFunction());
JavaRDD<String> outputData = finalSortedCoordinateRDD.map(parseOutputData);
// closestRDD.saveAsTextFile(outputfilepath);
outputData.saveAsTextFile(args[1]);
// Output your result, you need to sort your result!!!
// And,Don't add a additional clean up step delete the new generated
// file...
sc.close();
}
public static void main(String[] args) throws IOException {
Parameters param = new Parameters();
long initTime = System.currentTimeMillis();
SparkConf conf = new SparkConf().setAppName("StarJoin");
JavaSparkContext sc = new JavaSparkContext(conf);
if (param.useKryo) {
conf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer");
conf.set("spark.kryo.registrator", MyBloomFilter.BloomFilterRegistrator.class.getName());
conf.set("spark.kryoserializer.buffer.mb", param.buffer);
}
MyBloomFilter.BloomFilter<String> BFS =
new MyBloomFilter.BloomFilter(1.0, param.bitsS, param.hashes);
MyBloomFilter.BloomFilter<String> BFD =
new MyBloomFilter.BloomFilter(1.0, param.bitsD, param.hashes);
MyBloomFilter.BloomFilter<String> BFC =
new MyBloomFilter.BloomFilter(1.0, param.bitsC, param.hashes);
JavaPairRDD<String, String> supps =
sc.textFile(param.suppPath)
.map(
new Function<String, String[]>() {
public String[] call(String line) {
return line.split("\\|");
}
})
.filter(
new Function<String[], Boolean>() {
public Boolean call(String[] s) {
return s[3].equals("UNITED KI1") | s[3].equals("UNITED KI5");
}
})
.mapToPair(
new PairFunction<String[], String, String>() {
public Tuple2<String, String> call(String[] s) {
return new Tuple2<String, String>(s[0], s[3]);
}
});
List<Tuple2<String, String>> s = supps.collect();
for (int i = 0; i < s.size(); i++) {
BFS.add(s.get(i)._1);
}
final Broadcast<MyBloomFilter.BloomFilter<String>> varS = sc.broadcast(BFS);
JavaPairRDD<String, String> custs =
sc.textFile(param.custPath)
.map(
new Function<String, String[]>() {
public String[] call(String line) {
return line.split("\\|");
}
})
.filter(
new Function<String[], Boolean>() {
public Boolean call(String[] s) {
return s[3].equals("UNITED KI1") | s[3].equals("UNITED KI5");
}
})
.mapToPair(
new PairFunction<String[], String, String>() {
public Tuple2<String, String> call(String[] s) {
return new Tuple2<String, String>(s[0], s[3]);
}
});
List<Tuple2<String, String>> c = custs.collect();
for (int i = 0; i < c.size(); i++) {
BFC.add(c.get(i)._1);
}
final Broadcast<MyBloomFilter.BloomFilter<String>> varC = sc.broadcast(BFC);
JavaPairRDD<String, String> dates =
sc.textFile(param.datePath)
.map(
new Function<String, String[]>() {
public String[] call(String line) {
return line.split("\\|");
}
})
.filter(
new Function<String[], Boolean>() {
public Boolean call(String[] s) {
return s[6].equals("Dec1997");
}
})
.mapToPair(
new PairFunction<String[], String, String>() {
public Tuple2<String, String> call(String[] s) {
return new Tuple2<String, String>(s[0], s[4]);
}
});
List<Tuple2<String, String>> d = dates.collect();
for (int i = 0; i < d.size(); i++) {
BFD.add(d.get(i)._1);
}
final Broadcast<MyBloomFilter.BloomFilter<String>> varD = sc.broadcast(BFD);
JavaPairRDD<String, String[]> lines =
sc.textFile(param.linePath)
.map(
new Function<String, String[]>() {
public String[] call(String line) {
return line.split("\\|");
}
})
.filter(
new Function<String[], Boolean>() {
public Boolean call(String[] s) {
return varC.value().contains(s[2].getBytes())
& varS.value().contains(s[4].getBytes())
& varD.value().contains(s[5].getBytes());
}
})
.mapToPair(
new PairFunction<String[], String, String[]>() {
public Tuple2<String, String[]> call(String[] s) {
String[] v = {s[2], s[5], s[12]};
return new Tuple2<String, String[]>(s[4], v);
}
});
JavaPairRDD<String, String[]> result =
lines
.join(supps)
.mapToPair(
new PairFunction<Tuple2<String, Tuple2<String[], String>>, String, String[]>() {
public Tuple2<String, String[]> call(Tuple2<String, Tuple2<String[], String>> s) {
String[] v = {s._2._1[1], s._2._1[2], s._2._2};
return new Tuple2<String, String[]>(s._2._1[0], v);
}
});
result =
result
.join(custs)
.mapToPair(
new PairFunction<Tuple2<String, Tuple2<String[], String>>, String, String[]>() {
public Tuple2<String, String[]> call(Tuple2<String, Tuple2<String[], String>> s) {
String[] v = {s._2._1[1], s._2._1[2], s._2._2};
return new Tuple2<String, String[]>(s._2._1[0], v);
}
});
JavaPairRDD<String, Long> final_result =
result
.join(dates)
.mapToPair(
new PairFunction<Tuple2<String, Tuple2<String[], String>>, String, Long>() {
public Tuple2<String, Long> call(Tuple2<String, Tuple2<String[], String>> s) {
return new Tuple2<String, Long>(
s._2._1[2] + "," + s._2._1[1] + "," + s._2._2, Long.parseLong(s._2._1[0]));
}
})
.reduceByKey(
new Function2<Long, Long, Long>() {
public Long call(Long i1, Long i2) {
return i1 + i2;
}
});
JavaPairRDD<String, String> sub_result =
final_result.mapToPair(
new PairFunction<Tuple2<String, Long>, String, String>() {
public Tuple2<String, String> call(Tuple2<String, Long> line) {
return new Tuple2(line._1 + "," + line._2.toString(), null);
