Class: Daru::DataFrame

Inherits:
Object show all
Extended by:
Gem::Deprecate
Includes:
Maths::Arithmetic::DataFrame, Maths::Statistics::DataFrame, Plotting::DataFrame::NyaplotLibrary
Defined in:
lib/daru/dataframe.rb,
lib/daru/extensions/rserve.rb,
lib/daru/extensions/which_dsl.rb

Overview

rubocop:disable Metrics/ClassLength

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Methods included from Plotting::DataFrame::NyaplotLibrary

#plot

Methods included from Maths::Statistics::DataFrame

#acf, #correlation, #count, #covariance, #cumsum, #describe, #ema, #max, #mean, #median, #min, #mode, #percent_change, #product, #range, #rolling_count, #rolling_max, #rolling_mean, #rolling_median, #rolling_min, #rolling_std, #rolling_variance, #standardize, #std, #sum, #variance_sample

Methods included from Maths::Arithmetic::DataFrame

#%, #*, #**, #+, #-, #/, #exp, #round, #sqrt

Constructor Details

#initialize(source = {}, opts = {}) ⇒ DataFrame

DataFrame basically consists of an Array of Vector objects. These objects are indexed by row and column by vectors and index Index objects.

Arguments

  • source - Source from the DataFrame is to be initialized. Can be a Hash

of names and vectors (array or Daru::Vector), an array of arrays or array of Daru::Vectors.

Options

:order - An Array/Daru::Index/Daru::MultiIndex containing the order in which Vectors should appear in the DataFrame.

:index - An Array/Daru::Index/Daru::MultiIndex containing the order in which rows of the DataFrame will be named.

:name - A name for the DataFrame.

:clone - Specify as true or false. When set to false, and Vector objects are passed for the source, the Vector objects will not duplicated when creating the DataFrame. Will have no effect if Array is passed in the source, or if the passed Daru::Vectors have different indexes. Default to true.

Usage

df = Daru::DataFrame.new
# =>
# <Daru::DataFrame(0x0)>
# Creates an empty DataFrame with no rows or columns.

df = Daru::DataFrame.new({}, order: [:a, :b])
#<Daru::DataFrame(0x2)>
  a   b
# Creates a DataFrame with no rows and columns :a and :b

df = Daru::DataFrame.new({a: [1,2,3,4], b: [6,7,8,9]}, order: [:b, :a],
  index: [:a, :b, :c, :d], name: :spider_man)

# =>
# <Daru::DataFrame:80766980 @name = spider_man @size = 4>
#             b          a
#  a          6          1
#  b          7          2
#  c          8          3
#  d          9          4

df = Daru::DataFrame.new([[1,2,3,4],[6,7,8,9]], name: :bat_man)

# =>
# #<Daru::DataFrame: bat_man (4x2)>
#             0          1
#  0          1          6
#  1          2          7
#  2          3          8
#  3          4          9

# Dataframe having Index name

df = Daru::DataFrame.new({a: [1,2,3,4], b: [6,7,8,9]}, order: [:b, :a],
  index: Daru::Index.new([:a, :b, :c, :d], name: 'idx_name'),
  name: :spider_man)

# =>
# <Daru::DataFrame:80766980 @name = spider_man @size = 4>
# idx_name            b          a
#        a          6          1
#        b          7          2
#        c          8          3
#        d          9          4

idx = Daru::Index.new [100, 99, 101, 1, 2], name: "s1"
=> #<Daru::Index(5): s1 {100, 99, 101, 1, 2}>

df = Daru::DataFrame.new({b: [11,12,13,14,15], a: [1,2,3,4,5],
  c: [11,22,33,44,55]},
  order: [:a, :b, :c],
  index: idx)
 # =>
 #<Daru::DataFrame(5x3)>
 #   s1   a   b   c
 #  100   1  11  11
 #   99   2  12  22
 #  101   3  13  33
 #    1   4  14  44
 #    2   5  15  55


343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
# File 'lib/daru/dataframe.rb', line 343

def initialize source={}, opts={} # rubocop:disable Metrics/MethodLength
  vectors, index = opts[:order], opts[:index] # FIXME: just keyword arges after Ruby 2.1
  @data = []
  @name = opts[:name]

  case source
  when ->(s) { s.empty? }
    @vectors = Index.coerce vectors
    @index   = Index.coerce index
    create_empty_vectors
  when Array
    initialize_from_array source, vectors, index, opts
  when Hash
    initialize_from_hash source, vectors, index, opts
  end

  set_size
  validate
  update
  self.plotting_library = Daru.plotting_library
end

Dynamic Method Handling

This class handles dynamic methods through the method_missing method

#method_missing(name, *args, &block) ⇒ Object



2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
# File 'lib/daru/dataframe.rb', line 2218

def method_missing(name, *args, &block)
  case
  when name =~ /(.+)\=/
    name = name[/(.+)\=/].delete('=')
    name = name.to_sym unless has_vector?(name)
    insert_or_modify_vector [name], args[0]
  when has_vector?(name)
    self[name]
  when has_vector?(name.to_s)
    self[name.to_s]
  else
    super
  end
end

Instance Attribute Details

#dataObject (readonly)

TOREMOVE



243
244
245
# File 'lib/daru/dataframe.rb', line 243

def data
  @data
end

#indexObject

The index of the rows of the DataFrame



246
247
248
# File 'lib/daru/dataframe.rb', line 246

def index
  @index
end

#nameObject (readonly)

The name of the DataFrame



249
250
251
# File 'lib/daru/dataframe.rb', line 249

def name
  @name
end

#sizeObject (readonly)

The number of rows present in the DataFrame



252
253
254
# File 'lib/daru/dataframe.rb', line 252

def size
  @size
end

#vectorsObject

The vectors (columns) index of the DataFrame



241
242
243
# File 'lib/daru/dataframe.rb', line 241

def vectors
  @vectors
end

Class Method Details

._load(data) ⇒ Object



2144
2145
2146
2147
2148
2149
2150
# File 'lib/daru/dataframe.rb', line 2144

def self._load data
  h = Marshal.load data
  Daru::DataFrame.new(h[:data],
    index: h[:index],
    order: h[:order],
    name:  h[:name])
end

.crosstab_by_assignation(rows, columns, values) ⇒ Object

Generates a new dataset, using three vectors

  • Rows

  • Columns

  • Values

For example, you have these values

x   y   v
a   a   0
a   b   1
b   a   1
b   b   0

You obtain

id  a   b
 a  0   1
 b  1   0

Useful to process outputs from databases



199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
# File 'lib/daru/dataframe.rb', line 199

def crosstab_by_assignation rows, columns, values
  raise 'Three vectors should be equal size' if
    rows.size != columns.size || rows.size!=values.size

  data = Hash.new { |h, col|
    h[col] = rows.factors.map { |r| [r, nil] }.to_h
  }
  columns.zip(rows, values).each { |c, r, v| data[c][r] = v }

  # FIXME: in fact, WITHOUT this line you'll obtain more "right"
  # data: with vectors having "rows" as an index...
  data = data.map { |c, r| [c, r.values] }.to_h
  data[:_id] = rows.factors

  DataFrame.new(data)
end

.from_activerecord(relation, *fields) ⇒ Object

Read a dataframe from AR::Relation

USE:

# When Post model is defined as:
class Post < ActiveRecord::Base
  scope :active, -> { where.not(published_at: nil) }
end

# You can load active posts into a dataframe by:
Daru::DataFrame.from_activerecord(Post.active, :title, :published_at)

Parameters:

  • relation (ActiveRecord::Relation)

    An AR::Relation object from which data is loaded

  • fields (Array)

    Field names to be loaded (optional)

Returns:

  • A dataframe containing the data loaded from the relation



100
101
102
# File 'lib/daru/dataframe.rb', line 100

def from_activerecord relation, *fields
  Daru::IO.from_activerecord relation, *fields
end

.from_csv(path, opts = {}, &block) ⇒ Object

Load data from a CSV file. Specify an optional block to grab the CSV object and pre-condition it (for example use the ‘convert` or `header_convert` methods).

Arguments

  • path - Local path / Remote URL of the file to load specified as a String.

Options

Accepts the same options as the Daru::DataFrame constructor and CSV.open() and uses those to eventually construct the resulting DataFrame.

Verbose Description

You can specify all the options to the ‘.from_csv` function that you do to the Ruby `CSV.read()` function, since this is what is used internally.

For example, if the columns in your CSV file are separated by something other that commas, you can use the ‘:col_sep` option. If you want to convert numeric values to numbers and not keep them as strings, you can use the `:converters` option and set it to `:numeric`.

The ‘.from_csv` function uses the following defaults for reading CSV files (that are passed into the `CSV.read()` function):

{
  :col_sep           => ',',
  :converters        => :numeric
}


47
48
49
# File 'lib/daru/dataframe.rb', line 47

def from_csv path, opts={}, &block
  Daru::IO.from_csv path, opts, &block
end

.from_excel(path, opts = {}, &block) ⇒ Object

Read data from an Excel file into a DataFrame.

Arguments

  • path - Path of the file to be read.

Options

*:worksheet_id - ID of the worksheet that is to be read.



60
61
62
# File 'lib/daru/dataframe.rb', line 60

def from_excel path, opts={}, &block
  Daru::IO.from_excel path, opts, &block
end

.from_html(path, fields = {}) ⇒ Object

Read the table data from a remote html file. Please note that this module works only for static table elements on a HTML page, and won’t work in cases where the data is being loaded into the HTML table by Javascript.

By default - all <th> tag elements in the first proper row are considered as the order, and all the <th> tag elements in the first column are considered as the index.

Arguments

  • path [String] - URL of the target HTML file.

  • fields [Hash] -

    :match - A String to match and choose a particular table(s) from multiple tables of a HTML page.

    :order - An Array which would act as the user-defined order, to override the parsed Daru::DataFrame.

    :index - An Array which would act as the user-defined index, to override the parsed Daru::DataFrame.

    :name - A String that manually assigns a name to the scraped Daru::DataFrame, for user’s preference.

Returns

An Array of Daru::DataFrames, with each dataframe corresponding to a HTML table on that webpage.

Usage

dfs = Daru::DataFrame.from_html("http://www.moneycontrol.com/", match: "Sun Pharma")
dfs.count
# => 4

dfs.first
#
# => <Daru::DataFrame(5x4)>
#          Company      Price     Change Value (Rs
#     0 Sun Pharma     502.60     -65.05   2,117.87
#     1   Reliance    1356.90      19.60     745.10
#     2 Tech Mahin     379.45     -49.70     650.22
#     3        ITC     315.85       6.75     621.12
#     4       HDFC    1598.85      50.95     553.91


159
160
161
# File 'lib/daru/dataframe.rb', line 159

def from_html path, fields={}
  Daru::IO.from_html path, fields
end

.from_plaintext(path, fields) ⇒ Object

Read the database from a plaintext file. For this method to work, the data should be present in a plain text file in columns. See spec/fixtures/bank2.dat for an example.

