update to scalding 0.14.0

README.md

@@ -36,7 +36,7 @@ Assuming you already have SBT installed:
 
 The 'fat jar' is now available as:
 
-    target/scalding-tutorial-0.13.1.jar
+    target/scalding-tutorial-0.14.0.jar
 
 ## Project structure
 
@@ -54,7 +54,7 @@ based build.
 Each part of the tutorial explains, how to run it properly. However the general
 way is always
 
-    $ yarn jar target/scalding-tutorial-0.13.1.jar <TutorialPart> --local <addtional arguments>
+    $ yarn jar target/scalding-tutorial-0.14.0.jar <TutorialPart> --local <addtional arguments>
 
 ## Copyright and license
 

project/BuildSettings.scala

@@ -18,7 +18,7 @@ object BuildSettings {
   // Basic settings for our app
   lazy val basicSettings = Seq[Setting[_]](
     organization  := "Concurrent Inc.",
-    version       := "0.13.1", // -> follow the release numbers of scalding
+    version       := "0.14.0", // -> follow the release numbers of scalding
     description   := "The scalding tutorial as an SBT project",
     scalaVersion  := "2.10.0", 
     scalacOptions := Seq("-deprecation", "-encoding", "utf8"),

project/Dependencies.scala

@@ -19,7 +19,7 @@ object Dependencies {
   )
 
   object V {
-    val scalding  = "0.13.1"
+    val scalding  = "0.14.0"
     val hadoop    = "2.6.0"
     val specs2    = "1.13" // -> "1.13" when we bump to Scala 2.10.0
     // Add versions for your additional libraries here...

src/main/scala/tutorial/AvroTutorial0.scala

@@ -2,7 +2,7 @@
 Scalding with Avro (and Json) tutorial part 0.
 
 To run this job:
-   yarn jar target/scalding-tutorial-0.13.1.jar AvroTutorial0 --local --avro --json
+   yarn jar target/scalding-tutorial-0.14.0.jar AvroTutorial0 --local --avro --json
 
 Check the output:
   java -jar avro-tools-1.7.6.jar tojson tutorial/data/avrooutput0.avro

src/main/scala/tutorial/JsonTutorial0.scala

@@ -2,7 +2,7 @@
 Scalding with Json tutorial part 0.
 
 To run this job:
-  yarn jar target/scalding-tutorial-0.13.1.jar JsonTutorial0 --local --json
+  yarn jar target/scalding-tutorial-0.14.0.jar JsonTutorial0 --local --json
 
 Check the output:
   cat target/data/jsonoutput0.tsv

src/main/scala/tutorial/MatrixTutorial0.scala

@@ -7,7 +7,7 @@ import com.twitter.scalding.mathematics.Matrix
 * Loads a directed graph adjacency matrix where a[i,j] = 1 if there is an edge from a[i] to b[j]
 * and compute the outdegree of each node i
 *
-  yarn jar target/scalding-tutorial-0.13.1.jar MatrixTutorial0 --local\
+  yarn jar target/scalding-tutorial-0.14.0.jar MatrixTutorial0 --local\
     --input data/graph.tsv \
     --output target/data/outdegree.tsv
 *

src/main/scala/tutorial/MatrixTutorial1.scala

@@ -8,7 +8,7 @@ import com.twitter.scalding.mathematics.Matrix
 * Loads a directed graph adjacency matrix where a[i,j] = 1 if there is an edge from a[i] to b[j]
 * and compute the co-follows between any two nodes 
 *
-  yarn jar target/scalding-tutorial-0.13.1.jar MatrixTutorial1 --local\
+  yarn jar target/scalding-tutorial-0.14.0.jar MatrixTutorial1 --local\
     --input data/graph.tsv --output target/data/cofollows.tsv
 *
 */

src/main/scala/tutorial/MatrixTutorial2.scala

@@ -8,7 +8,7 @@ import com.twitter.scalding.mathematics.Matrix
 * Loads a directed graph adjacency matrix where a[i,j] = 1 if there is an edge from a[i] to b[j]
 * and returns a graph containing only the nodes with outdegree smaller than a given value
 * 
-  yarn jar target/scalding-tutorial-0.13.1.jar MatrixTutorial2 --local\
+  yarn jar target/scalding-tutorial-0.14.0.jar MatrixTutorial2 --local\
     --input data/graph.tsv --maxOutdegree 1000 --output target/data/graphFiltered.tsv
 * 
 */

src/main/scala/tutorial/MatrixTutorial3.scala

@@ -8,7 +8,7 @@ import com.twitter.scalding.mathematics.Matrix
 * Loads two directed graph adjacency matrices where a[i,j] = 1 if there is an edge from a[i] to b[j]
 * and computes the intersection and the differences between the two
 * 
-  yarn jar target/scalding-tutorial-0.13.1.jar MatrixTutorial3 --local\
+  yarn jar target/scalding-tutorial-0.14.0.jar MatrixTutorial3 --local\
     --input1 data/graph.tsv --input2 data/graph2.tsv --intersection data/intersection.tsv\
     --leftDiff target/data/leftDiff.tsv --rightDiff target/data/rightDiff.tsv
 *

src/main/scala/tutorial/MatrixTutorial4.scala

@@ -8,7 +8,7 @@ import com.twitter.scalding.mathematics.Matrix
 * Loads a directed graph adjacency matrix where a[i,j] = 1 if there is an edge from a[i] to b[j]
 * and computes the cosine of the angle between every two pairs of vectors
 * 
-  yarn jar target/scalding-tutorial-0.13.1.jar MatrixTutorial4 --local\
+  yarn jar target/scalding-tutorial-0.14.0.jar MatrixTutorial4 --local\
     --input data/graph.tsv --output target/data/cosineSim.tsv
 *
 */

