red_amber 0.2.2 → 0.2.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.rubocop.yml +12 -0
- data/CHANGELOG.md +114 -31
- data/Gemfile +4 -2
- data/README.md +41 -25
- data/benchmark/basic.yml +79 -0
- data/benchmark/combine.yml +63 -0
- data/benchmark/drop_nil.yml +15 -3
- data/benchmark/group.yml +33 -0
- data/benchmark/reshape.yml +27 -0
- data/benchmark/{csv_load_penguins.yml → rover/csv_load_penguins.yml} +3 -3
- data/benchmark/rover/flights.yml +23 -0
- data/benchmark/rover/penguins.yml +23 -0
- data/benchmark/rover/planes.yml +23 -0
- data/benchmark/rover/weather.yml +23 -0
- data/doc/DataFrame.md +332 -53
- data/doc/Vector.md +3 -0
- data/doc/image/dataframe/join.png +0 -0
- data/doc/image/dataframe/set_and_bind.png +0 -0
- data/doc/image/dataframe_model.png +0 -0
- data/lib/red_amber/data_frame.rb +6 -5
- data/lib/red_amber/data_frame_combinable.rb +283 -0
- data/lib/red_amber/data_frame_displayable.rb +2 -0
- data/lib/red_amber/data_frame_selectable.rb +9 -9
- data/lib/red_amber/data_frame_variable_operation.rb +4 -4
- data/lib/red_amber/group.rb +99 -18
- data/lib/red_amber/helper.rb +1 -13
- data/lib/red_amber/vector.rb +7 -0
- data/lib/red_amber/vector_functions.rb +0 -8
- data/lib/red_amber/vector_updatable.rb +60 -65
- data/lib/red_amber/version.rb +1 -1
- data/lib/red_amber.rb +1 -0
- data/red_amber.gemspec +1 -1
- metadata +21 -10
@@ -4,41 +4,47 @@
|
|
4
4
|
# reference: https://arrow.apache.org/docs/cpp/compute.html
|
5
5
|
|
6
6
|
module RedAmber
|
7
|
-
# mix-
|
7
|
+
# mix-in for class Vector
|
8
8
|
# Functions to make up some data (especially missing) for new data.
|
9
9
|
module VectorUpdatable
|
10
10
|
# Replace data
|
11
|
-
# @param
|
12
|
-
# @param replacer [Array, Vector, Arrow::Array] new data to replace for.
|
11
|
+
# @param specifier [Array, Vector, Arrow::Array] index or booleans.
|
12
|
+
# @param replacer [Scalar, Array, Vector, Arrow::Array] new data to replace for.
|
13
13
|
# @return [Vector] Replaced new Vector.
|
14
|
-
# If
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
args
|
20
|
-
when Range
|
21
|
-
normalize_element(args)
|
22
|
-
else
|
23
|
-
Array(args)
|
24
|
-
end
|
25
|
-
replacer = Array(replacer)
|
26
|
-
return self if args.empty? || args[0].nil?
|
14
|
+
# If specifier has no true, return self.
|
15
|
+
#
|
16
|
+
def replace(specifier, replacer)
|
17
|
+
vector = parse_to_vector(Array(specifier))
|
18
|
+
return self if vector.empty? || empty?
|
27
19
|
|
28
|
-
vector = parse_to_vector(args)
|
29
|
-
replacer = nil if replacer.empty?
|
30
20
|
booleans =
|
31
21
|
if vector.boolean?
|
32
|
-
return self unless vector.any
|
33
|
-
|
34
22
|
vector
|
35
23
|
elsif vector.numeric?
|
36
|
-
replacer.sort_by! { |x| args[replacer.index(x)] } if replacer # rubocop:disable Style/SafeNavigation
|
37
24
|
Vector.new(indices).is_in(vector)
|
38
25
|
else
|
39
|
-
raise VectorArgumentError, "Invalid data type #{
|
26
|
+
raise VectorArgumentError, "Invalid data type #{specifier}"
|
27
|
+
end
|
28
|
+
return self if booleans.sum.zero?
