diff options
author | Tathagata Das <tathagata.das1565@gmail.com> | 2013-06-24 23:57:47 -0700 |
---|---|---|
committer | Tathagata Das <tathagata.das1565@gmail.com> | 2013-06-24 23:57:47 -0700 |
commit | c89af0a7f9eebce22dfe2bb4d8b1676ec7f760f6 (patch) | |
tree | 01f9f42f30a4aa2f73cb200c89a71254bf74d80e /examples/src/main | |
parent | 48c7e373c62b2e8cf48157ceb0d92c38c3a40652 (diff) | |
parent | 78ffe164b33c6b11a2e511442605acd2f795a1b5 (diff) | |
download | spark-c89af0a7f9eebce22dfe2bb4d8b1676ec7f760f6.tar.gz spark-c89af0a7f9eebce22dfe2bb4d8b1676ec7f760f6.tar.bz2 spark-c89af0a7f9eebce22dfe2bb4d8b1676ec7f760f6.zip |
Merge branch 'master' into streaming
Conflicts:
.gitignore
Diffstat (limited to 'examples/src/main')
40 files changed, 734 insertions, 164 deletions
diff --git a/examples/src/main/java/spark/examples/JavaHdfsLR.java b/examples/src/main/java/spark/examples/JavaHdfsLR.java index 29839d5668..8b0a9b6808 100644 --- a/examples/src/main/java/spark/examples/JavaHdfsLR.java +++ b/examples/src/main/java/spark/examples/JavaHdfsLR.java @@ -10,6 +10,9 @@ import java.util.Arrays; import java.util.StringTokenizer; import java.util.Random; +/** + * Logistic regression based classification. + */ public class JavaHdfsLR { static int D = 10; // Number of dimensions @@ -85,7 +88,8 @@ public class JavaHdfsLR { System.exit(1); } - JavaSparkContext sc = new JavaSparkContext(args[0], "JavaHdfsLR"); + JavaSparkContext sc = new JavaSparkContext(args[0], "JavaHdfsLR", + System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); JavaRDD<String> lines = sc.textFile(args[1]); JavaRDD<DataPoint> points = lines.map(new ParsePoint()).cache(); int ITERATIONS = Integer.parseInt(args[2]); diff --git a/examples/src/main/java/spark/examples/JavaKMeans.java b/examples/src/main/java/spark/examples/JavaKMeans.java new file mode 100644 index 0000000000..626034eb0d --- /dev/null +++ b/examples/src/main/java/spark/examples/JavaKMeans.java @@ -0,0 +1,114 @@ +package spark.examples; + +import scala.Tuple2; +import spark.api.java.JavaPairRDD; +import spark.api.java.JavaRDD; +import spark.api.java.JavaSparkContext; +import spark.api.java.function.Function; +import spark.api.java.function.PairFunction; +import spark.util.Vector; + +import java.util.List; +import java.util.Map; + +/** + * K-means clustering using Java API. + */ +public class JavaKMeans { + + /** Parses numbers split by whitespace to a vector */ + static Vector parseVector(String line) { + String[] splits = line.split(" "); + double[] data = new double[splits.length]; + int i = 0; + for (String s : splits) + data[i] = Double.parseDouble(splits[i++]); + return new Vector(data); + } + + /** Computes the vector to which the input vector is closest using squared distance */ + static int closestPoint(Vector p, List<Vector> centers) { + int bestIndex = 0; + double closest = Double.POSITIVE_INFINITY; + for (int i = 0; i < centers.size(); i++) { + double tempDist = p.squaredDist(centers.get(i)); + if (tempDist < closest) { + closest = tempDist; + bestIndex = i; + } + } + return bestIndex; + } + + /** Computes the mean across all vectors in the input set of vectors */ + static Vector average(List<Vector> ps) { + int numVectors = ps.size(); + Vector out = new Vector(ps.get(0).elements()); + // start from i = 1 since we already copied index 0 above + for (int i = 1; i < numVectors; i++) { + out.addInPlace(ps.get(i)); + } + return out.divide(numVectors); + } + + public static void main(String[] args) throws Exception { + if (args.length < 4) { + System.err.println("Usage: JavaKMeans <master> <file> <k> <convergeDist>"); + System.exit(1); + } + JavaSparkContext sc = new JavaSparkContext(args[0], "JavaKMeans", + System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + String path = args[1]; + int K = Integer.parseInt(args[2]); + double convergeDist = Double.parseDouble(args[3]); + + JavaRDD<Vector> data = sc.textFile(path).map( + new Function<String, Vector>() { + @Override + public Vector call(String line) throws Exception { + return parseVector(line); + } + } + ).cache(); + + final List<Vector> centroids = data.takeSample(false, K, 42); + + double tempDist; + do { + // allocate each vector to closest centroid + JavaPairRDD<Integer, Vector> closest = data.map( + new PairFunction<Vector, Integer, Vector>() { + @Override + public Tuple2<Integer, Vector> call(Vector vector) throws Exception { + return new Tuple2<Integer, Vector>( + closestPoint(vector, centroids), vector); + } + } + ); + + // group by cluster id and average the vectors within each cluster to compute centroids + JavaPairRDD<Integer, List<Vector>> pointsGroup = closest.groupByKey(); + Map<Integer, Vector> newCentroids = pointsGroup.mapValues( + new Function<List<Vector>, Vector>() { + public Vector call(List<Vector> ps) throws Exception { + return average(ps); + } + }).collectAsMap(); + tempDist = 0.0; + for (int i = 0; i < K; i++) { + tempDist += centroids.get(i).squaredDist(newCentroids.get(i)); + } + for (Map.Entry<Integer, Vector> t: newCentroids.entrySet()) { + centroids.set(t.getKey(), t.getValue()); + } + System.out.println("Finished iteration (delta = " + tempDist + ")"); + } while (tempDist > convergeDist); + + System.out.println("Final centers:"); + for (Vector c : centroids) + System.out.println(c); + + System.exit(0); + + } +} diff --git a/examples/src/main/java/spark/examples/JavaLogQuery.java b/examples/src/main/java/spark/examples/JavaLogQuery.java new file mode 100644 index 0000000000..6b22e7120c --- /dev/null +++ b/examples/src/main/java/spark/examples/JavaLogQuery.java @@ -0,0 +1,114 @@ +package spark.examples; + +import com.google.common.collect.Lists; +import scala.Tuple2; +import scala.Tuple3; +import spark.api.java.JavaPairRDD; +import spark.api.java.JavaRDD; +import spark.api.java.JavaSparkContext; +import spark.api.java.function.Function2; +import spark.api.java.function.PairFunction; + +import java.io.Serializable; +import java.util.Collections; +import java.util.List; +import java.util.regex.Matcher; +import java.util.regex.Pattern; + +/** + * Executes a roll up-style query against Apache logs. + */ +public class JavaLogQuery { + + public static List<String> exampleApacheLogs = Lists.newArrayList( + "10.10.10.10 - \"FRED\" [18/Jan/2013:17:56:07 +1100] \"GET http://images.com/2013/Generic.jpg " + + "HTTP/1.1\" 304 315 \"http://referall.com/\" \"Mozilla/4.0 (compatible; MSIE 7.0; " + + "Windows NT 5.1; GTB7.4; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30; .NET CLR 3.0.04506.648; " + + ".NET CLR 3.5.21022; .NET CLR 3.0.4506.2152; .NET CLR 1.0.3705; .NET CLR 1.1.4322; .NET CLR " + + "3.5.30729; Release=ARP)\" \"UD-1\" - \"image/jpeg\" \"whatever\" 0.350 \"-\" - \"\" 265 923 934 \"\" " + + "62.24.11.25 images.com 1358492167 - Whatup", + "10.10.10.10 - \"FRED\" [18/Jan/2013:18:02:37 +1100] \"GET http://images.com/2013/Generic.jpg " + + "HTTP/1.1\" 304 306 \"http:/referall.com\" \"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; " + + "GTB7.4; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30; .NET CLR 3.0.04506.648; .NET CLR " + + "3.5.21022; .NET CLR 3.0.4506.2152; .NET CLR 1.0.3705; .NET CLR 1.1.4322; .NET CLR " + + "3.5.30729; Release=ARP)\" \"UD-1\" - \"image/jpeg\" \"whatever\" 0.352 \"-\" - \"\" 256 977 988 \"\" " + + "0 73.23.2.15 images.com 1358492557 - Whatup"); + + public static Pattern apacheLogRegex = Pattern.compile( + "^([\\d.]