Class: Polars::DataFrame

Inherits:
Object
  • Object
show all
Includes:
Plot
Defined in:
lib/polars/data_frame.rb

Overview

Two-dimensional data structure representing data as a table with rows and columns.

Instance Method Summary collapse

Constructor Details

#initialize(data = nil, schema: nil, columns: nil, schema_overrides: nil, orient: nil, infer_schema_length: 100, nan_to_null: false) ⇒ DataFrame

Create a new DataFrame.

Parameters:

  • data (Hash, Array, Series, nil) (defaults to: nil) —

    Two-dimensional data in various forms. Hash must contain Arrays. Array may contain Series.

  • columns (Array, Hash, nil) (defaults to: nil) —

    Column labels to use for resulting DataFrame. If specified, overrides any labels already present in the data. Must match data dimensions.

  • orient ("col", "row", nil) (defaults to: nil) —

    Whether to interpret two-dimensional data as columns or as rows. If nil, the orientation is inferred by matching the columns and data dimensions. If this does not yield conclusive results, column orientation is used.



21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
 
# File 'lib/polars/data_frame.rb', line 21

def initialize(data = nil, schema: nil, columns: nil, schema_overrides: nil, orient: nil, infer_schema_length: 100, nan_to_null: false)
  schema ||= columns

  if defined?(ActiveRecord) && (data.is_a?(ActiveRecord::Relation) || data.is_a?(ActiveRecord::Result))
    raise ArgumentError, "Use read_database instead"
  end

  if data.nil?
    self._df = self.class.hash_to_rbdf({}, schema: schema, schema_overrides: schema_overrides)
  elsif data.is_a?(Hash)
    data = data.transform_keys { |v| v.is_a?(Symbol) ? v.to_s : v }
    self._df = self.class.hash_to_rbdf(data, schema: schema, schema_overrides: schema_overrides, nan_to_null: nan_to_null)
  elsif data.is_a?(::Array)
    self._df = self.class.sequence_to_rbdf(data, schema: schema, schema_overrides: schema_overrides, orient: orient, infer_schema_length: infer_schema_length)
  elsif data.is_a?(Series)
    self._df = self.class.series_to_rbdf(data, schema: schema, schema_overrides: schema_overrides)
  else
    raise ArgumentError, "DataFrame constructor called with unsupported type; got #{data.class.name}"
  end
end

Instance Method Details

#!=(other) ⇒ DataFrame

Not equal.

Returns:



447
448
449
 
# File 'lib/polars/data_frame.rb', line 447

def !=(other)
  _comp(other, "neq")
end

#%(other) ⇒ DataFrame

Returns the modulo.

Returns:



530
531
532
533
534
535
536
537
 
# File 'lib/polars/data_frame.rb', line 530

def %(other)
  if other.is_a?(DataFrame)
    return _from_rbdf(_df.rem_df(other._df))
  end

  other = _prepare_other_arg(other)
  _from_rbdf(_df.rem(other._s))
end

#*(other) ⇒ DataFrame

Performs multiplication.

Returns:



482
483
484
485
486
487
488
489
 
# File 'lib/polars/data_frame.rb', line 482

def *(other)
  if other.is_a?(DataFrame)
    return _from_rbdf(_df.mul_df(other._df))
  end

  other = _prepare_other_arg(other)
  _from_rbdf(_df.mul(other._s))
end

#+(other) ⇒ DataFrame

Performs addition.

Returns:



506
507
508
509
510
511
512
513
 
# File 'lib/polars/data_frame.rb', line 506

def +(other)
  if other.is_a?(DataFrame)
    return _from_rbdf(_df.add_df(other._df))
  end

  other = _prepare_other_arg(other)
  _from_rbdf(_df.add(other._s))
end

#-(other) ⇒ DataFrame

Performs subtraction.

Returns:



518
519
520
521
522
523
524
525
 
# File 'lib/polars/data_frame.rb', line 518

def -(other)
  if other.is_a?(DataFrame)
    return _from_rbdf(_df.sub_df(other._df))
  end

  other = _prepare_other_arg(other)
  _from_rbdf(_df.sub(other._s))
end

#/(other) ⇒ DataFrame

Performs division.

Returns:



494
495
496
497
498
499
500
501
 
# File 'lib/polars/data_frame.rb', line 494

def /(other)
  if other.is_a?(DataFrame)
    return _from_rbdf(_df.div_df(other._df))
  end

  other = _prepare_other_arg(other)
  _from_rbdf(_df.div(other._s))
end

#<(other) ⇒ DataFrame

Less than.

Returns:



461
462
463
 
# File 'lib/polars/data_frame.rb', line 461

def <(other)
  _comp(other, "lt")
end

#<=(other) ⇒ DataFrame

Less than or equal.

Returns:



475
476
477
 
# File 'lib/polars/data_frame.rb', line 475

def <=(other)
  _comp(other, "lt_eq")
end

#==(other) ⇒ DataFrame

Equal.

Returns:



440
441
442
 
# File 'lib/polars/data_frame.rb', line 440

def ==(other)
  _comp(other, "eq")
end

#>(other) ⇒ DataFrame

Greater than.

Returns:



454
455
456
 
# File 'lib/polars/data_frame.rb', line 454

def >(other)
  _comp(other, "gt")
end

#>=(other) ⇒ DataFrame

Greater than or equal.

Returns:



468
469
470
 
# File 'lib/polars/data_frame.rb', line 468

def >=(other)
  _comp(other, "gt_eq")
end

#[](*args) ⇒ Object

Returns subset of the DataFrame.

Returns:

Raises:

  • (ArgumentError) 


571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
 
# File 'lib/polars/data_frame.rb', line 571

def [](*args)
  if args.size == 2
    row_selection, col_selection = args

    # df[.., unknown]
    if row_selection.is_a?(Range)

      # multiple slices
      # df[.., ..]
      if col_selection.is_a?(Range)
        raise Todo
      end
    end

    # df[2, ..] (select row as df)
    if row_selection.is_a?(Integer)
      if col_selection.is_a?(::Array)
        df = self[0.., col_selection]
        return df.slice(row_selection, 1)
      end
      # df[2, "a"]
      if col_selection.is_a?(::String) || col_selection.is_a?(Symbol)
        return self[col_selection][row_selection]
      end
    end

    # column selection can be "a" and ["a", "b"]
    if col_selection.is_a?(::String) || col_selection.is_a?(Symbol)
      col_selection = [col_selection]
    end

    # df[.., 1]
    if col_selection.is_a?(Integer)
      series = to_series(col_selection)
      return series[row_selection]
    end

    if col_selection.is_a?(::Array)
      # df[.., [1, 2]]
      if Utils.is_int_sequence(col_selection)
        series_list = col_selection.map { |i| to_series(i) }
        df = self.class.new(series_list)
        return df[row_selection]
      end
    end

    df = self[col_selection]
    return df[row_selection]
  elsif args.size == 1
    item = args[0]

    # select single column
    # df["foo"]
    if item.is_a?(::String) || item.is_a?(Symbol)
      return Utils.wrap_s(_df.get_column(item.to_s))
    end

    # df[idx]
    if item.is_a?(Integer)
      return slice(_pos_idx(item, 0), 1)
    end

    # df[..]
    if item.is_a?(Range)
      return Slice.new(self).apply(item)
    end

    if item.is_a?(::Array) && item.all? { |v| Utils.strlike?(v) }
      # select multiple columns
      # df[["foo", "bar"]]
      return _from_rbdf(_df.select(item.map(&:to_s)))
    end

    if Utils.is_int_sequence(item)
      item = Series.new("", item)
    end

    if item.is_a?(Series)
      dtype = item.dtype
      if dtype == String
        return _from_rbdf(_df.select(item))
      elsif dtype == UInt32
        return _from_rbdf(_df.take_with_series(item._s))
      elsif [UInt8, UInt16, UInt64, Int8, Int16, Int32, Int64].include?(dtype)
        return _from_rbdf(
          _df.take_with_series(_pos_idxs(item, 0)._s)
        )
      end
    end
  end

  # Ruby-specific
  if item.is_a?(Expr) || item.is_a?(Series)
    return filter(item)
  end

  raise ArgumentError, "Cannot get item of type: #{item.class.name}"
end

#[]=(*key, value) ⇒ Object

Set item.

Returns:



673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
 
# File 'lib/polars/data_frame.rb', line 673

def []=(*key, value)
  if key.length == 1
    key = key.first
  elsif key.length != 2
    raise ArgumentError, "wrong number of arguments (given #{key.length + 1}, expected 2..3)"
  end

  if Utils.strlike?(key)
    if value.is_a?(::Array) || (defined?(Numo::NArray) && value.is_a?(Numo::NArray))
      value = Series.new(value)
    elsif !value.is_a?(Series)
      value = Polars.lit(value)
    end
    self._df = with_column(value.alias(key.to_s))._df
  elsif key.is_a?(::Array)
    row_selection, col_selection = key

    if Utils.strlike?(col_selection)
      s = self[col_selection]
    elsif col_selection.is_a?(Integer)
      raise Todo
    else
      raise ArgumentError, "column selection not understood: #{col_selection}"
    end

    s[row_selection] = value

    if col_selection.is_a?(Integer)
      replace_column(col_selection, s)
    elsif Utils.strlike?(col_selection)
      replace(col_selection, s)
    end
  else
    raise Todo
  end
end

#apply(return_dtype: nil, inference_size: 256, &f) ⇒ Object

Note:

The frame-level apply cannot track column names (as the UDF is a black-box that may arbitrarily drop, rearrange, transform, or add new columns); if you want to apply a UDF such that column names are preserved, you should use the expression-level apply syntax instead.

Apply a custom/user-defined function (UDF) over the rows of the DataFrame.

The UDF will receive each row as a tuple of values: udf(row).

Implementing logic using a Ruby function is almost always significantly slower and more memory intensive than implementing the same logic using the native expression API because:

  • The native expression engine runs in Rust; UDFs run in Ruby.
  • Use of Ruby UDFs forces the DataFrame to be materialized in memory.
  • Polars-native expressions can be parallelised (UDFs cannot).
  • Polars-native expressions can be logically optimised (UDFs cannot).

Wherever possible you should strongly prefer the native expression API to achieve the best performance.

Examples:

df = Polars::DataFrame.new({"foo" => [1, 2, 3], "bar" => [-1, 5, 8]})

Return a DataFrame by mapping each row to a tuple:

df.apply { |t| [t[0] * 2, t[1] * 3] }
# =>
# shape: (3, 2)
# ┌──────────┬──────────┐
# │ column_0 ┆ column_1 │
# │ ---      ┆ ---      │
# │ i64      ┆ i64      │
# ╞══════════╪══════════╡
# │ 2        ┆ -3       │
# │ 4        ┆ 15       │
# │ 6        ┆ 24       │
# └──────────┴──────────┘

Return a Series by mapping each row to a scalar:

df.apply { |t| t[0] * 2 + t[1] }
# =>
# shape: (3, 1)
# ┌───────┐
# │ apply │
# │ ---   │
# │ i64   │
# ╞═══════╡
# │ 1     │
# │ 9     │
# │ 14    │
# └───────┘

Parameters:

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

    Output type of the operation. If none given, Polars tries to infer the type.

  • inference_size (Integer) (defaults to: 256) —

    Only used in the case when the custom function returns rows. This uses the first n rows to determine the output schema

Returns:



2595
2596
2597
2598
2599
2600
2601
2602
 
# File 'lib/polars/data_frame.rb', line 2595

def apply(return_dtype: nil, inference_size: 256, &f)
  out, is_df = _df.apply(f, return_dtype, inference_size)
  if is_df
    _from_rbdf(out)
  else
    _from_rbdf(Utils.wrap_s(out).to_frame._df)
  end
end

#clear(n = 0) ⇒ DataFrame Also known as: cleared

Create an empty copy of the current DataFrame.

Returns a DataFrame with identical schema but no data.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [nil, 2, 3, 4],
    "b" => [0.5, nil, 2.5, 13],
    "c" => [true, true, false, nil]
  }
)
df.clear
# =>
# shape: (0, 3)
# ┌─────┬─────┬──────┐
# │ a   ┆ b   ┆ c    │
# │ --- ┆ --- ┆ ---  │
# │ i64 ┆ f64 ┆ bool │
# ╞═════╪═════╪══════╡
# └─────┴─────┴──────┘
df.clear(2)
# =>
# shape: (2, 3)
# ┌──────┬──────┬──────┐
# │ a    ┆ b    ┆ c    │
# │ ---  ┆ ---  ┆ ---  │
# │ i64  ┆ f64  ┆ bool │
# ╞══════╪══════╪══════╡
# │ null ┆ null ┆ null │
# │ null ┆ null ┆ null │
# └──────┴──────┴──────┘

Returns:



2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
 
# File 'lib/polars/data_frame.rb', line 2896

def clear(n = 0)
  if n == 0
    _from_rbdf(_df.clear)
  elsif n > 0 || len > 0
    self.class.new(
      schema.to_h { |nm, tp| [nm, Series.new(nm, [], dtype: tp).extend_constant(nil, n)] }
    )
  else
    clone
  end
end

#columns ⇒ Array

Get column names.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.columns
# => ["foo", "bar", "ham"]

Returns:



364
365
366
 
# File 'lib/polars/data_frame.rb', line 364

def columns
  _df.columns
end

#columns=(columns) ⇒ Object

Change the column names of the DataFrame.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.columns = ["apple", "banana", "orange"]
df
# =>
# shape: (3, 3)
# ┌───────┬────────┬────────┐
# │ apple ┆ banana ┆ orange │
# │ ---   ┆ ---    ┆ ---    │
# │ i64   ┆ i64    ┆ str    │
# ╞═══════╪════════╪════════╡
# │ 1     ┆ 6      ┆ a      │
# │ 2     ┆ 7      ┆ b      │
# │ 3     ┆ 8      ┆ c      │
# └───────┴────────┴────────┘

Parameters:

  • columns (Array) —

    A list with new names for the DataFrame. The length of the list should be equal to the width of the DataFrame.

Returns:



397
398
399
 
# File 'lib/polars/data_frame.rb', line 397

def columns=(columns)
  _df.set_column_names(columns)
end

#delete(name) ⇒ Series

Drop in place if exists.

Parameters:

  • name (Object) —

    Column to drop.

Returns:



2856
2857
2858
 
# File 'lib/polars/data_frame.rb', line 2856

def delete(name)
  drop_in_place(name) if include?(name)
end

#describe ⇒ DataFrame

Summary statistics for a DataFrame.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1.0, 2.8, 3.0],
    "b" => [4, 5, nil],
    "c" => [true, false, true],
    "d" => [nil, "b", "c"],
    "e" => ["usd", "eur", nil]
  }
)
df.describe
# =>
# shape: (7, 6)
# ┌────────────┬──────────┬──────────┬──────────┬──────┬──────┐
# │ describe   ┆ a        ┆ b        ┆ c        ┆ d    ┆ e    │
# │ ---        ┆ ---      ┆ ---      ┆ ---      ┆ ---  ┆ ---  │
# │ str        ┆ f64      ┆ f64      ┆ f64      ┆ str  ┆ str  │
# ╞════════════╪══════════╪══════════╪══════════╪══════╪══════╡
# │ count      ┆ 3.0      ┆ 3.0      ┆ 3.0      ┆ 3    ┆ 3    │
# │ null_count ┆ 0.0      ┆ 1.0      ┆ 0.0      ┆ 1    ┆ 1    │
# │ mean       ┆ 2.266667 ┆ 4.5      ┆ 0.666667 ┆ null ┆ null │
# │ std        ┆ 1.101514 ┆ 0.707107 ┆ 0.57735  ┆ null ┆ null │
# │ min        ┆ 1.0      ┆ 4.0      ┆ 0.0      ┆ b    ┆ eur  │
# │ max        ┆ 3.0      ┆ 5.0      ┆ 1.0      ┆ c    ┆ usd  │
# │ median     ┆ 2.8      ┆ 4.5      ┆ 1.0      ┆ null ┆ null │
# └────────────┴──────────┴──────────┴──────────┴──────┴──────┘

Returns:



1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
 
# File 'lib/polars/data_frame.rb', line 1341

def describe
  describe_cast = lambda do |stat|
    columns = []
    self.columns.each_with_index do |s, i|
      if self[s].is_numeric || self[s].is_boolean
        columns << stat[0.., i].cast(:f64)
      else
        # for dates, strings, etc, we cast to string so that all
        # statistics can be shown
        columns << stat[0.., i].cast(:str)
      end
    end
    self.class.new(columns)
  end

  summary = _from_rbdf(
    Polars.concat(
      [
        describe_cast.(
          self.class.new(columns.to_h { |c| [c, [height]] })
        ),
        describe_cast.(null_count),
        describe_cast.(mean),
        describe_cast.(std),
        describe_cast.(min),
        describe_cast.(max),
        describe_cast.(median)
      ]
    )._df
  )
  summary.insert_column(
    0,
    Polars::Series.new(
      "describe",
      ["count", "null_count", "mean", "std", "min", "max", "median"],
    )
  )
  summary
end

#drop(columns) ⇒ DataFrame

Remove column from DataFrame and return as new.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6.0, 7.0, 8.0],
    "ham" => ["a", "b", "c"]
  }
)
df.drop("ham")
# =>
# shape: (3, 2)
# ┌─────┬─────┐
# │ foo ┆ bar │
# │ --- ┆ --- │
# │ i64 ┆ f64 │
# ╞═════╪═════╡
# │ 1   ┆ 6.0 │
# │ 2   ┆ 7.0 │
# │ 3   ┆ 8.0 │
# └─────┴─────┘

Parameters:

  • columns (Object) —

    Column(s) to drop.

Returns:



2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
 
# File 'lib/polars/data_frame.rb', line 2810

def drop(columns)
  if columns.is_a?(::Array)
    df = clone
    columns.each do |n|
      df._df.drop_in_place(n)
    end
    df
  else
    _from_rbdf(_df.drop(columns))
  end
end

#drop_in_place(name) ⇒ Series

Drop in place.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.drop_in_place("ham")
# =>
# shape: (3,)
# Series: 'ham' [str]
# [
#         "a"
#         "b"
#         "c"
# ]

Parameters:

  • name (Object) —

    Column to drop.