|
29
|
+
|
30
|
+
replacer_array =
|
31
|
+
case replacer
|
32
|
+
in []
|
33
|
+
return self
|
34
|
+
in nil | [nil]
|
35
|
+
return replace_to_nil(booleans.data)
|
36
|
+
in Arrow::Array
|
37
|
+
# nop
|
38
|
+
in Vector
|
39
|
+
replacer.data
|
40
|
+
in Array
|
41
|
+
Arrow::Array.new(replacer)
|
42
|
+
else # Broadcast scalar to Array
|
43
|
+
Arrow::Array.new(Array(replacer) * booleans.to_a.count(true))
|
40
44
|
end
|
41
|
-
|
45
|
+
raise VectorArgumentError, 'Replacements size unmatch' if booleans.sum != replacer_array.length
|
46
|
+
|
47
|
+
replace_with(booleans.data, replacer_array)
|
42
48
|
end
|
43
49
|
|
44
50
|
# (related functions)
|
@@ -76,52 +82,41 @@ module RedAmber
|
|
76
82
|
|
77
83
|
private
|
78
84
|
|
79
|
-
#
|
80
|
-
# Replace items selected with a boolean mask
|
85
|
+
# Replace elements selected with a boolean mask
|
81
86
|
#
|
82
|
-
#
|
83
|
-
#
|
84
|
-
#
|
85
|
-
#
|
86
|
-
#
|
87
|
-
# or
|
88
|
-
#
|
89
|
-
|
90
|
-
|
91
|
-
|
92
|
-
|
93
|
-
|
94
|
-
|
95
|
-
|
96
|
-
|
97
|
-
|
98
|
-
else
|
99
|
-
raise VectorTypeError, 'Not a valid type'
|
100
|
-
end
|
101
|
-
raise VectorArgumentError, 'Booleans size unmatch' if specifier.length != size
|
102
|
-
raise VectorArgumentError, 'Booleans not have any `true`' unless specifier.any?
|
103
|
-
|
104
|
-
r = Array(replacer) # scalar to [scalar]
|
105
|
-
r = [nil] if r.empty?
|
106
|
-
|
107
|
-
replacer =
|
108
|
-
if r.size == 1
|
109
|
-
case replacer
|
110
|
-
when Arrow::Array then replacer
|
111
|
-
when Vector then replacer.data
|
112
|
-
else
|
113
|
-
Arrow::Array.new(r * specifier.to_a.count(true)) # broadcast
|
114
|
-
end
|
115
|
-
else
|
116
|
-
Arrow::Array.new(r)
|
117
|
-
end
|
118
|
-
replacer = data.class.new(replacer) if replacer.uniq == [nil]
|
87
|
+
# @param boolean_mask [Arrow::BooleanArray] Boolean mask which indicates the position to be replaced.
|
88
|
+
# - Position with true will be replaced.
|
89
|
+
# - Position with nil will be nil.
|
90
|
+
#
|
91
|
+
# @param replacer [Arrow::Array] Values after replaced
|
92
|
+
# (either scalar or array). If Array is given, original values are replaced by
|
93
|
+
# each element of the array at the corresponding position of mask element.
|
94
|
+
# - `replacer.size` must be equal to `mask.count(true)`.
|
95
|
+
# - Types of self and replacer must be same
|
96
|
+
#
|
97
|
+
# @return [Vector] Replaced vector.
|
98
|
+
# Type of returned Vector is upcasted if needed.
|
99
|
+
#
|
100
|
+
def replace_with(boolean_mask, replacer)
|
101
|
+
raise VectorArgumentError, 'Booleans size unmatch' if boolean_mask.length != size
|
102
|
+
raise VectorArgumentError, 'Booleans not have any `true`' unless boolean_mask.any?
|
119
103
|
|
120
|
-
|
104
|
+
values = replacer.class.new(data) # Upcast
|
121
105
|
|
122
|
-
|
106
|
+
datum = find(:replace_with_mask).execute([values, boolean_mask, replacer])
|
107
|
+
Vector.new(datum.value)
