Merge branch 'main' into rewrite-makevars

DESCRIPTION

@@ -91,6 +91,8 @@ Collate:
     'functions__lazy.R'
     'functions__whenthen.R'
     'group_by.R'
+    'group_by_dynamic.R'
+    'group_by_rolling.R'
     'info.R'
     'ipc.R'
     'is_polars.R'

NAMESPACE

@@ -9,6 +9,7 @@ S3method("$",RPolarsChainedWhen)
 S3method("$",RPolarsDataFrame)
 S3method("$",RPolarsDataType)
 S3method("$",RPolarsDataTypeVector)
+S3method("$",RPolarsDynamicGroupBy)
 S3method("$",RPolarsErr)
 S3method("$",RPolarsExpr)
 S3method("$",RPolarsExprBinNameSpace)
@@ -26,6 +27,7 @@ S3method("$",RPolarsProtoExprArray)
 S3method("$",RPolarsRField)
 S3method("$",RPolarsRNullValues)
 S3method("$",RPolarsRThreadHandle)
+S3method("$",RPolarsRollingGroupBy)
 S3method("$",RPolarsSQLContext)
 S3method("$",RPolarsSeries)
 S3method("$",RPolarsStringCacheHolder)
@@ -68,6 +70,7 @@ S3method("[[",RPolarsChainedWhen)
 S3method("[[",RPolarsDataFrame)
 S3method("[[",RPolarsDataType)
 S3method("[[",RPolarsDataTypeVector)
+S3method("[[",RPolarsDynamicGroupBy)
 S3method("[[",RPolarsErr)
 S3method("[[",RPolarsExpr)
 S3method("[[",RPolarsGroupBy)
@@ -77,6 +80,7 @@ S3method("[[",RPolarsProtoExprArray)
 S3method("[[",RPolarsRField)
 S3method("[[",RPolarsRNullValues)
 S3method("[[",RPolarsRThreadHandle)
+S3method("[[",RPolarsRollingGroupBy)
 S3method("[[",RPolarsSQLContext)
 S3method("[[",RPolarsSeries)
 S3method("[[",RPolarsStringCacheHolder)
@@ -88,12 +92,14 @@ S3method("|",RPolarsExpr)
 S3method(.DollarNames,RPolarsChainedThen)
 S3method(.DollarNames,RPolarsChainedWhen)
 S3method(.DollarNames,RPolarsDataFrame)
+S3method(.DollarNames,RPolarsDynamicGroupBy)
 S3method(.DollarNames,RPolarsErr)
 S3method(.DollarNames,RPolarsExpr)
 S3method(.DollarNames,RPolarsGroupBy)
 S3method(.DollarNames,RPolarsLazyFrame)
 S3method(.DollarNames,RPolarsRField)
 S3method(.DollarNames,RPolarsRThreadHandle)
+S3method(.DollarNames,RPolarsRollingGroupBy)
 S3method(.DollarNames,RPolarsSQLContext)
 S3method(.DollarNames,RPolarsSeries)
 S3method(.DollarNames,RPolarsThen)
@@ -112,9 +118,11 @@ S3method(as.matrix,RPolarsLazyFrame)
 S3method(as.vector,RPolarsSeries)
 S3method(as_polars_df,ArrowTabular)
 S3method(as_polars_df,RPolarsDataFrame)
+S3method(as_polars_df,RPolarsDynamicGroupBy)
 S3method(as_polars_df,RPolarsGroupBy)
 S3method(as_polars_df,RPolarsLazyFrame)
 S3method(as_polars_df,RPolarsLazyGroupBy)
+S3method(as_polars_df,RPolarsRollingGroupBy)
 S3method(as_polars_df,RPolarsSeries)
 S3method(as_polars_df,data.frame)
 S3method(as_polars_df,default)
@@ -158,13 +166,15 @@ S3method(print,RPolarsChainedThen)
 S3method(print,RPolarsChainedWhen)
 S3method(print,RPolarsDataFrame)
 S3method(print,RPolarsDataType)
+S3method(print,RPolarsDynamicGroupBy)
 S3method(print,RPolarsErr)
 S3method(print,RPolarsExpr)
 S3method(print,RPolarsGroupBy)
 S3method(print,RPolarsLazyFrame)
 S3method(print,RPolarsLazyGroupBy)
 S3method(print,RPolarsRField)
 S3method(print,RPolarsRThreadHandle)
+S3method(print,RPolarsRollingGroupBy)
 S3method(print,RPolarsSQLContext)
 S3method(print,RPolarsSeries)
 S3method(print,RPolarsThen)

