daru_lite 0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.github/ISSUE_TEMPLATE.md +18 -0
- data/.github/workflows/ci.yml +33 -0
- data/.gitignore +10 -0
- data/.rspec +2 -0
- data/.rubocop.yml +27 -0
- data/.rubocop_todo.yml +137 -0
- data/CONTRIBUTING.md +47 -0
- data/Gemfile +2 -0
- data/History.md +4 -0
- data/LICENSE +24 -0
- data/README.md +218 -0
- data/Rakefile +69 -0
- data/ReleasePolicy.md +20 -0
- data/benchmarks/TradeoffData.csv +65 -0
- data/benchmarks/csv_reading.rb +22 -0
- data/benchmarks/dataframe_creation.rb +39 -0
- data/benchmarks/db_loading.rb +34 -0
- data/benchmarks/duplicating.rb +45 -0
- data/benchmarks/group_by.rb +32 -0
- data/benchmarks/joining.rb +52 -0
- data/benchmarks/row_access.rb +41 -0
- data/benchmarks/row_assign.rb +36 -0
- data/benchmarks/sorting.rb +51 -0
- data/benchmarks/statistics.rb +28 -0
- data/benchmarks/vector_access.rb +31 -0
- data/benchmarks/vector_assign.rb +42 -0
- data/benchmarks/where_clause.rb +48 -0
- data/benchmarks/where_vs_filter.rb +28 -0
- data/daru_lite.gemspec +55 -0
- data/images/README.md +5 -0
- 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/lib/daru_lite/accessors/array_wrapper.rb +109 -0
- data/lib/daru_lite/accessors/dataframe_by_row.rb +25 -0
- data/lib/daru_lite/accessors/mdarray_wrapper.rb +7 -0
- data/lib/daru_lite/category.rb +929 -0
- data/lib/daru_lite/configuration.rb +34 -0
- data/lib/daru_lite/core/group_by.rb +403 -0
- data/lib/daru_lite/core/merge.rb +270 -0
- data/lib/daru_lite/core/query.rb +109 -0
- data/lib/daru_lite/dataframe.rb +3080 -0
- data/lib/daru_lite/date_time/index.rb +569 -0
- data/lib/daru_lite/date_time/offsets.rb +397 -0
- data/lib/daru_lite/exceptions.rb +2 -0
- data/lib/daru_lite/extensions/which_dsl.rb +53 -0
- data/lib/daru_lite/formatters/table.rb +52 -0
- data/lib/daru_lite/helpers/array.rb +53 -0
- data/lib/daru_lite/index/categorical_index.rb +201 -0
- data/lib/daru_lite/index/index.rb +374 -0
- data/lib/daru_lite/index/multi_index.rb +374 -0
- data/lib/daru_lite/io/csv/converters.rb +21 -0
- data/lib/daru_lite/io/io.rb +294 -0
- data/lib/daru_lite/io/sql_data_source.rb +97 -0
- data/lib/daru_lite/iruby/helpers.rb +38 -0
- data/lib/daru_lite/iruby/templates/dataframe.html.erb +5 -0
- data/lib/daru_lite/iruby/templates/dataframe_mi.html.erb +5 -0
- data/lib/daru_lite/iruby/templates/dataframe_mi_tbody.html.erb +35 -0
- data/lib/daru_lite/iruby/templates/dataframe_mi_thead.html.erb +21 -0
- data/lib/daru_lite/iruby/templates/dataframe_tbody.html.erb +28 -0
- data/lib/daru_lite/iruby/templates/dataframe_thead.html.erb +21 -0
- data/lib/daru_lite/iruby/templates/multi_index.html.erb +12 -0
- data/lib/daru_lite/iruby/templates/vector.html.erb +5 -0
- data/lib/daru_lite/iruby/templates/vector_mi.html.erb +5 -0
- data/lib/daru_lite/iruby/templates/vector_mi_tbody.html.erb +26 -0
- data/lib/daru_lite/iruby/templates/vector_mi_thead.html.erb +8 -0
- data/lib/daru_lite/iruby/templates/vector_tbody.html.erb +17 -0
