release: Release 0.7.0

.Rbuildignore

@@ -16,3 +16,5 @@
 ^\.venv$
 ^Makefile$
 ^src/\.cargo$
+^cran-comments\.md$
+^CRAN-SUBMISSION$

CRAN-SUBMISSION

@@ -0,0 +1,3 @@
+Version: 0.7.0
+Date: 2023-07-06 23:17:33 UTC
+SHA: 45a6aac59da02d77628026744ebb9447fd7e9a2c

DESCRIPTION

@@ -1,14 +1,17 @@
 Package: polars
-Title: 'Polars' Ported to R
-Version: 0.6.1.9000
+Title: Lightning-Fast 'DataFrame' Library
+Version: 0.7.0
 Depends: R (>= 4.1.0)
 Imports: utils, codetools
 Authors@R:
  c(person("Ritchie", "Vink", , "ritchie46@gmail.com", role = c("aut")),
- person("Soren", "Welling", , "sorhawell@gmail.com", role = c("aut","cre")))
-Description: 'Polars' is a lightning fast Data Frame library written in Rust.
- This package allows converting R data to 'Polars' data and vice versa,
- and enabling fast data processing with 'Polars'.
+ person("Soren", "Welling", , "sorhawell@gmail.com", role = c("aut","cre")),
+ person("Tatsuya", "Shima", , "ts1s1andn@gmail.com", role = c("aut")),
+ person("Etienne", "Bacher", , "etienne.bacher@protonmail.com", role = c("ctb")))
+Description: Lightning-fast DataFrame library written in 'Rust'. Convert R data
+ to 'Polars' data and vice versa. Perform fast, lazy, larger-than-memory and
+ optimized data queries. 'Polars' is interoperable with the package 'arrow',
+ as both are based on 'Apache Arrow' Columnar Format.
 License: MIT + file LICENSE
 Language: en-US
 Encoding: UTF-8

NEWS.md

@@ -1,12 +1,11 @@
-# polars (development version)
+# polars 0.7.0
 
 ## BREAKING CHANGES
 
 - Replace the argument `reverse` by `descending` in all sorting functions. This
  is for consistency with the upstream Polars (#291, #293).
 - Bump rust-polars from 2023-04-20 unreleased version to version 0.30.0 released in 2023-05-30 (#289).
  - Rename `concat_lst` to `concat_list`.
- <!-- TODO: - Rename `arr` to `list`. -->
  - Rename `$str$explode` to `$str$str_explode`.
  - Remove `tz_aware` and `utc` arguments from `str_parse`.
  - in `$date_range`'s the `lazy` argument is now `TRUE` by default.
@@ -37,7 +36,11 @@ for demonstration purposes (#240).
 - `<DataFrame>$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 `$join()`
+- Cross joining is now possible with `how = "cross"` in `$join()` (#310).
+- Add license info of all rust crates to `LICENSE.note` (#309).
+- With CRAN 0.7.0 release candidate (#308).
+ - New author accredited, SHIMA Tatsuya (@eitsupi).
+ - DESCRIPTION revised.
 
 # polars 0.6.1
 
@@ -138,7 +141,7 @@ Release date: 2023-02-21. Full Changelog: [v0.4.3...v0.4.5](https://github.com/p
 - Customize **extendr** to better support cross Rust-R/R-Rust error handling
  - bump extendr_api by @sorhawell in #44
  - Str even more by @sorhawell in #47
-- **rpolars** is now available for install from [rpolars.r-universe.dev](https://rpolars.r-universe.dev/rpolars#install) @eitsupi
+- **rpolars** is now available for install from [rpolars.r-universe.dev](https://rpolars.r-universe.dev/polars#install) @eitsupi
  - advertise R-universe by @sorhawell in #39
  - Includes reasonably easy pre-compiled installation for arm64-MacBooks
 - All string Expressions available

R/dataframe__frame.R

@@ -658,7 +658,7 @@ DataFrame_to_series = function(idx = 0) {
 #' @description sort a DataFrame by on or more Expr.
 #'
 #' @param by Column(s) to sort by. Column name strings, character vector of
-#' column names, or Iterable Into<Expr> (e.g. one Expr, or list mixed Expr and
+#' column names, or Iterable `Into<Expr>` (e.g. one Expr, or list mixed Expr and
 #' column name strings).
 #' @param ... more columns to sort by as above but provided one Expr per argument.
 #' @param descending Sort descending? Default = FALSE logical vector of length 1 or same length