Returns:



2846
2847
2848
 
# File 'lib/polars/data_frame.rb', line 2846

def drop_in_place(name)
  Utils.wrap_s(_df.drop_in_place(name))
end

#drop_nulls(subset: nil) ⇒ DataFrame

Return a new DataFrame where the null values are dropped.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, nil, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.drop_nulls
# =>
# shape: (2, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ bar ┆ ham │
# │ --- ┆ --- ┆ --- │
# │ i64 ┆ i64 ┆ str │
# ╞═════╪═════╪═════╡
# │ 1   ┆ 6   ┆ a   │
# │ 3   ┆ 8   ┆ c   │
# └─────┴─────┴─────┘

Parameters:

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

    Subset of column(s) on which drop_nulls will be applied.

Returns:



1722
1723
1724
1725
1726
1727
 
# File 'lib/polars/data_frame.rb', line 1722

def drop_nulls(subset: nil)
  if subset.is_a?(::String)
    subset = [subset]
  end
  _from_rbdf(_df.drop_nulls(subset))
end

#dtypes ⇒ Array

Get dtypes of columns in DataFrame. Dtypes can also be found in column headers when printing the DataFrame.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6.0, 7.0, 8.0],
    "ham" => ["a", "b", "c"]
  }
)
df.dtypes
# => [Polars::Int64, Polars::Float64, Polars::String]

Returns:



415
416
417
 
# File 'lib/polars/data_frame.rb', line 415

def dtypes
  _df.dtypes
end

#each(&block) ⇒ Object

Returns an enumerator.

Returns:



564
565
566
 
# File 'lib/polars/data_frame.rb', line 564

def each(&block)
  get_columns.each(&block)
end

#each_row(named: true, buffer_size: 500, &block) ⇒ Object

Returns an iterator over the DataFrame of rows of Ruby-native values.

Parameters:

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

    Return hashes instead of arrays. The hashes are a mapping of column name to row value. This is more expensive than returning an array, but allows for accessing values by column name.

  • buffer_size (Integer) (defaults to: 500) —

    Determines the number of rows that are buffered internally while iterating over the data; you should only modify this in very specific cases where the default value is determined not to be a good fit to your access pattern, as the speedup from using the buffer is significant (~2-4x). Setting this value to zero disables row buffering.

Returns:



4671
4672
4673
 
# File 'lib/polars/data_frame.rb', line 4671

def each_row(named: true, buffer_size: 500, &block)
  iter_rows(named: named, buffer_size: buffer_size, &block)
end

#equals(other, null_equal: true) ⇒ Boolean Also known as: frame_equal

Check if DataFrame is equal to other.

Examples:

df1 = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6.0, 7.0, 8.0],
    "ham" => ["a", "b", "c"]
  }
)
df2 = Polars::DataFrame.new(
  {
    "foo" => [3, 2, 1],
    "bar" => [8.0, 7.0, 6.0],
    "ham" => ["c", "b", "a"]
  }
)
df1.equals(df1)
# => true
df1.equals(df2)
# => false

Parameters:

  • other (DataFrame) —

    DataFrame to compare with.

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

    Consider null values as equal.

Returns:



1534
1535
1536
 
# File 'lib/polars/data_frame.rb', line 1534

def equals(other, null_equal: true)
  _df.equals(other._df, null_equal)
end

#estimated_size(unit = "b") ⇒ Numeric

Return an estimation of the total (heap) allocated size of the DataFrame.

Estimated size is given in the specified unit (bytes by default).

This estimation is the sum of the size of its buffers, validity, including nested arrays. Multiple arrays may share buffers and bitmaps. Therefore, the size of 2 arrays is not the sum of the sizes computed from this function. In particular, StructArray's size is an upper bound.

When an array is sliced, its allocated size remains constant because the buffer unchanged. However, this function will yield a smaller number. This is because this function returns the visible size of the buffer, not its total capacity.

FFI buffers are included in this estimation.

Examples:

df = Polars::DataFrame.new(
  {
    "x" => 1_000_000.times.to_a.reverse,
    "y" => 1_000_000.times.map { |v| v / 1000.0 },
    "z" => 1_000_000.times.map(&:to_s)
  },
  columns: {"x" => :u32, "y" => :f64, "z" => :str}
)
df.estimated_size
# => 25888898
df.estimated_size("mb")
# => 26.702880859375

Parameters:

  • unit ("b", "kb", "mb", "gb", "tb") (defaults to: "b") —

    Scale the returned size to the given unit.

Returns:

  • (Numeric) 


1088
1089
1090
1091
 
# File 'lib/polars/data_frame.rb', line 1088

def estimated_size(unit = "b")
  sz = _df.estimated_size
  Utils.scale_bytes(sz, to: unit)
end

#explode(columns) ⇒ DataFrame

Explode DataFrame to long format by exploding a column with Lists.

Examples:

df = Polars::DataFrame.new(
  {
    "letters" => ["a", "a", "b", "c"],
    "numbers" => [[1], [2, 3], [4, 5], [6, 7, 8]]
  }
)
df.explode("numbers")
# =>
# shape: (8, 2)
# ┌─────────┬─────────┐
# │ letters ┆ numbers │
# │ ---     ┆ ---     │
# │ str     ┆ i64     │
# ╞═════════╪═════════╡
# │ a       ┆ 1       │
# │ a       ┆ 2       │
# │ a       ┆ 3       │
# │ b       ┆ 4       │
# │ b       ┆ 5       │
# │ c       ┆ 6       │
# │ c       ┆ 7       │
# │ c       ┆ 8       │
# └─────────┴─────────┘

Parameters:

  • columns (Object) —

    Column of LargeList type.

Returns:



3094
3095
3096
 
# File 'lib/polars/data_frame.rb', line 3094

def explode(columns)
  lazy.explode(columns).collect(no_optimization: true)
end

#extend(other) ⇒ DataFrame

Extend the memory backed by this DataFrame with the values from other.

Different from vstack which adds the chunks from other to the chunks of this DataFrame extend appends the data from other to the underlying memory locations and thus may cause a reallocation.

If this does not cause a reallocation, the resulting data structure will not have any extra chunks and thus will yield faster queries.

Prefer extend over vstack when you want to do a query after a single append. For instance during online operations where you add n rows and rerun a query.

Prefer vstack over extend when you want to append many times before doing a query. For instance when you read in multiple files and when to store them in a single DataFrame. In the latter case, finish the sequence of vstack operations with a rechunk.

Examples:

df1 = Polars::DataFrame.new({"foo" => [1, 2, 3], "bar" => [4, 5, 6]})
df2 = Polars::DataFrame.new({"foo" => [10, 20, 30], "bar" => [40, 50, 60]})
df1.extend(df2)
# =>
# shape: (6, 2)
# ┌─────┬─────┐
# │ foo ┆ bar │
# │ --- ┆ --- │
# │ i64 ┆ i64 │
# ╞═════╪═════╡
# │ 1   ┆ 4   │
# │ 2   ┆ 5   │
# │ 3   ┆ 6   │
# │ 10  ┆ 40  │
# │ 20  ┆ 50  │
# │ 30  ┆ 60  │
# └─────┴─────┘

Parameters:

  • other (DataFrame) —

    DataFrame to vertically add.

Returns:



2778
2779
2780
2781
 
# File 'lib/polars/data_frame.rb', line 2778

def extend(other)
  _df.extend(other._df)
  self
end

#fill_nan(fill_value) ⇒ DataFrame

Note:

Note that floating point NaNs (Not a Number) are not missing values! To replace missing values, use fill_null.

Fill floating point NaN values by an Expression evaluation.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1.5, 2, Float::NAN, 4],
    "b" => [0.5, 4, Float::NAN, 13]
  }
)
df.fill_nan(99)
# =>
# shape: (4, 2)
# ┌──────┬──────┐
# │ a    ┆ b    │
# │ ---  ┆ ---  │
# │ f64  ┆ f64  │
# ╞══════╪══════╡
# │ 1.5  ┆ 0.5  │
# │ 2.0  ┆ 4.0  │
# │ 99.0 ┆ 99.0 │
# │ 4.0  ┆ 13.0 │
# └──────┴──────┘

Parameters:

  • fill_value (Object) —

    Value to fill NaN with.

Returns:



3059
3060
3061
 
# File 'lib/polars/data_frame.rb', line 3059

def fill_nan(fill_value)
  lazy.fill_nan(fill_value).collect(no_optimization: true)
end

#fill_null(value = nil, strategy: nil, limit: nil, matches_supertype: true) ⇒ DataFrame

Fill null values using the specified value or strategy.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, nil, 4],
    "b" => [0.5, 4, nil, 13]
  }
)
df.fill_null(99)
# =>
# shape: (4, 2)
# ┌─────┬──────┐
# │ a   ┆ b    │
# │ --- ┆ ---  │
# │ i64 ┆ f64  │
# ╞═════╪══════╡
# │ 1   ┆ 0.5  │
# │ 2   ┆ 4.0  │
# │ 99  ┆ 99.0 │
# │ 4   ┆ 13.0 │
# └─────┴──────┘
df.fill_null(strategy: "forward")
# =>
# shape: (4, 2)
# ┌─────┬──────┐
# │ a   ┆ b    │
# │ --- ┆ ---  │
# │ i64 ┆ f64  │
# ╞═════╪══════╡
# │ 1   ┆ 0.5  │
# │ 2   ┆ 4.0  │
# │ 2   ┆ 4.0  │
# │ 4   ┆ 13.0 │
# └─────┴──────┘
df.fill_null(strategy: "max")
# =>
# shape: (4, 2)
# ┌─────┬──────┐
# │ a   ┆ b    │
# │ --- ┆ ---  │
# │ i64 ┆ f64  │
# ╞═════╪══════╡
# │ 1   ┆ 0.5  │
# │ 2   ┆ 4.0  │
# │ 4   ┆ 13.0 │
# │ 4   ┆ 13.0 │
# └─────┴──────┘
df.fill_null(strategy: "zero")
# =>
# shape: (4, 2)
# ┌─────┬──────┐
# │ a   ┆ b    │
# │ --- ┆ ---  │
# │ i64 ┆ f64  │
# ╞═════╪══════╡
# │ 1   ┆ 0.5  │
# │ 2   ┆ 4.0  │
# │ 0   ┆ 0.0  │
# │ 4   ┆ 13.0 │
# └─────┴──────┘

Parameters:

  • value (Numeric) (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.

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

    Fill all matching supertype of the fill value.

Returns:



3019
3020
3021
3022
3023
3024
3025
3026
 
# File 'lib/polars/data_frame.rb', line 3019

def fill_null(value = nil, strategy: nil, limit: nil, matches_supertype: true)
  _from_rbdf(
    lazy
      .fill_null(value, strategy: strategy, limit: limit, matches_supertype: matches_supertype)
      .collect(no_optimization: true)
      ._df
  )
end

#filter(predicate) ⇒ DataFrame

Filter the rows in the DataFrame based on a predicate expression.

Examples:

Filter on one condition:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.filter(Polars.col("foo") < 3)
# =>
# shape: (2, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ bar ┆ ham │
# │ --- ┆ --- ┆ --- │
# │ i64 ┆ i64 ┆ str │
# ╞═════╪═════╪═════╡
# │ 1   ┆ 6   ┆ a   │
# │ 2   ┆ 7   ┆ b   │
# └─────┴─────┴─────┘

Filter on multiple conditions:

df.filter((Polars.col("foo") < 3) & (Polars.col("ham") == "a"))
# =>
# shape: (1, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ bar ┆ ham │
# │ --- ┆ --- ┆ --- │
# │ i64 ┆ i64 ┆ str │
# ╞═════╪═════╪═════╡
# │ 1   ┆ 6   ┆ a   │
# └─────┴─────┴─────┘

Parameters:

  • predicate (Expr) —

    Expression that evaluates to a boolean Series.

Returns:



1307
1308
1309
 
# File 'lib/polars/data_frame.rb', line 1307

def filter(predicate)
  lazy.filter(predicate).collect
end

#fold(&operation) ⇒ Series

Apply a horizontal reduction on a DataFrame.

This can be used to effectively determine aggregations on a row level, and can be applied to any DataType that can be supercasted (casted to a similar parent type).

An example of the supercast rules when applying an arithmetic operation on two DataTypes are for instance:

i8 + str = str f32 + i64 = f32 f32 + f64 = f64

Examples:

A horizontal sum operation:

df = Polars::DataFrame.new(
  {
    "a" => [2, 1, 3],
    "b" => [1, 2, 3],
    "c" => [1.0, 2.0, 3.0]
  }
)
df.fold { |s1, s2| s1 + s2 }
# =>
# shape: (3,)
# Series: 'a' [f64]
# [
#         4.0
#         5.0
#         9.0
# ]

A horizontal minimum operation:

df = Polars::DataFrame.new({"a" => [2, 1, 3], "b" => [1, 2, 3], "c" => [1.0, 2.0, 3.0]})
df.fold { |s1, s2| s1.zip_with(s1 < s2, s2) }
# =>
# shape: (3,)
# Series: 'a' [f64]
# [
#         1.0
#         1.0
#         3.0
# ]

A horizontal string concatenation:

df = Polars::DataFrame.new(
  {
    "a" => ["foo", "bar", 2],
    "b" => [1, 2, 3],
    "c" => [1.0, 2.0, 3.0]
  }
)
df.fold { |s1, s2| s1 + s2 }
# =>
# shape: (3,)
# Series: 'a' [str]
# [
#         "foo11.0"
#         "bar22.0"
#         null
# ]

A horizontal boolean or, similar to a row-wise .any:

df = Polars::DataFrame.new(
  {
    "a" => [false, false, true],
    "b" => [false, true, false]
  }
)
df.fold { |s1, s2| s1 | s2 }
# =>
# shape: (3,)
# Series: 'a' [bool]
# [
#         false
#         true
#         true
# ]

Returns:



4480
4481
4482
4483
4484
4485
4486
4487
 
# File 'lib/polars/data_frame.rb', line 4480

def fold(&operation)
  acc = to_series(0)

  1.upto(width - 1) do |i|
    acc = operation.call(acc, to_series(i))
  end
  acc
end

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

Take every nth row in the DataFrame and return as a new DataFrame.

Examples:

s = Polars::DataFrame.new({"a" => [1, 2, 3, 4], "b" => [5, 6, 7, 8]})
s.gather_every(2)
# =>
# shape: (2, 2)
# ┌─────┬─────┐
# │ a   ┆ b   │
# │ --- ┆ --- │
# │ i64 ┆ i64 │
# ╞═════╪═════╡
# │ 1   ┆ 5   │
# │ 3   ┆ 7   │
# └─────┴─────┘

Returns:



4708
4709
4710
 
# File 'lib/polars/data_frame.rb', line 4708

def gather_every(n, offset = 0)
  select(Utils.col("*").gather_every(n, offset))
end

#get_column(name) ⇒ Series

Get a single column as Series by name.

Examples:

df = Polars::DataFrame.new({"foo" => [1, 2, 3], "bar" => [4, 5, 6]})
df.get_column("foo")
# =>
# shape: (3,)
# Series: 'foo' [i64]
# [
#         1
#         2
#         3
# ]

Parameters:

  • name (String) —

    Name of the column to retrieve.

Returns:



2936
2937
2938
 
# File 'lib/polars/data_frame.rb', line 2936

def get_column(name)
  self[name]
end

#get_column_index(name) ⇒ Series Also known as: find_idx_by_name

Find the index of a column by name.

Examples:

df = Polars::DataFrame.new(
  {"foo" => [1, 2, 3], "bar" => [6, 7, 8], "ham" => ["a", "b", "c"]}
)
df.get_column_index("ham")
# => 2

Parameters:

  • name (String) —

    Name of the column to find.

Returns:



1394
1395
1396
 
# File 'lib/polars/data_frame.rb', line 1394

def get_column_index(name)
  _df.get_column_index(name)
end

#get_columns ⇒ Array

Get the DataFrame as a Array of Series.

Returns:



2914
2915
2916
 
# File 'lib/polars/data_frame.rb', line 2914

def get_columns
  _df.get_columns.map { |s| Utils.wrap_s(s) }
end

#group_by(by, maintain_order: false) ⇒ GroupBy Also known as: groupby, group

Start a group by operation.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => ["a", "b", "a", "b", "b", "c"],
    "b" => [1, 2, 3, 4, 5, 6],
    "c" => [6, 5, 4, 3, 2, 1]
  }
)
df.group_by("a").agg(Polars.col("b").sum).sort("a")
# =>
# shape: (3, 2)
# ┌─────┬─────┐
# │ a   ┆ b   │
# │ --- ┆ --- │
# │ str ┆ i64 │
# ╞═════╪═════╡
# │ a   ┆ 4   │
# │ b   ┆ 11  │
# │ c   ┆ 6   │
# └─────┴─────┘

Parameters:

  • by (Object) —

    Column(s) to group by.

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

    Make sure that the order of the groups remain consistent. This is more expensive than a default group by. Note that this only works in expression aggregations.

Returns:



1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
 
# File 'lib/polars/data_frame.rb', line 1833

def group_by(by, maintain_order: false)
  if !Utils.bool?(maintain_order)
    raise TypeError, "invalid input for group_by arg `maintain_order`: #{maintain_order}."
  end
  GroupBy.new(
    self,
    by,
    maintain_order: maintain_order
  )
end

#group_by_dynamic(index_column, every:, period: nil, offset: nil, truncate: true, include_boundaries: false, closed: "left", by: nil, start_by: "window") ⇒ DataFrame Also known as: groupby_dynamic

Group based on a time value (or index value of type :i32, :i64).

Time windows are calculated and rows are assigned to windows. Different from a normal group by is that a row can be member of multiple groups. The time/index window could be seen as a rolling window, with a window size determined by dates/times/values instead of slots in the DataFrame.

