small corrections in refactored examples

stratosphere-examples/stratosphere-java-examples/src/main/java/eu/stratosphere/example/java/clustering/KMeans.java

@@ -37,7 +37,7 @@ import eu.stratosphere.example.java.clustering.util.KMeansData;
  * Each point is assigned to the cluster center which is closest to it.
  * Subsequently, each cluster center is moved to the center (<i>mean</i>) of all points that have been assigned to it.
  * The moved cluster centers are fed into the next iteration. 
- * The algorithm terminates after a fixed number of iteration (as in this implementation) 
+ * The algorithm terminates after a fixed number of iterations (as in this implementation) 
  * or if cluster centers do not (significantly) move in an iteration.
  * 
  * <p>
@@ -46,7 +46,7 @@ import eu.stratosphere.example.java.clustering.util.KMeansData;
  * each data point is annotated with the id of the final cluster (center) it belongs to.
  * 
  * <p>
- * Input files are plain text files must be formatted as follows:
+ * Input files are plain text files and must be formatted as follows:
  * <ul>
  * <li>Data points are represented as two double values separated by a blank character.
  * Data points are separated by newline characters.<br>
@@ -84,7 +84,7 @@ public class KMeans {
 		// set number of bulk iterations for KMeans algorithm
 		IterativeDataSet<Centroid> loop = centroids.iterate(numIterations);
 		
-		DataSet<Centroid> newCentriods = points
+		DataSet<Centroid> newCentroids = points
 			// compute closest centroid for each point
 			.map(new SelectNearestCenter()).withBroadcastSet(loop, "centroids")
 			// count and sum point coordinates for each centroid
@@ -94,7 +94,7 @@ public class KMeans {
 			.map(new CentroidAverager());
 		
 		// feed new centroids back into next iteration
-		DataSet<Centroid> finalCentroids = loop.closeWith(newCentriods);
+		DataSet<Centroid> finalCentroids = loop.closeWith(newCentroids);
 		
 		DataSet<Tuple2<Integer, Point>> clusteredPoints = points
 				// assign points to final clusters

stratosphere-examples/stratosphere-java-examples/src/main/java/eu/stratosphere/example/java/graph/ConnectedComponents.java

@@ -29,7 +29,8 @@ import eu.stratosphere.util.Collector;
 /**
  * An implementation of the connected components algorithm, using a delta iteration.
  * Initially, the algorithm assigns each vertex its own ID. After the algorithm has completed, all vertices in the
- * same component will have the same id. In each step, a vertex 
+ * same component will have the same id. In each step, a vertex picks the minimum of its own ID and its
+ * neighbors' IDs, as its new ID.
  * <p>
  * A vertex whose component did not change needs not propagate its information in the next step. Because of that,
  * the algorithm is easily expressible via a delta iteration. We here model the solution set as the vertices with
@@ -38,9 +39,9 @@ import eu.stratosphere.util.Collector;
  * is consequently also the next workset.
  * 
  * <p>
- * Input files are plain text files must be formatted as follows:
+ * Input files are plain text files and must be formatted as follows:
  * <ul>
- * <li>Vertexes represented as IDs and separated by new-line characters.<br> 
+ * <li>Vertices represented as IDs and separated by new-line characters.<br> 
  * For example <code>"1\n2\n12\n42\n63\n"</code> gives five vertices (1), (2), (12), (42), and (63). 
  * <li>Edges are represented as pairs for vertex IDs which are separated by space 
  * characters. Edges are separated by new-line characters.<br>
@@ -79,7 +80,7 @@ public class ConnectedComponents implements ProgramDescription {
 		DeltaIteration<Tuple2<Long, Long>, Tuple2<Long, Long>> iteration =
 				verticesWithInitialId.iterateDelta(verticesWithInitialId, maxIterations, 0);
 		
-		// apply the step logic: join with the edges, select the minimum neighbor, update the component of the candidate is smaller
+		// apply the step logic: join with the edges, select the minimum neighbor, update if the component of the candidate is smaller
 		DataSet<Tuple2<Long, Long>> changes = iteration.getWorkset().join(edges).where(0).equalTo(0).with(new NeighborWithComponentIDJoin())
 				.groupBy(0).aggregate(Aggregations.MIN, 1)
 				.join(iteration.getSolutionSet()).where(0).equalTo(0)

stratosphere-examples/stratosphere-java-examples/src/main/java/eu/stratosphere/example/java/graph/EnumTrianglesBasic.java

@@ -32,7 +32,7 @@ import eu.stratosphere.util.Collector;
 
 /**
  * Triangle enumeration is a preprocessing step to find closely connected parts in graphs.
- * A triangle are three edges that connect three vertices with each other.
+ * A triangle consists of three edges that connect three vertices with each other.
  * 
  * <p>
  * The algorithm works as follows: 
@@ -41,7 +41,7 @@ import eu.stratosphere.util.Collector;
  * that closes the triangle.
  *  
  * <p>
- * Input files are plain text files must be formatted as follows:
+ * Input files are plain text files and must be formatted as follows:
  * <ul>
  * <li>Edges are represented as pairs for vertex IDs which are separated by space 
  * characters. Edges are separated by new-line characters.<br>
@@ -128,7 +128,7 @@ public class EnumTrianglesBasic {
 			
