nealrichardson commented on code in PR #13509:
URL: https://github.com/apache/arrow/pull/13509#discussion_r917097216
##########
r/tests/testthat/test-dataset.R:
##########
@@ -618,6 +618,33 @@ test_that("UnionDataset handles InMemoryDatasets", {
expect_equal(actual, expected)
})
+test_that("scalar aggregates with many batches", {
+ test_data <- data.frame(val = 1:1e7)
+ expected_result_distr <- (
+ sapply(1:100, function(iter_ndx) {
+ test_data %>%
+ dplyr::summarise(min_val = min(val)) %>%
+ dplyr::collect() %>%
+ dplyr::pull(min_val)
+ }) %>%
+ table()
+ )
+
+ ds_tmpfile <- tempfile("test-aggregate", fileext = ".parquet")
+ arrow::write_parquet(test_data, ds_tmpfile)
+ actual_result_distr <- (
+ sapply(1:100, function(iter_ndx) {
+ arrow::open_dataset(ds_tmpfile) %>%
+ dplyr::summarise(min_val = min(val)) %>%
+ dplyr::collect() %>%
+ dplyr::pull(min_val)
+ }) %>%
+ table()
+ )
+
+ expect_equal(actual_result_distr, expected_result_distr)
+})
Review Comment:
Here's a simpler test--this fails on master (actually, the max is fine, the
min is the problem) but should pass with your fix
```suggestion
test_that("scalar aggregates with many batches (ARROW-16904)", {
tf <- tempfile()
write_parquet(data.frame(x = 1:100), tf, chunk_size = 20)
ds <- open_dataset(tf)
replicate(100, ds %>% summarize(min(x)) %>% pull())
expect_true(all(replicate(100, ds %>% summarize(min(x)) %>% pull()) == 1))
expect_true(all(replicate(100, ds %>% summarize(max(x)) %>% pull()) ==
100))
})
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
