refactor!: by -> group_by in $rolling() and $group_by_dynamic()

NEWS.md

@@ -46,6 +46,10 @@
     - In `<LazyFrame>$sink_*` functions, the first argument is now `path`.
   - In `$dt$convert_time_zone()` and `$dt$replace_time_zone()`, the `tz` argument
     is renamed to `time_zone` (#944).
+  - In `<DataFrame>$rolling()`, `<LazyFrame>$rolling()`, `<DataFrame>$group_by_dynamic()`
+    and `<LazyFrame>$group_by_dynamic()`, the `by` argument is renamed to `group_by` (#983).
+  - In `<DataFrame>$rolling()` and `<DataFrame>$group_by_dynamic()`, all arguments
+    except `index_column` must be named arguments (#983).
   - In `$dt$replace_time_zone()`, all arguments except `time_zone` must be named
     arguments (#944).
   - In `$bin$decode()`, the `strict` argument must be a named argument (#980).

R/dataframe__frame.R

@@ -1995,34 +1995,48 @@ DataFrame_write_ndjson = function(file) {
 
 #' @inherit LazyFrame_rolling title description params details
 #' @return A [RollingGroupBy][RollingGroupBy_class] object
-#'
+#' @seealso
+#' - [`<DataFrame>$group_by_dynamic()`][DataFrame_group_by_dynamic]
+#' @inheritSection polars_duration_string  Polars duration string language
 #' @examples
-#' df = pl$DataFrame(
-#'   dt = c("2020-01-01", "2020-01-01", "2020-01-01", "2020-01-02", "2020-01-03", "2020-01-08"),
-#'   a = c(3, 7, 5, 9, 2, 1)
-#' )$with_columns(
-#'   pl$col("dt")$str$strptime(pl$Date, format = NULL)$set_sorted()
+#' date = c(
+#'   "2020-01-01 13:45:48",
+#'   "2020-01-01 16:42:13",
+#'   "2020-01-01 16:45:09",
+#'   "2020-01-02 18:12:48",
+#'   "2020-01-03 19:45:32",
+#'   "2020-01-08 23:16:43"
+#' )
+#' df = pl$DataFrame(dt = date, a = c(3, 7, 5, 9, 2, 1))$with_columns(
+#'   pl$col("dt")$str$strptime(pl$Datetime())$set_sorted()
 #' )
 #'
 #' df$rolling(index_column = "dt", period = "2d")$agg(
-#'   pl$col("a"),
-#'   pl$sum("a")$alias("sum_a"),
-#'   pl$min("a")$alias("min_a"),
-#'   pl$max("a")$alias("max_a")
+#'   sum_a = pl$sum("a"),
+#'   min_a = pl$min("a"),
+#'   max_a = pl$max("a")
 #' )
-DataFrame_rolling = function(index_column, period, offset = NULL, closed = "right", by = NULL, check_sorted = TRUE) {
+DataFrame_rolling = function(
+    index_column,
+    ...,
+    period,
+    offset = NULL,
+    closed = "right",
+    group_by = NULL,
+    check_sorted = TRUE) {
   if (is.null(offset)) {
-    offset = paste0("-", period)
+    offset = paste0("-", period) # TODO: `paste0` should be executed after `period` is parsed as string
   }
-  construct_rolling_group_by(self, index_column, period, offset, closed, by, check_sorted)
+  construct_rolling_group_by(self, index_column, period, offset, closed, group_by, check_sorted)
 }
 
