This is an automated email from the ASF dual-hosted git repository.
wenchen pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new 6fba9e2 [SPARK-37951][MLLIB][K8S] Move test file from ../data/ to
corresponding module's resource folder
6fba9e2 is described below
commit 6fba9e27f6b7743fd582a44f87c6d77b165af58f
Author: Angerszhuuuu <angers....@gmail.com>
AuthorDate: Wed Jan 19 17:01:13 2022 +0800
[SPARK-37951][MLLIB][K8S] Move test file from ../data/ to corresponding
module's resource folder
### What changes were proposed in this pull request?
Move test file form `data/` dir to corresponding module's resource folder
1. move `../data/mllib/images/partitioned` to mllib's
`resources/inages/partitioned`
2. move `../data/mllib/iris_libsvm.txt` to mllib's
`resources/iris_libsvm.txt`
3. copy `data/mllib/pagerank_data.txt` to kubenets-integration-test's
`resources/pagerank_data.txt`
### Why are the changes needed?
Refactor code to avoid test failure
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Existed UT
Closes #35237 from AngersZhuuuu/SPARK-37951.
Authored-by: Angerszhuuuu <angers....@gmail.com>
Signed-off-by: Wenchen Fan <wenc...@databricks.com>
---
.../org/apache/spark/ml/source/image/ImageDataSource.scala | 4 ++--
.../cls=kittens/date=2018-01/29.5.a_b_EGDP022204.jpg | Bin
.../partitioned/cls=kittens/date=2018-01/not-image.txt | 0
.../images/partitioned/cls=kittens/date=2018-02/54893.jpg | Bin
.../partitioned/cls=kittens/date=2018-02/DP153539.jpg | Bin
.../partitioned/cls=kittens/date=2018-02/DP802813.jpg | Bin
.../partitioned/cls=multichannel/date=2018-01/BGRA.png | Bin
.../cls=multichannel/date=2018-01/BGRA_alpha_60.png | Bin
.../cls=multichannel/date=2018-02/chr30.4.184.jpg | Bin
.../partitioned/cls=multichannel/date=2018-02/grayscale.jpg | Bin
{data/mllib => mllib/src/test/resources}/iris_libsvm.txt | 0
.../spark/ml/evaluation/ClusteringEvaluatorSuite.scala | 2 +-
.../apache/spark/ml/source/image/ImageFileFormatSuite.scala | 3 +--
.../integration-tests/src/test/resources/pagerank_data.txt | 6 ++++++
.../spark/deploy/k8s/integrationtest/BasicTestsSuite.scala | 6 +++---
15 files changed, 13 insertions(+), 8 deletions(-)
diff --git
a/mllib/src/main/scala/org/apache/spark/ml/source/image/ImageDataSource.scala
b/mllib/src/main/scala/org/apache/spark/ml/source/image/ImageDataSource.scala
index d4d7408..9413d99 100644
---
a/mllib/src/main/scala/org/apache/spark/ml/source/image/ImageDataSource.scala
+++
b/mllib/src/main/scala/org/apache/spark/ml/source/image/ImageDataSource.scala
@@ -37,12 +37,12 @@ package org.apache.spark.ml.source.image
* // Scala
* val df = spark.read.format("image")
* .option("dropInvalid", true)
- * .load("data/mllib/images/partitioned")
+ * .load("/path/to/images")
*
* // Java
* Dataset<Row> df = spark.read().format("image")
* .option("dropInvalid", true)
- * .load("data/mllib/images/partitioned");
+ * .load("/path/to/images");
* }}}
*
* Image data source supports the following options:
diff --git
a/data/mllib/images/partitioned/cls=kittens/date=2018-01/29.5.a_b_EGDP022204.jpg
b/mllib/src/test/resources/images/partitioned/cls=kittens/date=2018-01/29.5.a_b_EGDP022204.jpg
similarity index 100%
rename from
data/mllib/images/partitioned/cls=kittens/date=2018-01/29.5.a_b_EGDP022204.jpg
rename to
mllib/src/test/resources/images/partitioned/cls=kittens/date=2018-01/29.5.a_b_EGDP022204.jpg
diff --git
