--- title: "Subassignment" output: rmarkdown::html_vignette vignette: > %\VignetteIndexEntry{subassign} %\VignetteEngine{knitr::rmarkdown} %\VignetteEncoding{UTF-8} --- ```{r, include = FALSE} knitr::opts_chunk$set( error = TRUE, collapse = TRUE, comment = "#>" ) tibble:::set_dftbl_hooks() options( lifecycle_disable_warnings = FALSE, lifecycle_verbose_soft_deprecation = TRUE, lifecycle_repeat_warnings = TRUE ) ``` This vignette is an attempt to provide a comprehensive overview over all subassignment operations, highlighting where the tibble implementation differs from the data frame implementation. ```{r setup} library(tibble) new_df <- function() { df <- data.frame(a = 1:4) df$b <- letters[5:8] df$cd <- list(9, 10:11, 12:14, "text") df } new_tbl <- function() { as_tibble(new_df()) } ``` Results of the same code for data frames and tibbles are presented side by side: ```{r show, dftbl = TRUE, dftbl_always = TRUE} new_df() ``` In the following, if the results are identical (after converting to a data frame if necessary), only the tibble result is shown, as in the example below. This allows to spot differences easier. ```{r show-compare, dftbl = TRUE} new_df() ``` For subassignment, we need a fresh copy of the data for each test. The `with_*()` functions allow for a more concise notation (`with_tbl()` omitted here for brevity): ```{r with-df-def} with_df <- function(code, verbose = FALSE) { code <- rlang::enexpr(code) full_code <- rlang::quo({ df <- new_df() !!code df }) if (verbose) rlang::expr_print(rlang::quo_get_expr(full_code)) rlang::eval_tidy(full_code) } ``` ```{r with-tbl-def, include = FALSE} with_tbl <- function(code, verbose = FALSE) { code <- rlang::enexpr(code) full_code <- rlang::quo({ tbl <- new_tbl() !!code tbl }) if (verbose) rlang::expr_print(rlang::quo_get_expr(full_code)) rlang::eval_tidy(full_code) } ``` This function takes an assignment expression and executes it on a fresh copy of the data. The first example prints what's really executed, further examples omit this output. ```{r with-demo, dftbl = TRUE} with_df(df$a <- rev(df$a), verbose = TRUE) ``` ## $<- ### Scalars and full length Assigning a scalar or a full-length vector to a column consistently overwrites existing data or appends a new column at the end. Partial matching doesn't happen: ```{r dollar-assign-scalar, dftbl = TRUE} with_df(df$a <- 1) with_df(df$b <- 1) with_df(df$c <- 1) with_df(df$cd <- 1) ``` ```{r dollar-assign-full, dftbl = TRUE} with_df(df$a <- 4:1) with_df(df$b <- 4:1) with_df(df$c <- 4:1) with_df(df$cd <- 4:1) ``` ### Recycling Tibbles allow recycling only for vectors of length 1 or of the same length as the data. ```{r dollar-assign-recycle, dftbl = TRUE} with_df(df$a <- 1:2) with_df(df$a <- 1:3) with_df(df$a <- 1:5) with_df(df$c <- 1:2) ``` ### Subset assignment Updating parts of a column extracted by `$` is the responsibility of the column vector. Tibbles can't control what happens after `$` has returned. ```{r dollar-assign-subset, dftbl = TRUE} with_df(df$a[1:2] <- 4:3) with_df(df$b[1:2] <- 4:3) with_df(df$c[1:2] <- 4:3) with_df(df$cd[1:2] <- 4:3) with_df(df$a[1:3] <- 4:3) with_df(df$a[1:4] <- 4:3) ``` For columns of the stricter `"vctrs_vctr"` class, this class implements the check, which then works identically for data frames and tibbles: ```{r vctrs} with_df({ df$v = vctrs::new_vctr(1:4); df$v[1:2] <- vctrs::new_vctr(4:3)}) with_df({ df$v = vctrs::new_vctr(1:4); df$v[1:2] <- vctrs::new_vctr(letters[4:3])}) ``` ## [[<- ### Scalars and full length As with `$` subsetting, columns are consistently overwritten, and partial matching doesn't occur. Numeric indexing is supported, but tibbles don't support creation of new numbered columns for a good reason. ```{r double-bracket-assign-col-scalar, dftbl = TRUE} with_df(df[["a"]] <- 1) with_df(df[["a"]] <- "x") with_df(df[["b"]] <- "x") with_df(df[["c"]] <- "x") with_df(df[["cd"]] <- "x") with_df(df[[1]] <- "x") with_df(df[[2]] <- "x") with_df(df[[4]] <- "x") with_df(df[[5]] <- "x") ``` ```{r double-bracket-assign-col-full, dftbl = TRUE} with_df(df[["a"]] <- 