A window is defined by:

  • every: interval of the window
  • period: length of the window
  • offset: offset of the window

The every, period and offset arguments are created with 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)

Or combine them: "3d12h4m25s" # 3 days, 12 hours, 4 minutes, and 25 seconds

In case of a group_by_dynamic on an integer column, the windows are defined by:

  • "1i" # length 1
  • "10i" # length 10

Examples:

df = Polars::DataFrame.new(
  {
    "time" => Polars.date_range(
      DateTime.new(2021, 12, 16),
      DateTime.new(2021, 12, 16, 3),
      "30m"
    ),
    "n" => 0..6
  }
)
# =>
# shape: (7, 2)
# ┌─────────────────────┬─────┐
# │ time                ┆ n   │
# │ ---                 ┆ --- │
# │ datetime[μs]        ┆ i64 │
# ╞═════════════════════╪═════╡
# │ 2021-12-16 00:00:00 ┆ 0   │
# │ 2021-12-16 00:30:00 ┆ 1   │
# │ 2021-12-16 01:00:00 ┆ 2   │
# │ 2021-12-16 01:30:00 ┆ 3   │
# │ 2021-12-16 02:00:00 ┆ 4   │
# │ 2021-12-16 02:30:00 ┆ 5   │
# │ 2021-12-16 03:00:00 ┆ 6   │
# └─────────────────────┴─────┘

Group by windows of 1 hour starting at 2021-12-16 00:00:00.

df.group_by_dynamic("time", every: "1h", closed: "right").agg(
  [
    Polars.col("time").min.alias("time_min"),
    Polars.col("time").max.alias("time_max")
  ]
)
# =>
# shape: (4, 3)
# ┌─────────────────────┬─────────────────────┬─────────────────────┐
# │ time                ┆ time_min            ┆ time_max            │
# │ ---                 ┆ ---                 ┆ ---                 │
# │ datetime[μs]        ┆ datetime[μs]        ┆ datetime[μs]        │
# ╞═════════════════════╪═════════════════════╪═════════════════════╡
# │ 2021-12-15 23:00:00 ┆ 2021-12-16 00:00:00 ┆ 2021-12-16 00:00:00 │
# │ 2021-12-16 00:00:00 ┆ 2021-12-16 00:30:00 ┆ 2021-12-16 01:00:00 │
# │ 2021-12-16 01:00:00 ┆ 2021-12-16 01:30:00 ┆ 2021-12-16 02:00:00 │
# │ 2021-12-16 02:00:00 ┆ 2021-12-16 02:30:00 ┆ 2021-12-16 03:00:00 │
# └─────────────────────┴─────────────────────┴─────────────────────┘

The window boundaries can also be added to the aggregation result.

df.group_by_dynamic(
  "time", every: "1h", include_boundaries: true, closed: "right"
).agg([Polars.col("time").count.alias("time_count")])
# =>
# shape: (4, 4)
# ┌─────────────────────┬─────────────────────┬─────────────────────┬────────────┐
# │ _lower_boundary     ┆ _upper_boundary     ┆ time                ┆ time_count │
# │ ---                 ┆ ---                 ┆ ---                 ┆ ---        │
# │ datetime[μs]        ┆ datetime[μs]        ┆ datetime[μs]        ┆ u32        │
# ╞═════════════════════╪═════════════════════╪═════════════════════╪════════════╡
# │ 2021-12-15 23:00:00 ┆ 2021-12-16 00:00:00 ┆ 2021-12-15 23:00:00 ┆ 1          │
# │ 2021-12-16 00:00:00 ┆ 2021-12-16 01:00:00 ┆ 2021-12-16 00:00:00 ┆ 2          │
# │ 2021-12-16 01:00:00 ┆ 2021-12-16 02:00:00 ┆ 2021-12-16 01:00:00 ┆ 2          │
# │ 2021-12-16 02:00:00 ┆ 2021-12-16 03:00:00 ┆ 2021-12-16 02:00:00 ┆ 2          │
# └─────────────────────┴─────────────────────┴─────────────────────┴────────────┘

When closed="left", should not include right end of interval.

df.group_by_dynamic("time", every: "1h", closed: "left").agg(
  [
    Polars.col("time").count.alias("time_count"),
    Polars.col("time").alias("time_agg_list")
  ]
)
# =>
# shape: (4, 3)
# ┌─────────────────────┬────────────┬───────────────────────────────────┐
# │ time                ┆ time_count ┆ time_agg_list                     │
# │ ---                 ┆ ---        ┆ ---                               │
# │ datetime[μs]        ┆ u32        ┆ list[datetime[μs]]                │
# ╞═════════════════════╪════════════╪═══════════════════════════════════╡
# │ 2021-12-16 00:00:00 ┆ 2          ┆ [2021-12-16 00:00:00, 2021-12-16… │
# │ 2021-12-16 01:00:00 ┆ 2          ┆ [2021-12-16 01:00:00, 2021-12-16… │
# │ 2021-12-16 02:00:00 ┆ 2          ┆ [2021-12-16 02:00:00, 2021-12-16… │
# │ 2021-12-16 03:00:00 ┆ 1          ┆ [2021-12-16 03:00:00]             │
# └─────────────────────┴────────────┴───────────────────────────────────┘

When closed="both" the time values at the window boundaries belong to 2 groups.

df.group_by_dynamic("time", every: "1h", closed: "both").agg(
  [Polars.col("time").count.alias("time_count")]
)
# =>
# shape: (5, 2)
# ┌─────────────────────┬────────────┐
# │ time                ┆ time_count │
# │ ---                 ┆ ---        │
# │ datetime[μs]        ┆ u32        │
# ╞═════════════════════╪════════════╡
# │ 2021-12-15 23:00:00 ┆ 1          │
# │ 2021-12-16 00:00:00 ┆ 3          │
# │ 2021-12-16 01:00:00 ┆ 3          │
# │ 2021-12-16 02:00:00 ┆ 3          │
# │ 2021-12-16 03:00:00 ┆ 1          │
# └─────────────────────┴────────────┘

Dynamic group bys can also be combined with grouping on normal keys.

df = Polars::DataFrame.new(
  {
    "time" => Polars.date_range(
      DateTime.new(2021, 12, 16),
      DateTime.new(2021, 12, 16, 3),
      "30m"
    ),
    "groups" => ["a", "a", "a", "b", "b", "a", "a"]
  }
)
df.group_by_dynamic(
  "time",
  every: "1h",
  closed: "both",
  by: "groups",
  include_boundaries: true
).agg([Polars.col("time").count.alias("time_count")])
# =>
# shape: (7, 5)
# ┌────────┬─────────────────────┬─────────────────────┬─────────────────────┬────────────┐
# │ groups ┆ _lower_boundary     ┆ _upper_boundary     ┆ time                ┆ time_count │
# │ ---    ┆ ---                 ┆ ---                 ┆ ---                 ┆ ---        │
# │ str    ┆ datetime[μs]        ┆ datetime[μs]        ┆ datetime[μs]        ┆ u32        │
# ╞════════╪═════════════════════╪═════════════════════╪═════════════════════╪════════════╡
# │ a      ┆ 2021-12-15 23:00:00 ┆ 2021-12-16 00:00:00 ┆ 2021-12-15 23:00:00 ┆ 1          │
# │ a      ┆ 2021-12-16 00:00:00 ┆ 2021-12-16 01:00:00 ┆ 2021-12-16 00:00:00 ┆ 3          │
# │ a      ┆ 2021-12-16 01:00:00 ┆ 2021-12-16 02:00:00 ┆ 2021-12-16 01:00:00 ┆ 1          │
# │ a      ┆ 2021-12-16 02:00:00 ┆ 2021-12-16 03:00:00 ┆ 2021-12-16 02:00:00 ┆ 2          │
# │ a      ┆ 2021-12-16 03:00:00 ┆ 2021-12-16 04:00:00 ┆ 2021-12-16 03:00:00 ┆ 1          │
# │ b      ┆ 2021-12-16 01:00:00 ┆ 2021-12-16 02:00:00 ┆ 2021-12-16 01:00:00 ┆ 2          │
# │ b      ┆ 2021-12-16 02:00:00 ┆ 2021-12-16 03:00:00 ┆ 2021-12-16 02:00:00 ┆ 1          │
# └────────┴─────────────────────┴─────────────────────┴─────────────────────┴────────────┘

Dynamic group by on an index column.

df = Polars::DataFrame.new(
  {
    "idx" => Polars.arange(0, 6, eager: true),
    "A" => ["A", "A", "B", "B", "B", "C"]
  }
)
df.group_by_dynamic(
  "idx",
  every: "2i",
  period: "3i",
  include_boundaries: true,
  closed: "right"
).agg(Polars.col("A").alias("A_agg_list"))
# =>
# shape: (3, 4)
# ┌─────────────────┬─────────────────┬─────┬─────────────────┐
# │ _lower_boundary ┆ _upper_boundary ┆ idx ┆ A_agg_list      │
# │ ---             ┆ ---             ┆ --- ┆ ---             │
# │ i64             ┆ i64             ┆ i64 ┆ list[str]       │
# ╞═════════════════╪═════════════════╪═════╪═════════════════╡
# │ 0               ┆ 3               ┆ 0   ┆ ["A", "B", "B"] │
# │ 2               ┆ 5               ┆ 2   ┆ ["B", "B", "C"] │
# │ 4               ┆ 7               ┆ 4   ┆ ["C"]           │
# └─────────────────┴─────────────────┴─────┴─────────────────┘

Parameters:

  • index_column —

    Column used to group based on the time window. Often to type Date/Datetime This column must be sorted in ascending order. If not the output will not make sense.

    In case of a dynamic group by on indices, dtype needs to be one of :i32, :i64. Note that :i32 gets temporarily cast to :i64, so if performance matters use an :i64 column.

  • every —

    Interval of the window.

  • period (defaults to: nil) —

    Length of the window, if None it is equal to 'every'.

  • offset (defaults to: nil) —

    Offset of the window if None and period is None it will be equal to negative every.

  • truncate (defaults to: true) —

    Truncate the time value to the window lower bound.

  • include_boundaries (defaults to: false) —

    Add the lower and upper bound of the window to the "_lower_bound" and "_upper_bound" columns. This will impact performance because it's harder to parallelize

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

    Define whether the temporal window interval is closed or not.

  • by (defaults to: nil) —

    Also group by this column/these columns

Returns:



2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
 
# File 'lib/polars/data_frame.rb', line 2174

def group_by_dynamic(
  index_column,
  every:,
  period: nil,
  offset: nil,
  truncate: true,
  include_boundaries: false,
  closed: "left",
  by: nil,
  start_by: "window"
)
  DynamicGroupBy.new(
    self,
    index_column,
    every,
    period,
    offset,
    truncate,
    include_boundaries,
    closed,
    by,
    start_by
  )
end

#group_by_rolling(index_column:, period:, offset: nil, closed: "right", by: nil, check_sorted: true) ⇒ RollingGroupBy Also known as: groupby_rolling

Create rolling groups based on a time column.

Also works for index values of type :i32 or :i64.

Different from a dynamic_group_by the windows are now determined by the individual values and are not of constant intervals. For constant intervals use group_by_dynamic

The period and offset arguments are created either from a timedelta, or by using 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)

Or combine them: "3d12h4m25s" # 3 days, 12 hours, 4 minutes, and 25 seconds

In case of a group_by_rolling on an integer column, the windows are defined by:

  • "1i" # length 1
  • "10i" # length 10

Examples:

dates = [
  "2020-01-01 13:45:48",
  "2020-01-01 16:42:13",
  "2020-01-01 16:45:09",
  "2020-01-02 18:12:48",
  "2020-01-03 19:45:32",
  "2020-01-08 23:16:43"
]
df = Polars::DataFrame.new({"dt" => dates, "a" => [3, 7, 5, 9, 2, 1]}).with_column(
  Polars.col("dt").str.strptime(Polars::Datetime).set_sorted
)
df.group_by_rolling(index_column: "dt", period: "2d").agg(
  [
    Polars.sum("a").alias("sum_a"),
    Polars.min("a").alias("min_a"),
    Polars.max("a").alias("max_a")
  ]
)
# =>
# shape: (6, 4)
# ┌─────────────────────┬───────┬───────┬───────┐
# │ dt                  ┆ sum_a ┆ min_a ┆ max_a │
# │ ---                 ┆ ---   ┆ ---   ┆ ---   │
# │ datetime[μs]        ┆ i64   ┆ i64   ┆ i64   │
# ╞═════════════════════╪═══════╪═══════╪═══════╡
# │ 2020-01-01 13:45:48 ┆ 3     ┆ 3     ┆ 3     │
# │ 2020-01-01 16:42:13 ┆ 10    ┆ 3     ┆ 7     │
# │ 2020-01-01 16:45:09 ┆ 15    ┆ 3     ┆ 7     │
# │ 2020-01-02 18:12:48 ┆ 24    ┆ 3     ┆ 9     │
# │ 2020-01-03 19:45:32 ┆ 11    ┆ 2     ┆ 9     │
# │ 2020-01-08 23:16:43 ┆ 1     ┆ 1     ┆ 1     │
# └─────────────────────┴───────┴───────┴───────┘

Parameters:

  • index_column (Object) —

    Column used to group based on the time window. Often to type Date/Datetime This column must be sorted in ascending order. If not the output will not make sense.

    In case of a rolling group by on indices, dtype needs to be one of :i32, :i64. Note that :i32 gets temporarily cast to :i64, so if performance matters use an :i64 column.

  • period (Object) —

    Length of the window.

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

    Offset of the window. Default is -period.

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

    Define whether the temporal window interval is closed or not.

  • by (Object) (defaults to: nil) —

    Also group by this column/these columns.

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

    When the by argument is given, polars can not check sortedness by the metadata and has to do a full scan on the index column to verify data is sorted. This is expensive. If you are sure the data within the by groups is sorted, you can set this to false. Doing so incorrectly will lead to incorrect output

Returns:



1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
 
# File 'lib/polars/data_frame.rb', line 1936

def group_by_rolling(
  index_column:,
  period:,
  offset: nil,
  closed: "right",
  by: nil,
  check_sorted: true
)
  RollingGroupBy.new(self, index_column, period, offset, closed, by, check_sorted)
end

#hash_rows(seed: 0, seed_1: nil, seed_2: nil, seed_3: nil) ⇒ Series

Hash and combine the rows in this DataFrame.

The hash value is of type :u64.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, nil, 3, 4],
    "ham" => ["a", "b", nil, "d"]
  }
)
df.hash_rows(seed: 42)
# =>
# shape: (4,)
# Series: '' [u64]
# [
#         4238614331852490969
#         17976148875586754089
#         4702262519505526977
#         18144177983981041107
# ]

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:



4745
4746
4747
4748
4749
4750
4751
 
# File 'lib/polars/data_frame.rb', line 4745

def hash_rows(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
  Utils.wrap_s(_df.hash_rows(k0, k1, k2, k3))
end

#head(n = 5) ⇒ DataFrame

Get the first n rows.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3, 4, 5],
    "bar" => [6, 7, 8, 9, 10],
    "ham" => ["a", "b", "c", "d", "e"]
  }
)
df.head(3)
# =>
# shape: (3, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ bar ┆ ham │
# │ --- ┆ --- ┆ --- │
# │ i64 ┆ i64 ┆ str │
# ╞═════╪═════╪═════╡
# │ 1   ┆ 6   ┆ a   │
# │ 2   ┆ 7   ┆ b   │
# │ 3   ┆ 8   ┆ c   │
# └─────┴─────┴─────┘

Parameters:

  • n (Integer) (defaults to: 5) —

    Number of rows to return.

Returns:



1661
1662
1663
 
# File 'lib/polars/data_frame.rb', line 1661

def head(n = 5)
  _from_rbdf(_df.head(n))
end

#height ⇒ Integer Also known as: count, length, size

Get the height of the DataFrame.

Examples:

df = Polars::DataFrame.new({"foo" => [1, 2, 3, 4, 5]})
df.height
# => 5

Returns:

  • (Integer) 


331
332
333
 
# File 'lib/polars/data_frame.rb', line 331

def height
  _df.height
end

#hstack(columns, in_place: false) ⇒ DataFrame

Return a new DataFrame grown horizontally by stacking multiple Series to it.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
x = Polars::Series.new("apple", [10, 20, 30])
df.hstack([x])
# =>
# shape: (3, 4)
# ┌─────┬─────┬─────┬───────┐
# │ foo ┆ bar ┆ ham ┆ apple │
# │ --- ┆ --- ┆ --- ┆ ---   │
# │ i64 ┆ i64 ┆ str ┆ i64   │
# ╞═════╪═════╪═════╪═══════╡
# │ 1   ┆ 6   ┆ a   ┆ 10    │
# │ 2   ┆ 7   ┆ b   ┆ 20    │
# │ 3   ┆ 8   ┆ c   ┆ 30    │
# └─────┴─────┴─────┴───────┘

Parameters:

  • columns (Object) —

    Series to stack.

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

    Modify in place.

Returns:



2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
 
# File 'lib/polars/data_frame.rb', line 2680

def hstack(columns, in_place: false)
  if !columns.is_a?(::Array)
    columns = columns.get_columns
  end
  if in_place
    _df.hstack_mut(columns.map(&:_s))
    self
  else
    _from_rbdf(_df.hstack(columns.map(&:_s)))
  end
end

#include?(name) ⇒ Boolean

Check if DataFrame includes column.

Returns:



557
558
559
 
# File 'lib/polars/data_frame.rb', line 557

def include?(name)
  columns.include?(name)
end

#insert_column(index, series) ⇒ DataFrame Also known as: insert_at_idx

Insert a Series at a certain column index. This operation is in place.

Examples:

df = Polars::DataFrame.new({"foo" => [1, 2, 3], "bar" => [4, 5, 6]})
s = Polars::Series.new("baz", [97, 98, 99])
df.insert_column(1, s)
# =>
# shape: (3, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ baz ┆ bar │
# │ --- ┆ --- ┆ --- │
# │ i64 ┆ i64 ┆ i64 │
# ╞═════╪═════╪═════╡
# │ 1   ┆ 97  ┆ 4   │
# │ 2   ┆ 98  ┆ 5   │
# │ 3   ┆ 99  ┆ 6   │
# └─────┴─────┴─────┘
df = Polars::DataFrame.new(
  {
    "a" => [1, 2, 3, 4],
    "b" => [0.5, 4, 10, 13],
    "c" => [true, true, false, true]
  }
)
s = Polars::Series.new("d", [-2.5, 15, 20.5, 0])
df.insert_column(3, s)
# =>
# shape: (4, 4)
# ┌─────┬──────┬───────┬──────┐
# │ a   ┆ b    ┆ c     ┆ d    │
# │ --- ┆ ---  ┆ ---   ┆ ---  │
# │ i64 ┆ f64  ┆ bool  ┆ f64  │
# ╞═════╪══════╪═══════╪══════╡
# │ 1   ┆ 0.5  ┆ true  ┆ -2.5 │
# │ 2   ┆ 4.0  ┆ true  ┆ 15.0 │
# │ 3   ┆ 10.0 ┆ false ┆ 20.5 │
# │ 4   ┆ 13.0 ┆ true  ┆ 0.0  │
# └─────┴──────┴───────┴──────┘

Parameters:

  • index (Integer) —

    Column to insert the new Series column.

