Class: Polars::Expr

Inherits:
Object
  • Object
show all
Defined in:
lib/polars/expr.rb

Overview

Expressions that can be used in various contexts.

Instance Method Summary collapse

Instance Method Details

#! ⇒ Expr

Performs boolean not.

Returns:



134
135
136
 
# File 'lib/polars/expr.rb', line 134

def !
  is_not
end

#!=(other) ⇒ Expr

Not equal.

Returns:



113
114
115
 
# File 'lib/polars/expr.rb', line 113

def !=(other)
  _from_rbexpr(_rbexpr.neq(_to_expr(other)._rbexpr))
end

#%(other) ⇒ Expr

Returns the modulo.

Returns:



77
78
79
 
# File 'lib/polars/expr.rb', line 77

def %(other)
  _from_rbexpr(_rbexpr % _to_rbexpr(other))
end

#&(other) ⇒ Expr

Bitwise AND.

Returns:



35
36
37
 
# File 'lib/polars/expr.rb', line 35

def &(other)
  _from_rbexpr(_rbexpr._and(_to_rbexpr(other)))
end

#*(other) ⇒ Expr

Performs multiplication.

Returns:



63
64
65
 
# File 'lib/polars/expr.rb', line 63

def *(other)
  _from_rbexpr(_rbexpr * _to_rbexpr(other))
end

#**(power) ⇒ Expr

Raises to the power of exponent.

Returns:



84
85
86
87
 
# File 'lib/polars/expr.rb', line 84

def **(power)
  exponent = Utils.parse_into_expression(power)
  _from_rbexpr(_rbexpr.pow(exponent))
end

#+(other) ⇒ Expr

Performs addition.

Returns:



49
50
51
 
# File 'lib/polars/expr.rb', line 49

def +(other)
  _from_rbexpr(_rbexpr + _to_rbexpr(other))
end

#-(other) ⇒ Expr

Performs subtraction.

Returns:



56
57
58
 
# File 'lib/polars/expr.rb', line 56

def -(other)
  _from_rbexpr(_rbexpr - _to_rbexpr(other))
end

#-@ ⇒ Expr

Performs negation.

Returns:



141
142
143
 
# File 'lib/polars/expr.rb', line 141

def -@
  _from_rbexpr(_rbexpr.neg)
end

#/(other) ⇒ Expr

Performs division.

Returns:



70
71
72
 
# File 'lib/polars/expr.rb', line 70

def /(other)
  _from_rbexpr(_rbexpr / _to_rbexpr(other))
end

#<(other) ⇒ Expr

Less than.

Returns:



120
121
122
 
# File 'lib/polars/expr.rb', line 120

def <(other)
  _from_rbexpr(_rbexpr.lt(_to_expr(other)._rbexpr))
end

#<=(other) ⇒ Expr

Less than or equal.

Returns:



99
100
101
 
# File 'lib/polars/expr.rb', line 99

def <=(other)
  _from_rbexpr(_rbexpr.lt_eq(_to_expr(other)._rbexpr))
end

#==(other) ⇒ Expr

Equal.

Returns:



106
107
108
 
# File 'lib/polars/expr.rb', line 106

def ==(other)
  _from_rbexpr(_rbexpr.eq(_to_expr(other)._rbexpr))
end

#>(other) ⇒ Expr

Greater than.

Returns:



127
128
129
 
# File 'lib/polars/expr.rb', line 127

def >(other)
  _from_rbexpr(_rbexpr.gt(_to_expr(other)._rbexpr))
end

#>=(other) ⇒ Expr

Greater than or equal.

Returns:



92
93
94
 
# File 'lib/polars/expr.rb', line 92

def >=(other)
  _from_rbexpr(_rbexpr.gt_eq(_to_expr(other)._rbexpr))
end

#^(other) ⇒ Expr

Bitwise XOR.

Returns:



28
29
30
 
# File 'lib/polars/expr.rb', line 28

def ^(other)
  _from_rbexpr(_rbexpr._xor(_to_rbexpr(other)))
end

#_hash(seed = 0, seed_1 = nil, seed_2 = nil, seed_3 = nil) ⇒ Expr

Hash the elements in the selection.

The hash value is of type :u64.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, nil],
    "b" => ["x", nil, "z"]
  }
)
df.with_column(Polars.all._hash(10, 20, 30, 40))
# =>
# shape: (3, 2)
# ┌──────────────────────┬──────────────────────┐
# │ a                    ┆ b                    │
# │ ---                  ┆ ---                  │
# │ u64                  ┆ u64                  │
# ╞══════════════════════╪══════════════════════╡
# │ 4629889412789719550  ┆ 6959506404929392568  │
# │ 16386608652769605760 ┆ 11638928888656214026 │
# │ 11638928888656214026 ┆ 11040941213715918520 │
# └──────────────────────┴──────────────────────┘

Parameters:

  • seed (Integer) (defaults to: 0) —

    Random seed parameter. Defaults to 0.

  • seed_1 (Integer) (defaults to: nil) —

    Random seed parameter. Defaults to seed if not set.

  • seed_2 (Integer) (defaults to: nil) —

    Random seed parameter. Defaults to seed if not set.

  • seed_3 (Integer) (defaults to: nil) —

    Random seed parameter. Defaults to seed if not set.

Returns:



3807
3808
3809
3810
3811
3812
3813
 
# File 'lib/polars/expr.rb', line 3807

def _hash(seed = 0, seed_1 = nil, seed_2 = nil, seed_3 = nil)
  k0 = seed
  k1 = seed_1.nil? ? seed : seed_1
  k2 = seed_2.nil? ? seed : seed_2
  k3 = seed_3.nil? ? seed : seed_3
  _from_rbexpr(_rbexpr._hash(k0, k1, k2, k3))
end

#abs ⇒ Expr

Compute absolute values.

Examples:

df = Polars::DataFrame.new(
  {
    "A" => [-1.0, 0.0, 1.0, 2.0]
  }
)
df.select(Polars.col("A").abs)
# =>
# shape: (4, 1)
# ┌─────┐
# │ A   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 1.0 │
# │ 0.0 │
# │ 1.0 │
# │ 2.0 │
# └─────┘

Returns:



5631
5632
5633
 
# File 'lib/polars/expr.rb', line 5631

def abs
  _from_rbexpr(_rbexpr.abs)
end

#add(other) ⇒ Expr

Method equivalent of addition operator expr + other.

Examples:

df = Polars::DataFrame.new({"x" => [1, 2, 3, 4, 5]})
df.with_columns(
  Polars.col("x").add(2).alias("x+int"),
  Polars.col("x").add(Polars.col("x").cum_prod).alias("x+expr")
)
# =>
# shape: (5, 3)
# ┌─────┬───────┬────────┐
# │ x   ┆ x+int ┆ x+expr │
# │ --- ┆ ---   ┆ ---    │
# │ i64 ┆ i64   ┆ i64    │
# ╞═════╪═══════╪════════╡
# │ 1   ┆ 3     ┆ 2      │
# │ 2   ┆ 4     ┆ 4      │
# │ 3   ┆ 5     ┆ 9      │
# │ 4   ┆ 6     ┆ 28     │
# │ 5   ┆ 7     ┆ 125    │
# └─────┴───────┴────────┘
df = Polars::DataFrame.new(
  {"x" => ["a", "d", "g"], "y": ["b", "e", "h"], "z": ["c", "f", "i"]}
)
df.with_columns(Polars.col("x").add(Polars.col("y")).add(Polars.col("z")).alias("xyz"))
# =>
# shape: (3, 4)
# ┌─────┬─────┬─────┬─────┐
# │ x   ┆ y   ┆ z   ┆ xyz │
# │ --- ┆ --- ┆ --- ┆ --- │
# │ str ┆ str ┆ str ┆ str │
# ╞═════╪═════╪═════╪═════╡
# │ a   ┆ b   ┆ c   ┆ abc │
# │ d   ┆ e   ┆ f   ┆ def │
# │ g   ┆ h   ┆ i   ┆ ghi │
# └─────┴─────┴─────┴─────┘

Parameters:

  • other (Object) —

    numeric or string value; accepts expression input.

Returns:



3396
3397
3398
 
# File 'lib/polars/expr.rb', line 3396

def add(other)
  self + other
end

#agg_groups ⇒ Expr

Get the group indexes of the group by operation.

Should be used in aggregation context only.

Examples:

df = Polars::DataFrame.new(
  {
    "group" => [
      "one",
      "one",
      "one",
      "two",
      "two",
      "two"
    ],
    "value" => [94, 95, 96, 97, 97, 99]
  }
)
df.group_by("group", maintain_order: true).agg(Polars.col("value").agg_groups)
# =>
# shape: (2, 2)
# ┌───────┬───────────┐
# │ group ┆ value     │
# │ ---   ┆ ---       │
# │ str   ┆ list[u32] │
# ╞═══════╪═══════════╡
# │ one   ┆ [0, 1, 2] │
# │ two   ┆ [3, 4, 5] │
# └───────┴───────────┘

Returns:



701
702
703
 
# File 'lib/polars/expr.rb', line 701

def agg_groups
  _from_rbexpr(_rbexpr.agg_groups)
end

#alias(name) ⇒ Expr

Rename the output of an expression.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, 3],
    "b" => ["a", "b", nil]
  }
)
df.select(
  [
    Polars.col("a").alias("bar"),
    Polars.col("b").alias("foo")
  ]
)
# =>
# shape: (3, 2)
# ┌─────┬──────┐
# │ bar ┆ foo  │
# │ --- ┆ ---  │
# │ i64 ┆ str  │
# ╞═════╪══════╡
# │ 1   ┆ a    │
# │ 2   ┆ b    │
# │ 3   ┆ null │
# └─────┴──────┘

Parameters:

Returns:



324
325
326
 
# File 'lib/polars/expr.rb', line 324

def alias(name)
  _from_rbexpr(_rbexpr._alias(name))
end

#all(drop_nulls: true) ⇒ Boolean

Check if all boolean values in a Boolean column are true.

This method is an expression - not to be confused with Polars.all which is a function to select all columns.

Examples:

df = Polars::DataFrame.new(
  {"TT" => [true, true], "TF" => [true, false], "FF" => [false, false]}
)
df.select(Polars.col("*").all)
# =>
# shape: (1, 3)
# ┌──────┬───────┬───────┐
# │ TT   ┆ TF    ┆ FF    │
# │ ---  ┆ ---   ┆ ---   │
# │ bool ┆ bool  ┆ bool  │
# ╞══════╪═══════╪═══════╡
# │ true ┆ false ┆ false │
# └──────┴───────┴───────┘

Returns:



223
224
225
 
# File 'lib/polars/expr.rb', line 223

def all(drop_nulls: true)
  _from_rbexpr(_rbexpr.all(drop_nulls))
end

#any(drop_nulls: true) ⇒ Boolean

Check if any boolean value in a Boolean column is true.

Examples:

df = Polars::DataFrame.new({"TF" => [true, false], "FF" => [false, false]})
df.select(Polars.all.any)
# =>
# shape: (1, 2)
# ┌──────┬───────┐
# │ TF   ┆ FF    │
# │ ---  ┆ ---   │
# │ bool ┆ bool  │
# ╞══════╪═══════╡
# │ true ┆ false │
# └──────┴───────┘

Returns:



198
199
200
 
# File 'lib/polars/expr.rb', line 198

def any(drop_nulls: true)
  _from_rbexpr(_rbexpr.any(drop_nulls))
end

#append(other, upcast: true) ⇒ Expr

Append expressions.

This is done by adding the chunks of other to this Series.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [8, 9, 10],
    "b" => [nil, 4, 4]
  }
)
df.select(Polars.all.head(1).append(Polars.all.tail(1)))
# =>
# shape: (2, 2)
# ┌─────┬──────┐
# │ a   ┆ b    │
# │ --- ┆ ---  │
# │ i64 ┆ i64  │
# ╞═════╪══════╡
# │ 8   ┆ null │
# │ 10  ┆ 4    │
# └─────┴──────┘

Parameters:

  • other (Expr) —

    Expression to append.

  • upcast (Boolean) (defaults to: true) —

    Cast both Series to the same supertype.

Returns:



813
814
815
816
 
# File 'lib/polars/expr.rb', line 813

def append(other, upcast: true)
  other = Utils.parse_into_expression(other)
  _from_rbexpr(_rbexpr.append(other, upcast))
end

#approx_n_unique ⇒ Expr Also known as: approx_unique

Approx count unique values.

This is done using the HyperLogLog++ algorithm for cardinality estimation.

Examples:

df = Polars::DataFrame.new({"a" => [1, 1, 2]})
df.select(Polars.col("a").approx_n_unique)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ u32 │
# ╞═════╡
# │ 2   │
# └─────┘

Returns:



2118
2119
2120
 
# File 'lib/polars/expr.rb', line 2118

def approx_n_unique
  _from_rbexpr(_rbexpr.approx_n_unique)
end

#arccos ⇒ Expr

Compute the element-wise value for the inverse cosine.

Examples:

df = Polars::DataFrame.new({"a" => [0.0]})
df.select(Polars.col("a").arccos)
# =>
# shape: (1, 1)
# ┌──────────┐
# │ a        │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ 1.570796 │
# └──────────┘

Returns:



6126
6127
6128
 
# File 'lib/polars/expr.rb', line 6126

def arccos
  _from_rbexpr(_rbexpr.arccos)
end

#arccosh ⇒ Expr

Compute the element-wise value for the inverse hyperbolic cosine.

Examples:

df = Polars::DataFrame.new({"a" => [1.0]})
df.select(Polars.col("a").arccosh)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 0.0 │
# └─────┘

Returns:



6246
6247
6248
 
# File 'lib/polars/expr.rb', line 6246

def arccosh
  _from_rbexpr(_rbexpr.arccosh)
end

#arcsin ⇒ Expr

Compute the element-wise value for the inverse sine.

Examples:

df = Polars::DataFrame.new({"a" => [1.0]})
df.select(Polars.col("a").arcsin)
# =>
# shape: (1, 1)
# ┌──────────┐
# │ a        │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ 1.570796 │
# └──────────┘

Returns:



6106
6107
6108
 
# File 'lib/polars/expr.rb', line 6106

def arcsin
  _from_rbexpr(_rbexpr.arcsin)
end

#arcsinh ⇒ Expr

Compute the element-wise value for the inverse hyperbolic sine.

Examples:

df = Polars::DataFrame.new({"a" => [1.0]})
df.select(Polars.col("a").arcsinh)
# =>
# shape: (1, 1)
# ┌──────────┐
# │ a        │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ 0.881374 │
# └──────────┘

Returns:



6226
6227
6228
 
# File 'lib/polars/expr.rb', line 6226

def arcsinh
  _from_rbexpr(_rbexpr.arcsinh)
end

#arctan ⇒ Expr

Compute the element-wise value for the inverse tangent.

Examples:

df = Polars::DataFrame.new({"a" => [1.0]})
df.select(Polars.col("a").arctan)
# =>
# shape: (1, 1)
# ┌──────────┐
# │ a        │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ 0.785398 │
# └──────────┘

Returns:



6146
6147
6148
 
# File 'lib/polars/expr.rb', line 6146

def arctan
  _from_rbexpr(_rbexpr.arctan)
end

#arctanh ⇒ Expr

Compute the element-wise value for the inverse hyperbolic tangent.

Examples:

df = Polars::DataFrame.new({"a" => [1.0]})
df.select(Polars.col("a").arctanh)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ inf │
# └─────┘

Returns:



6266
6267
6268
 
# File 'lib/polars/expr.rb', line 6266

def arctanh
  _from_rbexpr(_rbexpr.arctanh)
end

#arg_max ⇒ Expr

Get the index of the maximal value.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [20, 10, 30]
  }
)
df.select(Polars.col("a").arg_max)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ u32 │
# ╞═════╡
# │ 2   │
# └─────┘

Returns:



1443
1444
1445
 
# File 'lib/polars/expr.rb', line 1443

def arg_max
  _from_rbexpr(_rbexpr.arg_max)
end

#arg_min ⇒ Expr

Get the index of the minimal value.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [20, 10, 30]
  }
)
df.select(Polars.col("a").arg_min)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ u32 │
# ╞═════╡
# │ 1   │
# └─────┘

Returns:



1467
1468
1469
 
# File 'lib/polars/expr.rb', line 1467

def arg_min
  _from_rbexpr(_rbexpr.arg_min)
end

#arg_sort(reverse: false, nulls_last: false) ⇒ Expr

Get the index values that would sort this column.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [20, 10, 30]
  }
)
df.select(Polars.col("a").arg_sort)
# =>
# shape: (3, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ u32 │
# ╞═════╡
# │ 1   │
# │ 0   │
# │ 2   │
# └─────┘

Parameters:

  • reverse (Boolean) (defaults to: false) —

    Sort in reverse (descending) order.

  • nulls_last (Boolean) (defaults to: false) —

    Place null values last instead of first.

Returns:



1419
1420
1421
 
# File 'lib/polars/expr.rb', line 1419

def arg_sort(reverse: false, nulls_last: false)
  _from_rbexpr(_rbexpr.arg_sort(reverse, nulls_last))
end

#arg_unique ⇒ Expr

Get index of first unique value.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [8, 9, 10],
    "b" => [nil, 4, 4]
  }
)
df.select(Polars.col("a").arg_unique)
# =>
# shape: (3, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ u32 │
# ╞═════╡
# │ 0   │
# │ 1   │
# │ 2   │
# └─────┘
df.select(Polars.col("b").arg_unique)
# =>
# shape: (2, 1)
# ┌─────┐
# │ b   │
# │ --- │
# │ u32 │
# ╞═════╡
# │ 0   │
# │ 1   │
# └─────┘

Returns:



2184
2185
2186
 
# File 'lib/polars/expr.rb', line 2184

def arg_unique
  _from_rbexpr(_rbexpr.arg_unique)
end

#argsort(reverse: false, nulls_last: false) ⇒ expr

Get the index values that would sort this column.

Alias for #arg_sort.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [20, 10, 30]
  }
)
df.select(Polars.col("a").argsort)
# =>
# shape: (3, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ u32 │
# ╞═════╡
# │ 1   │
# │ 0   │
# │ 2   │
# └─────┘

Parameters:

  • reverse (Boolean) (defaults to: false) —

    Sort in reverse (descending) order.

  • nulls_last (Boolean) (defaults to: false) —

    Place null values last instead of first.

Returns:

  • (expr) 


5664
5665
5666
 
# File 'lib/polars/expr.rb', line 5664

def argsort(reverse: false, nulls_last: false)
  arg_sort(reverse: reverse, nulls_last: nulls_last)
end

#arr ⇒ ArrayExpr

Create an object namespace of all array related methods.

Returns:



7139
7140
7141
 
# File 'lib/polars/expr.rb', line 7139

def arr
  ArrayExpr.new(self)
end

#backward_fill(limit: nil) ⇒ Expr

Fill missing values with the next to be seen values.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, nil],
    "b" => [4, nil, 6]
  }
)
df.select(Polars.all.backward_fill)
# =>
# shape: (3, 2)
# ┌──────┬─────┐
# │ a    ┆ b   │
# │ ---  ┆ --- │
# │ i64  ┆ i64 │
# ╞══════╪═════╡
# │ 1    ┆ 4   │
# │ 2    ┆ 6   │
# │ null ┆ 6   │
# └──────┴─────┘

Parameters:

  • limit (Integer) (defaults to: nil) —

    The number of consecutive null values to backward fill.

Returns:



1859
1860
1861
 
# File 'lib/polars/expr.rb', line 1859

def backward_fill(limit: nil)
  _from_rbexpr(_rbexpr.backward_fill(limit))
end

#bin ⇒ BinaryExpr

Create an object namespace of all binary related methods.

Returns:



7146
7147
7148
 
# File 'lib/polars/expr.rb', line 7146

def bin
  BinaryExpr.new(self)
end

#bottom_k(k: 5) ⇒ Expr

Return the k smallest elements.

If 'reverse: true` the smallest elements will be given.

Examples:

df = Polars::DataFrame.new(
  {
    "value" => [1, 98, 2, 3, 99, 4]
  }
)
df.select(
  [
    Polars.col("value").top_k.alias("top_k"),
    Polars.col("value").bottom_k.alias("bottom_k")
  ]
)
# =>
# shape: (5, 2)
# ┌───────┬──────────┐
# │ top_k ┆ bottom_k │
# │ ---   ┆ ---      │
# │ i64   ┆ i64      │
# ╞═══════╪══════════╡
# │ 99    ┆ 1        │
# │ 98    ┆ 2        │
# │ 4     ┆ 3        │
# │ 3     ┆ 4        │
# │ 2     ┆ 98       │
# └───────┴──────────┘

Parameters:

  • k (Integer) (defaults to: 5) —

    Number of elements to return.

Returns:



1387
1388
1389
1390
 
# File 'lib/polars/expr.rb', line 1387

def bottom_k(k: 5)
  k = Utils.parse_into_expression(k)
  _from_rbexpr(_rbexpr.bottom_k(k))
end

#cast(dtype, strict: true) ⇒ Expr

Cast between data types.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, 3],
    "b" => ["4", "5", "6"]
  }
)
df.with_columns(
  [
    Polars.col("a").cast(:f64),
    Polars.col("b").cast(:i32)
  ]
)
# =>
# shape: (3, 2)
# ┌─────┬─────┐
# │ a   ┆ b   │
# │ --- ┆ --- │
# │ f64 ┆ i32 │
# ╞═════╪═════╡
# │ 1.0 ┆ 4   │
# │ 2.0 ┆ 5   │
# │ 3.0 ┆ 6   │
# └─────┴─────┘

Parameters:

  • dtype (Symbol) —

    DataType to cast to.

  • strict (Boolean) (defaults to: true) —

    Throw an error if a cast could not be done. For instance, due to an overflow.

Returns:



1234
1235
1236
1237
 
# File 'lib/polars/expr.rb', line 1234

def cast(dtype, strict: true)
  dtype = Utils.rb_type_to_dtype(dtype)
  _from_rbexpr(_rbexpr.cast(dtype, strict))
end

#cat ⇒ CatExpr

Create an object namespace of all categorical related methods.

Returns:



7153
7154
7155
 
# File 'lib/polars/expr.rb', line 7153

def cat
  CatExpr.new(self)
end

#ceil ⇒ Expr

Rounds up to the nearest integer value.

Only works on floating point Series.

Examples:

df = Polars::DataFrame.new({"a" => [0.3, 0.5, 1.0, 1.1]})
df.select(Polars.col("a").ceil)
# =>
# shape: (4, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 1.0 │
# │ 1.0 │
# │ 1.0 │
# │ 2.0 │
# └─────┘

Returns:



1113
1114
1115
 
# File 'lib/polars/expr.rb', line 1113

def ceil
  _from_rbexpr(_rbexpr.ceil)
end

#clip(lower_bound = nil, upper_bound = nil) ⇒ Expr

Set values outside the given boundaries to the boundary value.

Only works for numeric and temporal columns. If you want to clip other data types, consider writing a when-then-otherwise expression.

Examples:

df = Polars::DataFrame.new({"foo" => [-50, 5, nil, 50]})
df.with_column(Polars.col("foo").clip(1, 10).alias("foo_clipped"))
# =>
# shape: (4, 2)
# ┌──────┬─────────────┐
# │ foo  ┆ foo_clipped │
# │ ---  ┆ ---         │
# │ i64  ┆ i64         │
# ╞══════╪═════════════╡
# │ -50  ┆ 1           │
# │ 5    ┆ 5           │
# │ null ┆ null        │
# │ 50   ┆ 10          │
# └──────┴─────────────┘

Parameters:

  • lower_bound (Numeric) (defaults to: nil) —

    Minimum value.

  • upper_bound (Numeric) (defaults to: nil) —

    Maximum value.

Returns:



5888
5889
5890
5891
5892
5893
5894
5895
5896
 
# File 'lib/polars/expr.rb', line 5888

def clip(lower_bound = nil, upper_bound = nil)
  if !lower_bound.nil?
    lower_bound = Utils.parse_into_expression(lower_bound)
  end
  if !upper_bound.nil?
    upper_bound = Utils.parse_into_expression(upper_bound)
  end
  _from_rbexpr(_rbexpr.clip(lower_bound, upper_bound))
end

#clip_max(upper_bound) ⇒ Expr

Clip (limit) the values in an array to a max boundary.

Only works for numerical types.

If you want to clip other dtypes, consider writing a "when, then, otherwise" expression. See when for more information.

Examples:

df = Polars::DataFrame.new({"foo" => [-50, 5, nil, 50]})
df.with_column(Polars.col("foo").clip_max(0).alias("foo_clipped"))
# =>
# shape: (4, 2)
# ┌──────┬─────────────┐
# │ foo  ┆ foo_clipped │
# │ ---  ┆ ---         │
# │ i64  ┆ i64         │
# ╞══════╪═════════════╡
# │ -50  ┆ -50         │
# │ 5    ┆ 0           │
# │ null ┆ null        │
# │ 50   ┆ 0           │
# └──────┴─────────────┘

Parameters:

  • upper_bound (Numeric) —

    Maximum value.

Returns:



5956
5957
5958
 
# File 'lib/polars/expr.rb', line 5956

def clip_max(upper_bound)
  clip(nil, upper_bound)
end

#clip_min(lower_bound) ⇒ Expr

Clip (limit) the values in an array to a min boundary.

Only works for numerical types.

If you want to clip other dtypes, consider writing a "when, then, otherwise" expression. See when for more information.

Examples:

df = Polars::DataFrame.new({"foo" => [-50, 5, nil, 50]})
df.with_column(Polars.col("foo").clip_min(0).alias("foo_clipped"))
# =>
# shape: (4, 2)
# ┌──────┬─────────────┐
# │ foo  ┆ foo_clipped │
# │ ---  ┆ ---         │
# │ i64  ┆ i64         │
# ╞══════╪═════════════╡
# │ -50  ┆ 0           │
# │ 5    ┆ 5           │
# │ null ┆ null        │
# │ 50   ┆ 50          │
# └──────┴─────────────┘

Parameters:

  • lower_bound (Numeric) —

    Minimum value.

Returns:



5925
5926
5927
 
# File 'lib/polars/expr.rb', line 5925

def clip_min(lower_bound)
  clip(lower_bound, nil)
end

#cos ⇒ Expr

Compute the element-wise value for the cosine.

Examples:

df = Polars::DataFrame.new({"a" => [0.0]})
df.select(Polars.col("a").cos)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 1.0 │
# └─────┘

Returns:



6066
6067
6068
 
# File 'lib/polars/expr.rb', line 6066

def cos
  _from_rbexpr(_rbexpr.cos)
end

#cosh ⇒ Expr

Compute the element-wise value for the hyperbolic cosine.

Examples:

df = Polars::DataFrame.new({"a" => [1.0]})
df.select(Polars.col("a").cosh)
# =>
# shape: (1, 1)
# ┌──────────┐
# │ a        │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ 1.543081 │
# └──────────┘

Returns:



6186
6187
6188
 
# File 'lib/polars/expr.rb', line 6186

def cosh
  _from_rbexpr(_rbexpr.cosh)
end

#count ⇒ Expr

Count the number of values in this expression.