- data/lib/daru_lite/iruby/templates/vector_thead.html.erb +8 -0
- data/lib/daru_lite/maths/arithmetic/dataframe.rb +91 -0
- data/lib/daru_lite/maths/arithmetic/vector.rb +117 -0
- data/lib/daru_lite/maths/statistics/dataframe.rb +202 -0
- data/lib/daru_lite/maths/statistics/vector.rb +1019 -0
- data/lib/daru_lite/monkeys.rb +56 -0
- data/lib/daru_lite/vector.rb +1678 -0
- data/lib/daru_lite/version.rb +3 -0
- data/lib/daru_lite.rb +99 -0
- data/profile/_base.rb +23 -0
- data/profile/df_to_a.rb +10 -0
- data/profile/filter.rb +13 -0
- data/profile/joining.rb +13 -0
- data/profile/sorting.rb +12 -0
- data/profile/vector_each_with_index.rb +9 -0
- data/profile/vector_new.rb +9 -0
- data/spec/accessors/array_wrapper_spec.rb +3 -0
- data/spec/category_spec.rb +1741 -0
- data/spec/core/group_by_spec.rb +655 -0
- data/spec/core/merge_spec.rb +179 -0
- data/spec/core/query_spec.rb +347 -0
- data/spec/daru_lite_spec.rb +22 -0
- data/spec/dataframe_spec.rb +4330 -0
- data/spec/date_time/data_spec.rb +197 -0
- data/spec/date_time/date_time_index_helper_spec.rb +72 -0
- data/spec/date_time/index_spec.rb +588 -0
- data/spec/date_time/offsets_spec.rb +465 -0
- data/spec/extensions/which_dsl_spec.rb +38 -0
- data/spec/fixtures/bank2.dat +200 -0
- data/spec/fixtures/boolean_converter_test.csv +5 -0
- data/spec/fixtures/countries.json +7794 -0
- data/spec/fixtures/duplicates.csv +32 -0
- data/spec/fixtures/eciresults.html +394 -0
- data/spec/fixtures/empties.dat +2 -0
- data/spec/fixtures/empty_rows_test.csv +17 -0
- data/spec/fixtures/macau.html +3691 -0
- data/spec/fixtures/macd_data.csv +150 -0
- data/spec/fixtures/matrix_test.csv +100 -0
- data/spec/fixtures/moneycontrol.html +6812 -0
- data/spec/fixtures/music_data.tsv +2501 -0
- data/spec/fixtures/repeated_fields.csv +7 -0
- data/spec/fixtures/sales-funnel.csv +18 -0
- data/spec/fixtures/scientific_notation.csv +4 -0
- data/spec/fixtures/string_converter_test.csv +5 -0
- data/spec/fixtures/strings.dat +2 -0
- 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 +62 -0
- data/spec/fixtures/wiki_climate.html +1243 -0
- data/spec/fixtures/wiki_table_info.html +631 -0
- data/spec/formatters/table_formatter_spec.rb +137 -0
- data/spec/helpers_spec.rb +8 -0
- data/spec/index/categorical_index_spec.rb +170 -0
- data/spec/index/index_spec.rb +417 -0
- data/spec/index/multi_index_spec.rb +680 -0
- data/spec/io/io_spec.rb +373 -0
- data/spec/io/sql_data_source_spec.rb +56 -0
- data/spec/iruby/dataframe_spec.rb +170 -0
- data/spec/iruby/helpers_spec.rb +49 -0
- data/spec/iruby/multi_index_spec.rb +37 -0
- data/spec/iruby/vector_spec.rb +105 -0
- data/spec/maths/arithmetic/dataframe_spec.rb +148 -0
- data/spec/maths/arithmetic/vector_spec.rb +165 -0
- data/spec/maths/statistics/dataframe_spec.rb +178 -0
- data/spec/maths/statistics/vector_spec.rb +756 -0
- data/spec/monkeys_spec.rb +42 -0
- data/spec/shared/vector_display_spec.rb +213 -0
- data/spec/spec_helper.rb +87 -0
