Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/916#discussion_r13691382
--- Diff: core/src/test/scala/org/apache/spark/rdd/RDDSuite.scala ---
@@ -498,55 +501,56 @@ class RDDSuite extends FunSuite with
SharedSparkContext {
}
test("takeSample") {
- val data = sc.parallelize(1 to 100, 2)
+ val n = 1000000
+ val data = sc.parallelize(1 to n, 2)
for (num <- List(5, 20, 100)) {
val sample = data.takeSample(withReplacement=false, num=num)
assert(sample.size === num) // Got exactly num elements
assert(sample.toSet.size === num) // Elements are distinct
- assert(sample.forall(x => 1 <= x && x <= 100), "elements not in [1,
100]")
+ assert(sample.forall(x => 1 <= x && x <= n), s"elements not in [1,
$n]")
}
for (seed <- 1 to 5) {
val sample = data.takeSample(withReplacement=false, 20, seed)
assert(sample.size === 20) // Got exactly 20 elements
assert(sample.toSet.size === 20) // Elements are distinct
- assert(sample.forall(x => 1 <= x && x <= 100), "elements not in [1,
100]")
+ assert(sample.forall(x => 1 <= x && x <= n), s"elements not in [1,
$n]")
}
for (seed <- 1 to 5) {
- val sample = data.takeSample(withReplacement=false, 200, seed)
+ val sample = data.takeSample(withReplacement=false, 100, seed)
assert(sample.size === 100) // Got only 100 elements
assert(sample.toSet.size === 100) // Elements are distinct
- assert(sample.forall(x => 1 <= x && x <= 100), "elements not in [1,
100]")
+ assert(sample.forall(x => 1 <= x && x <= n), s"elements not in [1,
$n]")
}
for (seed <- 1 to 5) {
val sample = data.takeSample(withReplacement=true, 20, seed)
assert(sample.size === 20) // Got exactly 20 elements
- assert(sample.forall(x => 1 <= x && x <= 100), "elements not in [1,
100]")
+ assert(sample.forall(x => 1 <= x && x <= n), s"elements not in [1,
$n]")
}
{
val sample = data.takeSample(withReplacement=true, num=20)
assert(sample.size === 20) // Got exactly 100 elements
assert(sample.toSet.size <= 20, "sampling with replacement returned
all distinct elements")
- assert(sample.forall(x => 1 <= x && x <= 100), "elements not in [1,
100]")
+ assert(sample.forall(x => 1 <= x && x <= n), s"elements not in [1,
$n]")
}
{
- val sample = data.takeSample(withReplacement=true, num=100)
- assert(sample.size === 100) // Got exactly 100 elements
+ val sample = data.takeSample(withReplacement=true, num=n)
+ assert(sample.size === n) // Got exactly 100 elements
// Chance of getting all distinct elements is astronomically low, so
test we got < 100
- assert(sample.toSet.size < 100, "sampling with replacement returned
all distinct elements")
- assert(sample.forall(x => 1 <= x && x <= 100), "elements not in [1,
100]")
+ assert(sample.toSet.size < n, "sampling with replacement returned
all distinct elements")
+ assert(sample.forall(x => 1 <= x && x <= n), s"elements not in [1,
$n]")
}
for (seed <- 1 to 5) {
- val sample = data.takeSample(withReplacement=true, 100, seed)
- assert(sample.size === 100) // Got exactly 100 elements
+ val sample = data.takeSample(withReplacement=true, n, seed)
+ assert(sample.size === n) // Got exactly 100 elements
// Chance of getting all distinct elements is astronomically low, so
test we got < 100
- assert(sample.toSet.size < 100, "sampling with replacement returned
all distinct elements")
+ assert(sample.toSet.size < n, "sampling with replacement returned
all distinct elements")
}
for (seed <- 1 to 5) {
- val sample = data.takeSample(withReplacement=true, 200, seed)
- assert(sample.size === 200) // Got exactly 200 elements
+ val sample = data.takeSample(withReplacement=true, 2*n, seed)
+ assert(sample.size === 2*n) // Got exactly 200 elements
--- End diff --
`2 * n`
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