src/main/scala/tutorial/MatrixTutorial5.scala

@@ -8,7 +8,7 @@ import com.twitter.scalding.mathematics.Matrix
 * Loads a directed graph adjacency matrix where a[i,j] = 1 if there is an edge from a[i] to b[j]
 * and computes the jaccard similarity between any two pairs of vectors
 * 
-  yarn jar target/scalding-tutorial-0.13.1.jar MatrixTutorial5 --local\
+  yarn jar target/scalding-tutorial-0.14.0.jar MatrixTutorial5 --local\
     --input data/graph.tsv --output target/data/jaccardSim.tsv
 *
 */

src/main/scala/tutorial/MatrixTutorial6.scala

@@ -8,7 +8,7 @@ import com.twitter.scalding.mathematics.Matrix
 * computes the Tf-Idf score of each word w.r.t. to each document and keeps the top nrWords in each document
 * (see http://en.wikipedia.org/wiki/Tf*idf for more info)
 *
-  yarn jar target/scalding-tutorial-0.13.1.jar MatrixTutorial6 --local\
+  yarn jar target/scalding-tutorial-0.14.0.jar MatrixTutorial6 --local\
     --input data/docBOW.tsv --nrWords 300 --output target/data/featSelectedMatrix.tsv
 *
 */

src/main/scala/tutorial/Tutorial0.scala

@@ -25,7 +25,7 @@ To test it, from the science directory, first make sure you've built the target/
 from the base directory type:
   sbt assembly
 
-  yarn jar target/scalding-tutorial-0.13.1.jar Tutorial0 --local
+  yarn jar target/scalding-tutorial-0.14.0.jar Tutorial0 --local
 
 You can check the input:
   cat data/hello.txt

src/main/scala/tutorial/Tutorial1.scala

@@ -31,7 +31,7 @@ project() method. When we refer to a data stream's fields, we use Scala symbols,
 like this: 'line.
 
 To run this job:
-  yarn jar target/scalding-tutorial-0.13.1.jar Tutorial1 --local
+  yarn jar target/scalding-tutorial-0.14.0.jar Tutorial1 --local
 
 Check the output:
   cat target/data/output1.txt

src/main/scala/tutorial/Tutorial2.scala

@@ -22,7 +22,7 @@ In parts 0 and 1, we made copies of hello.txt. Now let's try to
 modify the copies by reversing each line.
 
 To run this job:
-  yarn jar target/scalding-tutorial-0.13.1.jar Tutorial2 --local
+  yarn jar target/scalding-tutorial-0.14.0.jar Tutorial2 --local
 
 Check the output:
   cat target/data/output2.txt

src/main/scala/tutorial/Tutorial3.scala

@@ -21,7 +21,7 @@ Scalding tutorial part 3.
 So far, we've been hardcoding the input file. Let's make that an argument,
 which changes how we run the job:
 
-  yarn jar target/scalding-tutorial-0.13.1.jar \
+  yarn jar target/scalding-tutorial-0.14.0.jar \
     Tutorial3 --local\
     --input data/hello.txt
 
@@ -32,7 +32,7 @@ Check the output:
 
 You can also of course try this with other input parameters. For example:
 
-  yarn jar target/scalding-tutorial-0.13.1.jar \
+  yarn jar target/scalding-tutorial-0.14.0.jar \
     Tutorial3 --local\
     --input target/data/output2.txt
 

src/main/scala/tutorial/Tutorial4.scala

@@ -24,7 +24,7 @@ Clearly we're ready for that most exciting of MapReduce examples, the word count
 Also, let's go ahead and make this fully general by parameterizing the output location.
 
 Run:
-  yarn jar target/scalding-tutorial-0.13.1.jar \
+  yarn jar target/scalding-tutorial-0.14.0.jar \
     Tutorial4 --local\
     --input data/hello.txt \
     --output target/data/output4.txt

src/main/scala/tutorial/Tutorial5.scala

@@ -31,7 +31,7 @@ with the words input file to get their individual ranks, then
 group by line to get a total score and output each line/score pair.
 
 Run:
-  yarn jar target/scalding-tutorial-0.13.1.jar \
+  yarn jar target/scalding-tutorial-0.14.0.jar \
     Tutorial5 --local\
     --input data/hello.txt \
     --output target/data/output5.txt \

src/main/scala/tutorial/Tutorial6.scala

@@ -21,7 +21,7 @@ Scalding tutorial part 6.
 This is similar to Tutorial1 except that we show the use of Scala Enumerations to specify fields.
 
 To run this job:
-  yarn jar target/scalding-tutorial-0.13.1.jar Tutorial6 --local 
+  yarn jar target/scalding-tutorial-0.14.0.jar Tutorial6 --local
 
 Check the output:
   cat target/data/output6.tsv

src/main/scala/tutorial/TypedTutorial.scala

@@ -10,7 +10,7 @@ These tutorials are all run from this single file; which one is run can
 be chosen with a command-line flag "--tutorial". For instance, to run the
 first tutorial example:
 
-yarn jar target/scalding-tutorial-0.13.1.jar TypedTutorial --local \
+yarn jar target/scalding-tutorial-0.14.0.jar TypedTutorial --local \
       --tutorial 0 \
       --input data/hello.txt \
       --output target/data/output0.txt \