- data/spec/support/database_helper.rb +30 -0
- data/spec/support/matchers.rb +5 -0
- data/spec/vector_spec.rb +2293 -0
- metadata +571 -0
@@ -0,0 +1,179 @@
|
|
1
|
+
describe DaruLite::DataFrame do
|
2
|
+
context "#join" do
|
3
|
+
before do
|
4
|
+
@left = DaruLite::DataFrame.new({
|
5
|
+
:id => [1,2,3,4],
|
6
|
+
:name => ['Pirate', 'Monkey', 'Ninja', 'Spaghetti']
|
7
|
+
})
|
8
|
+
@right = DaruLite::DataFrame.new({
|
9
|
+
:id => [1,2,3,4],
|
10
|
+
:name => ['Rutabaga', 'Pirate', 'Darth Vader', 'Ninja']
|
11
|
+
})
|
12
|
+
@right_many = DaruLite::DataFrame.new({
|
13
|
+
:id => [1,1,1,1],
|
14
|
+
:name => ['Rutabaga', 'Pirate', 'Darth Vader', 'Ninja']
|
15
|
+
})
|
16
|
+
@empty = DaruLite::DataFrame.new({
|
17
|
+
:id => [],
|
18
|
+
:name => []
|
19
|
+
})
|
20
|
+
end
|
21
|
+
|
22
|
+
it "performs an inner join of two dataframes" do
|
23
|
+
answer = DaruLite::DataFrame.new({
|
24
|
+
:id_1 => [3,1],
|
25
|
+
:name => ['Ninja', 'Pirate'],
|
26
|
+
:id_2 => [4,2]
|
27
|
+
}, order: [:id_1, :name, :id_2])
|
28
|
+
expect(@left.join(@right, how: :inner, on: [:name])).to eq(answer)
|
29
|
+
end
|
30
|
+
|
31
|
+
it "performs an inner join of two dataframes that has one to many mapping" do
|
32
|
+
answer = DaruLite::DataFrame.new({
|
33
|
+
:name_1 => ['Pirate', 'Pirate', 'Pirate', 'Pirate'],
|
34
|
+
:id => [1,1,1,1],
|
35
|
+
:name_2 => ['Rutabaga', 'Pirate', 'Darth Vader', 'Ninja']
|
36
|
+
}, order: [:name_1, :id, :name_2])
|
37
|
+
expect(@left.join(@right_many, how: :inner, on: [:id])).to eq(answer)
|
38
|
+
end
|
39
|
+
|
40
|
+
it "performs an inner join of two dataframes that has many to one mapping" do
|
41
|
+
left_many = @right_many
|
42
|
+
right = @left
|
43
|
+
|
44
|
+
answer = DaruLite::DataFrame.new({
|
45
|
+
:name_2 => ['Pirate', 'Pirate', 'Pirate', 'Pirate'],
|
46
|
+
:id => [1,1,1,1],
|
47
|
+
:name_1 => ['Rutabaga', 'Pirate', 'Darth Vader', 'Ninja']
|
48
|
+
}, order: [:name_1, :id, :name_2])
|
49
|
+
expect(left_many.join(right, how: :inner, on: [:id])).to eq(answer)
|
50
|
+
end
|
51
|
+
|
52
|
+
it "performs an inner join of two dataframes that has many to many mapping" do
|
53
|
+
@left[:id].recode! { |v| v == 2 ? 1 : v }
|
54
|
+
answer = DaruLite::DataFrame.new({
|
55
|
+
:name_1 => ['Pirate', 'Pirate', 'Pirate', 'Pirate', 'Monkey', 'Monkey', 'Monkey', 'Monkey'],
|
56
|
+
:id => [1,1,1,1,1,1,1,1],
|
57
|
+
:name_2 => ['Rutabaga', 'Pirate', 'Darth Vader', 'Ninja', 'Rutabaga', 'Pirate', 'Darth Vader', 'Ninja']
|
58
|
+
}, order: [:name_1, :id, :name_2])
|
59
|
+
expect(@left.join(@right_many, how: :inner, on: [:id])).to eq(answer)
|
60
|
+
end
|
61
|
+
|
62
|
+
it "performs a full outer join" do
|
63
|
+
answer = DaruLite::DataFrame.new({
|
64
|
+
:id_1 => [nil,2,3,1,nil,4],
|
65
|
+
:name => ["Darth Vader", "Monkey", "Ninja", "Pirate", "Rutabaga", "Spaghetti"],
|
66
|
+
:id_2 => [3,nil,4,2,1,nil]
|
67
|
+
}, order: [:id_1, :name, :id_2])
|
68
|
+
expect(@left.join(@right, how: :outer, on: [:name])).to eq(answer)