Examples:

df = Polars::DataFrame.new({"a" => [8, 9, 10], "b" => [nil, 4, 4]})
df.select(Polars.all.count)
# =>
# shape: (1, 2)
# ┌─────┬─────┐
# │ a   ┆ b   │
# │ --- ┆ --- │
# │ u32 ┆ u32 │
# ╞═════╪═════╡
# │ 3   ┆ 2   │
# └─────┴─────┘

Returns:



721
722
723
 
# File 'lib/polars/expr.rb', line 721

def count
  _from_rbexpr(_rbexpr.count)
end

#cum_count(reverse: false) ⇒ Expr Also known as: cumcount

Get an array with the cumulative count computed at every element.

Counting from 0 to len

Examples:

df = Polars::DataFrame.new({"a" => ["x", "k", nil, "d"]})
df.with_columns(
  [
    Polars.col("a").cum_count.alias("cum_count"),
    Polars.col("a").cum_count(reverse: true).alias("cum_count_reverse")
  ]
)
# =>
# shape: (4, 3)
# ┌──────┬───────────┬───────────────────┐
# │ a    ┆ cum_count ┆ cum_count_reverse │
# │ ---  ┆ ---       ┆ ---               │
# │ str  ┆ u32       ┆ u32               │
# ╞══════╪═══════════╪═══════════════════╡
# │ x    ┆ 1         ┆ 3                 │
# │ k    ┆ 2         ┆ 2                 │
# │ null ┆ 2         ┆ 1                 │
# │ d    ┆ 3         ┆ 1                 │
# └──────┴───────────┴───────────────────┘

Parameters:

  • reverse (Boolean) (defaults to: false) —

    Reverse the operation.

Returns:



1062
1063
1064
 
# File 'lib/polars/expr.rb', line 1062

def cum_count(reverse: false)
  _from_rbexpr(_rbexpr.cum_count(reverse))
end

#cum_max(reverse: false) ⇒ Expr Also known as: cummax

Get an array with the cumulative max computed at every element.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3, 4]})
df.select(
  [
    Polars.col("a").cum_max,
    Polars.col("a").cum_max(reverse: true).alias("a_reverse")
  ]
)
# =>
# shape: (4, 2)
# ┌─────┬───────────┐
# │ a   ┆ a_reverse │
# │ --- ┆ ---       │
# │ i64 ┆ i64       │
# ╞═════╪═══════════╡
# │ 1   ┆ 4         │
# │ 2   ┆ 4         │
# │ 3   ┆ 4         │
# │ 4   ┆ 4         │
# └─────┴───────────┘

Parameters:

  • reverse (Boolean) (defaults to: false) —

    Reverse the operation.

Returns:



1028
1029
1030
 
# File 'lib/polars/expr.rb', line 1028

def cum_max(reverse: false)
  _from_rbexpr(_rbexpr.cum_max(reverse))
end

#cum_min(reverse: false) ⇒ Expr Also known as: cummin

Get an array with the cumulative min computed at every element.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3, 4]})
df.select(
  [
    Polars.col("a").cum_min,
    Polars.col("a").cum_min(reverse: true).alias("a_reverse")
  ]
)
# =>
# shape: (4, 2)
# ┌─────┬───────────┐
# │ a   ┆ a_reverse │
# │ --- ┆ ---       │
# │ i64 ┆ i64       │
# ╞═════╪═══════════╡
# │ 1   ┆ 1         │
# │ 1   ┆ 2         │
# │ 1   ┆ 3         │
# │ 1   ┆ 4         │
# └─────┴───────────┘

Parameters:

  • reverse (Boolean) (defaults to: false) —

    Reverse the operation.

Returns:



996
997
998
 
# File 'lib/polars/expr.rb', line 996

def cum_min(reverse: false)
  _from_rbexpr(_rbexpr.cum_min(reverse))
end

#cum_prod(reverse: false) ⇒ Expr Also known as: cumprod

Note:

Dtypes in :i8, :u8, :i16, and :u16 are cast to :i64 before summing to prevent overflow issues.

Get an array with the cumulative product computed at every element.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3, 4]})
df.select(
  [
    Polars.col("a").cum_prod,
    Polars.col("a").cum_prod(reverse: true).alias("a_reverse")
  ]
)
# =>
# shape: (4, 2)
# ┌─────┬───────────┐
# │ a   ┆ a_reverse │
# │ --- ┆ ---       │
# │ i64 ┆ i64       │
# ╞═════╪═══════════╡
# │ 1   ┆ 24        │
# │ 2   ┆ 24        │
# │ 6   ┆ 12        │
# │ 24  ┆ 4         │
# └─────┴───────────┘

Parameters:

  • reverse (Boolean) (defaults to: false) —

    Reverse the operation.

Returns:



964
965
966
 
# File 'lib/polars/expr.rb', line 964

def cum_prod(reverse: false)
  _from_rbexpr(_rbexpr.cum_prod(reverse))
end

#cum_sum(reverse: false) ⇒ Expr Also known as: cumsum

Note:

Dtypes in :i8, :u8, :i16, and :u16 are cast to :i64 before summing to prevent overflow issues.

Get an array with the cumulative sum computed at every element.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3, 4]})
df.select(
  [
    Polars.col("a").cum_sum,
    Polars.col("a").cum_sum(reverse: true).alias("a_reverse")
  ]
)
# =>
# shape: (4, 2)
# ┌─────┬───────────┐
# │ a   ┆ a_reverse │
# │ --- ┆ ---       │
# │ i64 ┆ i64       │
# ╞═════╪═══════════╡
# │ 1   ┆ 10        │
# │ 3   ┆ 9         │
# │ 6   ┆ 7         │
# │ 10  ┆ 4         │
# └─────┴───────────┘

Parameters:

  • reverse (Boolean) (defaults to: false) —

    Reverse the operation.

Returns:



928
929
930
 
# File 'lib/polars/expr.rb', line 928

def cum_sum(reverse: false)
  _from_rbexpr(_rbexpr.cum_sum(reverse))
end

#cumulative_eval(expr, min_periods: 1, parallel: false) ⇒ Expr

Note:

This functionality is experimental and may change without it being considered a breaking change.

Note:

This can be really slow as it can have O(n^2) complexity. Don't use this for operations that visit all elements.

Run an expression over a sliding window that increases 1 slot every iteration.

Examples:

df = Polars::DataFrame.new({"values" => [1, 2, 3, 4, 5]})
df.select(
  [
    Polars.col("values").cumulative_eval(
      Polars.element.first - Polars.element.last ** 2
    )
  ]
)
# =>
# shape: (5, 1)
# ┌────────┐
# │ values │
# │ ---    │
# │ i64    │
# ╞════════╡
# │ 0      │
# │ -3     │
# │ -8     │
# │ -15    │
# │ -24    │
# └────────┘

Parameters:

  • expr (Expr) —

    Expression to evaluate

  • min_periods (Integer) (defaults to: 1) —

    Number of valid values there should be in the window before the expression is evaluated. valid values = length - null_count

  • parallel (Boolean) (defaults to: false) —

    Run in parallel. Don't do this in a group by or another operation that already has much parallelization.

Returns:



6721
6722
6723
6724
6725
 
# File 'lib/polars/expr.rb', line 6721

def cumulative_eval(expr, min_periods: 1, parallel: false)
  _from_rbexpr(
    _rbexpr.cumulative_eval(expr._rbexpr, min_periods, parallel)
  )
end

#cut(breaks, labels: nil, left_closed: false, include_breaks: false) ⇒ Expr

Bin continuous values into discrete categories.

Examples:

Divide a column into three categories.

df = Polars::DataFrame.new({"foo" => [-2, -1, 0, 1, 2]})
df.with_columns(
  Polars.col("foo").cut([-1, 1], labels: ["a", "b", "c"]).alias("cut")
)
# =>
# shape: (5, 2)
# ┌─────┬─────┐
# │ foo ┆ cut │
# │ --- ┆ --- │
# │ i64 ┆ cat │
# ╞═════╪═════╡
# │ -2  ┆ a   │
# │ -1  ┆ a   │
# │ 0   ┆ b   │
# │ 1   ┆ b   │
# │ 2   ┆ c   │
# └─────┴─────┘

Add both the category and the breakpoint.

df.with_columns(
  Polars.col("foo").cut([-1, 1], include_breaks: true).alias("cut")
).unnest("cut")
# =>
# shape: (5, 3)
# ┌─────┬────────────┬────────────┐
# │ foo ┆ breakpoint ┆ category   │
# │ --- ┆ ---        ┆ ---        │
# │ i64 ┆ f64        ┆ cat        │
# ╞═════╪════════════╪════════════╡
# │ -2  ┆ -1.0       ┆ (-inf, -1] │
# │ -1  ┆ -1.0       ┆ (-inf, -1] │
# │ 0   ┆ 1.0        ┆ (-1, 1]    │
# │ 1   ┆ 1.0        ┆ (-1, 1]    │
# │ 2   ┆ inf        ┆ (1, inf]   │
# └─────┴────────────┴────────────┘

Parameters:

  • breaks (Array) —

    List of unique cut points.

  • labels (Array) (defaults to: nil) —

    Names of the categories. The number of labels must be equal to the number of cut points plus one.

  • left_closed (Boolean) (defaults to: false) —

    Set the intervals to be left-closed instead of right-closed.

  • include_breaks (Boolean) (defaults to: false) —

    Include a column with the right endpoint of the bin each observation falls in. This will change the data type of the output from a Categorical to a Struct.

Returns:



2567
2568
2569
 
# File 'lib/polars/expr.rb', line 2567

def cut(breaks, labels: nil, left_closed: false, include_breaks: false)
  _from_rbexpr(_rbexpr.cut(breaks, labels, left_closed, include_breaks))
end

#diff(n: 1, null_behavior: "ignore") ⇒ Expr

Calculate the n-th discrete difference.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [20, 10, 30]
  }
)
df.select(Polars.col("a").diff)
# =>
# shape: (3, 1)
# ┌──────┐
# │ a    │
# │ ---  │
# │ i64  │
# ╞══════╡
# │ null │
# │ -10  │
# │ 20   │
# └──────┘

Parameters:

  • n (Integer) (defaults to: 1) —

    Number of slots to shift.

  • null_behavior ("ignore", "drop") (defaults to: "ignore") —

    How to handle null values.

Returns:



5759
5760
5761
 
# File 'lib/polars/expr.rb', line 5759

def diff(n: 1, null_behavior: "ignore")
  _from_rbexpr(_rbexpr.diff(n, null_behavior))
end

#dot(other) ⇒ Expr

Compute the dot/inner product between two Expressions.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 3, 5],
    "b" => [2, 4, 6]
  }
)
df.select(Polars.col("a").dot(Polars.col("b")))
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ i64 │
# ╞═════╡
# │ 44  │
# └─────┘

Parameters:

  • other (Expr) —

    Expression to compute dot product with.

Returns:



1167
1168
1169
1170
 
# File 'lib/polars/expr.rb', line 1167

def dot(other)
  other = Utils.parse_into_expression(other, str_as_lit: false)
  _from_rbexpr(_rbexpr.dot(other))
end

#drop_nans ⇒ Expr

Drop floating point NaN values.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [8, 9, 10, 11],
    "b" => [nil, 4.0, 4.0, Float::NAN]
  }
)
df.select(Polars.col("b").drop_nans)
# =>
# shape: (3, 1)
# ┌──────┐
# │ b    │
# │ ---  │
# │ f64  │
# ╞══════╡
# │ null │
# │ 4.0  │
# │ 4.0  │
# └──────┘

Returns:



893
894
895
 
# File 'lib/polars/expr.rb', line 893

def drop_nans
  _from_rbexpr(_rbexpr.drop_nans)
end

#drop_nulls ⇒ Expr

Drop null values.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [8, 9, 10, 11],
    "b" => [nil, 4.0, 4.0, Float::NAN]
  }
)
df.select(Polars.col("b").drop_nulls)
# =>
# shape: (3, 1)
# ┌─────┐
# │ b   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 4.0 │
# │ 4.0 │
# │ NaN │
# └─────┘

Returns:



866
867
868
 
# File 'lib/polars/expr.rb', line 866

def drop_nulls
  _from_rbexpr(_rbexpr.drop_nulls)
end

#dt ⇒ DateTimeExpr

Create an object namespace of all datetime related methods.

Returns:



7160
7161
7162
 
# File 'lib/polars/expr.rb', line 7160

def dt
  DateTimeExpr.new(self)
end

#entropy(base: 2, normalize: true) ⇒ Expr

Computes the entropy.

Uses the formula -sum(pk * log(pk) where pk are discrete probabilities.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3]})
df.select(Polars.col("a").entropy(base: 2))
# =>
# shape: (1, 1)
# ┌──────────┐
# │ a        │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ 1.459148 │
# └──────────┘
df.select(Polars.col("a").entropy(base: 2, normalize: false))
# =>
# shape: (1, 1)
# ┌───────────┐
# │ a         │
# │ ---       │
# │ f64       │
# ╞═══════════╡
# │ -6.754888 │
# └───────────┘

Parameters:

  • base (Float) (defaults to: 2) —

    Given base, defaults to e.

  • normalize (Boolean) (defaults to: true) —

    Normalize pk if it doesn't sum to 1.

Returns:



6674
6675
6676
 
# File 'lib/polars/expr.rb', line 6674

def entropy(base: 2, normalize: true)
  _from_rbexpr(_rbexpr.entropy(base, normalize))
end

#eq(other) ⇒ Expr

Method equivalent of equality operator expr == other.

Examples:

df = Polars::DataFrame.new(
  {
    "x" => [1.0, 2.0, Float::NAN, 4.0],
    "y" => [2.0, 2.0, Float::NAN, 4.0]
  }
)
df.with_columns(
  Polars.col("x").eq(Polars.col("y")).alias("x == y")
)
# =>
# shape: (4, 3)
# ┌─────┬─────┬────────┐
# │ x   ┆ y   ┆ x == y │
# │ --- ┆ --- ┆ ---    │
# │ f64 ┆ f64 ┆ bool   │
# ╞═════╪═════╪════════╡
# │ 1.0 ┆ 2.0 ┆ false  │
# │ 2.0 ┆ 2.0 ┆ true   │
# │ NaN ┆ NaN ┆ true   │
# │ 4.0 ┆ 4.0 ┆ true   │
# └─────┴─────┴────────┘

Parameters:

  • other (Object) —

    A literal or expression value to compare with.

Returns:



3106
3107
3108
 
# File 'lib/polars/expr.rb', line 3106

def eq(other)
  self == other
end

#eq_missing(other) ⇒ Expr

Method equivalent of equality operator expr == other where None == None.

This differs from default eq where null values are propagated.

Examples:

df = Polars::DataFrame.new(
  data={
    "x" => [1.0, 2.0, Float::NAN, 4.0, nil, nil],
    "y" => [2.0, 2.0, Float::NAN, 4.0, 5.0, nil]
  }
)
df.with_columns(
  Polars.col("x").eq(Polars.col("y")).alias("x eq y"),
  Polars.col("x").eq_missing(Polars.col("y")).alias("x eq_missing y")
)
# =>
# shape: (6, 4)
# ┌──────┬──────┬────────┬────────────────┐
# │ x    ┆ y    ┆ x eq y ┆ x eq_missing y │
# │ ---  ┆ ---  ┆ ---    ┆ ---            │
# │ f64  ┆ f64  ┆ bool   ┆ bool           │
# ╞══════╪══════╪════════╪════════════════╡
# │ 1.0  ┆ 2.0  ┆ false  ┆ false          │
# │ 2.0  ┆ 2.0  ┆ true   ┆ true           │
# │ NaN  ┆ NaN  ┆ true   ┆ true           │
# │ 4.0  ┆ 4.0  ┆ true   ┆ true           │
# │ null ┆ 5.0  ┆ null   ┆ false          │
# │ null ┆ null ┆ null   ┆ true           │
# └──────┴──────┴────────┴────────────────┘

Parameters:

  • other (Object) —

    A literal or expression value to compare with.

Returns:



3144
3145
3146
3147
 
# File 'lib/polars/expr.rb', line 3144

def eq_missing(other)
  other = Utils.parse_into_expression(other, str_as_lit: true)
  _from_rbexpr(_rbexpr.eq_missing(other))
end

#ewm_mean(com: nil, span: nil, half_life: nil, alpha: nil, adjust: true, min_periods: 1, ignore_nulls: true) ⇒ Expr

Exponentially-weighted moving average.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3]})
df.select(Polars.col("a").ewm_mean(com: 1))
# =>
# shape: (3, 1)
# ┌──────────┐
# │ a        │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ 1.0      │
# │ 1.666667 │
# │ 2.428571 │
# └──────────┘

Returns:



6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
 
# File 'lib/polars/expr.rb', line 6418

def ewm_mean(
  com: nil,
  span: nil,
  half_life: nil,
  alpha: nil,
  adjust: true,
  min_periods: 1,
  ignore_nulls: true
)
  alpha = _prepare_alpha(com, span, half_life, alpha)
  _from_rbexpr(_rbexpr.ewm_mean(alpha, adjust, min_periods, ignore_nulls))
end

#ewm_std(com: nil, span: nil, half_life: nil, alpha: nil, adjust: true, bias: false, min_periods: 1, ignore_nulls: true) ⇒ Expr

Exponentially-weighted moving standard deviation.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3]})
df.select(Polars.col("a").ewm_std(com: 1))
# =>
# shape: (3, 1)
# ┌──────────┐
# │ a        │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ 0.0      │
# │ 0.707107 │
# │ 0.963624 │
# └──────────┘

Returns:



6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
 
# File 'lib/polars/expr.rb', line 6449

def ewm_std(
  com: nil,
  span: nil,
  half_life: nil,
  alpha: nil,
  adjust: true,
  bias: false,
  min_periods: 1,
  ignore_nulls: true
)
  alpha = _prepare_alpha(com, span, half_life, alpha)
  _from_rbexpr(_rbexpr.ewm_std(alpha, adjust, bias, min_periods, ignore_nulls))
end

#ewm_var(com: nil, span: nil, half_life: nil, alpha: nil, adjust: true, bias: false, min_periods: 1, ignore_nulls: true) ⇒ Expr

Exponentially-weighted moving variance.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3]})
df.select(Polars.col("a").ewm_var(com: 1))
# =>
# shape: (3, 1)
# ┌──────────┐
# │ a        │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ 0.0      │
# │ 0.5      │
# │ 0.928571 │
# └──────────┘

Returns:



6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
 
# File 'lib/polars/expr.rb', line 6481

def ewm_var(
  com: nil,
  span: nil,
  half_life: nil,
  alpha: nil,
  adjust: true,
  bias: false,
  min_periods: 1,
  ignore_nulls: true
)
  alpha = _prepare_alpha(com, span, half_life, alpha)
  _from_rbexpr(_rbexpr.ewm_var(alpha, adjust, bias, min_periods, ignore_nulls))
end

#exclude(columns) ⇒ Expr

Exclude certain columns from a wildcard/regex selection.

You may also use regexes in the exclude list. They must start with ^ and end with $.

Examples:

df = Polars::DataFrame.new(
  {
    "aa" => [1, 2, 3],
    "ba" => ["a", "b", nil],
    "cc" => [nil, 2.5, 1.5]
  }
)
df.select(Polars.all.exclude("ba"))
# =>
# shape: (3, 2)
# ┌─────┬──────┐
# │ aa  ┆ cc   │
# │ --- ┆ ---  │
# │ i64 ┆ f64  │
# ╞═════╪══════╡
# │ 1   ┆ null │
# │ 2   ┆ 2.5  │
# │ 3   ┆ 1.5  │
# └─────┴──────┘

Parameters:

  • columns (Object) —

    Column(s) to exclude from selection. This can be:

    • a column name, or multiple column names
    • a regular expression starting with ^ and ending with $
    • a dtype or multiple dtypes

Returns:



365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
 
# File 'lib/polars/expr.rb', line 365

def exclude(columns)
  if columns.is_a?(::String)
    columns = [columns]
    return _from_rbexpr(_rbexpr.exclude(columns))
  elsif !columns.is_a?(::Array)
    columns = [columns]
    return _from_rbexpr(_rbexpr.exclude_dtype(columns))
  end

  if !columns.all? { |a| a.is_a?(::String) } || !columns.all? { |a| Utils.is_polars_dtype(a) }
    raise ArgumentError, "input should be all string or all DataType"
  end

  if columns[0].is_a?(::String)
    _from_rbexpr(_rbexpr.exclude(columns))
  else
    _from_rbexpr(_rbexpr.exclude_dtype(columns))
  end
end

#exp ⇒ Expr

Compute the exponential, element-wise.

Examples:

df = Polars::DataFrame.new({"values" => [1.0, 2.0, 4.0]})
df.select(Polars.col("values").exp)
# =>
# shape: (3, 1)
# ┌──────────┐
# │ values   │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ 2.718282 │
# │ 7.389056 │
# │ 54.59815 │
# └──────────┘

Returns:



289
290
291
 
# File 'lib/polars/expr.rb', line 289

def exp
  _from_rbexpr(_rbexpr.exp)
end

#explode ⇒ Expr

Explode a list or utf8 Series.

This means that every item is expanded to a new row.

Examples:

df = Polars::DataFrame.new({"b" => [[1, 2, 3], [4, 5, 6]]})
df.select(Polars.col("b").explode)
# =>
# shape: (6, 1)
# ┌─────┐
# │ b   │
# │ --- │
# │ i64 │
# ╞═════╡
# │ 1   │
# │ 2   │
# │ 3   │
# │ 4   │
# │ 5   │
# │ 6   │
# └─────┘

Returns:



2989
2990
2991
 
# File 'lib/polars/expr.rb', line 2989

def explode
  _from_rbexpr(_rbexpr.explode)
end

#extend_constant(value, n) ⇒ Expr

Extend the Series with given number of values.

Examples:

df = Polars::DataFrame.new({"values" => [1, 2, 3]})
df.select(Polars.col("values").extend_constant(99, 2))
# =>
# shape: (5, 1)
# ┌────────┐
# │ values │
# │ ---    │
# │ i64    │
# ╞════════╡
# │ 1      │
# │ 2      │
# │ 3      │
# │ 99     │
# │ 99     │
# └────────┘

Parameters:

  • value (Object) —

    The value to extend the Series with. This value may be nil to fill with nulls.

  • n (Integer) —

    The number of values to extend.

Returns:



6521
6522
6523
 
# File 'lib/polars/expr.rb', line 6521

def extend_constant(value, n)
  _from_rbexpr(_rbexpr.extend_constant(value, n))
end

#fill_nan(fill_value) ⇒ Expr

Fill floating point NaN value with a fill value.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1.0, nil, Float::NAN],
    "b" => [4.0, Float::NAN, 6]
  }
)
df.fill_nan("zero")
# =>
# shape: (3, 2)
# ┌──────┬──────┐
# │ a    ┆ b    │
# │ ---  ┆ ---  │
# │ str  ┆ str  │
# ╞══════╪══════╡
# │ 1.0  ┆ 4.0  │
# │ null ┆ zero │
# │ zero ┆ 6.0  │
# └──────┴──────┘

Returns:



1798
1799
1800
1801
 
# File 'lib/polars/expr.rb', line 1798

def fill_nan(fill_value)
  fill_value = Utils.parse_into_expression(fill_value, str_as_lit: true)
  _from_rbexpr(_rbexpr.fill_nan(fill_value))
end

#fill_null(value = nil, strategy: nil, limit: nil) ⇒ Expr

Fill null values using the specified value or strategy.

To interpolate over null values see interpolate.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, nil],
    "b" => [4, nil, 6]
  }
)
df.fill_null(strategy: "zero")
# =>
# shape: (3, 2)
# ┌─────┬─────┐
# │ a   ┆ b   │
# │ --- ┆ --- │
# │ i64 ┆ i64 │
# ╞═════╪═════╡
# │ 1   ┆ 4   │
# │ 2   ┆ 0   │
# │ 0   ┆ 6   │
# └─────┴─────┘
df.fill_null(99)
# =>
# shape: (3, 2)
# ┌─────┬─────┐
# │ a   ┆ b   │
# │ --- ┆ --- │
# │ i64 ┆ i64 │
# ╞═════╪═════╡
# │ 1   ┆ 4   │
# │ 2   ┆ 99  │
# │ 99  ┆ 6   │
# └─────┴─────┘
df.fill_null(strategy: "forward")
# =>
# shape: (3, 2)
# ┌─────┬─────┐
# │ a   ┆ b   │
# │ --- ┆ --- │
# │ i64 ┆ i64 │
# ╞═════╪═════╡
# │ 1   ┆ 4   │
# │ 2   ┆ 4   │
# │ 2   ┆ 6   │
# └─────┴─────┘

Parameters:

  • value (Object) (defaults to: nil) —

    Value used to fill null values.

  • strategy (nil, "forward", "backward", "min", "max", "mean", "zero", "one") (defaults to: nil) —

    Strategy used to fill null values.

  • limit (Integer) (defaults to: nil) —

    Number of consecutive null values to fill when using the 'forward' or 'backward' strategy.

Returns:



1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
 
# File 'lib/polars/expr.rb', line 1758

def fill_null(value = nil, strategy: nil, limit: nil)
  if !value.nil? && !strategy.nil?
    raise ArgumentError, "cannot specify both 'value' and 'strategy'."
  elsif value.nil? && strategy.nil?
    raise ArgumentError, "must specify either a fill 'value' or 'strategy'"
  elsif ["forward", "backward"].include?(strategy) && !limit.nil?
    raise ArgumentError, "can only specify 'limit' when strategy is set to 'backward' or 'forward'"
  end

  if !value.nil?
    value = Utils.parse_into_expression(value, str_as_lit: true)
    _from_rbexpr(_rbexpr.fill_null(value))
  else
    _from_rbexpr(_rbexpr.fill_null_with_strategy(strategy, limit))
  end
end

#filter(predicate) ⇒ Expr

Filter a single column.

Mostly useful in an aggregation context. If you want to filter on a DataFrame level, use LazyFrame#filter.

Examples:

df = Polars::DataFrame.new(
  {
    "group_col" => ["g1", "g1", "g2"],
    "b" => [1, 2, 3]
  }
)
(
  df.group_by("group_col").agg(
    [
      Polars.col("b").filter(Polars.col("b") < 2).sum.alias("lt"),
      Polars.col("b").filter(Polars.col("b") >= 2).sum.alias("gte")
    ]
  )
).sort("group_col")
# =>
# shape: (2, 3)
# ┌───────────┬─────┬─────┐
# │ group_col ┆ lt  ┆ gte │
# │ ---       ┆ --- ┆ --- │
# │ str       ┆ i64 ┆ i64 │
# ╞═══════════╪═════╪═════╡
# │ g1        ┆ 1   ┆ 2   │
# │ g2        ┆ 0   ┆ 3   │
# └───────────┴─────┴─────┘

Parameters:

  • predicate (Expr) —

    Boolean expression.

Returns:



2750
2751
2752
 
# File 'lib/polars/expr.rb', line 2750

def filter(predicate)
  _from_rbexpr(_rbexpr.filter(predicate._rbexpr))
end

#first ⇒ Expr

Get the first value.

Examples:

df = Polars::DataFrame.new({"a" => [1, 1, 2]})
df.select(Polars.col("a").first)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ i64 │
# ╞═════╡
# │ 1   │
# └─────┘

Returns:



2232
2233
2234
 
# File 'lib/polars/expr.rb', line 2232

def first
  _from_rbexpr(_rbexpr.first)
end

#flatten ⇒ Expr

Explode a list or utf8 Series. This means that every item is expanded to a new row.