 #' @inherit LazyFrame_group_by_dynamic title description details params
 #' @return A [GroupBy][GroupBy_class] object
-#'
+#' @seealso
+#' - [`<DataFrame>$rolling()`][DataFrame_rolling]
 #' @examples
 #' df = pl$DataFrame(
-#'   time = pl$date_range(
+#'   time = pl$datetime_range(
 #'     start = strptime("2021-12-16 00:00:00", format = "%Y-%m-%d %H:%M:%S", tz = "UTC"),
 #'     end = strptime("2021-12-16 03:00:00", format = "%Y-%m-%d %H:%M:%S", tz = "UTC"),
 #'     interval = "30m"
@@ -2065,7 +2079,7 @@ DataFrame_rolling = function(index_column, period, offset = NULL, closed = "righ
 #'   "time",
 #'   every = "1h",
 #'   closed = "both",
-#'   by = "groups",
+#'   group_by = "groups",
 #'   include_boundaries = TRUE
 #' )$agg(pl$col("n"))
 #'
@@ -2085,24 +2099,25 @@ DataFrame_rolling = function(index_column, period, offset = NULL, closed = "righ
 #' )$agg(A_agg_list = pl$col("A"))
 DataFrame_group_by_dynamic = function(
     index_column,
+    ...,
     every,
     period = NULL,
     offset = NULL,
     include_boundaries = FALSE,
     closed = "left",
     label = "left",
-    by = NULL,
+    group_by = NULL,
     start_by = "window",
     check_sorted = TRUE) {
   if (is.null(offset)) {
-    offset = paste0("-", every)
+    offset = paste0("-", every) # TODO: `paste0` should be executed after `period` is parsed as string
   }
   if (is.null(period)) {
     period = every
   }
   construct_group_by_dynamic(
     self, index_column, every, period, offset, include_boundaries, closed, label,
-    by, start_by, check_sorted
+    group_by, start_by, check_sorted
   )
 }
 

R/expr__expr.R

@@ -3345,7 +3345,7 @@ Expr_rolling = function(
     offset = paste0("-", period) # TODO: `paste0` should be executed after `period` is parsed as string
   }
   .pr$Expr$rolling(self, index_column, period, offset, closed, check_sorted) |>
-    unwrap("in $rolling():")
+    unwrap("in <Expr>$rolling():")
 }
 
 #' Replace values by different values

R/group_by_dynamic.R

@@ -40,7 +40,7 @@ RPolarsDynamicGroupBy = new.env(parent = emptyenv())
 #' @noRd
 construct_group_by_dynamic = function(
     df, index_column, every, period, offset, include_boundaries, closed, label,
-    by, start_by, check_sorted) {
+    group_by, start_by, check_sorted) {
   if (!inherits(df, "RPolarsDataFrame")) {
     stop("internal error: construct_group called not on DataFrame")
   }
@@ -57,7 +57,7 @@ construct_group_by_dynamic = function(
     include_boundaries = include_boundaries,
     closed = closed,
     label = label,
-    by = by,
+    group_by = group_by,
     start_by = start_by,
     check_sorted = check_sorted
   )
@@ -95,7 +95,7 @@ DynamicGroupBy_agg = function(...) {
     include_boundaries = prv$include_boundaries,
     closed = prv$closed,
     label = prv$label,
-    by = prv$by,
+    group_by = prv$group_by,
     start_by = prv$start_by,
     check_sorted = prv$check_sorted
   )$

R/group_by_rolling.R

@@ -36,7 +36,7 @@ RPolarsRollingGroupBy = new.env(parent = emptyenv())
 #' The internal RollingGroupBy constructor
 #' @return The input as grouped DataFrame
 #' @noRd
-construct_rolling_group_by = function(df, index_column, period, offset, closed, by, check_sorted) {
+construct_rolling_group_by = function(df, index_column, period, offset, closed, group_by, check_sorted) {
   if (!inherits(df, "RPolarsDataFrame")) {
     stop("internal error: construct_group called not on DataFrame")
   }
@@ -50,7 +50,7 @@ construct_rolling_group_by = function(df, index_column, period, offset, closed,
     period = period,
     offset = offset,
     closed = closed,
-    by = by,
+    group_by = group_by,
     check_sorted = check_sorted
   )
   class(out) = "RPolarsRollingGroupBy"
@@ -96,7 +96,7 @@ RollingGroupBy_agg = function(...) {
     period = prv$period,
     offset = prv$offset,
     closed = prv$closed,
-    by = prv$by,
+    group_by = prv$group_by,
     check_sorted = prv$check_sorted
   )$
     agg(unpack_list(..., .context = "in $agg():"))$