|
69
|
+
end
|
70
|
+
|
71
|
+
it "adds a left/right indicator" do
|
72
|
+
answer = DaruLite::DataFrame.new({
|
73
|
+
:id_1 => [nil,2,3,1,nil,4],
|
74
|
+
:name => ["Darth Vader", "Monkey", "Ninja", "Pirate", "Rutabaga", "Spaghetti"],
|
75
|
+
:id_2 => [3,nil,4,2,1,nil]
|
76
|
+
}, order: [:id_1, :name, :id_2])
|
77
|
+
|
78
|
+
outer = @left.join(@right, how: :outer, on: [:name], indicator: :my_indicator)
|
79
|
+
expect(outer[:my_indicator].to_a).to eq [:right_only, :left_only, :both, :both, :right_only, :left_only]
|
80
|
+
end
|
81
|
+
|
82
|
+
|
83
|
+
it "performs a full outer join when the right join keys have nils" do
|
84
|
+
@right[:name].recode! { |v| v == 'Rutabaga' ? nil : v }
|
85
|
+
answer = DaruLite::DataFrame.new({
|
86
|
+
:id_1 => [nil, nil,2,3,1,4],
|
87
|
+
:name => [nil, "Darth Vader", "Monkey", "Ninja", "Pirate", "Spaghetti"],
|
88
|
+
:id_2 => [1,3,nil,4,2,nil]
|
89
|
+
}, order: [:id_1, :name, :id_2])
|
90
|
+
expect(@left.join(@right, how: :outer, on: [:name])).to eq(answer)
|
91
|
+
end
|
92
|
+
|
93
|
+
it "performs a full outer join when the left join keys have nils" do
|
94
|
+
@left[:name].recode! { |v| v == 'Monkey' ? nil : v }
|
95
|
+
answer = DaruLite::DataFrame.new({
|
96
|
+
:id_1 => [2,nil,3,1,nil,4],
|
97
|
+
:name => [nil, "Darth Vader", "Ninja", "Pirate", "Rutabaga", "Spaghetti"],
|
98
|
+
:id_2 => [nil,3,4,2,1,nil]
|
99
|
+
}, order: [:id_1, :name, :id_2])
|
100
|
+
expect(@left.join(@right, how: :outer, on: [:name])).to eq(answer)
|
101
|
+
end
|
102
|
+
|
103
|
+
it "performs a full outer join when both left and right join keys have nils" do
|
104
|
+
@left[:name].recode! { |v| v == 'Monkey' ? nil : v }
|
105
|
+
@right[:name].recode! { |v| v == 'Rutabaga' ? nil : v }
|
106
|
+
|
107
|
+
answer = DaruLite::DataFrame.new({
|
108
|
+
:id_1 => [nil,2,nil,3,1,4],
|
109
|
+
:name => [nil, nil, "Darth Vader", "Ninja", "Pirate", "Spaghetti"],
|
110
|
+
:id_2 => [1,nil,3,4,2,nil]
|
111
|
+
}, order: [:id_1, :name, :id_2])
|
112
|
+
expect(@left.join(@right, how: :outer, on: [:name])).to eq(answer)
|
113
|
+
end
|
114
|
+
|
115
|
+
it "performs a left outer join" do
|
116
|
+
answer = DaruLite::DataFrame.new({
|
117
|
+
:id_1 => [2,3,1,4],
|
118
|
+
:name => ["Monkey", "Ninja", "Pirate", "Spaghetti"],
|
119
|
+
:id_2 => [nil,4,2,nil]
|
120
|
+
}, order: [:id_1, :name, :id_2])
|
121
|
+
expect(@left.join(@right, how: :left, on: [:name])).to eq(answer)
|
122
|
+
end
|
123
|
+
|
124
|
+
it "performs a left join with an empty dataframe" do
|
125
|
+
|
126
|
+
answer = DaruLite::DataFrame.new({
|
127
|
+
:id_1 => [2,3,1,4],
|
128
|
+
:name => ["Monkey", "Ninja", "Pirate", "Spaghetti"],
|
129
|
+
:id_2 => [nil,nil,nil,nil]
|
130
|
+
}, order: [:id_1, :name, :id_2])
|
131
|
+
|
132
|
+
expect(@left.join(@empty, how: :left, on: [:name])).to eq(answer)
|
133
|
+
end
|
134
|
+
|
135
|
+
it "performs a right outer join" do
|
136
|
+
answer = DaruLite::DataFrame.new({
|
137