}
});
final_result =
sub_result
.sortByKey(new Q3Comparator())
.mapToPair(
new PairFunction<Tuple2<String, String>, String, Long>() {
public Tuple2<String, Long> call(Tuple2<String, String> line) {
String[] s = line._1.split(",");
return new Tuple2<String, Long>(
s[0] + "," + s[1] + "," + s[2], Long.parseLong(s[3]));
}
});
Configuration HDFSconf = new Configuration();
FileSystem fs = FileSystem.get(HDFSconf);
fs.delete(new Path(param.output), true);
final_result.saveAsTextFile(param.output);
long finalTime = System.currentTimeMillis();
System.out.print("Tempo total(ms): ");
System.out.println(finalTime - initTime);
sc.close();
}
public static void main(String[] args) {
SparkConf conf = new SparkConf().setAppName("SpatialJoinQuery Application");
JavaSparkContext sc = new JavaSparkContext(conf);
// Read the input csv file holding set of polygons in a rdd of string
// objects
JavaRDD<String> firstInputPoints =
sc.textFile("hdfs://192.168.139.149:54310/harsh/spatialJoinFirstInput.csv");
// Map the above rdd of strings to a rdd of rectangles for the first
// input
// Repeat the above process but now for initializing the rdd for query
// window
JavaRDD<String> secondInputPoints =
sc.textFile("hdfs://192.168.139.149:54310/harsh/spatialJoinSecondInput.csv");
JavaRDD<Tuple2<Integer, ArrayList<Integer>>> joinQueryRDD =
new JavaRDD<Tuple2<Integer, ArrayList<Integer>>>(null, null);
if (args[0].equalsIgnoreCase("rectangle")) {
System.out.println(">>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>");
System.out.println("inside>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>");
final JavaRDD<Rectangle> firstInputRDD = firstInputPoints.map(mapInputStringToRectRDD());
System.out.println(firstInputRDD.collect());
// Map the query window to RDD object
final JavaRDD<Rectangle> secondInputRDD = secondInputPoints.map(mapInputStringToRectRDD());
// broadcast the second set of rectangles to each of the workers
final Broadcast<List<Rectangle>> firstInput = sc.broadcast(firstInputRDD.collect());
// map the id of first input to the multiple id’s of the second
// input if
// they contain the
// first rectangle.
joinQueryRDD =
secondInputRDD.map(
new Function<Rectangle, Tuple2<Integer, ArrayList<Integer>>>() {
public Tuple2<Integer, ArrayList<Integer>> call(Rectangle rectangle)
throws Exception {
// Get the list of rectangles from the second RDD input.
List<Rectangle> firstInputCollection = firstInput.value();
ArrayList<Integer> secondInputIds = new ArrayList<Integer>();
// Iterate the second input and check for the second set
// of rectangle id’s
// that hold the rectangle from first set obtained from
// the mapped RDD
for (Rectangle firstRects : firstInputCollection) {
if (rectangle.isRectangleinsideQueryWindow(firstRects)) {
secondInputIds.add(firstRects.getRectangleId());
}
}
// Create a new tuple of the mapped values and return
// back the mapped
// transformation.
Tuple2<Integer, ArrayList<Integer>> resultList =
new Tuple2<Integer, ArrayList<Integer>>(
rectangle.getRectangleId(), secondInputIds);
return resultList;
}
});
} else if (args[0].equalsIgnoreCase("point")) {
final JavaRDD<Point> firstInputRDD =
firstInputPoints.map(SpatialRangeQuery.mapInputStringToPointRDD());
// broadcast the second set of rectangles to each of the workers
final Broadcast<List<Point>> firstInput = sc.broadcast(firstInputRDD.collect());
// Map the query window to RDD object
final JavaRDD<Rectangle> secondInputRDD = secondInputPoints.map(mapInputStringToRectRDD());
joinQueryRDD =
secondInputRDD.map(
new Function<Rectangle, Tuple2<Integer, ArrayList<Integer>>>() {
public Tuple2<Integer, ArrayList<Integer>> call(Rectangle rectangle)
throws Exception {
// Get the list of rectangles from the second RDD input.
List<Point> firstInputCollection = firstInput.getValue();
ArrayList<Integer> secondInputIds = new ArrayList<Integer>();
// Iterate the second input and check for the second set
// of rectangle id’s
// that hold the rectangle from first set obtained from
// the mapped RDD
for (Point point : firstInputCollection) {
if (point.isPointinsideQueryWindow(rectangle)) {
secondInputIds.add(point.getPointID());
}
}
// Create a new tuple of the mapped values and return
// back the mapped
// transformation.
Tuple2<Integer, ArrayList<Integer>> resultList =
new Tuple2<Integer, ArrayList<Integer>>(
rectangle.getRectangleId(), secondInputIds);
return resultList;
}
});
}
JavaRDD<String> result =
joinQueryRDD.map(
new Function<Tuple2<Integer, ArrayList<Integer>>, String>() {
public String call(Tuple2<Integer, ArrayList<Integer>> inputPoint) {
Integer containingRect = inputPoint._1();
ArrayList<Integer> containedRects = inputPoint._2();
StringBuffer intermediateBuffer = new StringBuffer();
intermediateBuffer.append(containingRect);
for (Integer rects : containedRects) {
intermediateBuffer.append(", " + rects);
}
return intermediateBuffer.toString();
}
});
result.coalesce(1).saveAsTextFile("hdfs://192.168.139.149:54310/harsh/jQueryResult.csv");
sc.close();
}
