[
https://issues.apache.org/jira/browse/ARROW-17637?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Nicola Crane updated ARROW-17637:
---------------------------------
Description:
Using as.Date to convert from timestamp to date fails in Arrow even though this
is fine in R.
{code:r}
library(arrow)
library(dplyr)
library(lubridate)
tf <- tempfile()
dir.create(tf)
tbl <- tibble::tibble(x = as_datetime('2022-05-05T00:00:01.676632'))
write_dataset(tbl, tf)
open_dataset(tf) %>%
mutate(date = as.Date(x)) %>%
collect()
#> Error in `collect()`:
#> ! Invalid: Casting from timestamp[us, tz=UTC] to timestamp[s, tz=UTC] would
lose data: 1651708801676632
#> /home/nic2/arrow/cpp/src/arrow/compute/exec.cc:799
kernel_->exec(kernel_ctx_, input, out)
#> /home/nic2/arrow/cpp/src/arrow/compute/exec.cc:767 ExecuteSingleSpan(input,
&output)
#> /home/nic2/arrow/cpp/src/arrow/compute/exec/expression.cc:597
executor->Execute( ExecBatch(std::move(arguments), all_scalar ? 1 :
input.length), &listener)
#> /home/nic2/arrow/cpp/src/arrow/compute/exec/expression.cc:579
ExecuteScalarExpression(call->arguments[i], input, exec_context)
#> /home/nic2/arrow/cpp/src/arrow/compute/exec/project_node.cc:91
ExecuteScalarExpression(simplified_expr, target, plan()->exec_context())
#> /home/nic2/arrow/cpp/src/arrow/compute/exec/exec_plan.cc:573
iterator_.Next()
#> /home/nic2/arrow/cpp/src/arrow/record_batch.cc:337 ReadNext(&batch)
#> /home/nic2/arrow/cpp/src/arrow/record_batch.cc:351 ToRecordBatches()
tbl %>%
mutate(date = as.Date(x))
#> # A tibble: 1 × 2
#> x date
#> <dttm> <date>
#> 1 2022-05-05 00:00:01 2022-05-05
{code}
was:
Using as.Date to convert from timestamp to date fails even though this is fine
in R.
{code:r}
library(arrow)
library(dplyr)
library(lubridate)
tf <- tempfile()
dir.create(tf)
tbl <- tibble::tibble(x = as_datetime('2022-05-05T00:00:01.676632'))
write_dataset(tbl, tf)
open_dataset(tf) %>%
mutate(date = as.Date(x)) %>%
collect()
#> Error in `collect()`:
#> ! Invalid: Casting from timestamp[us, tz=UTC] to timestamp[s, tz=UTC] would
lose data: 1651708801676632
#> /home/nic2/arrow/cpp/src/arrow/compute/exec.cc:799
kernel_->exec(kernel_ctx_, input, out)
#> /home/nic2/arrow/cpp/src/arrow/compute/exec.cc:767 ExecuteSingleSpan(input,
&output)
#> /home/nic2/arrow/cpp/src/arrow/compute/exec/expression.cc:597
executor->Execute( ExecBatch(std::move(arguments), all_scalar ? 1 :
input.length), &listener)
#> /home/nic2/arrow/cpp/src/arrow/compute/exec/expression.cc:579
ExecuteScalarExpression(call->arguments[i], input, exec_context)
#> /home/nic2/arrow/cpp/src/arrow/compute/exec/project_node.cc:91
ExecuteScalarExpression(simplified_expr, target, plan()->exec_context())
#> /home/nic2/arrow/cpp/src/arrow/compute/exec/exec_plan.cc:573
iterator_.Next()
#> /home/nic2/arrow/cpp/src/arrow/record_batch.cc:337 ReadNext(&batch)
#> /home/nic2/arrow/cpp/src/arrow/record_batch.cc:351 ToRecordBatches()
tbl %>%
mutate(date = as.Date(x))
#> # A tibble: 1 × 2
#> x date
#> <dttm> <date>
#> 1 2022-05-05 00:00:01 2022-05-05
{code}
> [R] as.Date fails going from timestamp[us] to timestamp[s]
> ----------------------------------------------------------
>
> Key: ARROW-17637
> URL: https://issues.apache.org/jira/browse/ARROW-17637
> Project: Apache Arrow
> Issue Type: Improvement
> Components: R
> Reporter: Nicola Crane
> Priority: Major
>
> Using as.Date to convert from timestamp to date fails in Arrow even though
> this is fine in R.
> {code:r}
> library(arrow)
> library(dplyr)
> library(lubridate)
> tf <- tempfile()
> dir.create(tf)
> tbl <- tibble::tibble(x = as_datetime('2022-05-05T00:00:01.676632'))
> write_dataset(tbl, tf)
> open_dataset(tf) %>%
> mutate(date = as.Date(x)) %>%
> collect()
> #> Error in `collect()`:
> #> ! Invalid: Casting from timestamp[us, tz=UTC] to timestamp[s, tz=UTC]
> would lose data: 1651708801676632
> #> /home/nic2/arrow/cpp/src/arrow/compute/exec.cc:799
> kernel_->exec(kernel_ctx_, input, out)
> #> /home/nic2/arrow/cpp/src/arrow/compute/exec.cc:767
> ExecuteSingleSpan(input, &output)
> #> /home/nic2/arrow/cpp/src/arrow/compute/exec/expression.cc:597
> executor->Execute( ExecBatch(std::move(arguments), all_scalar ? 1 :
> input.length), &listener)
> #> /home/nic2/arrow/cpp/src/arrow/compute/exec/expression.cc:579
> ExecuteScalarExpression(call->arguments[i], input, exec_context)
> #> /home/nic2/arrow/cpp/src/arrow/compute/exec/project_node.cc:91
> ExecuteScalarExpression(simplified_expr, target, plan()->exec_context())
> #> /home/nic2/arrow/cpp/src/arrow/compute/exec/exec_plan.cc:573
> iterator_.Next()
> #> /home/nic2/arrow/cpp/src/arrow/record_batch.cc:337 ReadNext(&batch)
> #> /home/nic2/arrow/cpp/src/arrow/record_batch.cc:351 ToRecordBatches()
> tbl %>%
> mutate(date = as.Date(x))
> #> # A tibble: 1 × 2
> #> x date
> #> <dttm> <date>
> #> 1 2022-05-05 00:00:01 2022-05-05
> {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
