nealrichardson commented on a change in pull request #11143: URL: https://github.com/apache/arrow/pull/11143#discussion_r708236156
########## 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() Review comment: I'm not sure this is accurate ########## 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") Review comment: ```suggestion arrow_not_supported("`distinct()` with `.keep_all = TRUE`") ``` ########## 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 Review comment: I suspect what you're actually hitting here is ARROW-13550, that summarize isn't restoring groups as expected yet. ########## File path: r/tests/testthat/test-dplyr-distinct.R ########## @@ -0,0 +1,73 @@ +# 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. + +skip_if_not_available("dataset") + +library(dplyr) +library(stringr) + +tbl <- example_data +tbl$some_grouping <- rep(c(1, 2), 5) + +test_that("distinct()", { + expect_dplyr_equal( + input %>% + distinct(some_grouping, lgl) %>% + collect(), + tbl + ) +}) + +test_that("distinct() works without any variables", { + expect_dplyr_equal( + input %>% + distinct() %>% + collect(), + tbl + ) +}) + +test_that("distinct() can retain groups", { + skip("ARROW-13777 - internally uses mutate on grouped data; should work after this is merged") Review comment: I think you can remove your mutate call though and these should pass if you let group_by do the work ########## 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: Why are columns out of order? group_by should get the order right for you ########## 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, ...) Review comment: I don't think you need this: group_by will handle this for you, won't it? -- 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]