Arguments

  • path - Path of the file to be read.

  • fields - Vector names of the resulting database.

Usage

df = Daru::DataFrame.from_plaintext 'spec/fixtures/bank2.dat', [:v1,:v2,:v3,:v4,:v5,:v6]


116
117
118
# File 'lib/daru/dataframe.rb', line 116

def from_plaintext path, fields
  Daru::IO.from_plaintext path, fields
end

.from_sql(dbh, query) ⇒ Object

Read a database query and returns a Dataset

USE:

dbh = DBI.connect("DBI:Mysql:database:localhost", "user", "password")
Daru::DataFrame.from_sql(dbh, "SELECT * FROM test")

#Alternatively

require 'dbi'
Daru::DataFrame.from_sql("path/to/sqlite.db", "SELECT * FROM test")

Parameters:

  • dbh (DBI::DatabaseHandle, String)

    A DBI connection OR Path to a SQlite3 database.

  • query (String)

    The query to be executed

Returns:

  • A dataframe containing the data resulting from the query



80
81
82
# File 'lib/daru/dataframe.rb', line 80

def from_sql dbh, query
  Daru::IO.from_sql dbh, query
end

.rows(source, opts = {}) ⇒ Object

Create DataFrame by specifying rows as an Array of Arrays or Array of Daru::Vector objects.

Raises:



165
166
167
168
169
170
171
172
173
174
175
176
177
178
# File 'lib/daru/dataframe.rb', line 165

def rows source, opts={}
  raise SizeError, 'All vectors must have same length' \
    unless source.all? { |v| v.size == source.first.size }

  opts[:order] ||= guess_order(source)

  if ArrayHelper.array_of?(source, Array) || source.empty?
    DataFrame.new(source.transpose, opts)
  elsif ArrayHelper.array_of?(source, Vector)
    from_vector_rows(source, opts)
  else
    raise ArgumentError, "Can't create DataFrame from #{source}"
  end
end

Instance Method Details

#==(other) ⇒ Object



2193
2194
2195
2196
2197
2198
2199
# File 'lib/daru/dataframe.rb', line 2193

def == other
  self.class == other.class   &&
    @size    == other.size    &&
    @index   == other.index   &&
    @vectors == other.vectors &&
    @vectors.to_a.all? { |v| self[v] == other[v] }
end

#[](*names) ⇒ Object

Access row or vector. Specify name of row/vector followed by axis(:row, :vector). Defaults to :vector. Use of this method is not recommended for accessing rows. Use df.row for accessing row with index ‘:a’.



383
384
385
386
# File 'lib/daru/dataframe.rb', line 383

def [](*names)
  axis = extract_axis(names, :vector)
  dispatch_to_axis axis, :access, *names
end

#[]=(*args) ⇒ Object

Insert a new row/vector of the specified name or modify a previous row. Instead of using this method directly, use df.row = [1,2,3] to set/create a row ‘:a’ to [1,2,3], or df.vector = [1,2,3] for vectors.

In case a Daru::Vector is specified after the equality the sign, the indexes of the vector will be matched against the row/vector indexes of the DataFrame before an insertion is performed. Unmatched indexes will be set to nil.



527
528
529
530
531
532
533
# File 'lib/daru/dataframe.rb', line 527

def []=(*args)
  vector = args.pop
  axis = extract_axis(args)
  names = args

  dispatch_to_axis axis, :insert_or_modify, names, vector
end

#_dump(_depth) ⇒ Object



2135
2136
2137
2138
2139
2140
2141
2142
# File 'lib/daru/dataframe.rb', line 2135

def _dump(_depth)
  Marshal.dump(
    data:  @data,
    index: @index.to_a,
    order: @vectors.to_a,
    name:  @name
  )
end

#add_row(row, index = nil) ⇒ Object



535
536
537
# File 'lib/daru/dataframe.rb', line 535

def add_row row, index=nil
  self.row[*(index || @size)] = row
end

#add_vector(n, vector) ⇒ Object



539
540
541
# File 'lib/daru/dataframe.rb', line 539

def add_vector n, vector
  self[n] = vector
end

#add_vectors_by_split(name, join = '-', sep = Daru::SPLIT_TOKEN) ⇒ Object



1295
1296
1297
1298
1299
# File 'lib/daru/dataframe.rb', line 1295

def add_vectors_by_split(name,join='-',sep=Daru::SPLIT_TOKEN)
  self[name]
    .split_by_separator(sep)
    .each { |k,v| self["#{name}#{join}#{k}".to_sym] = v }
end

#add_vectors_by_split_recode(nm, join = '-', sep = Daru::SPLIT_TOKEN) ⇒ Object



1941
1942
1943
1944
1945
1946
1947
1948
# File 'lib/daru/dataframe.rb', line 1941

def add_vectors_by_split_recode(nm, join='-', sep=Daru::SPLIT_TOKEN)
  self[nm]
    .split_by_separator(sep)
    .each_with_index do |(k, v), i|
      v.rename "#{nm}:#{k}"
      self["#{nm}#{join}#{i + 1}".to_sym] = v
    end
end

#aggregate(options = {}, multi_index_level = -1)) ⇒ Daru::DataFrame

Function to use for aggregating the data.

Note: ‘GroupBy` class `aggregate` method uses this `aggregate` method internally.

Examples:

df = Daru::DataFrame.new(
   {col: [:a, :b, :c, :d, :e], num: [52,12,07,17,01]})
=> #<Daru::DataFrame(5x2)>
     col num
   0   a  52
   1   b  12
   2   c   7
   3   d  17
   4   e   1

 df.aggregate(num_100_times: ->(df) { (df.num*100).first })
=> #<Daru::DataFrame(5x1)>
            num_100_ti
          0       5200
          1       1200
          2        700
          3       1700
          4        100

When we have duplicate index :

idx = Daru::CategoricalIndex.new [:a, :b, :a, :a, :c]
df = Daru::DataFrame.new({num: [52,12,07,17,01]}, index: idx)
=> #<Daru::DataFrame(5x1)>
     num
   a  52
   b  12
   a   7
   a  17
   c   1

df.aggregate(num: :mean)
=> #<Daru::DataFrame(3x1)>
                   num
          a 25.3333333
          b         12
          c          1

Parameters:

  • options (Hash) (defaults to: {})

    options for column, you want in resultant dataframe

Returns:



2324
2325
2326
2327
2328
2329
2330
# File 'lib/daru/dataframe.rb', line 2324

def aggregate(options={}, multi_index_level=-1)
  positions_tuples, new_index = group_index_for_aggregation(@index, multi_index_level)

  colmn_value = aggregate_by_positions_tuples(options, positions_tuples)

  Daru::DataFrame.new(colmn_value, index: new_index, order: options.keys)
end

#all?(axis = :vector, &block) ⇒ Boolean

Works like Array#all?

Examples:

Using all?

df = Daru::DataFrame.new({a: [1,2,3,4,5], b: ['a', 'b', 'c', 'd', 'e']})
df.all?(:row) do |row|
  row[:a] < 10
end #=> true

Parameters:

  • axis (Symbol) (defaults to: :vector)

    (:vector) The axis to iterate over. Can be :vector or :row. A Daru::Vector object is yielded in the block.

Returns:

  • (Boolean)


1352
1353
1354
1355
1356
1357
1358
1359
1360
# File 'lib/daru/dataframe.rb', line 1352

def all? axis=:vector, &block
  if %i[vector column].include?(axis)
    @data.all?(&block)
  elsif axis == :row
    each_row.all?(&block)
  else
    raise ArgumentError, "Unidentified axis #{axis}"
  end
end

#any?(axis = :vector, &block) ⇒ Boolean

Works like Array#any?.

Examples:

Using any?

df = Daru::DataFrame.new({a: [1,2,3,4,5], b: ['a', 'b', 'c', 'd', 'e']})
df.any?(:row) do |row|
  row[:a] < 3 and row[:b] == 'b'
end #=> true

Parameters:

  • axis (Symbol) (defaults to: :vector)

    (:vector) The axis to iterate over. Can be :vector or :row. A Daru::Vector object is yielded in the block.

Returns:

  • (Boolean)


1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
# File 'lib/daru/dataframe.rb', line 1330

def any? axis=:vector, &block
  if %i[vector column].include?(axis)
    @data.any?(&block)
  elsif axis == :row
    each_row do |row|
      return true if yield(row)
    end
    false
  else
    raise ArgumentError, "Unidentified axis #{axis}"
  end
end

#apply_method(method, keys: nil, by_position: true) ⇒ Object Also known as: apply_method_on_sub_df



1008
1009
1010
1011
1012
1013
1014
1015
1016
# File 'lib/daru/dataframe.rb', line 1008

def apply_method(method, keys: nil, by_position: true)
  df = keys ? get_sub_dataframe(keys, by_position: by_position) : self

  case method
  when Symbol then df.send(method)
  when Proc   then method.call(df)
  else raise
  end
end

#at(*positions) ⇒ Daru::Vector, Daru::DataFrame

Retrive vectors by positions

Examples:

df = Daru::DataFrame.new({
  a: [1, 2, 3],
  b: ['a', 'b', 'c']
})
df.at 0
# => #<Daru::Vector(3)>
#       a
#   0   1
#   1   2
#   2   3

Parameters:

  • positions (Array<Integer>)

    of vectors to retrive

Returns:



465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
# File 'lib/daru/dataframe.rb', line 465

def at *positions
  if AXES.include? positions.last
    axis = positions.pop
    return row_at(*positions) if axis == :row
  end

  original_positions = positions
  positions = coerce_positions(*positions, ncols)
  validate_positions(*positions, ncols)

  if positions.is_a? Integer
    @data[positions].dup
  else
    Daru::DataFrame.new positions.map { |pos| @data[pos].dup },
      index: @index,
      order: @vectors.at(*original_positions),
      name: @name
  end
end

#bootstrap(n = nil) ⇒ Daru::DataFrame

Creates a DataFrame with the random data, of n size. If n not given, uses original number of rows.

Returns:



1101
1102
1103
1104
1105
1106
1107
1108
1109
# File 'lib/daru/dataframe.rb', line 1101

def bootstrap(n=nil)
  n ||= nrows
  Daru::DataFrame.new({}, order: @vectors).tap do |df_boot|
    n.times do
      df_boot.add_row(row[rand(n)])
    end
    df_boot.update
  end
end

#clone(*vectors_to_clone) ⇒ Object

Returns a ‘view’ of the DataFrame, i.e the object ID’s of vectors are preserved.

Arguments

vectors_to_clone - Names of vectors to clone. Optional. Will return a view of the whole data frame otherwise.