Alias for #explode.

Examples:

df = Polars::DataFrame.new(
  {
    "group" => ["a", "b", "b"],
    "values" => [[1, 2], [2, 3], [4]]
  }
)
df.group_by("group").agg(Polars.col("values").flatten)
# =>
# shape: (2, 2)
# ┌───────┬───────────┐
# │ group ┆ values    │
# │ ---   ┆ ---       │
# │ str   ┆ list[i64] │
# ╞═══════╪═══════════╡
# │ a     ┆ [1, 2]    │
# │ b     ┆ [2, 3, 4] │
# └───────┴───────────┘

Returns:



2962
2963
2964
 
# File 'lib/polars/expr.rb', line 2962

def flatten
  _from_rbexpr(_rbexpr.explode)
end

#floor ⇒ Expr

Rounds down to the nearest integer value.

Only works on floating point Series.

Examples:

df = Polars::DataFrame.new({"a" => [0.3, 0.5, 1.0, 1.1]})
df.select(Polars.col("a").floor)
# =>
# shape: (4, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 0.0 │
# │ 0.0 │
# │ 1.0 │
# │ 1.0 │
# └─────┘

Returns:



1088
1089
1090
 
# File 'lib/polars/expr.rb', line 1088

def floor
  _from_rbexpr(_rbexpr.floor)
end

#floordiv(other) ⇒ Expr

Method equivalent of integer division operator expr // other.

Examples:

df = Polars::DataFrame.new({"x" => [1, 2, 3, 4, 5]})
df.with_columns(
  Polars.col("x").truediv(2).alias("x/2"),
  Polars.col("x").floordiv(2).alias("x//2")
)
# =>
# shape: (5, 3)
# ┌─────┬─────┬──────┐
# │ x   ┆ x/2 ┆ x//2 │
# │ --- ┆ --- ┆ ---  │
# │ i64 ┆ f64 ┆ i64  │
# ╞═════╪═════╪══════╡
# │ 1   ┆ 0.5 ┆ 0    │
# │ 2   ┆ 1.0 ┆ 1    │
# │ 3   ┆ 1.5 ┆ 1    │
# │ 4   ┆ 2.0 ┆ 2    │
# │ 5   ┆ 2.5 ┆ 2    │
# └─────┴─────┴──────┘

Parameters:

  • other (Object) —

    Numeric literal or expression value.

Returns:



3426
3427
3428
 
# File 'lib/polars/expr.rb', line 3426

def floordiv(other)
  _from_rbexpr(_rbexpr.floordiv(_to_rbexpr(other)))
end

#forward_fill(limit: nil) ⇒ Expr

Fill missing values with the latest seen values.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, nil],
    "b" => [4, nil, 6]
  }
)
df.select(Polars.all.forward_fill)
# =>
# shape: (3, 2)
# ┌─────┬─────┐
# │ a   ┆ b   │
# │ --- ┆ --- │
# │ i64 ┆ i64 │
# ╞═════╪═════╡
# │ 1   ┆ 4   │
# │ 2   ┆ 4   │
# │ 2   ┆ 6   │
# └─────┴─────┘

Parameters:

  • limit (Integer) (defaults to: nil) —

    The number of consecutive null values to forward fill.

Returns:



1829
1830
1831
 
# File 'lib/polars/expr.rb', line 1829

def forward_fill(limit: nil)
  _from_rbexpr(_rbexpr.forward_fill(limit))
end

#gather(indices) ⇒ Expr Also known as: take

Take values by index.

Examples:

df = Polars::DataFrame.new(
  {
    "group" => [
      "one",
      "one",
      "one",
      "two",
      "two",
      "two"
    ],
    "value" => [1, 98, 2, 3, 99, 4]
  }
)
df.group_by("group", maintain_order: true).agg(Polars.col("value").take([2, 1]))
# =>
# shape: (2, 2)
# ┌───────┬───────────┐
# │ group ┆ value     │
# │ ---   ┆ ---       │
# │ str   ┆ list[i64] │
# ╞═══════╪═══════════╡
# │ one   ┆ [2, 98]   │
# │ two   ┆ [4, 99]   │
# └───────┴───────────┘

Parameters:

  • indices (Expr) —

    An expression that leads to a :u32 dtyped Series.

Returns:



1590
1591
1592
1593
1594
1595
1596
1597
 
# File 'lib/polars/expr.rb', line 1590

def gather(indices)
  if indices.is_a?(::Array)
    indices_lit = Polars.lit(Series.new("", indices, dtype: :u32))._rbexpr
  else
    indices_lit = Utils.parse_into_expression(indices, str_as_lit: false)
  end
  _from_rbexpr(_rbexpr.gather(indices_lit))
end

#gather_every(n, offset = 0) ⇒ Expr Also known as: take_every

Take every nth value in the Series and return as a new Series.

Examples:

df = Polars::DataFrame.new({"foo" => [1, 2, 3, 4, 5, 6, 7, 8, 9]})
df.select(Polars.col("foo").gather_every(3))
# =>
# shape: (3, 1)
# ┌─────┐
# │ foo │
# │ --- │
# │ i64 │
# ╞═════╡
# │ 1   │
# │ 4   │
# │ 7   │
# └─────┘

Returns:



3011
3012
3013
 
# File 'lib/polars/expr.rb', line 3011

def gather_every(n, offset = 0)
  _from_rbexpr(_rbexpr.gather_every(n, offset))
end

#ge(other) ⇒ Expr

Method equivalent of "greater than or equal" operator expr >= other.

Examples:

df = Polars::DataFrame.new(
  {
    "x" => [5.0, 4.0, Float::NAN, 2.0],
    "y" => [5.0, 3.0, Float::NAN, 1.0]
  }
)
df.with_columns(
  Polars.col("x").ge(Polars.col("y")).alias("x >= y")
)
# =>
# shape: (4, 3)
# ┌─────┬─────┬────────┐
# │ x   ┆ y   ┆ x >= y │
# │ --- ┆ --- ┆ ---    │
# │ f64 ┆ f64 ┆ bool   │
# ╞═════╪═════╪════════╡
# │ 5.0 ┆ 5.0 ┆ true   │
# │ 4.0 ┆ 3.0 ┆ true   │
# │ NaN ┆ NaN ┆ true   │
# │ 2.0 ┆ 1.0 ┆ true   │
# └─────┴─────┴────────┘

Parameters:

  • other (Object) —

    A literal or expression value to compare with.

Returns:



3178
3179
3180
 
# File 'lib/polars/expr.rb', line 3178

def ge(other)
  self >= other
end

#get(index) ⇒ Expr

Return a single value by index.

Examples:

df = Polars::DataFrame.new(
  {
    "group" => [
      "one",
      "one",
      "one",
      "two",
      "two",
      "two"
    ],
    "value" => [1, 98, 2, 3, 99, 4]
  }
)
df.group_by("group", maintain_order: true).agg(Polars.col("value").get(1))
# =>
# shape: (2, 2)
# ┌───────┬───────┐
# │ group ┆ value │
# │ ---   ┆ ---   │
# │ str   ┆ i64   │
# ╞═══════╪═══════╡
# │ one   ┆ 98    │
# │ two   ┆ 99    │
# └───────┴───────┘

Parameters:

  • index (Object) —

    An expression that leads to a UInt32 index.

Returns:



1632
1633
1634
1635
 
# File 'lib/polars/expr.rb', line 1632

def get(index)
  index_lit = Utils.parse_into_expression(index)
  _from_rbexpr(_rbexpr.get(index_lit))
end

#gt(other) ⇒ Expr

Method equivalent of "greater than" operator expr > other.

Examples:

df = Polars::DataFrame.new(
  {
    "x" => [5.0, 4.0, Float::NAN, 2.0],
    "y" => [5.0, 3.0, Float::NAN, 1.0]
  }
)
df.with_columns(
    Polars.col("x").gt(Polars.col("y")).alias("x > y")
)
# =>
# shape: (4, 3)
# ┌─────┬─────┬───────┐
# │ x   ┆ y   ┆ x > y │
# │ --- ┆ --- ┆ ---   │
# │ f64 ┆ f64 ┆ bool  │
# ╞═════╪═════╪═══════╡
# │ 5.0 ┆ 5.0 ┆ false │
# │ 4.0 ┆ 3.0 ┆ true  │
# │ NaN ┆ NaN ┆ false │
# │ 2.0 ┆ 1.0 ┆ true  │
# └─────┴─────┴───────┘

Parameters:

  • other (Object) —

    A literal or expression value to compare with.

Returns:



3211
3212
3213
 
# File 'lib/polars/expr.rb', line 3211

def gt(other)
  self > other
end

#head(n = 10) ⇒ Expr

Get the first n rows.

Examples:

df = Polars::DataFrame.new({"foo" => [1, 2, 3, 4, 5, 6, 7]})
df.head(3)
# =>
# shape: (3, 1)
# ┌─────┐
# │ foo │
# │ --- │
# │ i64 │
# ╞═════╡
# │ 1   │
# │ 2   │
# │ 3   │
# └─────┘

Parameters:

  • n (Integer) (defaults to: 10) —

    Number of rows to return.

Returns:



3037
3038
3039
 
# File 'lib/polars/expr.rb', line 3037

def head(n = 10)
  _from_rbexpr(_rbexpr.head(n))
end

#implode ⇒ Expr

Aggregate to list.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, 3],
    "b" => [4, 5, 6]
  }
)
df.select(Polars.all.implode)
# =>
# shape: (1, 2)
# ┌───────────┬───────────┐
# │ a         ┆ b         │
# │ ---       ┆ ---       │
# │ list[i64] ┆ list[i64] │
# ╞═══════════╪═══════════╡
# │ [1, 2, 3] ┆ [4, 5, 6] │
# └───────────┴───────────┘

Returns:



6777
6778
6779
 
# File 'lib/polars/expr.rb', line 6777

def implode
  _from_rbexpr(_rbexpr.implode)
end

#interpolate(method: "linear") ⇒ Expr

Fill nulls with linear interpolation over missing values.

Can also be used to regrid data to a new grid - see examples below.

Examples:

Fill nulls with linear interpolation

df = Polars::DataFrame.new(
  {
    "a" => [1, nil, 3],
    "b" => [1.0, Float::NAN, 3.0]
  }
)
df.select(Polars.all.interpolate)
# =>
# shape: (3, 2)
# ┌─────┬─────┐
# │ a   ┆ b   │
# │ --- ┆ --- │
# │ f64 ┆ f64 │
# ╞═════╪═════╡
# │ 1.0 ┆ 1.0 │
# │ 2.0 ┆ NaN │
# │ 3.0 ┆ 3.0 │
# └─────┴─────┘

Returns:



3908
3909
3910
 
# File 'lib/polars/expr.rb', line 3908

def interpolate(method: "linear")
  _from_rbexpr(_rbexpr.interpolate(method))
end

#is_between(lower_bound, upper_bound, closed: "both") ⇒ Expr

Check if this expression is between start and end.

Examples:

df = Polars::DataFrame.new({"num" => [1, 2, 3, 4, 5]})
df.with_columns(Polars.col("num").is_between(2, 4).alias("is_between"))
# =>
# shape: (5, 2)
# ┌─────┬────────────┐
# │ num ┆ is_between │
# │ --- ┆ ---        │
# │ i64 ┆ bool       │
# ╞═════╪════════════╡
# │ 1   ┆ false      │
# │ 2   ┆ true       │
# │ 3   ┆ true       │
# │ 4   ┆ true       │
# │ 5   ┆ false      │
# └─────┴────────────┘

Use the closed argument to include or exclude the values at the bounds:

df.with_columns(
  Polars.col("num").is_between(2, 4, closed: "left").alias("is_between")
)
# =>
# shape: (5, 2)
# ┌─────┬────────────┐
# │ num ┆ is_between │
# │ --- ┆ ---        │
# │ i64 ┆ bool       │
# ╞═════╪════════════╡
# │ 1   ┆ false      │
# │ 2   ┆ true       │
# │ 3   ┆ true       │
# │ 4   ┆ false      │
# │ 5   ┆ false      │
# └─────┴────────────┘

You can also use strings as well as numeric/temporal values:

df = Polars::DataFrame.new({"a" => ["a", "b", "c", "d", "e"]})
df.with_columns(
  Polars.col("a")
    .is_between(Polars.lit("a"), Polars.lit("c"), closed: "both")
    .alias("is_between")
)
# =>
# shape: (5, 2)
# ┌─────┬────────────┐
# │ a   ┆ is_between │
# │ --- ┆ ---        │
# │ str ┆ bool       │
# ╞═════╪════════════╡
# │ a   ┆ true       │
# │ b   ┆ true       │
# │ c   ┆ true       │
# │ d   ┆ false      │
# │ e   ┆ false      │
# └─────┴────────────┘

Parameters:

  • lower_bound (Object) —

    Lower bound as primitive type or datetime.

  • upper_bound (Object) —

    Upper bound as primitive type or datetime.

  • closed ("both", "left", "right", "none") (defaults to: "both") —

    Define which sides of the interval are closed (inclusive).

Returns:



3764
3765
3766
3767
3768
3769
3770
3771
 
# File 'lib/polars/expr.rb', line 3764

def is_between(lower_bound, upper_bound, closed: "both")
  lower_bound = Utils.parse_into_expression(lower_bound)
  upper_bound = Utils.parse_into_expression(upper_bound)

  _from_rbexpr(
    _rbexpr.is_between(lower_bound, upper_bound, closed)
  )
end

#is_duplicated ⇒ Expr

Get mask of duplicated values.

Examples:

df = Polars::DataFrame.new({"a" => [1, 1, 2]})
df.select(Polars.col("a").is_duplicated)
# =>
# shape: (3, 1)
# ┌───────┐
# │ a     │
# │ ---   │
# │ bool  │
# ╞═══════╡
# │ true  │
# │ true  │
# │ false │
# └───────┘

Returns:



2389
2390
2391
 
# File 'lib/polars/expr.rb', line 2389

def is_duplicated
  _from_rbexpr(_rbexpr.is_duplicated)
end

#is_finite ⇒ Expr

Returns a boolean Series indicating which values are finite.

Examples:

df = Polars::DataFrame.new(
  {
    "A" => [1.0, 2],
    "B" => [3.0, Float::INFINITY]
  }
)
df.select(Polars.all.is_finite)
# =>
# shape: (2, 2)
# ┌──────┬───────┐
# │ A    ┆ B     │
# │ ---  ┆ ---   │
# │ bool ┆ bool  │
# ╞══════╪═══════╡
# │ true ┆ true  │
# │ true ┆ false │
# └──────┴───────┘

Returns:



574
575
576
 
# File 'lib/polars/expr.rb', line 574

def is_finite
  _from_rbexpr(_rbexpr.is_finite)
end

#is_first_distinct ⇒ Expr Also known as: is_first

Get a mask of the first unique value.

Examples:

df = Polars::DataFrame.new(
  {
    "num" => [1, 2, 3, 1, 5]
  }
)
df.with_column(Polars.col("num").is_first.alias("is_first"))
# =>
# shape: (5, 2)
# ┌─────┬──────────┐
# │ num ┆ is_first │
# │ --- ┆ ---      │
# │ i64 ┆ bool     │
# ╞═════╪══════════╡
# │ 1   ┆ true     │
# │ 2   ┆ true     │
# │ 3   ┆ true     │
# │ 1   ┆ false    │
# │ 5   ┆ true     │
# └─────┴──────────┘

Returns:



2366
2367
2368
 
# File 'lib/polars/expr.rb', line 2366

def is_first_distinct
  _from_rbexpr(_rbexpr.is_first_distinct)
end

#is_in(other) ⇒ Expr Also known as: in?

Check if elements of this expression are present in the other Series.

Examples:

df = Polars::DataFrame.new(
  {"sets" => [[1, 2, 3], [1, 2], [9, 10]], "optional_members" => [1, 2, 3]}
)
df.select([Polars.col("optional_members").is_in("sets").alias("contains")])
# =>
# shape: (3, 1)
# ┌──────────┐
# │ contains │
# │ ---      │
# │ bool     │
# ╞══════════╡
# │ true     │
# │ true     │
# │ false    │
# └──────────┘

Parameters:

  • other (Object) —

    Series or sequence of primitive type.

Returns:



3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
 
# File 'lib/polars/expr.rb', line 3649

def is_in(other)
  if other.is_a?(::Array)
    if other.length == 0
      other = Polars.lit(nil)._rbexpr
    else
      other = Polars.lit(Series.new(other))._rbexpr
    end
  else
    other = Utils.parse_into_expression(other, str_as_lit: false)
  end
  _from_rbexpr(_rbexpr.is_in(other))
end

#is_infinite ⇒ Expr

Returns a boolean Series indicating which values are infinite.

Examples:

df = Polars::DataFrame.new(
  {
    "A" => [1.0, 2],
    "B" => [3.0, Float::INFINITY]
  }
)
df.select(Polars.all.is_infinite)
# =>
# shape: (2, 2)
# ┌───────┬───────┐
# │ A     ┆ B     │
# │ ---   ┆ ---   │
# │ bool  ┆ bool  │
# ╞═══════╪═══════╡
# │ false ┆ false │
# │ false ┆ true  │
# └───────┴───────┘

Returns:



600
601
602
 
# File 'lib/polars/expr.rb', line 600

def is_infinite
  _from_rbexpr(_rbexpr.is_infinite)
end

#is_nan ⇒ Expr

Note:

Floating point NaN (Not A Number) should not be confused with missing data represented as nil.

Returns a boolean Series indicating which values are NaN.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, nil, 1, 5],
    "b" => [1.0, 2.0, Float::NAN, 1.0, 5.0]
  }
)
df.with_column(Polars.col(Polars::Float64).is_nan.suffix("_isnan"))
# =>
# shape: (5, 3)
# ┌──────┬─────┬─────────┐
# │ a    ┆ b   ┆ b_isnan │
# │ ---  ┆ --- ┆ ---     │
# │ i64  ┆ f64 ┆ bool    │
# ╞══════╪═════╪═════════╡
# │ 1    ┆ 1.0 ┆ false   │
# │ 2    ┆ 2.0 ┆ false   │
# │ null ┆ NaN ┆ true    │
# │ 1    ┆ 1.0 ┆ false   │
# │ 5    ┆ 5.0 ┆ false   │
# └──────┴─────┴─────────┘

Returns:



633
634
635
 
# File 'lib/polars/expr.rb', line 633

def is_nan
  _from_rbexpr(_rbexpr.is_nan)
end

#is_not ⇒ Expr Also known as: not_

Negate a boolean expression.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [true, false, false],
    "b" => ["a", "b", nil]
  }
)
# =>
# shape: (3, 2)
# ┌───────┬──────┐
# │ a     ┆ b    │
# │ ---   ┆ ---  │
# │ bool  ┆ str  │
# ╞═══════╪══════╡
# │ true  ┆ a    │
# │ false ┆ b    │
# │ false ┆ null │
# └───────┴──────┘
df.select(Polars.col("a").is_not)
# =>
# shape: (3, 1)
# ┌───────┐
# │ a     │
# │ ---   │
# │ bool  │
# ╞═══════╡
# │ false │
# │ true  │
# │ true  │
# └───────┘

Returns:



489
490
491
 
# File 'lib/polars/expr.rb', line 489

def is_not
  _from_rbexpr(_rbexpr.not_)
end

#is_not_nan ⇒ Expr

Note:

Floating point NaN (Not A Number) should not be confused with missing data represented as nil.

Returns a boolean Series indicating which values are not NaN.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, nil, 1, 5],
    "b" => [1.0, 2.0, Float::NAN, 1.0, 5.0]
  }
)
df.with_column(Polars.col(Polars::Float64).is_not_nan.suffix("_is_not_nan"))
# =>
# shape: (5, 3)
# ┌──────┬─────┬──────────────┐
# │ a    ┆ b   ┆ b_is_not_nan │
# │ ---  ┆ --- ┆ ---          │
# │ i64  ┆ f64 ┆ bool         │
# ╞══════╪═════╪══════════════╡
# │ 1    ┆ 1.0 ┆ true         │
# │ 2    ┆ 2.0 ┆ true         │
# │ null ┆ NaN ┆ false        │
# │ 1    ┆ 1.0 ┆ true         │
# │ 5    ┆ 5.0 ┆ true         │
# └──────┴─────┴──────────────┘

Returns:



666
667
668
 
# File 'lib/polars/expr.rb', line 666

def is_not_nan
  _from_rbexpr(_rbexpr.is_not_nan)
end

#is_not_null ⇒ Expr

Returns a boolean Series indicating which values are not null.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, nil, 1, 5],
    "b" => [1.0, 2.0, Float::NAN, 1.0, 5.0]
  }
)
df.with_column(Polars.all.is_not_null.suffix("_not_null"))
# =>
# shape: (5, 4)
# ┌──────┬─────┬────────────┬────────────┐
# │ a    ┆ b   ┆ a_not_null ┆ b_not_null │
# │ ---  ┆ --- ┆ ---        ┆ ---        │
# │ i64  ┆ f64 ┆ bool       ┆ bool       │
# ╞══════╪═════╪════════════╪════════════╡
# │ 1    ┆ 1.0 ┆ true       ┆ true       │
# │ 2    ┆ 2.0 ┆ true       ┆ true       │
# │ null ┆ NaN ┆ false      ┆ true       │
# │ 1    ┆ 1.0 ┆ true       ┆ true       │
# │ 5    ┆ 5.0 ┆ true       ┆ true       │
# └──────┴─────┴────────────┴────────────┘

Returns:



548
549
550
 
# File 'lib/polars/expr.rb', line 548

def is_not_null
  _from_rbexpr(_rbexpr.is_not_null)
end

#is_null ⇒ Expr

Returns a boolean Series indicating which values are null.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, nil, 1, 5],
    "b" => [1.0, 2.0, Float::NAN, 1.0, 5.0]
  }
)
df.with_column(Polars.all.is_null.suffix("_isnull"))
# =>
# shape: (5, 4)
# ┌──────┬─────┬──────────┬──────────┐
# │ a    ┆ b   ┆ a_isnull ┆ b_isnull │
# │ ---  ┆ --- ┆ ---      ┆ ---      │
# │ i64  ┆ f64 ┆ bool     ┆ bool     │
# ╞══════╪═════╪══════════╪══════════╡
# │ 1    ┆ 1.0 ┆ false    ┆ false    │
# │ 2    ┆ 2.0 ┆ false    ┆ false    │
# │ null ┆ NaN ┆ true     ┆ false    │
# │ 1    ┆ 1.0 ┆ false    ┆ false    │
# │ 5    ┆ 5.0 ┆ false    ┆ false    │
# └──────┴─────┴──────────┴──────────┘

Returns:



519
520
521
 
# File 'lib/polars/expr.rb', line 519

def is_null
  _from_rbexpr(_rbexpr.is_null)
end

#is_unique ⇒ Expr

Get mask of unique values.

Examples:

df = Polars::DataFrame.new({"a" => [1, 1, 2]})
df.select(Polars.col("a").is_unique)
# =>
# shape: (3, 1)
# ┌───────┐
# │ a     │
# │ ---   │
# │ bool  │
# ╞═══════╡
# │ false │
# │ false │
# │ true  │
# └───────┘

Returns:



2338
2339
2340
 
# File 'lib/polars/expr.rb', line 2338

def is_unique
  _from_rbexpr(_rbexpr.is_unique)
end

#keep_name ⇒ Expr

Keep the original root name of the expression.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2],
    "b" => [3, 4]
  }
)
df.with_columns([(Polars.col("a") * 9).alias("c").keep_name])
# =>
# shape: (2, 2)
# ┌─────┬─────┐
# │ a   ┆ b   │
# │ --- ┆ --- │
# │ i64 ┆ i64 │
# ╞═════╪═════╡
# │ 9   ┆ 3   │
# │ 18  ┆ 4   │
# └─────┴─────┘

Returns:



407
408
409
 
# File 'lib/polars/expr.rb', line 407

def keep_name
  name.keep
end

#kurtosis(fisher: true, bias: true) ⇒ Expr

Compute the kurtosis (Fisher or Pearson) of a dataset.

Kurtosis is the fourth central moment divided by the square of the variance. If Fisher's definition is used, then 3.0 is subtracted from the result to give 0.0 for a normal distribution. If bias is False then the kurtosis is calculated using k statistics to eliminate bias coming from biased moment estimators

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3, 2, 1]})
df.select(Polars.col("a").kurtosis)
# =>
# shape: (1, 1)
# ┌───────────┐
# │ a         │
# │ ---       │
# │ f64       │
# ╞═══════════╡
# │ -1.153061 │
# └───────────┘

Parameters:

  • fisher (Boolean) (defaults to: true) —

    If true, Fisher's definition is used (normal ==> 0.0). If false, Pearson's definition is used (normal ==> 3.0).

  • bias (Boolean) (defaults to: true) —

    If false, the calculations are corrected for statistical bias.

Returns:



5857
5858
5859
 
# File 'lib/polars/expr.rb', line 5857

def kurtosis(fisher: true, bias: true)
  _from_rbexpr(_rbexpr.kurtosis(fisher, bias))
end

#last ⇒ Expr

Get the last value.

Examples:

df = Polars::DataFrame.new({"a" => [1, 1, 2]})
df.select(Polars.col("a").last)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ i64 │
# ╞═════╡
# │ 2   │
# └─────┘

Returns:



2252
2253
2254
 
# File 'lib/polars/expr.rb', line 2252

def last
  _from_rbexpr(_rbexpr.last)
end

#le(other) ⇒ Expr

Method equivalent of "less than or equal" operator expr <= other.

Examples:

df = Polars::DataFrame.new(
  {
    "x" => [5.0, 4.0, Float::NAN, 0.5],
    "y" => [5.0, 3.5, Float::NAN, 2.0]
  }
)
df.with_columns(
  Polars.col("x").le(Polars.col("y")).alias("x <= y")
)
# =>
# shape: (4, 3)
# ┌─────┬─────┬────────┐
# │ x   ┆ y   ┆ x <= y │
# │ --- ┆ --- ┆ ---    │
# │ f64 ┆ f64 ┆ bool   │
# ╞═════╪═════╪════════╡
# │ 5.0 ┆ 5.0 ┆ true   │
# │ 4.0 ┆ 3.5 ┆ false  │
# │ NaN ┆ NaN ┆ true   │
# │ 0.5 ┆ 2.0 ┆ true   │
# └─────┴─────┴────────┘

Parameters:

  • other (Object) —

    A literal or expression value to compare with.

Returns:



3244
3245
3246
 
# File 'lib/polars/expr.rb', line 3244

def le(other)
  self <= other
end

#len ⇒ Expr Also known as: length

Count the number of values in this expression.

Examples:

df = Polars::DataFrame.new({"a" => [8, 9, 10], "b" => [nil, 4, 4]})
df.select(Polars.all.len)
# =>
# shape: (1, 2)
# ┌─────┬─────┐
# │ a   ┆ b   │
# │ --- ┆ --- │
# │ u32 ┆ u32 │
# ╞═════╪═════╡
# │ 3   ┆ 3   │
# └─────┴─────┘

Returns:



741
742
743
 
# File 'lib/polars/expr.rb', line 741

def len
  _from_rbexpr(_rbexpr.len)
end

#limit(n = 10) ⇒ Expr

Get the first n rows.