|
+
:id_1 => [nil,3,1,nil],
|
138
|
+
:name => ["Darth Vader", "Ninja", "Pirate", "Rutabaga"],
|
139
|
+
:id_2 => [3,4,2,1]
|
140
|
+
}, order: [:id_1, :name, :id_2])
|
141
|
+
expect(@left.join(@right, how: :right, on: [:name])).to eq(answer)
|
142
|
+
end
|
143
|
+
|
144
|
+
it "doesn't convert false into nil when joining boolean values" do
|
145
|
+
left = DaruLite::DataFrame.new({ key: [1,2,3], left_value: [true, false, true] })
|
146
|
+
right = DaruLite::DataFrame.new({ key: [1,2,3], right_value: [true, false, true] })
|
147
|
+
|
148
|
+
answer = DaruLite::DataFrame.new({
|
149
|
+
left_value: [true, false, true],
|
150
|
+
key: [1,2,3],
|
151
|
+
right_value: [true, false, true]
|
152
|
+
}, order: [:left_value, :key, :right_value] )
|
153
|
+
|
154
|
+
expect(left.join(right, on: [:key], how: :inner)).to eq answer
|
155
|
+
end
|
156
|
+
|
157
|
+
it "raises if :on field are absent in one of dataframes" do
|
158
|
+
@right.vectors = DaruLite::Index.new [:id, :other_name]
|
159
|
+
expect { @left.join(@right, how: :right, on: [:name]) }.to \
|
160
|
+
raise_error(ArgumentError, /Both dataframes expected .* :name/)
|
161
|
+
|
162
|
+
expect { @left.join(@right, how: :right, on: [:other_name]) }.to \
|
163
|
+
raise_error(ArgumentError, /Both dataframes expected .* :other_name/)
|
164
|
+
end
|
165
|
+
|
166
|
+
it "is able to join by several :on fields" do
|
167
|
+
@left.gender = ['m', 'f', 'm', nil]
|
168
|
+
@right.gender = ['m', 'm', nil, 'f']
|
169
|
+
|
170
|
+
answer = DaruLite::DataFrame.new({
|
171
|
+
id_1: [1],
|
172
|
+
name: ['Pirate'],
|
173
|
+
gender: ['m'],
|
174
|
+
id_2: [2]
|
175
|
+
}, order: [:id_1, :name, :gender, :id_2])
|
176
|
+
expect(@left.join(@right, how: :inner, on: [:name, :gender])).to eq(answer)
|
177
|
+
end
|
178
|
+
end
|
179
|
+
end
|
@@ -0,0 +1,347 @@
|
|
1
|
+
describe DaruLite::Core::Query::BoolArray do
|
2
|
+
before do
|
3
|
+
@klass = DaruLite::Core::Query::BoolArray
|
4
|
+
@left = @klass.new([true, true, true, false, false, true])
|
5
|
+
@right = @klass.new([false, false, false, false, true, false])
|
6
|
+
end
|
7
|
+
|
8
|
+
context "#&" do
|
9
|
+
it "computes and logic of each element in the array" do
|
10
|
+
expect(@left & @right).to eq(
|
11
|
+
@klass.new([false, false, false, false, false, false]))
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
15
|
+
context "#|" do
|
16
|
+
it "computes or logic of each element in arrays" do
|
17
|
+
expect(@left | @right).to eq(
|
18
|
+
@klass.new([true, true, true, false, true, true]))
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
context "#!" do
|
23
|
+
it "computes not logic of each element" do
|
24
|
+
expect(!@left).to eq(
|
25
|
+
@klass.new([false, false, false, true, true, false])
|
26
|
+
)
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
30
|
+
context '#inspect' do
|
31
|
+
it 'is reasonable' do
|
32
|
+
expect(@left.inspect).to eq "#<DaruLite::Core::Query::BoolArray:#{@left.object_id} bool_arry=[true, true, true, false, false, true]>"