593
594
595
596
597
598
599
# File 'lib/daru/dataframe.rb', line 593

def clone *vectors_to_clone
  vectors_to_clone.flatten! if ArrayHelper.array_of?(vectors_to_clone, Array)
  vectors_to_clone = @vectors.to_a if vectors_to_clone.empty?

  h = vectors_to_clone.map { |vec| [vec, self[vec]] }.to_h
  Daru::DataFrame.new(h, clone: false, order: vectors_to_clone, name: @name)
end

#clone_only_validObject

Returns a ‘shallow’ copy of DataFrame if missing data is not present, or a full copy of only valid data if missing data is present.



603
604
605
606
607
608
609
# File 'lib/daru/dataframe.rb', line 603

def clone_only_valid
  if include_values?(*Daru::MISSING_VALUES)
    reject_values(*Daru::MISSING_VALUES)
  else
    clone
  end
end

#clone_structureObject

Only clone the structure of the DataFrame.



582
583
584
# File 'lib/daru/dataframe.rb', line 582

def clone_structure
  Daru::DataFrame.new([], order: @vectors.dup, index: @index.dup, name: @name)
end

#collect(axis = :vector, &block) ⇒ Object

Iterate over a row or vector and return results in a Daru::Vector. Specify axis with :vector or :row. Default to :vector.

Description

The #collect iterator works similar to #map, the only difference being that it returns a Daru::Vector comprising of the results of each block run. The resultant Vector has the same index as that of the axis over which collect has iterated. It also accepts the optional axis argument.

Arguments

  • axis - The axis to iterate over. Can be :vector (or :column)

or :row. Default to :vector.



847
848
849
# File 'lib/daru/dataframe.rb', line 847

def collect axis=:vector, &block
  dispatch_to_axis_pl axis, :collect, &block
end

#collect_matrix::Matrix

Generate a matrix, based on vector names of the DataFrame.

:nocov: FIXME: Even not trying to cover this: I can’t get, how it is expected to work.… – zverok

Returns:



1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
# File 'lib/daru/dataframe.rb', line 1053

def collect_matrix
  return to_enum(:collect_matrix) unless block_given?

  vecs = vectors.to_a
  rows = vecs.collect { |row|
    vecs.collect { |col|
      yield row,col
    }
  }

  Matrix.rows(rows)
end

#collect_row_with_index(&block) ⇒ Object



1027
1028
1029
1030
1031
# File 'lib/daru/dataframe.rb', line 1027

def collect_row_with_index &block
  return to_enum(:collect_row_with_index) unless block_given?

  Daru::Vector.new(each_row_with_index.map(&block), index: @index)
end

#collect_rows(&block) ⇒ Object

Retrieves a Daru::Vector, based on the result of calculation performed on each row.



1021
1022
1023
1024
1025
# File 'lib/daru/dataframe.rb', line 1021

def collect_rows &block
  return to_enum(:collect_rows) unless block_given?

  Daru::Vector.new(each_row.map(&block), index: @index)
end

#collect_vector_with_index(&block) ⇒ Object



1041
1042
1043
1044
1045
# File 'lib/daru/dataframe.rb', line 1041

def collect_vector_with_index &block
  return to_enum(:collect_vector_with_index) unless block_given?

  Daru::Vector.new(each_vector_with_index.map(&block), index: @vectors)
end

#collect_vectors(&block) ⇒ Object

Retrives a Daru::Vector, based on the result of calculation performed on each vector.



1035
1036
1037
1038
1039
# File 'lib/daru/dataframe.rb', line 1035

def collect_vectors &block
  return to_enum(:collect_vectors) unless block_given?

  Daru::Vector.new(each_vector.map(&block), index: @vectors)
end

#compute(text, &block) ⇒ Object

Returns a vector, based on a string with a calculation based on vector.

The calculation will be eval’ed, so you can put any variable or expression valid on ruby.

For example:

a = Daru::Vector.new [1,2]
b = Daru::Vector.new [3,4]
ds = Daru::DataFrame.new({:a => a,:b => b})
ds.compute("a+b")
=> Vector [4,6]


1220
1221
1222
1223
# File 'lib/daru/dataframe.rb', line 1220

def compute text, &block
  return instance_eval(&block) if block_given?
  instance_eval(text)
end

#concat(other_df) ⇒ Object

Concatenate another DataFrame along corresponding columns. If columns do not exist in both dataframes, they are filled with nils



1507
1508
1509
1510
1511
1512
1513
1514
1515
# File 'lib/daru/dataframe.rb', line 1507

def concat other_df
  vectors = (@vectors.to_a + other_df.vectors.to_a).uniq

  data = vectors.map do |v|
    get_vector_anyways(v).dup.concat(other_df.get_vector_anyways(v))
  end

  Daru::DataFrame.new(data, order: vectors)
end

#create_sql(table, charset = 'UTF8') ⇒ Object

Create a sql, basen on a given Dataset

Arguments

  • table - String specifying name of the table that will created in SQL.

  • charset - Character set. Default is “UTF8”.

Examples:


ds = Daru::DataFrame.new({
 :id   => Daru::Vector.new([1,2,3,4,5]),
 :name => Daru::Vector.new(%w{Alex Peter Susan Mary John})
})
ds.create_sql('names')
 #=>"CREATE TABLE names (id INTEGER,\n name VARCHAR (255)) CHARACTER SET=UTF8;"


1966
1967
1968
1969
1970
1971
1972
1973
1974
# File 'lib/daru/dataframe.rb', line 1966

def create_sql(table,charset='UTF8')
  sql    = "CREATE TABLE #{table} ("
  fields = vectors.to_a.collect do |f|
    v = self[f]
    f.to_s + ' ' + v.db_type
  end

  sql + fields.join(",\n ")+") CHARACTER SET=#{charset};"
end

#delete_row(index) ⇒ Object

Delete a row

Raises:

  • (IndexError)


1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
# File 'lib/daru/dataframe.rb', line 1085

def delete_row index
  idx = named_index_for index

  raise IndexError, "Index #{index} does not exist." unless @index.include? idx
  @index = Daru::Index.new(@index.to_a - [idx])
  each_vector do |vector|
    vector.delete_at idx
  end

  set_size
end

#delete_vector(vector) ⇒ Object

Delete a vector

Raises:

  • (IndexError)


1068
1069
1070
1071
1072
1073
1074
1075
# File 'lib/daru/dataframe.rb', line 1068

def delete_vector vector
  raise IndexError, "Vector #{vector} does not exist." unless @vectors.include?(vector)

  @data.delete_at @vectors[vector]
  @vectors = Daru::Index.new @vectors.to_a - [vector]

  self
end

#delete_vectors(*vectors) ⇒ Object

Deletes a list of vectors



1078
1079
1080
1081
1082
# File 'lib/daru/dataframe.rb', line 1078

def delete_vectors *vectors
  Array(vectors).each { |vec| delete_vector vec }

  self
end

#dup(vectors_to_dup = nil) ⇒ Object

Duplicate the DataFrame entirely.

Arguments

  • vectors_to_dup - An Array specifying the names of Vectors to

be duplicated. Will duplicate the entire DataFrame if not specified.



572
573
574
575
576
577
578
579
# File 'lib/daru/dataframe.rb', line 572

def dup vectors_to_dup=nil
  vectors_to_dup = @vectors.to_a unless vectors_to_dup

  src = vectors_to_dup.map { |vec| @data[@vectors.pos(vec)].dup }
  new_order = Daru::Index.new(vectors_to_dup)

  Daru::DataFrame.new src, order: new_order, index: @index.dup, name: @name, clone: true
end

#dup_only_valid(vecs = nil) ⇒ Object

Creates a new duplicate dataframe containing only rows without a single missing value.



613
614
615
616
617
618
619
620
# File 'lib/daru/dataframe.rb', line 613

def dup_only_valid vecs=nil
  rows_with_nil = @data.map { |vec| vec.indexes(*Daru::MISSING_VALUES) }
                       .inject(&:concat)
                       .uniq

  row_indexes = @index.to_a
  (vecs.nil? ? self : dup(vecs)).row[*(row_indexes - rows_with_nil)]
end

#each(axis = :vector, &block) ⇒ Object

Iterate over each row or vector of the DataFrame. Specify axis by passing :vector or :row as the argument. Default to :vector.

Description

‘#each` works exactly like Array#each. The default mode for `each` is to iterate over the columns of the DataFrame. To iterate over rows you must pass the axis, i.e `:row` as an argument.

Arguments

  • axis - The axis to iterate over. Can be :vector (or :column)

or :row. Default to :vector.



828
829
830
# File 'lib/daru/dataframe.rb', line 828

def each axis=:vector, &block
  dispatch_to_axis axis, :each, &block
end

#each_index(&block) ⇒ Object

Iterate over each index of the DataFrame.



762
763
764
765
766
767
768
# File 'lib/daru/dataframe.rb', line 762

def each_index &block
  return to_enum(:each_index) unless block_given?

  @index.each(&block)

  self
end

#each_rowObject

Iterate over each row



795
796
797
798
799
800
801
802
803
# File 'lib/daru/dataframe.rb', line 795

def each_row
  return to_enum(:each_row) unless block_given?

  @index.size.times do |pos|
    yield row_at(pos)
  end

  self
end

#each_row_with_indexObject



805
806
807
808
809
810
811
812
813
# File 'lib/daru/dataframe.rb', line 805

def each_row_with_index
  return to_enum(:each_row_with_index) unless block_given?

  @index.each do |index|
    yield access_row(index), index
  end

  self
end

#each_vector(&block) ⇒ Object Also known as: each_column

Iterate over each vector



771
772
773
774
775
776
777
# File 'lib/daru/dataframe.rb', line 771

def each_vector(&block)
  return to_enum(:each_vector) unless block_given?

  @data.each(&block)

  self
end

#each_vector_with_indexObject Also known as: each_column_with_index

Iterate over each vector alongwith the name of the vector



782
783
784
785
786
787
788
789
790
# File 'lib/daru/dataframe.rb', line 782

def each_vector_with_index
  return to_enum(:each_vector_with_index) unless block_given?

  @vectors.each do |vector|
    yield @data[@vectors[vector]], vector
  end

  self
end

#filter(axis = :vector, &block) ⇒ Object

Retain vectors or rows if the block returns a truthy value.

Description

For filtering out certain rows/vectors based on their values, use the #filter method. By default it iterates over vectors and keeps those vectors for which the block returns true. It accepts an optional axis argument which lets you specify whether you want to iterate over vectors or rows.

Arguments

  • axis - The axis to map over. Can be :vector (or :column) or :row.

Default to :vector.

Usage

# Filter vectors

df.filter do |vector|
  vector.type == :numeric and vector.median < 50
end

# Filter rows

df.filter(:row) do |row|
  row[:a] + row[:d] < 100
end


936
937
938
# File 'lib/daru/dataframe.rb', line 936

def filter axis=:vector, &block
  dispatch_to_axis_pl axis, :filter, &block
end

#filter_rowsObject

Iterates over each row and retains it in a new DataFrame if the block returns true for that row.