Alias for #head.

Parameters:

  • n (Integer) (defaults to: 10) —

    Number of rows to return.

Returns:



3074
3075
3076
 
# File 'lib/polars/expr.rb', line 3074

def limit(n = 10)
  head(n)
end

#list ⇒ ListExpr

Create an object namespace of all list related methods.

Returns:



7132
7133
7134
 
# File 'lib/polars/expr.rb', line 7132

def list
  ListExpr.new(self)
end

#log(base = Math::E) ⇒ Expr

Compute the logarithm to a given base.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3]})
df.select(Polars.col("a").log(2))
# =>
# shape: (3, 1)
# ┌──────────┐
# │ a        │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ 0.0      │
# │ 1.0      │
# │ 1.584963 │
# └──────────┘

Parameters:

  • base (Float) (defaults to: Math::E) —

    Given base, defaults to e.

Returns:



6635
6636
6637
 
# File 'lib/polars/expr.rb', line 6635

def log(base = Math::E)
  _from_rbexpr(_rbexpr.log(base))
end

#log10 ⇒ Expr

Compute the base 10 logarithm of the input array, element-wise.

Examples:

df = Polars::DataFrame.new({"values" => [1.0, 2.0, 4.0]})
df.select(Polars.col("values").log10)
# =>
# shape: (3, 1)
# ┌─────────┐
# │ values  │
# │ ---     │
# │ f64     │
# ╞═════════╡
# │ 0.0     │
# │ 0.30103 │
# │ 0.60206 │
# └─────────┘

Returns:



267
268
269
 
# File 'lib/polars/expr.rb', line 267

def log10
  log(10)
end

#lower_bound ⇒ Expr

Calculate the lower bound.

Returns a unit Series with the lowest value possible for the dtype of this expression.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3, 2, 1]})
df.select(Polars.col("a").lower_bound)
# =>
# shape: (1, 1)
# ┌──────────────────────┐
# │ a                    │
# │ ---                  │
# │ i64                  │
# ╞══════════════════════╡
# │ -9223372036854775808 │
# └──────────────────────┘

Returns:



5979
5980
5981
 
# File 'lib/polars/expr.rb', line 5979

def lower_bound
  _from_rbexpr(_rbexpr.lower_bound)
end

#lt(other) ⇒ Expr

Method equivalent of "less than" operator expr < other.

Examples:

df = Polars::DataFrame.new(
  {
    "x" => [1.0, 2.0, Float::NAN, 3.0],
    "y" => [2.0, 2.0, Float::NAN, 4.0]
  }
)
df.with_columns(
  Polars.col("x").lt(Polars.col("y")).alias("x < y"),
)
# =>
# shape: (4, 3)
# ┌─────┬─────┬───────┐
# │ x   ┆ y   ┆ x < y │
# │ --- ┆ --- ┆ ---   │
# │ f64 ┆ f64 ┆ bool  │
# ╞═════╪═════╪═══════╡
# │ 1.0 ┆ 2.0 ┆ true  │
# │ 2.0 ┆ 2.0 ┆ false │
# │ NaN ┆ NaN ┆ false │
# │ 3.0 ┆ 4.0 ┆ true  │
# └─────┴─────┴───────┘

Parameters:

  • other (Object) —

    A literal or expression value to compare with.

Returns:



3277
3278
3279
 
# File 'lib/polars/expr.rb', line 3277

def lt(other)
  self < other
end

#map_alias(&f) ⇒ Expr

Rename the output of an expression by mapping a function over the root name.

Examples:

df = Polars::DataFrame.new(
  {
    "A" => [1, 2],
    "B" => [3, 4]
  }
)
df.select(
  Polars.all.reverse.map_alias { |colName| colName + "_reverse" }
)
# =>
# shape: (2, 2)
# ┌───────────┬───────────┐
# │ A_reverse ┆ B_reverse │
# │ ---       ┆ ---       │
# │ i64       ┆ i64       │
# ╞═══════════╪═══════════╡
# │ 2         ┆ 4         │
# │ 1         ┆ 3         │
# └───────────┴───────────┘

Returns:



449
450
451
 
# File 'lib/polars/expr.rb', line 449

def map_alias(&f)
  name.map(&f)
end

#max ⇒ Expr

Get maximum value.

Examples:

df = Polars::DataFrame.new({"a" => [-1.0, Float::NAN, 1.0]})
df.select(Polars.col("a").max)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 1.0 │
# └─────┘

Returns:



1932
1933
1934
 
# File 'lib/polars/expr.rb', line 1932

def max
  _from_rbexpr(_rbexpr.max)
end

#mean ⇒ Expr

Get mean value.

Examples:

df = Polars::DataFrame.new({"a" => [-1, 0, 1]})
df.select(Polars.col("a").mean)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 0.0 │
# └─────┘

Returns:



2036
2037
2038
 
# File 'lib/polars/expr.rb', line 2036

def mean
  _from_rbexpr(_rbexpr.mean)
end

#median ⇒ Expr

Get median value using linear interpolation.

Examples:

df = Polars::DataFrame.new({"a" => [-1, 0, 1]})
df.select(Polars.col("a").median)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 0.0 │
# └─────┘

Returns:



2056
2057
2058
 
# File 'lib/polars/expr.rb', line 2056

def median
  _from_rbexpr(_rbexpr.median)
end

#meta ⇒ MetaExpr

Create an object namespace of all meta related expression methods.

Returns:



7167
7168
7169
 
# File 'lib/polars/expr.rb', line 7167

def meta
  MetaExpr.new(self)
end

#min ⇒ Expr

Get minimum value.

Examples:

df = Polars::DataFrame.new({"a" => [-1.0, Float::NAN, 1.0]})
df.select(Polars.col("a").min)
# =>
# shape: (1, 1)
# ┌──────┐
# │ a    │
# │ ---  │
# │ f64  │
# ╞══════╡
# │ -1.0 │
# └──────┘

Returns:



1952
1953
1954
 
# File 'lib/polars/expr.rb', line 1952

def min
  _from_rbexpr(_rbexpr.min)
end

#mod(other) ⇒ Expr

Method equivalent of modulus operator expr % other.

Examples:

df = Polars::DataFrame.new({"x" => [0, 1, 2, 3, 4]})
df.with_columns(Polars.col("x").mod(2).alias("x%2"))
# =>
# shape: (5, 2)
# ┌─────┬─────┐
# │ x   ┆ x%2 │
# │ --- ┆ --- │
# │ i64 ┆ i64 │
# ╞═════╪═════╡
# │ 0   ┆ 0   │
# │ 1   ┆ 1   │
# │ 2   ┆ 0   │
# │ 3   ┆ 1   │
# │ 4   ┆ 0   │
# └─────┴─────┘

Parameters:

  • other (Object) —

    Numeric literal or expression value.

Returns:



3453
3454
3455
 
# File 'lib/polars/expr.rb', line 3453

def mod(other)
  self % other
end

#mode ⇒ Expr

Compute the most occurring value(s).

Can return multiple Values.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 1, 2, 3],
    "b" => [1, 1, 2, 2]
  }
)
df.select(Polars.all.mode.first)
# =>
# shape: (2, 2)
# ┌─────┬─────┐
# │ a   ┆ b   │
# │ --- ┆ --- │
# │ i64 ┆ i64 │
# ╞═════╪═════╡
# │ 1   ┆ 1   │
# │ 1   ┆ 2   │
# └─────┴─────┘

Returns:



1196
1197
1198
 
# File 'lib/polars/expr.rb', line 1196

def mode
  _from_rbexpr(_rbexpr.mode)
end

#mul(other) ⇒ Expr

Method equivalent of multiplication operator expr * other.

Examples:

df = Polars::DataFrame.new({"x" => [1, 2, 4, 8, 16]})
df.with_columns(
  Polars.col("x").mul(2).alias("x*2"),
  Polars.col("x").mul(Polars.col("x").log(2)).alias("x * xlog2"),
)
# =>
# shape: (5, 3)
# ┌─────┬─────┬───────────┐
# │ x   ┆ x*2 ┆ x * xlog2 │
# │ --- ┆ --- ┆ ---       │
# │ i64 ┆ i64 ┆ f64       │
# ╞═════╪═════╪═══════════╡
# │ 1   ┆ 2   ┆ 0.0       │
# │ 2   ┆ 4   ┆ 2.0       │
# │ 4   ┆ 8   ┆ 8.0       │
# │ 8   ┆ 16  ┆ 24.0      │
# │ 16  ┆ 32  ┆ 64.0      │
# └─────┴─────┴───────────┘

Parameters:

  • other (Object) —

    Numeric literal or expression value.

Returns:



3483
3484
3485
 
# File 'lib/polars/expr.rb', line 3483

def mul(other)
  self * other
end

#n_unique ⇒ Expr

Count unique values.

Examples:

df = Polars::DataFrame.new({"a" => [1, 1, 2]})
df.select(Polars.col("a").n_unique)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ u32 │
# ╞═════╡
# │ 2   │
# └─────┘

Returns:



2096
2097
2098
 
# File 'lib/polars/expr.rb', line 2096

def n_unique
  _from_rbexpr(_rbexpr.n_unique)
end

#name ⇒ NameExpr

Create an object namespace of all expressions that modify expression names.

Returns:



7174
7175
7176
 
# File 'lib/polars/expr.rb', line 7174

def name
  NameExpr.new(self)
end

#nan_max ⇒ Expr

Get maximum value, but propagate/poison encountered NaN values.

Examples:

df = Polars::DataFrame.new({"a" => [0.0, Float::NAN]})
df.select(Polars.col("a").nan_max)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ NaN │
# └─────┘

Returns:



1972
1973
1974
 
# File 'lib/polars/expr.rb', line 1972

def nan_max
  _from_rbexpr(_rbexpr.nan_max)
end

#nan_min ⇒ Expr

Get minimum value, but propagate/poison encountered NaN values.

Examples:

df = Polars::DataFrame.new({"a" => [0.0, Float::NAN]})
df.select(Polars.col("a").nan_min)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ NaN │
# └─────┘

Returns:



1992
1993
1994
 
# File 'lib/polars/expr.rb', line 1992

def nan_min
  _from_rbexpr(_rbexpr.nan_min)
end

#ne(other) ⇒ Expr

Method equivalent of inequality operator expr != other.

Examples:

df = Polars::DataFrame.new(
  {
    "x" => [1.0, 2.0, Float::NAN, 4.0],
    "y" => [2.0, 2.0, Float::NAN, 4.0]
  }
)
df.with_columns(
  Polars.col("x").ne(Polars.col("y")).alias("x != y"),
)
# =>
# shape: (4, 3)
# ┌─────┬─────┬────────┐
# │ x   ┆ y   ┆ x != y │
# │ --- ┆ --- ┆ ---    │
# │ f64 ┆ f64 ┆ bool   │
# ╞═════╪═════╪════════╡
# │ 1.0 ┆ 2.0 ┆ true   │
# │ 2.0 ┆ 2.0 ┆ false  │
# │ NaN ┆ NaN ┆ false  │
# │ 4.0 ┆ 4.0 ┆ false  │
# └─────┴─────┴────────┘

Parameters:

  • other (Object) —

    A literal or expression value to compare with.

Returns:



3310
3311
3312
 
# File 'lib/polars/expr.rb', line 3310

def ne(other)
  self != other
end

#ne_missing(other) ⇒ Expr

Method equivalent of equality operator expr != other where None == None.

This differs from default ne where null values are propagated.

Examples:

df = Polars::DataFrame.new(
  {
    "x" => [1.0, 2.0, Float::NAN, 4.0, nil, nil],
    "y" => [2.0, 2.0, Float::NAN, 4.0, 5.0, nil]
  }
)
df.with_columns(
  Polars.col("x").ne(Polars.col("y")).alias("x ne y"),
  Polars.col("x").ne_missing(Polars.col("y")).alias("x ne_missing y")
)
# =>
# shape: (6, 4)
# ┌──────┬──────┬────────┬────────────────┐
# │ x    ┆ y    ┆ x ne y ┆ x ne_missing y │
# │ ---  ┆ ---  ┆ ---    ┆ ---            │
# │ f64  ┆ f64  ┆ bool   ┆ bool           │
# ╞══════╪══════╪════════╪════════════════╡
# │ 1.0  ┆ 2.0  ┆ true   ┆ true           │
# │ 2.0  ┆ 2.0  ┆ false  ┆ false          │
# │ NaN  ┆ NaN  ┆ false  ┆ false          │
# │ 4.0  ┆ 4.0  ┆ false  ┆ false          │
# │ null ┆ 5.0  ┆ null   ┆ true           │
# │ null ┆ null ┆ null   ┆ false          │
# └──────┴──────┴────────┴────────────────┘

Parameters:

  • other (Object) —

    A literal or expression value to compare with.

Returns:



3348
3349
3350
3351
 
# File 'lib/polars/expr.rb', line 3348

def ne_missing(other)
  other = Utils.parse_into_expression(other, str_as_lit: true)
  _from_rbexpr(_rbexpr.neq_missing(other))
end

#neg ⇒ Expr

Method equivalent of unary minus operator -expr.

Examples:

df = Polars::DataFrame.new({"a" => [-1, 0, 2, nil]})
df.with_columns(Polars.col("a").neg)
# =>
# shape: (4, 1)
# ┌──────┐
# │ a    │
# │ ---  │
# │ i64  │
# ╞══════╡
# │ 1    │
# │ 0    │
# │ -2   │
# │ null │
# └──────┘

Returns:



3536
3537
3538
 
# File 'lib/polars/expr.rb', line 3536

def neg
  -self
end

#null_count ⇒ Expr

Count null values.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [nil, 1, nil],
    "b" => [1, 2, 3]
  }
)
df.select(Polars.all.null_count)
# =>
# shape: (1, 2)
# ┌─────┬─────┐
# │ a   ┆ b   │
# │ --- ┆ --- │
# │ u32 ┆ u32 │
# ╞═════╪═════╡
# │ 2   ┆ 0   │
# └─────┴─────┘

Returns:



2144
2145
2146
 
# File 'lib/polars/expr.rb', line 2144

def null_count
  _from_rbexpr(_rbexpr.null_count)
end

#over(expr) ⇒ Expr

Apply window function over a subgroup.

This is similar to a group by + aggregation + self join. Or similar to window functions in Postgres.

Examples:

df = Polars::DataFrame.new(
  {
    "groups" => ["g1", "g1", "g2"],
    "values" => [1, 2, 3]
  }
)
df.with_column(
  Polars.col("values").max.over("groups").alias("max_by_group")
)
# =>
# shape: (3, 3)
# ┌────────┬────────┬──────────────┐
# │ groups ┆ values ┆ max_by_group │
# │ ---    ┆ ---    ┆ ---          │
# │ str    ┆ i64    ┆ i64          │
# ╞════════╪════════╪══════════════╡
# │ g1     ┆ 1      ┆ 2            │
# │ g1     ┆ 2      ┆ 2            │
# │ g2     ┆ 3      ┆ 3            │
# └────────┴────────┴──────────────┘
df = Polars::DataFrame.new(
  {
    "groups" => [1, 1, 2, 2, 1, 2, 3, 3, 1],
    "values" => [1, 2, 3, 4, 5, 6, 7, 8, 8]
  }
)
df.lazy
  .select([Polars.col("groups").sum.over("groups")])
  .collect
# =>
# shape: (9, 1)
# ┌────────┐
# │ groups │
# │ ---    │
# │ i64    │
# ╞════════╡
# │ 4      │
# │ 4      │
# │ 6      │
# │ 6      │
# │ 4      │
# │ 6      │
# │ 6      │
# │ 6      │
# │ 4      │
# └────────┘

Parameters:

  • expr (Object) —

    Column(s) to group by.

Returns:



2315
2316
2317
2318
 
# File 'lib/polars/expr.rb', line 2315

def over(expr)
  rbexprs = Utils.parse_into_list_of_expressions(expr)
  _from_rbexpr(_rbexpr.over(rbexprs))
end

#pct_change(n: 1) ⇒ Expr

Computes percentage change between values.

Percentage change (as fraction) between current element and most-recent non-null element at least n period(s) before the current element.

Computes the change from the previous row by default.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [10, 11, 12, nil, 12]
  }
)
df.with_column(Polars.col("a").pct_change.alias("pct_change"))
# =>
# shape: (5, 2)
# ┌──────┬────────────┐
# │ a    ┆ pct_change │
# │ ---  ┆ ---        │
# │ i64  ┆ f64        │
# ╞══════╪════════════╡
# │ 10   ┆ null       │
# │ 11   ┆ 0.1        │
# │ 12   ┆ 0.090909   │
# │ null ┆ 0.0        │
# │ 12   ┆ 0.0        │
# └──────┴────────────┘

Parameters:

  • n (Integer) (defaults to: 1) —

    Periods to shift for forming percent change.

Returns:



5795
5796
5797
5798
 
# File 'lib/polars/expr.rb', line 5795

def pct_change(n: 1)
  n = Utils.parse_into_expression(n)
  _from_rbexpr(_rbexpr.pct_change(n))
end

#peak_max ⇒ Expr

Get a boolean mask of the local maximum peaks.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3, 4, 5]})
df.select(Polars.col("a").peak_max)
# =>
# shape: (5, 1)
# ┌───────┐
# │ a     │
# │ ---   │
# │ bool  │
# ╞═══════╡
# │ false │
# │ false │
# │ false │
# │ false │
# │ true  │
# └───────┘

Returns:



2413
2414
2415
 
# File 'lib/polars/expr.rb', line 2413

def peak_max
  _from_rbexpr(_rbexpr.peak_max)
end

#peak_min ⇒ Expr

Get a boolean mask of the local minimum peaks.

Examples:

df = Polars::DataFrame.new({"a" => [4, 1, 3, 2, 5]})
df.select(Polars.col("a").peak_min)
# =>
# shape: (5, 1)
# ┌───────┐
# │ a     │
# │ ---   │
# │ bool  │
# ╞═══════╡
# │ false │
# │ true  │
# │ false │
# │ true  │
# │ false │
# └───────┘

Returns:



2437
2438
2439
 
# File 'lib/polars/expr.rb', line 2437

def peak_min
  _from_rbexpr(_rbexpr.peak_min)
end

#pow(exponent) ⇒ Expr

Raise expression to the power of exponent.

Examples:

df = Polars::DataFrame.new({"x" => [1, 2, 4, 8]})
df.with_columns(
  Polars.col("x").pow(3).alias("cube"),
  Polars.col("x").pow(Polars.col("x").log(2)).alias("x ** xlog2")
)
# =>
# shape: (4, 3)
# ┌─────┬──────┬────────────┐
# │ x   ┆ cube ┆ x ** xlog2 │
# │ --- ┆ ---  ┆ ---        │
# │ i64 ┆ i64  ┆ f64        │
# ╞═════╪══════╪════════════╡
# │ 1   ┆ 1    ┆ 1.0        │
# │ 2   ┆ 8    ┆ 2.0        │
# │ 4   ┆ 64   ┆ 16.0       │
# │ 8   ┆ 512  ┆ 512.0      │
# └─────┴──────┴────────────┘

Returns:



3594
3595
3596
 
# File 'lib/polars/expr.rb', line 3594

def pow(exponent)
  self**exponent
end

#prefix(prefix) ⇒ Expr

Add a prefix to the root column name of the expression.

Returns:



414
415
416
 
# File 'lib/polars/expr.rb', line 414

def prefix(prefix)
  name.prefix(prefix)
end

#product ⇒ Expr

Compute the product of an expression.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3]})
df.select(Polars.col("a").product)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ i64 │
# ╞═════╡
# │ 6   │
# └─────┘

Returns:



2076
2077
2078
 
# File 'lib/polars/expr.rb', line 2076

def product
  _from_rbexpr(_rbexpr.product)
end

#qcut(quantiles, labels: nil, left_closed: false, allow_duplicates: false, include_breaks: false) ⇒ Expr

Bin continuous values into discrete categories based on their quantiles.

Examples:

Divide a column into three categories according to pre-defined quantile probabilities.

df = Polars::DataFrame.new({"foo" => [-2, -1, 0, 1, 2]})
df.with_columns(
  Polars.col("foo").qcut([0.25, 0.75], labels: ["a", "b", "c"]).alias("qcut")
)
# =>
# shape: (5, 2)
# ┌─────┬──────┐
# │ foo ┆ qcut │
# │ --- ┆ ---  │
# │ i64 ┆ cat  │
# ╞═════╪══════╡
# │ -2  ┆ a    │
# │ -1  ┆ a    │
# │ 0   ┆ b    │
# │ 1   ┆ b    │
# │ 2   ┆ c    │
# └─────┴──────┘

Divide a column into two categories using uniform quantile probabilities.

df.with_columns(
  Polars.col("foo")
    .qcut(2, labels: ["low", "high"], left_closed: true)
    .alias("qcut")
)
# =>
# shape: (5, 2)
# ┌─────┬──────┐
# │ foo ┆ qcut │
# │ --- ┆ ---  │
# │ i64 ┆ cat  │
# ╞═════╪══════╡
# │ -2  ┆ low  │
# │ -1  ┆ low  │
# │ 0   ┆ high │
# │ 1   ┆ high │
# │ 2   ┆ high │
# └─────┴──────┘

Add both the category and the breakpoint.

df.with_columns(
  Polars.col("foo").qcut([0.25, 0.75], include_breaks: true).alias("qcut")
).unnest("qcut")
# =>
# shape: (5, 3)
# ┌─────┬────────────┬────────────┐
# │ foo ┆ breakpoint ┆ category   │
# │ --- ┆ ---        ┆ ---        │
# │ i64 ┆ f64        ┆ cat        │
# ╞═════╪════════════╪════════════╡
# │ -2  ┆ -1.0       ┆ (-inf, -1] │
# │ -1  ┆ -1.0       ┆ (-inf, -1] │
# │ 0   ┆ 1.0        ┆ (-1, 1]    │
# │ 1   ┆ 1.0        ┆ (-1, 1]    │
# │ 2   ┆ inf        ┆ (1, inf]   │
# └─────┴────────────┴────────────┘

Parameters:

  • quantiles (Array) —

    Either a list of quantile probabilities between 0 and 1 or a positive integer determining the number of bins with uniform probability.

  • labels (Array) (defaults to: nil) —

    Names of the categories. The number of labels must be equal to the number of categories.

  • left_closed (Boolean) (defaults to: false) —

    Set the intervals to be left-closed instead of right-closed.

  • allow_duplicates (Boolean) (defaults to: false) —

    If set to true, duplicates in the resulting quantiles are dropped, rather than raising a DuplicateError. This can happen even with unique probabilities, depending on the data.

  • include_breaks (Boolean) (defaults to: false) —

    Include a column with the right endpoint of the bin each observation falls in. This will change the data type of the output from a Categorical to a Struct.

Returns:



2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
 
# File 'lib/polars/expr.rb', line 2648

def qcut(quantiles, labels: nil, left_closed: false, allow_duplicates: false, include_breaks: false)
  if quantiles.is_a?(Integer)
    rbexpr = _rbexpr.qcut_uniform(
      quantiles, labels, left_closed, allow_duplicates, include_breaks
    )
  else
    rbexpr = _rbexpr.qcut(
      quantiles, labels, left_closed, allow_duplicates, include_breaks
    )
  end

  _from_rbexpr(rbexpr)
end

#quantile(quantile, interpolation: "nearest") ⇒ Expr

Get quantile value.

Examples:

df = Polars::DataFrame.new({"a" => [0, 1, 2, 3, 4, 5]})
df.select(Polars.col("a").quantile(0.3))
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 2.0 │
# └─────┘
df.select(Polars.col("a").quantile(0.3, interpolation: "higher"))
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 2.0 │
# └─────┘
df.select(Polars.col("a").quantile(0.3, interpolation: "lower"))
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 1.0 │
# └─────┘
df.select(Polars.col("a").quantile(0.3, interpolation: "midpoint"))
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 1.5 │
# └─────┘
df.select(Polars.col("a").quantile(0.3, interpolation: "linear"))
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 1.5 │
# └─────┘

Parameters:

  • quantile (Float) —

    Quantile between 0.0 and 1.0.

  • interpolation ("nearest", "higher", "lower", "midpoint", "linear") (defaults to: "nearest") —

    Interpolation method.

Returns:



2510
2511
2512
2513
 
# File 'lib/polars/expr.rb', line 2510

def quantile(quantile, interpolation: "nearest")
  quantile = Utils.parse_into_expression(quantile, str_as_lit: false)
  _from_rbexpr(_rbexpr.quantile(quantile, interpolation))
end

#rank(method: "average", reverse: false, seed: nil) ⇒ Expr

Assign ranks to data, dealing with ties appropriately.

Examples:

The 'average' method:

df = Polars::DataFrame.new({"a" => [3, 6, 1, 1, 6]})
df.select(Polars.col("a").rank)
# =>
# shape: (5, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 3.0 │
# │ 4.5 │
# │ 1.5 │
# │ 1.5 │
# │ 4.5 │
# └─────┘

The 'ordinal' method:

df = Polars::DataFrame.new({"a" => [3, 6, 1, 1, 6]})
df.select(Polars.col("a").rank(method: "ordinal"))
# =>
# shape: (5, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ u32 │
# ╞═════╡
# │ 3   │
# │ 4   │
# │ 1   │
# │ 2   │
# │ 5   │
# └─────┘

Parameters:

  • method ("average", "min", "max", "dense", "ordinal", "random") (defaults to: "average") —

    The method used to assign ranks to tied elements. The following methods are available:

    • 'average' : The average of the ranks that would have been assigned to all the tied values is assigned to each value.
    • 'min' : The minimum of the ranks that would have been assigned to all the tied values is assigned to each value. (This is also referred to as "competition" ranking.)
    • 'max' : The maximum of the ranks that would have been assigned to all the tied values is assigned to each value.
    • 'dense' : Like 'min', but the rank of the next highest element is assigned the rank immediately after those assigned to the tied elements.
    • 'ordinal' : All values are given a distinct rank, corresponding to the order that the values occur in the Series.
    • 'random' : Like 'ordinal', but the rank for ties is not dependent on the order that the values occur in the Series.
  • reverse (Boolean) (defaults to: false) —

    Reverse the operation.

  • seed (Integer) (defaults to: nil) —

    If method: "random", use this as seed.

Returns:



5728
5729
5730
 
# File 'lib/polars/expr.rb', line 5728

def rank(method: "average", reverse: false, seed: nil)
  _from_rbexpr(_rbexpr.rank(method, reverse, seed))
end

#rechunk ⇒ Expr

Create a single chunk of memory for this Series.

Examples:

Create a Series with 3 nulls, append column a then rechunk

df = Polars::DataFrame.new({"a" => [1, 1, 2]})
df.select(Polars.repeat(nil, 3).append(Polars.col("a")).rechunk)
# =>
# shape: (6, 1)
# ┌────────┐
# │ repeat │
# │ ---    │
# │ i64    │
# ╞════════╡
# │ null   │
# │ null   │
# │ null   │
# │ 1      │
# │ 1      │
# │ 2      │
# └────────┘

Returns:



839
840
841
 
# File 'lib/polars/expr.rb', line 839

def rechunk
  _from_rbexpr(_rbexpr.rechunk)
end

#reinterpret(signed: false) ⇒ Expr

Reinterpret the underlying bits as a signed/unsigned integer.

