daru_lite 0.3.3 → 0.3.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/History.md +60 -0
- data/README.md +1 -1
- data/lib/daru_lite/category.rb +1 -1
- data/lib/daru_lite/data_frame/duplicatable.rb +7 -1
- data/lib/daru_lite/data_frame/fetchable.rb +1 -1
- data/lib/daru_lite/data_frame/iterable.rb +5 -2
- data/lib/daru_lite/data_frame/sortable.rb +13 -5
- data/lib/daru_lite/dataframe.rb +52 -11
- data/lib/daru_lite/date_time/index.rb +2 -2
- data/lib/daru_lite/index/categorical_index.rb +62 -0
- data/lib/daru_lite/index/multi_index.rb +24 -6
- data/lib/daru_lite/maths/statistics/dataframe.rb +9 -5
- data/lib/daru_lite/maths/statistics/vector.rb +1 -1
- data/lib/daru_lite/version.rb +1 -1
- data/lib/daru_lite.rb +1 -0
- metadata +54 -284
- data/.github/ISSUE_TEMPLATE/bug_report.md +0 -38
- data/.github/ISSUE_TEMPLATE/feature_request.md +0 -20
- data/.github/dependabot.yml +0 -11
- data/.github/workflows/ci.yml +0 -33
- data/.gitignore +0 -10
- data/.rspec +0 -2
- data/.rubocop.yml +0 -27
- data/.rubocop_todo.yml +0 -139
- data/CONTRIBUTING.md +0 -47
- data/Gemfile +0 -2
- data/Rakefile +0 -69
- data/ReleasePolicy.md +0 -20
- data/benchmarks/TradeoffData.csv +0 -65
- data/benchmarks/csv_reading.rb +0 -22
- data/benchmarks/dataframe_creation.rb +0 -39
- data/benchmarks/db_loading.rb +0 -33
- data/benchmarks/duplicating.rb +0 -45
- data/benchmarks/group_by.rb +0 -32
- data/benchmarks/joining.rb +0 -52
- data/benchmarks/row_access.rb +0 -41
- data/benchmarks/row_assign.rb +0 -36
- data/benchmarks/sorting.rb +0 -51
- data/benchmarks/statistics.rb +0 -28
- data/benchmarks/vector_access.rb +0 -31
- data/benchmarks/vector_assign.rb +0 -42
- data/benchmarks/where_clause.rb +0 -48
- data/benchmarks/where_vs_filter.rb +0 -28
- data/daru_lite.gemspec +0 -54
- data/daru_lite_test-shm +0 -0
- data/daru_lite_test-wal +0 -0
- data/images/README.md +0 -5
- data/images/con0.png +0 -0
- data/images/con1.png +0 -0
- data/images/init0.png +0 -0
- data/images/init1.png +0 -0
- data/images/man0.png +0 -0
- data/images/man1.png +0 -0
- data/images/man2.png +0 -0
- data/images/man3.png +0 -0
- data/images/man4.png +0 -0
- data/images/man5.png +0 -0
- data/images/man6.png +0 -0
- data/profile/_base.rb +0 -23
- data/profile/df_to_a.rb +0 -10
- data/profile/filter.rb +0 -13
- data/profile/joining.rb +0 -13
- data/profile/sorting.rb +0 -12
- data/profile/vector_each_with_index.rb +0 -9
- data/profile/vector_new.rb +0 -9
- data/spec/accessors/array_wrapper_spec.rb +0 -3
- data/spec/category_spec.rb +0 -1741
- data/spec/core/group_by_spec.rb +0 -655
- data/spec/core/merge_spec.rb +0 -179
- data/spec/core/query_spec.rb +0 -347
- data/spec/daru_lite_spec.rb +0 -22
- data/spec/data_frame/aggregatable_example.rb +0 -65
- data/spec/data_frame/buildable_example.rb +0 -109
- data/spec/data_frame/calculatable_example.rb +0 -135
- data/spec/data_frame/convertible_example.rb +0 -180
- data/spec/data_frame/duplicatable_example.rb +0 -111
- data/spec/data_frame/fetchable_example.rb +0 -481
- data/spec/data_frame/filterable_example.rb +0 -456
- data/spec/data_frame/indexable_example.rb +0 -221