1130
1131
1132
1133
1134
1135
1136
# File 'lib/daru/dataframe.rb', line 1130

def filter_rows
  return to_enum(:filter_rows) unless block_given?

  keep_rows = @index.map { |index| yield access_row(index) }

  where keep_rows
end

#filter_vector(vec, &block) ⇒ Object

creates a new vector with the data of a given field which the block returns true



1124
1125
1126
# File 'lib/daru/dataframe.rb', line 1124

def filter_vector vec, &block
  Daru::Vector.new(each_row.select(&block).map { |row| row[vec] })
end

#filter_vectors(&block) ⇒ Object

Iterates over each vector and retains it in a new DataFrame if the block returns true for that vector.



1140
1141
1142
1143
1144
# File 'lib/daru/dataframe.rb', line 1140

def filter_vectors &block
  return to_enum(:filter_vectors) unless block_given?

  dup.tap { |df| df.keep_vector_if(&block) }
end

#get_sub_dataframe(keys, by_position: true) ⇒ Daru::Dataframe

Extract a dataframe given row indexes or positions

Parameters:

  • keys (Array)

    can be positions (if by_position is true) or indexes (if by_position if false)

Returns:

  • (Daru::Dataframe)


555
556
557
558
559
560
561
562
563
564
# File 'lib/daru/dataframe.rb', line 555

def get_sub_dataframe(keys, by_position: true)
  return Daru::DataFrame.new({}) if keys == []

  keys = @index.pos(*keys) unless by_position

  sub_df = row_at(*keys)
  sub_df = sub_df.to_df.transpose if sub_df.is_a?(Daru::Vector)

  sub_df
end

#get_vector_anyways(v) ⇒ Object



1501
1502
1503
# File 'lib/daru/dataframe.rb', line 1501

def get_vector_anyways(v)
  @vectors.include?(v) ? self[v].to_a : [nil] * size
end

#group_by(*vectors) ⇒ Object

Group elements by vector to perform operations on them. Returns a Daru::Core::GroupBy object.See the Daru::Core::GroupBy docs for a detailed list of possible operations.

Arguments

  • vectors - An Array contatining names of vectors to group by.

Usage

df = Daru::DataFrame.new({
  a: %w{foo bar foo bar   foo bar foo foo},
  b: %w{one one two three two two one three},
  c:   [1  ,2  ,3  ,1    ,3  ,6  ,3  ,8],
  d:   [11 ,22 ,33 ,44   ,55 ,66 ,77 ,88]
})
df.group_by([:a,:b,:c]).groups
#=> {["bar", "one", 2]=>[1],
# ["bar", "three", 1]=>[3],
# ["bar", "two", 6]=>[5],
# ["foo", "one", 1]=>[0],
# ["foo", "one", 3]=>[6],
# ["foo", "three", 8]=>[7],
# ["foo", "two", 3]=>[2, 4]}


1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
# File 'lib/daru/dataframe.rb', line 1477

def group_by *vectors
  vectors.flatten!
  missing = vectors - @vectors.to_a
  unless missing.empty?
    raise(ArgumentError, "Vector(s) missing: #{missing.join(', ')}")
  end

  vectors = [@vectors.first] if vectors.empty?

  Daru::Core::GroupBy.new(self, vectors)
end

#group_by_and_aggregate(*group_by_keys, **aggregation_map) ⇒ Object

Is faster than using group_by followed by aggregate (because it doesn’t generate an intermediary dataframe)



2333
2334
2335
2336
2337
2338
2339
2340
# File 'lib/daru/dataframe.rb', line 2333

def group_by_and_aggregate(*group_by_keys, **aggregation_map)
  positions_groups = Daru::Core::GroupBy.get_positions_group_map_for_df(self, group_by_keys.flatten, sort: true)

  new_index   = Daru::MultiIndex.from_tuples(positions_groups.keys).coerce_index
  colmn_value = aggregate_by_positions_tuples(aggregation_map, positions_groups.values)

  Daru::DataFrame.new(colmn_value, index: new_index, order: aggregation_map.keys)
end

#has_missing_data?Boolean Also known as: flawed?

Returns:

  • (Boolean)


1242
1243
1244
# File 'lib/daru/dataframe.rb', line 1242

def has_missing_data?
  @data.any? { |vec| vec.include_values?(*Daru::MISSING_VALUES) }
end

#has_vector?(vector) ⇒ Boolean

Check if a vector is present

Returns:

  • (Boolean)


1317
1318
1319
# File 'lib/daru/dataframe.rb', line 1317

def has_vector? vector
  @vectors.include? vector
end

#head(quantity = 10) ⇒ Object Also known as: first

The first ten elements of the DataFrame

Parameters:

  • quantity (Fixnum) (defaults to: 10)

    (10) The number of elements to display from the top.



1365
1366
1367
# File 'lib/daru/dataframe.rb', line 1365

def head quantity=10
  row.at 0..(quantity-1)
end

#include_values?(*values) ⇒ true, false

Check if any of given values occur in the data frame

Examples:

df = Daru::DataFrame.new({
  a: [1,    2,          3,   nil,        Float::NAN, nil, 1,   7],
  b: [:a,  :b,          nil, Float::NAN, nil,        3,   5,   8],
  c: ['a',  Float::NAN, 3,   4,          3,          5,   nil, 7]
}, index: 11..18)
df.include_values? nil
# => true

Parameters:

  • values (Array)

    to check for

Returns:

  • (true, false)

    true if any of the given values occur in the dataframe, false otherwise



1261
1262
1263
# File 'lib/daru/dataframe.rb', line 1261

def include_values?(*values)
  @data.any? { |vec| vec.include_values?(*values) }
end

#inspect(spacing = 10, threshold = 15) ⇒ Object

Pretty print in a nice table format for the command line (irb/pry/iruby)



2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
# File 'lib/daru/dataframe.rb', line 2175

def inspect spacing=10, threshold=15
  name_part = @name ? ": #{@name} " : ''

  "#<#{self.class}#{name_part}(#{nrows}x#{ncols})>\n" +
    Formatters::Table.format(
      each_row.lazy,
      row_headers: row_headers,
      headers: headers,
      threshold: threshold,
      spacing: spacing
    )
end

#interact_code(vector_names, full) ⇒ Object



2237
2238
2239
2240
2241
2242
2243
2244
2245
# File 'lib/daru/dataframe.rb', line 2237

def interact_code vector_names, full
  dfs = vector_names.zip(full).map do |vec_name, f|
    self[vec_name].contrast_code(full: f).each.to_a
  end

  all_vectors = recursive_product(dfs)
  Daru::DataFrame.new all_vectors,
    order: all_vectors.map(&:name)
end

#join(other_df, opts = {}) ⇒ Daru::DataFrame

Join 2 DataFrames with SQL style joins. Currently supports inner, left outer, right outer and full outer joins.

Examples:

Inner Join

left = Daru::DataFrame.new({
  :id   => [1,2,3,4],
  :name => ['Pirate', 'Monkey', 'Ninja', 'Spaghetti']
})
right = Daru::DataFrame.new({
  :id => [1,2,3,4],
  :name => ['Rutabaga', 'Pirate', 'Darth Vader', 'Ninja']
})
left.join(right, how: :inner, on: [:name])
#=>
##<Daru::DataFrame:82416700 @name = 74c0811b-76c6-4c42-ac93-e6458e82afb0 @size = 2>
#                 id_1       name       id_2
#         0          1     Pirate          2
#         1          3      Ninja          4

Parameters:

  • other_df (Daru::DataFrame)

    Another DataFrame on which the join is to be performed.

  • opts (Hash) (defaults to: {})

    Options Hash

  • :how (Hash)

    a customizable set of options

  • :on (Hash)

    a customizable set of options

  • :indicator (Hash)

    a customizable set of options

Returns:



1889
1890
1891
# File 'lib/daru/dataframe.rb', line 1889

def join(other_df,opts={})
  Daru::Core::Merge.join(self, other_df, opts)
end

#keep_row_ifObject



1111
1112
1113
1114
1115
# File 'lib/daru/dataframe.rb', line 1111

def keep_row_if
  @index
    .reject { |idx| yield access_row(idx) }
    .each { |idx| delete_row idx }
end

#keep_vector_ifObject



1117
1118
1119
1120
1121
# File 'lib/daru/dataframe.rb', line 1117

def keep_vector_if
  @vectors.each do |vector|
    delete_vector(vector) unless yield(@data[@vectors[vector]], vector)
  end
end

#map(axis = :vector, &block) ⇒ Object

Map over each vector or row of the data frame according to the argument specified. Will return an Array of the resulting elements. To map over each row/vector and get a DataFrame, see #recode.

Description

The #map iterator works like Array#map. The value returned by each run of the block is added to an Array and the Array is returned. This method also accepts an axis argument, like #each. The default is :vector.

Arguments

  • axis - The axis to map over. Can be :vector (or :column) or :row.

Default to :vector.



867
868
869
# File 'lib/daru/dataframe.rb', line 867

def map axis=:vector, &block
  dispatch_to_axis_pl axis, :map, &block
end

#map!(axis = :vector, &block) ⇒ Object

Destructive map. Modifies the DataFrame. Each run of the block must return a Daru::Vector. You can specify the axis to map over as the argument. Default to :vector.

Arguments

  • axis - The axis to map over. Can be :vector (or :column) or :row.

Default to :vector.



879
880
881
882
883
884
885
# File 'lib/daru/dataframe.rb', line 879

def map! axis=:vector, &block
  if %i[vector column].include?(axis)
    map_vectors!(&block)
  elsif axis == :row
    map_rows!(&block)
  end
end

#map_rows(&block) ⇒ Object

Map each row



986
987
988
989
990
# File 'lib/daru/dataframe.rb', line 986

def map_rows &block
  return to_enum(:map_rows) unless block_given?

  each_row.map(&block)
end

#map_rows!Object



998
999
1000
1001
1002
1003
1004
1005
1006
# File 'lib/daru/dataframe.rb', line 998

def map_rows!
  return to_enum(:map_rows!) unless block_given?

  index.dup.each do |i|
    row[i] = should_be_vector!(yield(row[i]))
  end

  self
end

#map_rows_with_index(&block) ⇒ Object



992
993
994
995
996
# File 'lib/daru/dataframe.rb', line 992

def map_rows_with_index &block
  return to_enum(:map_rows_with_index) unless block_given?

  each_row_with_index.map(&block)
end

#map_vectors(&block) ⇒ Object

Map each vector and return an Array.



961
962
963
964
965
# File 'lib/daru/dataframe.rb', line 961

def map_vectors &block
  return to_enum(:map_vectors) unless block_given?

  @data.map(&block)
end

#map_vectors!Object

Destructive form of #map_vectors



968
969
970
971
972
973
974
975
976
# File 'lib/daru/dataframe.rb', line 968

def map_vectors!
  return to_enum(:map_vectors!) unless block_given?

  vectors.dup.each do |n|
    self[n] = should_be_vector!(yield(self[n]))
  end

  self
end

#map_vectors_with_index(&block) ⇒ Object

Map vectors alongwith the index.



