From 712f5b7a9ab52c26e3d086629633950ec2fb7afc Mon Sep 17 00:00:00 2001
From: Hossein <hossein@databricks.com>
Date: Fri, 31 Jul 2015 19:24:00 -0700
Subject: [SPARK-9318] [SPARK-9320] [SPARKR] Aliases for merge and summary
 functions on DataFrames

This PR adds synonyms for ```merge``` and ```summary``` in SparkR DataFrame API.

cc shivaram

Author: Hossein <hossein@databricks.com>

Closes #7806 from falaki/SPARK-9320 and squashes the following commits:

72600f7 [Hossein] Updated docs
92a6e75 [Hossein] Fixed merge generic signature issue
4c2b051 [Hossein] Fixing naming with mllib summary
0f3a64c [Hossein] Added ... to generic for merge
30fbaf8 [Hossein] Merged master
ae1a4cf [Hossein] Merge branch 'master' into SPARK-9320
e8eb86f [Hossein] Add a generic for merge
fc01f2d [Hossein] Added unit test
8d92012 [Hossein] Added merge as an alias for join
5b8bedc [Hossein] Added unit test
632693d [Hossein] Added summary as an alias for describe for DataFrame
---
 R/pkg/inst/tests/test_sparkSQL.R | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

(limited to 'R/pkg/inst')

diff --git a/R/pkg/inst/tests/test_sparkSQL.R b/R/pkg/inst/tests/test_sparkSQL.R
index 9faee8d59c..7377fc8f1c 100644
--- a/R/pkg/inst/tests/test_sparkSQL.R
+++ b/R/pkg/inst/tests/test_sparkSQL.R
@@ -765,7 +765,7 @@ test_that("filter() on a DataFrame", {
   expect_equal(count(filtered6), 2)
 })
 
-test_that("join() on a DataFrame", {
+test_that("join() and merge() on a DataFrame", {
   df <- jsonFile(sqlContext, jsonPath)
 
   mockLines2 <- c("{\"name\":\"Michael\", \"test\": \"yes\"}",
@@ -794,6 +794,12 @@ test_that("join() on a DataFrame", {
   expect_equal(names(joined4), c("newAge", "name", "test"))
   expect_equal(count(joined4), 4)
   expect_equal(collect(orderBy(joined4, joined4$name))$newAge[3], 24)
+
+  merged <- select(merge(df, df2, df$name == df2$name, "outer"),
+                   alias(df$age + 5, "newAge"), df$name, df2$test)
+  expect_equal(names(merged), c("newAge", "name", "test"))
+  expect_equal(count(merged), 4)
+  expect_equal(collect(orderBy(merged, joined4$name))$newAge[3], 24)
 })
 
 test_that("toJSON() returns an RDD of the correct values", {
@@ -899,7 +905,7 @@ test_that("parquetFile works with multiple input paths", {
   expect_equal(count(parquetDF), count(df) * 2)
 })
 
-test_that("describe() on a DataFrame", {
+test_that("describe() and summarize() on a DataFrame", {
   df <- jsonFile(sqlContext, jsonPath)
   stats <- describe(df, "age")
   expect_equal(collect(stats)[1, "summary"], "count")
@@ -908,6 +914,10 @@ test_that("describe() on a DataFrame", {
   stats <- describe(df)
   expect_equal(collect(stats)[4, "name"], "Andy")
   expect_equal(collect(stats)[5, "age"], "30")
+
+  stats2 <- summary(df)
+  expect_equal(collect(stats2)[4, "name"], "Andy")
+  expect_equal(collect(stats2)[5, "age"], "30")
 })
 
 test_that("dropna() on a DataFrame", {
-- 
cgit v1.2.3