  • series (Series) —

    Series to insert.

Returns:



1260
1261
1262
1263
1264
1265
1266
 
# File 'lib/polars/data_frame.rb', line 1260

def insert_column(index, series)
  if index < 0
    index = columns.length + index
  end
  _df.insert_column(index, series._s)
  self
end

#interpolate ⇒ DataFrame

Interpolate intermediate values. The interpolation method is linear.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, nil, 9, 10],
    "bar" => [6, 7, 9, nil],
    "baz" => [1, nil, nil, 9]
  }
)
df.interpolate
# =>
# shape: (4, 3)
# ┌──────┬──────┬──────────┐
# │ foo  ┆ bar  ┆ baz      │
# │ ---  ┆ ---  ┆ ---      │
# │ f64  ┆ f64  ┆ f64      │
# ╞══════╪══════╪══════════╡
# │ 1.0  ┆ 6.0  ┆ 1.0      │
# │ 5.0  ┆ 7.0  ┆ 3.666667 │
# │ 9.0  ┆ 9.0  ┆ 6.333333 │
# │ 10.0 ┆ null ┆ 9.0      │
# └──────┴──────┴──────────┘

Returns:



4778
4779
4780
 
# File 'lib/polars/data_frame.rb', line 4778

def interpolate
  select(Utils.col("*").interpolate)
end

#is_duplicated ⇒ Series

Get a mask of all duplicated rows in this DataFrame.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, 3, 1],
    "b" => ["x", "y", "z", "x"],
  }
)
df.is_duplicated
# =>
# shape: (4,)
# Series: '' [bool]
# [
#         true
#         false
#         false
#         true
# ]

Returns:



3585
3586
3587
 
# File 'lib/polars/data_frame.rb', line 3585

def is_duplicated
  Utils.wrap_s(_df.is_duplicated)
end

#is_empty ⇒ Boolean Also known as: empty?

Check if the dataframe is empty.

Examples:

df = Polars::DataFrame.new({"foo" => [1, 2, 3], "bar" => [4, 5, 6]})
df.is_empty
# => false
df.filter(Polars.col("foo") > 99).is_empty
# => true

Returns:



4792
4793
4794
 
# File 'lib/polars/data_frame.rb', line 4792

def is_empty
  height == 0
end

#is_unique ⇒ Series

Get a mask of all unique rows in this DataFrame.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, 3, 1],
    "b" => ["x", "y", "z", "x"]
  }
)
df.is_unique
# =>
# shape: (4,)
# Series: '' [bool]
# [
#         false
#         true
#         true
#         false
# ]

Returns:



3610
3611
3612
 
# File 'lib/polars/data_frame.rb', line 3610

def is_unique
  Utils.wrap_s(_df.is_unique)
end

#item ⇒ Object

Return the dataframe as a scalar.

Equivalent to df[0,0], with a check that the shape is (1,1).

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3], "b" => [4, 5, 6]})
result = df.select((Polars.col("a") * Polars.col("b")).sum)
result.item
# => 32

Returns:



721
722
723
724
725
726
 
# File 'lib/polars/data_frame.rb', line 721

def item
  if shape != [1, 1]
    raise ArgumentError, "Can only call .item if the dataframe is of shape (1,1), dataframe is of shape #{shape}"
  end
  self[0, 0]
end

#iter_rows(named: false, buffer_size: 500, &block) ⇒ Object

Returns an iterator over the DataFrame of rows of Ruby-native values.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 3, 5],
    "b" => [2, 4, 6]
  }
)
df.iter_rows.map { |row| row[0] }
# => [1, 3, 5]
df.iter_rows(named: true).map { |row| row["b"] }
# => [2, 4, 6]

Parameters:

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

    Return hashes instead of arrays. The hashes are a mapping of column name to row value. This is more expensive than returning an array, but allows for accessing values by column name.

  • buffer_size (Integer) (defaults to: 500) —

    Determines the number of rows that are buffered internally while iterating over the data; you should only modify this in very specific cases where the default value is determined not to be a good fit to your access pattern, as the speedup from using the buffer is significant (~2-4x). Setting this value to zero disables row buffering.

Returns:



4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
 
# File 'lib/polars/data_frame.rb', line 4624

def iter_rows(named: false, buffer_size: 500, &block)
  return to_enum(:iter_rows, named: named, buffer_size: buffer_size) unless block_given?

  # load into the local namespace for a modest performance boost in the hot loops
  columns = self.columns

  # note: buffering rows results in a 2-4x speedup over individual calls
  # to ".row(i)", so it should only be disabled in extremely specific cases.
  if buffer_size
    offset = 0
    while offset < height
      zerocopy_slice = slice(offset, buffer_size)
      rows_chunk = zerocopy_slice.rows(named: false)
      if named
        rows_chunk.each do |row|
          yield columns.zip(row).to_h
        end
      else
        rows_chunk.each(&block)
      end
      offset += buffer_size
    end
  elsif named
    height.times do |i|
      yield columns.zip(row(i)).to_h
    end
  else
    height.times do |i|
      yield row(i)
    end
  end
end

#join(other, left_on: nil, right_on: nil, on: nil, how: "inner", suffix: "_right", join_nulls: false) ⇒ DataFrame

Join in SQL-like fashion.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6.0, 7.0, 8.0],
    "ham" => ["a", "b", "c"]
  }
)
other_df = Polars::DataFrame.new(
  {
    "apple" => ["x", "y", "z"],
    "ham" => ["a", "b", "d"]
  }
)
df.join(other_df, on: "ham")
# =>
# shape: (2, 4)
# ┌─────┬─────┬─────┬───────┐
# │ foo ┆ bar ┆ ham ┆ apple │
# │ --- ┆ --- ┆ --- ┆ ---   │
# │ i64 ┆ f64 ┆ str ┆ str   │
# ╞═════╪═════╪═════╪═══════╡
# │ 1   ┆ 6.0 ┆ a   ┆ x     │
# │ 2   ┆ 7.0 ┆ b   ┆ y     │
# └─────┴─────┴─────┴───────┘
df.join(other_df, on: "ham", how: "outer")
# =>
# shape: (4, 5)
# ┌──────┬──────┬──────┬───────┬───────────┐
# │ foo  ┆ bar  ┆ ham  ┆ apple ┆ ham_right │
# │ ---  ┆ ---  ┆ ---  ┆ ---   ┆ ---       │
# │ i64  ┆ f64  ┆ str  ┆ str   ┆ str       │
# ╞══════╪══════╪══════╪═══════╪═══════════╡
# │ 1    ┆ 6.0  ┆ a    ┆ x     ┆ a         │
# │ 2    ┆ 7.0  ┆ b    ┆ y     ┆ b         │
# │ null ┆ null ┆ null ┆ z     ┆ d         │
# │ 3    ┆ 8.0  ┆ c    ┆ null  ┆ null      │
# └──────┴──────┴──────┴───────┴───────────┘
df.join(other_df, on: "ham", how: "left")
# =>
# shape: (3, 4)
# ┌─────┬─────┬─────┬───────┐
# │ foo ┆ bar ┆ ham ┆ apple │
# │ --- ┆ --- ┆ --- ┆ ---   │
# │ i64 ┆ f64 ┆ str ┆ str   │
# ╞═════╪═════╪═════╪═══════╡
# │ 1   ┆ 6.0 ┆ a   ┆ x     │
# │ 2   ┆ 7.0 ┆ b   ┆ y     │
# │ 3   ┆ 8.0 ┆ c   ┆ null  │
# └─────┴─────┴─────┴───────┘
df.join(other_df, on: "ham", how: "semi")
# =>
# shape: (2, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ bar ┆ ham │
# │ --- ┆ --- ┆ --- │
# │ i64 ┆ f64 ┆ str │
# ╞═════╪═════╪═════╡
# │ 1   ┆ 6.0 ┆ a   │
# │ 2   ┆ 7.0 ┆ b   │
# └─────┴─────┴─────┘
df.join(other_df, on: "ham", how: "anti")
# =>
# shape: (1, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ bar ┆ ham │
# │ --- ┆ --- ┆ --- │
# │ i64 ┆ f64 ┆ str │
# ╞═════╪═════╪═════╡
# │ 3   ┆ 8.0 ┆ c   │
# └─────┴─────┴─────┘

Parameters:

  • other (DataFrame) —

    DataFrame to join with.

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

    Name(s) of the left join column(s).

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

    Name(s) of the right join column(s).

  • on (Object) (defaults to: nil) —

    Name(s) of the join columns in both DataFrames.

  • how ("inner", "left", "outer", "semi", "anti", "cross") (defaults to: "inner") —

    Join strategy.

  • suffix (String) (defaults to: "_right") —

    Suffix to append to columns with a duplicate name.

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

    Join on null values. By default null values will never produce matches.

Returns:



2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
 
# File 'lib/polars/data_frame.rb', line 2521

def join(other, left_on: nil, right_on: nil, on: nil, how: "inner", suffix: "_right", join_nulls: false)
  lazy
    .join(
      other.lazy,
      left_on: left_on,
      right_on: right_on,
      on: on,
      how: how,
      suffix: suffix,
      join_nulls: join_nulls
    )
    .collect(no_optimization: true)
end

#join_asof(other, left_on: nil, right_on: nil, on: nil, by_left: nil, by_right: nil, by: nil, strategy: "backward", suffix: "_right", tolerance: nil, allow_parallel: true, force_parallel: false) ⇒ DataFrame

Perform an asof join.

This is similar to a left-join except that we match on nearest key rather than equal keys.

Both DataFrames must be sorted by the asof_join key.

For each row in the left DataFrame:

  • A "backward" search selects the last row in the right DataFrame whose 'on' key is less than or equal to the left's key.
  • A "forward" search selects the first row in the right DataFrame whose 'on' key is greater than or equal to the left's key.

The default is "backward".

Examples:

gdp = Polars::DataFrame.new(
  {
    "date" => [
      DateTime.new(2016, 1, 1),
      DateTime.new(2017, 1, 1),
      DateTime.new(2018, 1, 1),
      DateTime.new(2019, 1, 1),
    ],  # note record date: Jan 1st (sorted!)
    "gdp" => [4164, 4411, 4566, 4696]
  }
).set_sorted("date")
population = Polars::DataFrame.new(
  {
    "date" => [
      DateTime.new(2016, 5, 12),
      DateTime.new(2017, 5, 12),
      DateTime.new(2018, 5, 12),
      DateTime.new(2019, 5, 12),
    ],  # note record date: May 12th (sorted!)
    "population" => [82.19, 82.66, 83.12, 83.52]
  }
).set_sorted("date")
population.join_asof(
  gdp, left_on: "date", right_on: "date", strategy: "backward"
)
# =>
# shape: (4, 3)
# ┌─────────────────────┬────────────┬──────┐
# │ date                ┆ population ┆ gdp  │
# │ ---                 ┆ ---        ┆ ---  │
# │ datetime[ns]        ┆ f64        ┆ i64  │
# ╞═════════════════════╪════════════╪══════╡
# │ 2016-05-12 00:00:00 ┆ 82.19      ┆ 4164 │
# │ 2017-05-12 00:00:00 ┆ 82.66      ┆ 4411 │
# │ 2018-05-12 00:00:00 ┆ 83.12      ┆ 4566 │
# │ 2019-05-12 00:00:00 ┆ 83.52      ┆ 4696 │
# └─────────────────────┴────────────┴──────┘

Parameters:

  • other (DataFrame) —

    DataFrame to join with.

  • left_on (String) (defaults to: nil) —

    Join column of the left DataFrame.

  • right_on (String) (defaults to: nil) —

    Join column of the right DataFrame.

  • on (String) (defaults to: nil) —

    Join column of both DataFrames. If set, left_on and right_on should be None.

  • by (Object) (defaults to: nil) —

    join on these columns before doing asof join

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

    join on these columns before doing asof join

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

    join on these columns before doing asof join

  • strategy ("backward", "forward") (defaults to: "backward") —

    Join strategy.

  • suffix (String) (defaults to: "_right") —

    Suffix to append to columns with a duplicate name.

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

    Numeric tolerance. By setting this the join will only be done if the near keys are within this distance. If an asof join is done on columns of dtype "Date", "Datetime", "Duration" or "Time" you use 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)

    Or combine them: "3d12h4m25s" # 3 days, 12 hours, 4 minutes, and 25 seconds

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

    Allow the physical plan to optionally evaluate the computation of both DataFrames up to the join in parallel.

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

    Force the physical plan to evaluate the computation of both DataFrames up to the join in parallel.

Returns:



2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
 
# File 'lib/polars/data_frame.rb', line 2391

def join_asof(
  other,
  left_on: nil,
  right_on: nil,
  on: nil,
  by_left: nil,
  by_right: nil,
  by: nil,
  strategy: "backward",
  suffix: "_right",
  tolerance: nil,
  allow_parallel: true,
  force_parallel: false
)
  lazy
    .join_asof(
      other.lazy,
      left_on: left_on,
      right_on: right_on,
      on: on,
      by_left: by_left,
      by_right: by_right,
      by: by,
      strategy: strategy,
      suffix: suffix,
      tolerance: tolerance,
      allow_parallel: allow_parallel,
      force_parallel: force_parallel
    )
    .collect(no_optimization: true)
end

#lazy ⇒ LazyFrame

Start a lazy query from this point.

Returns:



3617
3618
3619
 
# File 'lib/polars/data_frame.rb', line 3617

def lazy
  wrap_ldf(_df.lazy)
end

#limit(n = 5) ⇒ DataFrame

Get the first n rows.

Alias for #head.

Examples:

df = Polars::DataFrame.new(
  {"foo" => [1, 2, 3, 4, 5, 6], "bar" => ["a", "b", "c", "d", "e", "f"]}
)
df.limit(4)
# =>
# shape: (4, 2)
# ┌─────┬─────┐
# │ foo ┆ bar │
# │ --- ┆ --- │
# │ i64 ┆ str │
# ╞═════╪═════╡
# │ 1   ┆ a   │
# │ 2   ┆ b   │
# │ 3   ┆ c   │
# │ 4   ┆ d   │
# └─────┴─────┘

Parameters:

  • n (Integer) (defaults to: 5) —

    Number of rows to return.

Returns:



1630
1631
1632
 
# File 'lib/polars/data_frame.rb', line 1630

def limit(n = 5)
  head(n)
end

#max(axis: 0) ⇒ DataFrame

Aggregate the columns of this DataFrame to their maximum value.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.max
# =>
# shape: (1, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ bar ┆ ham │
# │ --- ┆ --- ┆ --- │
# │ i64 ┆ i64 ┆ str │
# ╞═════╪═════╪═════╡
# │ 3   ┆ 8   ┆ c   │
# └─────┴─────┴─────┘

Returns:



3877
3878
3879
3880
3881
3882
3883
3884
3885
 
# File 'lib/polars/data_frame.rb', line 3877

def max(axis: 0)
  if axis == 0
    lazy.max.collect(_eager: true)
  elsif axis == 1
    Utils.wrap_s(_df.max_horizontal)
  else
    raise ArgumentError, "Axis should be 0 or 1."
  end
end

#mean(axis: 0, null_strategy: "ignore") ⇒ DataFrame

Aggregate the columns of this DataFrame to their mean value.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.mean
# =>
# shape: (1, 3)
# ┌─────┬─────┬──────┐
# │ foo ┆ bar ┆ ham  │
# │ --- ┆ --- ┆ ---  │
# │ f64 ┆ f64 ┆ str  │
# ╞═════╪═════╪══════╡
# │ 2.0 ┆ 7.0 ┆ null │
# └─────┴─────┴──────┘

Parameters:

  • axis (Integer) (defaults to: 0) —

    Either 0 or 1.

  • null_strategy ("ignore", "propagate") (defaults to: "ignore") —

    This argument is only used if axis == 1.

Returns:



3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
 
# File 'lib/polars/data_frame.rb', line 3995

def mean(axis: 0, null_strategy: "ignore")
  case axis
  when 0
    lazy.mean.collect(_eager: true)
  when 1
    Utils.wrap_s(_df.mean_horizontal(null_strategy))
  else
    raise ArgumentError, "Axis should be 0 or 1."
  end
end

#median ⇒ DataFrame

Aggregate the columns of this DataFrame to their median value.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.median
# =>
# shape: (1, 3)
# ┌─────┬─────┬──────┐
# │ foo ┆ bar ┆ ham  │
# │ --- ┆ --- ┆ ---  │
# │ f64 ┆ f64 ┆ str  │
# ╞═════╪═════╪══════╡
# │ 2.0 ┆ 7.0 ┆ null │
# └─────┴─────┴──────┘

Returns:



4110
4111
4112
 
# File 'lib/polars/data_frame.rb', line 4110

def median
  lazy.median.collect(_eager: true)
end

#melt(id_vars: nil, value_vars: nil, variable_name: nil, value_name: nil) ⇒ DataFrame

Unpivot a DataFrame from wide to long format.

Optionally leaves identifiers set.

This function is useful to massage a DataFrame into a format where one or more columns are identifier variables (id_vars), while all other columns, considered measured variables (value_vars), are "unpivoted" to the row axis, leaving just two non-identifier columns, 'variable' and 'value'.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => ["x", "y", "z"],
    "b" => [1, 3, 5],
    "c" => [2, 4, 6]
  }
)
df.melt(id_vars: "a", value_vars: ["b", "c"])
# =>
# shape: (6, 3)
# ┌─────┬──────────┬───────┐
# │ a   ┆ variable ┆ value │
# │ --- ┆ ---      ┆ ---   │
# │ str ┆ str      ┆ i64   │
# ╞═════╪══════════╪═══════╡
# │ x   ┆ b        ┆ 1     │
# │ y   ┆ b        ┆ 3     │
# │ z   ┆ b        ┆ 5     │
# │ x   ┆ c        ┆ 2     │
# │ y   ┆ c        ┆ 4     │
# │ z   ┆ c        ┆ 6     │
# └─────┴──────────┴───────┘

Parameters:

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

    Columns to use as identifier variables.

