feat!: rename $not_ -> $not, $first -> $first_distinct, and add $last_distinct

NEWS.md

@@ -23,8 +23,10 @@
   columns to these functions will now compute the min/max/sum in each column 
   separately. Use `pl$min_horizontal()` `pl$max_horizontal()`, and 
   `pl$sum_horizontal()` instead for rowwise computation (#508).
-- `$is_not()` is deprecated and will be removed in 0.12.0. Use `$not_()` instead 
-  (#511).
+- `$is_not()` is deprecated and will be removed in 0.12.0. Use `$not()` instead 
+  (#511, #531).
+- `$is_first()` is deprecated and will be removed in 0.12.0. Use `$is_first_distinct()`
+  instead (#531).
 - In `pl$concat()`, the argument `to_supertypes` is removed. Use the suffix 
   `"_relaxed"` in the `how` argument to cast columns to their shared supertypes
   (#523).
@@ -56,6 +58,7 @@
   date/datetime/numeric indices (#470).
 - New methods `$name$to_lowercase()` and `$name$to_uppercase()` to transform 
   variable names (#529).
+- New method `$is_last_distinct()` (#531).
 - New methods of the Expressions class, `$floor_div()`, `$mod()`, `$eq_missing()`
   and `$neq_missing()`. The base R operators `%/%` and `%%` for Expressions are
   now translated to `$floor_div()` and `$mod()` (#523).

R/expr__expr.R

@@ -285,17 +285,17 @@ Expr_mul = Expr_mul = function(other) {
 #' @format NULL
 #' @examples
 #' # two syntaxes same result
-#' pl$lit(TRUE)$not_()
+#' pl$lit(TRUE)$not()
 #' !pl$lit(TRUE)
-Expr_not_ = "use_extendr_wrapper"
+Expr_not = "use_extendr_wrapper"
 #' @export
-#' @rdname Expr_not_
+#' @rdname Expr_not
 #' @param x Expr
-"!.Expr" = function(x) x$not_()
+"!.Expr" = function(x) x$not()
 
 Expr_is_not = function() {
-  warning("`$is_not()` is deprecated and will be removed in 0.12.0. Use `$not_()` instead.")
-  .pr$Expr$not_(self)
+  warning("`$is_not()` is deprecated and will be removed in 0.12.0. Use `$not()` instead.")
+  .pr$Expr$not(self)
 }
 
 #' Check strictly lower inequality
@@ -564,7 +564,7 @@ Expr_is_null = "use_extendr_wrapper"
 #' Check if elements are not NULL
 #'
 #' Returns a boolean Series indicating which values are not null. Syntactic sugar
-#' for `$is_null()$not_()`.
+#' for `$is_null()$not()`.
 #' @return Expr
 #' @docType NULL
 #' @format NULL
@@ -1130,7 +1130,7 @@ Expr_is_nan = "use_extendr_wrapper"
 #' Check if elements are not NaN
 #'
 #' Returns a boolean Series indicating which values are not NaN. Syntactic sugar
-#' for `$is_nan()$not_()`.
+#' for `$is_nan()$not()`.
 #' @return Expr
 #' @docType NULL
 #' @format NULL
@@ -1915,13 +1915,30 @@ Expr_is_unique = "use_extendr_wrapper"
 #'
 #' @examples
 #' pl$DataFrame(head(mtcars[, 1:2]))$
-#'   with_columns(is_ufirst = pl$col("mpg")$is_first())
-Expr_is_first = "use_extendr_wrapper"
+#'   with_columns(is_ufirst = pl$col("mpg")$is_first_distinct())
+Expr_is_first_distinct = "use_extendr_wrapper"
+
+Expr_is_first = function() {
+  warning("`$is_first()` is deprecated and will be removed in 0.12.0. Use `$is_first_distinct()` instead.")
+  .pr$Expr$is_first_distinct(self)
+}
+
+
+#' Check whether each value is the last occurrence
+#'
+#' @return Expr
+#' @docType NULL
+#' @format NULL
+#'
+#' @examples
+#' pl$DataFrame(head(mtcars[, 1:2]))$
+#'   with_columns(is_ulast = pl$col("mpg")$is_last_distinct())
+Expr_is_last_distinct = "use_extendr_wrapper"
 