979
980
981
982
983
# File 'lib/daru/dataframe.rb', line 979

def map_vectors_with_index &block
  return to_enum(:map_vectors_with_index) unless block_given?

  each_vector_with_index.map(&block)
end

#merge(other_df) ⇒ Daru::DataFrame

Merge vectors from two DataFrames. In case of name collision, the vectors names are changed to x_1, x_2 .…

Returns:



1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
# File 'lib/daru/dataframe.rb', line 1844

def merge other_df # rubocop:disable Metrics/AbcSize
  unless nrows == other_df.nrows
    raise ArgumentError,
      "Number of rows must be equal in this: #{nrows} and other: #{other_df.nrows}"
  end

  new_fields = (@vectors.to_a + other_df.vectors.to_a)
  new_fields = ArrayHelper.recode_repeated(new_fields)
  DataFrame.new({}, order: new_fields).tap do |df_new|
    (0...nrows).each do |i|
      df_new.add_row row[i].to_a + other_df.row[i].to_a
    end
    df_new.index = @index if @index == other_df.index
    df_new.update
  end
end

#missing_values_rows(missing_values = [nil]) ⇒ Object Also known as: vector_missing_values

Return a vector with the number of missing values in each row.

Arguments

  • missing_values - An Array of the values that should be

treated as ‘missing’. The default missing value is nil.



1231
1232
1233
1234
1235
1236
1237
# File 'lib/daru/dataframe.rb', line 1231

def missing_values_rows missing_values=[nil]
  number_of_missing = each_row.map do |row|
    row.indexes(*missing_values).size
  end

  Daru::Vector.new number_of_missing, index: @index, name: "#{@name}_missing_rows"
end

#ncolsObject

The number of vectors



1312
1313
1314
# File 'lib/daru/dataframe.rb', line 1312

def ncols
  @vectors.size
end

#nest(*tree_keys, &_block) ⇒ Object

Return a nested hash using vector names as keys and an array constructed of hashes with other values. If block provided, is used to provide the values, with parameters row of dataset, current last hash on hierarchy and name of the key to include



1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
# File 'lib/daru/dataframe.rb', line 1269

def nest *tree_keys, &_block
  tree_keys = tree_keys[0] if tree_keys[0].is_a? Array

  each_row.each_with_object({}) do |row, current|
    # Create tree
    *keys, last = tree_keys
    current = keys.inject(current) { |c, f| c[row[f]] ||= {} }
    name = row[last]

    if block_given?
      current[name] = yield(row, current, name)
    else
      current[name] ||= []
      current[name].push(row.to_h.delete_if { |key,_value| tree_keys.include? key })
    end
  end
end

#nrowsObject

The number of rows



1307
1308
1309
# File 'lib/daru/dataframe.rb', line 1307

def nrows
  @index.size
end

#numeric_vector_namesObject



1651
1652
1653
# File 'lib/daru/dataframe.rb', line 1651

def numeric_vector_names
  @vectors.select { |v| self[v].numeric? }
end

#numeric_vectorsObject

Return the indexes of all the numeric vectors. Will include vectors with nils alongwith numbers.



1644
1645
1646
1647
1648
1649
# File 'lib/daru/dataframe.rb', line 1644

def numeric_vectors
  # FIXME: Why _with_index ?..
  each_vector_with_index
    .select { |vec, _i| vec.numeric? }
    .map(&:last)
end

#one_to_many(parent_fields, pattern) ⇒ Object

Creates a new dataset for one to many relations on a dataset, based on pattern of field names.

for example, you have a survey for number of children with this structure:

id, name, child_name_1, child_age_1, child_name_2, child_age_2

with

ds.one_to_many([:id], "child_%v_%n"

the field of first parameters will be copied verbatim to new dataset, and fields which responds to second pattern will be added one case for each different %n.

Examples:

cases=[
  ['1','george','red',10,'blue',20,nil,nil],
  ['2','fred','green',15,'orange',30,'white',20],
  ['3','alfred',nil,nil,nil,nil,nil,nil]
]
ds=Daru::DataFrame.rows(cases, order:
  [:id, :name,
   :car_color1, :car_value1,
   :car_color2, :car_value2,
   :car_color3, :car_value3])
ds.one_to_many([:id],'car_%v%n').to_matrix
#=> Matrix[
#   ["red", "1", 10],
#   ["blue", "1", 20],
#   ["green", "2", 15],
#   ["orange", "2", 30],
#   ["white", "2", 20]
#   ]


1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
# File 'lib/daru/dataframe.rb', line 1924

def one_to_many(parent_fields, pattern)
  vars, numbers = one_to_many_components(pattern)

  DataFrame.new([], order: [*parent_fields, '_col_id', *vars]).tap do |ds|
    each_row do |row|
      verbatim = parent_fields.map { |f| [f, row[f]] }.to_h
      numbers.each do |n|
        generated = one_to_many_row row, n, vars, pattern
        next if generated.values.all?(&:nil?)

        ds.add_row(verbatim.merge(generated).merge('_col_id' => n))
      end
    end
    ds.update
  end
end

#only_numerics(opts = {}) ⇒ Object

Return a DataFrame of only the numerical Vectors. If clone: false is specified as option, only a view of the Vectors will be returned. Defaults to clone: true.



1658
1659
1660
1661
1662
1663
1664
# File 'lib/daru/dataframe.rb', line 1658

def only_numerics opts={}
  cln = opts[:clone] == false ? false : true
  arry = numeric_vectors.map { |v| self[v] }

  order = Index.new(numeric_vectors)
  Daru::DataFrame.new(arry, clone: cln, order: order, index: @index)
end

#order=(order_array) ⇒ Object

Reorder the vectors in a dataframe

Examples:

df = Daru::DataFrame({
  a: [1, 2, 3],
  b: [4, 5, 6]
}, order: [:a, :b])
df.order = [:b, :a]
df
# => #<Daru::DataFrame(3x2)>
#       b   a
#   0   4   1
#   1   5   2
#   2   6   3

Parameters:

  • order_array (Array)

    new order of the vectors

Raises:

  • (ArgumentError)


1202
1203
1204
1205
1206
# File 'lib/daru/dataframe.rb', line 1202

def order=(order_array)
  raise ArgumentError, 'Invalid order' unless
    order_array.sort == vectors.to_a.sort
  initialize(to_h, order: order_array)
end

#pivot_table(opts = {}) ⇒ Object

Pivots a data frame on specified vectors and applies an aggregate function to quickly generate a summary.

Options

:index - Keys to group by on the pivot table row index. Pass vector names contained in an Array.

:vectors - Keys to group by on the pivot table column index. Pass vector names contained in an Array.

:agg - Function to aggregate the grouped values. Default to :mean. Can use any of the statistics functions applicable on Vectors that can be found in the Daru::Statistics::Vector module.

:values - Columns to aggregate. Will consider all numeric columns not specified in :index or :vectors. Optional.

Usage

df = Daru::DataFrame.new({
  a: ['foo'  ,  'foo',  'foo',  'foo',  'foo',  'bar',  'bar',  'bar',  'bar'],
  b: ['one'  ,  'one',  'one',  'two',  'two',  'one',  'one',  'two',  'two'],
  c: ['small','large','large','small','small','large','small','large','small'],
  d: [1,2,2,3,3,4,5,6,7],
  e: [2,4,4,6,6,8,10,12,14]
})
df.pivot_table(index: [:a], vectors: [:b], agg: :sum, values: :e)

#=>
# #<Daru::DataFrame:88342020 @name = 08cdaf4e-b154-4186-9084-e76dd191b2c9 @size = 2>
#            [:e, :one] [:e, :two]
#     [:bar]         18         26
#     [:foo]         10         12

Raises:

  • (ArgumentError)


1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
# File 'lib/daru/dataframe.rb', line 1823

def pivot_table opts={}
  raise ArgumentError, 'Specify grouping index' if Array(opts[:index]).empty?

  index               = opts[:index]
  vectors             = opts[:vectors] || []
  aggregate_function  = opts[:agg] || :mean
  values              = prepare_pivot_values index, vectors, opts
  raise IndexError, 'No numeric vectors to aggregate' if values.empty?

  grouped = group_by(index)
  return grouped.send(aggregate_function) if vectors.empty?

  super_hash = make_pivot_hash grouped, vectors, values, aggregate_function

  pivot_dataframe super_hash
end

#plotting_library=(lib) ⇒ Object



365
366
367
368
369
370
371
372
373
374
375
376
377
378
# File 'lib/daru/dataframe.rb', line 365

def plotting_library= lib
  case lib
  when :gruff, :nyaplot
    @plotting_library = lib
    if Daru.send("has_#{lib}?".to_sym)
      extend Module.const_get(
        "Daru::Plotting::DataFrame::#{lib.to_s.capitalize}Library"
      )
    end
  else
    raise ArguementError, "Plotting library #{lib} not supported. "\
      'Supported libraries are :nyaplot and :gruff'
  end
end

#recast(opts = {}) ⇒ Object

Change dtypes of vectors by supplying a hash of :vector_name => :new_dtype

Usage

df = Daru::DataFrame.new({a: [1,2,3], b: [1,2,3], c: [1,2,3]})
df.recast a: :nmatrix, c: :nmatrix


2157
2158
2159
2160
2161
# File 'lib/daru/dataframe.rb', line 2157

def recast opts={}
  opts.each do |vector_name, dtype|
    self[vector_name].cast(dtype: dtype)
  end
end

#recode(axis = :vector, &block) ⇒ Object

Maps over the DataFrame and returns a DataFrame. Each run of the block must return a Daru::Vector object. You can specify the axis to map over. Default to :vector.

Description

Recode works similarly to #map, but an important difference between the two is that recode returns a modified Daru::DataFrame instead of an Array. For this reason, #recode expects that every run of the block to return a Daru::Vector.

Just like map and each, recode also accepts an optional axis argument.

Arguments

  • axis - The axis to map over. Can be :vector (or :column) or :row.

Default to :vector.



904
905
906
# File 'lib/daru/dataframe.rb', line 904

def recode axis=:vector, &block
  dispatch_to_axis_pl axis, :recode, &block
end

#recode_rowsObject



950
951
952
953
954
955
956
957
958
# File 'lib/daru/dataframe.rb', line 950

def recode_rows
  block_given? or return to_enum(:recode_rows)

  dup.tap do |df|
    df.each_row_with_index do |r, i|
      df.row[i] = should_be_vector!(yield(r))
    end
  end
end

#recode_vectorsObject



940
941
942
943
944
945
946
947
948
# File 'lib/daru/dataframe.rb', line 940

def recode_vectors
  block_given? or return to_enum(:recode_vectors)

  dup.tap do |df|
    df.each_vector_with_index do |v, i|
      df[*i] = should_be_vector!(yield(v))
    end
  end
end

#reindex(new_index) ⇒ Object

Change the index of the DataFrame and preserve the labels of the previous indexing. New index can be Daru::Index or any of its subclasses.