+) (\\S+) (\\S+) \\[([\\w\\d:/]+\\s[+\\-]\\d{4})\\] \"(.+?)\" (\\d{3}) ([\\d\\-]+) \"([^\"]+)\" \"([^\"]+)\".*"); + + /** Tracks the total query count and number of aggregate bytes for a particular group. */ + public static class Stats implements Serializable { + + private int count; + private int numBytes; + + public Stats(int count, int numBytes) { + this.count = count; + this.numBytes = numBytes; + } + public Stats merge(Stats other) { + return new Stats(count + other.count, numBytes + other.numBytes); + } + + public String toString() { + return String.format("bytes=%s\tn=%s", numBytes, count); + } + } + + public static Tuple3<String, String, String> extractKey(String line) { + Matcher m = apacheLogRegex.matcher(line); + List<String> key = Collections.emptyList(); + if (m.find()) { + String ip = m.group(1); + String user = m.group(3); + String query = m.group(5); + if (!user.equalsIgnoreCase("-")) { + return new Tuple3<String, String, String>(ip, user, query); + } + } + return new Tuple3<String, String, String>(null, null, null); + } + + public static Stats extractStats(String line) { + Matcher m = apacheLogRegex.matcher(line); + if (m.find()) { + int bytes = Integer.parseInt(m.group(7)); + return new Stats(1, bytes); + } + else + return new Stats(1, 0); + } + + public static void main(String[] args) throws Exception { + if (args.length == 0) { + System.err.println("Usage: JavaLogQuery <master> [logFile]"); + System.exit(1); + } + + JavaSparkContext jsc = new JavaSparkContext(args[0], "JavaLogQuery", + System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + + JavaRDD<String> dataSet = (args.length == 2) ? jsc.textFile(args[1]) : jsc.parallelize(exampleApacheLogs); + + JavaPairRDD<Tuple3<String, String, String>, Stats> extracted = dataSet.map(new PairFunction<String, Tuple3<String, String, String>, Stats>() { + @Override + public Tuple2<Tuple3<String, String, String>, Stats> call(String s) throws Exception { + return new Tuple2<Tuple3<String, String, String>, Stats>(extractKey(s), extractStats(s)); + } + }); + + JavaPairRDD<Tuple3<String, String, String>, Stats> counts = extracted.reduceByKey(new Function2<Stats, Stats, Stats>() { + @Override + public Stats call(Stats stats, Stats stats2) throws Exception { + return stats.merge(stats2); + } + }); + + List<Tuple2<Tuple3<String, String, String>, Stats>> output = counts.collect(); + for (Tuple2 t : output) { + System.out.println(t._1 + "\t" + t._2); + } + System.exit(0); + } +} diff --git a/examples/src/main/java/spark/examples/JavaSparkPi.java b/examples/src/main/java/spark/examples/JavaSparkPi.java new file mode 100644 index 0000000000..a15a967de8 --- /dev/null +++ b/examples/src/main/java/spark/examples/JavaSparkPi.java @@ -0,0 +1,48 @@ +package spark.examples; + +import spark.api.java.JavaRDD; +import spark.api.java.JavaSparkContext; +import spark.api.java.function.Function; +import spark.api.java.function.Function2; + +import java.util.ArrayList; +import java.util.List; + +/** Computes an approximation to pi */ +public class JavaSparkPi { + + + public static void main(String[] args) throws Exception { + if (args.length == 0) { + System.err.println("Usage: JavaLogQuery <master> [slices]"); + System.exit(1); + } + + JavaSparkContext jsc = new JavaSparkContext(args[0], "JavaLogQuery", + System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); + + int slices = (args.length == 2) ? Integer.parseInt(args[1]) : 2; + int n = 100000 * slices; + List<Integer> l = new ArrayList<Integer>(n); + for (int i = 0; i < n; i++) + l.add(i); + + JavaRDD<Integer> dataSet = jsc.parallelize(l, slices); + + int count = dataSet.map(new Function<Integer, Integer>() { + @Override + public Integer call(Integer integer) throws Exception { + double x = Math.random() * 2 - 1; + double y = Math.random() * 2 - 1; + return (x * x + y * y < 1) ? 1 : 0; + } + }).reduce(new Function2<Integer, Integer, Integer>() { + @Override + public Integer call(Integer integer, Integer integer2) throws Exception { + return integer + integer2; + } + }); + + System.out.println("Pi is roughly " + 4.0 * count / n); + } +} diff --git a/examples/src/main/java/spark/examples/JavaTC.java b/examples/src/main/java/spark/examples/JavaTC.java index e3bd881b8f..b319bdab44 100644 --- a/examples/src/main/java/spark/examples/JavaTC.java +++ b/examples/src/main/java/spark/examples/JavaTC.java @@ -28,7 +28,7 @@ public class JavaTC { Tuple2<Integer, Integer> e = new Tuple2<Integer, Integer>(from, to); if (from != to) edges.add(e); } - return new ArrayList(edges); + return new ArrayList<Tuple2<Integer, Integer>>(edges); } static class ProjectFn extends PairFunction<Tuple2<Integer, Tuple2<Integer, Integer>>, @@ -46,7 +46,8 @@ public class JavaTC { System.exit(1); } - JavaSparkContext sc = new JavaSparkContext(args[0], "JavaTC"); + JavaSparkContext sc = new JavaSparkContext(args[0], "JavaTC", + System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); Integer slices = (args.length > 1) ? Integer.parseInt(args[1]): 2; JavaPairRDD<Integer, Integer> tc = sc.parallelizePairs(generateGraph(), slices).cache(); diff --git a/examples/src/main/java/spark/examples/JavaWordCount.java b/examples/src/main/java/spark/examples/JavaWordCount.java index a44cf8a120..9d4c7a252d 100644 --- a/examples/src/main/java/spark/examples/JavaWordCount.java +++ b/examples/src/main/java/spark/examples/JavaWordCount.java @@ -18,7 +18,8 @@ public class JavaWordCount { System.exit(1); } - JavaSparkContext ctx = new JavaSparkContext(args[0], "JavaWordCount"); + JavaSparkContext ctx = new JavaSparkContext(args[0], "JavaWordCount", + System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); JavaRDD<String> lines = ctx.textFile(args[1], 1); JavaRDD<String> words = lines.flatMap(new FlatMapFunction<String, String>() { @@ -29,7 +30,7 @@ public class JavaWordCount { JavaPairRDD<String, Integer> ones = words.map(new PairFunction<String, String, Integer>() { public Tuple2<String, Integer> call(String s) { - return new Tuple2(s, 1); + return new Tuple2<String, Integer>(s, 1); } }); diff --git a/examples/src/main/java/spark/streaming/examples/JavaFlumeEventCount.java b/examples/src/main/java/spark/streaming/examples/JavaFlumeEventCount.java index cddce16e39..e24c6ddaa7 100644 --- a/examples/src/main/java/spark/streaming/examples/JavaFlumeEventCount.java +++ b/examples/src/main/java/spark/streaming/examples/JavaFlumeEventCount.java @@ -32,7 +32,8 @@ public class JavaFlumeEventCount { Duration batchInterval = new Duration(2000); - JavaStreamingContext sc = new JavaStreamingContext(master, "FlumeEventCount", batchInterval); + JavaStreamingContext sc = new JavaStreamingContext(master, "FlumeEventCount", batchInterval, + System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); JavaDStream<SparkFlumeEvent> flumeStream = sc.flumeStream("localhost", port); diff --git a/examples/src/main/java/spark/streaming/examples/JavaNetworkWordCount.java b/examples/src/main/java/spark/streaming/examples/JavaNetworkWordCount.java index 0e9eadd01b..3e57580fd4 100644 --- a/examples/src/main/java/spark/streaming/examples/JavaNetworkWordCount.java +++ b/examples/src/main/java/spark/streaming/examples/JavaNetworkWordCount.java @@ -30,8 +30,8 @@ public class JavaNetworkWordCount { } // Create the context with a 1 second batch size - JavaStreamingContext ssc = new JavaStreamingContext( - args[0], "NetworkWordCount", new Duration(1000)); + JavaStreamingContext ssc = new JavaStreamingContext(args[0], "NetworkWordCount", + new Duration(1000), System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); // Create a NetworkInputDStream on target ip:port and count the // words in input stream of \n delimited test (eg. generated by 'nc') diff --git a/examples/src/main/java/spark/streaming/examples/JavaQueueStream.java b/examples/src/main/java/spark/streaming/examples/JavaQueueStream.java index 43c3cd4dfa..15b82c8da1 100644 --- a/examples/src/main/java/spark/streaming/examples/JavaQueueStream.java +++ b/examples/src/main/java/spark/streaming/examples/JavaQueueStream.java @@ -22,7 +22,8 @@ public class JavaQueueStream { } // Create the context - JavaStreamingContext ssc = new JavaStreamingContext(args[0], "QueueStream", new Duration(1000)); + JavaStreamingContext ssc = new JavaStreamingContext(args[0], "QueueStream", new Duration(1000), + System.getenv("SPARK_HOME"), System.getenv("SPARK_EXAMPLES_JAR")); // Create the queue through which RDDs can be pushed to // a QueueInputDStream diff --git a/examples/src/main/scala/spark/examples/BroadcastTest.scala b/examples/src/main/scala/spark/examples/BroadcastTest.scala index 230097c7db..ba59be1687 100644 --- a/examples/src/main/scala/spark/examples/BroadcastTest.scala +++ b/examples/src/main/scala/spark/examples/BroadcastTest.scala @@ -9,19 +9,21 @@ object BroadcastTest { System.exit(1) } - val spark = new SparkContext(args(0), "Broadcast Test") + val sc = new SparkContext(args(0), "Broadcast Test", + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) val slices = if (args.length > 1) args(1).toInt else 2 val num = if (args.length > 2) args(2).toInt else 1000000 var arr1 = new Array[Int](num) - for (i <- 0 until arr1.length) + for (i <- 0 until arr1.length) { arr1(i) = i + } for (i <- 0 until 2) { println("Iteration " + i) println("===========") - val barr1 = spark.broadcast(arr1) - spark.parallelize(1 to 10, slices).foreach { + val barr1 = sc.broadcast(arr1) + sc.parallelize(1 to 10, slices).foreach { i => println(barr1.value.size) } } diff --git a/examples/src/main/scala/spark/examples/CassandraTest.scala b/examples/src/main/scala/spark/examples/CassandraTest.scala new file mode 100644 index 0000000000..0fe1833e83 --- /dev/null +++ b/examples/src/main/scala/spark/examples/CassandraTest.scala @@ -0,0 +1,196 @@ +package spark.examples + +import org.apache.hadoop.mapreduce.Job +import org.apache.cassandra.hadoop.ColumnFamilyOutputFormat +import org.apache.cassandra.hadoop.ConfigHelper +import org.apache.cassandra.hadoop.ColumnFamilyInputFormat +import org.apache.cassandra.thrift._ +import spark.SparkContext +import spark.SparkContext._ +import java.nio.ByteBuffer +import java.util.SortedMap +import org.apache.cassandra.db.IColumn +import org.apache.cassandra.utils.ByteBufferUtil +import scala.collection.JavaConversions._ + + +/* + * This example demonstrates using Spark with Cassandra with the New Hadoop API and Cassandra + * support for Hadoop. + * + * To run this example, run this file with the following command params - + * <spark_master> <cassandra_node> <cassandra_port> + * + * So if you want to run this on localhost this will be, + * local[3] localhost 9160 + * + * The example makes some assumptions: + * 1. You have already created a keyspace called casDemo and it has a column family named Words + * 2. There are column family has a column named "para" which has test content. + * + * You can create the content by running the following script at the bottom of this file with + * cassandra-cli. + * + */ +object CassandraTest { + + def main(args: Array[String]) { + + // Get a SparkContext + val sc = new SparkContext(args(0), "casDemo") + + // Build the job configuration with ConfigHelper provided by Cassandra + val job = new Job() + job.setInputFormatClass(classOf[ColumnFamilyInputFormat]) + + val host: String = args(1) + val port: String = args(2) + + ConfigHelper.setInputInitialAddress(job.getConfiguration(), host) + ConfigHelper.setInputRpcPort(job.getConfiguration(), port) + ConfigHelper.setOutputInitialAddress(job.getConfiguration(), host) + ConfigHelper.setOutputRpcPort(job.getConfiguration(), port) + ConfigHelper.setInputColumnFamily(job.getConfiguration(), "casDemo", "Words") + ConfigHelper.setOutputColumnFamily(job.getConfiguration(), "casDemo", "WordCount") + + val predicate = new SlicePredicate() + val sliceRange = new SliceRange() + sliceRange.setStart(Array.empty[Byte]) + sliceRange.setFinish(Array.empty[Byte]) + predicate.setSlice_range(sliceRange) + ConfigHelper.setInputSlicePredicate(job.getConfiguration(), predicate) + + ConfigHelper.setInputPartitioner(job.getConfiguration(), "Murmur3Partitioner") + ConfigHelper.setOutputPartitioner(job.getConfiguration(), "Murmur3Partitioner") + + // Make a new Hadoop RDD + val casRdd = sc.newAPIHadoopRDD( + job.getConfiguration(), + classOf[ColumnFamilyInputFormat], + classOf[ByteBuffer], + classOf[SortedMap[ByteBuffer, IColumn]]) + + // Let us first get all the paragraphs from the retrieved rows + val paraRdd = casRdd.map { + case (key, value) => { + ByteBufferUtil.string(value.get(ByteBufferUtil.bytes("para")).value()) + } + } + + // Lets get the word count in paras + val counts = paraRdd.flatMap(p => p.split(" ")).map(word => (word, 1)).reduceByKey(_ + _) + + counts.collect().foreach { + case (word, count) => println(word + ":" + count) + } + + counts.map { + case (word, count) => { + val colWord = new org.apache.cassandra.thrift.Column() + colWord.setName(ByteBufferUtil.bytes("word")) + colWord.setValue(ByteBufferUtil.bytes(word)) + colWord.setTimestamp(System.currentTimeMillis) + + val colCount = new org.apache.cassandra.thrift.Column() + colCount.setName(ByteBufferUtil.bytes("wcount")) + colCount.setValue(ByteBufferUtil.bytes(count.toLong)) + colCount.setTimestamp(System.currentTimeMillis) + + val outputkey = ByteBufferUtil.bytes(word + "-COUNT-" + System.currentTimeMillis) + + val mutations: java.util.List[Mutation] = new Mutation() :: new Mutation() :: Nil + mutations.get(0).setColumn_or_supercolumn(new ColumnOrSuperColumn()) + mutations.get(0).column_or_supercolumn.setColumn(colWord) + mutations.get(1).setColumn_or_supercolumn(new ColumnOrSuperColumn()) + mutations.get(1).column_or_supercolumn.setColumn(colCount) + (outputkey, mutations) + } + }.saveAsNewAPIHadoopFile("casDemo", classOf[ByteBuffer], classOf[List[Mutation]], + classOf[ColumnFamilyOutputFormat], job.getConfiguration) + } +} + +/* +create keyspace casDemo; +use casDemo; + +create column family WordCount with comparator = UTF8Type; +update column family WordCount with column_metadata = + [{column_name: word, validation_class: UTF8Type}, + {column_name: wcount, validation_class: LongType}]; + +create column family Words with comparator = UTF8Type; +update column family Words with column_metadata = + [{column_name: book, validation_class: UTF8Type}, + {column_name: para, validation_class: UTF8Type}]; + +assume Words