This operation is only allowed for 64bit integers. For lower bits integers, you can safely use that cast operation.

Examples:

s = Polars::Series.new("a", [1, 1, 2], dtype: :u64)
df = Polars::DataFrame.new([s])
df.select(
  [
    Polars.col("a").reinterpret(signed: true).alias("reinterpreted"),
    Polars.col("a").alias("original")
  ]
)
# =>
# shape: (3, 2)
# ┌───────────────┬──────────┐
# │ reinterpreted ┆ original │
# │ ---           ┆ ---      │
# │ i64           ┆ u64      │
# ╞═══════════════╪══════════╡
# │ 1             ┆ 1        │
# │ 1             ┆ 1        │
# │ 2             ┆ 2        │
# └───────────────┴──────────┘

Parameters:

  • signed (Boolean) (defaults to: false) —

    If true, reinterpret as :i64. Otherwise, reinterpret as :u64.

Returns:



3845
3846
3847
 
# File 'lib/polars/expr.rb', line 3845

def reinterpret(signed: false)
  _from_rbexpr(_rbexpr.reinterpret(signed))
end

#repeat_by(by) ⇒ Expr

Repeat the elements in this Series as specified in the given expression.

The repeated elements are expanded into a List.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => ["x", "y", "z"],
    "n" => [1, 2, 3]
  }
)
df.select(Polars.col("a").repeat_by("n"))
# =>
# shape: (3, 1)
# ┌─────────────────┐
# │ a               │
# │ ---             │
# │ list[str]       │
# ╞═════════════════╡
# │ ["x"]           │
# │ ["y", "y"]      │
# │ ["z", "z", "z"] │
# └─────────────────┘

Parameters:

  • by (Object) —

    Numeric column that determines how often the values will be repeated. The column will be coerced to UInt32. Give this dtype to make the coercion a no-op.

Returns:



3693
3694
3695
3696
 
# File 'lib/polars/expr.rb', line 3693

def repeat_by(by)
  by = Utils.parse_into_expression(by, str_as_lit: false)
  _from_rbexpr(_rbexpr.repeat_by(by))
end

#replace(old, new = NO_DEFAULT, default: NO_DEFAULT, return_dtype: nil) ⇒ Expr

Replace values by different values.

Examples:

Replace a single value by another value. Values that were not replaced remain unchanged.

df = Polars::DataFrame.new({"a" => [1, 2, 2, 3]})
df.with_columns(replaced: Polars.col("a").replace(2, 100))
# =>
# shape: (4, 2)
# ┌─────┬──────────┐
# │ a   ┆ replaced │
# │ --- ┆ ---      │
# │ i64 ┆ i64      │
# ╞═════╪══════════╡
# │ 1   ┆ 1        │
# │ 2   ┆ 100      │
# │ 2   ┆ 100      │
# │ 3   ┆ 3        │
# └─────┴──────────┘

Replace multiple values by passing sequences to the old and new parameters.

df.with_columns(replaced: Polars.col("a").replace([2, 3], [100, 200]))
# =>
# shape: (4, 2)
# ┌─────┬──────────┐
# │ a   ┆ replaced │
# │ --- ┆ ---      │
# │ i64 ┆ i64      │
# ╞═════╪══════════╡
# │ 1   ┆ 1        │
# │ 2   ┆ 100      │
# │ 2   ┆ 100      │
# │ 3   ┆ 200      │
# └─────┴──────────┘

Passing a mapping with replacements is also supported as syntactic sugar. Specify a default to set all values that were not matched.

mapping = {2 => 100, 3 => 200}
df.with_columns(replaced: Polars.col("a").replace(mapping, default: -1))
# =>
# shape: (4, 2)
# ┌─────┬──────────┐
# │ a   ┆ replaced │
# │ --- ┆ ---      │
# │ i64 ┆ i64      │
# ╞═════╪══════════╡
# │ 1   ┆ -1       │
# │ 2   ┆ 100      │
# │ 2   ┆ 100      │
# │ 3   ┆ 200      │
# └─────┴──────────┘

Replacing by values of a different data type sets the return type based on a combination of the new data type and either the original data type or the default data type if it was set.

df = Polars::DataFrame.new({"a" => ["x", "y", "z"]})
mapping = {"x" => 1, "y" => 2, "z" => 3}
df.with_columns(replaced: Polars.col("a").replace(mapping))
# =>
# shape: (3, 2)
# ┌─────┬──────────┐
# │ a   ┆ replaced │
# │ --- ┆ ---      │
# │ str ┆ str      │
# ╞═════╪══════════╡
# │ x   ┆ 1        │
# │ y   ┆ 2        │
# │ z   ┆ 3        │
# └─────┴──────────┘
df.with_columns(replaced: Polars.col("a").replace(mapping, default: nil))
# =>
# shape: (3, 2)
# ┌─────┬──────────┐
# │ a   ┆ replaced │
# │ --- ┆ ---      │
# │ str ┆ i64      │
# ╞═════╪══════════╡
# │ x   ┆ 1        │
# │ y   ┆ 2        │
# │ z   ┆ 3        │
# └─────┴──────────┘

Set the return_dtype parameter to control the resulting data type directly.

df.with_columns(
  replaced: Polars.col("a").replace(mapping, return_dtype: Polars::UInt8)
)
# =>
# shape: (3, 2)
# ┌─────┬──────────┐
# │ a   ┆ replaced │
# │ --- ┆ ---      │
# │ str ┆ u8       │
# ╞═════╪══════════╡
# │ x   ┆ 1        │
# │ y   ┆ 2        │
# │ z   ┆ 3        │
# └─────┴──────────┘

Expression input is supported for all parameters.

df = Polars::DataFrame.new({"a" => [1, 2, 2, 3], "b" => [1.5, 2.5, 5.0, 1.0]})
df.with_columns(
  replaced: Polars.col("a").replace(
    Polars.col("a").max,
    Polars.col("b").sum,
    default: Polars.col("b")
  )
)
# =>
# shape: (4, 3)
# ┌─────┬─────┬──────────┐
# │ a   ┆ b   ┆ replaced │
# │ --- ┆ --- ┆ ---      │
# │ i64 ┆ f64 ┆ f64      │
# ╞═════╪═════╪══════════╡
# │ 1   ┆ 1.5 ┆ 1.5      │
# │ 2   ┆ 2.5 ┆ 2.5      │
# │ 2   ┆ 5.0 ┆ 5.0      │
# │ 3   ┆ 1.0 ┆ 10.0     │
# └─────┴─────┴──────────┘

Parameters:

  • old (Object) —

    Value or sequence of values to replace. Accepts expression input. Sequences are parsed as Series, other non-expression inputs are parsed as literals. Also accepts a mapping of values to their replacement.

  • new (Object) (defaults to: NO_DEFAULT) —

    Value or sequence of values to replace by. Accepts expression input. Sequences are parsed as Series, other non-expression inputs are parsed as literals. Length must match the length of old or have length 1.

  • default (Object) (defaults to: NO_DEFAULT) —

    Set values that were not replaced to this value. Defaults to keeping the original value. Accepts expression input. Non-expression inputs are parsed as literals.

  • return_dtype (Object) (defaults to: nil) —

    The data type of the resulting expression. If set to nil (default), the data type is determined automatically based on the other inputs.

Returns:



6952
6953
6954
6955
6956
6957
6958
6959
6960
6961
6962
6963
6964
6965
6966
6967
6968
6969
6970
6971
6972
6973
6974
6975
6976
6977
6978
6979
 
# File 'lib/polars/expr.rb', line 6952

def replace(old, new = NO_DEFAULT, default: NO_DEFAULT, return_dtype: nil)
  if !default.eql?(NO_DEFAULT)
    return replace_strict(old, new, default: default, return_dtype: return_dtype)
  end

  if new.eql?(NO_DEFAULT) && old.is_a?(Hash)
    new = Series.new(old.values)
    old = Series.new(old.keys)
  else
    if old.is_a?(::Array)
      old = Series.new(old)
    end
    if new.is_a?(::Array)
      new = Series.new(new)
    end
  end

  old = Utils.parse_into_expression(old, str_as_lit: true)
  new = Utils.parse_into_expression(new, str_as_lit: true)

  result = _from_rbexpr(_rbexpr.replace(old, new))

  if !return_dtype.nil?
    result = result.cast(return_dtype)
  end

  result
end

#replace_strict(old, new = NO_DEFAULT, default: NO_DEFAULT, return_dtype: nil) ⇒ Expr

Note:

The global string cache must be enabled when replacing categorical values.

Replace all values by different values.

Examples:

Replace values by passing sequences to the old and new parameters.

df = Polars::DataFrame.new({"a" => [1, 2, 2, 3]})
df.with_columns(
  replaced: Polars.col("a").replace_strict([1, 2, 3], [100, 200, 300])
)
# =>
# shape: (4, 2)
# ┌─────┬──────────┐
# │ a   ┆ replaced │
# │ --- ┆ ---      │
# │ i64 ┆ i64      │
# ╞═════╪══════════╡
# │ 1   ┆ 100      │
# │ 2   ┆ 200      │
# │ 2   ┆ 200      │
# │ 3   ┆ 300      │
# └─────┴──────────┘

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.

mapping = {2 => 200, 3 => 300}
df.with_columns(replaced: Polars.col("a").replace_strict(mapping, default: -1))
# =>
# shape: (4, 2)
# ┌─────┬──────────┐
# │ a   ┆ replaced │
# │ --- ┆ ---      │
# │ i64 ┆ i64      │
# ╞═════╪══════════╡
# │ 1   ┆ -1       │
# │ 2   ┆ 200      │
# │ 2   ┆ 200      │
# │ 3   ┆ 300      │
# └─────┴──────────┘

Replacing by values of a different data type sets the return type based on a combination of the new data type and the default data type.

df = Polars::DataFrame.new({"a" => ["x", "y", "z"]})
mapping = {"x" => 1, "y" => 2, "z" => 3}
df.with_columns(replaced: Polars.col("a").replace_strict(mapping))
# =>
# shape: (3, 2)
# ┌─────┬──────────┐
# │ a   ┆ replaced │
# │ --- ┆ ---      │
# │ str ┆ i64      │
# ╞═════╪══════════╡
# │ x   ┆ 1        │
# │ y   ┆ 2        │
# │ z   ┆ 3        │
# └─────┴──────────┘
df.with_columns(replaced: Polars.col("a").replace_strict(mapping, default: "x"))
# =>
# shape: (3, 2)
# ┌─────┬──────────┐
# │ a   ┆ replaced │
# │ --- ┆ ---      │
# │ str ┆ str      │
# ╞═════╪══════════╡
# │ x   ┆ 1        │
# │ y   ┆ 2        │
# │ z   ┆ 3        │
# └─────┴──────────┘

Set the return_dtype parameter to control the resulting data type directly.

df.with_columns(
  replaced: Polars.col("a").replace_strict(mapping, return_dtype: Polars::UInt8)
)
# =>
# shape: (3, 2)
# ┌─────┬──────────┐
# │ a   ┆ replaced │
# │ --- ┆ ---      │
# │ str ┆ u8       │
# ╞═════╪══════════╡
# │ x   ┆ 1        │
# │ y   ┆ 2        │
# │ z   ┆ 3        │
# └─────┴──────────┘

Expression input is supported for all parameters.

df = Polars::DataFrame.new({"a" => [1, 2, 2, 3], "b" => [1.5, 2.5, 5.0, 1.0]})
df.with_columns(
  replaced: Polars.col("a").replace_strict(
    Polars.col("a").max,
    Polars.col("b").sum,
    default: Polars.col("b")
  )
)
# =>
# shape: (4, 3)
# ┌─────┬─────┬──────────┐
# │ a   ┆ b   ┆ replaced │
# │ --- ┆ --- ┆ ---      │
# │ i64 ┆ f64 ┆ f64      │
# ╞═════╪═════╪══════════╡
# │ 1   ┆ 1.5 ┆ 1.5      │
# │ 2   ┆ 2.5 ┆ 2.5      │
# │ 2   ┆ 5.0 ┆ 5.0      │
# │ 3   ┆ 1.0 ┆ 10.0     │
# └─────┴─────┴──────────┘

Parameters:

  • old (Object) —

    Value or sequence of values to replace. Accepts expression input. Sequences are parsed as Series, other non-expression inputs are parsed as literals. Also accepts a mapping of values to their replacement as syntactic sugar for replace_all(old: Series.new(mapping.keys), new: Serie.new(mapping.values)).

  • new (Object) (defaults to: NO_DEFAULT) —

    Value or sequence of values to replace by. Accepts expression input. Sequences are parsed as Series, other non-expression inputs are parsed as literals. Length must match the length of old or have length 1.

  • default (Object) (defaults to: NO_DEFAULT) —

    Set values that were not replaced to this value. If no default is specified, (default), an error is raised if any values were not replaced. Accepts expression input. Non-expression inputs are parsed as literals.

  • return_dtype (Object) (defaults to: nil) —

    The data type of the resulting expression. If set to nil (default), the data type is determined automatically based on the other inputs.

Returns:



7108
7109
7110
7111
7112
7113
7114
7115
7116
7117
7118
7119
7120
7121
7122
7123
7124
7125
7126
7127
 
# File 'lib/polars/expr.rb', line 7108

def replace_strict(
  old,
  new = NO_DEFAULT,
  default: NO_DEFAULT,
  return_dtype: nil
)
  if new.eql?(NO_DEFAULT) && old.is_a?(Hash)
    new = Series.new(old.values)
    old = Series.new(old.keys)
  end

  old = Utils.parse_into_expression(old, str_as_lit: true, list_as_series: true)
  new = Utils.parse_into_expression(new, str_as_lit: true, list_as_series: true)

  default = default.eql?(NO_DEFAULT) ? nil : Utils.parse_into_expression(default, str_as_lit: true)

  _from_rbexpr(
    _rbexpr.replace_strict(old, new, default, return_dtype)
  )
end

#reshape(dims) ⇒ Expr

Reshape this Expr to a flat Series or a Series of Lists.

Examples:

df = Polars::DataFrame.new({"foo" => [1, 2, 3, 4, 5, 6, 7, 8, 9]})
square = df.select(Polars.col("foo").reshape([3, 3]))
# =>
# shape: (3, 1)
# ┌───────────────┐
# │ foo           │
# │ ---           │
# │ array[i64, 3] │
# ╞═══════════════╡
# │ [1, 2, 3]     │
# │ [4, 5, 6]     │
# │ [7, 8, 9]     │
# └───────────────┘
square.select(Polars.col("foo").reshape([9]))
# =>
# shape: (9, 1)
# ┌─────┐
# │ foo │
# │ --- │
# │ i64 │
# ╞═════╡
# │ 1   │
# │ 2   │
# │ 3   │
# │ 4   │
# │ 5   │
# │ 6   │
# │ 7   │
# │ 8   │
# │ 9   │
# └─────┘

Parameters:

  • dims (Array) —

    Tuple of the dimension sizes. If a -1 is used in any of the dimensions, that dimension is inferred.

Returns:



6312
6313
6314
 
# File 'lib/polars/expr.rb', line 6312

def reshape(dims)
  _from_rbexpr(_rbexpr.reshape(dims))
end

#reverse ⇒ Expr

Reverse the selection.

Returns:



1866
1867
1868
 
# File 'lib/polars/expr.rb', line 1866

def reverse
  _from_rbexpr(_rbexpr.reverse)
end

#rle ⇒ Expr

Get the lengths of runs of identical values.

Examples:

df = Polars::DataFrame.new(Polars::Series.new("s", [1, 1, 2, 1, nil, 1, 3, 3]))
df.select(Polars.col("s").rle).unnest("s")
# =>
# shape: (6, 2)
# ┌─────┬───────┐
# │ len ┆ value │
# │ --- ┆ ---   │
# │ u32 ┆ i64   │
# ╞═════╪═══════╡
# │ 2   ┆ 1     │
# │ 1   ┆ 2     │
# │ 1   ┆ 1     │
# │ 1   ┆ null  │
# │ 1   ┆ 1     │
# │ 2   ┆ 3     │
# └─────┴───────┘

Returns:



2683
2684
2685
 
# File 'lib/polars/expr.rb', line 2683

def rle
  _from_rbexpr(_rbexpr.rle)
end

#rle_id ⇒ Expr

Map values to run IDs.

Similar to RLE, but it maps each value to an ID corresponding to the run into which it falls. This is especially useful when you want to define groups by runs of identical values rather than the values themselves.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 1, 1, 1], "b" => ["x", "x", nil, "y", "y"]})
df.with_columns([Polars.col("a").rle_id.alias("a_r"), Polars.struct(["a", "b"]).rle_id.alias("ab_r")])
# =>
# shape: (5, 4)
# ┌─────┬──────┬─────┬──────┐
# │ a   ┆ b    ┆ a_r ┆ ab_r │
# │ --- ┆ ---  ┆ --- ┆ ---  │
# │ i64 ┆ str  ┆ u32 ┆ u32  │
# ╞═════╪══════╪═════╪══════╡
# │ 1   ┆ x    ┆ 0   ┆ 0    │
# │ 2   ┆ x    ┆ 1   ┆ 1    │
# │ 1   ┆ null ┆ 2   ┆ 2    │
# │ 1   ┆ y    ┆ 2   ┆ 3    │
# │ 1   ┆ y    ┆ 2   ┆ 3    │
# └─────┴──────┴─────┴──────┘

Returns:



2711
2712
2713
 
# File 'lib/polars/expr.rb', line 2711

def rle_id
  _from_rbexpr(_rbexpr.rle_id)
end

#rolling_max(window_size, weights: nil, min_periods: nil, center: false) ⇒ Expr

Note:

This functionality is experimental and may change without it being considered a breaking change.

Note:

If you want to compute multiple aggregation statistics over the same dynamic window, consider using group_by_rolling this method can cache the window size computation.

Apply a rolling max (moving max) over the values in this array.

A window of length window_size will traverse the array. The values that fill this window will (optionally) be multiplied with the weights given by the weight vector. The resulting values will be aggregated to their sum.

Examples:

df = Polars::DataFrame.new({"A" => [1.0, 2.0, 3.0, 4.0, 5.0, 6.0]})
df.select(
  [
    Polars.col("A").rolling_max(2)
  ]
)
# =>
# shape: (6, 1)
# ┌──────┐
# │ A    │
# │ ---  │
# │ f64  │
# ╞══════╡
# │ null │
# │ 2.0  │
# │ 3.0  │
# │ 4.0  │
# │ 5.0  │
# │ 6.0  │
# └──────┘

Parameters:

  • window_size (Integer) —

    The length of the window. Can be a fixed integer size, or a dynamic temporal size indicated by a timedelta or the following string language:

    • 1ns (1 nanosecond)
    • 1us (1 microsecond)
    • 1ms (1 millisecond)
    • 1s (1 second)
    • 1m (1 minute)
    • 1h (1 hour)
    • 1d (1 day)
    • 1w (1 week)
    • 1mo (1 calendar month)
    • 1y (1 calendar year)
    • 1i (1 index count)

    If a timedelta or the dynamic string language is used, the by and closed arguments must also be set.

  • weights (Array) (defaults to: nil) —

    An optional slice with the same length as the window that will be multiplied elementwise with the values in the window.

  • min_periods (Integer) (defaults to: nil) —

    The number of values in the window that should be non-null before computing a result. If None, it will be set equal to window size.

  • center (Boolean) (defaults to: false) —

    Set the labels at the center of the window

Returns:



5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
 
# File 'lib/polars/expr.rb', line 5051

def rolling_max(
  window_size,
  weights: nil,
  min_periods: nil,
  center: false
)
  _from_rbexpr(
    _rbexpr.rolling_max(
      window_size, weights, min_periods, center
    )
  )
end

#rolling_max_by(by, window_size, min_periods: 1, closed: "right", warn_if_unsorted: nil) ⇒ Expr

Note:

If you want to compute multiple aggregation statistics over the same dynamic window, consider using rolling - this method can cache the window size computation.

Apply a rolling max based on another column.

Examples:

Create a DataFrame with a datetime column and a row number column

start = DateTime.new(2001, 1, 1)
stop = DateTime.new(2001, 1, 2)
df_temporal = Polars::DataFrame.new(
    {"date" => Polars.datetime_range(start, stop, "1h", eager: true)}
).with_row_index
# =>
# shape: (25, 2)
# ┌───────┬─────────────────────┐
# │ index ┆ date                │
# │ ---   ┆ ---                 │
# │ u32   ┆ datetime[ns]        │
# ╞═══════╪═════════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 │
# │ 1     ┆ 2001-01-01 01:00:00 │
# │ 2     ┆ 2001-01-01 02:00:00 │
# │ 3     ┆ 2001-01-01 03:00:00 │
# │ 4     ┆ 2001-01-01 04:00:00 │
# │ …     ┆ …                   │
# │ 20    ┆ 2001-01-01 20:00:00 │
# │ 21    ┆ 2001-01-01 21:00:00 │
# │ 22    ┆ 2001-01-01 22:00:00 │
# │ 23    ┆ 2001-01-01 23:00:00 │
# │ 24    ┆ 2001-01-02 00:00:00 │
# └───────┴─────────────────────┘

Compute the rolling max with the temporal windows closed on the right (default)

df_temporal.with_columns(
  rolling_row_max: Polars.col("index").rolling_max_by("date", "2h")
)
# =>
# shape: (25, 3)
# ┌───────┬─────────────────────┬─────────────────┐
# │ index ┆ date                ┆ rolling_row_max │
# │ ---   ┆ ---                 ┆ ---             │
# │ u32   ┆ datetime[ns]        ┆ u32             │
# ╞═══════╪═════════════════════╪═════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 ┆ 0               │
# │ 1     ┆ 2001-01-01 01:00:00 ┆ 1               │
# │ 2     ┆ 2001-01-01 02:00:00 ┆ 2               │
# │ 3     ┆ 2001-01-01 03:00:00 ┆ 3               │
# │ 4     ┆ 2001-01-01 04:00:00 ┆ 4               │
# │ …     ┆ …                   ┆ …               │
# │ 20    ┆ 2001-01-01 20:00:00 ┆ 20              │
# │ 21    ┆ 2001-01-01 21:00:00 ┆ 21              │
# │ 22    ┆ 2001-01-01 22:00:00 ┆ 22              │
# │ 23    ┆ 2001-01-01 23:00:00 ┆ 23              │
# │ 24    ┆ 2001-01-02 00:00:00 ┆ 24              │
# └───────┴─────────────────────┴─────────────────┘

Compute the rolling max with the closure of windows on both sides

df_temporal.with_columns(
  rolling_row_max: Polars.col("index").rolling_max_by(
    "date", "2h", closed: "both"
  )
)
# =>
# shape: (25, 3)
# ┌───────┬─────────────────────┬─────────────────┐
# │ index ┆ date                ┆ rolling_row_max │
# │ ---   ┆ ---                 ┆ ---             │
# │ u32   ┆ datetime[ns]        ┆ u32             │
# ╞═══════╪═════════════════════╪═════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 ┆ 0               │
# │ 1     ┆ 2001-01-01 01:00:00 ┆ 1               │
# │ 2     ┆ 2001-01-01 02:00:00 ┆ 2               │
# │ 3     ┆ 2001-01-01 03:00:00 ┆ 3               │
# │ 4     ┆ 2001-01-01 04:00:00 ┆ 4               │
# │ …     ┆ …                   ┆ …               │
# │ 20    ┆ 2001-01-01 20:00:00 ┆ 20              │
# │ 21    ┆ 2001-01-01 21:00:00 ┆ 21              │
# │ 22    ┆ 2001-01-01 22:00:00 ┆ 22              │
# │ 23    ┆ 2001-01-01 23:00:00 ┆ 23              │
# │ 24    ┆ 2001-01-02 00:00:00 ┆ 24              │
# └───────┴─────────────────────┴─────────────────┘

Parameters:

  • by (String) —

    This column must be of dtype Datetime or Date.

  • window_size (String) —

    The length of the window. Can be a dynamic temporal size indicated by a timedelta or the following string language:

    • 1ns (1 nanosecond)
    • 1us (1 microsecond)
    • 1ms (1 millisecond)
    • 1s (1 second)
    • 1m (1 minute)
    • 1h (1 hour)
    • 1d (1 calendar day)
    • 1w (1 calendar week)
    • 1mo (1 calendar month)
    • 1q (1 calendar quarter)
    • 1y (1 calendar year)

    By "calendar day", we mean the corresponding time on the next day (which may not be 24 hours, due to daylight savings). Similarly for "calendar week", "calendar month", "calendar quarter", and "calendar year".

  • min_periods (Integer) (defaults to: 1) —

    The number of values in the window that should be non-null before computing a result.

  • closed ('left', 'right', 'both', 'none') (defaults to: "right") —

    Define which sides of the temporal interval are closed (inclusive), defaults to 'right'.

  • warn_if_unsorted (Boolean) (defaults to: nil) —

    Warn if data is not known to be sorted by by column.

Returns:



4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
 
# File 'lib/polars/expr.rb', line 4130

def rolling_max_by(
  by,
  window_size,
  min_periods: 1,
  closed: "right",
  warn_if_unsorted: nil
)
  window_size = _prepare_rolling_by_window_args(window_size)
  by = Utils.parse_into_expression(by)
  _from_rbexpr(
    _rbexpr.rolling_max_by(by, window_size, min_periods, closed)
  )
end

#rolling_mean(window_size, weights: nil, min_periods: nil, center: false) ⇒ Expr

Note:

This functionality is experimental and may change without it being considered a breaking change.

Note:

If you want to compute multiple aggregation statistics over the same dynamic window, consider using group_by_rolling this method can cache the window size computation.

Apply a rolling mean (moving mean) over the values in this array.

A window of length window_size will traverse the array. The values that fill this window will (optionally) be multiplied with the weights given by the weight vector. The resulting values will be aggregated to their sum.

Examples:

df = Polars::DataFrame.new({"A" => [1.0, 8.0, 6.0, 2.0, 16.0, 10.0]})
df.select(
  [
    Polars.col("A").rolling_mean(2)
  ]
)
# =>
# shape: (6, 1)
# ┌──────┐
# │ A    │
# │ ---  │
# │ f64  │
# ╞══════╡
# │ null │
# │ 4.5  │
# │ 7.0  │
# │ 4.0  │
# │ 9.0  │
# │ 13.0 │
# └──────┘

Parameters:

  • window_size (Integer) —

    The length of the window. Can be a fixed integer size, or a dynamic temporal size indicated by a timedelta or the following string language:

    • 1ns (1 nanosecond)
    • 1us (1 microsecond)
    • 1ms (1 millisecond)
    • 1s (1 second)
    • 1m (1 minute)
    • 1h (1 hour)
    • 1d (1 day)
    • 1w (1 week)
    • 1mo (1 calendar month)
    • 1y (1 calendar year)
    • 1i (1 index count)

    If a timedelta or the dynamic string language is used, the by and closed arguments must also be set.

  • weights (Array) (defaults to: nil) —

    An optional slice with the same length as the window that will be multiplied elementwise with the values in the window.