|
33
|
+
end
|
34
|
+
end
|
35
|
+
end
|
36
|
+
|
37
|
+
describe "Arel-like syntax" do
|
38
|
+
describe "comparison operators" do
|
39
|
+
describe DaruLite::Vector do
|
40
|
+
describe "non-categorical type" do
|
41
|
+
before do
|
42
|
+
@vector = DaruLite::Vector.new([23,51,1214,352,32,11])
|
43
|
+
@comparator = DaruLite::Vector.new([45,22,1214,55,32,9])
|
44
|
+
@klass = DaruLite::Core::Query::BoolArray
|
45
|
+
end
|
46
|
+
|
47
|
+
context "#eq" do
|
48
|
+
it "accepts scalar value" do
|
49
|
+
expect(@vector.eq(352)).to eq(
|
50
|
+
@klass.new([false,false,false,true,false,false]))
|
51
|
+
end
|
52
|
+
|
53
|
+
it "accepts vector and compares corrensponding elements" do
|
54
|
+
expect(@vector.eq(@comparator)).to eq(
|
55
|
+
@klass.new([false,false,true,false,true,false]))
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
59
|
+
context "#not_eq" do
|
60
|
+
it "accepts scalar value" do
|
61
|
+
expect(@vector.not_eq(51)).to eq(
|
62
|
+
@klass.new([true, false, true, true, true, true]))
|
63
|
+
end
|
64
|
+
|
65
|
+
it "accepts vector and compares corrensponding elements" do
|
66
|
+
expect(@vector.not_eq(@comparator)).to eq(
|
67
|
+
@klass.new([true, true, false, true, false, true]))
|
68
|
+
end
|
69
|
+
end
|
70
|
+
|
71
|
+
context "#lt" do
|
72
|
+
it "accepts scalar value" do
|
73
|
+
expect(@vector.lt(51)).to eq(
|
74
|
+
@klass.new([true, false, false, false, true, true]))
|
75
|
+
end
|
76
|
+
|
77
|
+
it "accepts vector and compares corrensponding elements" do
|
78
|
+
expect(@vector.lt(@comparator)).to eq(
|
79
|
+
@klass.new([true,false,false,false,false,false]))
|
80
|
+
end
|
81
|
+
end
|
82
|
+
|
83
|
+
context "#lteq" do
|
84
|
+
it "accepts scalar value" do
|
85
|
+
expect(@vector.lteq(51)).to eq(
|
86
|
+
@klass.new([true, true, false, false, true, true]))
|
87
|
+
end
|
88
|
+
|
89
|
+
it "accepts vector and compares corrensponding elements" do
|
90
|
+
expect(@vector.lteq(@comparator)).to eq(
|
91
|
+
@klass.new([true,false,true,false,true,false]))
|
92
|
+
end
|
93
|
+
end
|
94
|
+
|
95
|
+
context "#mt" do
|
96
|
+
it "accepts scalar value" do
|
97
|
+
expect(@vector.mt(51)).to eq(
|
98
|
+
@klass.new([false, false, true, true, false, false]))
|
99
|
+
end
|
100
|
+
|
101
|
+
it "accepts vector and compares corrensponding elements" do
|
102
|
+
expect(@vector.mt(@comparator)).to eq(
|
103
|
+
@klass.new([false,true,false,true,false,true]))
|
104
|
+
end
|
105
|
+
end
|
106
|
+
|
107
|
+
context "#mteq" do
|
108
|
+
it "accepts scalar value" do
|
109
|
+
expect(@vector.mteq(51)).to eq(
|
110
|
+
@klass.new([false, true, true, true, false, false]))
|
111
|
+
end
|
112
|
+
|
113
|
+
it "accepts vector and compares corrensponding elements" do
|
114
|
+
expect(@vector.mteq(@comparator)).to eq(
|
115
|
+
@klass.new([false,true,true,true,true,true]))
|
116
|
+
end
|
117
|
+
end
|
118
|
+
|
119
|
+
context "#in" do
|
120
|
+
