thisisnic commented on a change in pull request #11143: URL: https://github.com/apache/arrow/pull/11143#discussion_r708510117
########## File path: r/R/dplyr-distinct.R ########## @@ -0,0 +1,71 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. + +# The following S3 methods are registered on load if dplyr is present + +distinct.arrow_dplyr_query <- function(.data, ..., .keep_all = FALSE) { + + if (.keep_all == TRUE) { + # After ARROW-13767 is merged, we can implement this via e.g. + # iris %>% group_by(Species) %>% slice(1) %>% ungroup() + abort("`distinct()` with `keep_all = TRUE` argument not supported in Arrow") + } + + distinct_groups <- ensure_named_exprs(quos(...)) + + # Get ordering to use when returning data + cols_in_order <- intersect( + unique(c(names(.data), names(distinct_groups))), + names(distinct_groups) + ) + + # Get grouping in the data to add back in later, as the call to summarize() + # will remove it + gv <- dplyr::group_vars(.data) + + vars_to_group <- unique(c( + names(distinct_groups), + gv + )) + + if (length(vars_to_group) == 0) { + return(.data) + } + + # Call mutate in case any columns are expressions + .data <- dplyr::mutate(.data, ...) + + # This works as distinct(data, x, y) == summarise(group_by(data, x, y)) + .data <- dplyr::group_by(.data, !!!syms(vars_to_group)) + .data <- dplyr::summarize(.data) + + # Add back in any grouping which existed in the data previously + if (length(gv) > 0) { + .data$group_by_vars <- gv + } + + # Select the columns to return in the correct order Review comment: The order of columns returned by `group_by()` and then `summarise()` are the order in which they're supplied to `group_by()`, whereas the order of columns returned from `distinct()` are the order in which they occur in the data, even if there's a `group_by()` call previously. ``` > tbl %>% + group_by(some_grouping, int) %>% + summarise() %>% + collect() `summarise()` has grouped output by 'some_grouping'. You can override using the `.groups` argument. # A tibble: 10 × 2 # Groups: some_grouping [2] some_grouping int <dbl> <int> 1 1 1 2 1 3 3 1 5 4 1 7 5 1 9 6 2 2 7 2 6 8 2 8 9 2 10 10 2 NA > tbl %>% + group_by(some_grouping, int) %>% + distinct(lgl) %>% + collect() # A tibble: 10 × 3 # Groups: some_grouping, int [10] int lgl some_grouping <int> <lgl> <dbl> 1 1 TRUE 1 2 2 NA 2 3 3 TRUE 1 4 NA FALSE 2 5 5 TRUE 1 6 6 NA 2 7 7 NA 1 8 8 FALSE 2 9 9 FALSE 1 10 10 NA 2 ``` -- 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]