keys as utf8; + +set Words['3musk001']['book'] = 'The Three Musketeers'; +set Words['3musk001']['para'] = 'On the first Monday of the month of April, 1625, the market + town of Meung, in which the author of ROMANCE OF THE ROSE was born, appeared to + be in as perfect a state of revolution as if the Huguenots had just made + a second La Rochelle of it. Many citizens, seeing the women flying + toward the High Street, leaving their children crying at the open doors, + hastened to don the cuirass, and supporting their somewhat uncertain + courage with a musket or a partisan, directed their steps toward the + hostelry of the Jolly Miller, before which was gathered, increasing + every minute, a compact group, vociferous and full of curiosity.'; + +set Words['3musk002']['book'] = 'The Three Musketeers'; +set Words['3musk002']['para'] = 'In those times panics were common, and few days passed without + some city or other registering in its archives an event of this kind. There were + nobles, who made war against each other; there was the king, who made + war against the cardinal; there was Spain, which made war against the + king. Then, in addition to these concealed or public, secret or open + wars, there were robbers, mendicants, Huguenots, wolves, and scoundrels, + who made war upon everybody. The citizens always took up arms readily + against thieves, wolves or scoundrels, often against nobles or + Huguenots, sometimes against the king, but never against cardinal or + Spain. It resulted, then, from this habit that on the said first Monday + of April, 1625, the citizens, on hearing the clamor, and seeing neither + the red-and-yellow standard nor the livery of the Duc de Richelieu, + rushed toward the hostel of the Jolly Miller. When arrived there, the + cause of the hubbub was apparent to all'; + +set Words['3musk003']['book'] = 'The Three Musketeers'; +set Words['3musk003']['para'] = 'You ought, I say, then, to husband the means you have, however + large the sum may be; but you ought also to endeavor to perfect yourself in + the exercises becoming a gentleman. I will write a letter today to the + Director of the Royal Academy, and tomorrow he will admit you without + any expense to yourself. Do not refuse this little service. Our + best-born and richest gentlemen sometimes solicit it without being able + to obtain it. You will learn horsemanship, swordsmanship in all its + branches, and dancing. You will make some desirable acquaintances; and + from time to time you can call upon me, just to tell me how you are + getting on, and to say whether I can be of further service to you.'; + + +set Words['thelostworld001']['book'] = 'The Lost World'; +set Words['thelostworld001']['para'] = 'She sat with that proud, delicate profile of hers outlined + against the red curtain. How beautiful she was! And yet how aloof! We had been + friends, quite good friends; but never could I get beyond the same + comradeship which I might have established with one of my + fellow-reporters upon the Gazette,--perfectly frank, perfectly kindly, + and perfectly unsexual. My instincts are all against a woman being too + frank and at her ease with me. It is no compliment to a man. Where + the real sex feeling begins, timidity and distrust are its companions, + heritage from old wicked days when love and violence went often hand in + hand. The bent head, the averted eye, the faltering voice, the wincing + figure--these, and not the unshrinking gaze and frank reply, are the + true signals of passion. Even in my short life I had learned as much + as that--or had inherited it in that race memory which we call instinct.'; + +set Words['thelostworld002']['book'] = 'The Lost World'; +set Words['thelostworld002']['para'] = 'I always liked McArdle, the crabbed, old, round-backed, + red-headed news editor, and I rather hoped that he liked me. Of course, Beaumont was + the real boss; but he lived in the rarefied atmosphere of some Olympian + height from which he could distinguish nothing smaller than an + international crisis or a split in the Cabinet. Sometimes we saw him + passing in lonely majesty to his inner sanctum, with his eyes staring + vaguely and his mind hovering over the Balkans or the Persian Gulf. He + was above and beyond us. But McArdle was his first lieutenant, and it + was he that we knew. The old man nodded as I entered the room, and he + pushed his spectacles far up on his bald forehead.'; + +*/ diff --git a/examples/src/main/scala/spark/examples/ExceptionHandlingTest.scala b/examples/src/main/scala/spark/examples/ExceptionHandlingTest.scala index c89f3dac0c..21a90f2e5a 100644 --- a/examples/src/main/scala/spark/examples/ExceptionHandlingTest.scala +++ b/examples/src/main/scala/spark/examples/ExceptionHandlingTest.scala @@ -9,9 +9,10 @@ object ExceptionHandlingTest { System.exit(1) } - val sc = new SparkContext(args(0), "ExceptionHandlingTest") + val sc = new SparkContext(args(0), "ExceptionHandlingTest", + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) sc.parallelize(0 until sc.defaultParallelism).foreach { i => - if (Math.random > 0.75) + if (math.random > 0.75) throw new Exception("Testing exception handling") } diff --git a/examples/src/main/scala/spark/examples/GroupByTest.scala b/examples/src/main/scala/spark/examples/GroupByTest.scala index 86dfba3a40..a6603653f1 100644 --- a/examples/src/main/scala/spark/examples/GroupByTest.scala +++ b/examples/src/main/scala/spark/examples/GroupByTest.scala @@ -9,14 +9,15 @@ object GroupByTest { if (args.length == 0) { System.err.println("Usage: GroupByTest <master> [numMappers] [numKVPairs] [KeySize] [numReducers]") System.exit(1) - } + } var numMappers = if (args.length > 1) args(1).toInt else 2 var numKVPairs = if (args.length > 2) args(2).toInt else 1000 var valSize = if (args.length > 3) args(3).toInt else 1000 var numReducers = if (args.length > 4) args(4).toInt else numMappers - val sc = new SparkContext(args(0), "GroupBy Test") + val sc = new SparkContext(args(0), "GroupBy Test", + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) val pairs1 = sc.parallelize(0 until numMappers, numMappers).flatMap { p => val ranGen = new Random diff --git a/examples/src/main/scala/spark/examples/HBaseTest.scala b/examples/src/main/scala/spark/examples/HBaseTest.scala new file mode 100644 index 0000000000..6e910154d4 --- /dev/null +++ b/examples/src/main/scala/spark/examples/HBaseTest.scala @@ -0,0 +1,35 @@ +package spark.examples + +import spark._ +import spark.rdd.NewHadoopRDD +import org.apache.hadoop.hbase.{HBaseConfiguration, HTableDescriptor} +import org.apache.hadoop.hbase.client.HBaseAdmin +import org.apache.hadoop.hbase.mapreduce.TableInputFormat + +object HBaseTest { + def main(args: Array[String]) { + val sc = new SparkContext(args(0), "HBaseTest", + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + + val conf = HBaseConfiguration.create() + + // Other options for configuring scan behavior are available. More information available at + // http://hbase.apache.org/apidocs/org/apache/hadoop/hbase/mapreduce/TableInputFormat.html + conf.set(TableInputFormat.INPUT_TABLE, args(1)) + + // Initialize hBase table if necessary + val admin = new HBaseAdmin(conf) + if(!admin.isTableAvailable(args(1))) { + val tableDesc = new HTableDescriptor(args(1)) + admin.createTable(tableDesc) + } + + val hBaseRDD = sc.newAPIHadoopRDD(conf, classOf[TableInputFormat], + classOf[org.apache.hadoop.hbase.io.ImmutableBytesWritable], + classOf[org.apache.hadoop.hbase.client.Result]) + + hBaseRDD.count() + + System.exit(0) + } +}
