feat!: Update for polars 1.0.0 (#194)

Author: etiennebacher

.github/workflows/R-CMD-check.yml

@@ -60,7 +60,8 @@ jobs:
       - name: Install r-polars
         run: |
           Sys.setenv(NOT_CRAN = "true") # Enable installation with pre-built Rust library binary, or enable Rust caching
-          install.packages("polars", repos = "https://community.r-multiverse.org")
+          install.packages("polars", repos = c("https://community.r-multiverse.org", getOption("repos")))
+
         shell: Rscript {0}
 
       - name: Dependencies

DESCRIPTION

@@ -29,7 +29,7 @@ Imports:
     dplyr,
     glue,
     lifecycle,
-    polars (>= 0.21.0),
+    polars (>= 1.0.0),
     rlang,
     tidyr,
     tidyselect,

NAMESPACE

@@ -1,88 +1,85 @@
 # Generated by roxygen2: do not edit by hand
 
-S3method(add_count,RPolarsDataFrame)
-S3method(add_count,RPolarsLazyFrame)
-S3method(anti_join,RPolarsDataFrame)
-S3method(anti_join,RPolarsLazyFrame)
-S3method(arrange,RPolarsDataFrame)
-S3method(arrange,RPolarsLazyFrame)
-S3method(as_tibble,RPolarsDataFrame)
-S3method(as_tibble,RPolarsLazyFrame)
-S3method(as_tibble,tidypolars)
-S3method(collect,RPolarsLazyFrame)
-S3method(complete,RPolarsDataFrame)
-S3method(complete,RPolarsLazyFrame)
-S3method(compute,RPolarsLazyFrame)
-S3method(count,RPolarsDataFrame)
-S3method(count,RPolarsLazyFrame)
-S3method(cross_join,RPolarsDataFrame)
-S3method(cross_join,RPolarsLazyFrame)
-S3method(distinct,RPolarsDataFrame)
-S3method(distinct,RPolarsLazyFrame)
-S3method(drop_na,RPolarsDataFrame)
-S3method(drop_na,RPolarsLazyFrame)
-S3method(explain,RPolarsLazyFrame)
-S3method(fill,RPolarsDataFrame)
-S3method(fill,RPolarsLazyFrame)
-S3method(filter,RPolarsDataFrame)
-S3method(filter,RPolarsLazyFrame)
-S3method(full_join,RPolarsDataFrame)
-S3method(full_join,RPolarsLazyFrame)
-S3method(group_by,RPolarsDataFrame)
-S3method(group_by,RPolarsLazyFrame)
-S3method(group_keys,RPolarsDataFrame)
-S3method(group_keys,RPolarsLazyFrame)
-S3method(group_split,RPolarsDataFrame)
-S3method(group_vars,RPolarsDataFrame)
-S3method(group_vars,RPolarsLazyFrame)
-S3method(inner_join,RPolarsDataFrame)
-S3method(inner_join,RPolarsLazyFrame)
-S3method(left_join,RPolarsDataFrame)
-S3method(left_join,RPolarsLazyFrame)
-S3method(mutate,RPolarsDataFrame)
-S3method(mutate,RPolarsLazyFrame)
-S3method(pivot_longer,RPolarsDataFrame)
-S3method(pivot_longer,RPolarsLazyFrame)
-S3method(pivot_wider,RPolarsDataFrame)
+S3method(add_count,polars_data_frame)
+S3method(add_count,polars_lazy_frame)
+S3method(anti_join,polars_data_frame)
+S3method(anti_join,polars_lazy_frame)
+S3method(arrange,polars_data_frame)
+S3method(arrange,polars_lazy_frame)
+S3method(collect,polars_lazy_frame)
+S3method(complete,polars_data_frame)
+S3method(complete,polars_lazy_frame)
+S3method(compute,polars_lazy_frame)
+S3method(count,polars_data_frame)
+S3method(count,polars_lazy_frame)
+S3method(cross_join,polars_data_frame)
+S3method(cross_join,polars_lazy_frame)
+S3method(distinct,polars_data_frame)
+S3method(distinct,polars_lazy_frame)
+S3method(drop_na,polars_data_frame)
+S3method(drop_na,polars_lazy_frame)
+S3method(explain,polars_lazy_frame)
+S3method(fill,polars_data_frame)
+S3method(fill,polars_lazy_frame)
+S3method(filter,polars_data_frame)
+S3method(filter,polars_lazy_frame)
+S3method(full_join,polars_data_frame)
+S3method(full_join,polars_lazy_frame)
+S3method(group_by,polars_data_frame)
+S3method(group_by,polars_lazy_frame)
+S3method(group_keys,polars_data_frame)
+S3method(group_keys,polars_lazy_frame)
+S3method(group_split,polars_data_frame)
+S3method(group_vars,polars_data_frame)
+S3method(group_vars,polars_lazy_frame)
+S3method(inner_join,polars_data_frame)
+S3method(inner_join,polars_lazy_frame)
+S3method(left_join,polars_data_frame)
