Basic scaffold

Generate, read, means, write all the points

.gitignore

@@ -33,3 +33,6 @@ dependency-reduced-pom.xml
 buildNumber.properties
 .mvn/timing.properties
 .mvn/wrapper/maven-wrapper.jar
+
+# This project
+*.csv

README.md

@@ -0,0 +1,24 @@
+
+# Usage
+
+Compile job data
+
+```shell
+mvn package
+```
+
+Generate vectors to cluster
+
+```shell
+./genVectors.py $DIMENSION $NUMBER > $FILE
+```
+
+(example: `./genVectors.py 2 15 > myInput.csv`)
+
+
+
+Run
+
+```shell
+flink run target/project-*.jar --input $INPUT --output $OUTPUT
+```

genVectors.py

@@ -0,0 +1,12 @@
+#!/usr/bin/env python3
+
+import random
+import sys
+
+random.seed(0)
+
+D = int(sys.argv[1]) # Number of dimensions
+N = int(sys.argv[2]) # Number of vectors
+
+for _ in range(N):
+    print(','.join([str(random.random()) for _ in range(D)]))

pom.xml

@@ -144,7 +144,7 @@ under the License.
 							</filters>
 							<transformers>
 								<transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
-									<mainClass>it.polimi.middleware.projects.flink.StreamingJob</mainClass>
+									<mainClass>it.polimi.middleware.projects.flink.KMeans</mainClass>
 								</transformer>
 							</transformers>
 						</configuration>

src/main/java/it/polimi/middleware/projects/flink/BatchJob.java

@@ -1,66 +0,0 @@
-/*
- * Licensed to the Apache Software Foundation (ASF) under one
- * or more contributor license agreements.  See the NOTICE file
- * distributed with this work for additional information
- * regarding copyright ownership.  The ASF licenses this file
- * to you under the Apache License, Version 2.0 (the
- * "License"); you may not use this file except in compliance
- * with the License.  You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-package it.polimi.middleware.projects.flink;
-
-import org.apache.flink.api.java.ExecutionEnvironment;
-
-/**
- * Skeleton for a Flink Batch Job.
- *
- * <p>For a tutorial how to write a Flink batch application, check the
- * tutorials and examples on the <a href="http://flink.apache.org/docs/stable/">Flink Website</a>.
- *
- * <p>To package your application into a JAR file for execution,
- * change the main class in the POM.xml file to this class (simply search for 'mainClass')
- * and run 'mvn clean package' on the command line.
- */
-public class BatchJob {
-
-	public static void main(String[] args) throws Exception {
-		// set up the batch execution environment
-		final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
-
-		/*
-		 * Here, you can start creating your execution plan for Flink.
-		 *
-		 * Start with getting some data from the environment, like
-		 * 	env.readTextFile(textPath);
-		 *
-		 * then, transform the resulting DataSet<String> using operations
-		 * like
-		 * 	.filter()
-		 * 	.flatMap()
-		 * 	.join()
-		 * 	.coGroup()
-		 *
-		 * and many more.
-		 * Have a look at the programming guide for the Java API:
-		 *
-		 * http://flink.apache.org/docs/latest/apis/batch/index.html
-		 *
-		 * and the examples
-		 *
-		 * http://flink.apache.org/docs/latest/apis/batch/examples.html
-		 *
-		 */
-
-		// execute program
-		env.execute("Flink Batch Java API Skeleton");
-	}
-}

src/main/java/it/polimi/middleware/projects/flink/KMeans.java

@@ -0,0 +1,50 @@
+package it.polimi.middleware.projects.flink;
+
+import org.apache.flink.api.common.functions.MapFunction;
+import org.apache.flink.api.common.functions.ReduceFunction;
+import org.apache.flink.api.common.typeinfo.TypeHint;
+import org.apache.flink.api.common.typeinfo.TypeInformation;
+import org.apache.flink.api.java.tuple.Tuple1;
+import org.apache.flink.api.java.tuple.Tuple2;
+
+import org.apache.flink.api.java.DataSet;
+import org.apache.flink.api.java.ExecutionEnvironment;
+import org.apache.flink.api.java.utils.ParameterTool;
+
+
+public class KMeans {
+
+    public static void main(String[] args) throws Exception {
+        final ParameterTool params = ParameterTool.fromArgs(args);
+        final ExecutionEnvironment env = ExecutionEnvironment.getExecutionEnvironment();
+
+        // Read CSV input
+        DataSet<Tuple1<Double>> csvInput = env.readCsvFile(params.get("input")).types(Double.class);
+
+        // Convert CSV to internal format
+        DataSet<Double> input = csvInput
+            .map(point -> point.f0);
+
+        // DEBUG Means all the points
+        DataSet<Tuple1<Double>> mean = input
+            .map(new MapFunction<Double, Tuple2<Double, Integer>>() {
+                public Tuple2<Double, Integer> map(Double value) {
+                    return new Tuple2<Double, Integer>(value, 1);
+                }
+            })
+            .reduce(new ReduceFunction<Tuple2<Double, Integer>>() {
+                public Tuple2<Double, Integer> reduce(Tuple2<Double, Integer> a, Tuple2<Double, Integer> b) {
+                    return new Tuple2<Double, Integer>(a.f0 + b.f0, a.f1 + b.f1);
+                }
+            })
+            .map(new MapFunction<Tuple2<Double, Integer>, Tuple1<Double>>() {
+                public Tuple1<Double> map(Tuple2<Double, Integer> value) {
+                    return new Tuple1<Double>(value.f0 / value.f1);
+                }
+            });
+
+        mean.writeAsCsv(params.get("output", "output.csv"));
+
+        env.execute("K-Means clustering");
+    }
+}

src/main/java/it/polimi/middleware/projects/flink/StreamingJob.java

@@ -1,64 +0,0 @@
-/*
- * Licensed to the Apache Software Foundation (ASF) under one
- * or more contributor license agreements.  See the NOTICE file
- * distributed with this work for additional information
- * regarding copyright ownership.  The ASF licenses this file
- * to you under the Apache License, Version 2.0 (the
- * "License"); you may not use this file except in compliance
- * with the License.  You may obtain a copy of the License at
- *
- *     http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-package it.polimi.middleware.projects.flink;
-
-import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment;
-
-/**
- * Skeleton for a Flink Streaming Job.
- *
- * <p>For a tutorial how to write a Flink streaming application, check the
- * tutorials and examples on the <a href="http://flink.apache.org/docs/stable/">Flink Website</a>.
- *
- * <p>To package your application into a JAR file for execution, run
- * 'mvn clean package' on the command line.
- *
- * <p>If you change the name of the main class (with the public static void main(String[] args))
- * method, change the respective entry in the POM.xml file (simply search for 'mainClass').
- */
-public class StreamingJob {
-
-	public static void main(String[] args) throws Exception {
-		// set up the streaming execution environment
-		final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
-
-		/*
-		 * Here, you can start creating your execution plan for Flink.
-		 *
-		 * Start with getting some data from the environment, like
-		 * 	env.readTextFile(textPath);
-		 *
-		 * then, transform the resulting DataStream<String> using operations
-		 * like
-		 * 	.filter()
-		 * 	.flatMap()
-		 * 	.join()
-		 * 	.coGroup()
-		 *
-		 * and many more.
-		 * Have a look at the programming guide for the Java API:
-		 *
-		 * http://flink.apache.org/docs/latest/apis/streaming/index.html
-		 *
-		 */
-
-		// execute program
-		env.execute("Flink Streaming Java API Skeleton");
-	}
-}