Examples:

Reindexing DataFrame

df = Daru::DataFrame.new({a: [1,2,3,4], b: [11,22,33,44]},
  index: ['a','b','c','d'])
#=>
##<Daru::DataFrame:83278130 @name = b19277b8-c548-41da-ad9a-2ad8c060e273 @size = 4>
#                    a          b
#         a          1         11
#         b          2         22
#         c          3         33
#         d          4         44
df.reindex Daru::Index.new(['b', 0, 'a', 'g'])
#=>
##<Daru::DataFrame:83177070 @name = b19277b8-c548-41da-ad9a-2ad8c060e273 @size = 4>
#                    a          b
#         b          2         22
#         0        nil        nil
#         a          1         11
#         g        nil        nil

Parameters:

  • new_index (Daru::Index)

    The new Index for reindexing the DataFrame.



1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
# File 'lib/daru/dataframe.rb', line 1563

def reindex new_index
  unless new_index.is_a?(Daru::Index)
    raise ArgumentError, 'Must pass the new index of type Index or its '\
      "subclasses, not #{new_index.class}"
  end

  cl = Daru::DataFrame.new({}, order: @vectors, index: new_index, name: @name)
  new_index.each_with_object(cl) do |idx, memo|
    memo.row[idx] = @index.include?(idx) ? row[idx] : [nil]*ncols
  end
end

#reindex_vectors(new_vectors) ⇒ Object



1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
# File 'lib/daru/dataframe.rb', line 1489

def reindex_vectors new_vectors
  unless new_vectors.is_a?(Daru::Index)
    raise ArgumentError, 'Must pass the new index of type Index or its '\
      "subclasses, not #{new_index.class}"
  end

  cl = Daru::DataFrame.new({}, order: new_vectors, index: @index, name: @name)
  new_vectors.each_with_object(cl) do |vec, memo|
    memo[vec] = @vectors.include?(vec) ? self[vec] : [nil]*nrows
  end
end

#reject_values(*values) ⇒ Daru::DataFrame

Returns a dataframe in which rows with any of the mentioned values

are ignored.

Examples:

df = Daru::DataFrame.new({
  a: [1,    2,          3,   nil,        Float::NAN, nil, 1,   7],
  b: [:a,  :b,          nil, Float::NAN, nil,        3,   5,   8],
  c: ['a',  Float::NAN, 3,   4,          3,          5,   nil, 7]
}, index: 11..18)
df.reject_values nil, Float::NAN
# => #<Daru::DataFrame(2x3)>
#       a   b   c
#   11   1   a   a
#   18   7   8   7

Parameters:

  • values (Array)

    to reject to form the new dataframe

Returns:

  • (Daru::DataFrame)

    Data Frame with only rows which doesn’t contain the mentioned values



639
640
641
642
643
644
645
646
647
648
649
# File 'lib/daru/dataframe.rb', line 639

def reject_values(*values)
  positions =
    size.times.to_a - @data.flat_map { |vec| vec.positions(*values) }
  # Handle the case when positions size is 1 and #row_at wouldn't return a df
  if positions.size == 1
    pos = positions.first
    row_at(pos..pos)
  else
    row_at(*positions)
  end
end

#rename(new_name) ⇒ Object Also known as: name=

Rename the DataFrame.



2082
2083
2084
2085
# File 'lib/daru/dataframe.rb', line 2082

def rename new_name
  @name = new_name
  self
end

#rename_vectors(name_map) ⇒ Object

Renames the vectors

Arguments

  • name_map - A hash where the keys are the exising vector names and

    the values are the new names.  If a vector is renamed
    to a vector name that is already in use, the existing
    one is overwritten.
    

Usage

df = Daru::DataFrame.new({ a: [1,2,3,4], b: [:a,:b,:c,:d], c: [11,22,33,44] })
df.rename_vectors :a => :alpha, :c => :gamma
df.vectors.to_a #=> [:alpha, :b, :gamma]


1634
1635
1636
1637
1638
1639
1640
# File 'lib/daru/dataframe.rb', line 1634

def rename_vectors name_map
  existing_targets = name_map.reject { |k,v| k == v }.values & vectors.to_a
  delete_vectors(*existing_targets)

  new_names = vectors.to_a.map { |v| name_map[v] ? name_map[v] : v }
  self.vectors = Daru::Index.new new_names
end

#replace_values(old_values, new_value) ⇒ Daru::DataFrame

Replace specified values with given value

Examples:

df = Daru::DataFrame.new({
  a: [1,    2,          3,   nil,        Float::NAN, nil, 1,   7],
  b: [:a,  :b,          nil, Float::NAN, nil,        3,   5,   8],
  c: ['a',  Float::NAN, 3,   4,          3,          5,   nil, 7]
}, index: 11..18)
df.replace_values nil, Float::NAN
# => #<Daru::DataFrame(8x3)>
#       a   b   c
#   11   1   a   a
#   12   2   b NaN
#   13   3 NaN   3
#   14 NaN NaN   4
#   15 NaN NaN   3
#   16 NaN   3   5
#   17   1   5 NaN
#   18   7   8   7

Parameters:

  • old_values (Array)

    values to replace with new value

  • new_value (object)

    new value to replace with

Returns:

  • (Daru::DataFrame)

    Data Frame itself with old values replace with new value



673
674
675
676
# File 'lib/daru/dataframe.rb', line 673

def replace_values old_values, new_value
  @data.each { |vec| vec.replace_values old_values, new_value }
  self
end

#respond_to_missing?(name, include_private = false) ⇒ Boolean

Returns:

  • (Boolean)


2233
2234
2235
# File 'lib/daru/dataframe.rb', line 2233

def respond_to_missing?(name, include_private=false)
  name.to_s.end_with?('=') || has_vector?(name) || super
end

#rolling_fillna(direction = :forward) ⇒ Object



718
719
720
# File 'lib/daru/dataframe.rb', line 718

def rolling_fillna(direction=:forward)
  dup.rolling_fillna!(direction)
end

#rolling_fillna!(direction = :forward) ⇒ Object

Rolling fillna replace all Float::NAN and NIL values with the preceeding or following value

Examples:

df = Daru::DataFrame.new({
 a: [1,    2,          3,   nil,        Float::NAN, nil, 1,   7],
 b: [:a,  :b,          nil, Float::NAN, nil,        3,   5,   nil],
 c: ['a',  Float::NAN, 3,   4,          3,          5,   nil, 7]
})

=> #<Daru::DataFrame(8x3)>
     a   b   c
 0   1   a   a
 1   2   b NaN
 2   3 nil   3
 3 nil NaN   4
 4 NaN nil   3
 5 nil   3   5
 6   1   5 nil
 7   7 nil   7

2.3.3 :068 > df.rolling_fillna(:forward)
=> #<Daru::DataFrame(8x3)>
     a   b   c
 0   1   a   a
 1   2   b   a
 2   3   b   3
 3   3   b   4
 4   3   b   3
 5   3   3   5
 6   1   5   5
 7   7   5   7

Parameters:

  • direction (Symbol) (defaults to: :forward)

    (:forward, :backward) whether replacement value is preceeding or following



713
714
715
716
# File 'lib/daru/dataframe.rb', line 713

def rolling_fillna!(direction=:forward)
  @data.each { |vec| vec.rolling_fillna!(direction) }
  self
end

#rowObject

Access a row or set/create a row. Refer #[] and #[]= docs for details.

Usage

df.row[:a] # access row named ':a'
df.row[:b] = [1,2,3] # set row ':b' to [1,2,3]


548
549
550
# File 'lib/daru/dataframe.rb', line 548

def row
  Daru::Accessors::DataFrameByRow.new(self)
end

#row_at(*positions) ⇒ Daru::Vector, Daru::DataFrame

Retrive rows by positions

Examples:

df = Daru::DataFrame.new({
  a: [1, 2, 3],
  b: ['a', 'b', 'c']
})
df.row_at 1, 2
# => #<Daru::DataFrame(2x2)>
#       a   b
#   1   2   b
#   2   3   c

Parameters:

  • positions (Array<Integer>)

    of rows to retrive

Returns:



401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
# File 'lib/daru/dataframe.rb', line 401

def row_at *positions
  original_positions = positions
  positions = coerce_positions(*positions, nrows)
  validate_positions(*positions, nrows)

  if positions.is_a? Integer
    return Daru::Vector.new @data.map { |vec| vec.at(*positions) },
      index: @vectors
  else
    new_rows = @data.map { |vec| vec.at(*original_positions) }
    return Daru::DataFrame.new new_rows,
      index: @index.at(*original_positions),
      order: @vectors
  end
end

#save(filename) ⇒ Object

Use marshalling to save dataframe to a file.



2131
2132
2133
# File 'lib/daru/dataframe.rb', line 2131

def save filename
  Daru::IO.save self, filename
end

#set_at(positions, vector) ⇒ Object

Set vectors by positions

Examples:

df = Daru::DataFrame.new({
  a: [1, 2, 3],
  b: ['a', 'b', 'c']
})
df.set_at [0], ['x', 'y', 'z']
df
#=> #<Daru::DataFrame(3x2)>
#       a   b
#   0   x   a
#   1   y   b
#   2   z   c

Parameters:

  • positions (Array<Integer>)

    positions of vectors to set

  • vector (Array, Daru::Vector)

    vector to be assigned

Raises:



500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
# File 'lib/daru/dataframe.rb', line 500

def set_at positions, vector
  if positions.last == :row
    positions.pop
    return set_row_at(positions, vector)
  end

  validate_positions(*positions, ncols)
  vector =
    if vector.is_a? Daru::Vector
      vector.reindex @index
    else
      Daru::Vector.new vector
    end

  raise SizeError, 'Vector length should match index length' if
    vector.size != @index.size

  positions.each { |pos| @data[pos] = vector }
end

#set_index(new_index, opts = {}) ⇒ Object

Set a particular column as the new DF

Raises:

  • (ArgumentError)


1531
1532
1533
1534
1535
1536
1537
1538
1539
# File 'lib/daru/dataframe.rb', line 1531

def set_index new_index, opts={}
  raise ArgumentError, 'All elements in new index must be unique.' if
    @size != self[new_index].uniq.size

  self.index = Daru::Index.new(self[new_index].to_a)
  delete_vector(new_index) unless opts[:keep]

  self
end

#set_row_at(positions, vector) ⇒ Object

Set rows by positions

Examples:

df = Daru::DataFrame.new({
  a: [1, 2, 3],
  b: ['a', 'b', 'c']
})
df.set_row_at [0, 1], ['x', 'x']
df
#=> #<Daru::DataFrame(3x2)>
#       a   b
#   0   x   x
#   1   x   x
#   2   3   c

Parameters:

  • positions (Array<Integer>)

    positions of rows to set

  • vector (Array, Daru::Vector)

    vector to be assigned

Raises:



432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
# File 'lib/daru/dataframe.rb', line 432

def set_row_at positions, vector
  validate_positions(*positions, nrows)
  vector =
    if vector.is_a? Daru::Vector
      vector.reindex @vectors
    else
      Daru::Vector.new vector
    end

  raise SizeError, 'Vector length should match row length' if
    vector.size != @vectors.size

  @data.each_with_index do |vec, pos|
    vec.set_at(positions, vector.at(pos))
  end
  @index = @data[0].index
  set_size
end

#shapeObject

Return the number of rows and columns of the DataFrame in an Array.