  • min_periods (Integer) (defaults to: nil) —

    The number of values in the window that should be non-null before computing a result. If None, it will be set equal to window size.

  • center (Boolean) (defaults to: false) —

    Set the labels at the center of the window

Returns:



5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
 
# File 'lib/polars/expr.rb', line 5129

def rolling_mean(
  window_size,
  weights: nil,
  min_periods: nil,
  center: false
)
  _from_rbexpr(
    _rbexpr.rolling_mean(
      window_size, weights, min_periods, center
    )
  )
end

#rolling_mean_by(by, window_size, min_periods: 1, closed: "right", warn_if_unsorted: nil) ⇒ Expr

Note:

If you want to compute multiple aggregation statistics over the same dynamic window, consider using rolling - this method can cache the window size computation.

Apply a rolling mean based on another column.

Examples:

Create a DataFrame with a datetime column and a row number column

start = DateTime.new(2001, 1, 1)
stop = DateTime.new(2001, 1, 2)
df_temporal = Polars::DataFrame.new(
    {"date" => Polars.datetime_range(start, stop, "1h", eager: true)}
).with_row_index
# =>
# shape: (25, 2)
# ┌───────┬─────────────────────┐
# │ index ┆ date                │
# │ ---   ┆ ---                 │
# │ u32   ┆ datetime[ns]        │
# ╞═══════╪═════════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 │
# │ 1     ┆ 2001-01-01 01:00:00 │
# │ 2     ┆ 2001-01-01 02:00:00 │
# │ 3     ┆ 2001-01-01 03:00:00 │
# │ 4     ┆ 2001-01-01 04:00:00 │
# │ …     ┆ …                   │
# │ 20    ┆ 2001-01-01 20:00:00 │
# │ 21    ┆ 2001-01-01 21:00:00 │
# │ 22    ┆ 2001-01-01 22:00:00 │
# │ 23    ┆ 2001-01-01 23:00:00 │
# │ 24    ┆ 2001-01-02 00:00:00 │
# └───────┴─────────────────────┘

Compute the rolling mean with the temporal windows closed on the right (default)

df_temporal.with_columns(
  rolling_row_mean: Polars.col("index").rolling_mean_by(
    "date", "2h"
  )
)
# =>
# shape: (25, 3)
# ┌───────┬─────────────────────┬──────────────────┐
# │ index ┆ date                ┆ rolling_row_mean │
# │ ---   ┆ ---                 ┆ ---              │
# │ u32   ┆ datetime[ns]        ┆ f64              │
# ╞═══════╪═════════════════════╪══════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 ┆ 0.0              │
# │ 1     ┆ 2001-01-01 01:00:00 ┆ 0.5              │
# │ 2     ┆ 2001-01-01 02:00:00 ┆ 1.5              │
# │ 3     ┆ 2001-01-01 03:00:00 ┆ 2.5              │
# │ 4     ┆ 2001-01-01 04:00:00 ┆ 3.5              │
# │ …     ┆ …                   ┆ …                │
# │ 20    ┆ 2001-01-01 20:00:00 ┆ 19.5             │
# │ 21    ┆ 2001-01-01 21:00:00 ┆ 20.5             │
# │ 22    ┆ 2001-01-01 22:00:00 ┆ 21.5             │
# │ 23    ┆ 2001-01-01 23:00:00 ┆ 22.5             │
# │ 24    ┆ 2001-01-02 00:00:00 ┆ 23.5             │
# └───────┴─────────────────────┴──────────────────┘

Compute the rolling mean with the closure of windows on both sides

df_temporal.with_columns(
  rolling_row_mean: Polars.col("index").rolling_mean_by(
    "date", "2h", closed: "both"
  )
)
# =>
# shape: (25, 3)
# ┌───────┬─────────────────────┬──────────────────┐
# │ index ┆ date                ┆ rolling_row_mean │
# │ ---   ┆ ---                 ┆ ---              │
# │ u32   ┆ datetime[ns]        ┆ f64              │
# ╞═══════╪═════════════════════╪══════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 ┆ 0.0              │
# │ 1     ┆ 2001-01-01 01:00:00 ┆ 0.5              │
# │ 2     ┆ 2001-01-01 02:00:00 ┆ 1.0              │
# │ 3     ┆ 2001-01-01 03:00:00 ┆ 2.0              │
# │ 4     ┆ 2001-01-01 04:00:00 ┆ 3.0              │
# │ …     ┆ …                   ┆ …                │
# │ 20    ┆ 2001-01-01 20:00:00 ┆ 19.0             │
# │ 21    ┆ 2001-01-01 21:00:00 ┆ 20.0             │
# │ 22    ┆ 2001-01-01 22:00:00 ┆ 21.0             │
# │ 23    ┆ 2001-01-01 23:00:00 ┆ 22.0             │
# │ 24    ┆ 2001-01-02 00:00:00 ┆ 23.0             │
# └───────┴─────────────────────┴──────────────────┘

Parameters:

  • by (String) —

    This column must be of dtype Datetime or Date.

  • window_size (String) —

    The length of the window. Can be a dynamic temporal size indicated by a timedelta or the following string language:

    • 1ns (1 nanosecond)
    • 1us (1 microsecond)
    • 1ms (1 millisecond)
    • 1s (1 second)
    • 1m (1 minute)
    • 1h (1 hour)
    • 1d (1 calendar day)
    • 1w (1 calendar week)
    • 1mo (1 calendar month)
    • 1q (1 calendar quarter)
    • 1y (1 calendar year)

    By "calendar day", we mean the corresponding time on the next day (which may not be 24 hours, due to daylight savings). Similarly for "calendar week", "calendar month", "calendar quarter", and "calendar year".

  • min_periods (Integer) (defaults to: 1) —

    The number of values in the window that should be non-null before computing a result.

  • closed ('left', 'right', 'both', 'none') (defaults to: "right") —

    Define which sides of the temporal interval are closed (inclusive), defaults to 'right'.

  • warn_if_unsorted (Boolean) (defaults to: nil) —

    Warn if data is not known to be sorted by by column.

Returns:



4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
 
# File 'lib/polars/expr.rb', line 4261

def rolling_mean_by(
  by,
  window_size,
  min_periods: 1,
  closed: "right",
  warn_if_unsorted: nil
)
  window_size = _prepare_rolling_by_window_args(window_size)
  by = Utils.parse_into_expression(by)
  _from_rbexpr(
    _rbexpr.rolling_mean_by(
      by,
      window_size,
      min_periods,
      closed
    )
  )
end

#rolling_median(window_size, weights: nil, min_periods: nil, center: false) ⇒ Expr

Note:

This functionality is experimental and may change without it being considered a breaking change.

Note:

If you want to compute multiple aggregation statistics over the same dynamic window, consider using group_by_rolling this method can cache the window size computation.

Compute a rolling median.

Examples:

df = Polars::DataFrame.new({"A" => [1.0, 2.0, 3.0, 4.0, 6.0, 8.0]})
df.select(
  [
    Polars.col("A").rolling_median(3)
  ]
)
# =>
# shape: (6, 1)
# ┌──────┐
# │ A    │
# │ ---  │
# │ f64  │
# ╞══════╡
# │ null │
# │ null │
# │ 2.0  │
# │ 3.0  │
# │ 4.0  │
# │ 6.0  │
# └──────┘

Parameters:

  • window_size (Integer) —

    The length of the window. Can be a fixed integer size, or a dynamic temporal size indicated by a timedelta or the following string language:

    • 1ns (1 nanosecond)
    • 1us (1 microsecond)
    • 1ms (1 millisecond)
    • 1s (1 second)
    • 1m (1 minute)
    • 1h (1 hour)
    • 1d (1 day)
    • 1w (1 week)
    • 1mo (1 calendar month)
    • 1y (1 calendar year)
    • 1i (1 index count)

    If a timedelta or the dynamic string language is used, the by and closed arguments must also be set.

  • weights (Array) (defaults to: nil) —

    An optional slice with the same length as the window that will be multiplied elementwise with the values in the window.

  • min_periods (Integer) (defaults to: nil) —

    The number of values in the window that should be non-null before computing a result. If None, it will be set equal to window size.

  • center (Boolean) (defaults to: false) —

    Set the labels at the center of the window

Returns:



5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
 
# File 'lib/polars/expr.rb', line 5439

def rolling_median(
  window_size,
  weights: nil,
  min_periods: nil,
  center: false
)
  _from_rbexpr(
    _rbexpr.rolling_median(
      window_size, weights, min_periods, center
    )
  )
end

#rolling_median_by(by, window_size, min_periods: 1, closed: "right", warn_if_unsorted: nil) ⇒ Expr

Note:

If you want to compute multiple aggregation statistics over the same dynamic window, consider using rolling - this method can cache the window size computation.

Compute a rolling median based on another column.

Examples:

Create a DataFrame with a datetime column and a row number column

start = DateTime.new(2001, 1, 1)
stop = DateTime.new(2001, 1, 2)
df_temporal = Polars::DataFrame.new(
  {"date" => Polars.datetime_range(start, stop, "1h", eager: true)}
).with_row_index
# =>
# shape: (25, 2)
# ┌───────┬─────────────────────┐
# │ index ┆ date                │
# │ ---   ┆ ---                 │
# │ u32   ┆ datetime[ns]        │
# ╞═══════╪═════════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 │
# │ 1     ┆ 2001-01-01 01:00:00 │
# │ 2     ┆ 2001-01-01 02:00:00 │
# │ 3     ┆ 2001-01-01 03:00:00 │
# │ 4     ┆ 2001-01-01 04:00:00 │
# │ …     ┆ …                   │
# │ 20    ┆ 2001-01-01 20:00:00 │
# │ 21    ┆ 2001-01-01 21:00:00 │
# │ 22    ┆ 2001-01-01 22:00:00 │
# │ 23    ┆ 2001-01-01 23:00:00 │
# │ 24    ┆ 2001-01-02 00:00:00 │
# └───────┴─────────────────────┘

Compute the rolling median with the temporal windows closed on the right:

df_temporal.with_columns(
  rolling_row_median: Polars.col("index").rolling_median_by(
    "date", "2h"
  )
)
# =>
# shape: (25, 3)
# ┌───────┬─────────────────────┬────────────────────┐
# │ index ┆ date                ┆ rolling_row_median │
# │ ---   ┆ ---                 ┆ ---                │
# │ u32   ┆ datetime[ns]        ┆ f64                │
# ╞═══════╪═════════════════════╪════════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 ┆ 0.0                │
# │ 1     ┆ 2001-01-01 01:00:00 ┆ 0.5                │
# │ 2     ┆ 2001-01-01 02:00:00 ┆ 1.5                │
# │ 3     ┆ 2001-01-01 03:00:00 ┆ 2.5                │
# │ 4     ┆ 2001-01-01 04:00:00 ┆ 3.5                │
# │ …     ┆ …                   ┆ …                  │
# │ 20    ┆ 2001-01-01 20:00:00 ┆ 19.5               │
# │ 21    ┆ 2001-01-01 21:00:00 ┆ 20.5               │
# │ 22    ┆ 2001-01-01 22:00:00 ┆ 21.5               │
# │ 23    ┆ 2001-01-01 23:00:00 ┆ 22.5               │
# │ 24    ┆ 2001-01-02 00:00:00 ┆ 23.5               │
# └───────┴─────────────────────┴────────────────────┘

Parameters:

  • by (String) —

    This column must be of dtype Datetime or Date.

  • window_size (String) —

    The length of the window. Can be a dynamic temporal size indicated by a timedelta or the following string language:

    • 1ns (1 nanosecond)
    • 1us (1 microsecond)
    • 1ms (1 millisecond)
    • 1s (1 second)
    • 1m (1 minute)
    • 1h (1 hour)
    • 1d (1 calendar day)
    • 1w (1 calendar week)
    • 1mo (1 calendar month)
    • 1q (1 calendar quarter)
    • 1y (1 calendar year)

    By "calendar day", we mean the corresponding time on the next day (which may not be 24 hours, due to daylight savings). Similarly for "calendar week", "calendar month", "calendar quarter", and "calendar year".

  • min_periods (Integer) (defaults to: 1) —

    The number of values in the window that should be non-null before computing a result.

  • closed ('left', 'right', 'both', 'none') (defaults to: "right") —

    Define which sides of the temporal interval are closed (inclusive), defaults to 'right'.

  • warn_if_unsorted (Boolean) (defaults to: nil) —

    Warn if data is not known to be sorted by by column.

Returns:



4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
 
# File 'lib/polars/expr.rb', line 4776

def rolling_median_by(
  by,
  window_size,
  min_periods: 1,
  closed: "right",
  warn_if_unsorted: nil
)
  window_size = _prepare_rolling_by_window_args(window_size)
  by = Utils.parse_into_expression(by)
  _from_rbexpr(
    _rbexpr.rolling_median_by(by, window_size, min_periods, closed)
  )
end

#rolling_min(window_size, weights: nil, min_periods: nil, center: false) ⇒ Expr

Note:

This functionality is experimental and may change without it being considered a breaking change.

Note:

If you want to compute multiple aggregation statistics over the same dynamic window, consider using group_by_rolling this method can cache the window size computation.

Apply a rolling min (moving min) over the values in this array.

A window of length window_size will traverse the array. The values that fill this window will (optionally) be multiplied with the weights given by the weight vector. The resulting values will be aggregated to their sum.

Examples:

df = Polars::DataFrame.new({"A" => [1.0, 2.0, 3.0, 4.0, 5.0, 6.0]})
df.select(
  [
    Polars.col("A").rolling_min(2)
  ]
)
# =>
# shape: (6, 1)
# ┌──────┐
# │ A    │
# │ ---  │
# │ f64  │
# ╞══════╡
# │ null │
# │ 1.0  │
# │ 2.0  │
# │ 3.0  │
# │ 4.0  │
# │ 5.0  │
# └──────┘

Parameters:

  • window_size (Integer) —

    The length of the window. Can be a fixed integer size, or a dynamic temporal size indicated by a timedelta or the following string language:

    • 1ns (1 nanosecond)
    • 1us (1 microsecond)
    • 1ms (1 millisecond)
    • 1s (1 second)
    • 1m (1 minute)
    • 1h (1 hour)
    • 1d (1 day)
    • 1w (1 week)
    • 1mo (1 calendar month)
    • 1y (1 calendar year)
    • 1i (1 index count)

    If a timedelta or the dynamic string language is used, the by and closed arguments must also be set.

  • weights (Array) (defaults to: nil) —

    An optional slice with the same length as the window that will be multiplied elementwise with the values in the window.

  • min_periods (Integer) (defaults to: nil) —

    The number of values in the window that should be non-null before computing a result. If None, it will be set equal to window size.

  • center (Boolean) (defaults to: false) —

    Set the labels at the center of the window

Returns:



4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
 
# File 'lib/polars/expr.rb', line 4973

def rolling_min(
  window_size,
  weights: nil,
  min_periods: nil,
  center: false
)
  _from_rbexpr(
    _rbexpr.rolling_min(
      window_size, weights, min_periods, center
    )
  )
end

#rolling_min_by(by, window_size, min_periods: 1, closed: "right", warn_if_unsorted: nil) ⇒ Expr

Note:

If you want to compute multiple aggregation statistics over the same dynamic window, consider using rolling - this method can cache the window size computation.

Apply a rolling min based on another column.

Examples:

Create a DataFrame with a datetime column and a row number column

start = DateTime.new(2001, 1, 1)
stop = DateTime.new(2001, 1, 2)
df_temporal = Polars::DataFrame.new(
  {"date" => Polars.datetime_range(start, stop, "1h", eager: true)}
).with_row_index
# =>
# shape: (25, 2)
# ┌───────┬─────────────────────┐
# │ index ┆ date                │
# │ ---   ┆ ---                 │
# │ u32   ┆ datetime[ns]        │
# ╞═══════╪═════════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 │
# │ 1     ┆ 2001-01-01 01:00:00 │
# │ 2     ┆ 2001-01-01 02:00:00 │
# │ 3     ┆ 2001-01-01 03:00:00 │
# │ 4     ┆ 2001-01-01 04:00:00 │
# │ …     ┆ …                   │
# │ 20    ┆ 2001-01-01 20:00:00 │
# │ 21    ┆ 2001-01-01 21:00:00 │
# │ 22    ┆ 2001-01-01 22:00:00 │
# │ 23    ┆ 2001-01-01 23:00:00 │
# │ 24    ┆ 2001-01-02 00:00:00 │
# └───────┴─────────────────────┘

Compute the rolling min with the temporal windows closed on the right (default)

df_temporal.with_columns(
  rolling_row_min: Polars.col("index").rolling_min_by("date", "2h")
)
# =>
# shape: (25, 3)
# ┌───────┬─────────────────────┬─────────────────┐
# │ index ┆ date                ┆ rolling_row_min │
# │ ---   ┆ ---                 ┆ ---             │
# │ u32   ┆ datetime[ns]        ┆ u32             │
# ╞═══════╪═════════════════════╪═════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 ┆ 0               │
# │ 1     ┆ 2001-01-01 01:00:00 ┆ 0               │
# │ 2     ┆ 2001-01-01 02:00:00 ┆ 1               │
# │ 3     ┆ 2001-01-01 03:00:00 ┆ 2               │
# │ 4     ┆ 2001-01-01 04:00:00 ┆ 3               │
# │ …     ┆ …                   ┆ …               │
# │ 20    ┆ 2001-01-01 20:00:00 ┆ 19              │
# │ 21    ┆ 2001-01-01 21:00:00 ┆ 20              │
# │ 22    ┆ 2001-01-01 22:00:00 ┆ 21              │
# │ 23    ┆ 2001-01-01 23:00:00 ┆ 22              │
# │ 24    ┆ 2001-01-02 00:00:00 ┆ 23              │
# └───────┴─────────────────────┴─────────────────┘

Parameters:

  • by (String) —

    This column must be of dtype Datetime or Date.

  • window_size (String) —

    The length of the window. Can be a dynamic temporal size indicated by a timedelta or the following string language:

    • 1ns (1 nanosecond)
    • 1us (1 microsecond)
    • 1ms (1 millisecond)
    • 1s (1 second)
    • 1m (1 minute)
    • 1h (1 hour)
    • 1d (1 calendar day)
    • 1w (1 calendar week)
    • 1mo (1 calendar month)
    • 1q (1 calendar quarter)
    • 1y (1 calendar year)

    By "calendar day", we mean the corresponding time on the next day (which may not be 24 hours, due to daylight savings). Similarly for "calendar week", "calendar month", "calendar quarter", and "calendar year".

  • min_periods (Integer) (defaults to: 1) —

    The number of values in the window that should be non-null before computing a result.

  • closed ('left', 'right', 'both', 'none') (defaults to: "right") —

    Define which sides of the temporal interval are closed (inclusive), defaults to 'right'.

  • warn_if_unsorted (Boolean) (defaults to: nil) —

    Warn if data is not known to be sorted by by column.

Returns:



4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
 
# File 'lib/polars/expr.rb', line 4001

def rolling_min_by(
  by,
  window_size,
  min_periods: 1,
  closed: "right",
  warn_if_unsorted: nil
)
  window_size = _prepare_rolling_by_window_args(window_size)
  by = Utils.parse_into_expression(by)
  _from_rbexpr(
    _rbexpr.rolling_min_by(by, window_size, min_periods, closed)
  )
end

#rolling_quantile(quantile, interpolation: "nearest", window_size: 2, weights: nil, min_periods: nil, center: false) ⇒ Expr

Note:

This functionality is experimental and may change without it being considered a breaking change.

Note:

If you want to compute multiple aggregation statistics over the same dynamic window, consider using group_by_rolling this method can cache the window size computation.

Compute a rolling quantile.

Examples:

df = Polars::DataFrame.new({"A" => [1.0, 2.0, 3.0, 4.0, 6.0, 8.0]})
df.select(
  [
    Polars.col("A").rolling_quantile(0.33, window_size: 3)
  ]
)
# =>
# shape: (6, 1)
# ┌──────┐
# │ A    │
# │ ---  │
# │ f64  │
# ╞══════╡
# │ null │
# │ null │
# │ 1.0  │
# │ 2.0  │
# │ 3.0  │
# │ 4.0  │
# └──────┘

Parameters:

  • quantile (Float) —

    Quantile between 0.0 and 1.0.

  • interpolation ("nearest", "higher", "lower", "midpoint", "linear") (defaults to: "nearest") —

    Interpolation method.

  • window_size (Integer) (defaults to: 2) —

    The length of the window. Can be a fixed integer size, or a dynamic temporal size indicated by a timedelta or the following string language:

    • 1ns (1 nanosecond)
    • 1us (1 microsecond)
    • 1ms (1 millisecond)
    • 1s (1 second)
    • 1m (1 minute)
    • 1h (1 hour)
    • 1d (1 day)
    • 1w (1 week)
    • 1mo (1 calendar month)
    • 1y (1 calendar year)
    • 1i (1 index count)

    If a timedelta or the dynamic string language is used, the by and closed arguments must also be set.

  • weights (Array) (defaults to: nil) —

    An optional slice with the same length as the window that will be multiplied elementwise with the values in the window.

  • min_periods (Integer) (defaults to: nil) —

    The number of values in the window that should be non-null before computing a result. If None, it will be set equal to window size.

  • center (Boolean) (defaults to: false) —

    Set the labels at the center of the window

Returns:



5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
 
# File 'lib/polars/expr.rb', line 5517

def rolling_quantile(
  quantile,
  interpolation: "nearest",
  window_size: 2,
  weights: nil,
  min_periods: nil,
  center: false
)
  _from_rbexpr(
    _rbexpr.rolling_quantile(
      quantile, interpolation, window_size, weights, min_periods, center
    )
  )
end

#rolling_quantile_by(by, window_size, quantile:, interpolation: "nearest", min_periods: 1, closed: "right", warn_if_unsorted: nil) ⇒ Expr

Note:

If you want to compute multiple aggregation statistics over the same dynamic window, consider using rolling - this method can cache the window size computation.

Compute a rolling quantile based on another column.

Examples:

Create a DataFrame with a datetime column and a row number column

start = DateTime.new(2001, 1, 1)
stop = DateTime.new(2001, 1, 2)
df_temporal = Polars::DataFrame.new(
    {"date" => Polars.datetime_range(start, stop, "1h", eager: true)}
).with_row_index
# =>
# shape: (25, 2)
# ┌───────┬─────────────────────┐
# │ index ┆ date                │
# │ ---   ┆ ---                 │
# │ u32   ┆ datetime[ns]        │
# ╞═══════╪═════════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 │
# │ 1     ┆ 2001-01-01 01:00:00 │
# │ 2     ┆ 2001-01-01 02:00:00 │
# │ 3     ┆ 2001-01-01 03:00:00 │
# │ 4     ┆ 2001-01-01 04:00:00 │
# │ …     ┆ …                   │
# │ 20    ┆ 2001-01-01 20:00:00 │
# │ 21    ┆ 2001-01-01 21:00:00 │
# │ 22    ┆ 2001-01-01 22:00:00 │
# │ 23    ┆ 2001-01-01 23:00:00 │
# │ 24    ┆ 2001-01-02 00:00:00 │
# └───────┴─────────────────────┘

Compute the rolling quantile with the temporal windows closed on the right:

df_temporal.with_columns(
  rolling_row_quantile: Polars.col("index").rolling_quantile_by(
    "date", "2h", quantile: 0.3
  )
)
# =>
# shape: (25, 3)
# ┌───────┬─────────────────────┬──────────────────────┐
# │ index ┆ date                ┆ rolling_row_quantile │
# │ ---   ┆ ---                 ┆ ---                  │
# │ u32   ┆ datetime[ns]        ┆ f64                  │
# ╞═══════╪═════════════════════╪══════════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 ┆ 0.0                  │
# │ 1     ┆ 2001-01-01 01:00:00 ┆ 0.0                  │
# │ 2     ┆ 2001-01-01 02:00:00 ┆ 1.0                  │
# │ 3     ┆ 2001-01-01 03:00:00 ┆ 2.0                  │
# │ 4     ┆ 2001-01-01 04:00:00 ┆ 3.0                  │
# │ …     ┆ …                   ┆ …                    │
# │ 20    ┆ 2001-01-01 20:00:00 ┆ 19.0                 │
# │ 21    ┆ 2001-01-01 21:00:00 ┆ 20.0                 │
# │ 22    ┆ 2001-01-01 22:00:00 ┆ 21.0                 │
# │ 23    ┆ 2001-01-01 23:00:00 ┆ 22.0                 │
# │ 24    ┆ 2001-01-02 00:00:00 ┆ 23.0                 │
# └───────┴─────────────────────┴──────────────────────┘

Parameters:

  • by (String) —

    This column must be of dtype Datetime or Date.

  • quantile (Float) —

    Quantile between 0.0 and 1.0.

  • interpolation ('nearest', 'higher', 'lower', 'midpoint', 'linear') (defaults to: "nearest") —

    Interpolation method.

  • window_size (String) —

    The length of the window. Can be a dynamic temporal size indicated by a timedelta or the following string language:

    • 1ns (1 nanosecond)
    • 1us (1 microsecond)
    • 1ms (1 millisecond)
    • 1s (1 second)
    • 1m (1 minute)
    • 1h (1 hour)
    • 1d (1 calendar day)
    • 1w (1 calendar week)
    • 1mo (1 calendar month)
    • 1q (1 calendar quarter)
    • 1y (1 calendar year)

    By "calendar day", we mean the corresponding time on the next day (which may not be 24 hours, due to daylight savings). Similarly for "calendar week", "calendar month", "calendar quarter", and "calendar year".

  • min_periods (Integer) (defaults to: 1) —

    The number of values in the window that should be non-null before computing a result.

  • closed ('left', 'right', 'both', 'none') (defaults to: "right") —

    Define which sides of the temporal interval are closed (inclusive), defaults to 'right'.

  • warn_if_unsorted (Boolean) (defaults to: nil) —

    Warn if data is not known to be sorted by by column.

Returns:



4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
 
# File 'lib/polars/expr.rb', line 4885

def rolling_quantile_by(
  by,
  window_size,
  quantile:,
  interpolation: "nearest",
  min_periods: 1,
  closed: "right",
  warn_if_unsorted: nil
)
  window_size = _prepare_rolling_by_window_args(window_size)
  by = Utils.parse_into_expression(by)
  _from_rbexpr(
    _rbexpr.rolling_quantile_by(
      by,
      quantile,
      interpolation,
      window_size,
      min_periods,
      closed,
    )
  )
end

#rolling_skew(window_size, bias: true) ⇒ Expr

Compute a rolling skew.

Parameters:

  • window_size (Integer) —

    Integer size of the rolling window.

  • bias (Boolean) (defaults to: true) —

    If false, the calculations are corrected for statistical bias.

Returns:



5604
5605
5606
 
# File 'lib/polars/expr.rb', line 5604

def rolling_skew(window_size, bias: true)
  _from_rbexpr(_rbexpr.rolling_skew(window_size, bias))
end

#rolling_std(window_size, weights: nil, min_periods: nil, center: false, ddof: 1) ⇒ Expr

Note:

This functionality is experimental and may change without it being considered a breaking change.

Note:

If you want to compute multiple aggregation statistics over the same dynamic window, consider using group_by_rolling this method can cache the window size computation.

Compute a rolling standard deviation.