NEWS.md

@@ -14,7 +14,10 @@
 
 ### What's changed
 
--   New method `$rolling()` for `DataFrame` and `LazyFrame` (#682).
+-   New method `$rolling()` for `DataFrame` and `LazyFrame`. When this is
+    applied, it creates an object of class `RPolarsRollingGroupBy` (#682, #694).
+-   New method `$group_by_dynamic()` for `DataFrame` and `LazyFrame`. When this 
+    is applied, it creates an object of class `RPolarsDynamicGroupBy` (#691).
 -   New method `$sink_ndjson()` for LazyFrame (#681).
 -   New function `pl$duration()` to create a duration by components (week, day,
     hour, etc.), and use them with date(time) variables (#692).

R/as_polars.R

@@ -102,6 +102,13 @@ as_polars_df.RPolarsGroupBy = function(x, ...) {
   x$ungroup()
 }
 
+#' @rdname as_polars_df
+#' @export
+as_polars_df.RPolarsRollingGroupBy = as_polars_df.RPolarsGroupBy
+
+#' @rdname as_polars_df
+#' @export
+as_polars_df.RPolarsDynamicGroupBy = as_polars_df.RPolarsGroupBy
 
 #' @rdname as_polars_df
 #' @export

R/dataframe__frame.R

@@ -1828,8 +1828,96 @@ DataFrame_write_ndjson = function(file) {
 #'   pl$max("a")$alias("max_a")
 #' )
 DataFrame_rolling = function(index_column, period, offset = NULL, closed = "right", by = NULL, check_sorted = TRUE) {
-  out = self$lazy()$rolling(index_column, period, offset, closed, by, check_sorted)
-  attr(out, "is_rolling_group_by") = TRUE
-  class(out) = "RPolarsGroupBy"
-  out
+  if (is.null(offset)) {
+    offset = paste0("-", period)
+  }
+  construct_rolling_group_by(self, index_column, period, offset, closed, by, check_sorted)
+}
+
+#' @inherit LazyFrame_group_by_dynamic title description details params
+#' @return A [GroupBy][GroupBy_class] object
+#'
+#' @examples
+#' df = pl$DataFrame(
+#'   time = pl$date_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",
+#'     eager = TRUE,
+#'   ),
+#'   n = 0:6
+#' )
+#'
+#' # get the sum in the following hour relative to the "time" column
+#' df$group_by_dynamic("time", every = "1h")$agg(
+#'   vals = pl$col("n"),
+#'   sum = pl$col("n")$sum()
+#' )
+#'
+#' # using "include_boundaries = TRUE" is helpful to see the period considered
+#' df$group_by_dynamic("time", every = "1h", include_boundaries = TRUE)$agg(
+#'   vals = pl$col("n")
+#' )
+#'
+#' # in the example above, the values didn't include the one *exactly* 1h after
+#' # the start because "closed = 'left'" by default.
+#' # Changing it to "right" includes values that are exactly 1h after. Note that
+#' # the value at 00:00:00 now becomes included in the interval [23:00:00 - 00:00:00],
+#' # even if this interval wasn't there originally
+#' df$group_by_dynamic("time", every = "1h", closed = "right")$agg(
+#'   vals = pl$col("n")
+#' )
+#' # To keep both boundaries, we use "closed = 'both'". Some values now belong to
+#' # several groups:
+#' df$group_by_dynamic("time", every = "1h", closed = "both")$agg(
+#'   vals = pl$col("n")
+#' )
+#'
+#' # Dynamic group bys can also be combined with grouping on normal keys
+#' df = df$with_columns(groups = pl$Series(c("a", "a", "a", "b", "b", "a", "a")))
+#' df
+#'
+#' df$group_by_dynamic(
+#'   "time",
+#'   every = "1h",
+#'   closed = "both",
+#'   by = "groups",
+#'   include_boundaries = TRUE
+#' )$agg(pl$col("n"))
+#'
+#' # We can also create a dynamic group by based on an index column
+#' df = pl$LazyFrame(
+#'   idx = 0:5,
+#'   A = c("A", "A", "B", "B", "B", "C")
+#' )$with_columns(pl$col("idx")$set_sorted())
+#' df
+#'
+#' df$group_by_dynamic(
+#'   "idx",
+#'   every = "2i",
+#'   period = "3i",
+#'   include_boundaries = TRUE,
+#'   closed = "right"
+#' )$agg(A_agg_list = pl$col("A"))
+DataFrame_group_by_dynamic = function(
+    index_column,
+    every,
+    period = NULL,
+    offset = NULL,
+    include_boundaries = FALSE,
+    closed = "left",
+    label = "left",
+    by = NULL,
+    start_by = "window",
+    check_sorted = TRUE) {
+  if (is.null(offset)) {
+    offset = paste0("-", every)
+  }
+  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
+  )
 }

