dc4c351837
## What changes were proposed in this pull request? Move all existing tests to non-installed directory so that it will never run by installing SparkR package For a follow-up PR: - remove all skip_on_cran() calls in tests - clean up test timer - improve or change basic tests that do run on CRAN (if anyone has suggestion) It looks like `R CMD build pkg` will still put pkg\tests (ie. the full tests) into the source package but `R CMD INSTALL` on such source package does not install these tests (and so `R CMD check` does not run them) ## How was this patch tested? - [x] unit tests, Jenkins - [x] AppVeyor - [x] make a source package, install it, `R CMD check` it - verify the full tests are not installed or run Author: Felix Cheung <felixcheung_m@hotmail.com> Closes #18264 from felixcheung/rtestset.
54 lines
2.1 KiB
R
54 lines
2.1 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.
|
|
#
|
|
|
|
library(testthat)
|
|
|
|
context("MLlib statistics algorithms")
|
|
|
|
# Tests for MLlib statistics algorithms in SparkR
|
|
sparkSession <- sparkR.session(master = sparkRTestMaster, enableHiveSupport = FALSE)
|
|
|
|
test_that("spark.kstest", {
|
|
data <- data.frame(test = c(0.1, 0.15, 0.2, 0.3, 0.25, -1, -0.5))
|
|
df <- createDataFrame(data)
|
|
testResult <- spark.kstest(df, "test", "norm")
|
|
stats <- summary(testResult)
|
|
|
|
rStats <- ks.test(data$test, "pnorm", alternative = "two.sided")
|
|
|
|
expect_equal(stats$p.value, rStats$p.value, tolerance = 1e-4)
|
|
expect_equal(stats$statistic, unname(rStats$statistic), tolerance = 1e-4)
|
|
expect_match(capture.output(stats)[1], "Kolmogorov-Smirnov test summary:")
|
|
|
|
testResult <- spark.kstest(df, "test", "norm", -0.5)
|
|
stats <- summary(testResult)
|
|
|
|
rStats <- ks.test(data$test, "pnorm", -0.5, 1, alternative = "two.sided")
|
|
|
|
expect_equal(stats$p.value, rStats$p.value, tolerance = 1e-4)
|
|
expect_equal(stats$statistic, unname(rStats$statistic), tolerance = 1e-4)
|
|
expect_match(capture.output(stats)[1], "Kolmogorov-Smirnov test summary:")
|
|
|
|
# Test print.summary.KSTest
|
|
printStats <- capture.output(print.summary.KSTest(stats))
|
|
expect_match(printStats[1], "Kolmogorov-Smirnov test summary:")
|
|
expect_match(printStats[5],
|
|
"Low presumption against null hypothesis: Sample follows theoretical distribution. ")
|
|
})
|
|
|
|
sparkR.session.stop()
|