R/lazyframe__lazy.R

@@ -1793,36 +1793,47 @@ LazyFrame_with_context = function(other) {
 #' case of a rolling group by on indices, dtype needs to be either Int32 or Int64.
 #' Note that Int32 gets temporarily cast to Int64, so if performance matters use
 #' an Int64 column.
-#' @param by Also group by this column/these columns.
+#' @param group_by Also group by this column/these columns.
 #'
+#' @inheritSection polars_duration_string  Polars duration string language
 #' @return A [LazyGroupBy][LazyGroupBy_class] object
-#'
+#' @seealso
+#' - [`<LazyFrame>$group_by_dynamic()`][LazyFrame_group_by_dynamic]
 #' @examples
-#' df = pl$LazyFrame(
-#'   dt = c("2020-01-01", "2020-01-01", "2020-01-01", "2020-01-02", "2020-01-03", "2020-01-08"),
-#'   a = c(3, 7, 5, 9, 2, 1)
-#' )$with_columns(
-#'   pl$col("dt")$str$strptime(pl$Date, format = NULL)$set_sorted()
+#' dates = c(
+#'   "2020-01-01 13:45:48",
+#'   "2020-01-01 16:42:13",
+#'   "2020-01-01 16:45:09",
+#'   "2020-01-02 18:12:48",
+#'   "2020-01-03 19:45:32",
+#'   "2020-01-08 23:16:43"
 #' )
 #'
-#' df$collect()
+#' df = pl$LazyFrame(dt = dates, a = c(3, 7, 5, 9, 2, 1))$with_columns(
+#'   pl$col("dt")$str$strptime(pl$Datetime())$set_sorted()
+#' )
 #'
 #' df$rolling(index_column = "dt", period = "2d")$agg(
-#'   pl$col("a"),
-#'   pl$sum("a")$alias("sum_a"),
-#'   pl$min("a")$alias("min_a"),
-#'   pl$max("a")$alias("max_a")
+#'   sum_a = pl$sum("a"),
+#'   min_a = pl$min("a"),
+#'   max_a = pl$max("a")
 #' )$collect()
 LazyFrame_rolling = function(
-    index_column, ..., period, offset = NULL, closed = "right", by = NULL, check_sorted = TRUE) {
+    index_column,
+    ...,
+    period,
+    offset = NULL,
+    closed = "right",
+    group_by = NULL,
+    check_sorted = TRUE) {
   if (is.null(offset)) {
-    offset = paste0("-", period)
+    offset = paste0("-", period) # TODO: `paste0` should be executed after `period` is parsed as string
   }
   .pr$LazyFrame$rolling(
     self, index_column, period, offset, closed,
-    wrap_elist_result(by, str_to_lit = FALSE), check_sorted
+    wrap_elist_result(group_by, str_to_lit = FALSE), check_sorted
   ) |>
-    unwrap("in $rolling():")
+    unwrap("in <LazyFrame>$rolling():")
 }
 
 
@@ -1848,7 +1859,8 @@ LazyFrame_rolling = function(
 #'   starts the window on the Monday before the first data point, etc.
 #'
 #' @return A [LazyGroupBy][LazyGroupBy_class] object
-#'
+#' @seealso
+#' - [`<LazyFrame>$rolling()`][LazyFrame_rolling]
 #' @examples
 #' lf = pl$LazyFrame(
 #'   time = pl$date_range(
@@ -1895,7 +1907,7 @@ LazyFrame_rolling = function(
 #'   "time",
 #'   every = "1h",
 #'   closed = "both",
-#'   by = "groups",
+#'   group_by = "groups",
 #'   include_boundaries = TRUE
 #' )$agg(pl$col("n"))$collect()
 #'
@@ -1922,18 +1934,18 @@ LazyFrame_group_by_dynamic = function(
     include_boundaries = FALSE,
     closed = "left",
     label = "left",
-    by = NULL,
+    group_by = NULL,
     start_by = "window",
     check_sorted = TRUE) {
   if (is.null(offset)) {
-    offset = paste0("-", every)
+    offset = paste0("-", every) # TODO: `paste0` should be executed after `period` is parsed as string
   }
   if (is.null(period)) {
     period = every
   }
   .pr$LazyFrame$group_by_dynamic(
     self, index_column, every, period, offset, label, include_boundaries, closed,
-    wrap_elist_result(by, str_to_lit = FALSE), start_by, check_sorted
+    wrap_elist_result(group_by, str_to_lit = FALSE), start_by, check_sorted
   ) |>
     unwrap("in $group_by_dynamic():")
 }