$over() should accept a vector of column names

[etiennebacher]

library(polars)

test <- pl$DataFrame(mtcars)

Works fine:

test$with_columns(
  pl$col("mpg")$mean()$over("cyl", "drat")
)
#> shape: (32, 11)
#> ┌──────┬─────┬───────┬───────┬───┬─────┬─────┬──────┬──────┐
#> │ mpg  ┆ cyl ┆ disp  ┆ hp    ┆ … ┆ vs  ┆ am  ┆ gear ┆ carb │
#> │ ---  ┆ --- ┆ ---   ┆ ---   ┆   ┆ --- ┆ --- ┆ ---  ┆ ---  │
#> │ f64  ┆ f64 ┆ f64   ┆ f64   ┆   ┆ f64 ┆ f64 ┆ f64  ┆ f64  │
#> ╞══════╪═════╪═══════╪═══════╪═══╪═════╪═════╪══════╪══════╡
#> │ 21.0 ┆ 6.0 ┆ 160.0 ┆ 110.0 ┆ … ┆ 0.0 ┆ 1.0 ┆ 4.0  ┆ 4.0  │
#> │ 21.0 ┆ 6.0 ┆ 160.0 ┆ 110.0 ┆ … ┆ 0.0 ┆ 1.0 ┆ 4.0  ┆ 4.0  │
#> │ 22.8 ┆ 4.0 ┆ 108.0 ┆ 93.0  ┆ … ┆ 1.0 ┆ 1.0 ┆ 4.0  ┆ 1.0  │
#> │ 21.4 ┆ 6.0 ┆ 258.0 ┆ 110.0 ┆ … ┆ 1.0 ┆ 0.0 ┆ 3.0  ┆ 1.0  │
#> │ …    ┆ …   ┆ …     ┆ …     ┆ … ┆ …   ┆ …   ┆ …    ┆ …    │
#> │ 15.8 ┆ 8.0 ┆ 351.0 ┆ 264.0 ┆ … ┆ 0.0 ┆ 1.0 ┆ 5.0  ┆ 4.0  │
#> │ 19.7 ┆ 6.0 ┆ 145.0 ┆ 175.0 ┆ … ┆ 0.0 ┆ 1.0 ┆ 5.0  ┆ 6.0  │
#> │ 15.0 ┆ 8.0 ┆ 301.0 ┆ 335.0 ┆ … ┆ 0.0 ┆ 1.0 ┆ 5.0  ┆ 8.0  │
#> │ 21.4 ┆ 4.0 ┆ 121.0 ┆ 109.0 ┆ … ┆ 1.0 ┆ 1.0 ┆ 4.0  ┆ 2.0  │
#> └──────┴─────┴───────┴───────┴───┴─────┴─────┴──────┴──────┘

A vector of column names is not accepted:

test$with_columns(
  pl$col("mpg")$mean()$over(c("cyl", "drat"))
)
#> Error: in $collect(): when calling $collect() on LazyFrame:
#> ComputeError(ErrString("The name: 'mpg' passed to `LazyFrame.with_columns` is duplicate\n\nError originated just after this operation:\nDF [\"mpg\", \"cyl\", \"disp\", \"hp\"]; PROJECT */11 COLUMNS; SELECTION: \"None\"")) When calling: 
#> [TRUNCATED]

This is annoying for example if I have a vector with column names:

vars = c("cyl", "drat")
test$with_columns(
  pl$col("mpg")$mean()$over(vars)
)
#> Error: in $collect(): when calling $collect() on LazyFrame:
#> ComputeError(ErrString("The name: 'mpg' passed to `LazyFrame.with_columns` is duplicate\n\nError originated just after this operation:\nDF [\"mpg\", \"cyl\", \"disp\", \"hp\"]; PROJECT */11 COLUMNS; SELECTION: \"None\"")) When calling: 
#> [TRUNCATED]

This behavior is inconsistent with the behavior of other functions like groupby() and select():

test$groupby(vars)
#> shape: (32, 11)
#> ┌──────┬─────┬───────┬───────┬───┬─────┬─────┬──────┬──────┐
#> │ mpg  ┆ cyl ┆ disp  ┆ hp    ┆ … ┆ vs  ┆ am  ┆ gear ┆ carb │
#> │ ---  ┆ --- ┆ ---   ┆ ---   ┆   ┆ --- ┆ --- ┆ ---  ┆ ---  │
#> │ f64  ┆ f64 ┆ f64   ┆ f64   ┆   ┆ f64 ┆ f64 ┆ f64  ┆ f64  │
#> ╞══════╪═════╪═══════╪═══════╪═══╪═════╪═════╪══════╪══════╡
#> │ 21.0 ┆ 6.0 ┆ 160.0 ┆ 110.0 ┆ … ┆ 0.0 ┆ 1.0 ┆ 4.0  ┆ 4.0  │
#> │ 21.0 ┆ 6.0 ┆ 160.0 ┆ 110.0 ┆ … ┆ 0.0 ┆ 1.0 ┆ 4.0  ┆ 4.0  │
#> │ 22.8 ┆ 4.0 ┆ 108.0 ┆ 93.0  ┆ … ┆ 1.0 ┆ 1.0 ┆ 4.0  ┆ 1.0  │
#> │ 21.4 ┆ 6.0 ┆ 258.0 ┆ 110.0 ┆ … ┆ 1.0 ┆ 0.0 ┆ 3.0  ┆ 1.0  │
#> │ …    ┆ …   ┆ …     ┆ …     ┆ … ┆ …   ┆ …   ┆ …    ┆ …    │
#> │ 15.8 ┆ 8.0 ┆ 351.0 ┆ 264.0 ┆ … ┆ 0.0 ┆ 1.0 ┆ 5.0  ┆ 4.0  │
#> │ 19.7 ┆ 6.0 ┆ 145.0 ┆ 175.0 ┆ … ┆ 0.0 ┆ 1.0 ┆ 5.0  ┆ 6.0  │
#> │ 15.0 ┆ 8.0 ┆ 301.0 ┆ 335.0 ┆ … ┆ 0.0 ┆ 1.0 ┆ 5.0  ┆ 8.0  │
#> │ 21.4 ┆ 4.0 ┆ 121.0 ┆ 109.0 ┆ … ┆ 1.0 ┆ 1.0 ┆ 4.0  ┆ 2.0  │
#> └──────┴─────┴───────┴───────┴───┴─────┴─────┴──────┴──────┘
#> groups: [[1]]
#> [1] "cyl"  "drat"
#> 
#> maintain order:  FALSE
test$select(pl$col(vars))
#> shape: (32, 2)
#> ┌─────┬──────┐
#> │ cyl ┆ drat │
#> │ --- ┆ ---  │
#> │ f64 ┆ f64  │
#> ╞═════╪══════╡
#> │ 6.0 ┆ 3.9  │
#> │ 6.0 ┆ 3.9  │
#> │ 4.0 ┆ 3.85 │
#> │ 6.0 ┆ 3.08 │
#> │ …   ┆ …    │
#> │ 8.0 ┆ 4.22 │
#> │ 6.0 ┆ 3.62 │
#> │ 8.0 ┆ 3.54 │
#> │ 4.0 ┆ 4.11 │
#> └─────┴──────┘

^{Created on 2023-06-30 with reprex v2.0.2}