Merge pull request #528 from MLnick/java-examples

[SPARK-707] Adding Java versions of Pi, LogQuery and K-Means examples

5 files changed, 278 insertions, 0 deletions

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/scala/spark/examples/SparkKMeans.scala b/examples/src/main/scala/spark/examples/SparkKMeans.scala
index 7c21ea12fb..4161c59fea 100644
--- a/examples/src/main/scala/spark/examples/SparkKMeans.scala
+++ b/examples/src/main/scala/spark/examples/SparkKMeans.scala
@@ -64,6 +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/SparkPi.scala b/examples/src/main/scala/spark/examples/SparkPi.scala
index 5a31d74444..f598d2ff9c 100644
--- a/examples/src/main/scala/spark/examples/SparkPi.scala
+++ b/examples/src/main/scala/spark/examples/SparkPi.scala
@@ -4,6 +4,7 @@ import scala.math.random
 import spark._
 import SparkContext._
 
+/** Computes an approximation to pi */
 object SparkPi {
   def main(args: Array[String]) {
     if (args.length == 0) {