- data/spec/data_frame/iterable_example.rb +0 -465
- data/spec/data_frame/joinable_example.rb +0 -131
- data/spec/data_frame/missable_example.rb +0 -47
- data/spec/data_frame/pivotable_example.rb +0 -297
- data/spec/data_frame/queryable_example.rb +0 -92
- data/spec/data_frame/setable_example.rb +0 -482
- data/spec/data_frame/sortable_example.rb +0 -350
- data/spec/dataframe_spec.rb +0 -1306
- data/spec/date_time/data_spec.rb +0 -197
- data/spec/date_time/date_time_index_helper_spec.rb +0 -72
- data/spec/date_time/index_spec.rb +0 -588
- data/spec/date_time/offsets_spec.rb +0 -465
- data/spec/extensions/which_dsl_spec.rb +0 -38
- data/spec/fixtures/bank2.dat +0 -200
- data/spec/fixtures/boolean_converter_test.csv +0 -5
- data/spec/fixtures/countries.json +0 -7794
- data/spec/fixtures/duplicates.csv +0 -32
- data/spec/fixtures/eciresults.html +0 -394
- data/spec/fixtures/empties.dat +0 -2
- data/spec/fixtures/empty_rows_test.csv +0 -17
- data/spec/fixtures/macau.html +0 -3691
- data/spec/fixtures/macd_data.csv +0 -150
- data/spec/fixtures/matrix_test.csv +0 -100
- data/spec/fixtures/moneycontrol.html +0 -6812
- data/spec/fixtures/music_data.tsv +0 -2501
- data/spec/fixtures/repeated_fields.csv +0 -7
- data/spec/fixtures/sales-funnel.csv +0 -18
- data/spec/fixtures/scientific_notation.csv +0 -4
- data/spec/fixtures/string_converter_test.csv +0 -5
- data/spec/fixtures/strings.dat +0 -2
- data/spec/fixtures/test_xls.xls +0 -0
- data/spec/fixtures/test_xls_2.xls +0 -0
- data/spec/fixtures/url_test.txt~ +0 -0
- data/spec/fixtures/valid_markup.html +0 -62
- data/spec/fixtures/wiki_climate.html +0 -1243
- data/spec/fixtures/wiki_table_info.html +0 -631
- data/spec/formatters/table_formatter_spec.rb +0 -137
- data/spec/helpers_spec.rb +0 -8
- data/spec/index/categorical_index_spec.rb +0 -221
- data/spec/index/index_spec.rb +0 -438
- data/spec/index/multi_index_spec.rb +0 -713
- data/spec/io/io_spec.rb +0 -357
- data/spec/io/sql_data_source_spec.rb +0 -48
- data/spec/iruby/dataframe_spec.rb +0 -170
- data/spec/iruby/helpers_spec.rb +0 -49
- data/spec/iruby/multi_index_spec.rb +0 -37
- data/spec/iruby/vector_spec.rb +0 -105
- data/spec/maths/arithmetic/dataframe_spec.rb +0 -148
- data/spec/maths/arithmetic/vector_spec.rb +0 -165
- data/spec/maths/statistics/dataframe_spec.rb +0 -178
- data/spec/maths/statistics/vector_spec.rb +0 -756
- data/spec/monkeys_spec.rb +0 -42
- data/spec/shared/vector_display_spec.rb +0 -213
- data/spec/spec_helper.rb +0 -87
- data/spec/support/database_helper.rb +0 -29
- data/spec/support/matchers.rb +0 -5
- data/spec/vector/aggregatable_example.rb +0 -27
- data/spec/vector/calculatable_example.rb +0 -82
- data/spec/vector/convertible_example.rb +0 -126
- data/spec/vector/duplicatable_example.rb +0 -48
- data/spec/vector/fetchable_example.rb +0 -463
- data/spec/vector/filterable_example.rb +0 -165
- data/spec/vector/indexable_example.rb +0 -201
- data/spec/vector/iterable_example.rb +0 -111
- data/spec/vector/joinable_example.rb +0 -25
- data/spec/vector/missable_example.rb +0 -88
- data/spec/vector/queryable_example.rb +0 -91