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

    Values to use as identifier variables. If value_vars is empty all columns that are not in id_vars will be used.

  • variable_name (String) (defaults to: nil) —

    Name to give to the value column. Defaults to "variable"

  • value_name (String) (defaults to: nil) —

    Name to give to the value column. Defaults to "value"

Returns:



3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
 
# File 'lib/polars/data_frame.rb', line 3241

def melt(id_vars: nil, value_vars: nil, variable_name: nil, value_name: nil)
  if value_vars.is_a?(::String)
    value_vars = [value_vars]
  end
  if id_vars.is_a?(::String)
    id_vars = [id_vars]
  end
  if value_vars.nil?
    value_vars = []
  end
  if id_vars.nil?
    id_vars = []
  end
  _from_rbdf(
    _df.melt(id_vars, value_vars, value_name, variable_name)
  )
end

#merge_sorted(other, key) ⇒ DataFrame

Take two sorted DataFrames and merge them by the sorted key.

The output of this operation will also be sorted. It is the callers responsibility that the frames are sorted by that key otherwise the output will not make sense.

The schemas of both DataFrames must be equal.

Examples:

df0 = Polars::DataFrame.new(
  {"name" => ["steve", "elise", "bob"], "age" => [42, 44, 18]}
).sort("age")
df1 = Polars::DataFrame.new(
  {"name" => ["anna", "megan", "steve", "thomas"], "age" => [21, 33, 42, 20]}
).sort("age")
df0.merge_sorted(df1, "age")
# =>
# shape: (7, 2)
# ┌────────┬─────┐
# │ name   ┆ age │
# │ ---    ┆ --- │
# │ str    ┆ i64 │
# ╞════════╪═════╡
# │ bob    ┆ 18  │
# │ thomas ┆ 20  │
# │ anna   ┆ 21  │
# │ megan  ┆ 33  │
# │ steve  ┆ 42  │
# │ steve  ┆ 42  │
# │ elise  ┆ 44  │
# └────────┴─────┘

Parameters:

  • other (DataFrame) —

    Other DataFrame that must be merged

  • key (String) —

    Key that is sorted.

Returns:



4907
4908
4909
 
# File 'lib/polars/data_frame.rb', line 4907

def merge_sorted(other, key)
  lazy.merge_sorted(other.lazy, key).collect(_eager: true)
end

#min(axis: 0) ⇒ DataFrame

Aggregate the columns of this DataFrame to their minimum value.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.min
# =>
# shape: (1, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ bar ┆ ham │
# │ --- ┆ --- ┆ --- │
# │ i64 ┆ i64 ┆ str │
# ╞═════╪═════╪═════╡
# │ 1   ┆ 6   ┆ a   │
# └─────┴─────┴─────┘

Returns:



3909
3910
3911
3912
3913
3914
3915
3916
3917
 
# File 'lib/polars/data_frame.rb', line 3909

def min(axis: 0)
  if axis == 0
    lazy.min.collect(_eager: true)
  elsif axis == 1
    Utils.wrap_s(_df.min_horizontal)
  else
    raise ArgumentError, "Axis should be 0 or 1."
  end
end

#n_chunks(strategy: "first") ⇒ Object

Get number of chunks used by the ChunkedArrays of this DataFrame.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, 3, 4],
    "b" => [0.5, 4, 10, 13],
    "c" => [true, true, false, true]
  }
)
df.n_chunks
# => 1
df.n_chunks(strategy: "all")
# => [1, 1, 1]

Parameters:

  • strategy ("first", "all") (defaults to: "first") —

    Return the number of chunks of the 'first' column, or 'all' columns in this DataFrame.

Returns:



3845
3846
3847
3848
3849
3850
3851
3852
3853
 
# File 'lib/polars/data_frame.rb', line 3845

def n_chunks(strategy: "first")
  if strategy == "first"
    _df.n_chunks
  elsif strategy == "all"
    get_columns.map(&:n_chunks)
  else
    raise ArgumentError, "Strategy: '{strategy}' not understood. Choose one of {{'first',  'all'}}"
  end
end

#n_unique(subset: nil) ⇒ DataFrame

Return the number of unique rows, or the number of unique row-subsets.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 1, 2, 3, 4, 5],
    "b" => [0.5, 0.5, 1.0, 2.0, 3.0, 3.0],
    "c" => [true, true, true, false, true, true]
  }
)
df.n_unique
# => 5

Simple columns subset

df.n_unique(subset: ["b", "c"])
# => 4

Expression subset

df.n_unique(
  subset: [
    (Polars.col("a").floordiv(2)),
    (Polars.col("c") | (Polars.col("b") >= 2))
  ]
)
# => 3

Parameters:

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

    One or more columns/expressions that define what to count; omit to return the count of unique rows.

Returns:



4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
 
# File 'lib/polars/data_frame.rb', line 4283

def n_unique(subset: nil)
  if subset.is_a?(StringIO)
    subset = [Polars.col(subset)]
  elsif subset.is_a?(Expr)
    subset = [subset]
  end

  if subset.is_a?(::Array) && subset.length == 1
    expr = Utils.expr_to_lit_or_expr(subset[0], str_to_lit: false)
  else
    struct_fields = subset.nil? ? Polars.all : subset
    expr = Polars.struct(struct_fields)
  end

  df = lazy.select(expr.n_unique).collect
  df.is_empty ? 0 : df.row(0)[0]
end

#null_count ⇒ DataFrame

Create a new DataFrame that shows the null counts per column.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, nil, 3],
    "bar" => [6, 7, nil],
    "ham" => ["a", "b", "c"]
  }
)
df.null_count
# =>
# shape: (1, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ bar ┆ ham │
# │ --- ┆ --- ┆ --- │
# │ u32 ┆ u32 ┆ u32 │
# ╞═════╪═════╪═════╡
# │ 1   ┆ 1   ┆ 0   │
# └─────┴─────┴─────┘

Returns:



4333
4334
4335
 
# File 'lib/polars/data_frame.rb', line 4333

def null_count
  _from_rbdf(_df.null_count)
end

#partition_by(groups, maintain_order: true, include_key: true, as_dict: false) ⇒ Object

Split into multiple DataFrames partitioned by groups.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => ["A", "A", "B", "B", "C"],
    "N" => [1, 2, 2, 4, 2],
    "bar" => ["k", "l", "m", "m", "l"]
  }
)
df.partition_by("foo", maintain_order: true)
# =>
# [shape: (2, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ N   ┆ bar │
# │ --- ┆ --- ┆ --- │
# │ str ┆ i64 ┆ str │
# ╞═════╪═════╪═════╡
# │ A   ┆ 1   ┆ k   │
# │ A   ┆ 2   ┆ l   │
# └─────┴─────┴─────┘, shape: (2, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ N   ┆ bar │
# │ --- ┆ --- ┆ --- │
# │ str ┆ i64 ┆ str │
# ╞═════╪═════╪═════╡
# │ B   ┆ 2   ┆ m   │
# │ B   ┆ 4   ┆ m   │
# └─────┴─────┴─────┘, shape: (1, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ N   ┆ bar │
# │ --- ┆ --- ┆ --- │
# │ str ┆ i64 ┆ str │
# ╞═════╪═════╪═════╡
# │ C   ┆ 2   ┆ l   │
# └─────┴─────┴─────┘]
df.partition_by("foo", maintain_order: true, as_dict: true)
# =>
# {"A"=>shape: (2, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ N   ┆ bar │
# │ --- ┆ --- ┆ --- │
# │ str ┆ i64 ┆ str │
# ╞═════╪═════╪═════╡
# │ A   ┆ 1   ┆ k   │
# │ A   ┆ 2   ┆ l   │
# └─────┴─────┴─────┘, "B"=>shape: (2, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ N   ┆ bar │
# │ --- ┆ --- ┆ --- │
# │ str ┆ i64 ┆ str │
# ╞═════╪═════╪═════╡
# │ B   ┆ 2   ┆ m   │
# │ B   ┆ 4   ┆ m   │
# └─────┴─────┴─────┘, "C"=>shape: (1, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ N   ┆ bar │
# │ --- ┆ --- ┆ --- │
# │ str ┆ i64 ┆ str │
# ╞═════╪═════╪═════╡
# │ C   ┆ 2   ┆ l   │
# └─────┴─────┴─────┘}

Parameters:

  • groups (Object) —

    Groups to partition by.

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

    Keep predictable output order. This is slower as it requires an extra sort operation.

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

    If true, return the partitions in a dictionary keyed by the distinct group values instead of a list.

Returns:



3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
 
# File 'lib/polars/data_frame.rb', line 3458

def partition_by(groups, maintain_order: true, include_key: true, as_dict: false)
  if groups.is_a?(::String)
    groups = [groups]
  elsif !groups.is_a?(::Array)
    groups = Array(groups)
  end

  if as_dict
    out = {}
    if groups.length == 1
      _df.partition_by(groups, maintain_order, include_key).each do |df|
        df = _from_rbdf(df)
        out[df[groups][0, 0]] = df
      end
    else
      _df.partition_by(groups, maintain_order, include_key).each do |df|
        df = _from_rbdf(df)
        out[df[groups].row(0)] = df
      end
    end
    out
  else
    _df.partition_by(groups, maintain_order, include_key).map { |df| _from_rbdf(df) }
  end
end

#pipe(func, *args, **kwargs, &block) ⇒ Object

Note:

It is recommended to use LazyFrame when piping operations, in order to fully take advantage of query optimization and parallelization. See #lazy.

Offers a structured way to apply a sequence of user-defined functions (UDFs).

Examples:

cast_str_to_int = lambda do |data, col_name:|
  data.with_column(Polars.col(col_name).cast(:i64))
end

df = Polars::DataFrame.new({"a" => [1, 2, 3, 4], "b" => ["10", "20", "30", "40"]})
df.pipe(cast_str_to_int, col_name: "b")
# =>
# shape: (4, 2)
# ┌─────┬─────┐
# │ a   ┆ b   │
# │ --- ┆ --- │
# │ i64 ┆ i64 │
# ╞═════╪═════╡
# │ 1   ┆ 10  │
# │ 2   ┆ 20  │
# │ 3   ┆ 30  │
# │ 4   ┆ 40  │
# └─────┴─────┘

Parameters:

  • func (Object) —

    Callable; will receive the frame as the first parameter, followed by any given args/kwargs.

  • args (Object) —

    Arguments to pass to the UDF.

  • kwargs (Object) —

    Keyword arguments to pass to the UDF.

Returns:



1765
1766
1767
 
# File 'lib/polars/data_frame.rb', line 1765

def pipe(func, *args, **kwargs, &block)
  func.call(self, *args, **kwargs, &block)
end

#pivot(values:, index:, columns:, aggregate_fn: "first", maintain_order: true, sort_columns: false, separator: "_") ⇒ DataFrame

Create a spreadsheet-style pivot table as a DataFrame.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => ["one", "one", "one", "two", "two", "two"],
    "bar" => ["A", "B", "C", "A", "B", "C"],
    "baz" => [1, 2, 3, 4, 5, 6]
  }
)
df.pivot(values: "baz", index: "foo", columns: "bar")
# =>
# shape: (2, 4)
# ┌─────┬─────┬─────┬─────┐
# │ foo ┆ A   ┆ B   ┆ C   │
# │ --- ┆ --- ┆ --- ┆ --- │
# │ str ┆ i64 ┆ i64 ┆ i64 │
# ╞═════╪═════╪═════╪═════╡
# │ one ┆ 1   ┆ 2   ┆ 3   │
# │ two ┆ 4   ┆ 5   ┆ 6   │
# └─────┴─────┴─────┴─────┘

Parameters:

  • values (Object) —

    Column values to aggregate. Can be multiple columns if the columns arguments contains multiple columns as well

  • index (Object) —

    One or multiple keys to group by

  • columns (Object) —

    Columns whose values will be used as the header of the output DataFrame

  • aggregate_fn ("first", "sum", "max", "min", "mean", "median", "last", "count") (defaults to: "first") —

    A predefined aggregate function str or an expression.

  • maintain_order (Object) (defaults to: true) —

    Sort the grouped keys so that the output order is predictable.

  • sort_columns (Object) (defaults to: false) —

    Sort the transposed columns by name. Default is by order of discovery.

Returns:



3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
 
# File 'lib/polars/data_frame.rb', line 3135

def pivot(
  values:,
  index:,
  columns:,
  aggregate_fn: "first",
  maintain_order: true,
  sort_columns: false,
  separator: "_"
)
  if values.is_a?(::String)
    values = [values]
  end
  if index.is_a?(::String)
    index = [index]
  end
  if columns.is_a?(::String)
    columns = [columns]
  end

  if aggregate_fn.is_a?(::String)
    case aggregate_fn
    when "first"
      aggregate_expr = Polars.element.first._rbexpr
    when "sum"
      aggregate_expr = Polars.element.sum._rbexpr
    when "max"
      aggregate_expr = Polars.element.max._rbexpr
    when "min"
      aggregate_expr = Polars.element.min._rbexpr
    when "mean"
      aggregate_expr = Polars.element.mean._rbexpr
    when "median"
      aggregate_expr = Polars.element.median._rbexpr
    when "last"
      aggregate_expr = Polars.element.last._rbexpr
    when "len"
      aggregate_expr = Polars.len._rbexpr
    when "count"
      warn "`aggregate_function: \"count\"` input for `pivot` is deprecated. Use `aggregate_function: \"len\"` instead."
      aggregate_expr = Polars.len._rbexpr
    else
      raise ArgumentError, "Argument aggregate fn: '#{aggregate_fn}' was not expected."
    end
  elsif aggregate_fn.nil?
    aggregate_expr = nil
  else
    aggregate_expr = aggregate_function._rbexpr
  end

  _from_rbdf(
    _df.pivot_expr(
      index,
      columns,
      values,
      maintain_order,
      sort_columns,
      aggregate_expr,
      separator
    )
  )
end

#plot(x = nil, y = nil, type: nil, group: nil, stacked: nil) ⇒ Vega::LiteChart Originally defined in module Plot

Plot data.

Returns:

  • (Vega::LiteChart)

Raises:

  • (ArgumentError)

#product ⇒ DataFrame

Aggregate the columns of this DataFrame to their product values.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, 3],
    "b" => [0.5, 4, 10],
    "c" => [true, true, false]
  }
)
df.product
# =>
# shape: (1, 3)
# ┌─────┬──────┬─────┐
# │ a   ┆ b    ┆ c   │
# │ --- ┆ ---  ┆ --- │
# │ i64 ┆ f64  ┆ i64 │
# ╞═════╪══════╪═════╡
# │ 6   ┆ 20.0 ┆ 0   │
# └─────┴──────┴─────┘

Returns:



4136
4137
4138
 
# File 'lib/polars/data_frame.rb', line 4136

def product
  select(Polars.all.product)
end

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

Aggregate the columns of this DataFrame to their quantile value.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.quantile(0.5, interpolation: "nearest")
# =>
# shape: (1, 3)
# ┌─────┬─────┬──────┐
# │ foo ┆ bar ┆ ham  │
# │ --- ┆ --- ┆ ---  │
# │ f64 ┆ f64 ┆ str  │
# ╞═════╪═════╪══════╡
# │ 2.0 ┆ 7.0 ┆ null │
# └─────┴─────┴──────┘

Parameters:

  • quantile (Float) —

    Quantile between 0.0 and 1.0.

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

    Interpolation method.

Returns:



4167
4168
4169
 
# File 'lib/polars/data_frame.rb', line 4167

def quantile(quantile, interpolation: "nearest")
  lazy.quantile(quantile, interpolation: interpolation).collect(_eager: true)
end

#rechunk ⇒ DataFrame

This will make sure all subsequent operations have optimal and predictable performance.

Returns:



4307
4308
4309
 
# File 'lib/polars/data_frame.rb', line 4307

def rechunk
  _from_rbdf(_df.rechunk)
end

#rename(mapping) ⇒ DataFrame

Rename column names.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.rename({"foo" => "apple"})
# =>
# shape: (3, 3)
# ┌───────┬─────┬─────┐
# │ apple ┆ bar ┆ ham │
# │ ---   ┆ --- ┆ --- │
# │ i64   ┆ i64 ┆ str │
# ╞═══════╪═════╪═════╡
# │ 1     ┆ 6   ┆ a   │
# │ 2     ┆ 7   ┆ b   │
# │ 3     ┆ 8   ┆ c   │
# └───────┴─────┴─────┘

Parameters:

  • mapping (Hash) —

    Key value pairs that map from old name to new name.

Returns:



1209
1210
1211
 
# File 'lib/polars/data_frame.rb', line 1209

def rename(mapping)
  lazy.rename(mapping).collect(no_optimization: true)
end

#replace(column, new_col) ⇒ DataFrame

Replace a column by a new Series.

Examples:

df = Polars::DataFrame.new({"foo" => [1, 2, 3], "bar" => [4, 5, 6]})
s = Polars::Series.new([10, 20, 30])
df.replace("foo", s)
# =>
# shape: (3, 2)
# ┌─────┬─────┐
# │ foo ┆ bar │
# │ --- ┆ --- │
# │ i64 ┆ i64 │
# ╞═════╪═════╡
# │ 10  ┆ 4   │
# │ 20  ┆ 5   │
# │ 30  ┆ 6   │
# └─────┴─────┘

Parameters:

  • column (String) —

    Column to replace.

  • new_col (Series) —

    New column to insert.