 
 #' Check whether each value is duplicated
 #'
-#' This is syntactic sugar for `$is_unique()$not_()`.
+#' This is syntactic sugar for `$is_unique()$not()`.
 #' @return Expr
 #' @docType NULL
 #' @format NULL

R/extendr-wrappers.R

@@ -793,12 +793,14 @@ Expr$is_duplicated <- function() .Call(wrap__Expr__is_duplicated, self)
 
 Expr$is_finite <- function() .Call(wrap__Expr__is_finite, self)
 
-Expr$is_first <- function() .Call(wrap__Expr__is_first, self)
+Expr$is_first_distinct <- function() .Call(wrap__Expr__is_first_distinct, self)
 
 Expr$is_in <- function(other) .Call(wrap__Expr__is_in, self, other)
 
 Expr$is_infinite <- function() .Call(wrap__Expr__is_infinite, self)
 
+Expr$is_last_distinct <- function() .Call(wrap__Expr__is_last_distinct, self)
+
 Expr$is_nan <- function() .Call(wrap__Expr__is_nan, self)
 
 Expr$is_not_null <- function() .Call(wrap__Expr__is_not_null, self)
@@ -809,7 +811,7 @@ Expr$is_null <- function() .Call(wrap__Expr__is_null, self)
 
 Expr$is_unique <- function() .Call(wrap__Expr__is_unique, self)
 
-Expr$not_ <- function() .Call(wrap__Expr__not_, self)
+Expr$not <- function() .Call(wrap__Expr__not, self)
 
 Expr$count <- function() .Call(wrap__Expr__count, self)
 

src/rust/Cargo.toml

@@ -90,6 +90,7 @@ features = [
   "interpolate",
   "ipc",
   "is_first_distinct",
+  "is_last_distinct",
   "is_in",
   "is_unique",
   "json",

src/rust/src/lazy/dsl.rs

@@ -1600,8 +1600,7 @@ impl Expr {
         self.0.clone().is_finite().into()
     }
 
-    // TODO: rename to is_first_distinct
-    pub fn is_first(&self) -> Self {
+    pub fn is_first_distinct(&self) -> Self {
         self.clone().0.is_first_distinct().into()
     }
 
@@ -1613,7 +1612,9 @@ impl Expr {
         self.0.clone().is_infinite().into()
     }
 
-    // TODO: is_last_distinct
+    pub fn is_last_distinct(&self) -> Self {
+        self.clone().0.is_last_distinct().into()
+    }
 
     pub fn is_nan(&self) -> Self {
         self.0.clone().is_nan().into()
@@ -1632,7 +1633,7 @@ impl Expr {
     pub fn is_unique(&self) -> Self {
         self.0.clone().is_unique().into()
     }
-    pub fn not_(&self) -> Self {
+    pub fn not(&self) -> Self {
         self.0.clone().not().into()
     }
 

