You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@wayang.apache.org by at...@apache.org on 2021/09/05 15:19:22 UTC

[incubator-wayang] branch main updated (c64278f -> af261d9)

This is an automated email from the ASF dual-hosted git repository.

atroudi pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-wayang.git.


    from c64278f  Merge pull request #22 from apache/WAYANG-35
     add 0ed02d7  add TPC-H Query 1
     add c6f2709  feat(wordcount): add WordCount app
     add 5016d57  fix(RheemApps): set Rheem version correctly and register UDF jars in apps
     add 9afc0e0  refactor(wordcount): use stdout sink instead of collecting sink
     add ee22c38  fix(wordcount): remove target Platforms from RheemPlan
     add cffeb84  feat(kmeans): implement basic k-means
     add 2aecc6e  feat(kmeans): improve output on faulty platform
     add bd73125  test(kmeans): improve k-means test
     add 7729c96  feat(kmeans): "resurrect" lost centroids
     add 16e0485  fix(wordcount,tpch): add rheem-java JAR as UDF JAR
     add bc2eb95  Merge branch 'master' of https://github.com/daqcri/RheemApps
     add 9ce990a  chore(RheemApps): remove Flink dependencies
     add d88283a  chore(RheemApps): use Scala Maven Plugin
     add ac095e7  fix(kmeans): fix main method signature
     add 48b7257  fix(kmeans): use random cluster IDs
     add 44f850d  fix(kmeans): print out usage only if no args are passed
     add b6f1c42  fix(kmeans): annotate UDF JARs
     add 9edcdf7  feat(simwords): build tool to find similar words
     add 5511055  fix(simwords): fix sampling and main method
     add 8afea62  feat(simwords): generate centroids instead of sampling them
     add 1669fc9  feat(wordcount): add Scala implementation
     add 8e3cc36  fix(wordcount): add UDF JAR to Scala implementation
     add f0235b4  feat(crocopr): add cross-community PageRank
     add 2f818ff  feat(kmeans): make point resurrection optional
     add dd4405b  feat(RheemApps): add +spark as warmed up Spark
     add 4b3dc35  feat(rheem-core,rheem-spark,rheem-java): keep track of ChannelInstance lineage
     add 67c1e1a  feat(util): create Parameters utility class
     add 4554572  fix(util): remove optional argument from overloaded method
     add 6819fbb  feat(*): add Job names for all Scala-based apps
     add a308e91  feat(*): add optimization hints here and there
     add f2daef8  fix(kmeans): use correct UDF load function
     add e680b70  feat(simwords): improve plan
     add 7e8ad17  feat(kmeans): override CardinalityEstimator for centroid resurrection
     add c1364e2  feat(wordcount): let user specify words per line
     add d266de4  feat(simwords): improve optimization hints
     add 71a6b5a  feat(wordcount): specify selectivity of "Filter empty words"
     add a740441  feat(rheem-api): add SQL support
     add 7060bbb  feat(tpch): add Scala/HDFS implementation of TPC-H query 3
     add 866e8a1  fix(tpch): register UDF JAR
     add ab9e086  feat(tpch): add Query3Sqlite
     add 046e0d9  feat(tpch): add Query3Hybrid
     add 0662623  feat(tpch): make Query3Hybrid executable via TpcH
     add b2588eb  feat(tpch): add Record-based projection
     add 8d7ff4b  refactor(rheem): introduce plug-ins
     add eec0c17  feat(Parameters): allow yaml(...) as plugin parameter
     add 0f679d3  feat(crocopr): limit the printed page ranks
     add ff3a671  fix(util): fix StdOut.printLimited signature
     add 708ce24  refactor(rheem-graphchi): refactor module
     add ec10927  feat(*): use novel Spark/Java/Sqlite3/... objects
     add 20d30c3  refactor(rheem-basic,rheem-java,rheem-tests): use Long as vertex IDs
     add c01068e  refactor(crocopr): use pageRank(...) function
     add a5ac421  feat(util): register java-conversions as plugin name
