Enable how = "cross" in $join() (#310)

NEWS.md

@@ -37,6 +37,7 @@ for demonstration purposes (#240).
 - `<DataFrame>$glimpse()` is a fast `str()`-like view of a `DataFrame` (#277).
 - `$over()` now accepts a vector of column names (#287).
 - New method `<DataFrame>$describe()` (#268).
+- Cross joining is now possible with `how = "cross"` in `$join()`
 
 # polars 0.6.1
 

R/dataframe__frame.R

@@ -983,9 +983,16 @@ DataFrame_to_list = function(unnest_structs = TRUE) {
 #' @return DataFrame
 #' @keywords DataFrame
 #' @examples
-#' print(df1 <- pl$DataFrame(list(key = 1:3, payload = c("f", "i", NA))))
-#' print(df2 <- pl$DataFrame(list(key = c(3L, 4L, 5L, NA_integer_))))
+#' # inner join by default
+#' df1 <- pl$DataFrame(list(key = 1:3, payload = c("f", "i", NA)))
+#' df2 <- pl$DataFrame(list(key = c(3L, 4L, 5L, NA_integer_)))
 #' df1$join(other = df2, on = "key")
+#'
+#' # cross join
+#' df1 <- pl$DataFrame(x = letters[1:3])
+#' df2 <- pl$DataFrame(y = 1:4)
+#' df1$join(other = df2, how = "cross")
+#'
 DataFrame_join = function(
     other, # : LazyFrame or DataFrame,
     left_on = NULL, # : str | pli.Expr | Sequence[str | pli.Expr] | None = None,

R/lazyframe__lazy.R

@@ -586,19 +586,18 @@ LazyFrame_join = function(
   how_opts = c("inner", "left", "outer", "semi", "anti", "cross")
   how = match.arg(how[1L], how_opts)
 
-  if (how == "cross") {
-    stopf("not implemented how == cross")
-  }
-
   if (!is.null(on)) {
     rexprs = do.call(construct_ProtoExprArray, as.list(on))
     rexprs_left = rexprs
     rexprs_right = rexprs
   } else if ((!is.null(left_on) && !is.null(right_on))) {
     rexprs_left = do.call(construct_ProtoExprArray, as.list(left_on))
     rexprs_right = do.call(construct_ProtoExprArray, as.list(right_on))
-  } else {
+  } else if (how != "cross") {
     stopf("must specify `on` OR (  `left_on` AND `right_on` ) ")
+  } else {
+    rexprs_left = do.call(construct_ProtoExprArray, as.list(self$columns))
+    rexprs_right = do.call(construct_ProtoExprArray, as.list(other$columns))
   }
 
   .pr$LazyFrame$join(

tests/testthat/test-joins.R

@@ -80,3 +80,41 @@ test_that("test_semi_anti_join", {
     data.frame(a = 3L, b = "c", payload = 30L)
   )
 })
+
+
+test_that("cross join, DataFrame", {
+  dat = pl$DataFrame(
+    x = letters[1:3]
+  )
+  dat2 = pl$DataFrame(
+    y = 1:4
+  )
+
+  expect_identical(
+    dat$join(dat2, how = "cross")$to_data_frame(),
+    data.frame(
+      x = rep(letters[1:3], each = 4),
+      y = rep(1:4, 3)
+    )
+  )
+
+  # one empty dataframe
+  dat_empty = pl$DataFrame(y = character())
+  expect_identical(
+    dat$join(dat_empty, how = "cross")$to_data_frame(),
+    data.frame(x = character(), y = character())
+  )
+  expect_identical(
+    dat_empty$join(dat, how = "cross")$to_data_frame(),
+    data.frame(y = character(), x = character())
+  )
+
+  # suffix works
+  expect_identical(
+    dat$join(dat, how = "cross")$to_data_frame(),
+    data.frame(
+      x = rep(letters[1:3], each = 3),
+      x_right = rep(letters[1:3], 3)
+    )
+  )
+})