tests/testthat/test-expr_expr.R

@@ -13,20 +13,20 @@ test_that("expression boolean operators", {
 
   cmp_operators_df = pl$DataFrame(list())$with_columns(
     (pl$lit(1) < 2)$alias("1 lt 2"),
-    (pl$lit(1) < 1)$alias("1 lt 1 not")$not_(),
+    (pl$lit(1) < 1)$alias("1 lt 1 not")$not(),
     (pl$lit(2) > 1)$alias("2 gt 1"),
-    (pl$lit(1) > 1)$alias("1 gt 1 not")$not_(),
+    (pl$lit(1) > 1)$alias("1 gt 1 not")$not(),
     (pl$lit(1) == 1)$alias("1 eq 1"),
-    (pl$lit(1) == 2)$alias("1 eq 2 not")$not_(),
+    (pl$lit(1) == 2)$alias("1 eq 2 not")$not(),
     (pl$lit(1) <= 1)$alias("1 lt_eq 1"),
-    (pl$lit(2) <= 1)$alias("2 lt_eq 1 not")$not_(),
+    (pl$lit(2) <= 1)$alias("2 lt_eq 1 not")$not(),
     (pl$lit(2) >= 2)$alias("2 gt_eq 2"),
-    (pl$lit(1) >= 2)$alias("1 gt_eq 2 not")$not_(),
+    (pl$lit(1) >= 2)$alias("1 gt_eq 2 not")$not(),
     (pl$lit(2) != 1)$alias("2 not eq 1"),
-    (pl$lit(2) != 2)$alias("2 not eq 1 not")$not_(),
-    (pl$lit(TRUE)$not_() == pl$lit(FALSE))$alias("not true == false"),
+    (pl$lit(2) != 2)$alias("2 not eq 1 not")$not(),
+    (pl$lit(TRUE)$not() == pl$lit(FALSE))$alias("not true == false"),
     (pl$lit(TRUE) != pl$lit(FALSE))$alias("true != false"),
-    (pl$lit(TRUE)$not_() == FALSE)$alias("not true == false wrap"),
+    (pl$lit(TRUE)$not() == FALSE)$alias("not true == false wrap"),
     (pl$lit(TRUE) != FALSE)$alias("true != false wrap")
   )
 
@@ -253,7 +253,7 @@ test_that("is_null", {
 
   expect_equal(
     df$with_columns(pl$all()$is_not_null()$name$suffix("_isnull"))$to_data_frame(),
-    df$with_columns(pl$all()$is_null()$not_()$name$suffix("_isnull"))$to_data_frame()
+    df$with_columns(pl$all()$is_null()$not()$name$suffix("_isnull"))$to_data_frame()
   )
 })
 
@@ -471,7 +471,7 @@ test_that("and or is_in xor", {
       pl$lit(NA_real_)$is_in(pl$lit(NULL))$alias("NULL typed is in NULL")
 
       # anymore from rust-polars 0.30-0.32
-      # pl$lit(NULL)$is_in(pl$lit(NULL))$not_()$alias("NULL is in NULL, NOY")
+      # pl$lit(NULL)$is_in(pl$lit(NULL))$not()$alias("NULL is in NULL, NOY")
     )$to_data_frame() |> unlist() |> all(na.rm = TRUE)
   )
 })
@@ -1266,18 +1266,20 @@ test_that("std var", {
 })
 
 
-test_that("is_unique is_first is_duplicated", {
+test_that("is_unique is_first_distinct is_last_distinct is_duplicated", {
   v = c(1, 1, 2, 2, 3, NA, NaN, Inf)
   expect_identical(
     pl$select(
       pl$lit(v)$is_unique()$alias("is_unique"),
-      pl$lit(v)$is_first()$alias("is_first"),
+      pl$lit(v)$is_first_distinct()$alias("is_first_distinct"),
+      pl$lit(v)$is_last_distinct()$alias("is_last_distinct"),
       pl$lit(v)$is_duplicated()$alias("is_duplicated"),
-      pl$lit(v)$is_first()$not_()$alias("R_duplicated")
+      pl$lit(v)$is_first_distinct()$not()$alias("R_duplicated")
     )$to_list(),
     list(
       is_unique = !v %in% v[duplicated(v)],
-      is_first = !duplicated(v),
+      is_first_distinct = !duplicated(v),
+      is_last_distinct = !xor(v %in% v[duplicated(v)], duplicated(v)),
       is_duplicated = v %in% v[duplicated(v)],
       R_duplicated = duplicated(v)
     )