     add 00896c6  feat(util): register spark-graph as plugin
     add 852c85d  feat(*): integrate with profiledb
     add cddf06c  feat(util): enhance experiment parameter
     add bd7f0c9  feat(crocopr): add configuration to experiment
     add b8ae5c3  feat(*): add configurations for ProfileDB
     add 10d3bf3  refactor(*): adapt to Rheem API changes
     add 54aaae1  fix(kmeans): use only a single PlanBuilder
     add 35bfd4e  feat(sindy): add Rheem-based SINDY implementation
     add 64d7f1a  chore(*): update Rheem and Scala version
     add 712d08c  chore(*): switch to stable ProfileDB version
     add fadce8d  fix(sindy): set name, experiment, and jars of job correctly
     add 0657374  refactor(*): do some adjustments according to dependencies
     add 7176a9a  feat(crocopr,simwords,wordcount): add input file size as experiment configuration
     add 051f661  feat(crocopr): add input file size as experiment configuration
     add b536725  feat(*): bounce to Rheem 0.2.1-SNAPSHOT
     add 6604581  feat(sgd): add SGD implementation as new Rheem app
     add eb81b58  improved SGD with map partitions and pre-aggregation
     add de85d5c  fix(sgd): force the sampling to be executed inside of the loop
     add 2807280  feat(sgd): allow to choose SGD implementation from command line
     add 1639f26  feat(*): enable conversion plugins for Spark, SQLite3, and PostgreSQL
     add 3dd16da  feat(simwords): allow to specify wordsPerLine confidence
     add c0aa382  feat(wordcount): allow to specify confidence of the words per line
     add e1ba7bb  feat(simwords): add UDF CPU load for the word vector creation
     add 1eba944  refactor(kmeans,simwords): tag UDF load functions via keys
     add 6341bc6  allow to use Postgres for the TPC-H queries
     add dbf47ac  add TPC-H query 1
     add abd6223  store input sizes for most apps
     add ae31c63  use pipe character to parse TPC-H files (rather than semicolon)
     add dfbb994  allow no databases in TpcH for file-based queries
     add 93e5ca5  fix parsing error in TpcH
     add 0dbab3f  fix parsing error in TpcH
     add 87f519b  feat(sindy): allow to select CSV separator
     add 507a72f  feat(tpch): allow to specify DB schema
     add 4fe6853  declare UDF jar files in SGD
     add 4b779e6  pass Experiment to SGD to obtain measurements
     add 13f13a0  feat(word2nvec): add app to turn words into vectors
     add f82ae10  feat(optimizer-scalability): add app to measure the optimizer scalability
     add 375eb5d  feat(optimizer-scalability): add plugin and plan type to experiment data
     add 9ea24e8  make SGD robust for skipped executions
     add 1dd25b6  add PostgreSQL-based version of k-means
     add 931345b  adapt command-line for PSQL-based k-means
     add 8542688  add expected number of iterations to SGD
     add 8c53770  store experiments in k-means (PostgreSQL version)
     add 7daba41  amend simplelogger.properties
     add 252600e  Create README.md
     add d6451f0  Update README.md
     add dc2feae  Update README.md
     add 2594d2b  Update README.md
     add 11f5317  Update README.md
     add 049ba53  Update README.md
     add 2e77606  Update README.md
     add 338b344  Update README.md
     add b2b8820  Update README.md
     add 732aea1  Update README.md
     add 78d38bb  rename artifactId to rheem-benchmark
     add b3b66f1  Added rheem.properties so that tests pass
     add a9ecdaf  Update README.md
     add b45fd11  Update readme
     add 5be2b58  everything to one folder
     add 58e2efa  Merge branch 'moved' into WAYANG-36
     add c7594c3  [WAYANG-36] Change name of input file to "*.input"
     add b174f9c  [WAYANG-36] Addition of the benchmark from "https://github.com/rheem-ecosystem/rheem-benchmark.git" and rebranding
     new af261d9  Merge pull request #23 from apache/WAYANG-36