- data/spec/vector/setable_example.rb +0 -300
- data/spec/vector/sortable_example.rb +0 -242
- data/spec/vector_spec.rb +0 -599
data/benchmarks/sorting.rb
DELETED
|
@@ -1,51 +0,0 @@
|
|
|
1
|
-
$:.unshift File.expand_path("../../lib", __FILE__)
|
|
2
|
-
|
|
3
|
-
require 'benchmark'
|
|
4
|
-
require 'daru_lite'
|
|
5
|
-
|
|
6
|
-
vector = DaruLite::Vector.new(10000.times.map.to_a.shuffle)
|
|
7
|
-
df = DaruLite::DataFrame.new({
|
|
8
|
-
a: vector,
|
|
9
|
-
b: vector,
|
|
10
|
-
c: vector
|
|
11
|
-
})
|
|
12
|
-
Benchmark.bm do |x|
|
|
13
|
-
x.report("Sort a Vector without any args") do
|
|
14
|
-
vector.sort
|
|
15
|
-
end
|
|
16
|
-
|
|
17
|
-
x.report("Sort vector in descending order with custom <=> operator") do
|
|
18
|
-
vector.sort(ascending: false) { |a,b| a.to_s <=> b.to_s }
|
|
19
|
-
end
|
|
20
|
-
|
|
21
|
-
x.report("Sort single column of DataFrame") do
|
|
22
|
-
df.sort([:a])
|
|
23
|
-
end
|
|
24
|
-
|
|
25
|
-
x.report("Sort two columns of DataFrame") do
|
|
26
|
-
df.sort([:c,:a])
|
|
27
|
-
end
|
|
28
|
-
|
|
29
|
-
x.report("Sort two columns with custom operators in different orders of DataFrame") do
|
|
30
|
-
df.sort([:c,:a], ascending: [true, false],
|
|
31
|
-
by: { c: lambda { |a| a.to_s },
|
|
32
|
-
a: lambda { |a| a+1 } })
|
|
33
|
-
end
|
|
34
|
-
end
|
|
35
|
-
|
|
36
|
-
# FIXME: MASSIVE SPEEDUP NECESSARY!
|
|
37
|
-
|
|
38
|
-
# ===== Benchamarks =====
|
|
39
|
-
# user system total real
|
|
40
|
-
# Sort a Vector without any args 0.130000 0.000000 0.130000 ( 0.128006)
|
|
41
|
-
# Sort vector in descending order with custom <=> operator 0.190000 0.000000 0.190000 ( 0.184604)
|
|
42
|
-
# Sort single column of DataFrame 2502.450000 0.000000 2502.450000 (2503.808073)
|
|
43
|
-
# Sort two columns of DataFrame 0.540000 0.000000 0.540000 ( 0.537670)
|
|
44
|
-
# Sort two columns with custom operators in different orders of DataFrame 2084.160000 7.260000 2091.420000 (2092.716603)
|
|
45
|
-
|
|
46
|
-
# ===== Current Benchamarks =====
|
|
47
|
-
# Sort a Vector without any args 0.070000 0.000000 0.070000 ( 0.070323)
|
|
48
|
-
# Sort vector in descending order with custom <=> operator 0.120000 0.000000 0.120000 ( 0.119462)
|
|
49
|
-
# Sort single column of DataFrame 0.940000 0.010000 0.950000 ( 0.950349)
|
|
50
|
-
# Sort two columns of DataFrame 1.490000 0.010000 1.500000 ( 1.505680)
|
|
51
|
-
# Sort two columns with custom operators in different orders of DataFrame 1.480000 0.000000 1.480000 ( 1.495839)
|
data/benchmarks/statistics.rb
DELETED
|
@@ -1,28 +0,0 @@
|
|
|
1
|
-
require 'daru_lite'
|
|
2
|
-
require 'benchmark'
|
|
3
|
-
|
|
4
|
-
vector = DaruLite::Vector.new(
|
|
5
|
-
(10**6).times.map.to_a.shuffle,
|
|
6
|
-
missing_values: 100.times.map.to_a.shuffle
|
|
7
|
-
)
|
|
8
|
-
|
|
9
|
-
vector = DaruLite::Vector.new(
|
|
10
|
-
10000.times.map.to_a.shuffle,
|
|
11
|
-
missing_values: 100.times.map.to_a.shuffle,
|
|
12
|
-
)
|
|
13
|
-
|
|
14
|
-
Benchmark.bm do |x|
|
|
15
|
-
x.report("Mean of a vector") do
|
|
16
|
-
vector.mean
|
|
17
|
-
end
|
|
18
|
-
|
|
19
|
-
x.report("Minimum of a vector") do
