[SPARK-9324] [SPARK-9322] [SPARK-9321] [SPARKR] Some aliases for R-like functions in DataFrames

Adds following aliases:
* unique (distinct)
* rbind (unionAll): accepts many DataFrames
* nrow (count)
* ncol
* dim
* names (columns): along with the replacement function to change names

Author: Hossein <hossein@databricks.com>

Closes #7764 from falaki/sparkR-alias and squashes the following commits:

56016f5 [Hossein] Updated R documentation
5e4a4d0 [Hossein] Removed extra code
f51cbef [Hossein] Merge branch 'master' into sparkR-alias
c1b88bd [Hossein] Moved setGeneric and other comments applied
d9307f8 [Hossein] Added tests
b5aa988 [Hossein] Added dim, ncol, nrow, names, rbind, and unique functions to DataFrames

1 files changed, 19 insertions, 3 deletions

diff --git a/R/pkg/inst/tests/test_sparkSQL.R b/R/pkg/inst/tests/test_sparkSQL.R
index 25f697314f..9faee8d59c 100644
--- a/R/pkg/inst/tests/test_sparkSQL.R
+++ b/R/pkg/inst/tests/test_sparkSQL.R
@@ -88,6 +88,9 @@ test_that("create DataFrame from RDD", {
   df <- createDataFrame(sqlContext, rdd, list("a", "b"))
   expect_is(df, "DataFrame")
   expect_equal(count(df), 10)
+  expect_equal(nrow(df), 10)
+  expect_equal(ncol(df), 2)
+  expect_equal(dim(df), c(10, 2))
   expect_equal(columns(df), c("a", "b"))
   expect_equal(dtypes(df), list(c("a", "int"), c("b", "string")))
 
@@ -491,7 +494,7 @@ test_that("head() and first() return the correct data", {
   expect_equal(nrow(testFirst), 1)
 })
 
-test_that("distinct() on DataFrames", {
+test_that("distinct() and unique on DataFrames", {
   lines <- c("{\"name\":\"Michael\"}",
              "{\"name\":\"Andy\", \"age\":30}",
              "{\"name\":\"Justin\", \"age\":19}",
@@ -503,6 +506,10 @@ test_that("distinct() on DataFrames", {
   uniques <- distinct(df)
   expect_is(uniques, "DataFrame")
   expect_equal(count(uniques), 3)
+
+  uniques2 <- unique(df)
+  expect_is(uniques2, "DataFrame")
+  expect_equal(count(uniques2), 3)
 })
 
 test_that("sample on a DataFrame", {
@@ -815,7 +822,7 @@ test_that("isLocal()", {
   expect_false(isLocal(df))
 })
 
-test_that("unionAll(), except(), and intersect() on a DataFrame", {
+test_that("unionAll(), rbind(), except(), and intersect() on a DataFrame", {
   df <- jsonFile(sqlContext, jsonPath)
 
   lines <- c("{\"name\":\"Bob\", \"age\":24}",
@@ -830,6 +837,11 @@ test_that("unionAll(), except(), and intersect() on a DataFrame", {
   expect_equal(count(unioned), 6)
   expect_equal(first(unioned)$name, "Michael")
 
+  unioned2 <- arrange(rbind(unioned, df, df2), df$age)
+  expect_is(unioned2, "DataFrame")
+  expect_equal(count(unioned2), 12)
+  expect_equal(first(unioned2)$name, "Michael")
+
   excepted <- arrange(except(df, df2), desc(df$age))
   expect_is(unioned, "DataFrame")
   expect_equal(count(excepted), 2)
@@ -853,7 +865,7 @@ test_that("withColumn() and withColumnRenamed()", {
   expect_equal(columns(newDF2)[1], "newerAge")
 })
 
-test_that("mutate() and rename()", {
+test_that("mutate(), rename() and names()", {
   df <- jsonFile(sqlContext, jsonPath)
   newDF <- mutate(df, newAge = df$age + 2)
   expect_equal(length(columns(newDF)), 3)
@@ -863,6 +875,10 @@ test_that("mutate() and rename()", {
   newDF2 <- rename(df, newerAge = df$age)
   expect_equal(length(columns(newDF2)), 2)
   expect_equal(columns(newDF2)[1], "newerAge")
+
+  names(newDF2) <- c("newerName", "evenNewerAge")
+  expect_equal(length(names(newDF2)), 2)
+  expect_equal(names(newDF2)[1], "newerName")
 })
 
 test_that("write.df() on DataFrame and works with parquetFile", {