The 1 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails.  The revisions
listed as "add" were already present in the repository and have only
been added to this reference.


Summary of changes:
 README.md                                          |     4 -
 pom.xml                                            |     8 +-
 wayang-benchmark/README.md                         |   128 +
 wayang-benchmark/pom.xml                           |    78 +
 .../java/org/apache/wayang/apps/sgd/SGDImpl.java   |   265 +
 .../apache/wayang/apps/sgd/SGDImprovedImpl.java    |   176 +
 .../java/org/apache/wayang/apps/tpch/Main.java     |   179 +
 .../wayang/apps/tpch/data/LineItemTuple.java       |   252 +
 .../apache/wayang/apps/tpch/data/q1/GroupKey.java  |    49 +-
 .../wayang/apps/tpch/data/q1/ReturnTuple.java      |    88 +
 .../org/apache/wayang/apps/wordcount/Main.java     |   155 +
 .../src/main/resources/simplelogger.properties     |    21 +
 .../apps/benchmark/OptimizerScalabilityTest.scala  |    79 +
 .../wayang/apps/benchmark/PlanGenerator.scala      |    96 +
 .../apps/crocopr/CreateInitialPageRanks.scala      |    23 +-
 .../org/apache/wayang/apps/crocopr/CrocoPR.scala   |   156 +
 .../org/apache/wayang/apps/kmeans/Kmeans.scala     |   258 +
 .../wayang/apps/kmeans/postgres/Kmeans.scala       |   258 +
 .../scala/org/apache/wayang/apps/sgd/SGD.scala     |    81 +
 .../wayang/apps/simwords/AddIdFunction.scala       |    21 +-
 .../simwords/CreateWordNeighborhoodFunction.scala  |    66 +
 .../apps/simwords/ResolveClusterFunction.scala     |    25 +-
 .../wayang/apps/simwords/ScrubFunction.scala       |    25 +-
 .../simwords/SelectNearestCentroidFunction.scala   |    66 +
 .../org/apache/wayang/apps/simwords/SimWords.scala |   173 +
 .../apache/wayang/apps/simwords/SparseVector.scala |   231 +
 .../apache/wayang/apps/simwords/TextScrubber.scala |    14 +-
 .../apache/wayang/apps/simwords/Word2NVec.scala    |   158 +
 .../scala/org/apache/wayang/apps/sindy/Sindy.scala |   217 +
 .../org/apache/wayang/apps/tpch/CsvUtils.scala     |    22 +-
 .../org/apache/wayang/apps/tpch/SqlUtils.scala     |    17 +-
 .../scala/org/apache/wayang/apps/tpch/TpcH.scala   |   115 +
 .../apache/wayang/apps/tpch/data/Customer.scala    |    58 +
 .../apache/wayang/apps/tpch/data/LineItem.scala    |    96 +
 .../org/apache/wayang/apps/tpch/data/Order.scala   |    72 +
 .../apache/wayang/apps/tpch/queries/Query1.scala   |   155 +
 .../wayang/apps/tpch/queries/Query3Database.scala  |   170 +
 .../wayang/apps/tpch/queries/Query3File.scala      |   155 +
 .../wayang/apps/tpch/queries/Query3Hybrid.scala    |   166 +
 .../wayang/apps/util/ExperimentDescriptor.scala    |    57 +
 .../org/apache/wayang/apps/util/Parameters.scala   |   138 +
 .../apache/wayang/apps/util/ProfileDBHelper.scala  |    50 +
 .../scala/org/apache/wayang/apps/util/StdOut.scala |    21 +-
 .../wayang/apps/wordcount/WordCountScala.scala     |   110 +
 .../wayang/apps/tpch/data/LineItemTupleTest.java   |    70 +
 .../src/test/resources/kmeans-datagenerator.py     |    56 +
 .../src/test/resources/kmeans-k4-10000.input       | 10000 +++++++++++++++++++
 .../src/test/resources/rheem.properties            |    19 +
 .../org/apache/wayang/apps/kmeans/KmeansTest.scala |    95 +
 .../apache/wayang/apps/util/ParametersTest.scala   |    88 +
 .../wayang/basic/operators/TextFileSourceTest.java |     2 +-
 .../wayang-basic/src/test/resources/ulysses.input  |     0
 .../operators/GiraphPagaRankOperatorTest.java      |     2 +-