|
|
20
|
-
vector.min
|
|
21
|
-
end
|
|
22
|
-
end
|
|
23
|
-
|
|
24
|
-
# ===== Benchmarks =====
|
|
25
|
-
#
|
|
26
|
-
# user system total real
|
|
27
|
-
# Mean of a vector 0.130000 0.010000 0.140000 ( 0.145534)
|
|
28
|
-
# Min of a vector 0.150000 0.000000 0.150000 ( 0.163623)
|
data/benchmarks/vector_access.rb
DELETED
|
@@ -1,31 +0,0 @@
|
|
|
1
|
-
$:.unshift File.expand_path("../../lib", __FILE__)
|
|
2
|
-
|
|
3
|
-
require 'benchmark'
|
|
4
|
-
require 'daru_lite'
|
|
5
|
-
|
|
6
|
-
df = DaruLite::DataFrame.new({
|
|
7
|
-
a: 10000.times.map { rand },
|
|
8
|
-
b: 10000.times.map { rand },
|
|
9
|
-
c: 10000.times.map { rand }
|
|
10
|
-
})
|
|
11
|
-
|
|
12
|
-
Benchmark.bm do |x|
|
|
13
|
-
x.report("Single Vector access") do
|
|
14
|
-
df[:a]
|
|
15
|
-
end
|
|
16
|
-
|
|
17
|
-
x.report("Access as range") do
|
|
18
|
-
df[:a..:c]
|
|
19
|
-
end
|
|
20
|
-
|
|
21
|
-
x.report("Access with commas") do
|
|
22
|
-
df[:a, :c]
|
|
23
|
-
end
|
|
24
|
-
end
|
|
25
|
-
|
|
26
|
-
# ======== Benchmarks =======
|
|
27
|
-
#
|
|
28
|
-
# user system total real
|
|
29
|
-
# Single Vector access 0.000000 0.000000 0.000000 ( 0.000012)
|
|
30
|
-
# Access as range 0.090000 0.000000 0.090000 ( 0.084584)
|
|
31
|
-
# Access with commas 0.050000 0.000000 0.050000 ( 0.051951)
|
data/benchmarks/vector_assign.rb
DELETED
|
@@ -1,42 +0,0 @@
|
|
|
1
|
-
$:.unshift File.expand_path("../../lib", __FILE__)
|
|
2
|
-
|
|
3
|
-
require 'benchmark'
|
|
4
|
-
require 'daru_lite'
|
|
5
|
-
|
|
6
|
-
df = DaruLite::DataFrame.new({
|
|
7
|
-
a: 100000.times.map { rand },
|
|
8
|
-
b: 100000.times.map { rand },
|
|
9
|
-
c: 100000.times.map { rand }
|
|
10
|
-
})
|
|
11
|
-
|
|
12
|
-
index = DaruLite::Index.new((0...100000).to_a.shuffle)
|
|
13
|
-
|
|
14
|
-
Benchmark.bm do |x|
|
|
15
|
-
x.report("Assign new vector as Array") do
|
|
16
|
-
df[:d] = 100000.times.map { rand }
|
|
17
|
-
end
|
|
18
|
-
|
|
19
|
-
x.report("Reassign same vector as Array") do
|
|
20
|
-
df[:a] = 100000.times.map { rand }
|
|
21
|
-
end
|
|
22
|
-
|
|
23
|
-
x.report("Assign new Vector as DaruLite::Vector") do
|
|
24
|
-
df[:e] = DaruLite::Vector.new(100000.times.map { rand })
|
|
25
|
-
end
|
|
26
|
-
|
|
27
|
-
x.report("Reassign same Vector as DaruLite::Vector") do
|
|
28
|
-
df[:b] = DaruLite::Vector.new(100000.times.map { rand })
|
|
29
|
-
end
|
|
30
|
-
|
|
31
|
-
x.report("Reassgin differently indexed DaruLite::Vector") do
|
|
32
|
-
df[:b] = DaruLite::Vector.new(100000.times.map { rand }, index: index)
|
|
33
|
-
end
|
|
34
|
-
end
|
|
35
|
-
|
|
36
|
-
# ===== Benchmarks =====
|
|
37
|
-
# user system total real
|
|
38
|
-
# Assign new vector as Array 0.370000 0.000000 0.370000 (0.364515)
|
|
39
|
-
# Reassign same vector as Array 0.470000 0.000000 0.470000 (0.471408)
|
|
40
|
-
# Assign new Vector as DaruLite::Vector 0.940000 0.000000 0.940000 (0.947879)
|
|
41
|
-
# Reassign same Vector as DaruLite::Vector 0.760000 0.020000 0.780000 (0.769969)
|
|
42
|
-
# Reassgin differently indexed DaruLite::Vector <Too embarassingly slow.>
|
data/benchmarks/where_clause.rb
DELETED
|