Returns:



1563
1564
1565
1566
 
# File 'lib/polars/data_frame.rb', line 1563

def replace(column, new_col)
  _df.replace(column.to_s, new_col._s)
  self
end

#replace_column(index, series) ⇒ DataFrame Also known as: replace_at_idx

Replace a column at an index location.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
s = Polars::Series.new("apple", [10, 20, 30])
df.replace_column(0, s)
# =>
# shape: (3, 3)
# ┌───────┬─────┬─────┐
# │ apple ┆ bar ┆ ham │
# │ ---   ┆ --- ┆ --- │
# │ i64   ┆ i64 ┆ str │
# ╞═══════╪═════╪═════╡
# │ 10    ┆ 6   ┆ a   │
# │ 20    ┆ 7   ┆ b   │
# │ 30    ┆ 8   ┆ c   │
# └───────┴─────┴─────┘

Parameters:

  • index (Integer) —

    Column index.

  • series (Series) —

    Series that will replace the column.

Returns:



1429
1430
1431
1432
1433
1434
1435
 
# File 'lib/polars/data_frame.rb', line 1429

def replace_column(index, series)
  if index < 0
    index = columns.length + index
  end
  _df.replace_column(index, series._s)
  self
end

#reverse ⇒ DataFrame

Reverse the DataFrame.

Examples:

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

Returns:



1178
1179
1180
 
# File 'lib/polars/data_frame.rb', line 1178

def reverse
  select(Polars.col("*").reverse)
end

#row(index = nil, by_predicate: nil, named: false) ⇒ Object

Note:

The index and by_predicate params are mutually exclusive. Additionally, to ensure clarity, the by_predicate parameter must be supplied by keyword.

When using by_predicate it is an error condition if anything other than one row is returned; more than one row raises TooManyRowsReturned, and zero rows will raise NoRowsReturned (both inherit from RowsException).

Get a row as tuple, either by index or by predicate.

Examples:

Return the row at the given index

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.row(2)
# => [3, 8, "c"]

Get a hash instead with a mapping of column names to row values

df.row(2, named: true)
# => {"foo"=>3, "bar"=>8, "ham"=>"c"}

Return the row that matches the given predicate

df.row(by_predicate: Polars.col("ham") == "b")
# => [2, 7, "b"]

Parameters:

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

    Row index.

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

    Select the row according to a given expression/predicate.

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

    Return a hash instead of an array. The hash is a mapping of column name to row value. This is more expensive than returning an array, but allows for accessing values by column name.

Returns:



4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
 
# File 'lib/polars/data_frame.rb', line 4528

def row(index = nil, by_predicate: nil, named: false)
  if !index.nil? && !by_predicate.nil?
    raise ArgumentError, "Cannot set both 'index' and 'by_predicate'; mutually exclusive"
  elsif index.is_a?(Expr)
    raise TypeError, "Expressions should be passed to the 'by_predicate' param"
  end

  if !index.nil?
    row = _df.row_tuple(index)
    if named
      columns.zip(row).to_h
    else
      row
    end
  elsif !by_predicate.nil?
    if !by_predicate.is_a?(Expr)
      raise TypeError, "Expected by_predicate to be an expression; found #{by_predicate.class.name}"
    end
    rows = filter(by_predicate).rows
    n_rows = rows.length
    if n_rows > 1
      raise TooManyRowsReturned, "Predicate #{by_predicate} returned #{n_rows} rows"
    elsif n_rows == 0
      raise NoRowsReturned, "Predicate #{by_predicate} returned no rows"
    end
    row = rows[0]
    if named
      columns.zip(row).to_h
    else
      row
    end
  else
    raise ArgumentError, "One of 'index' or 'by_predicate' must be set"
  end
end

#rows(named: false) ⇒ Array

Convert columnar data to rows as Ruby arrays.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 3, 5],
    "b" => [2, 4, 6]
  }
)
df.rows
# => [[1, 2], [3, 4], [5, 6]]
df.rows(named: true)
# => [{"a"=>1, "b"=>2}, {"a"=>3, "b"=>4}, {"a"=>5, "b"=>6}]

Parameters:

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

    Return hashes instead of arrays. The hashes are a mapping of column name to row value. This is more expensive than returning an array, but allows for accessing values by column name.

Returns:



4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
 
# File 'lib/polars/data_frame.rb', line 4585

def rows(named: false)
  if named
    columns = self.columns
    _df.row_tuples.map do |v|
      columns.zip(v).to_h
    end
  else
    _df.row_tuples
  end
end

#sample(n: nil, frac: nil, with_replacement: false, shuffle: false, seed: nil) ⇒ DataFrame

Sample from this DataFrame.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.sample(n: 2, seed: 0)
# =>
# shape: (2, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ bar ┆ ham │
# │ --- ┆ --- ┆ --- │
# │ i64 ┆ i64 ┆ str │
# ╞═════╪═════╪═════╡
# │ 3   ┆ 8   ┆ c   │
# │ 2   ┆ 7   ┆ b   │
# └─────┴─────┴─────┘

Parameters:

  • n (Integer) (defaults to: nil) —

    Number of items to return. Cannot be used with frac. Defaults to 1 if frac is nil.

  • frac (Float) (defaults to: nil) —

    Fraction of items to return. Cannot be used with n.

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

    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 nil (default), a random seed is used.

Returns:



4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
 
# File 'lib/polars/data_frame.rb', line 4373

def sample(
  n: nil,
  frac: nil,
  with_replacement: false,
  shuffle: false,
  seed: nil
)
  if !n.nil? && !frac.nil?
    raise ArgumentError, "cannot specify both `n` and `frac`"
  end

  if n.nil? && !frac.nil?
    frac = Series.new("frac", [frac]) unless frac.is_a?(Series)

    _from_rbdf(
      _df.sample_frac(frac._s, with_replacement, shuffle, seed)
    )
  end

  if n.nil?
    n = 1
  end

  n = Series.new("", [n]) unless n.is_a?(Series)

  _from_rbdf(_df.sample_n(n._s, with_replacement, shuffle, seed))
end

#schema ⇒ Hash

Get the schema.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6.0, 7.0, 8.0],
    "ham" => ["a", "b", "c"]
  }
)
df.schema
# => {"foo"=>Polars::Int64, "bar"=>Polars::Float64, "ham"=>Polars::String}

Returns:

  • (Hash) 


433
434
435
 
# File 'lib/polars/data_frame.rb', line 433

def schema
  columns.zip(dtypes).to_h
end

#select(*exprs, **named_exprs) ⇒ DataFrame

Select columns from this DataFrame.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.select("foo")
# =>
# shape: (3, 1)
# ┌─────┐
# │ foo │
# │ --- │
# │ i64 │
# ╞═════╡
# │ 1   │
# │ 2   │
# │ 3   │
# └─────┘
df.select(["foo", "bar"])
# =>
# shape: (3, 2)
# ┌─────┬─────┐
# │ foo ┆ bar │
# │ --- ┆ --- │
# │ i64 ┆ i64 │
# ╞═════╪═════╡
# │ 1   ┆ 6   │
# │ 2   ┆ 7   │
# │ 3   ┆ 8   │
# └─────┴─────┘
df.select(Polars.col("foo") + 1)
# =>
# shape: (3, 1)
# ┌─────┐
# │ foo │
# │ --- │
# │ i64 │
# ╞═════╡
# │ 2   │
# │ 3   │
# │ 4   │
# └─────┘
df.select([Polars.col("foo") + 1, Polars.col("bar") + 1])
# =>
# shape: (3, 2)
# ┌─────┬─────┐
# │ foo ┆ bar │
# │ --- ┆ --- │
# │ i64 ┆ i64 │
# ╞═════╪═════╡
# │ 2   ┆ 7   │
# │ 3   ┆ 8   │
# │ 4   ┆ 9   │
# └─────┴─────┘
df.select(Polars.when(Polars.col("foo") > 2).then(10).otherwise(0))
# =>
# shape: (3, 1)
# ┌─────────┐
# │ literal │
# │ ---     │
# │ i64     │
# ╞═════════╡
# │ 0       │
# │ 0       │
# │ 10      │
# └─────────┘

Parameters:

  • exprs (Array) —

    Column(s) to select, specified as positional arguments. Accepts expression input. Strings are parsed as column names, other non-expression inputs are parsed as literals.

  • named_exprs (Hash) —

    Additional columns to select, specified as keyword arguments. The columns will be renamed to the keyword used.

Returns:



3709
3710
3711
 
# File 'lib/polars/data_frame.rb', line 3709

def select(*exprs, **named_exprs)
  lazy.select(*exprs, **named_exprs).collect(_eager: true)
end

#set_sorted(column, *more_columns, descending: false) ⇒ DataFrame

Indicate that one or multiple columns are sorted.

Parameters:

  • column (Object) —

    Columns that are sorted

  • more_columns (Object) —

    Additional columns that are sorted, specified as positional arguments.

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

    Whether the columns are sorted in descending order.

Returns:



4921
4922
4923
4924
4925
4926
4927
4928
4929
 
# File 'lib/polars/data_frame.rb', line 4921

def set_sorted(
  column,
  *more_columns,
  descending: false
)
  lazy
    .set_sorted(column, *more_columns, descending: descending)
    .collect(no_optimization: true)
end

#shape ⇒ Array

Get the shape of the DataFrame.

Examples:

df = Polars::DataFrame.new({"foo" => [1, 2, 3, 4, 5]})
df.shape
# => [5, 1]

Returns:



319
320
321
 
# File 'lib/polars/data_frame.rb', line 319

def shape
  _df.shape
end

#shift(n, fill_value: nil) ⇒ DataFrame

Shift values by the given period.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.shift(1)
# =>
# shape: (3, 3)
# ┌──────┬──────┬──────┐
# │ foo  ┆ bar  ┆ ham  │
# │ ---  ┆ ---  ┆ ---  │
# │ i64  ┆ i64  ┆ str  │
# ╞══════╪══════╪══════╡
# │ null ┆ null ┆ null │
# │ 1    ┆ 6    ┆ a    │
# │ 2    ┆ 7    ┆ b    │
# └──────┴──────┴──────┘
df.shift(-1)
# =>
# shape: (3, 3)
# ┌──────┬──────┬──────┐
# │ foo  ┆ bar  ┆ ham  │
# │ ---  ┆ ---  ┆ ---  │
# │ i64  ┆ i64  ┆ str  │
# ╞══════╪══════╪══════╡
# │ 2    ┆ 7    ┆ b    │
# │ 3    ┆ 8    ┆ c    │
# │ null ┆ null ┆ null │
# └──────┴──────┴──────┘

Parameters:

  • n (Integer) —

    Number of places to shift (may be negative).

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

    Fill the resulting null values with this value.

Returns:



3527
3528
3529
 
# File 'lib/polars/data_frame.rb', line 3527

def shift(n, fill_value: nil)
  lazy.shift(n, fill_value: fill_value).collect(_eager: true)
end

#shift_and_fill(periods, fill_value) ⇒ DataFrame

Shift the values by a given period and fill the resulting null values.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.shift_and_fill(1, 0)
# =>
# shape: (3, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ bar ┆ ham │
# │ --- ┆ --- ┆ --- │
# │ i64 ┆ i64 ┆ str │
# ╞═════╪═════╪═════╡
# │ 0   ┆ 0   ┆ 0   │
# │ 1   ┆ 6   ┆ a   │
# │ 2   ┆ 7   ┆ b   │
# └─────┴─────┴─────┘

Parameters:

  • periods (Integer) —

    Number of places to shift (may be negative).

  • fill_value (Object) —

    fill nil values with this value.

Returns:



3560
3561
3562
 
# File 'lib/polars/data_frame.rb', line 3560

def shift_and_fill(periods, fill_value)
  shift(periods, fill_value: fill_value)
end

#shrink_to_fit(in_place: false) ⇒ DataFrame

Shrink DataFrame memory usage.

Shrinks to fit the exact capacity needed to hold the data.

Returns:



4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
 
# File 'lib/polars/data_frame.rb', line 4680

def shrink_to_fit(in_place: false)
  if in_place
    _df.shrink_to_fit
    self
  else
    df = clone
    df._df.shrink_to_fit
    df
  end
end

#slice(offset, length = nil) ⇒ DataFrame

Get a slice of this DataFrame.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6.0, 7.0, 8.0],
    "ham" => ["a", "b", "c"]
  }
)
df.slice(1, 2)
# =>
# shape: (2, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ bar ┆ ham │
# │ --- ┆ --- ┆ --- │
# │ i64 ┆ f64 ┆ str │
# ╞═════╪═════╪═════╡
# │ 2   ┆ 7.0 ┆ b   │
# │ 3   ┆ 8.0 ┆ c   │
# └─────┴─────┴─────┘

Parameters:

  • offset (Integer) —

    Start index. Negative indexing is supported.

  • length (Integer, nil) (defaults to: nil) —

    Length of the slice. If set to nil, all rows starting at the offset will be selected.

Returns:



1597
1598
1599
1600
1601
1602
 
# File 'lib/polars/data_frame.rb', line 1597

def slice(offset, length = nil)
  if !length.nil? && length < 0
    length = height - offset + length
  end
  _from_rbdf(_df.slice(offset, length))
end

#sort(by, reverse: false, nulls_last: false) ⇒ DataFrame

Sort the DataFrame by column.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6.0, 7.0, 8.0],
    "ham" => ["a", "b", "c"]
  }
)
df.sort("foo", reverse: true)
# =>
# shape: (3, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ bar ┆ ham │
# │ --- ┆ --- ┆ --- │
# │ i64 ┆ f64 ┆ str │
# ╞═════╪═════╪═════╡
# │ 3   ┆ 8.0 ┆ c   │
# │ 2   ┆ 7.0 ┆ b   │
# │ 1   ┆ 6.0 ┆ a   │
# └─────┴─────┴─────┘

Sort by multiple columns.

df.sort(
  [Polars.col("foo"), Polars.col("bar")**2],
  reverse: [true, false]
)
# =>
# shape: (3, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ bar ┆ ham │
# │ --- ┆ --- ┆ --- │
# │ i64 ┆ f64 ┆ str │
# ╞═════╪═════╪═════╡
# │ 3   ┆ 8.0 ┆ c   │
# │ 2   ┆ 7.0 ┆ b   │
# │ 1   ┆ 6.0 ┆ a   │
# └─────┴─────┴─────┘

Parameters:

  • by (String) —

    By which column to sort.

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

    Reverse/descending sort.

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

    Place null values last. Can only be used if sorted by a single column.

Returns:



1486
1487
1488
1489
1490
 
# File 'lib/polars/data_frame.rb', line 1486

def sort(by, reverse: false, nulls_last: false)
  lazy
    .sort(by, reverse: reverse, nulls_last: nulls_last)
    .collect(no_optimization: true)
end

#sort!(by, reverse: false, nulls_last: false) ⇒ DataFrame

Sort the DataFrame by column in-place.

Parameters:

  • by (String) —

    By which column to sort.

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

    Reverse/descending sort.

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

    Place null values last. Can only be used if sorted by a single column.

Returns:



1502
1503
1504
 
# File 'lib/polars/data_frame.rb', line 1502

def sort!(by, reverse: false, nulls_last: false)
  self._df = sort(by, reverse: reverse, nulls_last: nulls_last)._df
end

#std(ddof: 1) ⇒ DataFrame

Aggregate the columns of this DataFrame to their standard deviation value.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.std
# =>
# shape: (1, 3)
# ┌─────┬─────┬──────┐
# │ foo ┆ bar ┆ ham  │
# │ --- ┆ --- ┆ ---  │
# │ f64 ┆ f64 ┆ str  │
# ╞═════╪═════╪══════╡
# │ 1.0 ┆ 1.0 ┆ null │
# └─────┴─────┴──────┘
df.std(ddof: 0)
# =>
# shape: (1, 3)
# ┌──────────┬──────────┬──────┐
# │ foo      ┆ bar      ┆ ham  │
# │ ---      ┆ ---      ┆ ---  │
# │ f64      ┆ f64      ┆ str  │
# ╞══════════╪══════════╪══════╡
# │ 0.816497 ┆ 0.816497 ┆ null │
# └──────────┴──────────┴──────┘

Parameters:

  • ddof (Integer) (defaults to: 1) —

    Degrees of freedom

Returns:



4043
4044
4045
 
# File 'lib/polars/data_frame.rb', line 4043

def std(ddof: 1)
  lazy.std(ddof: ddof).collect(_eager: true)
end

#sum(axis: 0, null_strategy: "ignore") ⇒ DataFrame

Aggregate the columns of this DataFrame to their sum value.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"],
  }
)
df.sum
# =>
# shape: (1, 3)
# ┌─────┬─────┬──────┐
# │ foo ┆ bar ┆ ham  │
# │ --- ┆ --- ┆ ---  │
# │ i64 ┆ i64 ┆ str  │
# ╞═════╪═════╪══════╡
# │ 6   ┆ 21  ┆ null │
# └─────┴─────┴──────┘
df.sum(axis: 1)
# =>
# shape: (3,)
# Series: 'foo' [str]
# [
#         "16a"
#         "27b"
#         "38c"
# ]

Parameters:

  • axis (Integer) (defaults to: 0) —

    Either 0 or 1.

  • null_strategy ("ignore", "propagate") (defaults to: "ignore") —

    This argument is only used if axis == 1.

Returns:



3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
 
# File 'lib/polars/data_frame.rb', line 3957

def sum(axis: 0, null_strategy: "ignore")
  case axis
  when 0
    lazy.sum.collect(_eager: true)
  when 1
    Utils.wrap_s(_df.sum_horizontal(null_strategy))
  else
    raise ArgumentError, "Axis should be 0 or 1."
  end
end

#tail(n = 5) ⇒ DataFrame

Get the last n rows.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3, 4, 5],
    "bar" => [6, 7, 8, 9, 10],
    "ham" => ["a", "b", "c", "d", "e"]
  }
)
df.tail(3)
# =>
# shape: (3, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ bar ┆ ham │
# │ --- ┆ --- ┆ --- │
# │ i64 ┆ i64 ┆ str │
# ╞═════╪═════╪═════╡
# │ 3   ┆ 8   ┆ c   │
# │ 4   ┆ 9   ┆ d   │
# │ 5   ┆ 10  ┆ e   │
# └─────┴─────┴─────┘

Parameters:

  • n (Integer) (defaults to: 5) —

    Number of rows to return.

Returns:



1692
1693
1694
 
# File 'lib/polars/data_frame.rb', line 1692

def tail(n = 5)
  _from_rbdf(_df.tail(n))
end

#to_a ⇒ Array

Returns an array representing the DataFrame

Returns:



550
551
552
 
# File 'lib/polars/data_frame.rb', line 550

def to_a
  rows(named: true)
end

#to_csv(**options) ⇒ String

Write to comma-separated values (CSV) string.