R/expr__expr.R

@@ -3507,6 +3507,7 @@ Expr_peak_max = function() {
 #' column represents an index, it has to be either Int32 or Int64. Note that
 #' Int32 gets temporarily cast to Int64, so if performance matters use an Int64
 #' column.
+#' @param ... Ignored.
 #' @param period Length of the window, must be non-negative.
 #' @param offset Offset of the window. Default is `-period`.
 #' @param closed Define which sides of the temporal interval are closed
@@ -3569,8 +3570,11 @@ Expr_peak_max = function() {
 #' df$with_columns(
 #'   sum_a_offset1 = pl$sum("a")$rolling(index_column = "dt", period = "2d", offset = "1d")
 #' )
-Expr_rolling = function(index_column, period, offset = NULL,
-                        closed = "right", check_sorted = TRUE) {
+Expr_rolling = function(
+    index_column,
+    ...,
+    period, offset = NULL,
+    closed = "right", check_sorted = TRUE) {
   if (is.null(offset)) {
     offset = paste0("-", period)
   }

R/extendr-wrappers.R

@@ -1121,6 +1121,8 @@ RPolarsLazyFrame$with_context <- function(contexts) .Call(wrap__RPolarsLazyFrame
 
 RPolarsLazyFrame$rolling <- function(index_column, period, offset, closed, by, check_sorted) .Call(wrap__RPolarsLazyFrame__rolling, self, index_column, period, offset, closed, by, check_sorted)
 
+RPolarsLazyFrame$group_by_dynamic <- function(index_column, every, period, offset, label, include_boundaries, closed, by, start_by, check_sorted) .Call(wrap__RPolarsLazyFrame__group_by_dynamic, self, index_column, every, period, offset, label, include_boundaries, closed, by, start_by, check_sorted)
+
 #' @export
 `$.RPolarsLazyFrame` <- function (self, name) { func <- RPolarsLazyFrame[[name]]; environment(func) <- environment(); func }
 

R/group_by.R

@@ -12,7 +12,6 @@
 NULL
 
 
-
 RPolarsGroupBy = new.env(parent = emptyenv())
 
 #' @export
@@ -25,28 +24,30 @@ RPolarsGroupBy = new.env(parent = emptyenv())
 #' @export
 `[[.RPolarsGroupBy` = `$.RPolarsGroupBy`
 
