Replace all values by different values
Description
This changes all the values in a column, either using a specific
replacement or a default one. See $replace() to replace
only a subset of values.
Usage
<Expr>$replace_strict(old, new, ..., default = NULL, return_dtype = NULL)
Arguments
old
|
Value or vector of values to replace. Accepts expression input. Vectors
are parsed as Series, other non-expression inputs are parsed as
literals. Also accepts a list of values like list(old =
new).
|
new
|
Value or vector of values to replace by. Accepts expression input.
Vectors are parsed as Series, other non-expression inputs are parsed as
literals. Length must match the length of old or have
length 1.
|
…
|
These dots are for future extensions and must be empty. |
default
|
Set values that were not replaced to this value. If NULL
(default), an error is raised if any values were not replaced. Accepts
expression input. Non-expression inputs are parsed as literals.
|
return_dtype
|
The data type of the resulting expression. If NULL
(default), the data type is determined automatically based on the other
inputs.
|
Details
The global string cache must be enabled when replacing categorical values.
Value
A polars expression
Examples
library("polars")
df <- pl$DataFrame(a = c(1, 2, 2, 3))
# "old" and "new" can take vectors of length 1 or of same length
df$with_columns(replaced = pl$col("a")$replace_strict(2, 100, default = 1))
#> shape: (4, 2)
#> ┌─────┬──────────┐
#> │ a ┆ replaced │
#> │ --- ┆ --- │
#> │ f64 ┆ f64 │
#> ╞═════╪══════════╡
#> │ 1.0 ┆ 1.0 │
#> │ 2.0 ┆ 100.0 │
#> │ 2.0 ┆ 100.0 │
#> │ 3.0 ┆ 1.0 │
#> └─────┴──────────┘
#> shape: (4, 2)
#> ┌─────┬──────────┐
#> │ a ┆ replaced │
#> │ --- ┆ --- │
#> │ f64 ┆ f64 │
#> ╞═════╪══════════╡
#> │ 1.0 ┆ 1.0 │
#> │ 2.0 ┆ 100.0 │
#> │ 2.0 ┆ 100.0 │
#> │ 3.0 ┆ 200.0 │
#> └─────┴──────────┘
# "old" can be a named list where names are values to replace, and values are
# the replacements
mapping <- list(`2` = 100, `3` = 200)
df$with_columns(replaced = pl$col("a")$replace_strict(mapping, default = -1))
#> shape: (4, 2)
#> ┌─────┬──────────┐
#> │ a ┆ replaced │
#> │ --- ┆ --- │
#> │ f64 ┆ f64 │
#> ╞═════╪══════════╡
#> │ 1.0 ┆ -1.0 │
#> │ 2.0 ┆ 100.0 │
#> │ 2.0 ┆ 100.0 │
#> │ 3.0 ┆ 200.0 │
#> └─────┴──────────┘
# By default, an error is raised if any non-null values were not replaced.
# Specify a default to set all values that were not matched.
tryCatch(
df$with_columns(replaced = pl$col("a")$replace_strict(mapping)),
error = function(e) print(e)
)
#> <error/rlang_error>
#> Error in `df$with_columns()`:
#> ! Evaluation failed in `$with_columns()`.
#> Caused by error:
#> ! Evaluation failed in `$collect()`.
#> Caused by error:
#> ! Invalid operation: incomplete mapping specified for `replace_strict`
#>
#> Hint: Pass a `default` value to set unmapped values.
#> ---
#> Backtrace:
#> ▆
#> 1. ├─base::tryCatch(...)
#> 2. │ └─base (local) tryCatchList(expr, classes, parentenv, handlers)
#> 3. │ └─base (local) tryCatchOne(expr, names, parentenv, handlers[[1L]])
#> 4. │ └─base (local) doTryCatch(return(expr), name, parentenv, handler)
#> 5. └─df$with_columns(replaced = pl$col("a")$replace_strict(mapping))
#> 6. ├─polars:::wrap(self$lazy()$with_columns(...)$collect(`_eager` = TRUE)) at neo-r-polars/R/dataframe-frame.R:428:3
#> 7. │ └─rlang::try_fetch(...) at neo-r-polars/R/utils-wrap.R:3:3
#> 8. │ ├─base::tryCatch(...)
#> 9. │ │ └─base (local) tryCatchList(expr, classes, parentenv, handlers)
#> 10. │ │ └─base (local) tryCatchOne(expr, names, parentenv, handlers[[1L]])
#> 11. │ │ └─base (local) doTryCatch(return(expr), name, parentenv, handler)
#> 12. │ └─base::withCallingHandlers(...)
#> 13. └─self$lazy()$with_columns(...)$collect(`_eager` = TRUE) at neo-r-polars/R/utils-wrap.R:3:3
#> 14. ├─polars:::wrap(...) at neo-r-polars/R/lazyframe-frame.R:284:3
#> 15. │ └─rlang::try_fetch(...) at neo-r-polars/R/utils-wrap.R:3:3
#> 16. │ ├─base::tryCatch(...)
#> 17. │ │ └─base (local) tryCatchList(expr, classes, parentenv, handlers)
#> 18. │ │ └─base (local) tryCatchOne(expr, names, parentenv, handlers[[1L]])
#> 19. │ │ └─base (local) doTryCatch(return(expr), name, parentenv, handler)
#> 20. │ └─base::withCallingHandlers(...)
#> 21. └─ldf$collect(engine) at neo-r-polars/R/lazyframe-frame.R:331:5
#> 22. └─polars:::.savvy_wrap_PlRDataFrame(...) at neo-r-polars/R/000-wrappers.R:3579:5
# one can specify the data type to return instead of automatically
# inferring it
df$with_columns(
replaced = pl$col("a")$replace_strict(
mapping,
default = 1, return_dtype = pl$Int32
)
)
#> shape: (4, 2)
#> ┌─────┬──────────┐
#> │ a ┆ replaced │
#> │ --- ┆ --- │
#> │ f64 ┆ i32 │
#> ╞═════╪══════════╡
#> │ 1.0 ┆ 1 │
#> │ 2.0 ┆ 100 │
#> │ 2.0 ┆ 100 │
#> │ 3.0 ┆ 200 │
#> └─────┴──────────┘
# "old", "new", and "default" can take Expr
df <- pl$DataFrame(a = c(1, 2, 2, 3), b = c(1.5, 2.5, 5, 1))
df$with_columns(
replaced = pl$col("a")$replace_strict(
old = pl$col("a")$max(),
new = pl$col("b")$sum(),
default = pl$col("b"),
)
)
#> shape: (4, 3)
#> ┌─────┬─────┬──────────┐
#> │ a ┆ b ┆ replaced │
#> │ --- ┆ --- ┆ --- │
#> │ f64 ┆ f64 ┆ f64 │
#> ╞═════╪═════╪══════════╡
#> │ 1.0 ┆ 1.5 ┆ 1.5 │
#> │ 2.0 ┆ 2.5 ┆ 2.5 │
#> │ 2.0 ┆ 5.0 ┆ 5.0 │
#> │ 3.0 ┆ 1.0 ┆ 10.0 │
#> └─────┴─────┴──────────┘