Github user felixcheung commented on a diff in the pull request:
https://github.com/apache/spark/pull/23256#discussion_r239997109
--- Diff: R/pkg/tests/fulltests/test_mllib_fpm.R ---
@@ -84,19 +84,20 @@ 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"))
- result1 <- spark.findFrequentSequentialPatterns(df, minSupport = 0.5,
maxPatternLength = 5L,
- maxLocalProjDBSize =
32000000L)
-
- 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"))
- })
+ 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"))
+ result <- spark.findFrequentSequentialPatterns(df, minSupport = 0.5,
maxPatternLength = 5L,
+ maxLocalProjDBSize =
32000000L)
+
+ 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, result)
--- End diff --
this is an important fix..
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