Returns:



962
963
964
 
# File 'lib/polars/data_frame.rb', line 962

def to_csv(**options)
  write_csv(**options)
end

#to_dummies(columns: nil, separator: "_", drop_first: false) ⇒ DataFrame

Get one hot encoded dummy variables.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2],
    "bar" => [3, 4],
    "ham" => ["a", "b"]
  }
)
df.to_dummies
# =>
# shape: (2, 6)
# ┌───────┬───────┬───────┬───────┬───────┬───────┐
# │ foo_1 ┆ foo_2 ┆ bar_3 ┆ bar_4 ┆ ham_a ┆ ham_b │
# │ ---   ┆ ---   ┆ ---   ┆ ---   ┆ ---   ┆ ---   │
# │ u8    ┆ u8    ┆ u8    ┆ u8    ┆ u8    ┆ u8    │
# ╞═══════╪═══════╪═══════╪═══════╪═══════╪═══════╡
# │ 1     ┆ 0     ┆ 1     ┆ 0     ┆ 1     ┆ 0     │
# │ 0     ┆ 1     ┆ 0     ┆ 1     ┆ 0     ┆ 1     │
# └───────┴───────┴───────┴───────┴───────┴───────┘

Parameters:

  • columns (defaults to: nil) —

    A subset of columns to convert to dummy variables. nil means "all columns".

Returns:



4198
4199
4200
4201
4202
4203
 
# File 'lib/polars/data_frame.rb', line 4198

def to_dummies(columns: nil, separator: "_", drop_first: false)
  if columns.is_a?(::String)
    columns = [columns]
  end
  _from_rbdf(_df.to_dummies(columns, separator, drop_first))
end

#to_h(as_series: true) ⇒ Hash

Convert DataFrame to a hash mapping column name to values.

Returns:

  • (Hash) 


733
734
735
736
737
738
739
 
# File 'lib/polars/data_frame.rb', line 733

def to_h(as_series: true)
  if as_series
    get_columns.to_h { |s| [s.name, s] }
  else
    get_columns.to_h { |s| [s.name, s.to_a] }
  end
end

#to_hashes ⇒ Array

Convert every row to a dictionary.

Note that this is slow.

Examples:

df = Polars::DataFrame.new({"foo" => [1, 2, 3], "bar" => [4, 5, 6]})
df.to_hashes
# =>
# [{"foo"=>1, "bar"=>4}, {"foo"=>2, "bar"=>5}, {"foo"=>3, "bar"=>6}]

Returns:



752
753
754
755
756
757
758
759
 
# File 'lib/polars/data_frame.rb', line 752

def to_hashes
  rbdf = _df
  names = columns

  height.times.map do |i|
    names.zip(rbdf.row_tuple(i)).to_h
  end
end

#to_numo ⇒ Numo::NArray

Convert DataFrame to a 2D Numo array.

This operation clones data.

Examples:

df = Polars::DataFrame.new(
  {"foo" => [1, 2, 3], "bar" => [6, 7, 8], "ham" => ["a", "b", "c"]}
)
df.to_numo.class
# => Numo::RObject

Returns:

  • (Numo::NArray) 


773
774
775
776
777
778
779
780
 
# File 'lib/polars/data_frame.rb', line 773

def to_numo
  out = _df.to_numo
  if out.nil?
    Numo::NArray.vstack(width.times.map { |i| to_series(i).to_numo }).transpose
  else
    out
  end
end

#to_s ⇒ String Also known as: inspect

Returns a string representing the DataFrame.

Returns:



542
543
544
 
# File 'lib/polars/data_frame.rb', line 542

def to_s
  _df.to_s
end

#to_series(index = 0) ⇒ Series

Select column as Series at index location.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.to_series(1)
# =>
# shape: (3,)
# Series: 'bar' [i64]
# [
#         6
#         7
#         8
# ]

Parameters:

  • index (Integer) (defaults to: 0) —

    Location of selection.

Returns:



808
809
810
811
812
813
 
# File 'lib/polars/data_frame.rb', line 808

def to_series(index = 0)
  if index < 0
    index = columns.length + index
  end
  Utils.wrap_s(_df.select_at_idx(index))
end

#to_struct(name) ⇒ Series

Convert a DataFrame to a Series of type Struct.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, 3, 4, 5],
    "b" => ["one", "two", "three", "four", "five"]
  }
)
df.to_struct("nums")
# =>
# shape: (5,)
# Series: 'nums' [struct[2]]
# [
#         {1,"one"}
#         {2,"two"}
#         {3,"three"}
#         {4,"four"}
#         {5,"five"}
# ]

Parameters:

  • name (String) —

    Name for the struct Series

Returns:



4822
4823
4824
 
# File 'lib/polars/data_frame.rb', line 4822

def to_struct(name)
  Utils.wrap_s(_df.to_struct(name))
end

#transpose(include_header: false, header_name: "column", column_names: nil) ⇒ DataFrame

Note:

This is a very expensive operation. Perhaps you can do it differently.

Transpose a DataFrame over the diagonal.

Examples:

df = Polars::DataFrame.new({"a" => [1, 2, 3], "b" => [1, 2, 3]})
df.transpose(include_header: true)
# =>
# shape: (2, 4)
# ┌────────┬──────────┬──────────┬──────────┐
# │ column ┆ column_0 ┆ column_1 ┆ column_2 │
# │ ---    ┆ ---      ┆ ---      ┆ ---      │
# │ str    ┆ i64      ┆ i64      ┆ i64      │
# ╞════════╪══════════╪══════════╪══════════╡
# │ a      ┆ 1        ┆ 2        ┆ 3        │
# │ b      ┆ 1        ┆ 2        ┆ 3        │
# └────────┴──────────┴──────────┴──────────┘

Replace the auto-generated column names with a list

df.transpose(include_header: false, column_names: ["a", "b", "c"])
# =>
# shape: (2, 3)
# ┌─────┬─────┬─────┐
# │ a   ┆ b   ┆ c   │
# │ --- ┆ --- ┆ --- │
# │ i64 ┆ i64 ┆ i64 │
# ╞═════╪═════╪═════╡
# │ 1   ┆ 2   ┆ 3   │
# │ 1   ┆ 2   ┆ 3   │
# └─────┴─────┴─────┘

Include the header as a separate column

df.transpose(
  include_header: true, header_name: "foo", column_names: ["a", "b", "c"]
)
# =>
# shape: (2, 4)
# ┌─────┬─────┬─────┬─────┐
# │ foo ┆ a   ┆ b   ┆ c   │
# │ --- ┆ --- ┆ --- ┆ --- │
# │ str ┆ i64 ┆ i64 ┆ i64 │
# ╞═════╪═════╪═════╪═════╡
# │ a   ┆ 1   ┆ 2   ┆ 3   │
# │ b   ┆ 1   ┆ 2   ┆ 3   │
# └─────┴─────┴─────┴─────┘

Parameters:

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

    If set, the column names will be added as first column.

  • header_name (String) (defaults to: "column") —

    If include_header is set, this determines the name of the column that will be inserted.

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

    Optional generator/iterator that yields column names. Will be used to replace the columns in the DataFrame.

Returns:



1150
1151
1152
1153
 
# File 'lib/polars/data_frame.rb', line 1150

def transpose(include_header: false, header_name: "column", column_names: nil)
  keep_names_as = include_header ? header_name : nil
  _from_rbdf(_df.transpose(keep_names_as, column_names))
end

#unique(maintain_order: true, subset: nil, keep: "first") ⇒ DataFrame

Note:

Note that this fails if there is a column of type List in the DataFrame or subset.

Drop duplicate rows from this DataFrame.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 1, 2, 3, 4, 5],
    "b" => [0.5, 0.5, 1.0, 2.0, 3.0, 3.0],
    "c" => [true, true, true, false, true, true]
  }
)
df.unique
# =>
# shape: (5, 3)
# ┌─────┬─────┬───────┐
# │ a   ┆ b   ┆ c     │
# │ --- ┆ --- ┆ ---   │
# │ i64 ┆ f64 ┆ bool  │
# ╞═════╪═════╪═══════╡
# │ 1   ┆ 0.5 ┆ true  │
# │ 2   ┆ 1.0 ┆ true  │
# │ 3   ┆ 2.0 ┆ false │
# │ 4   ┆ 3.0 ┆ true  │
# │ 5   ┆ 3.0 ┆ true  │
# └─────┴─────┴───────┘

Parameters:

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

    Keep the same order as the original DataFrame. This requires more work to compute.

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

    Subset to use to compare rows.

  • keep ("first", "last") (defaults to: "first") —

    Which of the duplicate rows to keep (in conjunction with subset).

Returns:



4243
4244
4245
4246
4247
4248
4249
4250
 
# File 'lib/polars/data_frame.rb', line 4243

def unique(maintain_order: true, subset: nil, keep: "first")
  self._from_rbdf(
    lazy
      .unique(maintain_order: maintain_order, subset: subset, keep: keep)
      .collect(no_optimization: true)
      ._df
  )
end

#unnest(names) ⇒ DataFrame

Decompose a struct into its fields.

The fields will be inserted into the DataFrame on the location of the struct type.

Examples:

df = Polars::DataFrame.new(
  {
    "before" => ["foo", "bar"],
    "t_a" => [1, 2],
    "t_b" => ["a", "b"],
    "t_c" => [true, nil],
    "t_d" => [[1, 2], [3]],
    "after" => ["baz", "womp"]
  }
).select(["before", Polars.struct(Polars.col("^t_.$")).alias("t_struct"), "after"])
df.unnest("t_struct")
# =>
# shape: (2, 6)
# ┌────────┬─────┬─────┬──────┬───────────┬───────┐
# │ before ┆ t_a ┆ t_b ┆ t_c  ┆ t_d       ┆ after │
# │ ---    ┆ --- ┆ --- ┆ ---  ┆ ---       ┆ ---   │
# │ str    ┆ i64 ┆ str ┆ bool ┆ list[i64] ┆ str   │
# ╞════════╪═════╪═════╪══════╪═══════════╪═══════╡
# │ foo    ┆ 1   ┆ a   ┆ true ┆ [1, 2]    ┆ baz   │
# │ bar    ┆ 2   ┆ b   ┆ null ┆ [3]       ┆ womp  │
# └────────┴─────┴─────┴──────┴───────────┴───────┘

Parameters:

  • names (Object) —

    Names of the struct columns that will be decomposed by its fields

Returns:



4858
4859
4860
4861
4862
4863
 
# File 'lib/polars/data_frame.rb', line 4858

def unnest(names)
  if names.is_a?(::String)
    names = [names]
  end
  _from_rbdf(_df.unnest(names))
end

#unstack(step:, how: "vertical", columns: nil, fill_values: nil) ⇒ DataFrame

Note:

This functionality is experimental and may be subject to changes without it being considered a breaking change.

Unstack a long table to a wide form without doing an aggregation.

This can be much faster than a pivot, because it can skip the grouping phase.

Examples:

df = Polars::DataFrame.new(
  {
    "col1" => "A".."I",
    "col2" => Polars.arange(0, 9, eager: true)
  }
)
# =>
# shape: (9, 2)
# ┌──────┬──────┐
# │ col1 ┆ col2 │
# │ ---  ┆ ---  │
# │ str  ┆ i64  │
# ╞══════╪══════╡
# │ A    ┆ 0    │
# │ B    ┆ 1    │
# │ C    ┆ 2    │
# │ D    ┆ 3    │
# │ E    ┆ 4    │
# │ F    ┆ 5    │
# │ G    ┆ 6    │
# │ H    ┆ 7    │
# │ I    ┆ 8    │
# └──────┴──────┘
df.unstack(step: 3, how: "vertical")
# =>
# shape: (3, 6)
# ┌────────┬────────┬────────┬────────┬────────┬────────┐
# │ col1_0 ┆ col1_1 ┆ col1_2 ┆ col2_0 ┆ col2_1 ┆ col2_2 │
# │ ---    ┆ ---    ┆ ---    ┆ ---    ┆ ---    ┆ ---    │
# │ str    ┆ str    ┆ str    ┆ i64    ┆ i64    ┆ i64    │
# ╞════════╪════════╪════════╪════════╪════════╪════════╡
# │ A      ┆ D      ┆ G      ┆ 0      ┆ 3      ┆ 6      │
# │ B      ┆ E      ┆ H      ┆ 1      ┆ 4      ┆ 7      │
# │ C      ┆ F      ┆ I      ┆ 2      ┆ 5      ┆ 8      │
# └────────┴────────┴────────┴────────┴────────┴────────┘
df.unstack(step: 3, how: "horizontal")
# =>
# shape: (3, 6)
# ┌────────┬────────┬────────┬────────┬────────┬────────┐
# │ col1_0 ┆ col1_1 ┆ col1_2 ┆ col2_0 ┆ col2_1 ┆ col2_2 │
# │ ---    ┆ ---    ┆ ---    ┆ ---    ┆ ---    ┆ ---    │
# │ str    ┆ str    ┆ str    ┆ i64    ┆ i64    ┆ i64    │
# ╞════════╪════════╪════════╪════════╪════════╪════════╡
# │ A      ┆ B      ┆ C      ┆ 0      ┆ 1      ┆ 2      │
# │ D      ┆ E      ┆ F      ┆ 3      ┆ 4      ┆ 5      │
# │ G      ┆ H      ┆ I      ┆ 6      ┆ 7      ┆ 8      │
# └────────┴────────┴────────┴────────┴────────┴────────┘

Parameters:

  • step —

    Integer Number of rows in the unstacked frame.

  • how ("vertical", "horizontal") (defaults to: "vertical") —

    Direction of the unstack.

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

    Column to include in the operation.

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

    Fill values that don't fit the new size with this value.

Returns:



3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
 
# File 'lib/polars/data_frame.rb', line 3330

def unstack(step:, how: "vertical", columns: nil, fill_values: nil)
  if !columns.nil?
    df = select(columns)
  else
    df = self
  end

  height = df.height
  if how == "vertical"
    n_rows = step
    n_cols = (height / n_rows.to_f).ceil
  else
    n_cols = step
    n_rows = (height / n_cols.to_f).ceil
  end

  n_fill = n_cols * n_rows - height

  if n_fill > 0
    if !fill_values.is_a?(::Array)
      fill_values = [fill_values] * df.width
    end

    df = df.select(
      df.get_columns.zip(fill_values).map do |s, next_fill|
        s.extend_constant(next_fill, n_fill)
      end
    )
  end

  if how == "horizontal"
    df = (
      df.with_column(
        (Polars.arange(0, n_cols * n_rows, eager: true) % n_cols).alias(
          "__sort_order"
        )
      )
      .sort("__sort_order")
      .drop("__sort_order")
    )
  end

  zfill_val = Math.log10(n_cols).floor + 1
  slices =
    df.get_columns.flat_map do |s|
      n_cols.times.map do |slice_nbr|
        s.slice(slice_nbr * n_rows, n_rows).alias("%s_%0#{zfill_val}d" % [s.name, slice_nbr])
      end
    end

  _from_rbdf(DataFrame.new(slices)._df)
end

#upsample(time_column:, every:, offset: nil, by: nil, maintain_order: false) ⇒ DataFrame

Upsample a DataFrame at a regular frequency.

The every and offset arguments are created with 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)

Or combine them: "3d12h4m25s" # 3 days, 12 hours, 4 minutes, and 25 seconds

Examples:

Upsample a DataFrame by a certain interval.

df = Polars::DataFrame.new(
  {
    "time" => [
      DateTime.new(2021, 2, 1),
      DateTime.new(2021, 4, 1),
      DateTime.new(2021, 5, 1),
      DateTime.new(2021, 6, 1)
    ],
    "groups" => ["A", "B", "A", "B"],
    "values" => [0, 1, 2, 3]
  }
).set_sorted("time")
df.upsample(
  time_column: "time", every: "1mo", by: "groups", maintain_order: true
).select(Polars.all.forward_fill)
# =>
# shape: (7, 3)
# ┌─────────────────────┬────────┬────────┐
# │ time                ┆ groups ┆ values │
# │ ---                 ┆ ---    ┆ ---    │
# │ datetime[ns]        ┆ str    ┆ i64    │
# ╞═════════════════════╪════════╪════════╡
# │ 2021-02-01 00:00:00 ┆ A      ┆ 0      │
# │ 2021-03-01 00:00:00 ┆ A      ┆ 0      │
# │ 2021-04-01 00:00:00 ┆ A      ┆ 0      │
# │ 2021-05-01 00:00:00 ┆ A      ┆ 2      │
# │ 2021-04-01 00:00:00 ┆ B      ┆ 1      │
# │ 2021-05-01 00:00:00 ┆ B      ┆ 1      │
# │ 2021-06-01 00:00:00 ┆ B      ┆ 3      │
# └─────────────────────┴────────┴────────┘

Parameters:

  • time_column (Object) —

    time column will be used to determine a date_range. Note that this column has to be sorted for the output to make sense.

  • every (String) —

    interval will start 'every' duration

  • offset (String) (defaults to: nil) —

    change the start of the date_range by this offset.

  • by (Object) (defaults to: nil) —

    First group by these columns and then upsample for every group

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

    Keep the ordering predictable. This is slower.

