From 382fefd1879e4670f3e9e8841ec243e3eb11c578 Mon Sep 17 00:00:00 2001
From: Felix Cheung <felixcheung_m@hotmail.com>
Date: Tue, 30 May 2017 22:33:29 -0700
Subject: [PATCH] [SPARK-20877][SPARKR][WIP] add timestamps to test runs
## What changes were proposed in this pull request?
to investigate how long they run
## How was this patch tested?
Jenkins, AppVeyor
Author: Felix Cheung <felixcheung_m@hotmail.com>
Closes #18104 from felixcheung/rtimetest.
---
R/pkg/inst/tests/testthat/test_Windows.R | 3 +
.../testthat/test_mllib_classification.R | 4 +
.../tests/testthat/test_mllib_clustering.R | 2 +
R/pkg/inst/tests/testthat/test_mllib_tree.R | 82 +++++++++++--------
R/pkg/inst/tests/testthat/test_sparkSQL.R | 15 ++++
R/pkg/inst/tests/testthat/test_utils.R | 3 +
R/pkg/tests/run-all.R | 6 ++
7 files changed, 81 insertions(+), 34 deletions(-)
diff --git a/R/pkg/inst/tests/testthat/test_Windows.R b/R/pkg/inst/tests/testthat/test_Windows.R
index 919b063bf0..00d684e1a4 100644
--- a/R/pkg/inst/tests/testthat/test_Windows.R
+++ b/R/pkg/inst/tests/testthat/test_Windows.R
@@ -27,3 +27,6 @@ test_that("sparkJars tag in SparkContext", {
abcPath <- testOutput[1]
expect_equal(abcPath, "a\\b\\c")
})
+
+message("--- End test (Windows) ", as.POSIXct(Sys.time(), tz = "GMT"))
+message("elapsed ", (proc.time() - timer_ptm)[3])
diff --git a/R/pkg/inst/tests/testthat/test_mllib_classification.R b/R/pkg/inst/tests/testthat/test_mllib_classification.R
index c1c746828d..82e588dc46 100644
--- a/R/pkg/inst/tests/testthat/test_mllib_classification.R
+++ b/R/pkg/inst/tests/testthat/test_mllib_classification.R
@@ -28,6 +28,8 @@ absoluteSparkPath <- function(x) {
}
test_that("spark.svmLinear", {
+ skip_on_cran()
+
df <- suppressWarnings(createDataFrame(iris))
training <- df[df$Species %in% c("versicolor", "virginica"), ]
model <- spark.svmLinear(training, Species ~ ., regParam = 0.01, maxIter = 10)
@@ -226,6 +228,8 @@ test_that("spark.logit", {
})
test_that("spark.mlp", {
+ skip_on_cran()
+
df <- read.df(absoluteSparkPath("data/mllib/sample_multiclass_classification_data.txt"),
source = "libsvm")
model <- spark.mlp(df, label ~ features, blockSize = 128, layers = c(4, 5, 4, 3),
diff --git a/R/pkg/inst/tests/testthat/test_mllib_clustering.R b/R/pkg/inst/tests/testthat/test_mllib_clustering.R
index 8f71de1cbc..e827e961ab 100644
--- a/R/pkg/inst/tests/testthat/test_mllib_clustering.R
+++ b/R/pkg/inst/tests/testthat/test_mllib_clustering.R
@@ -28,6 +28,8 @@ absoluteSparkPath <- function(x) {
}
test_that("spark.bisectingKmeans", {
+ skip_on_cran()
+
newIris <- iris
newIris$Species <- NULL
training <- suppressWarnings(createDataFrame(newIris))
diff --git a/R/pkg/inst/tests/testthat/test_mllib_tree.R b/R/pkg/inst/tests/testthat/test_mllib_tree.R
index 5fd6a38ecb..31427ee52a 100644
--- a/R/pkg/inst/tests/testthat/test_mllib_tree.R
+++ b/R/pkg/inst/tests/testthat/test_mllib_tree.R
@@ -28,6 +28,8 @@ absoluteSparkPath <- function(x) {
}
test_that("spark.gbt", {
+ skip_on_cran()
+
# regression
data <- suppressWarnings(createDataFrame(longley))
model <- spark.gbt(data, Employed ~ ., "regression", maxDepth = 5, maxBins = 16, seed = 123)
@@ -103,10 +105,12 @@ test_that("spark.gbt", {
expect_equal(stats$maxDepth, 5)
# spark.gbt classification can work on libsvm data
- data <- read.df(absoluteSparkPath("data/mllib/sample_binary_classification_data.txt"),
- source = "libsvm")
- model <- spark.gbt(data, label ~ features, "classification")
- expect_equal(summary(model)$numFeatures, 692)
+ if (not_cran_or_windows_with_hadoop()) {
+ data <- read.df(absoluteSparkPath("data/mllib/sample_binary_classification_data.txt"),
+ source = "libsvm")
+ model <- spark.gbt(data, label ~ features, "classification")