a/data/mllib/images/partitioned/cls=kittens/date=2018-01/not-image.txt
b/mllib/src/test/resources/images/partitioned/cls=kittens/date=2018-01/not-image.txt
similarity index 100%
rename from data/mllib/images/partitioned/cls=kittens/date=2018-01/not-image.txt
rename to
mllib/src/test/resources/images/partitioned/cls=kittens/date=2018-01/not-image.txt
diff --git a/data/mllib/images/partitioned/cls=kittens/date=2018-02/54893.jpg
b/mllib/src/test/resources/images/partitioned/cls=kittens/date=2018-02/54893.jpg
similarity index 100%
rename from data/mllib/images/partitioned/cls=kittens/date=2018-02/54893.jpg
rename to
mllib/src/test/resources/images/partitioned/cls=kittens/date=2018-02/54893.jpg
diff --git
a/data/mllib/images/partitioned/cls=kittens/date=2018-02/DP153539.jpg
b/mllib/src/test/resources/images/partitioned/cls=kittens/date=2018-02/DP153539.jpg
similarity index 100%
rename from data/mllib/images/partitioned/cls=kittens/date=2018-02/DP153539.jpg
rename to
mllib/src/test/resources/images/partitioned/cls=kittens/date=2018-02/DP153539.jpg
diff --git
a/data/mllib/images/partitioned/cls=kittens/date=2018-02/DP802813.jpg
b/mllib/src/test/resources/images/partitioned/cls=kittens/date=2018-02/DP802813.jpg
similarity index 100%
rename from data/mllib/images/partitioned/cls=kittens/date=2018-02/DP802813.jpg
rename to
mllib/src/test/resources/images/partitioned/cls=kittens/date=2018-02/DP802813.jpg
diff --git
a/data/mllib/images/partitioned/cls=multichannel/date=2018-01/BGRA.png
b/mllib/src/test/resources/images/partitioned/cls=multichannel/date=2018-01/BGRA.png
similarity index 100%
rename from data/mllib/images/partitioned/cls=multichannel/date=2018-01/BGRA.png
rename to
mllib/src/test/resources/images/partitioned/cls=multichannel/date=2018-01/BGRA.png
diff --git
a/data/mllib/images/partitioned/cls=multichannel/date=2018-01/BGRA_alpha_60.png
b/mllib/src/test/resources/images/partitioned/cls=multichannel/date=2018-01/BGRA_alpha_60.png
similarity index 100%
rename from
data/mllib/images/partitioned/cls=multichannel/date=2018-01/BGRA_alpha_60.png
rename to
mllib/src/test/resources/images/partitioned/cls=multichannel/date=2018-01/BGRA_alpha_60.png
diff --git
a/data/mllib/images/partitioned/cls=multichannel/date=2018-02/chr30.4.184.jpg
b/mllib/src/test/resources/images/partitioned/cls=multichannel/date=2018-02/chr30.4.184.jpg
similarity index 100%
rename from
data/mllib/images/partitioned/cls=multichannel/date=2018-02/chr30.4.184.jpg
rename to
mllib/src/test/resources/images/partitioned/cls=multichannel/date=2018-02/chr30.4.184.jpg
diff --git
a/data/mllib/images/partitioned/cls=multichannel/date=2018-02/grayscale.jpg
b/mllib/src/test/resources/images/partitioned/cls=multichannel/date=2018-02/grayscale.jpg
similarity index 100%
rename from
data/mllib/images/partitioned/cls=multichannel/date=2018-02/grayscale.jpg
rename to
mllib/src/test/resources/images/partitioned/cls=multichannel/date=2018-02/grayscale.jpg
diff --git a/data/mllib/iris_libsvm.txt
b/mllib/src/test/resources/iris_libsvm.txt
similarity index 100%
rename from data/mllib/iris_libsvm.txt
rename to mllib/src/test/resources/iris_libsvm.txt
diff --git
a/mllib/src/test/scala/org/apache/spark/ml/evaluation/ClusteringEvaluatorSuite.scala
b/mllib/src/test/scala/org/apache/spark/ml/evaluation/ClusteringEvaluatorSuite.scala
index 06f2cb2..baeebfb 100644
---
a/mllib/src/test/scala/org/apache/spark/ml/evaluation/ClusteringEvaluatorSuite.scala