4:1) with_df(df[["a"]] <- letters[4:1]) with_df(df[["b"]] <- letters[4:1]) with_df(df[["c"]] <- letters[4:1]) with_df(df[["cd"]] <- letters[4:1]) ``` ### Cells Tibbles are stricter when updating single cells, the value must be coercible to the existing contents. Updating a list column requires the contents to be wrapped in a list, consistently with `[[` subsetting which returns a list if a cell in a list column is accessed: ```{r double-bracket-assign-cell, dftbl = TRUE} with_df(df[[2, "a"]] <- 1) with_df(df[[2, "a"]] <- 1.5) with_df(df[[2, "a"]] <- "x") with_df(df[[2, "b"]] <- "x") with_df(df[[2, 1]] <- "x") with_df(df[[2, 2]] <- "x") with_df(df[[2, "cd"]] <- "x") with_df(df[[2, "cd"]] <- list("x")) with_df(df[[2, "c"]] <- "x") with_df(df[[1:2, "cd"]] <- "x") with_df(df[[1:2, "c"]] <- "x") with_df(df[[2, c("cd", "d")]] <- "x") ``` ## [<- ### Scalars ```{r bracket-assign-scalar-col, dftbl = TRUE} with_df(df[2, "a"] <- 1) with_df(df[2, "a"] <- 1.5) with_df(df[2, "a"] <- "x") with_df(df[2, "b"] <- "x") with_df(df[2, "cd"] <- "x") with_df(df[2, "cd"] <- list("x")) with_df(df[2, "c"] <- "x") with_df(df[2, 1] <- "x") with_df(df[2, 2] <- "x") with_df(df[2, 3] <- "x") with_df(df[2, 4] <- "x") ``` ### Full length columns ```{r bracket-assign-full-col, dftbl = TRUE} with_df(df[, "a"] <- 4:1) with_df(df[, "b"] <- 4:1) with_df(df[, "c"] <- 4:1) with_df(df[, "cd"] <- 4:1) with_df(df[, 1] <- 4:1) with_df(df[, 2] <- 4:1) with_df(df[, 3] <- 4:1) with_df(df[, 4] <- 4:1) with_df(df[, "a"] <- 1) with_df(df[, "b"] <- 1) with_df(df[, "c"] <- 1) with_df(df[, "cd"] <- 1) with_df(df[, 1] <- 1) with_df(df[, 2] <- 1) with_df(df[, 3] <- 1) with_df(df[, 4] <- 1) ``` ### Multiple full length columns ```{r bracket-assign-full-multicol, dftbl = TRUE} with_df(df[, c("a", "b")] <- 4:1) with_df(df[, c("a", "b")] <- 1) with_df(df[, c("a", "b")] <- data.frame(a = 4:1, b = letters[4:1])) with_df(df[, c("a", "b")] <- data.frame(b = 4:1, a = letters[4:1])) with_df(df[, c("a", "b")] <- data.frame(c = 4:1, d = letters[4:1])) with_df(df[, c("a", "b")] <- data.frame(a = 4:1)) with_df(df[, c("a", "b")] <- data.frame(a = 4:1, b = letters[4:1], c = 1:4)) with_df(df[, c("a", "b")] <- data.frame(4:1, 1)) with_df(df[, c("a", "b", "c")] <- data.frame(4:1, letters[4:1])) with_df(df[, c("a", "b", "cd")] <- data.frame(4:1, letters[4:1])) ``` ### Full length rows ```{r bracket-assign-full-row, dftbl = TRUE} with_df(df[2, ] <- 1) with_df(df[2, ] <- "x") with_df(df[2, ] <- tibble(a = 1, b = "x")) with_df(df[2, ] <- tibble(a = 1, b = "x", c = list("y"))) with_df(df[2, ] <- tibble(a = 1, b = "x", c = list("y"), d = "z")) with_df(df[0, ] <- tibble(a = 1, b = "x", c = list("y"))) with_df(df[5, ] <- tibble(a = 1, b = "x", c = list("y"))) ``` ### Multiple full length rows ```{r bracket-assign-full-multirow, dftbl = TRUE} with_df(df[2:3, ] <- 1) with_df(df[2:3, ] <- 1:2) with_df(df[2:3, ] <- c("x", "y")) with_df(df[2:3, ] <- tibble(a = 1:2, b = c("x", "y"))) with_df(df[2:3, ] <- tibble(a = 1, b = "x", c = list("y"))) with_df(df[2:3, ] <- tibble(a = 1:2, b = "x", c = list("y"))) with_df(df[2:3, ] <- tibble(a = 1, b = "x", c = list("y"), d = "z")) with_df(df[-(1:2), ] <- tibble(a = 1:2, b = "x", c = list("y"))) with_df(df[0:1, ] <- tibble(a = 1:2, b = "x", c = list("y"))) with_df(df[4:5, ] <- tibble(a = 1:2, b = "x", c = list("y"))) ``` ### Unspecified ```{r bracket-assign-unspecified, dftbl = TRUE} with_df(df[] <- 1) with_df(df[] <- 4:1) with_df(df[] <- 3:1) with_df(df[] <- 5:1) with_df(df[] <- data.frame(1, "x")) with_df(df[] <- data.frame(4:1, "x", 2)) with_df(df[] <- data.frame(1, "x", 2)) with_df(df[] <- data.frame(1, "x", 2, 3)) with_df(df[] <- df) with_df(df[,] <- 1) with_df(df[,] <- 4:1) with_df(df[,] <- 3:1) with_df(df[,] <- 5:1) with_df(df[,] <- data.frame(1, "x")) with_df(df[,] <- data.frame(4:1, "x", 2)) with_df(df[,] <- data.frame(1, "x", 2)) with_df(df[,] <- data.frame(1, "x", 2, 3)) with_df(df[,] <- df) ``` ### Subset assignment Due to tibble's default of `drop = FALSE`, updating a portion of a `[` subset is still safe, because tibble is still in control. Only one example is given here. ```{r bracket-assign-subset, dftbl = TRUE} with_df(df["a"][1, ] <- "b") ```