@@ -1,48 +0,0 @@
|
|
|
1
|
-
$:.unshift File.expand_path("../../lib", __FILE__)
|
|
2
|
-
|
|
3
|
-
require 'benchmark'
|
|
4
|
-
require 'daru_lite'
|
|
5
|
-
|
|
6
|
-
df = DaruLite::DataFrame.new({
|
|
7
|
-
a: 100000.times.map { |i| i },
|
|
8
|
-
b: 100000.times.map { |i| i },
|
|
9
|
-
c: 100000.times.map { |i| i }
|
|
10
|
-
}, index: DaruLite::Index.new(100000.times.map.to_a.shuffle))
|
|
11
|
-
|
|
12
|
-
puts "Benchmarking DataFrame#where\n"
|
|
13
|
-
Benchmark.bm do |x|
|
|
14
|
-
x.report("Basic one liner") do
|
|
15
|
-
df.where(df[:a].mt(2341))
|
|
16
|
-
end
|
|
17
|
-
|
|
18
|
-
x.report("Little complex statement") do
|
|
19
|
-
df.where(df[:a].lt(235) | df[:b].eq(2341) | df[:c].in([35,355,22]))
|
|
20
|
-
end
|
|
21
|
-
end
|
|
22
|
-
|
|
23
|
-
puts "Benchmarking Vector#where\n"
|
|
24
|
-
v = DaruLite::Vector.new(
|
|
25
|
-
100000.times.map { |i| i }, index: 100000.times.map.to_a.shuffle)
|
|
26
|
-
|
|
27
|
-
Benchmark.bm do |x|
|
|
28
|
-
x.report("Basic one liner") do
|
|
29
|
-
v.where(v.mteq(1000))
|
|
30
|
-
end
|
|
31
|
-
|
|
32
|
-
x.report("Little complex statement") do
|
|
33
|
-
v.where(v.lt(235) & v.eq(2341) | v.in([23,511,55]))
|
|
34
|
-
end
|
|
35
|
-
end
|
|
36
|
-
|
|
37
|
-
# ====== Benchmarks ======
|
|
38
|
-
#
|
|
39
|
-
# Benchmarking DataFrame#where
|
|
40
|
-
#
|
|
41
|
-
# user system total real
|
|
42
|
-
# Basic one liner 0.700000 0.000000 0.700000 (0.703532)
|
|
43
|
-
# Little complex statement 0.120000 0.000000 0.120000 (0.121765)
|
|
44
|
-
#
|
|
45
|
-
# Benchmarking Vector#where
|
|
46
|
-
# user system total real
|
|
47
|
-
# Basic one liner 0.240000 0.000000 0.240000 (0.245787)
|
|
48
|
-
# Little complex statement 0.100000 0.000000 0.100000 (0.094423)
|
|
@@ -1,28 +0,0 @@
|
|
|
1
|
-
$:.unshift File.expand_path("../../lib", __FILE__)
|
|
2
|
-
|
|
3
|
-
require 'benchmark'
|
|
4
|
-
require 'daru_lite'
|
|
5
|
-
|
|
6
|
-
df = DaruLite::DataFrame.new({
|
|
7
|
-
a: [1,2,3,4,5,6]*100,
|
|
8
|
-
b: ['a','b','c','d','e','f']*100,
|
|
9
|
-
c: [11,22,33,44,55,66]*100
|
|
10
|
-
}, index: (1..600).to_a.shuffle)
|
|
11
|
-
|
|
12
|
-
Benchmark.bm do |x|
|
|
13
|
-
x.report("where") do
|
|
14
|
-
df.where(df[:a].eq(2) | df[:c].eq(55))
|
|
15
|
-
end
|
|
16
|
-
|
|
17
|
-
x.report("filter_rows") do
|
|
18
|
-
df.filter(:row) do |r|
|
|
19
|
-
r[:a] == 2 or r[:c] == 55
|
|
20
|
-
end
|
|
21
|
-
end
|
|
22
|
-
end
|
|
23
|
-
|
|
24
|
-
# ===== Benchmarks =====
|
|
25
|
-
#
|
|
26
|
-
# user system total real
|
|
27
|
-
# where 0.000000 0.000000 0.000000 ( 0.002575)
|
|
28
|
-
# filter_rows 0.210000 0.000000 0.210000 ( 0.205403)
|
data/daru_lite.gemspec
DELETED
|
@@ -1,54 +0,0 @@
|
|
|
1
|
-
# coding: utf-8
|
|
2
|
-
$:.unshift File.expand_path("../lib", __FILE__)
|
|
3
|
-
|
|
4
|
-
require 'daru_lite/version.rb'
|
|
5
|
-
|
|
6
|
-
DaruLite::DESCRIPTION = <<MSG
|
|
7
|
-
Daru (Data Analysis in RUby) is a library for analysis, manipulation and visualization
|
|
8
|
-
of data. Daru works seamlessly accross interpreters and leverages interpreter-specific
|
|
9
|
-
optimizations whenever they are available.