1302
1303
1304
# File 'lib/daru/dataframe.rb', line 1302

def shape
  [nrows, ncols]
end

#sort(vector_order, opts = {}) ⇒ Object

Non-destructive version of #sort!



1785
1786
1787
# File 'lib/daru/dataframe.rb', line 1785

def sort vector_order, opts={}
  dup.sort! vector_order, opts
end

#sort!(vector_order, opts = {}) ⇒ Object

Sorts a dataframe (ascending/descending) in the given pripority sequence of vectors, with or without a block.

Examples:

Sort a dataframe with a vector sequence.


df = Daru::DataFrame.new({a: [1,2,1,2,3], b: [5,4,3,2,1]})

df.sort [:a, :b]
# =>
# <Daru::DataFrame:30604000 @name = d6a9294e-2c09-418f-b646-aa9244653444 @size = 5>
#                   a          b
#        2          1          3
#        0          1          5
#        3          2          2
#        1          2          4
#        4          3          1

Sort a dataframe without a block. Here nils will be handled automatically.


df = Daru::DataFrame.new({a: [-3,nil,-1,nil,5], b: [4,3,2,1,4]})

df.sort([:a])
# =>
# <Daru::DataFrame:14810920 @name = c07fb5c7-2201-458d-b679-6a1f7ebfe49f @size = 5>
#                    a          b
#         1        nil          3
#         3        nil          1
#         0         -3          4
#         2         -1          2
#         4          5          4

Sort a dataframe with a block with nils handled automatically.


df = Daru::DataFrame.new({a: [nil,-1,1,nil,-1,1], b: ['aaa','aa',nil,'baaa','x',nil] })

df.sort [:b], by: {b: lambda { |a| a.length } }
# NoMethodError: undefined method `length' for nil:NilClass
# from (pry):8:in `block in __pry__'

df.sort [:b], by: {b: lambda { |a| a.length } }, handle_nils: true

# =>
# <Daru::DataFrame:28469540 @name = 5f986508-556f-468b-be0c-88cc3534445c @size = 6>
#                    a          b
#         2          1        nil
#         5          1        nil
#         4         -1          x
#         1         -1         aa
#         0        nil        aaa
#         3        nil       baaa

Sort a dataframe with a block with nils handled manually.


df = Daru::DataFrame.new({a: [nil,-1,1,nil,-1,1], b: ['aaa','aa',nil,'baaa','x',nil] })

# To print nils at the bottom one can use lambda { |a| (a.nil?)[1]:[0,a.length] }
df.sort [:b], by: {b: lambda { |a| (a.nil?)?[1]:[0,a.length] } }, handle_nils: true

# =>
#<Daru::DataFrame:22214180 @name = cd7703c7-1dca-4560-840b-5ea51a852ef9 @size = 6>
#                 a          b
#      4         -1          x
#      1         -1         aa
#      0        nil        aaa
#      3        nil       baaa
#      2          1        nil
#      5          1        nil

Parameters:

  • vector_order (Array)

    The order of vector names in which the DataFrame should be sorted.

  • opts (Hash) (defaults to: {})

    opts The options to sort with.

Options Hash (opts):

  • :ascending (TrueClass, FalseClass, Array) — default: true

    Sort in ascending or descending order. Specify Array corresponding to order for multiple sort orders.

  • :by (Hash) — default: lambda{|a| a }

    Specify attributes of objects to to be used for sorting, for each vector name in order as a hash of vector name and lambda expressions. In case a lambda for a vector is not specified, the default will be used.

  • :handle_nils (TrueClass, FalseClass, Array) — default: false

    Handle nils automatically or not when a block is provided. If set to True, nils will appear at top after sorting.

Raises:

  • (ArgumentError)


1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
# File 'lib/daru/dataframe.rb', line 1761

def sort! vector_order, opts={}
  raise ArgumentError, 'Required atleast one vector name' if vector_order.empty?

  # To enable sorting with categorical data,
  # map categories to integers preserving their order
  old = convert_categorical_vectors vector_order
  block = sort_prepare_block vector_order, opts

  order = @index.size.times.sort(&block)
  new_index = @index.reorder order

  # To reverse map mapping of categorical data to integers
  restore_categorical_vectors old

  @data.each do |vector|
    vector.reorder! order
  end

  self.index = new_index

  self
end

#split_by_category(cat_name) ⇒ Array

Split the dataframe into many dataframes based on category vector

Examples:

df = Daru::DataFrame.new({
  a: [1, 2, 3],
  b: ['a', 'a', 'b']
})
df.to_category :b
df.split_by_category :b
# => [#<Daru::DataFrame: a (2x1)>
#       a
#   0   1
#   1   2,
# #<Daru::DataFrame: b (1x1)>
#       a
#   2   3]

Parameters:

  • cat_name (object)

    name of category vector to split the dataframe

Returns:

  • (Array)

    array of dataframes split by category with category vector used to split not included

Raises:

  • (ArguementError)


2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
# File 'lib/daru/dataframe.rb', line 2265

def split_by_category cat_name
  cat_dv = self[cat_name]
  raise ArguementError, "#{cat_name} is not a category vector" unless
    cat_dv.category?

  cat_dv.categories.map do |cat|
    where(cat_dv.eq cat)
      .rename(cat)
      .delete_vector cat_name
  end
end

#summaryString

Generate a summary of this DataFrame based on individual vectors in the DataFrame

Returns:

  • (String)

    String containing the summary of the DataFrame



1668
1669
1670
1671
1672
1673
1674
1675
1676
# File 'lib/daru/dataframe.rb', line 1668

def summary
  summary = "= #{name}"
  summary << "\n  Number of rows: #{nrows}"
  @vectors.each do |v|
    summary << "\n  Element:[#{v}]\n"
    summary << self[v].summary(1)
  end
  summary
end

#tail(quantity = 10) ⇒ Object Also known as: last

The last ten elements of the DataFrame

Parameters:

  • quantity (Fixnum) (defaults to: 10)

    (10) The number of elements to display from the bottom.



1374
1375
1376
1377
# File 'lib/daru/dataframe.rb', line 1374

def tail quantity=10
  start = [-quantity, -size].max
  row.at start..-1
end

#to_aObject

Converts the DataFrame into an array of hashes where key is vector name and value is the corresponding element. The 0th index of the array contains the array of hashes while the 1th index contains the indexes of each row of the dataframe. Each element in the index array corresponds to its row in the array of hashes, which has the same index.



2014
2015
2016
# File 'lib/daru/dataframe.rb', line 2014

def to_a
  [each_row.map(&:to_h), @index.to_a]
end

#to_category(*names) ⇒ Daru::DataFrame

Converts the specified non category type vectors to category type vectors

Examples:

df = Daru::DataFrame.new({
  a: [1, 2, 3],
  b: ['a', 'a', 'b']
})
df.to_category :b
df[:b].type
# => :category

Parameters:

  • names (Array)

    of non category type vectors to be converted

Returns:

  • (Daru::DataFrame)

    data frame in which specified vectors have been converted to category type



2213
2214
2215
2216
# File 'lib/daru/dataframe.rb', line 2213

def to_category *names
  names.each { |n| self[n] = self[n].to_category }
  self
end

#to_dfself

Returns the dataframe. This can be convenient when the user does not know whether the object is a vector or a dataframe.

Returns:

  • (self)

    the dataframe



1979
1980
1981
# File 'lib/daru/dataframe.rb', line 1979

def to_df
  self
end

#to_gslObject

Convert all numeric vectors to GSL::Matrix



1984
1985
1986
1987
1988
# File 'lib/daru/dataframe.rb', line 1984

def to_gsl
  numerics_as_arrays = numeric_vectors.map { |n| self[n].to_a }

  GSL::Matrix.alloc(*numerics_as_arrays.transpose)
end

#to_hObject

Converts DataFrame to a hash (explicit) with keys as vector names and values as the corresponding vectors.



2030
2031
2032
2033
2034
# File 'lib/daru/dataframe.rb', line 2030

def to_h
  @vectors
    .each_with_index
    .map { |vec_name, idx| [vec_name, @data[idx]] }.to_h
end

#to_html(threshold = 30) ⇒ Object

Convert to html for IRuby.



2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
# File 'lib/daru/dataframe.rb', line 2037

def to_html(threshold=30)
  table_thead = to_html_thead
  table_tbody = to_html_tbody(threshold)
  path = if index.is_a?(MultiIndex)
           File.expand_path('../iruby/templates/dataframe_mi.html.erb', __FILE__)
         else
           File.expand_path('../iruby/templates/dataframe.html.erb', __FILE__)
         end
  ERB.new(File.read(path).strip).result(binding)
end

#to_html_tbody(threshold = 30) ⇒ Object



2058
2059
2060
2061
2062
2063
2064
2065
2066
# File 'lib/daru/dataframe.rb', line 2058

def to_html_tbody(threshold=30)
  table_tbody_path =
    if index.is_a?(MultiIndex)
      File.expand_path('../iruby/templates/dataframe_mi_tbody.html.erb', __FILE__)
    else
      File.expand_path('../iruby/templates/dataframe_tbody.html.erb', __FILE__)
    end
  ERB.new(File.read(table_tbody_path).strip).result(binding)
end

#to_html_theadObject



2048
2049
2050
2051
2052
2053
2054
2055
2056
# File 'lib/daru/dataframe.rb', line 2048

def to_html_thead
  table_thead_path =
    if index.is_a?(MultiIndex)
      File.expand_path('../iruby/templates/dataframe_mi_thead.html.erb', __FILE__)
    else
      File.expand_path('../iruby/templates/dataframe_thead.html.erb', __FILE__)
    end
  ERB.new(File.read(table_thead_path).strip).result(binding)
end

#to_json(no_index = true) ⇒ Object

Convert to json. If no_index is false then the index will NOT be included in the JSON thus created.



2020
2021
2022
2023
2024
2025
2026
# File 'lib/daru/dataframe.rb', line 2020

def to_json no_index=true
  if no_index
    to_a[0].to_json
  else
    to_a.to_json
  end
end

#to_matrixObject

Convert all vectors of type :numeric into a Matrix.