 .../src/test/resources/test.edgelist.input}        |     0
 .../operators/GraphChiPageRankOperatorTest.java    |     2 +-
 .../src/test/resources/test.edgelist.input}        |     0
 .../java/operators/JavaObjectFileSourceTest.java   |     2 +-
 .../src/test/resources/0-to-10000.input}           |   Bin
 .../spark/operators/SparkObjectFileSourceTest.java |     2 +-
 .../src/test/resources/0-to-10000.input}           |   Bin
 .../java/org/apache/wayang/tests/WayangPlans.java  |    10 +-
 .../{lines-with-key1.txt => lines-with-key1.input} |     0
 .../{lines-with-key2.txt => lines-with-key2.input} |     0
 .../{other-lines.txt => other-lines.input}         |     0
 .../resources/{some-lines.txt => some-lines.input} |     0
 .../src/test/resources/ulysses.input               |     0
 66 files changed, 14976 insertions(+), 124 deletions(-)
 create mode 100644 wayang-benchmark/README.md
 create mode 100644 wayang-benchmark/pom.xml
 create mode 100644 wayang-benchmark/src/main/java/org/apache/wayang/apps/sgd/SGDImpl.java
 create mode 100644 wayang-benchmark/src/main/java/org/apache/wayang/apps/sgd/SGDImprovedImpl.java
 create mode 100644 wayang-benchmark/src/main/java/org/apache/wayang/apps/tpch/Main.java
 create mode 100644 wayang-benchmark/src/main/java/org/apache/wayang/apps/tpch/data/LineItemTuple.java
 copy wayang-commons/wayang-core/src/main/java/org/apache/wayang/core/util/Tuple.java => wayang-benchmark/src/main/java/org/apache/wayang/apps/tpch/data/q1/GroupKey.java (53%)
 create mode 100644 wayang-benchmark/src/main/java/org/apache/wayang/apps/tpch/data/q1/ReturnTuple.java
 create mode 100644 wayang-benchmark/src/main/java/org/apache/wayang/apps/wordcount/Main.java
 create mode 100644 wayang-benchmark/src/main/resources/simplelogger.properties
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/benchmark/OptimizerScalabilityTest.scala
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/benchmark/PlanGenerator.scala
 copy wayang-api/wayang-api-scala-java/src/main/scala/org/apache/wayang/api/graph/package.scala => wayang-benchmark/src/main/scala/org/apache/wayang/apps/crocopr/CreateInitialPageRanks.scala (53%)
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/crocopr/CrocoPR.scala
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/kmeans/Kmeans.scala
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/kmeans/postgres/Kmeans.scala
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/sgd/SGD.scala
 copy wayang-api/wayang-api-scala-java/src/main/scala/org/apache/wayang/api/graph/Edge.scala => wayang-benchmark/src/main/scala/org/apache/wayang/apps/simwords/AddIdFunction.scala (68%)
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/simwords/CreateWordNeighborhoodFunction.scala
 copy wayang-api/wayang-api-scala-java/src/main/scala/org/apache/wayang/api/graph/package.scala => wayang-benchmark/src/main/scala/org/apache/wayang/apps/simwords/ResolveClusterFunction.scala (53%)
 copy wayang-api/wayang-api-scala-java/src/main/scala/org/apache/wayang/api/graph/package.scala => wayang-benchmark/src/main/scala/org/apache/wayang/apps/simwords/ScrubFunction.scala (56%)
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/simwords/SelectNearestCentroidFunction.scala
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/simwords/SimWords.scala
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/simwords/SparseVector.scala
 copy wayang-api/wayang-api-python/src/main/java/org/apache/wayang/api/python/PythonAPI.java => wayang-benchmark/src/main/scala/org/apache/wayang/apps/simwords/TextScrubber.scala (75%)
