spark-instrumented-optimizer/R/pkg/inst/tests/testthat/test_broadcast.R
Felix Cheung 8c198e246d [SPARK-15159][SPARKR] SparkR SparkSession API
## What changes were proposed in this pull request?

This PR introduces the new SparkSession API for SparkR.
`sparkR.session.getOrCreate()` and `sparkR.session.stop()`

"getOrCreate" is a bit unusual in R but it's important to name this clearly.

SparkR implementation should
- SparkSession is the main entrypoint (vs SparkContext; due to limited functionality supported with SparkContext in SparkR)
- SparkSession replaces SQLContext and HiveContext (both a wrapper around SparkSession, and because of API changes, supporting all 3 would be a lot more work)
- Changes to SparkSession is mostly transparent to users due to SPARK-10903
- Full backward compatibility is expected - users should be able to initialize everything just in Spark 1.6.1 (`sparkR.init()`), but with deprecation warning
- Mostly cosmetic changes to parameter list - users should be able to move to `sparkR.session.getOrCreate()` easily
- An advanced syntax with named parameters (aka varargs aka "...") is supported; that should be closer to the Builder syntax that is in Scala/Python (which unfortunately does not work in R because it will look like this: `enableHiveSupport(config(config(master(appName(builder(), "foo"), "local"), "first", "value"), "next, "value"))`
- Updating config on an existing SparkSession is supported, the behavior is the same as Python, in which config is applied to both SparkContext and SparkSession
- Some SparkSession changes are not matched in SparkR, mostly because it would be breaking API change: `catalog` object, `createOrReplaceTempView`
- Other SQLContext workarounds are replicated in SparkR, eg. `tables`, `tableNames`
- `sparkR` shell is updated to use the SparkSession entrypoint (`sqlContext` is removed, just like with Scale/Python)
- All tests are updated to use the SparkSession entrypoint
- A bug in `read.jdbc` is fixed

TODO
- [x] Add more tests
- [ ] Separate PR - update all roxygen2 doc coding example
- [ ] Separate PR - update SparkR programming guide

## How was this patch tested?

unit tests, manual tests

shivaram sun-rui rxin

Author: Felix Cheung <felixcheung_m@hotmail.com>
Author: felixcheung <felixcheung_m@hotmail.com>

Closes #13635 from felixcheung/rsparksession.
2016-06-17 21:36:01 -07:00

50 lines
1.7 KiB
R

#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements. See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
context("broadcast variables")
# JavaSparkContext handle
sparkSession <- sparkR.session()
sc <- callJStatic("org.apache.spark.sql.api.r.SQLUtils", "getJavaSparkContext", sparkSession)
# Partitioned data
nums <- 1:2
rrdd <- parallelize(sc, nums, 2L)
test_that("using broadcast variable", {
randomMat <- matrix(nrow = 10, ncol = 10, data = rnorm(100))
randomMatBr <- broadcast(sc, randomMat)
useBroadcast <- function(x) {
sum(SparkR:::value(randomMatBr) * x)
}
actual <- collect(lapply(rrdd, useBroadcast))
expected <- list(sum(randomMat) * 1, sum(randomMat) * 2)
expect_equal(actual, expected)
})
test_that("without using broadcast variable", {
randomMat <- matrix(nrow = 10, ncol = 10, data = rnorm(100))
useBroadcast <- function(x) {
sum(randomMat * x)
}
actual <- collect(lapply(rrdd, useBroadcast))
expected <- list(sum(randomMat) * 1, sum(randomMat) * 2)
expect_equal(actual, expected)
})