1991
1992
1993
# File 'lib/daru/dataframe.rb', line 1991

def to_matrix
  Matrix.columns each_vector.select(&:numeric?).map(&:to_a)
end

#to_nmatrixObject

Convert all vectors of type :numeric and not containing nils into an NMatrix.



2003
2004
2005
2006
2007
# File 'lib/daru/dataframe.rb', line 2003

def to_nmatrix
  each_vector.select do |vector|
    vector.numeric? && !vector.include_values?(*Daru::MISSING_VALUES)
  end.map(&:to_a).transpose.to_nm
end

#to_nyaplotdfObject

Return a Nyaplot::DataFrame from the data of this DataFrame. :nocov:



1997
1998
1999
# File 'lib/daru/dataframe.rb', line 1997

def to_nyaplotdf
  Nyaplot::DataFrame.new(to_a[0])
end

#to_REXPObject

rubocop:disable Style/MethodName



5
6
7
8
9
10
11
12
13
# File 'lib/daru/extensions/rserve.rb', line 5

def to_REXP # rubocop:disable Style/MethodName
  names = @vectors.to_a
  data  = names.map do |f|
    Rserve::REXP::Wrapper.wrap(self[f].to_a)
  end
  l = Rserve::Rlist.new(data, names.map(&:to_s))

  Rserve::REXP.create_data_frame(l)
end

#to_sObject



2068
2069
2070
# File 'lib/daru/dataframe.rb', line 2068

def to_s
  "#<#{self.class}#{': ' + @name.to_s if @name}(#{nrows}x#{ncols})>"
end

#transposeObject

Transpose a DataFrame, tranposing elements and row, column indexing.



2164
2165
2166
2167
2168
2169
2170
2171
2172
# File 'lib/daru/dataframe.rb', line 2164

def transpose
  Daru::DataFrame.new(
    each_vector.map(&:to_a).transpose,
    index: @vectors,
    order: @index,
    dtype: @dtype,
    name: @name
  )
end

#union(other_df) ⇒ Object

Concatenates another DataFrame as #concat. Additionally it tries to preserve the index. If the indices contain common elements, #union will overwrite the according rows in the first dataframe.



1521
1522
1523
1524
1525
1526
1527
1528
# File 'lib/daru/dataframe.rb', line 1521

def union other_df
  index = (@index.to_a + other_df.index.to_a).uniq
  df = row[*(@index.to_a - other_df.index.to_a)]

  df = df.concat(other_df)
  df.index = Daru::Index.new(index)
  df
end

#uniq(*vtrs) ⇒ Object

Return unique rows by vector specified or all vectors

Examples:


=> #<Daru::DataFrame(6x2)>
     a   b
 0   1   a
 1   2   b
 2   3   c
 3   4   d
 2   3   c
 3   4   f

2.3.3 :> df.unique
=> #<Daru::DataFrame(5x2)>
     a   b
 0   1   a
 1   2   b
 2   3   c
 3   4   d
 3   4   f

2.3.3 :> df.unique(:a)
=> #<Daru::DataFrame(5x2)>
     a   b
 0   1   a
 1   2   b
 2   3   c
 3   4   d

Parameters:

  • vtrs (String)
    Symbol

    vector names(s) that should be considered



754
755
756
757
758
759
# File 'lib/daru/dataframe.rb', line 754

def uniq(*vtrs)
  vecs = vtrs.empty? ? vectors.map(&:to_s) : Array(vtrs)
  grouped = group_by(vecs)
  indexes = grouped.groups.values.map { |v| v[0] }.sort
  row[*indexes]
end

#updateObject

Method for updating the metadata (i.e. missing value positions) of the after assingment/deletion etc. are complete. This is provided so that time is not wasted in creating the metadata for the vector each time assignment/deletion of elements is done. Updating data this way is called lazy loading. To set or unset lazy loading, see the .lazy_update= method.



2077
2078
2079
# File 'lib/daru/dataframe.rb', line 2077

def update
  @data.each(&:update) if Daru.lazy_update
end

#vector_by_calculation(&block) ⇒ Object

DSL for yielding each row and returning a Daru::Vector based on the value each run of the block returns.

Usage

a1 = Daru::Vector.new([1, 2, 3, 4, 5, 6, 7])
a2 = Daru::Vector.new([10, 20, 30, 40, 50, 60, 70])
a3 = Daru::Vector.new([100, 200, 300, 400, 500, 600, 700])
ds = Daru::DataFrame.new({ :a => a1, :b => a2, :c => a3 })
total = ds.vector_by_calculation { a + b + c }
# <Daru::Vector:82314050 @name = nil @size = 7 >
#   nil
# 0 111
# 1 222
# 2 333
# 3 444
# 4 555
# 5 666
# 6 777


1182
1183
1184
1185
1186
# File 'lib/daru/dataframe.rb', line 1182

def vector_by_calculation &block
  a = each_row.map { |r| r.instance_eval(&block) }

  Daru::Vector.new a, index: @index
end

#vector_count_characters(vecs = nil) ⇒ Object



1287
1288
1289
1290
1291
1292
1293
# File 'lib/daru/dataframe.rb', line 1287

def vector_count_characters vecs=nil
  vecs ||= @vectors.to_a

  collect_rows do |row|
    vecs.map { |v| row[v].to_s.size }.inject(:+)
  end
end

#vector_mean(max_missing = 0) ⇒ Object

Calculate mean of the rows of the dataframe.

Arguments

  • max_missing - The maximum number of elements in the row that can be

zero for the mean calculation to happen. Default to 0.



1443
1444
1445
1446
1447
1448
1449
1450
1451
# File 'lib/daru/dataframe.rb', line 1443

def vector_mean max_missing=0
  # FIXME: in vector_sum we preserve created vector dtype, but
  # here we are not. Is this by design or ...? - zverok, 2016-05-18
  mean_vec = Daru::Vector.new [0]*@size, index: @index, name: "mean_#{@name}"

  each_row_with_index.each_with_object(mean_vec) do |(row, i), memo|
    memo[i] = row.indexes(*Daru::MISSING_VALUES).size > max_missing ? nil : row.mean
  end
end

#vector_sum(*args) ⇒ Object

Sum all numeric/specified vectors in the DataFrame.

Returns a new vector that’s a containing a sum of all numeric or specified vectors of the DataFrame. By default, if the vector contains a nil, the sum is nil. With :skipnil argument set to true, nil values are assumed to be 0 (zero) and the sum vector is returned.

Examples:

df = Daru::DataFrame.new({
   a: [1, 2, nil],
   b: [2, 1, 3],
   c: [1, 1, 1]
 })
=> #<Daru::DataFrame(3x3)>
       a   b   c
   0   1   2   1
   1   2   1   1
   2 nil   3   1
df.vector_sum [:a, :c]
=> #<Daru::Vector(3)>
   0   2
   1   3
   2 nil
df.vector_sum
=> #<Daru::Vector(3)>
   0   4
   1   4
   2 nil
df.vector_sum skipnil: true
=> #<Daru::Vector(3)>
       c
   0   4
   1   4
   2   4

Parameters:

  • args (Array)

    List of vectors to sum. Default is nil in which case all numeric vectors are summed.

  • opts (Hash)

    a customizable set of options

Returns:

  • Vector with sum of all vectors specified in the argument. If vecs parameter is empty, sum all numeric vector.



1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
# File 'lib/daru/dataframe.rb', line 1425

def vector_sum(*args)
  defaults = {vecs: nil, skipnil: false}
  options = args.last.is_a?(::Hash) ? args.pop : {}
  options = defaults.merge(options)
  vecs = args[0] || options[:vecs]
  skipnil = args[1] || options[:skipnil]

  vecs ||= numeric_vectors
  sum = Daru::Vector.new [0]*@size, index: @index, name: @name, dtype: @dtype
  vecs.inject(sum) { |memo, n| self[n].add(memo, skipnil: skipnil) }
end

#verify(*tests) ⇒ Object

Test each row with one or more tests. The function returns an array with all errors.

FIXME: description here is too sparse. As far as I can get, it should tell something about that each test is [descr, fields, block], and that first value may be column name to output. - zverok, 2016-05-18

Parameters:

  • tests (Proc)

    Each test is a Proc with the form *Proc.new {|row| row > 0}*



1154
1155
1156
1157
1158
1159
1160
1161
# File 'lib/daru/dataframe.rb', line 1154

def verify(*tests)
  id = tests.first.is_a?(Symbol) ? tests.shift : @vectors.first

  each_row_with_index.map do |row, i|
    tests.reject { |*_, block| block.call(row) }
         .map { |test| verify_error_message row, test, id, i }
  end.flatten
end

#where(bool_array) ⇒ Object

Query a DataFrame by passing a Daru::Core::Query::BoolArray object.



2189
2190
2191
# File 'lib/daru/dataframe.rb', line 2189

def where bool_array
  Daru::Core::Query.df_where self, bool_array
end

#which(&block) ⇒ Object

a simple query DSL for accessing where(), inspired by gem “squeel” e.g.: df.which{ ‘FamilySize` == `FamilySize`.max } equals df.where( df.eq( df.max ) )

e.g.: df.which{ (‘NameTitle` == ’Dr’) & (‘Sex` == ’female’) } equals df.where( df.eq(‘Dr’) & df.eq(‘female’) )



15
16
17
# File 'lib/daru/extensions/which_dsl.rb', line 15

def which(&block)
  WhichQuery.new(self, &block).exec
end

#write_csv(filename, opts = {}) ⇒ Object

Write this DataFrame to a CSV file.

Arguements

  • filename - Path of CSV file where the DataFrame is to be saved.

Options

  • convert_comma - If set to true, will convert any commas in any

of the data to full stops (‘.’). All the options accepted by CSV.read() can also be passed into this function.



2101
2102
2103
# File 'lib/daru/dataframe.rb', line 2101

def write_csv filename, opts={}
  Daru::IO.dataframe_write_csv self, filename, opts
end

#write_excel(filename, opts = {}) ⇒ Object

Write this dataframe to an Excel Spreadsheet

Arguments

  • filename - The path of the file where the DataFrame should be written.



2110
2111
2112
# File 'lib/daru/dataframe.rb', line 2110

def write_excel filename, opts={}
  Daru::IO.dataframe_write_excel self, filename, opts
end

#write_sql(dbh, table) ⇒ Object

Insert each case of the Dataset on the selected table

Arguments

  • dbh - DBI database connection object.

  • query - Query string.

Usage

ds = Daru::DataFrame.new({:id=>Daru::Vector.new([1,2,3]), :name=>Daru::Vector.new(["a","b","c"])})
dbh = DBI.connect("DBI:Mysql:database:localhost", "user", "password")
ds.write_sql(dbh,"test")


2126
2127
2128
# File 'lib/daru/dataframe.rb', line 2126

def write_sql dbh, table
  Daru::IO.dataframe_write_sql self, dbh, table
end