+S3method(left_join,polars_lazy_frame)
+S3method(mutate,polars_data_frame)
+S3method(mutate,polars_lazy_frame)
+S3method(pivot_longer,polars_data_frame)
+S3method(pivot_longer,polars_lazy_frame)
+S3method(pivot_wider,polars_data_frame)
 S3method(print,tidypolars)
-S3method(pull,RPolarsDataFrame)
-S3method(pull,RPolarsLazyFrame)
-S3method(relocate,RPolarsDataFrame)
-S3method(relocate,RPolarsLazyFrame)
-S3method(rename,RPolarsDataFrame)
-S3method(rename,RPolarsLazyFrame)
-S3method(rename_with,RPolarsDataFrame)
-S3method(rename_with,RPolarsLazyFrame)
-S3method(replace_na,RPolarsDataFrame)
-S3method(replace_na,RPolarsLazyFrame)
-S3method(right_join,RPolarsDataFrame)
-S3method(right_join,RPolarsLazyFrame)
-S3method(rowwise,RPolarsDataFrame)
-S3method(rowwise,RPolarsLazyFrame)
-S3method(select,RPolarsDataFrame)
-S3method(select,RPolarsLazyFrame)
-S3method(semi_join,RPolarsDataFrame)
-S3method(semi_join,RPolarsLazyFrame)
-S3method(separate,RPolarsDataFrame)
-S3method(separate,RPolarsLazyFrame)
-S3method(slice_head,RPolarsDataFrame)
-S3method(slice_head,RPolarsLazyFrame)
-S3method(slice_sample,RPolarsDataFrame)
-S3method(slice_tail,RPolarsDataFrame)
-S3method(slice_tail,RPolarsLazyFrame)
-S3method(summarise,RPolarsDataFrame)
-S3method(summarise,RPolarsLazyFrame)
-S3method(summarize,RPolarsDataFrame)
-S3method(summarize,RPolarsLazyFrame)
-S3method(summary,RPolarsDataFrame)
-S3method(tally,RPolarsDataFrame)
-S3method(tally,RPolarsLazyFrame)
-S3method(uncount,RPolarsDataFrame)
-S3method(uncount,RPolarsLazyFrame)
-S3method(ungroup,RPolarsDataFrame)
-S3method(ungroup,RPolarsLazyFrame)
-S3method(unite,RPolarsDataFrame)
-S3method(unite,RPolarsLazyFrame)
+S3method(pull,polars_data_frame)
+S3method(pull,polars_lazy_frame)
+S3method(relocate,polars_data_frame)
+S3method(relocate,polars_lazy_frame)
+S3method(rename,polars_data_frame)
+S3method(rename,polars_lazy_frame)
+S3method(rename_with,polars_data_frame)
+S3method(rename_with,polars_lazy_frame)
+S3method(replace_na,polars_data_frame)
+S3method(replace_na,polars_lazy_frame)
+S3method(right_join,polars_data_frame)
+S3method(right_join,polars_lazy_frame)
+S3method(rowwise,polars_data_frame)
+S3method(rowwise,polars_lazy_frame)
+S3method(select,polars_data_frame)
+S3method(select,polars_lazy_frame)
+S3method(semi_join,polars_data_frame)
+S3method(semi_join,polars_lazy_frame)
+S3method(separate,polars_data_frame)
+S3method(separate,polars_lazy_frame)
+S3method(slice_head,polars_data_frame)
+S3method(slice_head,polars_lazy_frame)
+S3method(slice_sample,polars_data_frame)
+S3method(slice_tail,polars_data_frame)
+S3method(slice_tail,polars_lazy_frame)
+S3method(summarise,polars_data_frame)
+S3method(summarise,polars_lazy_frame)
+S3method(summarize,polars_data_frame)
+S3method(summarize,polars_lazy_frame)
+S3method(summary,polars_data_frame)
+S3method(tally,polars_data_frame)
+S3method(tally,polars_lazy_frame)
+S3method(uncount,polars_data_frame)
+S3method(uncount,polars_lazy_frame)
+S3method(ungroup,polars_data_frame)
+S3method(ungroup,polars_lazy_frame)
+S3method(unite,polars_data_frame)
+S3method(unite,polars_lazy_frame)
 export(as_polars_df)
 export(as_polars_lf)
 export(bind_cols_polars)
@@ -92,6 +89,9 @@ export(describe_optimized_plan)
 export(describe_plan)
 export(duplicated_rows)
 export(fetch)
+export(is_polars_df)
+export(is_polars_expr)
+export(is_polars_lf)
 export(make_unique_id)
 export(read_csv_polars)
 export(read_ipc_polars)
@@ -118,3 +118,6 @@ import(tidyr)
 importFrom(lifecycle,deprecated)
 importFrom(polars,as_polars_df)
 importFrom(polars,as_polars_lf)
+importFrom(polars,is_polars_df)
+importFrom(polars,is_polars_expr)
+importFrom(polars,is_polars_lf)

NEWS.md

@@ -1,5 +1,44 @@
 # tidypolars (development version)
 