-#' @title auto complete $-access into a polars object
-#' @description called by the interactive R session internally
-#' @param x GroupBy
-#' @param pattern code-stump as string to auto-complete
-#' @return char vec
 #' @export
-#' @inherit .DollarNames.RPolarsDataFrame return
 #' @noRd
 .DollarNames.RPolarsGroupBy = function(x, pattern = "") {
   paste0(ls(RPolarsGroupBy, pattern = pattern), "()")
 }
 
-
 #' The internal GroupBy constructor
 #' @return The input as grouped DataFrame
 #' @noRd
 construct_group_by = function(df, groupby_input, maintain_order) {
-  if (!inherits(df, "RPolarsDataFrame")) stop("internal error: construct_group called not on DataFrame")
-  df = df$clone()
-  attr(df, "private") = list(groupby_input = unlist(groupby_input), maintain_order = maintain_order)
-  class(df) = "RPolarsGroupBy"
-  df
+  if (!inherits(df, "RPolarsDataFrame")) {
+    stop("internal error: construct_group called not on DataFrame")
+  }
+  # Make an empty object. Store everything (including data) in attributes, so
+  # that we can keep the RPolarsDataFrame class on the data but still return
+  # a RPolarsGroupBy object here.
+  out = c(" ")
+  attr(out, "private") = list(
+    dat = df$clone(),
+    groupby_input = unlist(groupby_input),
+    maintain_order = maintain_order
+  )
+  class(out) = "RPolarsGroupBy"
+  out
 }
 
 
@@ -58,13 +59,13 @@ construct_group_by = function(df, groupby_input, maintain_order) {
 #' @return self
 #' @export
 #'
-#' @examples pl$DataFrame(iris)$group_by("Species")
+#' @examples
+#' pl$DataFrame(iris)$group_by("Species")
 print.RPolarsGroupBy = function(x, ...) {
-  .pr$DataFrame$print(x)
-  cat("groups: ")
   prv = attr(x, "private")
-  cat(toString(prv$groupby_input))
-  cat("\nmaintain order: ", prv$maintain_order)
+  .pr$DataFrame$print(prv$dat)
+  cat("groups:", toString(prv$groupby_input))
+  cat("\nmaintain order:", prv$maintain_order)
   invisible(x)
 }
 
@@ -86,18 +87,13 @@ print.RPolarsGroupBy = function(x, ...) {
 #'   pl$col("bar")$mean()$alias("bar_tail_sum")
 #' )
 GroupBy_agg = function(...) {
-  if (isTRUE(attributes(self)[["is_rolling_group_by"]])) {
-    class(self) = "RPolarsLazyGroupBy"
-    self$agg(unpack_list(..., .context = "in $agg():"))$collect(no_optimization = TRUE)
-  } else {
-    class(self) = "RPolarsDataFrame"
-    self$lazy()$group_by(
-      attr(self, "private")$groupby_input,
-      maintain_order = attr(self, "private")$maintain_order
-    )$
-      agg(...)$
-      collect(no_optimization = TRUE)
-  }
+  prv = attr(self, "private")
+  prv$dat$lazy()$group_by(
+    prv$groupby_input,
+    maintain_order = prv$maintain_order
+  )$
+    agg(...)$
+    collect(no_optimization = TRUE)
 }
 
 
@@ -300,13 +296,6 @@ GroupBy_null_count = function() {
 #'
 #' gb$ungroup()
 GroupBy_ungroup = function() {
-  if (isTRUE(attributes(self)[["is_rolling_group_by"]])) {
-    class(self) = "RPolarsLazyGroupBy"
-    self = self$ungroup()$collect(no_optimization = TRUE)
-  } else {
-    self = .pr$DataFrame$clone_in_rust(self)
-    class(self) = "RPolarsDataFrame"
-    attr(self, "private") = NULL
-  }
-  self
+  prv = attr(self, "private")
+  prv$dat
 }