Merge pull request #5 from apache/master

pull request from apache/master

Author: rekhajoshm

.gitignore

@@ -50,6 +50,7 @@ spark-tests.log
 streaming-tests.log
 dependency-reduced-pom.xml
 .ensime
+.ensime_cache/
 .ensime_lucene
 checkpoint
 derby.log
@@ -74,3 +75,7 @@ metastore/
 warehouse/
 TempStatsStore/
 sql/hive-thriftserver/test_warehouses
+
+# For R session data
+.RHistory
+.RData

.rat-excludes

@@ -15,20 +15,8 @@ TAGS
 RELEASE
 control
 docs
-docker.properties.template
-fairscheduler.xml.template
-spark-defaults.conf.template
-log4j.properties
-log4j.properties.template
-metrics.properties
-metrics.properties.template
 slaves
-slaves.template
-spark-env.sh
 spark-env.cmd
-spark-env.sh.template
-log4j-defaults.properties
-log4j-defaults-repl.properties
 bootstrap-tooltip.js
 jquery-1.11.1.min.js
 d3.min.js

LICENSE

@@ -572,3 +572,38 @@ Copyright 2009-2013 The Apache Software Foundation
 
 Apache Avro IPC
 Copyright 2009-2013 The Apache Software Foundation
+
+
+Vis.js
+Copyright 2010-2015 Almende B.V.
+
+Vis.js is dual licensed under both
+
+  * The Apache 2.0 License
+    http://www.apache.org/licenses/LICENSE-2.0
+
+    and
+
+  * The MIT License
+    http://opensource.org/licenses/MIT
+
+Vis.js may be distributed under either license.
+
+
+Vis.js uses and redistributes the following third-party libraries:
+
+- component-emitter
+  https://github.com/component/emitter
+  The MIT License
+
+- hammer.js
+  http://hammerjs.github.io/
+  The MIT License
+
+- moment.js
+  http://momentjs.com/
+  The MIT License
+
+- keycharm
+  https://github.com/AlexDM0/keycharm
+  The MIT License

NOTICE

@@ -25,3 +25,9 @@ set SPARK_HOME=%~dp0..
 MKDIR %SPARK_HOME%\R\lib
 
 R.exe CMD INSTALL --library="%SPARK_HOME%\R\lib"  %SPARK_HOME%\R\pkg\
+
+rem Zip the SparkR package so that it can be distributed to worker nodes on YARN
+pushd %SPARK_HOME%\R\lib
+%JAVA_HOME%\bin\jar.exe cfM "%SPARK_HOME%\R\lib\sparkr.zip" SparkR
+popd
+

R/install-dev.bat

@@ -42,4 +42,8 @@ Rscript -e ' if("devtools" %in% rownames(installed.packages())) { library(devtoo
 # Install SparkR to $LIB_DIR
 R CMD INSTALL --library=$LIB_DIR $FWDIR/pkg/
 
+# Zip the SparkR package so that it can be distributed to worker nodes on YARN
+cd $LIB_DIR
+jar cfM "$LIB_DIR/sparkr.zip" SparkR
+
 popd > /dev/null

R/install-dev.sh

@@ -33,4 +33,6 @@ Collate:
     'mllib.R'
     'serialize.R'
     'sparkR.R'
+    'stats.R'
+    'types.R'
     'utils.R'

R/pkg/DESCRIPTION

@@ -23,10 +23,15 @@ export("setJobGroup",
 exportClasses("DataFrame")
 
 exportMethods("arrange",
+              "as.data.frame",
+              "attach",
               "cache",
               "collect",
+              "coltypes",
               "columns",
               "count",
+              "cov",
+              "corr",
               "crosstab",
               "describe",
               "dim",
@@ -38,6 +43,7 @@ exportMethods("arrange",
               "fillna",
               "filter",
               "first",
+              "freqItems",
               "group_by",
               "groupBy",
               "head",
@@ -61,6 +67,7 @@ exportMethods("arrange",
               "repartition",
               "sample",
               "sample_frac",
+              "sampleBy",
               "saveAsParquetFile",
               "saveAsTable",
               "saveDF",
@@ -78,6 +85,7 @@ exportMethods("arrange",
               "unique",
               "unpersist",
               "where",
+              "with",
               "withColumn",
               "withColumnRenamed",
               "write.df")
@@ -90,6 +98,7 @@ exportMethods("%in%",
               "add_months",
               "alias",
               "approxCountDistinct",
+              "array_contains",
               "asc",
               "ascii",
               "asin",
@@ -104,6 +113,7 @@ exportMethods("%in%",
               "cbrt",
               "ceil",
               "ceiling",
+              "column",
               "concat",
               "concat_ws",
               "contains",
@@ -113,12 +123,14 @@ exportMethods("%in%",
               "count",
               "countDistinct",
               "crc32",
+              "cumeDist",
               "date_add",
               "date_format",
               "date_sub",
               "datediff",
               "dayofmonth",
               "dayofyear",
+              "denseRank",
               "desc",
               "endsWith",
               "exp",
@@ -144,8 +156,11 @@ exportMethods("%in%",
               "isNaN",
               "isNotNull",
               "isNull",
+              "kurtosis",
+              "lag",
               "last",
               "last_day",
+              "lead",
               "least",
               "length",
               "levenshtein",
@@ -171,17 +186,21 @@ exportMethods("%in%",
               "nanvl",
               "negate",
               "next_day",
+              "ntile",
               "otherwise",
+              "percentRank",
               "pmod",
               "quarter",
               "rand",
               "randn",
+              "rank",
               "regexp_extract",
               "regexp_replace",
               "reverse",
               "rint",
               "rlike",
               "round",
+              "rowNumber",
               "rpad",
               "rtrim",
               "second",
@@ -190,12 +209,18 @@ exportMethods("%in%",
               "shiftLeft",
               "shiftRight",
               "shiftRightUnsigned",
+              "sd",
               "sign",
               "signum",
               "sin",
               "sinh",
               "size",
+              "skewness",
+              "sort_array",
               "soundex",
+              "stddev",
+              "stddev_pop",
+              "stddev_samp",
               "sqrt",
               "startsWith",
               "substr",
@@ -214,6 +239,10 @@ exportMethods("%in%",
               "unhex",
               "unix_timestamp",
               "upper",
+              "var",
+              "variance",
+              "var_pop",
+              "var_samp",
               "weekofyear",
               "when",
               "year")
@@ -224,7 +253,8 @@ exportMethods("agg")
 export("sparkRSQL.init",
        "sparkRHive.init")
 
-export("cacheTable",
+export("as.DataFrame",
+       "cacheTable",
        "clearCache",
        "createDataFrame",
        "createExternalTable",
@@ -246,4 +276,4 @@ export("structField",
        "structType",
        "structType.jobj",
        "structType.structField",
-       "print.structType")
+       "print.structType")