+* `tidypolars` requires `polars` >= 1.0.0. This release of `polars` contains
+  many breaking changes. Those should be invisible to `tidypolars` users, with
+  the exception of deprecation messages (see below). However, if your code
+  contains user-defined functions that use `polars` syntax, you may need to
+  revise those (#194).
+
+## Deprecations and breaking changes
+
+* The following arguments are deprecated and will be removed in a future
+  version. The recommended replacement is indicated on the right of the arrow
+  (#194):
+  - in `compute()` and `collect()`: `streaming` -> `engine`;
+  - in `read_csv_polars()` and `scan_csv_polars()`:
+    * `dtypes` -> `schema_overrides`
+    * `reuse_downloaded` -> no replacement
+  - in `read_ndjson_polars` and `scan_ndjson_polars()`:
+    * `reuse_downloaded` -> no replacement
+  - in `read_ipc_polars` and `scan_ipc_polars()`:
+    * `memory_map` -> no replacement
+  - in `write_csv_polars()` and `sink_csv()`:
+    * `null_values` -> `null_value`
+    * `quote` -> `quote_char`
+  - in `write_ndjson_polars()`:
+    * `pretty` -> no replacement
+    * `row_oriented` -> no replacement
+  - in `write_ipc_polars()`:
+    * `future` -> `compat_level`
+    
+* `fetch()` is deprecated, use `head()` before `collect()` instead (#194).
+
+* `group_keys()` now returns a `tibble` and not a `data.frame` anymore (#194).
+
+* `lubridate::make_date()`, `lubridate::make_datetime()`, and `ISOdatetime()`
+  now error if some components go over their expected range, e.g. `month = 20`
+  or `hour = 25`. Before, those functions were returning `NA` in this situation
+  (#194).
+  
+* `summary()` returns an additional row for the 50% percentile (#194).
+
 ## New features
 
 * Added support for various `lubridate` functions:

R/arrange.R

@@ -22,7 +22,7 @@
 #'   group_by(x1) |>
 #'   arrange(-x2, .by_group = TRUE)
 
-arrange.RPolarsDataFrame <- function(.data, ..., .by_group = FALSE) {
+arrange.polars_data_frame <- function(.data, ..., .by_group = FALSE) {
   grps <- attributes(.data)$pl_grps
   mo <- attributes(data)$maintain_grp_order
   is_grouped <- !is.null(grps)
@@ -50,14 +50,14 @@ arrange.RPolarsDataFrame <- function(.data, ..., .by_group = FALSE) {
   }
 
   out <- if (is_grouped) {
-    .data$sort(polars_exprs, descending = descending, nulls_last = TRUE) |>
+    .data$sort(!!!polars_exprs, descending = descending, nulls_last = TRUE) |>
       group_by(all_of(grps), maintain_order = mo)
   } else {
-    .data$sort(polars_exprs, descending = descending, nulls_last = TRUE)
+    .data$sort(!!!polars_exprs, descending = descending, nulls_last = TRUE)
   }
 
   add_tidypolars_class(out)
 }
 
 #' @export
-arrange.RPolarsLazyFrame <- arrange.RPolarsDataFrame
+arrange.polars_lazy_frame <- arrange.polars_data_frame

R/as_tibble.R

@@ -78,10 +78,10 @@ concat_ <- function(..., how, .id = NULL, .name_repair = NULL) {
   }
 
   all_df <- all(
-    vapply(dots, inherits, "RPolarsDataFrame", FUN.VALUE = logical(1L))
+    vapply(dots, inherits, "polars_data_frame", FUN.VALUE = logical(1L))
   )
   all_lf <- all(
-    vapply(dots, inherits, "RPolarsLazyFrame", FUN.VALUE = logical(1L))
+    vapply(dots, inherits, "polars_lazy_frame", FUN.VALUE = logical(1L))
   )
 
   if (!(all_df || all_lf)) {
@@ -150,26 +150,27 @@ concat_ <- function(..., how, .id = NULL, .name_repair = NULL) {
 
           for (i in seq_along(dots)) {
             n_names <- ncol(dots[[i]])
-            dots[[i]] <- dots[[i]]$rename(mapping[1:n_names])
+            dots[[i]] <- dots[[i]]$rename(!!!mapping[1:n_names])
             mapping <- mapping[-(1:n_names)]
           }
         }
       }
 
-      if (inherits(dots[[1]], "RPolarsDataFrame")) {
-        pl$concat(dots, how = how)
+      if (is_polars_df(dots[[1]])) {
+        pl$concat(!!!dots, how = how)
       } else {
+        # TODO: remove this limitation
         if (length(dots) > 2) {
           cli_abort(
             "{.code bind_cols_polars()} doesn't work with more than two LazyFrames.",
             call = caller_env()
           )
         }
-        dots[[1]]$with_context(dots[[2]])$select(pl$all())
+        pl$concat(dots[[1]], dots[[2]], how = "horizontal")
       }
     },
     # default
-    pl$concat(dots, how = how)
+    pl$concat(!!!dots, how = how)
   )
   add_tidypolars_class(out)
 }