A window of length window_size will traverse the array. The values that fill this window will (optionally) be multiplied with the weights given by the weight vector. The resulting values will be aggregated to their sum.

Examples:

df = Polars::DataFrame.new({"A" => [1.0, 2.0, 3.0, 4.0, 6.0, 8.0]})
df.select(
  [
    Polars.col("A").rolling_std(3)
  ]
)
# =>
# shape: (6, 1)
# ┌──────────┐
# │ A        │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ null     │
# │ null     │
# │ 1.0      │
# │ 1.0      │
# │ 1.527525 │
# │ 2.0      │
# └──────────┘

Parameters:

  • window_size (Integer) —

    The length of the window. Can be a fixed integer size, or a dynamic temporal size indicated by a timedelta or the following string language:

    • 1ns (1 nanosecond)
    • 1us (1 microsecond)
    • 1ms (1 millisecond)
    • 1s (1 second)
    • 1m (1 minute)
    • 1h (1 hour)
    • 1d (1 day)
    • 1w (1 week)
    • 1mo (1 calendar month)
    • 1y (1 calendar year)
    • 1i (1 index count)

    If a timedelta or the dynamic string language is used, the by and closed arguments must also be set.

  • weights (Array) (defaults to: nil) —

    An optional slice with the same length as the window that will be multiplied elementwise with the values in the window.

  • min_periods (Integer) (defaults to: nil) —

    The number of values in the window that should be non-null before computing a result. If None, it will be set equal to window size.

  • center (Boolean) (defaults to: false) —

    Set the labels at the center of the window

Returns:



5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
 
# File 'lib/polars/expr.rb', line 5285

def rolling_std(
  window_size,
  weights: nil,
  min_periods: nil,
  center: false,
  ddof: 1
)
  _from_rbexpr(
    _rbexpr.rolling_std(
      window_size, weights, min_periods, center, ddof
    )
  )
end

#rolling_std_by(by, window_size, min_periods: 1, closed: "right", ddof: 1, warn_if_unsorted: nil) ⇒ Expr

Note:

If you want to compute multiple aggregation statistics over the same dynamic window, consider using rolling - this method can cache the window size computation.

Compute a rolling standard deviation based on another column.

Examples:

Create a DataFrame with a datetime column and a row number column

start = DateTime.new(2001, 1, 1)
stop = DateTime.new(2001, 1, 2)
df_temporal = Polars::DataFrame.new(
    {"date" => Polars.datetime_range(start, stop, "1h", eager: true)}
).with_row_index
# =>
# shape: (25, 2)
# ┌───────┬─────────────────────┐
# │ index ┆ date                │
# │ ---   ┆ ---                 │
# │ u32   ┆ datetime[ns]        │
# ╞═══════╪═════════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 │
# │ 1     ┆ 2001-01-01 01:00:00 │
# │ 2     ┆ 2001-01-01 02:00:00 │
# │ 3     ┆ 2001-01-01 03:00:00 │
# │ 4     ┆ 2001-01-01 04:00:00 │
# │ …     ┆ …                   │
# │ 20    ┆ 2001-01-01 20:00:00 │
# │ 21    ┆ 2001-01-01 21:00:00 │
# │ 22    ┆ 2001-01-01 22:00:00 │
# │ 23    ┆ 2001-01-01 23:00:00 │
# │ 24    ┆ 2001-01-02 00:00:00 │
# └───────┴─────────────────────┘

Compute the rolling std with the temporal windows closed on the right (default)

df_temporal.with_columns(
  rolling_row_std: Polars.col("index").rolling_std_by("date", "2h")
)
# =>
# shape: (25, 3)
# ┌───────┬─────────────────────┬─────────────────┐
# │ index ┆ date                ┆ rolling_row_std │
# │ ---   ┆ ---                 ┆ ---             │
# │ u32   ┆ datetime[ns]        ┆ f64             │
# ╞═══════╪═════════════════════╪═════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 ┆ null            │
# │ 1     ┆ 2001-01-01 01:00:00 ┆ 0.707107        │
# │ 2     ┆ 2001-01-01 02:00:00 ┆ 0.707107        │
# │ 3     ┆ 2001-01-01 03:00:00 ┆ 0.707107        │
# │ 4     ┆ 2001-01-01 04:00:00 ┆ 0.707107        │
# │ …     ┆ …                   ┆ …               │
# │ 20    ┆ 2001-01-01 20:00:00 ┆ 0.707107        │
# │ 21    ┆ 2001-01-01 21:00:00 ┆ 0.707107        │
# │ 22    ┆ 2001-01-01 22:00:00 ┆ 0.707107        │
# │ 23    ┆ 2001-01-01 23:00:00 ┆ 0.707107        │
# │ 24    ┆ 2001-01-02 00:00:00 ┆ 0.707107        │
# └───────┴─────────────────────┴─────────────────┘

Compute the rolling std with the closure of windows on both sides

df_temporal.with_columns(
  rolling_row_std: Polars.col("index").rolling_std_by(
    "date", "2h", closed: "both"
  )
)
# =>
# shape: (25, 3)
# ┌───────┬─────────────────────┬─────────────────┐
# │ index ┆ date                ┆ rolling_row_std │
# │ ---   ┆ ---                 ┆ ---             │
# │ u32   ┆ datetime[ns]        ┆ f64             │
# ╞═══════╪═════════════════════╪═════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 ┆ null            │
# │ 1     ┆ 2001-01-01 01:00:00 ┆ 0.707107        │
# │ 2     ┆ 2001-01-01 02:00:00 ┆ 1.0             │
# │ 3     ┆ 2001-01-01 03:00:00 ┆ 1.0             │
# │ 4     ┆ 2001-01-01 04:00:00 ┆ 1.0             │
# │ …     ┆ …                   ┆ …               │
# │ 20    ┆ 2001-01-01 20:00:00 ┆ 1.0             │
# │ 21    ┆ 2001-01-01 21:00:00 ┆ 1.0             │
# │ 22    ┆ 2001-01-01 22:00:00 ┆ 1.0             │
# │ 23    ┆ 2001-01-01 23:00:00 ┆ 1.0             │
# │ 24    ┆ 2001-01-02 00:00:00 ┆ 1.0             │
# └───────┴─────────────────────┴─────────────────┘

Parameters:

  • by (String) —

    This column must be of dtype Datetime or Date.

  • window_size (String) —

    The length of the window. Can be a dynamic temporal size indicated by a timedelta or the following string language:

    • 1ns (1 nanosecond)
    • 1us (1 microsecond)
    • 1ms (1 millisecond)
    • 1s (1 second)
    • 1m (1 minute)
    • 1h (1 hour)
    • 1d (1 calendar day)
    • 1w (1 calendar week)
    • 1mo (1 calendar month)
    • 1q (1 calendar quarter)
    • 1y (1 calendar year)

    By "calendar day", we mean the corresponding time on the next day (which may not be 24 hours, due to daylight savings). Similarly for "calendar week", "calendar month", "calendar quarter", and "calendar year".

  • min_periods (Integer) (defaults to: 1) —

    The number of values in the window that should be non-null before computing a result.

  • closed ('left', 'right', 'both', 'none') (defaults to: "right") —

    Define which sides of the temporal interval are closed (inclusive), defaults to 'right'.

  • ddof (Integer) (defaults to: 1) —

    "Delta Degrees of Freedom": The divisor for a length N window is N - ddof

  • warn_if_unsorted (Boolean) (defaults to: nil) —

    Warn if data is not known to be sorted by by column.

Returns:



4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
 
# File 'lib/polars/expr.rb', line 4526

def rolling_std_by(
  by,
  window_size,
  min_periods: 1,
  closed: "right",
  ddof: 1,
  warn_if_unsorted: nil
)
  window_size = _prepare_rolling_by_window_args(window_size)
  by = Utils.parse_into_expression(by)
  _from_rbexpr(
    _rbexpr.rolling_std_by(
      by,
      window_size,
      min_periods,
      closed,
      ddof
    )
  )
end

#rolling_sum(window_size, weights: nil, min_periods: nil, center: false) ⇒ Expr

Note:

This functionality is experimental and may change without it being considered a breaking change.

Note:

If you want to compute multiple aggregation statistics over the same dynamic window, consider using group_by_rolling this method can cache the window size computation.

Apply a rolling sum (moving sum) over the values in this array.

A window of length window_size will traverse the array. The values that fill this window will (optionally) be multiplied with the weights given by the weight vector. The resulting values will be aggregated to their sum.

Examples:

df = Polars::DataFrame.new({"A" => [1.0, 2.0, 3.0, 4.0, 5.0, 6.0]})
df.select(
  [
    Polars.col("A").rolling_sum(2)
  ]
)
# =>
# shape: (6, 1)
# ┌──────┐
# │ A    │
# │ ---  │
# │ f64  │
# ╞══════╡
# │ null │
# │ 3.0  │
# │ 5.0  │
# │ 7.0  │
# │ 9.0  │
# │ 11.0 │
# └──────┘

Parameters:

  • window_size (Integer) —

    The length of the window. Can be a fixed integer size, or a dynamic temporal size indicated by a timedelta or the following string language:

    • 1ns (1 nanosecond)
    • 1us (1 microsecond)
    • 1ms (1 millisecond)
    • 1s (1 second)
    • 1m (1 minute)
    • 1h (1 hour)
    • 1d (1 day)
    • 1w (1 week)
    • 1mo (1 calendar month)
    • 1y (1 calendar year)
    • 1i (1 index count)

    If a timedelta or the dynamic string language is used, the by and closed arguments must also be set.

  • weights (Array) (defaults to: nil) —

    An optional slice with the same length as the window that will be multiplied elementwise with the values in the window.

  • min_periods (Integer) (defaults to: nil) —

    The number of values in the window that should be non-null before computing a result. If None, it will be set equal to window size.

  • center (Boolean) (defaults to: false) —

    Set the labels at the center of the window

Returns:



5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
 
# File 'lib/polars/expr.rb', line 5207

def rolling_sum(
  window_size,
  weights: nil,
  min_periods: nil,
  center: false
)
  _from_rbexpr(
    _rbexpr.rolling_sum(
      window_size, weights, min_periods, center
    )
  )
end

#rolling_sum_by(by, window_size, min_periods: 1, closed: "right", warn_if_unsorted: nil) ⇒ Expr

Note:

If you want to compute multiple aggregation statistics over the same dynamic window, consider using rolling - this method can cache the window size computation.

Apply a rolling sum based on another column.

Examples:

Create a DataFrame with a datetime column and a row number column

start = DateTime.new(2001, 1, 1)
stop = DateTime.new(2001, 1, 2)
df_temporal = Polars::DataFrame.new(
    {"date" => Polars.datetime_range(start, stop, "1h", eager: true)}
).with_row_index
# =>
# shape: (25, 2)
# ┌───────┬─────────────────────┐
# │ index ┆ date                │
# │ ---   ┆ ---                 │
# │ u32   ┆ datetime[ns]        │
# ╞═══════╪═════════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 │
# │ 1     ┆ 2001-01-01 01:00:00 │
# │ 2     ┆ 2001-01-01 02:00:00 │
# │ 3     ┆ 2001-01-01 03:00:00 │
# │ 4     ┆ 2001-01-01 04:00:00 │
# │ …     ┆ …                   │
# │ 20    ┆ 2001-01-01 20:00:00 │
# │ 21    ┆ 2001-01-01 21:00:00 │
# │ 22    ┆ 2001-01-01 22:00:00 │
# │ 23    ┆ 2001-01-01 23:00:00 │
# │ 24    ┆ 2001-01-02 00:00:00 │
# └───────┴─────────────────────┘

Compute the rolling sum with the temporal windows closed on the right (default)

df_temporal.with_columns(
  rolling_row_sum: Polars.col("index").rolling_sum_by("date", "2h")
)
# =>
# shape: (25, 3)
# ┌───────┬─────────────────────┬─────────────────┐
# │ index ┆ date                ┆ rolling_row_sum │
# │ ---   ┆ ---                 ┆ ---             │
# │ u32   ┆ datetime[ns]        ┆ u32             │
# ╞═══════╪═════════════════════╪═════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 ┆ 0               │
# │ 1     ┆ 2001-01-01 01:00:00 ┆ 1               │
# │ 2     ┆ 2001-01-01 02:00:00 ┆ 3               │
# │ 3     ┆ 2001-01-01 03:00:00 ┆ 5               │
# │ 4     ┆ 2001-01-01 04:00:00 ┆ 7               │
# │ …     ┆ …                   ┆ …               │
# │ 20    ┆ 2001-01-01 20:00:00 ┆ 39              │
# │ 21    ┆ 2001-01-01 21:00:00 ┆ 41              │
# │ 22    ┆ 2001-01-01 22:00:00 ┆ 43              │
# │ 23    ┆ 2001-01-01 23:00:00 ┆ 45              │
# │ 24    ┆ 2001-01-02 00:00:00 ┆ 47              │
# └───────┴─────────────────────┴─────────────────┘

Compute the rolling sum with the closure of windows on both sides

df_temporal.with_columns(
  rolling_row_sum: Polars.col("index").rolling_sum_by(
    "date", "2h", closed: "both"
  )
)
# =>
# shape: (25, 3)
# ┌───────┬─────────────────────┬─────────────────┐
# │ index ┆ date                ┆ rolling_row_sum │
# │ ---   ┆ ---                 ┆ ---             │
# │ u32   ┆ datetime[ns]        ┆ u32             │
# ╞═══════╪═════════════════════╪═════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 ┆ 0               │
# │ 1     ┆ 2001-01-01 01:00:00 ┆ 1               │
# │ 2     ┆ 2001-01-01 02:00:00 ┆ 3               │
# │ 3     ┆ 2001-01-01 03:00:00 ┆ 6               │
# │ 4     ┆ 2001-01-01 04:00:00 ┆ 9               │
# │ …     ┆ …                   ┆ …               │
# │ 20    ┆ 2001-01-01 20:00:00 ┆ 57              │
# │ 21    ┆ 2001-01-01 21:00:00 ┆ 60              │
# │ 22    ┆ 2001-01-01 22:00:00 ┆ 63              │
# │ 23    ┆ 2001-01-01 23:00:00 ┆ 66              │
# │ 24    ┆ 2001-01-02 00:00:00 ┆ 69              │
# └───────┴─────────────────────┴─────────────────┘

Parameters:

  • by (String) —

    This column must of dtype {Date, Datetime}

  • window_size (String) —

    The length of the window. Can be a dynamic temporal size indicated by a timedelta or the following string language:

    • 1ns (1 nanosecond)
    • 1us (1 microsecond)
    • 1ms (1 millisecond)
    • 1s (1 second)
    • 1m (1 minute)
    • 1h (1 hour)
    • 1d (1 calendar day)
    • 1w (1 calendar week)
    • 1mo (1 calendar month)
    • 1q (1 calendar quarter)
    • 1y (1 calendar year)

    By "calendar day", we mean the corresponding time on the next day (which may not be 24 hours, due to daylight savings). Similarly for "calendar week", "calendar month", "calendar quarter", and "calendar year".

  • min_periods (Integer) (defaults to: 1) —

    The number of values in the window that should be non-null before computing a result.

  • closed ('left', 'right', 'both', 'none') (defaults to: "right") —

    Define which sides of the temporal interval are closed (inclusive), defaults to 'right'.

  • warn_if_unsorted (Boolean) (defaults to: nil) —

    Warn if data is not known to be sorted by by column.

Returns:



4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
 
# File 'lib/polars/expr.rb', line 4395

def rolling_sum_by(
  by,
  window_size,
  min_periods: 1,
  closed: "right",
  warn_if_unsorted: nil
)
  window_size = _prepare_rolling_by_window_args(window_size)
  by = Utils.parse_into_expression(by)
  _from_rbexpr(
    _rbexpr.rolling_sum_by(by, window_size, min_periods, closed)
  )
end

#rolling_var(window_size, weights: nil, min_periods: nil, center: false, ddof: 1) ⇒ Expr

Note:

This functionality is experimental and may change without it being considered a breaking change.

Note:

If you want to compute multiple aggregation statistics over the same dynamic window, consider using group_by_rolling this method can cache the window size computation.

Compute a rolling variance.

A window of length window_size will traverse the array. The values that fill this window will (optionally) be multiplied with the weights given by the weight vector. The resulting values will be aggregated to their sum.

Examples:

df = Polars::DataFrame.new({"A" => [1.0, 2.0, 3.0, 4.0, 6.0, 8.0]})
df.select(
  [
    Polars.col("A").rolling_var(3)
  ]
)
# =>
# shape: (6, 1)
# ┌──────────┐
# │ A        │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ null     │
# │ null     │
# │ 1.0      │
# │ 1.0      │
# │ 2.333333 │
# │ 4.0      │
# └──────────┘

Parameters:

  • window_size (Integer) —

    The length of the window. Can be a fixed integer size, or a dynamic temporal size indicated by a timedelta or the following string language:

    • 1ns (1 nanosecond)
    • 1us (1 microsecond)
    • 1ms (1 millisecond)
    • 1s (1 second)
    • 1m (1 minute)
    • 1h (1 hour)
    • 1d (1 day)
    • 1w (1 week)
    • 1mo (1 calendar month)
    • 1y (1 calendar year)
    • 1i (1 index count)

    If a timedelta or the dynamic string language is used, the by and closed arguments must also be set.

  • weights (Array) (defaults to: nil) —

    An optional slice with the same length as the window that will be multiplied elementwise with the values in the window.

  • min_periods (Integer) (defaults to: nil) —

    The number of values in the window that should be non-null before computing a result. If None, it will be set equal to window size.

  • center (Boolean) (defaults to: false) —

    Set the labels at the center of the window

Returns:



5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
 
# File 'lib/polars/expr.rb', line 5364

def rolling_var(
  window_size,
  weights: nil,
  min_periods: nil,
  center: false,
  ddof: 1
)
  _from_rbexpr(
    _rbexpr.rolling_var(
      window_size, weights, min_periods, center, ddof
    )
  )
end

#rolling_var_by(by, window_size, min_periods: 1, closed: "right", ddof: 1, warn_if_unsorted: nil) ⇒ Expr

Note:

If you want to compute multiple aggregation statistics over the same dynamic window, consider using rolling - this method can cache the window size computation.

Compute a rolling variance based on another column.

Examples:

Create a DataFrame with a datetime column and a row number column

start = DateTime.new(2001, 1, 1)
stop = DateTime.new(2001, 1, 2)
df_temporal = Polars::DataFrame.new(
    {"date" => Polars.datetime_range(start, stop, "1h", eager: true)}
).with_row_index
# =>
# shape: (25, 2)
# ┌───────┬─────────────────────┐
# │ index ┆ date                │
# │ ---   ┆ ---                 │
# │ u32   ┆ datetime[ns]        │
# ╞═══════╪═════════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 │
# │ 1     ┆ 2001-01-01 01:00:00 │
# │ 2     ┆ 2001-01-01 02:00:00 │
# │ 3     ┆ 2001-01-01 03:00:00 │
# │ 4     ┆ 2001-01-01 04:00:00 │
# │ …     ┆ …                   │
# │ 20    ┆ 2001-01-01 20:00:00 │
# │ 21    ┆ 2001-01-01 21:00:00 │
# │ 22    ┆ 2001-01-01 22:00:00 │
# │ 23    ┆ 2001-01-01 23:00:00 │
# │ 24    ┆ 2001-01-02 00:00:00 │
# └───────┴─────────────────────┘

Compute the rolling var with the temporal windows closed on the right (default)

df_temporal.with_columns(
  rolling_row_var: Polars.col("index").rolling_var_by("date", "2h")
)
# =>
# shape: (25, 3)
# ┌───────┬─────────────────────┬─────────────────┐
# │ index ┆ date                ┆ rolling_row_var │
# │ ---   ┆ ---                 ┆ ---             │
# │ u32   ┆ datetime[ns]        ┆ f64             │
# ╞═══════╪═════════════════════╪═════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 ┆ null            │
# │ 1     ┆ 2001-01-01 01:00:00 ┆ 0.5             │
# │ 2     ┆ 2001-01-01 02:00:00 ┆ 0.5             │
# │ 3     ┆ 2001-01-01 03:00:00 ┆ 0.5             │
# │ 4     ┆ 2001-01-01 04:00:00 ┆ 0.5             │
# │ …     ┆ …                   ┆ …               │
# │ 20    ┆ 2001-01-01 20:00:00 ┆ 0.5             │
# │ 21    ┆ 2001-01-01 21:00:00 ┆ 0.5             │
# │ 22    ┆ 2001-01-01 22:00:00 ┆ 0.5             │
# │ 23    ┆ 2001-01-01 23:00:00 ┆ 0.5             │
# │ 24    ┆ 2001-01-02 00:00:00 ┆ 0.5             │
# └───────┴─────────────────────┴─────────────────┘

Compute the rolling var with the closure of windows on both sides

df_temporal.with_columns(
  rolling_row_var: Polars.col("index").rolling_var_by(
    "date", "2h", closed: "both"
  )
)
# =>
# shape: (25, 3)
# ┌───────┬─────────────────────┬─────────────────┐
# │ index ┆ date                ┆ rolling_row_var │
# │ ---   ┆ ---                 ┆ ---             │
# │ u32   ┆ datetime[ns]        ┆ f64             │
# ╞═══════╪═════════════════════╪═════════════════╡
# │ 0     ┆ 2001-01-01 00:00:00 ┆ null            │
# │ 1     ┆ 2001-01-01 01:00:00 ┆ 0.5             │
# │ 2     ┆ 2001-01-01 02:00:00 ┆ 1.0             │
# │ 3     ┆ 2001-01-01 03:00:00 ┆ 1.0             │
# │ 4     ┆ 2001-01-01 04:00:00 ┆ 1.0             │
# │ …     ┆ …                   ┆ …               │
# │ 20    ┆ 2001-01-01 20:00:00 ┆ 1.0             │
# │ 21    ┆ 2001-01-01 21:00:00 ┆ 1.0             │
# │ 22    ┆ 2001-01-01 22:00:00 ┆ 1.0             │
# │ 23    ┆ 2001-01-01 23:00:00 ┆ 1.0             │
# │ 24    ┆ 2001-01-02 00:00:00 ┆ 1.0             │
# └───────┴─────────────────────┴─────────────────┘

Parameters:

  • by (String) —

    This column must be of dtype Datetime or Date.

  • window_size (String) —

    The length of the window. Can be a dynamic temporal size indicated by a timedelta or the following string language:

    • 1ns (1 nanosecond)
    • 1us (1 microsecond)
    • 1ms (1 millisecond)
    • 1s (1 second)
    • 1m (1 minute)
    • 1h (1 hour)
    • 1d (1 calendar day)
    • 1w (1 calendar week)
    • 1mo (1 calendar month)
    • 1q (1 calendar quarter)
    • 1y (1 calendar year)

    By "calendar day", we mean the corresponding time on the next day (which may not be 24 hours, due to daylight savings). Similarly for "calendar week", "calendar month", "calendar quarter", and "calendar year".

  • min_periods (Integer) (defaults to: 1) —

    The number of values in the window that should be non-null before computing a result.

  • closed ('left', 'right', 'both', 'none') (defaults to: "right") —

    Define which sides of the temporal interval are closed (inclusive), defaults to 'right'.

  • ddof (Integer) (defaults to: 1) —

    "Delta Degrees of Freedom": The divisor for a length N window is N - ddof

  • warn_if_unsorted (Boolean) (defaults to: nil) —

    Warn if data is not known to be sorted by by column.

Returns:



4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
 
# File 'lib/polars/expr.rb', line 4664

def rolling_var_by(
  by,
  window_size,
  min_periods: 1,
  closed: "right",
  ddof: 1,
  warn_if_unsorted: nil
)
  window_size = _prepare_rolling_by_window_args(window_size)
  by = Utils.parse_into_expression(by)
  _from_rbexpr(
    _rbexpr.rolling_var_by(
      by,
      window_size,
      min_periods,
      closed,
      ddof
    )
  )
end

#round(decimals = 0) ⇒ Expr

Round underlying floating point data by decimals digits.

Examples:

df = Polars::DataFrame.new({"a" => [0.33, 0.52, 1.02, 1.17]})
df.select(Polars.col("a").round(1))
# =>
# shape: (4, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 0.3 │
# │ 0.5 │
# │ 1.0 │
# │ 1.2 │
# └─────┘

Parameters:

  • decimals (Integer) (defaults to: 0) —

    Number of decimals to round by.

Returns:



1139
1140
1141
 
# File 'lib/polars/expr.rb', line 1139

def round(decimals = 0)
  _from_rbexpr(_rbexpr.round(decimals))
end

#sample(frac: nil, with_replacement: true, shuffle: false, seed: nil, n: nil) ⇒ Expr

Sample from this expression.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3]})
df.select(Polars.col("a").sample(frac: 1.0, with_replacement: true, seed: 1))
# =>
# shape: (3, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ i64 │
# ╞═════╡
# │ 3   │
# │ 1   │
# │ 1   │
# └─────┘

Parameters:

  • frac (Float) (defaults to: nil) —

    Fraction of items to return. Cannot be used with n.

  • with_replacement (Boolean) (defaults to: true) —

    Allow values to be sampled more than once.

  • shuffle (Boolean) (defaults to: false) —

    Shuffle the order of sampled data points.

  • seed (Integer) (defaults to: nil) —

    Seed for the random number generator. If set to None (default), a random seed is used.

  • n (Integer) (defaults to: nil) —

    Number of items to return. Cannot be used with frac.

Returns:



6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
 
# File 'lib/polars/expr.rb', line 6375

def sample(
  frac: nil,
  with_replacement: true,
  shuffle: false,
  seed: nil,
  n: nil
)
  if !n.nil? && !frac.nil?
    raise ArgumentError, "cannot specify both `n` and `frac`"
  end

  if !n.nil? && frac.nil?
    n = Utils.parse_into_expression(n)
    return _from_rbexpr(_rbexpr.sample_n(n, with_replacement, shuffle, seed))
  end

  if frac.nil?
    frac = 1.0
  end
  frac = Utils.parse_into_expression(frac)
  _from_rbexpr(
    _rbexpr.sample_frac(frac, with_replacement, shuffle, seed)
  )
end

#search_sorted(element, side: "any") ⇒ Expr

Find indices where elements should be inserted to maintain order.

Examples:

df = Polars::DataFrame.new(
  {
    "values" => [1, 2, 3, 5]
  }
)
df.select(
  [
    Polars.col("values").search_sorted(0).alias("zero"),
    Polars.col("values").search_sorted(3).alias("three"),
    Polars.col("values").search_sorted(6).alias("six")
  ]
)
# =>
# shape: (1, 3)
# ┌──────┬───────┬─────┐
# │ zero ┆ three ┆ six │
# │ ---  ┆ ---   ┆ --- │
# │ u32  ┆ u32   ┆ u32 │
# ╞══════╪═══════╪═════╡
# │ 0    ┆ 2     ┆ 4   │
# └──────┴───────┴─────┘

Parameters:

  • element (Object) —

    Expression or scalar value.

Returns:



1500
1501
1502
1503
 
# File 'lib/polars/expr.rb', line 1500

def search_sorted(element, side: "any")
  element = Utils.parse_into_expression(element, str_as_lit: false)
  _from_rbexpr(_rbexpr.search_sorted(element, side))
end

#set_sorted(descending: false) ⇒ Expr

Note:

This can lead to incorrect results if this Series is not sorted!! Use with care!

