Github user huaxingao commented on a diff in the pull request:
https://github.com/apache/spark/pull/21710#discussion_r203229794
--- Diff: R/pkg/tests/fulltests/test_mllib_fpm.R ---
@@ -82,4 +82,26 @@ test_that("spark.fpGrowth", {
})
+test_that("spark.prefixSpan", {
+ df <- createDataFrame(list(list(list(list(1L, 2L), list(3L))),
+ list(list(list(1L), list(3L, 2L), list(1L, 2L))),
+ list(list(list(1L, 2L), list(5L))),
+ list(list(list(6L)))), schema = c("sequence"))
+ prefix_Span1 <- spark.prefixSpan(minSupport = 0.5, maxPatternLength =
5L,
+ maxLocalProjDBSize = 32000000L)
+ result1 <- spark.findFrequentSequentialPatterns(prefix_Span1, df)
+
+ expected_result <- createDataFrame(list(list(list(list(1L)), 3L),
+ list(list(list(3L)), 2L),
+ list(list(list(2L)), 3L),
+ list(list(list(1L, 2L)), 3L),
+ list(list(list(1L), list(3L)),
2L)),
+ schema = c("sequence", "freq"))
+ expect_equivalent(expected_result, result1)
+
+ prefix_Span2 <- spark.prefixSpan(minSupport = 0.5, maxPatternLength =
5L)
+ result2 <- spark.findFrequentSequentialPatterns(prefix_Span2, df)
+ expect_equivalent(expected_result, result2)
--- End diff --
Just trying to test that the default value (```maxLocalProjDBSize =
32000000L```) will be used if the parameter isn't set explicitly.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