Returns:



2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
 
# File 'lib/polars/data_frame.rb', line 2265

def upsample(
  time_column:,
  every:,
  offset: nil,
  by: nil,
  maintain_order: false
)
  if by.nil?
    by = []
  end
  if by.is_a?(::String)
    by = [by]
  end
  if offset.nil?
    offset = "0ns"
  end

  every = Utils._timedelta_to_pl_duration(every)
  offset = Utils._timedelta_to_pl_duration(offset)

  _from_rbdf(
    _df.upsample(by, time_column, every, offset, maintain_order)
  )
end

#var(ddof: 1) ⇒ DataFrame

Aggregate the columns of this DataFrame to their variance value.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3],
    "bar" => [6, 7, 8],
    "ham" => ["a", "b", "c"]
  }
)
df.var
# =>
# shape: (1, 3)
# ┌─────┬─────┬──────┐
# │ foo ┆ bar ┆ ham  │
# │ --- ┆ --- ┆ ---  │
# │ f64 ┆ f64 ┆ str  │
# ╞═════╪═════╪══════╡
# │ 1.0 ┆ 1.0 ┆ null │
# └─────┴─────┴──────┘
df.var(ddof: 0)
# =>
# shape: (1, 3)
# ┌──────────┬──────────┬──────┐
# │ foo      ┆ bar      ┆ ham  │
# │ ---      ┆ ---      ┆ ---  │
# │ f64      ┆ f64      ┆ str  │
# ╞══════════╪══════════╪══════╡
# │ 0.666667 ┆ 0.666667 ┆ null │
# └──────────┴──────────┴──────┘

Parameters:

  • ddof (Integer) (defaults to: 1) —

    Degrees of freedom

Returns:



4084
4085
4086
 
# File 'lib/polars/data_frame.rb', line 4084

def var(ddof: 1)
  lazy.var(ddof: ddof).collect(_eager: true)
end

#vstack(df, in_place: false) ⇒ DataFrame

Grow this DataFrame vertically by stacking a DataFrame to it.

Examples:

df1 = Polars::DataFrame.new(
  {
    "foo" => [1, 2],
    "bar" => [6, 7],
    "ham" => ["a", "b"]
  }
)
df2 = Polars::DataFrame.new(
  {
    "foo" => [3, 4],
    "bar" => [8, 9],
    "ham" => ["c", "d"]
  }
)
df1.vstack(df2)
# =>
# shape: (4, 3)
# ┌─────┬─────┬─────┐
# │ foo ┆ bar ┆ ham │
# │ --- ┆ --- ┆ --- │
# │ i64 ┆ i64 ┆ str │
# ╞═════╪═════╪═════╡
# │ 1   ┆ 6   ┆ a   │
# │ 2   ┆ 7   ┆ b   │
# │ 3   ┆ 8   ┆ c   │
# │ 4   ┆ 9   ┆ d   │
# └─────┴─────┴─────┘

Parameters:

  • df (DataFrame) —

    DataFrame to stack.

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

    Modify in place

Returns:



2729
2730
2731
2732
2733
2734
2735
2736
 
# File 'lib/polars/data_frame.rb', line 2729

def vstack(df, in_place: false)
  if in_place
    _df.vstack_mut(df._df)
    self
  else
    _from_rbdf(_df.vstack(df._df))
  end
end

#width ⇒ Integer

Get the width of the DataFrame.

Examples:

df = Polars::DataFrame.new({"foo" => [1, 2, 3, 4, 5]})
df.width
# => 1

Returns:

  • (Integer) 


346
347
348
 
# File 'lib/polars/data_frame.rb', line 346

def width
  _df.width
end

#with_column(column) ⇒ DataFrame

Return a new DataFrame with the column added or replaced.

Examples:

Added

df = Polars::DataFrame.new(
  {
    "a" => [1, 3, 5],
    "b" => [2, 4, 6]
  }
)
df.with_column((Polars.col("b") ** 2).alias("b_squared"))
# =>
# shape: (3, 3)
# ┌─────┬─────┬───────────┐
# │ a   ┆ b   ┆ b_squared │
# │ --- ┆ --- ┆ ---       │
# │ i64 ┆ i64 ┆ f64       │
# ╞═════╪═════╪═══════════╡
# │ 1   ┆ 2   ┆ 4.0       │
# │ 3   ┆ 4   ┆ 16.0      │
# │ 5   ┆ 6   ┆ 36.0      │
# └─────┴─────┴───────────┘

Replaced

df.with_column(Polars.col("a") ** 2)
# =>
# shape: (3, 2)
# ┌──────┬─────┐
# │ a    ┆ b   │
# │ ---  ┆ --- │
# │ f64  ┆ i64 │
# ╞══════╪═════╡
# │ 1.0  ┆ 2   │
# │ 9.0  ┆ 4   │
# │ 25.0 ┆ 6   │
# └──────┴─────┘

Parameters:

  • column (Object) —

    Series, where the name of the Series refers to the column in the DataFrame.

Returns:



2644
2645
2646
2647
2648
 
# File 'lib/polars/data_frame.rb', line 2644

def with_column(column)
  lazy
    .with_column(column)
    .collect(no_optimization: true, string_cache: false)
end

#with_columns(*exprs, **named_exprs) ⇒ DataFrame

Add columns to this DataFrame.

Added columns will replace existing columns with the same name.

Examples:

Pass an expression to add it as a new column.

df = Polars::DataFrame.new(
  {
    "a" => [1, 2, 3, 4],
    "b" => [0.5, 4, 10, 13],
    "c" => [true, true, false, true]
  }
)
df.with_columns((Polars.col("a") ** 2).alias("a^2"))
# =>
# shape: (4, 4)
# ┌─────┬──────┬───────┬──────┐
# │ a   ┆ b    ┆ c     ┆ a^2  │
# │ --- ┆ ---  ┆ ---   ┆ ---  │
# │ i64 ┆ f64  ┆ bool  ┆ f64  │
# ╞═════╪══════╪═══════╪══════╡
# │ 1   ┆ 0.5  ┆ true  ┆ 1.0  │
# │ 2   ┆ 4.0  ┆ true  ┆ 4.0  │
# │ 3   ┆ 10.0 ┆ false ┆ 9.0  │
# │ 4   ┆ 13.0 ┆ true  ┆ 16.0 │
# └─────┴──────┴───────┴──────┘

Added columns will replace existing columns with the same name.

df.with_columns(Polars.col("a").cast(Polars::Float64))
# =>
# shape: (4, 3)
# ┌─────┬──────┬───────┐
# │ a   ┆ b    ┆ c     │
# │ --- ┆ ---  ┆ ---   │
# │ f64 ┆ f64  ┆ bool  │
# ╞═════╪══════╪═══════╡
# │ 1.0 ┆ 0.5  ┆ true  │
# │ 2.0 ┆ 4.0  ┆ true  │
# │ 3.0 ┆ 10.0 ┆ false │
# │ 4.0 ┆ 13.0 ┆ true  │
# └─────┴──────┴───────┘

Multiple columns can be added by passing a list of expressions.

df.with_columns(
  [
    (Polars.col("a") ** 2).alias("a^2"),
    (Polars.col("b") / 2).alias("b/2"),
    (Polars.col("c").not_).alias("not c"),
  ]
)
# =>
# shape: (4, 6)
# ┌─────┬──────┬───────┬──────┬──────┬───────┐
# │ a   ┆ b    ┆ c     ┆ a^2  ┆ b/2  ┆ not c │
# │ --- ┆ ---  ┆ ---   ┆ ---  ┆ ---  ┆ ---   │
# │ i64 ┆ f64  ┆ bool  ┆ f64  ┆ f64  ┆ bool  │
# ╞═════╪══════╪═══════╪══════╪══════╪═══════╡
# │ 1   ┆ 0.5  ┆ true  ┆ 1.0  ┆ 0.25 ┆ false │
# │ 2   ┆ 4.0  ┆ true  ┆ 4.0  ┆ 2.0  ┆ false │
# │ 3   ┆ 10.0 ┆ false ┆ 9.0  ┆ 5.0  ┆ true  │
# │ 4   ┆ 13.0 ┆ true  ┆ 16.0 ┆ 6.5  ┆ false │
# └─────┴──────┴───────┴──────┴──────┴───────┘

Multiple columns also can be added using positional arguments instead of a list.

df.with_columns(
  (Polars.col("a") ** 2).alias("a^2"),
  (Polars.col("b") / 2).alias("b/2"),
  (Polars.col("c").not_).alias("not c"),
)
# =>
# shape: (4, 6)
# ┌─────┬──────┬───────┬──────┬──────┬───────┐
# │ a   ┆ b    ┆ c     ┆ a^2  ┆ b/2  ┆ not c │
# │ --- ┆ ---  ┆ ---   ┆ ---  ┆ ---  ┆ ---   │
# │ i64 ┆ f64  ┆ bool  ┆ f64  ┆ f64  ┆ bool  │
# ╞═════╪══════╪═══════╪══════╪══════╪═══════╡
# │ 1   ┆ 0.5  ┆ true  ┆ 1.0  ┆ 0.25 ┆ false │
# │ 2   ┆ 4.0  ┆ true  ┆ 4.0  ┆ 2.0  ┆ false │
# │ 3   ┆ 10.0 ┆ false ┆ 9.0  ┆ 5.0  ┆ true  │
# │ 4   ┆ 13.0 ┆ true  ┆ 16.0 ┆ 6.5  ┆ false │
# └─────┴──────┴───────┴──────┴──────┴───────┘

Use keyword arguments to easily name your expression inputs.

df.with_columns(
  ab: Polars.col("a") * Polars.col("b"),
  not_c: Polars.col("c").not_
)
# =>
# shape: (4, 5)
# ┌─────┬──────┬───────┬──────┬───────┐
# │ a   ┆ b    ┆ c     ┆ ab   ┆ not_c │
# │ --- ┆ ---  ┆ ---   ┆ ---  ┆ ---   │
# │ i64 ┆ f64  ┆ bool  ┆ f64  ┆ bool  │
# ╞═════╪══════╪═══════╪══════╪═══════╡
# │ 1   ┆ 0.5  ┆ true  ┆ 0.5  ┆ false │
# │ 2   ┆ 4.0  ┆ true  ┆ 8.0  ┆ false │
# │ 3   ┆ 10.0 ┆ false ┆ 30.0 ┆ true  │
# │ 4   ┆ 13.0 ┆ true  ┆ 52.0 ┆ false │
# └─────┴──────┴───────┴──────┴───────┘

Parameters:

  • exprs (Array) —

    Column(s) to add, specified as positional arguments. Accepts expression input. Strings are parsed as column names, other non-expression inputs are parsed as literals.

  • named_exprs (Hash) —

    Additional columns to add, specified as keyword arguments. The columns will be renamed to the keyword used.

Returns:



3821
3822
3823
 
# File 'lib/polars/data_frame.rb', line 3821

def with_columns(*exprs, **named_exprs)
  lazy.with_columns(*exprs, **named_exprs).collect(_eager: true)
end

#with_row_index(name: "row_nr", offset: 0) ⇒ DataFrame Also known as: with_row_count

Add a column at index 0 that counts the rows.

Examples:

df = Polars::DataFrame.new(
  {
    "a" => [1, 3, 5],
    "b" => [2, 4, 6]
  }
)
df.with_row_index
# =>
# shape: (3, 3)
# ┌────────┬─────┬─────┐
# │ row_nr ┆ a   ┆ b   │
# │ ---    ┆ --- ┆ --- │
# │ u32    ┆ i64 ┆ i64 │
# ╞════════╪═════╪═════╡
# │ 0      ┆ 1   ┆ 2   │
# │ 1      ┆ 3   ┆ 4   │
# │ 2      ┆ 5   ┆ 6   │
# └────────┴─────┴─────┘

Parameters:

  • name (String) (defaults to: "row_nr") —

    Name of the column to add.

  • offset (Integer) (defaults to: 0) —

    Start the row count at this offset.

Returns:



1797
1798
1799
 
# File 'lib/polars/data_frame.rb', line 1797

def with_row_index(name: "row_nr", offset: 0)
  _from_rbdf(_df.with_row_index(name, offset))
end

#write_avro(file, compression = "uncompressed") ⇒ nil

Write to Apache Avro file.

Parameters:

  • file (String) —

    File path to which the file should be written.

  • compression ("uncompressed", "snappy", "deflate") (defaults to: "uncompressed") —

    Compression method. Defaults to "uncompressed".

Returns:

  • (nil) 


974
975
976
977
978
979
980
981
982
983
 
# File 'lib/polars/data_frame.rb', line 974

def write_avro(file, compression = "uncompressed")
  if compression.nil?
    compression = "uncompressed"
  end
  if Utils.pathlike?(file)
    file = Utils.normalise_filepath(file)
  end

  _df.write_avro(file, compression)
end

#write_csv(file = nil, has_header: true, include_header: nil, sep: ",", quote: '"', batch_size: 1024, datetime_format: nil, date_format: nil, time_format: nil, float_precision: nil, null_value: nil) ⇒ String?

Write to comma-separated values (CSV) file.

Examples:

df = Polars::DataFrame.new(
  {
    "foo" => [1, 2, 3, 4, 5],
    "bar" => [6, 7, 8, 9, 10],
    "ham" => ["a", "b", "c", "d", "e"]
  }
)
df.write_csv("file.csv")

Parameters:

  • file (String, nil) (defaults to: nil) —

    File path to which the result should be written. If set to nil (default), the output is returned as a string instead.

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

    Whether to include header in the CSV output.

  • sep (String) (defaults to: ",") —

    Separate CSV fields with this symbol.

  • quote (String) (defaults to: '"') —

    Byte to use as quoting character.

  • batch_size (Integer) (defaults to: 1024) —

    Number of rows that will be processed per thread.

  • datetime_format (String, nil) (defaults to: nil) —

    A format string, with the specifiers defined by the chrono Rust crate. If no format specified, the default fractional-second precision is inferred from the maximum timeunit found in the frame's Datetime cols (if any).

  • date_format (String, nil) (defaults to: nil) —

    A format string, with the specifiers defined by the chrono Rust crate.

  • time_format (String, nil) (defaults to: nil) —

    A format string, with the specifiers defined by the chrono Rust crate.

  • float_precision (Integer, nil) (defaults to: nil) —

    Number of decimal places to write, applied to both :f32 and :f64 datatypes.

  • null_value (String, nil) (defaults to: nil) —

    A string representing null values (defaulting to the empty string).

Returns:



899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
 
# File 'lib/polars/data_frame.rb', line 899

def write_csv(
  file = nil,
  has_header: true,
  include_header: nil,
  sep: ",",
  quote: '"',
  batch_size: 1024,
  datetime_format: nil,
  date_format: nil,
  time_format: nil,
  float_precision: nil,
  null_value: nil
)
  include_header = has_header if include_header.nil?

  if sep.length > 1
    raise ArgumentError, "only single byte separator is allowed"
  elsif quote.length > 1
    raise ArgumentError, "only single byte quote char is allowed"
  elsif null_value == ""
    null_value = nil
  end

  if file.nil?
    buffer = StringIO.new
    buffer.set_encoding(Encoding::BINARY)
    _df.write_csv(
      buffer,
      include_header,
      sep.ord,
      quote.ord,
      batch_size,
      datetime_format,
      date_format,
      time_format,
      float_precision,
      null_value
    )
    return buffer.string.force_encoding(Encoding::UTF_8)
  end

  if Utils.pathlike?(file)
    file = Utils.normalise_filepath(file)
  end

  _df.write_csv(
    file,
    include_header,
    sep.ord,
    quote.ord,
    batch_size,
    datetime_format,
    date_format,
    time_format,
    float_precision,
    null_value,
  )
  nil
end

#write_ipc(file, compression: "uncompressed") ⇒ nil

Write to Arrow IPC binary stream or Feather file.

Parameters:

  • file (String) —

    File path to which the file should be written.

  • compression ("uncompressed", "lz4", "zstd") (defaults to: "uncompressed") —

    Compression method. Defaults to "uncompressed".

Returns:

  • (nil) 


993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
 
# File 'lib/polars/data_frame.rb', line 993

def write_ipc(file, compression: "uncompressed")
  return_bytes = file.nil?
  if return_bytes
    file = StringIO.new
    file.set_encoding(Encoding::BINARY)
  end
  if Utils.pathlike?(file)
    file = Utils.normalise_filepath(file)
  end

  if compression.nil?
    compression = "uncompressed"
  end

  _df.write_ipc(file, compression)
  return_bytes ? file.string : nil
end

#write_json(file, pretty: false, row_oriented: false) ⇒ nil

Serialize to JSON representation.

Parameters:

  • file (String) —

    File path to which the result should be written.

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

    Pretty serialize json.

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

    Write to row oriented json. This is slower, but more common.

Returns:

  • (nil)

See Also:



827
828
829
830
831
832
833
834
835
836
837
838
 
# File 'lib/polars/data_frame.rb', line 827

def write_json(
  file,
  pretty: false,
  row_oriented: false
)
  if Utils.pathlike?(file)
    file = Utils.normalise_filepath(file)
  end

  _df.write_json(file, pretty, row_oriented)
  nil
end

#write_ndjson(file) ⇒ nil

Serialize to newline delimited JSON representation.

Parameters:

  • file (String) —

    File path to which the result should be written.

Returns:

  • (nil) 


846
847
848
849
850
851
852
853
 
# File 'lib/polars/data_frame.rb', line 846

def write_ndjson(file)
  if Utils.pathlike?(file)
    file = Utils.normalise_filepath(file)
  end

  _df.write_ndjson(file)
  nil
end

#write_parquet(file, compression: "zstd", compression_level: nil, statistics: false, row_group_size: nil) ⇒ nil

Write to Apache Parquet file.

Parameters:

  • file (String) —

    File path to which the file should be written.

  • compression ("lz4", "uncompressed", "snappy", "gzip", "lzo", "brotli", "zstd") (defaults to: "zstd") —

    Choose "zstd" for good compression performance. Choose "lz4" for fast compression/decompression. Choose "snappy" for more backwards compatibility guarantees when you deal with older parquet readers.

  • compression_level (Integer, nil) (defaults to: nil) —

    The level of compression to use. Higher compression means smaller files on disk.

    • "gzip" : min-level: 0, max-level: 10.
    • "brotli" : min-level: 0, max-level: 11.
    • "zstd" : min-level: 1, max-level: 22.
  • statistics (Boolean) (defaults to: false) —

    Write statistics to the parquet headers. This requires extra compute.

  • row_group_size (Integer, nil) (defaults to: nil) —

    Size of the row groups in number of rows. If nil (default), the chunks of the DataFrame are used. Writing in smaller chunks may reduce memory pressure and improve writing speeds.

Returns:

  • (nil) 


1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
 
# File 'lib/polars/data_frame.rb', line 1036

def write_parquet(
  file,
  compression: "zstd",
  compression_level: nil,
  statistics: false,
  row_group_size: nil
)
  if compression.nil?
    compression = "uncompressed"
  end
  if Utils.pathlike?(file)
    file = Utils.normalise_filepath(file)
  end

  _df.write_parquet(
    file, compression, compression_level, statistics, row_group_size
  )
end