 			// flip vertices if necessary
 			if(inEdge.getFirstVertex() > inEdge.getSecondVertex()) {
-				inEdge.flipVertics();
+				inEdge.flipVertices();
 			}
 			
 			return inEdge;

stratosphere-examples/stratosphere-java-examples/src/main/java/eu/stratosphere/example/java/graph/EnumTrianglesOpt.java

@@ -35,7 +35,7 @@ import eu.stratosphere.util.Collector;
 
 /**
  * Triangle enumeration is a preprocessing step to find closely connected parts in graphs.
- * A triangle are three edges that connect three vertices with each other.
+ * A triangle consists of three edges that connect three vertices with each other.
  * 
  * <p>
  * The basic algorithm works as follows: 
@@ -51,7 +51,7 @@ import eu.stratosphere.util.Collector;
  * grouping on edges on the vertex with the smaller degree.
  * 
  * <p>
- * Input files are plain text files must be formatted as follows:
+ * Input files are plain text files and must be formatted as follows:
  * <ul>
  * <li>Edges are represented as pairs for vertex IDs which are separated by space 
  * characters. Edges are separated by new-line characters.<br>
@@ -141,7 +141,7 @@ public class EnumTrianglesOpt {
 		@Override
 		public void flatMap(Edge edge, Collector<Edge> out) throws Exception {
 			out.collect(edge);
-			edge.flipVertics();
+			edge.flipVertices();
 			out.collect(edge);
 		}
 	}
@@ -231,7 +231,7 @@ public class EnumTrianglesOpt {
 
 			// flip vertices if first degree is larger than second degree.
 			if(inEdge.getFirstDegree() > inEdge.getSecondDegree()) {
-				outEdge.flipVertics();
+				outEdge.flipVertices();
 			}
 
 			// return edge
@@ -247,7 +247,7 @@ public class EnumTrianglesOpt {
 			
 			// flip vertices if necessary
 			if(inEdge.getFirstVertex() > inEdge.getSecondVertex()) {
-				inEdge.flipVertics();
+				inEdge.flipVertices();
 			}
 			
 			return inEdge;

stratosphere-examples/stratosphere-java-examples/src/main/java/eu/stratosphere/example/java/graph/PageRankBasic.java

@@ -37,12 +37,12 @@ import eu.stratosphere.util.Collector;
  * This implementation requires a set of pages (vertices) with associated ranks and a set 
  * of directed links (edges) as input and works as follows. <br> 
  * In each iteration, the rank of every page is evenly distributed to all pages it points to.
- * Each page collects the partial ranks of all pages that point to it, sums them up, and apply a dampening factor to the sum.
+ * Each page collects the partial ranks of all pages that point to it, sums them up, and applies a dampening factor to the sum.
  * The result is the new rank of the page. A new iteration is started with the new ranks of all pages.
  * This implementation terminates after a fixed number of iterations.
  * 
  * <p>
- * Input files are plain text files must be formatted as follows:
+ * Input files are plain text files and must be formatted as follows:
  * <ul>
  * <li>Pages represented as an (long) ID and a (double) rank separated by new-line characters.<br> 
  * For example <code>"1 0.4\n2 0.3\n12 0.15\n42 0.05\n63 0.1\n"</code> gives five pages with associated ranks 

stratosphere-examples/stratosphere-java-examples/src/main/java/eu/stratosphere/example/java/graph/util/EnumTrianglesDataTypes.java

@@ -52,7 +52,7 @@ public class EnumTrianglesDataTypes {
 			this.setSecondVertex(ewd.getSecondVertex());
 		}
 		
-		public void flipVertics() {
+		public void flipVertices() {
 			Integer tmp = this.getFirstVertex();
 			this.setFirstVertex(this.getSecondVertex());
 			this.setSecondVertex(tmp);

stratosphere-examples/stratosphere-java-examples/src/main/java/eu/stratosphere/example/java/relational/TPCHQuery3.java

@@ -157,7 +157,7 @@ public class TPCHQuery3 {
 								}
 							});
 		
-		// Join the last join result with Orders
+		// Join the last join result with LineItems
 		DataSet<ShippingPriorityItem> joined = 
 				customerWithOrders.join(li)
 									.where(4)

stratosphere-examples/stratosphere-java-examples/src/main/java/eu/stratosphere/example/java/wordcount/WordCount.java

@@ -23,11 +23,11 @@ import eu.stratosphere.example.java.wordcount.util.WordCountData;
 import eu.stratosphere.util.Collector;
 
 /**
- * Implements a the "WordCount" program that computes a simple word occurrence histogram
+ * Implements the "WordCount" program that computes a simple word occurrence histogram
  * over text files. 
  * 
  * <p>
- * The input are plain text files.
+ * The input is plain text files.
  * 
  * <p>
  * This example shows how to: