ianmcook commented on a change in pull request #9521: URL: https://github.com/apache/arrow/pull/9521#discussion_r581514795
########## File path: r/tests/testthat/test-dplyr-mutate.R ########## @@ -0,0 +1,311 @@ +# 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. + +library(dplyr) +library(stringr) + +tbl <- example_data +# Add some better string data +tbl$verses <- verses[[1]] +# c(" a ", " b ", " c ", ...) increasing padding +# nchar = 3 5 7 9 11 13 15 17 19 21 +tbl$padded_strings <- stringr::str_pad(letters[1:10], width = 2*(1:10)+1, side = "both") + +test_that("mutate() is lazy", { + expect_is( + tbl %>% record_batch() %>% mutate(int = int + 6L), + "arrow_dplyr_query" + ) +}) + +test_that("basic mutate", { + expect_dplyr_equal( + input %>% + select(int, chr) %>% + filter(int > 5) %>% + mutate(int = int + 6L) %>% + collect(), + tbl + ) +}) + +test_that("transmute", { + expect_dplyr_equal( + input %>% + select(int, chr) %>% + filter(int > 5) %>% + transmute(int = int + 6L) %>% + collect(), + tbl + ) +}) + +test_that("mutate and refer to previous mutants", { + expect_dplyr_equal( + input %>% + select(int, padded_strings) %>% + mutate( + line_lengths = nchar(padded_strings), + longer = line_lengths * 10 + ) %>% + filter(line_lengths > 15) %>% + collect(), + tbl + ) +}) + +test_that("mutate with .data pronoun", { + expect_dplyr_equal( + input %>% + select(int, padded_strings) %>% + mutate( + line_lengths = nchar(padded_strings), + longer = .data$line_lengths * 10 + ) %>% + filter(line_lengths > 15) %>% + collect(), + tbl + ) +}) + +test_that("mutate with single value for recycling", { + skip("Not implemented (ARROW-11705") Review comment: Oh, hmm, I was running some tests and left off the `collect()`, and in that case the error happens in `get_field_names()`: ```r > mtcars %>% record_batch() %>% mutate(a=1) Called from: mutate.ArrowTabular(., a = 1) > traceback() 7: .$field_name %||% .$args$field_name 6: .$field_name %||% .$args$field_name %||% "" 5: .f(.x[[i]], ...) 4: map_chr(selected_cols, ~.$field_name %||% .$args$field_name %||% "") at dplyr.R#87 3: get_field_names(x) at dplyr.R#54 2: print.arrow_dplyr_query(x) 1: (function (x, ...) UseMethod("print"))(x) ``` ########## File path: r/tests/testthat/test-dplyr-mutate.R ########## @@ -0,0 +1,311 @@ +# 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. + +library(dplyr) +library(stringr) + +tbl <- example_data +# Add some better string data +tbl$verses <- verses[[1]] +# c(" a ", " b ", " c ", ...) increasing padding +# nchar = 3 5 7 9 11 13 15 17 19 21 +tbl$padded_strings <- stringr::str_pad(letters[1:10], width = 2*(1:10)+1, side = "both") + +test_that("mutate() is lazy", { + expect_is( + tbl %>% record_batch() %>% mutate(int = int + 6L), + "arrow_dplyr_query" + ) +}) + +test_that("basic mutate", { + expect_dplyr_equal( + input %>% + select(int, chr) %>% + filter(int > 5) %>% + mutate(int = int + 6L) %>% + collect(), + tbl + ) +}) + +test_that("transmute", { + expect_dplyr_equal( + input %>% + select(int, chr) %>% + filter(int > 5) %>% + transmute(int = int + 6L) %>% + collect(), + tbl + ) +}) + +test_that("mutate and refer to previous mutants", { + expect_dplyr_equal( + input %>% + select(int, padded_strings) %>% + mutate( + line_lengths = nchar(padded_strings), + longer = line_lengths * 10 + ) %>% + filter(line_lengths > 15) %>% + collect(), + tbl + ) +}) + +test_that("mutate with .data pronoun", { + expect_dplyr_equal( + input %>% + select(int, padded_strings) %>% + mutate( + line_lengths = nchar(padded_strings), + longer = .data$line_lengths * 10 + ) %>% + filter(line_lengths > 15) %>% + collect(), + tbl + ) +}) + +test_that("mutate with single value for recycling", { + skip("Not implemented (ARROW-11705") Review comment: Oh, hmm, I was running some tests and left off the `collect()`, and in that case the error happens in `get_field_names()`: ```r > mtcars %>% record_batch() %>% mutate(a=1) Error in .$field_name : $ operator is invalid for atomic vectors > traceback() 7: .$field_name %||% .$args$field_name 6: .$field_name %||% .$args$field_name %||% "" 5: .f(.x[[i]], ...) 4: map_chr(selected_cols, ~.$field_name %||% .$args$field_name %||% "") at dplyr.R#87 3: get_field_names(x) at dplyr.R#54 2: print.arrow_dplyr_query(x) 1: (function (x, ...) UseMethod("print"))(x) ``` ########## File path: r/tests/testthat/test-dplyr-mutate.R ########## @@ -0,0 +1,311 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. + +library(dplyr) +library(stringr) + +tbl <- example_data +# Add some better string data +tbl$verses <- verses[[1]] +# c(" a ", " b ", " c ", ...) increasing padding +# nchar = 3 5 7 9 11 13 15 17 19 21 +tbl$padded_strings <- stringr::str_pad(letters[1:10], width = 2*(1:10)+1, side = "both") + +test_that("mutate() is lazy", { + expect_is( + tbl %>% record_batch() %>% mutate(int = int + 6L), + "arrow_dplyr_query" + ) +}) + +test_that("basic mutate", { + expect_dplyr_equal( + input %>% + select(int, chr) %>% + filter(int > 5) %>% + mutate(int = int + 6L) %>% + collect(), + tbl + ) +}) + +test_that("transmute", { + expect_dplyr_equal( + input %>% + select(int, chr) %>% + filter(int > 5) %>% + transmute(int = int + 6L) %>% + collect(), + tbl + ) +}) + +test_that("mutate and refer to previous mutants", { + expect_dplyr_equal( + input %>% + select(int, padded_strings) %>% + mutate( + line_lengths = nchar(padded_strings), + longer = line_lengths * 10 + ) %>% + filter(line_lengths > 15) %>% + collect(), + tbl + ) +}) + +test_that("mutate with .data pronoun", { + expect_dplyr_equal( + input %>% + select(int, padded_strings) %>% + mutate( + line_lengths = nchar(padded_strings), + longer = .data$line_lengths * 10 + ) %>% + filter(line_lengths > 15) %>% + collect(), + tbl + ) +}) + +test_that("mutate with single value for recycling", { + skip("Not implemented (ARROW-11705") Review comment: I guess that's a separate issue—which we should also try to fix ########## File path: r/tests/testthat/test-dplyr-mutate.R ########## @@ -0,0 +1,311 @@ +# 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. + +library(dplyr) +library(stringr) + +tbl <- example_data +# Add some better string data +tbl$verses <- verses[[1]] +# c(" a ", " b ", " c ", ...) increasing padding +# nchar = 3 5 7 9 11 13 15 17 19 21 +tbl$padded_strings <- stringr::str_pad(letters[1:10], width = 2*(1:10)+1, side = "both") + +test_that("mutate() is lazy", { + expect_is( + tbl %>% record_batch() %>% mutate(int = int + 6L), + "arrow_dplyr_query" + ) +}) + +test_that("basic mutate", { + expect_dplyr_equal( + input %>% + select(int, chr) %>% + filter(int > 5) %>% + mutate(int = int + 6L) %>% + collect(), + tbl + ) +}) + +test_that("transmute", { + expect_dplyr_equal( + input %>% + select(int, chr) %>% + filter(int > 5) %>% + transmute(int = int + 6L) %>% + collect(), + tbl + ) +}) + +test_that("mutate and refer to previous mutants", { + expect_dplyr_equal( + input %>% + select(int, padded_strings) %>% + mutate( + line_lengths = nchar(padded_strings), + longer = line_lengths * 10 + ) %>% + filter(line_lengths > 15) %>% + collect(), + tbl + ) +}) + +test_that("mutate with .data pronoun", { + expect_dplyr_equal( + input %>% + select(int, padded_strings) %>% + mutate( + line_lengths = nchar(padded_strings), + longer = .data$line_lengths * 10 + ) %>% + filter(line_lengths > 15) %>% + collect(), + tbl + ) +}) + +test_that("mutate with single value for recycling", { + skip("Not implemented (ARROW-11705") Review comment: Ah, ok I was running some tests and left off the `collect()`, and in that case the error happens in `get_field_names()` which is called by `print.arrow_dplyr_query()`: ```r > mtcars %>% record_batch() %>% mutate(a=1) Error in .$field_name : $ operator is invalid for atomic vectors > traceback() 7: .$field_name %||% .$args$field_name 6: .$field_name %||% .$args$field_name %||% "" 5: .f(.x[[i]], ...) 4: map_chr(selected_cols, ~.$field_name %||% .$args$field_name %||% "") at dplyr.R#87 3: get_field_names(x) at dplyr.R#54 2: print.arrow_dplyr_query(x) 1: (function (x, ...) UseMethod("print"))(x) ``` ########## File path: r/R/dplyr.R ########## @@ -309,8 +344,27 @@ collect.arrow_dplyr_query <- function(x, as_data_frame = TRUE, ...) { # See dataset.R for Dataset and Scanner(Builder) classes Review comment: But also per that dplyr docs page: >`collect()` retrieves data into a local tibble I think repurposing `collect()` with `as_data_frame = FALSE` to force computation without actually returning a tibble/data frame is kinda sus (as the kids say). Despite the database-centric framing of `compute()` in the dplyr docs, I think `compute()` is really the appropriate verb to describe this action. ########## File path: r/R/dplyr.R ########## @@ -73,6 +80,22 @@ print.arrow_dplyr_query <- function(x, ...) { invisible(x) } +get_field_names <- function(selected_cols) { + if (inherits(selected_cols, "arrow_dplyr_query")) { + selected_cols <- selected_cols$selected_columns + } + map_chr(selected_cols, ~.$field_name %||% .$args$field_name %||% "") Review comment: See [my other comment](https://github.com/apache/arrow/pull/9521/files#r581514795) in which an error happens on this line ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org