\ No newline at end of file diff --git a/examples/src/main/scala/spark/examples/HdfsTest.scala b/examples/src/main/scala/spark/examples/HdfsTest.scala index 7a4530609d..dd61c467f7 100644 --- a/examples/src/main/scala/spark/examples/HdfsTest.scala +++ b/examples/src/main/scala/spark/examples/HdfsTest.scala @@ -4,7 +4,8 @@ import spark._ object HdfsTest { def main(args: Array[String]) { - val sc = new SparkContext(args(0), "HdfsTest") + val sc = new SparkContext(args(0), "HdfsTest", + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) val file = sc.textFile(args(1)) val mapped = file.map(s => s.length).cache() for (iter <- 1 to 10) { diff --git a/examples/src/main/scala/spark/examples/LocalALS.scala b/examples/src/main/scala/spark/examples/LocalALS.scala index 10e03359c9..2de810e062 100644 --- a/examples/src/main/scala/spark/examples/LocalALS.scala +++ b/examples/src/main/scala/spark/examples/LocalALS.scala @@ -1,11 +1,13 @@ package spark.examples -import java.util.Random import scala.math.sqrt import cern.jet.math._ import cern.colt.matrix._ import cern.colt.matrix.linalg._ +/** + * Alternating least squares matrix factorization. + */ object LocalALS { // Parameters set through command line arguments var M = 0 // Number of movies diff --git a/examples/src/main/scala/spark/examples/LocalKMeans.scala b/examples/src/main/scala/spark/examples/LocalKMeans.scala index b442c604cd..4849f216fb 100644 --- a/examples/src/main/scala/spark/examples/LocalKMeans.scala +++ b/examples/src/main/scala/spark/examples/LocalKMeans.scala @@ -6,74 +6,77 @@ import spark.SparkContext._ import scala.collection.mutable.HashMap import scala.collection.mutable.HashSet +/** + * K-means clustering. + */ object LocalKMeans { - val N = 1000 - val R = 1000 // Scaling factor - val D = 10 - val K = 10 - val convergeDist = 0.001 - val rand = new Random(42) - - def generateData = { - def generatePoint(i: Int) = { - Vector(D, _ => rand.nextDouble * R) - } - Array.tabulate(N)(generatePoint) - } - - def closestPoint(p: Vector, centers: HashMap[Int, Vector]): Int = { - var index = 0 - var bestIndex = 0 - var closest = Double.PositiveInfinity - - for (i <- 1 to centers.size) { - val vCurr = centers.get(i).get - val tempDist = p.squaredDist(vCurr) - if (tempDist < closest) { - closest = tempDist - bestIndex = i - } - } - - return bestIndex - } - - def main(args: Array[String]) { - val data = generateData - var points = new HashSet[Vector] - var kPoints = new HashMap[Int, Vector] - var tempDist = 1.0 - - while (points.size < K) { - points.add(data(rand.nextInt(N))) - } - - val iter = points.iterator - for (i <- 1 to points.size) { - kPoints.put(i, iter.next()) - } - - println("Initial centers: " + kPoints) - - while(tempDist > convergeDist) { - var closest = data.map (p => (closestPoint(p, kPoints), (p, 1))) - - var mappings = closest.groupBy[Int] (x => x._1) - - var pointStats = mappings.map(pair => pair._2.reduceLeft [(Int, (Vector, Int))] {case ((id1, (x1, y1)), (id2, (x2, y2))) => (id1, (x1 + x2, y1+y2))}) - - var newPoints = pointStats.map {mapping => (mapping._1, mapping._2._1/mapping._2._2)} - - tempDist = 0.0 - for (mapping <- newPoints) { - tempDist += kPoints.get(mapping._1).get.squaredDist(mapping._2) - } - - for (newP <- newPoints) { - kPoints.put(newP._1, newP._2) - } - } - - println("Final centers: " + kPoints) - } + val N = 1000 + val R = 1000 // Scaling factor + val D = 10 + val K = 10 + val convergeDist = 0.001 + val rand = new Random(42) + + def generateData = { + def generatePoint(i: Int) = { + Vector(D, _ => rand.nextDouble * R) + } + Array.tabulate(N)(generatePoint) + } + + def closestPoint(p: Vector, centers: HashMap[Int, Vector]): Int = { + var index = 0 + var bestIndex = 0 + var closest = Double.PositiveInfinity + + for (i <- 1 to centers.size) { + val vCurr = centers.get(i).get + val tempDist = p.squaredDist(vCurr) + if (tempDist < closest) { + closest = tempDist + bestIndex = i + } + } + + return bestIndex + } + + def main(args: Array[String]) { + val data = generateData + var points = new HashSet[Vector] + var kPoints = new HashMap[Int, Vector] + var tempDist = 1.0 + + while (points.size < K) { + points.add(data(rand.nextInt(N))) + } + + val iter = points.iterator + for (i <- 1 to points.size) { + kPoints.put(i, iter.next()) + } + + println("Initial centers: " + kPoints) + + while(tempDist > convergeDist) { + var closest = data.map (p => (closestPoint(p, kPoints), (p, 1))) + + var mappings = closest.groupBy[Int] (x => x._1) + + var pointStats = mappings.map(pair => pair._2.reduceLeft [(Int, (Vector, Int))] {case ((id1, (x1, y1)), (id2, (x2, y2))) => (id1, (x1 + x2, y1+y2))}) + + var newPoints = pointStats.map {mapping => (mapping._1, mapping._2._1/mapping._2._2)} + + tempDist = 0.0 + for (mapping <- newPoints) { + tempDist += kPoints.get(mapping._1).get.squaredDist(mapping._2) + } + + for (newP <- newPoints) { + kPoints.put(newP._1, newP._2) + } + } + + println("Final centers: " + kPoints) + } } diff --git a/examples/src/main/scala/spark/examples/LocalLR.scala b/examples/src/main/scala/spark/examples/LocalLR.scala index 9553162004..cd73f553d6 100644 --- a/examples/src/main/scala/spark/examples/LocalLR.scala +++ b/examples/src/main/scala/spark/examples/LocalLR.scala @@ -3,6 +3,9 @@ package spark.examples import java.util.Random import spark.util.Vector +/** + * Logistic regression based classification. + */ object LocalLR { val N = 10000 // Number of data points val D = 10 // Number of dimensions diff --git a/examples/src/main/scala/spark/examples/LogQuery.scala b/examples/src/main/scala/spark/examples/LogQuery.scala index 5330b8da94..6497596d35 100644 --- a/examples/src/main/scala/spark/examples/LogQuery.scala +++ b/examples/src/main/scala/spark/examples/LogQuery.scala @@ -26,7 +26,9 @@ object LogQuery { System.err.println("Usage: LogQuery <master> [logFile]") System.exit(1) } - val sc = new SparkContext(args(0), "Log Query") + + val sc = new SparkContext(args(0), "Log Query", + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) val dataSet = if (args.length == 2) sc.textFile(args(1)) diff --git a/examples/src/main/scala/spark/examples/MultiBroadcastTest.scala b/examples/src/main/scala/spark/examples/MultiBroadcastTest.scala index 83ae014e94..a0aaf60918 100644 --- a/examples/src/main/scala/spark/examples/MultiBroadcastTest.scala +++ b/examples/src/main/scala/spark/examples/MultiBroadcastTest.scala @@ -8,25 +8,29 @@ object MultiBroadcastTest { System.err.println("Usage: BroadcastTest <master> [<slices>] [numElem]") System.exit(1) } - - val spark = new SparkContext(args(0), "Broadcast Test") + + val sc = new SparkContext(args(0), "Broadcast Test", + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + val slices = if (args.length > 1) args(1).toInt else 2 val num = if (args.length > 2) args(2).toInt else 1000000 var arr1 = new Array[Int](num) - for (i <- 0 until arr1.length) + for (i <- 0 until arr1.length) { arr1(i) = i - + } + var arr2 = new Array[Int](num) - for (i <- 0 until arr2.length) + for (i <- 0 until arr2.length) { arr2(i) = i + } - val barr1 = spark.broadcast(arr1) - val barr2 = spark.broadcast(arr2) - spark.parallelize(1 to 10, slices).foreach { + val barr1 = sc.broadcast(arr1) + val barr2 = sc.broadcast(arr2) + sc.parallelize(1 to 10, slices).foreach { i => println(barr1.value.size + barr2.value.size) } - + System.exit(0) } } diff --git a/examples/src/main/scala/spark/examples/SimpleSkewedGroupByTest.scala b/examples/src/main/scala/spark/examples/SimpleSkewedGroupByTest.scala index 50b3a263b4..461b84a2c6 100644 --- a/examples/src/main/scala/spark/examples/SimpleSkewedGroupByTest.scala +++ b/examples/src/main/scala/spark/examples/SimpleSkewedGroupByTest.scala @@ -11,15 +11,16 @@ object SimpleSkewedGroupByTest { "[numMappers] [numKVPairs] [valSize] [numReducers] [ratio]") System.exit(1) } - + var numMappers = if (args.length > 1) args(1).toInt else 2 var numKVPairs = if (args.length > 2) args(2).toInt else 1000 var valSize = if (args.length > 3) args(3).toInt else 1000 var numReducers = if (args.length > 4) args(4).toInt else numMappers var ratio = if (args.length > 5) args(5).toInt else 5.0 - val sc = new SparkContext(args(0), "GroupBy Test") - + val sc = new SparkContext(args(0), "GroupBy Test", + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + val pairs1 = sc.parallelize(0 until numMappers, numMappers).flatMap { p => val ranGen = new Random var result = new Array[(Int, Array[Byte])](numKVPairs) diff --git a/examples/src/main/scala/spark/examples/SkewedGroupByTest.scala b/examples/src/main/scala/spark/examples/SkewedGroupByTest.scala index d2117a263e..435675f9de 100644 --- a/examples/src/main/scala/spark/examples/SkewedGroupByTest.scala +++ b/examples/src/main/scala/spark/examples/SkewedGroupByTest.scala @@ -10,19 +10,20 @@ object SkewedGroupByTest { System.err.println("Usage: GroupByTest <master> [numMappers] [numKVPairs] [KeySize] [numReducers]") System.exit(1) } - + var numMappers = if (args.length > 1) args(1).toInt else 2 var numKVPairs = if (args.length > 2) args(2).toInt else 1000 var valSize = if (args.length > 3) args(3).toInt else 1000 var numReducers = if (args.length > 4) args(4).toInt else numMappers - val sc = new SparkContext(args(0), "GroupBy Test") - + val sc = new SparkContext(args(0), "GroupBy Test", + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) + val pairs1 = sc.parallelize(0 until numMappers, numMappers).flatMap { p => val ranGen = new Random // map output sizes lineraly increase from the 1st to the last - numKVPairs = (1. * (p + 1) / numMappers * numKVPairs).toInt + numKVPairs = (1.0 * (p + 1) / numMappers * numKVPairs).toInt var arr1 = new Array[(Int, Array[Byte])](numKVPairs) for (i <- 0 until numKVPairs) { @@ -31,11 +32,11 @@ object SkewedGroupByTest { arr1(i) = (ranGen.nextInt(Int.MaxValue), byteArr) } arr1 - }.cache + }.cache() // Enforce that everything has been calculated and in cache - pairs1.count + pairs1.count() - println(pairs1.groupByKey(numReducers).count) + println(pairs1.groupByKey(numReducers).count()) System.exit(0) } diff --git a/examples/src/main/scala/spark/examples/SparkALS.scala b/examples/src/main/scala/spark/examples/SparkALS.scala index 5e01885dbb..8fb3b0fb2a 100644 --- a/examples/src/main/scala/spark/examples/SparkALS.scala +++ b/examples/src/main/scala/spark/examples/SparkALS.scala @@ -1,14 +1,14 @@ package spark.examples -import java.io.Serializable -import java.util.Random import scala.math.sqrt import cern.jet.math._ import cern.colt.matrix._ import cern.colt.matrix.linalg._ import spark._ -import scala.Option +/** + * Alternating least squares matrix factorization. + */ object SparkALS { // Parameters set through command line arguments var M = 0 // Number of movies @@ -70,30 +70,32 @@ object SparkALS { } def main(args: Array[String]) { + if (args.length == 0) { + System.err.println("Usage: SparkALS <master> [<M> <U> <F> <iters> <slices>]") + System.exit(1) + } + var host = "" var slices = 0 - (0 to 5).map(i => { - i match { - case a if a < args.length => Some(args(a)) - case _ => None - } - }).toArray match { - case Array(host_, m, u, f, iters, slices_) => { - host = host_ getOrElse "local" - M = (m getOrElse "100").toInt - U = (u getOrElse "500").toInt - F = (f getOrElse "10").toInt - ITERATIONS = (iters getOrElse "5").toInt - slices = (slices_ getOrElse "2").toInt - } - case _ => { - System.err.println("Usage: SparkALS [<master> <M> <U> <F> <iters> <slices>]") + val options = (0 to 5).map(i => if (i < args.length) Some(args(i)) else None) + + options.toArray match { + case Array(host_, m, u, f, iters, slices_) => + host = host_.get + M = m.getOrElse("100").toInt + U = u.getOrElse("500").toInt + F = f.getOrElse("10").toInt + ITERATIONS = iters.getOrElse("5").toInt + slices = slices_.getOrElse("2").toInt + case _ => + System.err.println("Usage: SparkALS <master> [<M> <U> <F> <iters> <slices>]") System.exit(1) - } } printf("Running with M=%d, U=%d, F=%d, iters=%d\n", M, U, F, ITERATIONS) - val spark = new SparkContext(host, "SparkALS") + + val sc = new SparkContext(host, "SparkALS", + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) val R = generateR() @@ -102,19 +104,19 @@ object SparkALS { var us = Array.fill(U)(factory1D.random(F)) // Iteratively update movies then users - val Rc = spark.broadcast(R) - var msc = spark.broadcast(ms) - var usc = spark.broadcast(us) + val Rc = sc.broadcast(R) + var msb = sc.broadcast(ms) + var usb = sc.broadcast(us) for (iter <- 1 to ITERATIONS) { println("Iteration " + iter + ":") - ms = spark.parallelize(0 until M, slices) - .map(i => update(i, msc.value(i), usc.value, Rc.value)) + ms = sc.parallelize(0 until M, slices) + .map(i => update(i, msb.value(i), usb.value, Rc.value)) .toArray - msc = spark.broadcast(ms) // Re-broadcast ms because it was updated - us = spark.parallelize(0 until U, slices) - .map(i => update(i, usc.value(i), msc.value, algebra.transpose(Rc.value))) + msb = sc.broadcast(ms) // Re-broadcast ms because it was updated + us = sc.parallelize(0 until U, slices) + .map(i => update(i, usb.value(i), msb.value, algebra.transpose(Rc.value))) .toArray - usc = spark.broadcast(us) // Re-broadcast us because it was updated + usb = sc.broadcast(us) // Re-broadcast us because it was updated println("RMSE = " + rmse(R, ms, us)) println() } diff --git a/examples/src/main/scala/spark/examples/SparkHdfsLR.scala b/examples/src/main/scala/spark/examples/SparkHdfsLR.scala index 5b2bc84d69..3d080a0257 100644 --- a/examples/src/main/scala/spark/examples/SparkHdfsLR.scala +++ b/examples/src/main/scala/spark/examples/SparkHdfsLR.scala @@ -4,7 +4,12 @@ import java.util.Random import scala.math.exp import spark.util.Vector import spark._ +import spark.deploy.SparkHadoopUtil +import spark.scheduler.InputFormatInfo +/** + * Logistic regression based classification. + */ object SparkHdfsLR { val D = 10 // Numer of dimensions val rand = new Random(42) @@ -29,8 +34,13 @@ object SparkHdfsLR { System.err.println("Usage: SparkHdfsLR <master> <file> <iters>") System.exit(1) } - val sc = new SparkContext(args(0), "SparkHdfsLR") - val lines = sc.textFile(args(1)) + val inputPath = args(1) + val conf = SparkHadoopUtil.newConfiguration() + val sc = new