+ expect_equal(summary(model)$numFeatures, 692)
+ }
})
test_that("spark.randomForest", {
@@ -211,13 +215,17 @@ test_that("spark.randomForest", {
expect_equal(length(grep("2.0", predictions)), 50)
# spark.randomForest classification can work on libsvm data
- data <- read.df(absoluteSparkPath("data/mllib/sample_multiclass_classification_data.txt"),
- source = "libsvm")
- model <- spark.randomForest(data, label ~ features, "classification")
- expect_equal(summary(model)$numFeatures, 4)
+ if (not_cran_or_windows_with_hadoop()) {
+ data <- read.df(absoluteSparkPath("data/mllib/sample_multiclass_classification_data.txt"),
+ source = "libsvm")
+ model <- spark.randomForest(data, label ~ features, "classification")
+ expect_equal(summary(model)$numFeatures, 4)
+ }
})
test_that("spark.decisionTree", {
+ skip_on_cran()
+
# regression
data <- suppressWarnings(createDataFrame(longley))
model <- spark.decisionTree(data, Employed ~ ., "regression", maxDepth = 5, maxBins = 16)
@@ -234,19 +242,21 @@ test_that("spark.decisionTree", {
expect_error(capture.output(stats), NA)
expect_true(length(capture.output(stats)) > 6)
- modelPath <- tempfile(pattern = "spark-decisionTreeRegression", fileext = ".tmp")
- write.ml(model, modelPath)
- expect_error(write.ml(model, modelPath))
- write.ml(model, modelPath, overwrite = TRUE)
- model2 <- read.ml(modelPath)
- stats2 <- summary(model2)
- expect_equal(stats$formula, stats2$formula)
- expect_equal(stats$numFeatures, stats2$numFeatures)
- expect_equal(stats$features, stats2$features)
- expect_equal(stats$featureImportances, stats2$featureImportances)
- expect_equal(stats$maxDepth, stats2$maxDepth)
+ if (not_cran_or_windows_with_hadoop()) {
+ modelPath <- tempfile(pattern = "spark-decisionTreeRegression", fileext = ".tmp")
+ write.ml(model, modelPath)
+ expect_error(write.ml(model, modelPath))
+ write.ml(model, modelPath, overwrite = TRUE)
+ model2 <- read.ml(modelPath)
+ stats2 <- summary(model2)
+ expect_equal(stats$formula, stats2$formula)
+ expect_equal(stats$numFeatures, stats2$numFeatures)
+ expect_equal(stats$features, stats2$features)
+ expect_equal(stats$featureImportances, stats2$featureImportances)
+ expect_equal(stats$maxDepth, stats2$maxDepth)
- unlink(modelPath)
+ unlink(modelPath)
+ }
# classification
data <- suppressWarnings(createDataFrame(iris))
@@ -263,17 +273,19 @@ test_that("spark.decisionTree", {
expect_equal(length(grep("setosa", predictions)), 50)
expect_equal(length(grep("versicolor", predictions)), 50)
- modelPath <- tempfile(pattern = "spark-decisionTreeClassification", fileext = ".tmp")
- write.ml(model, modelPath)
- expect_error(write.ml(model, modelPath))
- write.ml(model, modelPath, overwrite = TRUE)
- model2 <- read.ml(modelPath)
- stats2 <- summary(model2)
- expect_equal(stats$depth, stats2$depth)
- expect_equal(stats$numNodes, stats2$numNodes)
- expect_equal(stats$numClasses, stats2$numClasses)
+ if (not_cran_or_windows_with_hadoop()) {
+ modelPath <- tempfile(pattern = "spark-decisionTreeClassification", fileext = ".tmp")
+ write.ml(model, modelPath)
+ expect_error(write.ml(model, modelPath))
+ write.ml(model, modelPath, overwrite = TRUE)
+ model2 <- read.ml(modelPath)
+ stats2 <- summary(model2)
+ expect_equal(stats$depth, stats2$depth)
+ expect_equal(stats$numNodes, stats2$numNodes)
+ expect_equal(stats$numClasses, stats2$numClasses)
- unlink(modelPath)
+ unlink(modelPath)
+ }
# Test numeric response variable
labelToIndex <- function(species) {
@@ -297,10 +309,12 @@ test_that("spark.decisionTree", {
expect_equal(length(grep("2.0", predictions)), 50)
# spark.decisionTree classification can work on libsvm data
- data <- read.df(absoluteSparkPath("data/mllib/sample_multiclass_classification_data.txt"),