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/simwords/Word2NVec.scala
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/sindy/Sindy.scala
 copy wayang-api/wayang-api-scala-java/src/main/scala/org/apache/wayang/api/graph/Edge.scala => wayang-benchmark/src/main/scala/org/apache/wayang/apps/tpch/CsvUtils.scala (58%)
 copy wayang-api/wayang-api-scala-java/src/main/scala/org/apache/wayang/api/graph/Edge.scala => wayang-benchmark/src/main/scala/org/apache/wayang/apps/tpch/SqlUtils.scala (67%)
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/tpch/TpcH.scala
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/tpch/data/Customer.scala
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/tpch/data/LineItem.scala
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/tpch/data/Order.scala
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/tpch/queries/Query1.scala
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/tpch/queries/Query3Database.scala
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/tpch/queries/Query3File.scala
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/tpch/queries/Query3Hybrid.scala
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/util/ExperimentDescriptor.scala
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/util/Parameters.scala
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/util/ProfileDBHelper.scala
 copy wayang-commons/wayang-basic/src/test/java/org/apache/wayang/basic/operators/test/TestSink.java => wayang-benchmark/src/main/scala/org/apache/wayang/apps/util/StdOut.scala (63%)
 create mode 100644 wayang-benchmark/src/main/scala/org/apache/wayang/apps/wordcount/WordCountScala.scala
 create mode 100644 wayang-benchmark/src/test/java/org/apache/wayang/apps/tpch/data/LineItemTupleTest.java
 create mode 100755 wayang-benchmark/src/test/resources/kmeans-datagenerator.py
 create mode 100644 wayang-benchmark/src/test/resources/kmeans-k4-10000.input
 create mode 100644 wayang-benchmark/src/test/resources/rheem.properties
 create mode 100644 wayang-benchmark/src/test/scala/org/apache/wayang/apps/kmeans/KmeansTest.scala
 create mode 100644 wayang-benchmark/src/test/scala/org/apache/wayang/apps/util/ParametersTest.scala
 rename wayang-tests-integration/src/test/resources/ulysses.txt => wayang-commons/wayang-basic/src/test/resources/ulysses.input (100%)
 rename wayang-platforms/{wayang-graphchi/src/test/resources/test.edgelist => wayang-giraph/src/test/resources/test.edgelist.input} (100%)
 rename wayang-platforms/{wayang-giraph/src/test/resources/test.edgelist => wayang-graphchi/src/test/resources/test.edgelist.input} (100%)
 rename wayang-platforms/{wayang-spark/src/test/resources/0-to-10000.sequence_file => wayang-java/src/test/resources/0-to-10000.input} (100%)
 rename wayang-platforms/{wayang-java/src/test/resources/0-to-10000.sequence_file => wayang-spark/src/test/resources/0-to-10000.input} (100%)
 rename wayang-tests-integration/src/test/resources/{lines-with-key1.txt => lines-with-key1.input} (100%)
 rename wayang-tests-integration/src/test/resources/{lines-with-key2.txt => lines-with-key2.input} (100%)
 rename wayang-tests-integration/src/test/resources/{other-lines.txt => other-lines.input} (100%)
 rename wayang-tests-integration/src/test/resources/{some-lines.txt => some-lines.input} (100%)
 rename wayang-commons/wayang-basic/src/test/resources/ulysses.txt => wayang-tests-integration/src/test/resources/ulysses.input (100%)