R/expr__datetime.R

@@ -22,6 +22,7 @@
 #' @return Date/Datetime expr
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$truncate
 #' @examples
 #' t1 = as.POSIXct("3040-01-01", tz = "GMT")
@@ -74,6 +75,7 @@ ExprDT_truncate = function(
 #' @return Date/Datetime expr
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$round
 #' @examples
 #' t1 = as.POSIXct("3040-01-01", tz = "GMT")
@@ -115,6 +117,7 @@ ExprDT_round = function(every, offset = NULL) {
 #' @return Date/Datetime expr
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$combine
 #' @examples
 #' # Using pl$PTime
@@ -148,6 +151,7 @@ ExprDT_combine = function(tm, tu = "us") {
 #' @return Date/Datetime expr
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$strftime
 #' @examples
 #' pl$lit(as.POSIXct("2021-01-02 12:13:14", tz = "GMT"))$dt$strftime("this is the year: %Y")$to_r()
@@ -166,6 +170,7 @@ ExprDT_strftime = function(fmt) {
 #' @return Expr of Year as Int32
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$year
 #' @examples
 #' df = pl$DataFrame(
@@ -197,6 +202,7 @@ ExprDT_year = function() {
 #' @return Expr of iso_year as Int32
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$iso_year
 #' @examples
 #' df = pl$DataFrame(
@@ -226,6 +232,7 @@ ExprDT_iso_year = function() {
 #' @return Expr of quarter as UInt32
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$quarter
 #' @examples
 #' df = pl$DataFrame(
@@ -254,6 +261,7 @@ ExprDT_quarter = function() {
 #' @return Expr of month as UInt32
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dtmonth
 #' @examples
 #' df = pl$DataFrame(
@@ -283,6 +291,7 @@ ExprDT_month = function() {
 #' @return Expr of week as UInt32
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$week
 #' @examples
 #' df = pl$DataFrame(
@@ -310,6 +319,7 @@ ExprDT_week = function() {
 #' @return Expr of weekday as UInt32
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$weekday
 #' @examples
 #' df = pl$DataFrame(
@@ -339,6 +349,7 @@ ExprDT_weekday = function() {
 #' @return Expr of day as UInt32
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$day
 #' @examples
 #' df = pl$DataFrame(
@@ -367,6 +378,7 @@ ExprDT_day = function() {
 #' @return Expr of ordinal_day as UInt32
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$ordinal_day
 #' @examples
 #' df = pl$DataFrame(
@@ -395,6 +407,7 @@ ExprDT_ordinal_day = function() {
 #' @return Expr of hour as UInt32
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$hour
 #' @examples
 #' df = pl$DataFrame(
@@ -422,6 +435,7 @@ ExprDT_hour = function() {
 #' @return Expr of minute as UInt32
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$minute
 #' @examples
 #' df = pl$DataFrame(
@@ -451,6 +465,7 @@ ExprDT_minute = function() {
 #' @return Expr of second as UInt32
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$second
 #' @examples
 #' pl$DataFrame(date = pl$date_range(
@@ -480,6 +495,7 @@ ExprDT_second = function(fractional = FALSE) {
 #' @return Expr of millisecond as Int64
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$millisecond
 #' @examples
 #' pl$DataFrame(date = pl$date_range(
@@ -504,6 +520,7 @@ ExprDT_millisecond = function() {
 #' @return Expr of microsecond as Int64
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$microsecond
 #' @examples
 #' pl$DataFrame(
@@ -535,6 +552,7 @@ ExprDT_microsecond = function() {
 #' @return Expr of second as Int64
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$nanosecond
 #' @examples
 #' pl$DataFrame(date = pl$date_range(
@@ -563,6 +581,7 @@ ExprDT_nanosecond = function() {
 #' @return Expr of epoch as UInt32
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$epoch
 #' @examples
 #' pl$date_range(as.Date("2022-1-1"), lazy = TRUE)$dt$epoch("ns")$lit_to_s()
@@ -596,6 +615,7 @@ ExprDT_epoch = function(tu = c("us", "ns", "ms", "s", "d")) {
 #' @return Expr of i64
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$timestamp
 #' @examples
 #' df = pl$DataFrame(
@@ -627,6 +647,7 @@ ExprDT_timestamp = function(tu = c("ns", "us", "ms")) {
 #' @return Expr of i64
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$with_time_unit
 #' @examples
 #' df = pl$DataFrame(
@@ -659,6 +680,7 @@ ExprDT_with_time_unit = function(tu = c("ns", "us", "ms")) {
 #' @return Expr of i64
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$cast_time_unit
 #' @examples
 #' df = pl$DataFrame(
@@ -689,6 +711,7 @@ ExprDT_cast_time_unit = function(tu = c("ns", "us", "ms")) {
 #' @keywords ExprDT
 #' @details corresponds to in R manually modifying the tzone attribute of POSIXt objects
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$convert_time_zone
 #' @examples
 #' df = pl$DataFrame(
@@ -731,6 +754,7 @@ ExprDT_convert_time_zone = function(tz) {
 #' @return Expr of i64
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$replace_time_zone
 #' @examples
 #' df_1 = pl$DataFrame(x = as.POSIXct("2009-08-07 00:00:01", tz = "America/New_York"))
@@ -773,6 +797,7 @@ ExprDT_replace_time_zone = function(tz, use_earliest = NULL) {
 #' @return Expr of i64
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$tz_localize
 #' @examples
 #' df = pl$DataFrame(
@@ -819,6 +844,7 @@ ExprDT_tz_localize = function(tz) {
 #' @return Expr of i64
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$days
 #' @examples
 #' df = pl$DataFrame(
@@ -843,6 +869,7 @@ ExprDT_days = function() {
 #' @return Expr of i64
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$hours
 #' @examples
 #' df = pl$DataFrame(
@@ -867,6 +894,7 @@ ExprDT_hours = function() {
 #' @return Expr of i64
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$minutes
 #' @examples
 #' df = pl$DataFrame(
@@ -892,6 +920,7 @@ ExprDT_minutes = function() {
 #' @return Expr of i64
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$seconds
 #' @examples
 #' df = pl$DataFrame(date = pl$date_range(
@@ -914,6 +943,7 @@ ExprDT_seconds = function() {
 #' @return Expr of i64
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$milliseconds
 #' @examples
 #' df = pl$DataFrame(date = pl$date_range(
@@ -936,6 +966,7 @@ ExprDT_milliseconds = function() {
 #' @return Expr of i64
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$microseconds
 #' @examples
 #' df = pl$DataFrame(date = pl$date_range(
@@ -958,6 +989,7 @@ ExprDT_microseconds = function() {
 #' @return Expr of i64
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$nanoseconds
 #' @examples
 #' df = pl$DataFrame(date = pl$date_range(
@@ -1005,6 +1037,7 @@ ExprDT_nanoseconds = function() {
 #' @return Date/Datetime expr
 #' @keywords ExprDT
 #' @format function
+#' @usage NULL
 #' @aliases (Expr)$dt$offset_by
 #' @examples
 #' df = pl$DataFrame(