- source = "libsvm")
- model <- spark.decisionTree(data, label ~ features, "classification")
- expect_equal(summary(model)$numFeatures, 4)
+ if (not_cran_or_windows_with_hadoop()) {
+ data <- read.df(absoluteSparkPath("data/mllib/sample_multiclass_classification_data.txt"),
+ source = "libsvm")
+ model <- spark.decisionTree(data, label ~ features, "classification")
+ expect_equal(summary(model)$numFeatures, 4)
+ }
})
sparkR.session.stop()
diff --git a/R/pkg/inst/tests/testthat/test_sparkSQL.R b/R/pkg/inst/tests/testthat/test_sparkSQL.R
index 9fc6e5dabe..c790d02b10 100644
--- a/R/pkg/inst/tests/testthat/test_sparkSQL.R
+++ b/R/pkg/inst/tests/testthat/test_sparkSQL.R
@@ -1395,6 +1395,8 @@ test_that("column operators", {
})
test_that("column functions", {
+ skip_on_cran()
+
c <- column("a")
c1 <- abs(c) + acos(c) + approxCountDistinct(c) + ascii(c) + asin(c) + atan(c)
c2 <- avg(c) + base64(c) + bin(c) + bitwiseNOT(c) + cbrt(c) + ceil(c) + cos(c)
@@ -1780,6 +1782,8 @@ test_that("when(), otherwise() and ifelse() with column on a DataFrame", {
})
test_that("group by, agg functions", {
+ skip_on_cran()
+
df <- read.json(jsonPath)
df1 <- agg(df, name = "max", age = "sum")
expect_equal(1, count(df1))
@@ -2121,6 +2125,8 @@ test_that("filter() on a DataFrame", {
})
test_that("join(), crossJoin() and merge() on a DataFrame", {
+ skip_on_cran()
+
df <- read.json(jsonPath)
mockLines2 <- c("{\"name\":\"Michael\", \"test\": \"yes\"}",
@@ -2978,6 +2984,7 @@ test_that("dapply() and dapplyCollect() on a DataFrame", {
})
test_that("dapplyCollect() on DataFrame with a binary column", {
+ skip_on_cran()
df <- data.frame(key = 1:3)
df$bytes <- lapply(df$key, serialize, connection = NULL)
@@ -2999,6 +3006,8 @@ test_that("dapplyCollect() on DataFrame with a binary column", {
})
test_that("repartition by columns on DataFrame", {
+ skip_on_cran()
+
df <- createDataFrame(
list(list(1L, 1, "1", 0.1), list(1L, 2, "2", 0.2), list(3L, 3, "3", 0.3)),
c("a", "b", "c", "d"))
@@ -3037,6 +3046,8 @@ test_that("repartition by columns on DataFrame", {
})
test_that("coalesce, repartition, numPartitions", {
+ skip_on_cran()
+
df <- as.DataFrame(cars, numPartitions = 5)
expect_equal(getNumPartitions(df), 5)
expect_equal(getNumPartitions(coalesce(df, 3)), 3)
@@ -3056,6 +3067,8 @@ test_that("coalesce, repartition, numPartitions", {
})
test_that("gapply() and gapplyCollect() on a DataFrame", {
+ skip_on_cran()
+
df <- createDataFrame (
list(list(1L, 1, "1", 0.1), list(1L, 2, "1", 0.2), list(3L, 3, "3", 0.3)),
c("a", "b", "c", "d"))
@@ -3208,6 +3221,8 @@ test_that("createDataFrame sqlContext parameter backward compatibility", {
})
test_that("randomSplit", {
+ skip_on_cran()
+
num <- 4000
df <- createDataFrame(data.frame(id = 1:num))
weights <- c(2, 3, 5)
diff --git a/R/pkg/inst/tests/testthat/test_utils.R b/R/pkg/inst/tests/testthat/test_utils.R
index 02691f0f64..6197ae7569 100644
--- a/R/pkg/inst/tests/testthat/test_utils.R
+++ b/R/pkg/inst/tests/testthat/test_utils.R
@@ -243,3 +243,6 @@ test_that("basenameSansExtFromUrl", {
})
sparkR.session.stop()
+
+message("--- End test (utils) ", as.POSIXct(Sys.time(), tz = "GMT"))
+message("elapsed ", (proc.time() - timer_ptm)[3])
diff --git a/R/pkg/tests/run-all.R b/R/pkg/tests/run-all.R
index 9c6cba535d..f0bef4f6d2 100644
--- a/R/pkg/tests/run-all.R
+++ b/R/pkg/tests/run-all.R
@@ -21,6 +21,12 @@ library(SparkR)
# Turn all warnings into errors
options("warn" = 2)
+if (.Platform$OS.type == "windows") {
+ Sys.setenv(TZ = "GMT")
+}
+message("--- Start test ", as.POSIXct(Sys.time(), tz = "GMT"))
+timer_ptm <- proc.time()
+
# Setup global test environment
# Install Spark first to set SPARK_HOME
install.spark()
--
GitLab