SparkContext(args(0), "SparkHdfsLR", + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR")), Map(), + InputFormatInfo.computePreferredLocations( + Seq(new InputFormatInfo(conf, classOf[org.apache.hadoop.mapred.TextInputFormat], inputPath)))) + val lines = sc.textFile(inputPath) val points = lines.map(parsePoint _).cache() val ITERATIONS = args(2).toInt diff --git a/examples/src/main/scala/spark/examples/SparkKMeans.scala b/examples/src/main/scala/spark/examples/SparkKMeans.scala index 6375961390..4161c59fea 100644 --- a/examples/src/main/scala/spark/examples/SparkKMeans.scala +++ b/examples/src/main/scala/spark/examples/SparkKMeans.scala @@ -7,6 +7,9 @@ import spark.SparkContext._ import scala.collection.mutable.HashMap import scala.collection.mutable.HashSet +/** + * K-means clustering. + */ object SparkKMeans { val R = 1000 // Scaling factor val rand = new Random(42) @@ -36,7 +39,8 @@ object SparkKMeans { System.err.println("Usage: SparkLocalKMeans <master> <file> <k> <convergeDist>") System.exit(1) } - val sc = new SparkContext(args(0), "SparkLocalKMeans") + val sc = new SparkContext(args(0), "SparkLocalKMeans", + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) val lines = sc.textFile(args(1)) val data = lines.map(parseVector _).cache() val K = args(2).toInt @@ -60,6 +64,7 @@ object SparkKMeans { for (newP <- newPoints) { kPoints(newP._1) = newP._2 } + println("Finished iteration (delta = " + tempDist + ")") } println("Final centers:") diff --git a/examples/src/main/scala/spark/examples/SparkLR.scala b/examples/src/main/scala/spark/examples/SparkLR.scala index aaaf062c8f..2f41aeb376 100644 --- a/examples/src/main/scala/spark/examples/SparkLR.scala +++ b/examples/src/main/scala/spark/examples/SparkLR.scala @@ -5,6 +5,9 @@ import scala.math.exp import spark.util.Vector import spark._ +/** + * Logistic regression based classification. + */ object SparkLR { val N = 10000 // Number of data points val D = 10 // Numer of dimensions @@ -28,7 +31,8 @@ object SparkLR { System.err.println("Usage: SparkLR <master> [<slices>]") System.exit(1) } - val sc = new SparkContext(args(0), "SparkLR") + val sc = new SparkContext(args(0), "SparkLR", + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) val numSlices = if (args.length > 1) args(1).toInt else 2 val points = sc.parallelize(generateData, numSlices).cache() diff --git a/examples/src/main/scala/spark/examples/SparkPi.scala b/examples/src/main/scala/spark/examples/SparkPi.scala index 2f226f1380..f598d2ff9c 100644 --- a/examples/src/main/scala/spark/examples/SparkPi.scala +++ b/examples/src/main/scala/spark/examples/SparkPi.scala @@ -4,13 +4,15 @@ import scala.math.random import spark._ import SparkContext._ +/** Computes an approximation to pi */ object SparkPi { def main(args: Array[String]) { if (args.length == 0) { System.err.println("Usage: SparkPi <master> [<slices>]") System.exit(1) } - val spark = new SparkContext(args(0), "SparkPi") + val spark = new SparkContext(args(0), "SparkPi", + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) val slices = if (args.length > 1) args(1).toInt else 2 val n = 100000 * slices val count = spark.parallelize(1 to n, slices).map { i => diff --git a/examples/src/main/scala/spark/examples/SparkTC.scala b/examples/src/main/scala/spark/examples/SparkTC.scala index 90bae011ad..911ae8f168 100644 --- a/examples/src/main/scala/spark/examples/SparkTC.scala +++ b/examples/src/main/scala/spark/examples/SparkTC.scala @@ -9,7 +9,6 @@ import scala.collection.mutable * Transitive closure on a graph. */ object SparkTC { - val numEdges = 200 val numVertices = 100 val rand = new Random(42) @@ -29,7 +28,8 @@ object SparkTC { System.err.println("Usage: SparkTC <master> [<slices>]") System.exit(1) } - val spark = new SparkContext(args(0), "SparkTC") + val spark = new SparkContext(args(0), "SparkTC", + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) val slices = if (args.length > 1) args(1).toInt else 2 var tc = spark.parallelize(generateGraph, slices).cache() diff --git a/examples/src/main/scala/spark/streaming/examples/ActorWordCount.scala b/examples/src/main/scala/spark/streaming/examples/ActorWordCount.scala index 76293fbb96..3b847fe603 100644 --- a/examples/src/main/scala/spark/streaming/examples/ActorWordCount.scala +++ b/examples/src/main/scala/spark/streaming/examples/ActorWordCount.scala @@ -131,7 +131,8 @@ object ActorWordCount { val Seq(master, host, port) = args.toSeq // Create the context and set the batch size - val ssc = new StreamingContext(master, "ActorWordCount", Seconds(2)) + val ssc = new StreamingContext(master, "ActorWordCount", Seconds(2), + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) /* * Following is the use of actorStream to plug in custom actor as receiver diff --git a/examples/src/main/scala/spark/streaming/examples/FlumeEventCount.scala b/examples/src/main/scala/spark/streaming/examples/FlumeEventCount.scala index 461929fba2..39c76fd98a 100644 --- a/examples/src/main/scala/spark/streaming/examples/FlumeEventCount.scala +++ b/examples/src/main/scala/spark/streaming/examples/FlumeEventCount.scala @@ -30,7 +30,8 @@ object FlumeEventCount { val batchInterval = Milliseconds(2000) // Create the context and set the batch size - val ssc = new StreamingContext(master, "FlumeEventCount", batchInterval) + val ssc = new StreamingContext(master, "FlumeEventCount", batchInterval, + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) // Create a flume stream val stream = ssc.flumeStream(host,port,StorageLevel.MEMORY_ONLY) diff --git a/examples/src/main/scala/spark/streaming/examples/HdfsWordCount.scala b/examples/src/main/scala/spark/streaming/examples/HdfsWordCount.scala index 8530f5c175..9389f8a38d 100644 --- a/examples/src/main/scala/spark/streaming/examples/HdfsWordCount.scala +++ b/examples/src/main/scala/spark/streaming/examples/HdfsWordCount.scala @@ -22,7 +22,8 @@ object HdfsWordCount { } // Create the context - val ssc = new StreamingContext(args(0), "HdfsWordCount", Seconds(2)) + val ssc = new StreamingContext(args(0), "HdfsWordCount", Seconds(2), + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) // Create the FileInputDStream on the directory and use the // stream to count words in new files created diff --git a/examples/src/main/scala/spark/streaming/examples/KafkaWordCount.scala b/examples/src/main/scala/spark/streaming/examples/KafkaWordCount.scala index e0c3555f21..9202e65e09 100644 --- a/examples/src/main/scala/spark/streaming/examples/KafkaWordCount.scala +++ b/examples/src/main/scala/spark/streaming/examples/KafkaWordCount.scala @@ -32,8 +32,8 @@ object KafkaWordCount { val Array(master, zkQuorum, group, topics, numThreads) = args - val sc = new SparkContext(master, "KafkaWordCount") - val ssc = new StreamingContext(sc, Seconds(2)) + val ssc = new StreamingContext(master, "KafkaWordCount", Seconds(2), + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) ssc.checkpoint("checkpoint") val topicpMap = topics.split(",").map((_,numThreads.toInt)).toMap diff --git a/examples/src/main/scala/spark/streaming/examples/NetworkWordCount.scala b/examples/src/main/scala/spark/streaming/examples/NetworkWordCount.scala index 5ac6d19b34..704540c2bf 100644 --- a/examples/src/main/scala/spark/streaming/examples/NetworkWordCount.scala +++ b/examples/src/main/scala/spark/streaming/examples/NetworkWordCount.scala @@ -23,7 +23,8 @@ object NetworkWordCount { } // Create the context with a 1 second batch size - val ssc = new StreamingContext(args(0), "NetworkWordCount", Seconds(1)) + val ssc = new StreamingContext(args(0), "NetworkWordCount", Seconds(1), + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) // Create a NetworkInputDStream on target ip:port and count the // words in input stream of \n delimited test (eg. generated by 'nc') diff --git a/examples/src/main/scala/spark/streaming/examples/QueueStream.scala b/examples/src/main/scala/spark/streaming/examples/QueueStream.scala index 2a265d021d..f450e21040 100644 --- a/examples/src/main/scala/spark/streaming/examples/QueueStream.scala +++ b/examples/src/main/scala/spark/streaming/examples/QueueStream.scala @@ -15,7 +15,8 @@ object QueueStream { } // Create the context - val ssc = new StreamingContext(args(0), "QueueStream", Seconds(1)) + val ssc = new StreamingContext(args(0), "QueueStream", Seconds(1), + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) // Create the queue through which RDDs can be pushed to // a QueueInputDStream @@ -30,10 +31,10 @@ object QueueStream { // Create and push some RDDs into for (i <- 1 to 30) { - rddQueue += ssc.sc.makeRDD(1 to 1000, 10) + rddQueue += ssc.sparkContext.makeRDD(1 to 1000, 10) Thread.sleep(1000) } ssc.stop() System.exit(0) } -}
\ No newline at end of file +} diff --git a/examples/src/main/scala/spark/streaming/examples/RawNetworkGrep.scala b/examples/src/main/scala/spark/streaming/examples/RawNetworkGrep.scala index 66e709b7a3..175281e095 100644 --- a/examples/src/main/scala/spark/streaming/examples/RawNetworkGrep.scala +++ b/examples/src/main/scala/spark/streaming/examples/RawNetworkGrep.scala @@ -31,10 +31,11 @@ object RawNetworkGrep { val Array(master, IntParam(numStreams), host, IntParam(port), IntParam(batchMillis)) = args // Create the context - val ssc = new StreamingContext(master, "RawNetworkGrep", Milliseconds(batchMillis)) + val ssc = new StreamingContext(master, "RawNetworkGrep", Milliseconds(batchMillis), + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) // Warm up the JVMs on master and slave for JIT compilation to kick in - RawTextHelper.warmUp(ssc.sc) + RawTextHelper.warmUp(ssc.sparkContext) val rawStreams = (1 to numStreams).map(_ => ssc.rawSocketStream[String](host, port, StorageLevel.MEMORY_ONLY_SER_2)).toArray diff --git a/examples/src/main/scala/spark/streaming/examples/TwitterAlgebirdCMS.scala b/examples/src/main/scala/spark/streaming/examples/TwitterAlgebirdCMS.scala index 39a1a702ee..a9642100e3 100644 --- a/examples/src/main/scala/spark/streaming/examples/TwitterAlgebirdCMS.scala +++ b/examples/src/main/scala/spark/streaming/examples/TwitterAlgebirdCMS.scala @@ -43,12 +43,13 @@ object TwitterAlgebirdCMS { val Array(master, username, password) = args.slice(0, 3) val filters = args.slice(3, args.length) - val ssc = new StreamingContext(master, "TwitterAlgebirdCMS", Seconds(10)) + val ssc = new StreamingContext(master, "TwitterAlgebirdCMS", Seconds(10), + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) val stream = ssc.twitterStream(username, password, filters, StorageLevel.MEMORY_ONLY_SER) val users = stream.map(status => status.getUser.getId) - val cms = new CountMinSketchMonoid(DELTA, EPS, SEED, PERC) + val cms = new CountMinSketchMonoid(EPS, DELTA, SEED, PERC) var globalCMS = cms.zero val mm = new MapMonoid[Long, Int]() var globalExact = Map[Long, Int]() diff --git a/examples/src/main/scala/spark/streaming/examples/TwitterAlgebirdHLL.scala b/examples/src/main/scala/spark/streaming/examples/TwitterAlgebirdHLL.scala index 914fba4ca2..f3288bfb85 100644 --- a/examples/src/main/scala/spark/streaming/examples/TwitterAlgebirdHLL.scala +++ b/examples/src/main/scala/spark/streaming/examples/TwitterAlgebirdHLL.scala @@ -32,7 +32,8 @@ object TwitterAlgebirdHLL { val Array(master, username, password) = args.slice(0, 3) val filters = args.slice(3, args.length) - val ssc = new StreamingContext(master, "TwitterAlgebirdHLL", Seconds(5)) + val ssc = new StreamingContext(master, "TwitterAlgebirdHLL", Seconds(5), + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) val stream = ssc.twitterStream(username, password, filters, StorageLevel.MEMORY_ONLY_SER) val users = stream.map(status => status.getUser.getId) diff --git a/examples/src/main/scala/spark/streaming/examples/TwitterPopularTags.scala b/examples/src/main/scala/spark/streaming/examples/TwitterPopularTags.scala index fdb3a4c73c..9d4494c6f2 100644 --- a/examples/src/main/scala/spark/streaming/examples/TwitterPopularTags.scala +++ b/examples/src/main/scala/spark/streaming/examples/TwitterPopularTags.scala @@ -21,7 +21,8 @@ object TwitterPopularTags { val Array(master, username, password) = args.slice(0, 3) val filters = args.slice(3, args.length) - val ssc = new StreamingContext(master, "TwitterPopularTags", Seconds(2)) + val ssc = new StreamingContext(master, "TwitterPopularTags", Seconds(2), + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) val stream = ssc.twitterStream(username, password, filters) val hashTags = stream.flatMap(status => status.getText.split(" ").filter(_.startsWith("#"))) diff --git a/examples/src/main/scala/spark/streaming/examples/ZeroMQWordCount.scala b/examples/src/main/scala/spark/streaming/examples/ZeroMQWordCount.scala index 5ed9b7cb76..74d0d338b7 100644 --- a/examples/src/main/scala/spark/streaming/examples/ZeroMQWordCount.scala +++ b/examples/src/main/scala/spark/streaming/examples/ZeroMQWordCount.scala @@ -58,7 +58,8 @@ object ZeroMQWordCount { val Seq(master, url, topic) = args.toSeq // Create the context and set the batch size - val ssc = new StreamingContext(master, "ZeroMQWordCount", Seconds(2)) + val ssc = new StreamingContext(master, "ZeroMQWordCount", Seconds(2), + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) def bytesToStringIterator(x: Seq[Seq[Byte]]) = (x.map(x => new String(x.toArray))).iterator @@ -70,4 +71,4 @@ object ZeroMQWordCount { ssc.start() } -}
\ No newline at end of file +} diff --git a/examples/src/main/scala/spark/streaming/examples/clickstream/PageViewStream.scala b/examples/src/main/scala/spark/streaming/examples/clickstream/PageViewStream.scala index fba72519a9..e226a4a73a 100644 --- a/examples/src/main/scala/spark/streaming/examples/clickstream/PageViewStream.scala +++ b/examples/src/main/scala/spark/streaming/examples/clickstream/PageViewStream.scala @@ -24,7 +24,8 @@ object PageViewStream { val port = args(2).toInt // Create the context - val ssc = new StreamingContext("local[2]", "PageViewStream", Seconds(1)) + val ssc = new StreamingContext("local[2]", "PageViewStream", Seconds(1), + System.getenv("SPARK_HOME"), Seq(System.getenv("SPARK_EXAMPLES_JAR"))) // Create a NetworkInputDStream on target host:port and convert each line to a PageView val pageViews = ssc.socketTextStream(host, port) @@ -60,7 +61,7 @@ object PageViewStream { .map("Unique active users: " + _) // An external dataset we want to join to this stream - val userList = ssc.sc.parallelize( + val userList = ssc.sparkContext.parallelize( Map(1 -> "Patrick Wendell", 2->"Reynold Xin", 3->"Matei Zaharia").toSeq) metric match { |