|
|
10
|
-
|
|
11
|
-
It is the default data storage gem for all the statsample gems (glm, timeseries, etc.)
|
|
12
|
-
and can be used with many others like mixed_models, gnuplotrb and iruby.
|
|
13
|
-
|
|
14
|
-
Daru Lite is a fork of Daru that aims to focus on data manipulation and stability.
|
|
15
|
-
MSG
|
|
16
|
-
|
|
17
|
-
Gem::Specification.new do |spec|
|
|
18
|
-
spec.name = 'daru_lite'
|
|
19
|
-
spec.version = DaruLite::VERSION
|
|
20
|
-
spec.authors = ['Thomas Naude-Filonnière', 'Maxime Lasserre', 'Julie Thomas', 'Amar Slaoua', 'Mourtada Belhantri']
|
|
21
|
-
spec.summary = %q{Data Analysis in RUby, stripped down}
|
|
22
|
-
spec.description = DaruLite::DESCRIPTION
|
|
23
|
-
spec.homepage = "https://github.com/pollandroll/daru"
|
|
24
|
-
spec.license = 'BSD-2-Clause'
|
|
25
|
-
|
|
26
|
-
spec.files = `git ls-files -z`.split("\x0")
|
|
27
|
-
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
|
28
|
-
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
|
29
|
-
spec.require_paths = ["lib"]
|
|
30
|
-
|
|
31
|
-
spec.add_development_dependency 'activerecord', '~> 8.0'
|
|
32
|
-
spec.add_development_dependency 'awesome_print', '~> 1.9.2'
|
|
33
|
-
spec.add_development_dependency 'bundler', '~> 2.6'
|
|
34
|
-
spec.add_development_dependency 'csv', '~> 3.3.4'
|
|
35
|
-
spec.add_development_dependency 'debug', '>= 1.0.0'
|
|
36
|
-
spec.add_development_dependency 'distribution', '~> 0.8'
|
|
37
|
-
spec.add_development_dependency 'matrix', '~> 0.4.2'
|
|
38
|
-
spec.add_development_dependency 'nokogiri', '~> 1.18.0'
|
|
39
|
-
spec.add_development_dependency 'prime', '~> 0.1.2'
|
|
40
|
-
spec.add_development_dependency 'rake', '~> 13.0'
|
|
41
|
-
spec.add_development_dependency 'rspec', '~> 3.11'
|
|
42
|
-
spec.add_development_dependency 'rspec-its', '~> 2.0.0'
|
|
43
|
-
spec.add_development_dependency 'rubocop', '~> 1.86'
|
|
44
|
-
spec.add_development_dependency 'rubocop-performance', '~> 1.25.0'
|
|
45
|
-
spec.add_development_dependency 'rubocop-rspec', '~> 3.6'
|
|
46
|
-
spec.add_development_dependency 'ruby-prof', '~> 1.7.0'
|
|
47
|
-
spec.add_development_dependency 'simplecov', '~> 0.22.0'
|
|
48
|
-
spec.add_development_dependency 'simplecov_json_formatter', '~> 0.1.4'
|
|
49
|
-
spec.add_development_dependency 'spreadsheet', '~> 1.3.0'
|
|
50
|
-
spec.add_development_dependency 'sqlite3', '~> 2.6.0'
|
|
51
|
-
# issue : https://github.com/SciRuby/daru/issues/493 occured
|
|
52
|
-
# with latest version of sqlite3
|
|
53
|
-
spec.add_development_dependency 'webmock', '~> 3.25.0'
|