|
108
|
+
end
|
123
109
|
|
124
|
-
|
110
|
+
# Replace elements selected with a boolean mask by nil
|
111
|
+
#
|
112
|
+
# @param boolean_mask [Arrow::BooleanArray] Boolean mask which indicates the position to be replaced.
|
113
|
+
# - Position with true will be replaced by nil
|
114
|
+
# - Position with nil will remain as nil.
|
115
|
+
# @return [Vector] Replaced vector.
|
116
|
+
#
|
117
|
+
def replace_to_nil(boolean_mask)
|
118
|
+
nil_array = data.class.new([nil] * size) # Casted nil Array
|
119
|
+
datum = find(:if_else).execute([boolean_mask, nil_array, data])
|
125
120
|
Vector.new(datum.value)
|
126
121
|
end
|
127
122
|
end
|
data/lib/red_amber/version.rb
CHANGED
data/lib/red_amber.rb
CHANGED
data/red_amber.gemspec
CHANGED
@@ -30,7 +30,7 @@ Gem::Specification.new do |spec|
|
|
30
30
|
spec.executables = spec.files.grep(%r{\Aexe/}) { |f| File.basename(f) }
|
31
31
|
spec.require_paths = ['lib']
|
32
32
|
|
33
|
-
spec.add_dependency 'red-arrow', '
|
33
|
+
spec.add_dependency 'red-arrow', '~> 10.0.0'
|
34
34
|
|
35
35
|
# Development dependency has gone to the Gemfile (rubygems/bundler#7237)
|
36
36
|
|
metadata
CHANGED
@@ -1,29 +1,29 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: red_amber
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Hirokazu SUZUKI (heronshoes)
|
8
|
-
autorequire:
|
8
|
+
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2022-
|
11
|
+
date: 2022-11-16 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: red-arrow
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- - "
|
17
|
+
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version:
|
19
|
+
version: 10.0.0
|
20
20
|
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
|
-
- - "
|
24
|
+
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version:
|
26
|
+
version: 10.0.0
|
27
27
|
description: RedAmber is a simple dataframe library inspired by Rover-df and powered
|
28
28
|
by Red Arrow.
|
29
29
|
email:
|
@@ -40,8 +40,16 @@ files:
|
|
40
40
|
- LICENSE
|
41
41
|
- README.md
|
42
42
|
- Rakefile
|
43
|
-
- benchmark/
|
43
|
+
- benchmark/basic.yml
|
44
|
+
- benchmark/combine.yml
|
44
45
|
- benchmark/drop_nil.yml
|
46
|
+
- benchmark/group.yml
|
47
|
+
- benchmark/reshape.yml
|
48
|
+
- benchmark/rover/csv_load_penguins.yml
|
49
|
+
- benchmark/rover/flights.yml
|
50
|
+
- benchmark/rover/penguins.yml
|
51
|
+
- benchmark/rover/planes.yml
|
52
|
+
- benchmark/rover/weather.yml
|
45
53
|
- doc/CODE_OF_CONDUCT.md
|
46
54
|
- doc/DataFrame.md
|
47
55
|
- doc/Vector.md
|
@@ -50,12 +58,14 @@ files:
|
|
50
58
|
- doc/image/dataframe/assign.png
|
51
59
|
- doc/image/dataframe/assign_operation.png
|
52
60
|
- doc/image/dataframe/drop.png
|
61
|
+
- doc/image/dataframe/join.png
|
53
62
|
- doc/image/dataframe/pick.png
|
54
63
|
- doc/image/dataframe/pick_operation.png
|
55
64
|
- doc/image/dataframe/remove.png
|
56
65
|
- doc/image/dataframe/rename.png
|
57
66
|
- doc/image/dataframe/rename_operation.png
|
58
67
|
- doc/image/dataframe/reshaping_DataFrames.png
|
68
|
+
- doc/image/dataframe/set_and_bind.png
|
59
69
|
- doc/image/dataframe/slice.png
|
60
70
|
- doc/image/dataframe/slice_operation.png
|
61
71
|
- doc/image/dataframe_model.png
|
@@ -76,6 +86,7 @@ files:
|
|
76
86
|
- lib/red-amber.rb
|
77
87
|
- lib/red_amber.rb
|
78
88
|
- lib/red_amber/data_frame.rb
|
89
|
+
- lib/red_amber/data_frame_combinable.rb
|
79
90
|
- lib/red_amber/data_frame_displayable.rb
|
80
91
|
- lib/red_amber/data_frame_indexable.rb
|
81
92
|
- lib/red_amber/data_frame_loadsave.rb
|
@@ -99,7 +110,7 @@ metadata:
|
|
99
110
|
source_code_uri: https://github.com/heronshoes/red_amber
|
100
111
|
changelog_uri: https://github.com/heronshoes/red_amber/blob/main/CHANGELOG.md
|
101
112
|
rubygems_mfa_required: 'true'
|
102
|
-
post_install_message:
|
113
|
+
post_install_message:
|
103
114
|
rdoc_options: []
|
104
115
|
require_paths:
|
105
116
|
- lib
|
@@ -115,7 +126,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
115
126
|
version: '0'
|
116
127
|
requirements: []
|
117
128
|
rubygems_version: 3.3.7
|
118
|
-
signing_key:
|
129
|
+
signing_key:
|
119
130
|
specification_version: 4
|
120
131
|
summary: Simple dataframe library for Ruby
|
121
132
|
test_files: []
|