Flags the expression as 'sorted'.

Enables downstream code to user fast paths for sorted arrays.

Examples:

df = Polars::DataFrame.new({"values" => [1, 2, 3]})
df.select(Polars.col("values").set_sorted.max)
# =>
# shape: (1, 1)
# ┌────────┐
# │ values │
# │ ---    │
# │ i64    │
# ╞════════╡
# │ 3      │
# └────────┘

Parameters:

  • descending (Boolean) (defaults to: false) —

    Whether the Series order is descending.

Returns:



6752
6753
6754
 
# File 'lib/polars/expr.rb', line 6752

def set_sorted(descending: false)
  _from_rbexpr(_rbexpr.set_sorted_flag(descending))
end

#shift(n = 1, fill_value: nil) ⇒ Expr

Shift the values by a given period.

Examples:

df = Polars::DataFrame.new({"foo" => [1, 2, 3, 4]})
df.select(Polars.col("foo").shift(1))
# =>
# shape: (4, 1)
# ┌──────┐
# │ foo  │
# │ ---  │
# │ i64  │
# ╞══════╡
# │ null │
# │ 1    │
# │ 2    │
# │ 3    │
# └──────┘

Parameters:

  • n (Integer) (defaults to: 1) —

    Number of places to shift (may be negative).

  • fill_value (Object) (defaults to: nil) —

    Fill the resulting null values with this value.

Returns:



1661
1662
1663
1664
1665
1666
1667
 
# File 'lib/polars/expr.rb', line 1661

def shift(n = 1, fill_value: nil)
  if !fill_value.nil?
    fill_value = Utils.parse_into_expression(fill_value, str_as_lit: true)
  end
  n = Utils.parse_into_expression(n)
  _from_rbexpr(_rbexpr.shift(n, fill_value))
end

#shift_and_fill(periods, fill_value) ⇒ Expr

Shift the values by a given period and fill the resulting null values.

Examples:

df = Polars::DataFrame.new({"foo" => [1, 2, 3, 4]})
df.select(Polars.col("foo").shift_and_fill(1, "a"))
# =>
# shape: (4, 1)
# ┌─────┐
# │ foo │
# │ --- │
# │ str │
# ╞═════╡
# │ a   │
# │ 1   │
# │ 2   │
# │ 3   │
# └─────┘

Parameters:

  • periods (Integer) —

    Number of places to shift (may be negative).

  • fill_value (Object) —

    Fill nil values with the result of this expression.

Returns:



1693
1694
1695
 
# File 'lib/polars/expr.rb', line 1693

def shift_and_fill(periods, fill_value)
  shift(periods, fill_value: fill_value)
end

#shrink_dtype ⇒ Expr

Shrink numeric columns to the minimal required datatype.

Shrink to the dtype needed to fit the extrema of this Series. This can be used to reduce memory pressure.

Examples:

Polars::DataFrame.new(
  {
    "a" => [1, 2, 3],
    "b" => [1, 2, 2 << 32],
    "c" => [-1, 2, 1 << 30],
    "d" => [-112, 2, 112],
    "e" => [-112, 2, 129],
    "f" => ["a", "b", "c"],
    "g" => [0.1, 1.32, 0.12],
    "h" => [true, nil, false]
  }
).select(Polars.all.shrink_dtype)
# =>
# shape: (3, 8)
# ┌─────┬────────────┬────────────┬──────┬──────┬─────┬──────┬───────┐
# │ a   ┆ b          ┆ c          ┆ d    ┆ e    ┆ f   ┆ g    ┆ h     │
# │ --- ┆ ---        ┆ ---        ┆ ---  ┆ ---  ┆ --- ┆ ---  ┆ ---   │
# │ i8  ┆ i64        ┆ i32        ┆ i8   ┆ i16  ┆ str ┆ f32  ┆ bool  │
# ╞═════╪════════════╪════════════╪══════╪══════╪═════╪══════╪═══════╡
# │ 1   ┆ 1          ┆ -1         ┆ -112 ┆ -112 ┆ a   ┆ 0.1  ┆ true  │
# │ 2   ┆ 2          ┆ 2          ┆ 2    ┆ 2    ┆ b   ┆ 1.32 ┆ null  │
# │ 3   ┆ 8589934592 ┆ 1073741824 ┆ 112  ┆ 129  ┆ c   ┆ 0.12 ┆ false │
# └─────┴────────────┴────────────┴──────┴──────┴─────┴──────┴───────┘

Returns:



6812
6813
6814
 
# File 'lib/polars/expr.rb', line 6812

def shrink_dtype
  _from_rbexpr(_rbexpr.shrink_dtype)
end

#shuffle(seed: nil) ⇒ Expr

Shuffle the contents of this expr.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3]})
df.select(Polars.col("a").shuffle(seed: 1))
# =>
# shape: (3, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ i64 │
# ╞═════╡
# │ 2   │
# │ 1   │
# │ 3   │
# └─────┘

Parameters:

  • seed (Integer) (defaults to: nil) —

    Seed for the random number generator. If set to None (default), a random seed is generated using the random module.

Returns:



6338
6339
6340
6341
6342
6343
 
# File 'lib/polars/expr.rb', line 6338

def shuffle(seed: nil)
  if seed.nil?
    seed = rand(10000)
  end
  _from_rbexpr(_rbexpr.shuffle(seed))
end

#sign ⇒ Expr

Compute the element-wise indication of the sign.

Examples:

df = Polars::DataFrame.new({"a" => [-9.0, -0.0, 0.0, 4.0, nil]})
df.select(Polars.col("a").sign)
# =>
# shape: (5, 1)
# ┌──────┐
# │ a    │
# │ ---  │
# │ f64  │
# ╞══════╡
# │ -1.0 │
# │ -0.0 │
# │ 0.0  │
# │ 1.0  │
# │ null │
# └──────┘

Returns:



6026
6027
6028
 
# File 'lib/polars/expr.rb', line 6026

def sign
  _from_rbexpr(_rbexpr.sign)
end

#sin ⇒ Expr

Compute the element-wise value for the sine.

Examples:

df = Polars::DataFrame.new({"a" => [0.0]})
df.select(Polars.col("a").sin)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 0.0 │
# └─────┘

Returns:



6046
6047
6048
 
# File 'lib/polars/expr.rb', line 6046

def sin
  _from_rbexpr(_rbexpr.sin)
end

#sinh ⇒ Expr

Compute the element-wise value for the hyperbolic sine.

Examples:

df = Polars::DataFrame.new({"a" => [1.0]})
df.select(Polars.col("a").sinh)
# =>
# shape: (1, 1)
# ┌──────────┐
# │ a        │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ 1.175201 │
# └──────────┘

Returns:



6166
6167
6168
 
# File 'lib/polars/expr.rb', line 6166

def sinh
  _from_rbexpr(_rbexpr.sinh)
end

#skew(bias: true) ⇒ Expr

Compute the sample skewness of a data set.

For normally distributed data, the skewness should be about zero. For unimodal continuous distributions, a skewness value greater than zero means that there is more weight in the right tail of the distribution. The function skewtest can be used to determine if the skewness value is close enough to zero, statistically speaking.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3, 2, 1]})
df.select(Polars.col("a").skew)
# =>
# shape: (1, 1)
# ┌──────────┐
# │ a        │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ 0.343622 │
# └──────────┘

Parameters:

  • bias (Boolean) (defaults to: true) —

    If false, the calculations are corrected for statistical bias.

Returns:



5825
5826
5827
 
# File 'lib/polars/expr.rb', line 5825

def skew(bias: true)
  _from_rbexpr(_rbexpr.skew(bias))
end

#slice(offset, length = nil) ⇒ Expr

Get a slice of this expression.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [8, 9, 10, 11],
    "b" => [nil, 4, 4, 4]
  }
)
df.select(Polars.all.slice(1, 2))
# =>
# shape: (2, 2)
# ┌─────┬─────┐
# │ a   ┆ b   │
# │ --- ┆ --- │
# │ i64 ┆ i64 │
# ╞═════╪═════╡
# │ 9   ┆ 4   │
# │ 10  ┆ 4   │
# └─────┴─────┘

Parameters:

  • offset (Integer) —

    Start index. Negative indexing is supported.

  • length (Integer) (defaults to: nil) —

    Length of the slice. If set to nil, all rows starting at the offset will be selected.

Returns:



774
775
776
777
778
779
780
781
782
 
# File 'lib/polars/expr.rb', line 774

def slice(offset, length = nil)
  if !offset.is_a?(Expr)
    offset = Polars.lit(offset)
  end
  if !length.is_a?(Expr)
    length = Polars.lit(length)
  end
  _from_rbexpr(_rbexpr.slice(offset._rbexpr, length._rbexpr))
end

#sort(reverse: false, nulls_last: false) ⇒ Expr

Sort this column. In projection/ selection context the whole column is sorted.

If used in a group by context, the groups are sorted.

Examples:

df = Polars::DataFrame.new(
  {
    "group" => [
      "one",
      "one",
      "one",
      "two",
      "two",
      "two"
    ],
    "value" => [1, 98, 2, 3, 99, 4]
  }
)
df.select(Polars.col("value").sort)
# =>
# shape: (6, 1)
# ┌───────┐
# │ value │
# │ ---   │
# │ i64   │
# ╞═══════╡
# │ 1     │
# │ 2     │
# │ 3     │
# │ 4     │
# │ 98    │
# │ 99    │
# └───────┘
df.select(Polars.col("value").sort)
# =>
# shape: (6, 1)
# ┌───────┐
# │ value │
# │ ---   │
# │ i64   │
# ╞═══════╡
# │ 1     │
# │ 2     │
# │ 3     │
# │ 4     │
# │ 98    │
# │ 99    │
# └───────┘
df.group_by("group").agg(Polars.col("value").sort)
# =>
# shape: (2, 2)
# ┌───────┬────────────┐
# │ group ┆ value      │
# │ ---   ┆ ---        │
# │ str   ┆ list[i64]  │
# ╞═══════╪════════════╡
# │ two   ┆ [3, 4, 99] │
# │ one   ┆ [1, 2, 98] │
# └───────┴────────────┘

Parameters:

  • reverse (Boolean) (defaults to: false) —

    false -> order from small to large. true -> order from large to small.

  • nulls_last (Boolean) (defaults to: false) —

    If true nulls are considered to be larger than any valid value.

Returns:



1310
1311
1312
 
# File 'lib/polars/expr.rb', line 1310

def sort(reverse: false, nulls_last: false)
  _from_rbexpr(_rbexpr.sort_with(reverse, nulls_last))
end

#sort_by(by, *more_by, reverse: false, nulls_last: false, multithreaded: true, maintain_order: false) ⇒ Expr

Sort this column by the ordering of another column, or multiple other columns.

In projection/ selection context the whole column is sorted. If used in a group by context, the groups are sorted.

Examples:

df = Polars::DataFrame.new(
  {
    "group" => [
      "one",
      "one",
      "one",
      "two",
      "two",
      "two"
    ],
    "value" => [1, 98, 2, 3, 99, 4]
  }
)
df.select(Polars.col("group").sort_by("value"))
# =>
# shape: (6, 1)
# ┌───────┐
# │ group │
# │ ---   │
# │ str   │
# ╞═══════╡
# │ one   │
# │ one   │
# │ two   │
# │ two   │
# │ one   │
# │ two   │
# └───────┘

Parameters:

  • by (Object) —

    The column(s) used for sorting.

  • reverse (Boolean) (defaults to: false) —

    false -> order from small to large. true -> order from large to small.

Returns:



1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
 
# File 'lib/polars/expr.rb', line 1547

def sort_by(by, *more_by, reverse: false, nulls_last: false, multithreaded: true, maintain_order: false)
  by = Utils.parse_into_list_of_expressions(by, *more_by)
  reverse = Utils.extend_bool(reverse, by.length, "reverse", "by")
  nulls_last = Utils.extend_bool(nulls_last, by.length, "nulls_last", "by")
  _from_rbexpr(
    _rbexpr.sort_by(
      by, reverse, nulls_last, multithreaded, maintain_order
    )
  )
end

#sqrt ⇒ Expr

Compute the square root of the elements.

Examples:

df = Polars::DataFrame.new({"values" => [1.0, 2.0, 4.0]})
df.select(Polars.col("values").sqrt)
# =>
# shape: (3, 1)
# ┌──────────┐
# │ values   │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ 1.0      │
# │ 1.414214 │
# │ 2.0      │
# └──────────┘

Returns:



245
246
247
 
# File 'lib/polars/expr.rb', line 245

def sqrt
  self**0.5
end

#std(ddof: 1) ⇒ Expr

Get standard deviation.

Examples:

df = Polars::DataFrame.new({"a" => [-1, 0, 1]})
df.select(Polars.col("a").std)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 1.0 │
# └─────┘

Parameters:

  • ddof (Integer) (defaults to: 1) —

    Degrees of freedom.

Returns:



1889
1890
1891
 
# File 'lib/polars/expr.rb', line 1889

def std(ddof: 1)
  _from_rbexpr(_rbexpr.std(ddof))
end

#str ⇒ StringExpr

Create an object namespace of all string related methods.

Returns:



7181
7182
7183
 
# File 'lib/polars/expr.rb', line 7181

def str
  StringExpr.new(self)
end

#struct ⇒ StructExpr

Create an object namespace of all struct related methods.

Returns:



7188
7189
7190
 
# File 'lib/polars/expr.rb', line 7188

def struct
  StructExpr.new(self)
end

#sub(other) ⇒ Expr

Method equivalent of subtraction operator expr - other.

Examples:

df = Polars::DataFrame.new({"x" => [0, 1, 2, 3, 4]})
df.with_columns(
  Polars.col("x").sub(2).alias("x-2"),
  Polars.col("x").sub(Polars.col("x").cum_sum).alias("x-expr"),
)
# =>
# shape: (5, 3)
# ┌─────┬─────┬────────┐
# │ x   ┆ x-2 ┆ x-expr │
# │ --- ┆ --- ┆ ---    │
# │ i64 ┆ i64 ┆ i64    │
# ╞═════╪═════╪════════╡
# │ 0   ┆ -2  ┆ 0      │
# │ 1   ┆ -1  ┆ 0      │
# │ 2   ┆ 0   ┆ -1     │
# │ 3   ┆ 1   ┆ -3     │
# │ 4   ┆ 2   ┆ -6     │
# └─────┴─────┴────────┘

Parameters:

  • other (Object) —

    Numeric literal or expression value.

Returns:



3513
3514
3515
 
# File 'lib/polars/expr.rb', line 3513

def sub(other)
  self - other
end

#suffix(suffix) ⇒ Expr

Add a suffix to the root column name of the expression.

Returns:



421
422
423
 
# File 'lib/polars/expr.rb', line 421

def suffix(suffix)
  name.suffix(suffix)
end

#sum ⇒ Expr

Note:

Dtypes in :i8, :u8, :i16, and :u16 are cast to :i64 before summing to prevent overflow issues.

Get sum value.

Examples:

df = Polars::DataFrame.new({"a" => [-1, 0, 1]})
df.select(Polars.col("a").sum)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ i64 │
# ╞═════╡
# │ 0   │
# └─────┘

Returns:



2016
2017
2018
 
# File 'lib/polars/expr.rb', line 2016

def sum
  _from_rbexpr(_rbexpr.sum)
end

#tail(n = 10) ⇒ Expr

Get the last n rows.

Examples:

df = Polars::DataFrame.new({"foo" => [1, 2, 3, 4, 5, 6, 7]})
df.tail(3)
# =>
# shape: (3, 1)
# ┌─────┐
# │ foo │
# │ --- │
# │ i64 │
# ╞═════╡
# │ 5   │
# │ 6   │
# │ 7   │
# └─────┘

Parameters:

  • n (Integer) (defaults to: 10) —

    Number of rows to return.

Returns:



3062
3063
3064
 
# File 'lib/polars/expr.rb', line 3062

def tail(n = 10)
  _from_rbexpr(_rbexpr.tail(n))
end

#tan ⇒ Expr

Compute the element-wise value for the tangent.

Examples:

df = Polars::DataFrame.new({"a" => [1.0]})
df.select(Polars.col("a").tan)
# =>
# shape: (1, 1)
# ┌──────────┐
# │ a        │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ 1.557408 │
# └──────────┘

Returns:



6086
6087
6088
 
# File 'lib/polars/expr.rb', line 6086

def tan
  _from_rbexpr(_rbexpr.tan)
end

#tanh ⇒ Expr

Compute the element-wise value for the hyperbolic tangent.

Examples:

df = Polars::DataFrame.new({"a" => [1.0]})
df.select(Polars.col("a").tanh)
# =>
# shape: (1, 1)
# ┌──────────┐
# │ a        │
# │ ---      │
# │ f64      │
# ╞══════════╡
# │ 0.761594 │
# └──────────┘

Returns:



6206
6207
6208
 
# File 'lib/polars/expr.rb', line 6206

def tanh
  _from_rbexpr(_rbexpr.tanh)
end

#to_physical ⇒ Expr

Cast to physical representation of the logical dtype.

  • :date -> :i32
  • :datetime -> :i64
  • :time -> :i64
  • :duration -> :i64
  • :cat -> :u32
  • Other data types will be left unchanged.

Examples:

Polars::DataFrame.new({"vals" => ["a", "x", nil, "a"]}).with_columns(
  [
    Polars.col("vals").cast(:cat),
    Polars.col("vals")
      .cast(:cat)
      .to_physical
      .alias("vals_physical")
  ]
)
# =>
# shape: (4, 2)
# ┌──────┬───────────────┐
# │ vals ┆ vals_physical │
# │ ---  ┆ ---           │
# │ cat  ┆ u32           │
# ╞══════╪═══════════════╡
# │ a    ┆ 0             │
# │ x    ┆ 1             │
# │ null ┆ null          │
# │ a    ┆ 0             │
# └──────┴───────────────┘

Returns:



178
179
180
 
# File 'lib/polars/expr.rb', line 178

def to_physical
  _from_rbexpr(_rbexpr.to_physical)
end

#to_s ⇒ String Also known as: inspect

Returns a string representing the Expr.

Returns:



20
21
22
 
# File 'lib/polars/expr.rb', line 20

def to_s
  _rbexpr.to_str
end

#top_k(k: 5) ⇒ Expr

Return the k largest elements.

If 'reverse: true` the smallest elements will be given.

Examples:

df = Polars::DataFrame.new(
  {
    "value" => [1, 98, 2, 3, 99, 4]
  }
)
df.select(
  [
    Polars.col("value").top_k.alias("top_k"),
    Polars.col("value").bottom_k.alias("bottom_k")
  ]
)
# =>
# shape: (5, 2)
# ┌───────┬──────────┐
# │ top_k ┆ bottom_k │
# │ ---   ┆ ---      │
# │ i64   ┆ i64      │
# ╞═══════╪══════════╡
# │ 99    ┆ 1        │
# │ 98    ┆ 2        │
# │ 4     ┆ 3        │
# │ 3     ┆ 4        │
# │ 2     ┆ 98       │
# └───────┴──────────┘

Parameters:

  • k (Integer) (defaults to: 5) —

    Number of elements to return.

Returns:



1348
1349
1350
1351
 
# File 'lib/polars/expr.rb', line 1348

def top_k(k: 5)
  k = Utils.parse_into_expression(k)
  _from_rbexpr(_rbexpr.top_k(k))
end

#truediv(other) ⇒ Expr

Method equivalent of float division operator expr / other.

Examples:

df = Polars::DataFrame.new(
  {"x" => [-2, -1, 0, 1, 2], "y" => [0.5, 0.0, 0.0, -4.0, -0.5]}
)
df.with_columns(
  Polars.col("x").truediv(2).alias("x/2"),
  Polars.col("x").truediv(Polars.col("y")).alias("x/y")
)
# =>
# shape: (5, 4)
# ┌─────┬──────┬──────┬───────┐
# │ x   ┆ y    ┆ x/2  ┆ x/y   │
# │ --- ┆ ---  ┆ ---  ┆ ---   │
# │ i64 ┆ f64  ┆ f64  ┆ f64   │
# ╞═════╪══════╪══════╪═══════╡
# │ -2  ┆ 0.5  ┆ -1.0 ┆ -4.0  │
# │ -1  ┆ 0.0  ┆ -0.5 ┆ -inf  │
# │ 0   ┆ 0.0  ┆ 0.0  ┆ NaN   │
# │ 1   ┆ -4.0 ┆ 0.5  ┆ -0.25 │
# │ 2   ┆ -0.5 ┆ 1.0  ┆ -4.0  │
# └─────┴──────┴──────┴───────┘

Parameters:

  • other (Object) —

    Numeric literal or expression value.

Returns:



3568
3569
3570
 
# File 'lib/polars/expr.rb', line 3568

def truediv(other)
  self / other
end

#unique(maintain_order: false) ⇒ Expr

Get unique values of this expression.

Examples:

df = Polars::DataFrame.new({"a" => [1, 1, 2]})
df.select(Polars.col("a").unique(maintain_order: true))
# =>
# shape: (2, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ i64 │
# ╞═════╡
# │ 1   │
# │ 2   │
# └─────┘

Parameters:

  • maintain_order (Boolean) (defaults to: false) —

    Maintain order of data. This requires more work.

Returns:



2208
2209
2210
2211
2212
2213
2214
 
# File 'lib/polars/expr.rb', line 2208

def unique(maintain_order: false)
  if maintain_order
    _from_rbexpr(_rbexpr.unique_stable)
  else
    _from_rbexpr(_rbexpr.unique)
  end
end

#unique_counts ⇒ Expr

Return a count of the unique values in the order of appearance.

This method differs from value_counts in that it does not return the values, only the counts and might be faster

Examples:

df = Polars::DataFrame.new(
  {
    "id" => ["a", "b", "b", "c", "c", "c"]
  }
)
df.select(
  [
    Polars.col("id").unique_counts
  ]
)
# =>
# shape: (3, 1)
# ┌─────┐
# │ id  │
# │ --- │
# │ u32 │
# ╞═════╡
# │ 1   │
# │ 2   │
# │ 3   │
# └─────┘

Returns:



6610
6611
6612
 
# File 'lib/polars/expr.rb', line 6610

def unique_counts
  _from_rbexpr(_rbexpr.unique_counts)
end

#upper_bound ⇒ Expr

Calculate the upper bound.

Returns a unit Series with the highest value possible for the dtype of this expression.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3, 2, 1]})
df.select(Polars.col("a").upper_bound)
# =>
# shape: (1, 1)
# ┌─────────────────────┐
# │ a                   │
# │ ---                 │
# │ i64                 │
# ╞═════════════════════╡
# │ 9223372036854775807 │
# └─────────────────────┘

Returns:



6002
6003
6004
 
# File 'lib/polars/expr.rb', line 6002

def upper_bound
  _from_rbexpr(_rbexpr.upper_bound)
end

#value_counts(sort: false, parallel: false, name: nil, normalize: false) ⇒ Expr

Count all unique values and create a struct mapping value to count.

Examples:

df = Polars::DataFrame.new(
  {
    "id" => ["a", "b", "b", "c", "c", "c"]
  }
)
df.select(
  [
    Polars.col("id").value_counts(sort: true),
  ]
)
# =>
# shape: (3, 1)
# ┌───────────┐
# │ id        │
# │ ---       │
# │ struct[2] │
# ╞═══════════╡
# │ {"c",3}   │
# │ {"b",2}   │
# │ {"a",1}   │
# └───────────┘

Parameters:

  • sort (Boolean) (defaults to: false) —

    Sort the output by count in descending order. If set to false (default), the order of the output is random.

  • parallel (Boolean) (defaults to: false) —

    Execute the computation in parallel.

  • name (String) (defaults to: nil) —

    Give the resulting count column a specific name; if normalize is true defaults to "count", otherwise defaults to "proportion".

  • normalize (Boolean) (defaults to: false) —

    If true gives relative frequencies of the unique values

Returns:



6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
 
# File 'lib/polars/expr.rb', line 6563

def value_counts(
  sort: false,
  parallel: false,
  name: nil,
  normalize: false
)
  if name.nil?
    if normalize
      name = "proportion"
    else
      name = "count"
    end
  end
  _from_rbexpr(
    _rbexpr.value_counts(sort, parallel, name, normalize)
  )
end

#var(ddof: 1) ⇒ Expr

Get variance.

Examples:

df = Polars::DataFrame.new({"a" => [-1, 0, 1]})
df.select(Polars.col("a").var)
# =>
# shape: (1, 1)
# ┌─────┐
# │ a   │
# │ --- │
# │ f64 │
# ╞═════╡
# │ 1.0 │
# └─────┘

Parameters:

  • ddof (Integer) (defaults to: 1) —

    Degrees of freedom.

Returns:



1912
1913
1914
 
# File 'lib/polars/expr.rb', line 1912

def var(ddof: 1)
  _from_rbexpr(_rbexpr.var(ddof))
end

#where(predicate) ⇒ Expr

Filter a single column.

Alias for #filter.

Examples:

df = Polars::DataFrame.new(
  {
    "group_col" => ["g1", "g1", "g2"],
    "b" => [1, 2, 3]
  }
)
(
  df.group_by("group_col").agg(
    [
      Polars.col("b").where(Polars.col("b") < 2).sum.alias("lt"),
      Polars.col("b").where(Polars.col("b") >= 2).sum.alias("gte")
    ]
  )
).sort("group_col")
# =>
# shape: (2, 3)
# ┌───────────┬─────┬─────┐
# │ group_col ┆ lt  ┆ gte │
# │ ---       ┆ --- ┆ --- │
# │ str       ┆ i64 ┆ i64 │
# ╞═══════════╪═════╪═════╡
# │ g1        ┆ 1   ┆ 2   │
# │ g2        ┆ 0   ┆ 3   │
# └───────────┴─────┴─────┘

Parameters:

  • predicate (Expr) —

    Boolean expression.

Returns:



2788
2789
2790
 
# File 'lib/polars/expr.rb', line 2788

def where(predicate)
  filter(predicate)
end

#xor(other) ⇒ Expr

Method equivalent of bitwise exclusive-or operator expr ^ other.

Examples:

df = Polars::DataFrame.new(
  {"x" => [true, false, true, false], "y" => [true, true, false, false]}
)
df.with_columns(Polars.col("x").xor(Polars.col("y")).alias("x ^ y"))
# =>
# shape: (4, 3)
# ┌───────┬───────┬───────┐
# │ x     ┆ y     ┆ x ^ y │
# │ ---   ┆ ---   ┆ ---   │
# │ bool  ┆ bool  ┆ bool  │
# ╞═══════╪═══════╪═══════╡
# │ true  ┆ true  ┆ false │
# │ false ┆ true  ┆ true  │
# │ true  ┆ false ┆ true  │
# │ false ┆ false ┆ false │
# └───────┴───────┴───────┘

Parameters:

  • other (Object) —

    Integer or boolean value; accepts expression input.

Returns:



3622
3623
3624
 
# File 'lib/polars/expr.rb', line 3622

def xor(other)
  self ^ other
end

#|(other) ⇒ Expr

Bitwise OR.

Returns:



42
43
44
 
# File 'lib/polars/expr.rb', line 42

def |(other)
  _from_rbexpr(_rbexpr._or(_to_rbexpr(other)))
end