|
54
|
-
end
|
data/daru_lite_test-shm
DELETED
|
Binary file
|
data/daru_lite_test-wal
DELETED
|
File without changes
|
data/images/README.md
DELETED
data/images/con0.png
DELETED
|
Binary file
|
data/images/con1.png
DELETED
|
Binary file
|
data/images/init0.png
DELETED
|
Binary file
|
data/images/init1.png
DELETED
|
Binary file
|
data/images/man0.png
DELETED
|
Binary file
|
data/images/man1.png
DELETED
|
Binary file
|
data/images/man2.png
DELETED
|
Binary file
|
data/images/man3.png
DELETED
|
Binary file
|
data/images/man4.png
DELETED
|
Binary file
|
data/images/man5.png
DELETED
|
Binary file
|
data/images/man6.png
DELETED
|
Binary file
|
data/profile/_base.rb
DELETED
|
@@ -1,23 +0,0 @@
|
|
|
1
|
-
$:.unshift File.expand_path("../../lib", __FILE__)
|
|
2
|
-
|
|
3
|
-
require 'ruby-prof'
|
|
4
|
-
require 'fileutils'
|
|
5
|
-
|
|
6
|
-
require 'daru_lite'
|
|
7
|
-
|
|
8
|
-
def __profile__(name = nil)
|
|
9
|
-
# infers name to be "sorting" when called from "profile/sorting.rb:10:in `<main>'"
|
|
10
|
-
name ||= caller.first.split(':').first.split('/').last.sub('.rb', '')
|
|
11
|
-
|
|
12
|
-
path = File.expand_path("../out/#{name}.html", __FILE__)
|
|
13
|
-
FileUtils.mkdir_p File.dirname(path)
|
|
14
|
-
|
|
15
|
-
RubyProf.start
|
|
16
|
-
|
|
17
|
-
yield
|
|
18
|
-
|
|
19
|
-
res = RubyProf.stop
|
|
20
|
-
RubyProf::GraphHtmlPrinter.new(res)
|
|
21
|
-
.print(File.open(path, 'w'))
|
|
22
|
-
|
|
23
|
-
end
|
data/profile/df_to_a.rb
DELETED
data/profile/filter.rb
DELETED
|
@@ -1,13 +0,0 @@
|
|
|
1
|
-
require_relative '_base'
|
|
2
|
-
|
|
3
|
-
df = DaruLite::DataFrame.new({
|
|
4
|
-
a: [1,2,3,4,5,6]*1000,
|
|
5
|
-
b: ['a','b','c','d','e','f']*1000,
|
|
6
|
-
c: [11,22,33,44,55,66]*1000
|
|
7
|
-
}, index: (1..6000).to_a.shuffle)
|
|
8
|
-
|
|
9
|
-
__profile__ do
|
|
10
|
-
df.filter(:row) do |r|
|
|
11
|
-
r[:a] == 2 or r[:c] == 55
|
|
12
|
-
end
|
|
13
|
-
end
|
data/profile/joining.rb
DELETED
|
@@ -1,13 +0,0 @@
|
|
|
1
|
-
require_relative '_base'
|
|
2
|
-
|
|
3
|
-
n = 40_000
|
|
4
|
-
keys = (1..(n)).to_a
|
|
5
|
-
base_data = { idx: 1.upto(n).to_a, keys: 1.upto(n).map { |v| keys[Random.rand(n)]}}
|
|
6
|
-
lookup_hash = keys.map { |k| [k, k * 100]}.to_h
|
|
7
|
-
|
|
8
|
-
base_data_df = DaruLite::DataFrame.new(base_data)
|
|
9
|
-
lookup_df = DaruLite::DataFrame.new(keys: lookup_hash.keys, values: lookup_hash.values)
|
|
10
|
-
|
|
11
|
-
__profile__ do
|
|
12
|
-
base_data_df.join(lookup_df, on: [:keys], how: :inner)
|
|
13
|
-
end
|
data/profile/sorting.rb
DELETED
data/profile/vector_new.rb
DELETED