wjones127 commented on code in PR #13509:
URL: https://github.com/apache/arrow/pull/13509#discussion_r917097365
##########
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()
+ )
Review Comment:
nit: if we aren't using iter_idx, can use replicate
```suggestion
actual_result_distr <- (
replicate(100, {
arrow::open_dataset(ds_tmpfile) %>%
dplyr::summarise(min_val = min(val)) %>%
dplyr::collect() %>%
dplyr::pull(min_val)
}) %>%
table()
)
```
--
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: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