[incubator-wayang] 01/01: Merge pull request #23 from apache/WAYANG-36

Posted by at...@apache.org.
This is an automated email from the ASF dual-hosted git repository.

atroudi pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-wayang.git

commit af261d9dfbe89c89ca4df6c6558a6e481652ea87
Merge: c64278f b174f9c
Author: migi@ <at...@hbku.edu.qa>
AuthorDate: Sun Sep 5 18:19:18 2021 +0300

    Merge pull request #23 from apache/WAYANG-36
    
    [Wayang-36] Adding benchmarks

 README.md                                          |     4 -
 pom.xml                                            |     8 +-
 wayang-benchmark/README.md                         |   128 +
 wayang-benchmark/pom.xml                           |    78 +
 .../java/org/apache/wayang/apps/sgd/SGDImpl.java   |   265 +
 .../apache/wayang/apps/sgd/SGDImprovedImpl.java    |   176 +
 .../java/org/apache/wayang/apps/tpch/Main.java     |   179 +
 .../wayang/apps/tpch/data/LineItemTuple.java       |   252 +
 .../apache/wayang/apps/tpch/data/q1/GroupKey.java  |    54 +
 .../wayang/apps/tpch/data/q1/ReturnTuple.java      |    88 +
 .../org/apache/wayang/apps/wordcount/Main.java     |   155 +
 .../src/main/resources/simplelogger.properties     |    21 +
 .../apps/benchmark/OptimizerScalabilityTest.scala  |    79 +
 .../wayang/apps/benchmark/PlanGenerator.scala      |    96 +
 .../apps/crocopr/CreateInitialPageRanks.scala      |    40 +
 .../org/apache/wayang/apps/crocopr/CrocoPR.scala   |   156 +
 .../org/apache/wayang/apps/kmeans/Kmeans.scala     |   258 +
 .../wayang/apps/kmeans/postgres/Kmeans.scala       |   258 +
 .../scala/org/apache/wayang/apps/sgd/SGD.scala     |    81 +
 .../wayang/apps/simwords/AddIdFunction.scala       |    34 +
 .../simwords/CreateWordNeighborhoodFunction.scala  |    66 +
 .../apps/simwords/ResolveClusterFunction.scala     |    40 +
 .../wayang/apps/simwords/ScrubFunction.scala       |    42 +
 .../simwords/SelectNearestCentroidFunction.scala   |    66 +
 .../org/apache/wayang/apps/simwords/SimWords.scala |   173 +
 .../apache/wayang/apps/simwords/SparseVector.scala |   231 +
 .../apache/wayang/apps/simwords/TextScrubber.scala |    32 +
 .../apache/wayang/apps/simwords/Word2NVec.scala    |   158 +
 .../scala/org/apache/wayang/apps/sindy/Sindy.scala |   217 +
 .../org/apache/wayang/apps/tpch/CsvUtils.scala     |    41 +
 .../org/apache/wayang/apps/tpch/SqlUtils.scala     |    34 +
 .../scala/org/apache/wayang/apps/tpch/TpcH.scala   |   115 +
 .../apache/wayang/apps/tpch/data/Customer.scala    |    58 +
 .../apache/wayang/apps/tpch/data/LineItem.scala    |    96 +
 .../org/apache/wayang/apps/tpch/data/Order.scala   |    72 +
 .../apache/wayang/apps/tpch/queries/Query1.scala   |   155 +
 .../wayang/apps/tpch/queries/Query3Database.scala  |   170 +
 .../wayang/apps/tpch/queries/Query3File.scala      |   155 +
 .../wayang/apps/tpch/queries/Query3Hybrid.scala    |   166 +
 .../wayang/apps/util/ExperimentDescriptor.scala    |    57 +
 .../org/apache/wayang/apps/util/Parameters.scala   |   138 +
 .../apache/wayang/apps/util/ProfileDBHelper.scala  |    50 +
 .../scala/org/apache/wayang/apps/util/StdOut.scala |    38 +
 .../wayang/apps/wordcount/WordCountScala.scala     |   110 +
 .../wayang/apps/tpch/data/LineItemTupleTest.java   |    70 +
 .../src/test/resources/kmeans-datagenerator.py     |    56 +
 .../src/test/resources/kmeans-k4-10000.input       | 10000 +++++++++++++++++++
 .../src/test/resources/rheem.properties            |    19 +
 .../org/apache/wayang/apps/kmeans/KmeansTest.scala |    95 +
 .../apache/wayang/apps/util/ParametersTest.scala   |    88 +
 .../wayang/basic/operators/TextFileSourceTest.java |     2 +-
 .../wayang-basic/src/test/resources/ulysses.input  |     0
 .../operators/GiraphPagaRankOperatorTest.java      |     2 +-
 .../src/test/resources/test.edgelist.input}        |     0
 .../operators/GraphChiPageRankOperatorTest.java    |     2 +-
 .../src/test/resources/test.edgelist.input}        |     0
 .../java/operators/JavaObjectFileSourceTest.java   |     2 +-
 .../src/test/resources/0-to-10000.input}           |   Bin
 .../spark/operators/SparkObjectFileSourceTest.java |     2 +-
 .../src/test/resources/0-to-10000.input}           |   Bin
 .../java/org/apache/wayang/tests/WayangPlans.java  |    10 +-
 .../{lines-with-key1.txt => lines-with-key1.input} |     0
 .../{lines-with-key2.txt => lines-with-key2.input} |     0
 .../{other-lines.txt => other-lines.input}         |     0
 .../resources/{some-lines.txt => some-lines.input} |     0
 .../src/test/resources/ulysses.input               |     0
 66 files changed, 15219 insertions(+), 19 deletions(-)