+++
b/mllib/src/test/scala/org/apache/spark/ml/evaluation/ClusteringEvaluatorSuite.scala
@@ -40,7 +40,7 @@ class ClusteringEvaluatorSuite
override def beforeAll(): Unit = {
super.beforeAll()
- irisDataset =
spark.read.format("libsvm").load("../data/mllib/iris_libsvm.txt")
+ irisDataset =
spark.read.format("libsvm").load(getTestResourcePath("iris_libsvm.txt"))
val datasets = MLTestingUtils.generateArrayFeatureDataset(irisDataset)
newIrisDataset = datasets._1
newIrisDatasetD = datasets._2
diff --git
a/mllib/src/test/scala/org/apache/spark/ml/source/image/ImageFileFormatSuite.scala
b/mllib/src/test/scala/org/apache/spark/ml/source/image/ImageFileFormatSuite.scala
index 0ec2747..10b9bbb 100644
---
a/mllib/src/test/scala/org/apache/spark/ml/source/image/ImageFileFormatSuite.scala
+++
b/mllib/src/test/scala/org/apache/spark/ml/source/image/ImageFileFormatSuite.scala
@@ -29,8 +29,7 @@ import org.apache.spark.sql.functions.{col, substring_index}
class ImageFileFormatSuite extends SparkFunSuite with MLlibTestSparkContext {
// Single column of images named "image"
- private lazy val imagePath = "../data/mllib/images/partitioned"
- private lazy val recursiveImagePath = "../data/mllib/images"
+ private lazy val imagePath = getTestResourcePath("images/partitioned")
test("Smoke test: create basic ImageSchema dataframe") {
val origin = "path"
diff --git
a/resource-managers/kubernetes/integration-tests/src/test/resources/pagerank_data.txt
b/resource-managers/kubernetes/integration-tests/src/test/resources/pagerank_data.txt
new file mode 100644
index 0000000..95755ab
--- /dev/null
+++
b/resource-managers/kubernetes/integration-tests/src/test/resources/pagerank_data.txt
@@ -0,0 +1,6 @@
+1 2
+1 3
+1 4
+2 1
+3 1
+4 1
diff --git
a/resource-managers/kubernetes/integration-tests/src/test/scala/org/apache/spark/deploy/k8s/integrationtest/BasicTestsSuite.scala
b/resource-managers/kubernetes/integration-tests/src/test/scala/org/apache/spark/deploy/k8s/integrationtest/BasicTestsSuite.scala
index 6db4bee..d704ef7 100644
---
a/resource-managers/kubernetes/integration-tests/src/test/scala/org/apache/spark/deploy/k8s/integrationtest/BasicTestsSuite.scala
+++
b/resource-managers/kubernetes/integration-tests/src/test/scala/org/apache/spark/deploy/k8s/integrationtest/BasicTestsSuite.scala
@@ -22,7 +22,7 @@ import io.fabric8.kubernetes.api.model.Pod
import org.scalatest.concurrent.Eventually
import org.scalatest.matchers.should.Matchers._
-import org.apache.spark.TestUtils
+import org.apache.spark.{SparkFunSuite, TestUtils}
import org.apache.spark.launcher.SparkLauncher
private[spark] trait BasicTestsSuite { k8sSuite: KubernetesSuite =>
@@ -126,11 +126,11 @@ private[spark] trait BasicTestsSuite { k8sSuite:
KubernetesSuite =>
}
}
-private[spark] object BasicTestsSuite {
+private[spark] object BasicTestsSuite extends SparkFunSuite {
val SPARK_PAGE_RANK_MAIN_CLASS: String =
"org.apache.spark.examples.SparkPageRank"
val CONTAINER_LOCAL_FILE_DOWNLOAD_PATH = "/var/spark-data/spark-files"
val CONTAINER_LOCAL_DOWNLOADED_PAGE_RANK_DATA_FILE =
s"$CONTAINER_LOCAL_FILE_DOWNLOAD_PATH/pagerank_data.txt"
- val REMOTE_PAGE_RANK_DATA_FILE = "data/mllib/pagerank_data.txt"
+ val REMOTE_PAGE_RANK_DATA_FILE = getTestResourcePath("pagerank_data.txt")
val REMOTE_PAGE_RANK_FILE_NAME = "pagerank_data.txt"
}
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