R/expr__expr.R

@@ -124,7 +124,7 @@ wrap_e_result = function(e, str_to_lit = TRUE, argname = NULL) {
 #' @description make sure all elements of a list is wrapped as Expr
 #' DEPRECATED: prefer robj_to!(VecPlExpr) on rust side
 #' Capture any conversion error in the result
-#' @param elist a list Expr or any R object Into<Expr> (passable to pl$lit)
+#' @param elist a list Expr or any R object `Into<Expr>` (passable to pl$lit)
 #' @details
 #' Used internally to ensure an object is a list of expression
 #' The output is wrapped in a result, which can contain an ok or

R/expr__string.R

@@ -633,8 +633,8 @@ ExprStr_splitn = function(by, n) {
 #' @description
 #' Replace first matching regex/literal substring with a new string value.
 #' @keywords ExprStr
-#' @param pattern Into<Expr>, regex pattern
-#' @param value Into<Expr> replacement
+#' @param pattern `Into<Expr>`, regex pattern
+#' @param value `Into<Expr>` replacement
 #' @param literal bool, Treat pattern as a literal string.
 #'
 #' @return Expr of Utf8 Series
@@ -659,8 +659,8 @@ ExprStr_replace = function(pattern, value, literal = FALSE) {
 #' @description
 #' Replace all matching regex/literal substrings with a new string value.
 #' @keywords ExprStr
-#' @param pattern Into<Expr>, regex pattern
-#' @param value Into<Expr> replacement
+#' @param pattern `Into<Expr>`, regex pattern
+#' @param value `Into<Expr>` replacement
 #' @param literal bool, treat pattern as a literal string.
 #'
 #' @return Expr of Utf8 Series
@@ -684,8 +684,8 @@ ExprStr_replace_all = function(pattern, value, literal = FALSE) {
 #' @description
 #' Create subslices of the string values of a Utf8 Series.
 #' @keywords ExprStr
-#' @param pattern Into<Expr>, regex pattern
-#' @param value Into<Expr> replacement
+#' @param pattern `Into<Expr>`, regex pattern
+#' @param value `Into<Expr>` replacement
 #' @param literal bool, treat pattern as a literal string.
 #'
 #' @return Expr: Series of dtype Utf8.

R/lazyframe__lazy.R

@@ -613,7 +613,7 @@ LazyFrame_join = function(
 #' @description sort a LazyFrame by on or more Expr
 #'
 #' @param by Column(s) to sort by. Column name strings, character vector of
-#' column names, or Iterable Into<Expr> (e.g. one Expr, or list mixed Expr and
+#' column names, or Iterable `Into<Expr>` (e.g. one Expr, or list mixed Expr and
 #' column name strings).
 #' @param ... more columns to sort by as above but provided one Expr per argument.
 #' @param descending Sort descending? Default = FALSE logical vector of length 1 or same length