Skip to content

Pivot data from long to wide

Source code

Description

Pivot data from long to wide

Usage

<DataFrame>$pivot(
  on,
  ...,
  index,
  values,
  aggregate_function = NULL,
  maintain_order = TRUE,
  sort_columns = FALSE,
  separator = "_"
)

Arguments

on Name of the column(s) whose values will be used as the header of the output DataFrame.
… Not used.
index One or multiple keys to group by.
values Column values to aggregate. Can be multiple columns if the on arguments contains multiple columns as well.
aggregate_function One of:
  • string indicating the expressions to aggregate with, such as ‘first’, ‘sum’, ‘max’, ‘min’, ‘mean’, ‘median’, ‘last’, ‘count’),
  • an Expr e.g. pl$element()$sum()
maintain_order Sort the grouped keys so that the output order is predictable.
sort_columns Sort the transposed columns by name. Default is by order of discovery.
separator Used as separator/delimiter in generated column names.

Value

DataFrame

Examples

library("polars")

df = pl$DataFrame(
  foo = c("one", "one", "one", "two", "two", "two"),
  bar = c("A", "B", "C", "A", "B", "C"),
  baz = c(1, 2, 3, 4, 5, 6)
)
df

#> shape: (6, 3)
#> ┌─────┬─────┬─────┐
#> │ foo ┆ bar ┆ baz │
#> │ --- ┆ --- ┆ --- │
#> │ str ┆ str ┆ f64 │
#> ╞═════╪═════╪═════╡
#> │ one ┆ A   ┆ 1.0 │
#> │ one ┆ B   ┆ 2.0 │
#> │ one ┆ C   ┆ 3.0 │
#> │ two ┆ A   ┆ 4.0 │
#> │ two ┆ B   ┆ 5.0 │
#> │ two ┆ C   ┆ 6.0 │
#> └─────┴─────┴─────┘

df$pivot(
  values = "baz", index = "foo", on = "bar"
)

#> shape: (2, 4)
#> ┌─────┬─────┬─────┬─────┐
#> │ foo ┆ A   ┆ B   ┆ C   │
#> │ --- ┆ --- ┆ --- ┆ --- │
#> │ str ┆ f64 ┆ f64 ┆ f64 │
#> ╞═════╪═════╪═════╪═════╡
#> │ one ┆ 1.0 ┆ 2.0 ┆ 3.0 │
#> │ two ┆ 4.0 ┆ 5.0 ┆ 6.0 │
#> └─────┴─────┴─────┴─────┘

# Run an expression as aggregation function
df = pl$DataFrame(
  col1 = c("a", "a", "a", "b", "b", "b"),
  col2 = c("x", "x", "x", "x", "y", "y"),
  col3 = c(6, 7, 3, 2, 5, 7)
)
df

#> shape: (6, 3)
#> ┌──────┬──────┬──────┐
#> │ col1 ┆ col2 ┆ col3 │
#> │ ---  ┆ ---  ┆ ---  │
#> │ str  ┆ str  ┆ f64  │
#> ╞══════╪══════╪══════╡
#> │ a    ┆ x    ┆ 6.0  │
#> │ a    ┆ x    ┆ 7.0  │
#> │ a    ┆ x    ┆ 3.0  │
#> │ b    ┆ x    ┆ 2.0  │
#> │ b    ┆ y    ┆ 5.0  │
#> │ b    ┆ y    ┆ 7.0  │
#> └──────┴──────┴──────┘

df$pivot(
  index = "col1",
  on = "col2",
  values = "col3",
  aggregate_function = pl$element()$tanh()$mean()
)

#> shape: (2, 3)
#> ┌──────┬──────────┬──────────┐
#> │ col1 ┆ x        ┆ y        │
#> │ ---  ┆ ---      ┆ ---      │
#> │ str  ┆ f64      ┆ f64      │
#> ╞══════╪══════════╪══════════╡
#> │ a    ┆ 0.998347 ┆ null     │
#> │ b    ┆ 0.964028 ┆ 0.999954 │
#> └──────┴──────────┴──────────┘