it "checks if any of elements in the arg are present in the vector" do
|
121
|
+
expect(@vector.in([23,55,1,33,32])).to eq(
|
122
|
+
@klass.new([true, false, false, false, true, false]))
|
123
|
+
end
|
124
|
+
end
|
125
|
+
end
|
126
|
+
|
127
|
+
describe "categorical type" do
|
128
|
+
let(:dv) { DaruLite::Vector.new ['e', 'd', 'd', 'x', 'x'],
|
129
|
+
categories: ['a', 'x', 'c', 'd', 'e'], type: :category }
|
130
|
+
let(:comp) { DaruLite::Vector.new ['a', 'd', 'x', 'e', 'x'],
|
131
|
+
categories: ['a', 'x', 'c', 'd', 'e'], type: :category }
|
132
|
+
let(:query_bool_class) { DaruLite::Core::Query::BoolArray }
|
133
|
+
|
134
|
+
context "#eq" do
|
135
|
+
context "scalar" do
|
136
|
+
subject { dv.eq 'd' }
|
137
|
+
|
138
|
+
it { is_expected.to be_a query_bool_class }
|
139
|
+
its(:to_a) { is_expected.to eq [false, true, true, false, false] }
|
140
|
+
end
|
141
|
+
|
142
|
+
context "vector" do
|
143
|
+
subject { dv.eq comp }
|
144
|
+
|
145
|
+
it { is_expected.to be_a query_bool_class }
|
146
|
+
its(:to_a) { is_expected.to eq [false, true, false, false, true] }
|
147
|
+
end
|
148
|
+
end
|
149
|
+
|
150
|
+
context "#not_eq" do
|
151
|
+
context "scalar" do
|
152
|
+
subject { dv.not_eq 'd' }
|
153
|
+
|
154
|
+
it { is_expected.to be_a query_bool_class }
|
155
|
+
its(:to_a) { is_expected.to eq [true, false, false, true, true] }
|
156
|
+
end
|
157
|
+
|
158
|
+
context "vector" do
|
159
|
+
subject { dv.not_eq comp }
|
160
|
+
|
161
|
+
it { is_expected.to be_a query_bool_class }
|
162
|
+
its(:to_a) { is_expected.to eq [true, false, true, true, false] }
|
163
|
+
end
|
164
|
+
end
|
165
|
+
|
166
|
+
context "#lt" do
|
167
|
+
context "scalar" do
|
168
|
+
subject { dv.lt 'd' }
|
169
|
+
|
170
|
+
it { is_expected.to be_a query_bool_class }
|
171
|
+
its(:to_a) { is_expected.to eq [false, false, false, true, true] }
|
172
|
+
end
|
173
|
+
|
174
|
+
context "vector" do
|
175
|
+
subject { dv.lt comp }
|
176
|
+
|
177
|
+
it { is_expected.to be_a query_bool_class }
|
178
|
+
its(:to_a) { is_expected.to eq [false, false, false, true, false] }
|
179
|
+
end
|
180
|
+
end
|
181
|
+
|
182
|
+
context "#lteq" do
|
183
|
+
context "scalar" do
|
184
|
+
subject { dv.lteq 'd' }
|
185
|
+
|
186
|
+
it { is_expected.to be_a query_bool_class }
|
187
|
+
its(:to_a) { is_expected.to eq [false, true, true, true, true] }
|
188
|
+
end
|
189
|
+
|
190
|
+
context "vector" do
|
191
|
+
subject { dv.lteq comp }
|
192
|
+
|
193
|
+
it { is_expected.to be_a query_bool_class }
|
194
|
+
its(:to_a) { is_expected.to eq [false, true, false, true, true] }
|
195
|
+
end
|
196
|
+
end
|
197
|
+
|
198
|
+
context "#mt" do
|
199
|
+
context "scalar" do
|
200
|
+
subject { dv.mt 'd' }
|
201
|
+
|
202
|
+
it { is_expected.to be_a query_bool_class }
|
203
|
+
its(:to_a) { is_expected.to eq [true, false, false, false, false] }
|
204
|
+
end
|
205
|
+
|
206
|
+
context "vector" do
|
207
|
+
subject { dv.mt comp }
|
208
|
+
|
209
|
+
it { is_expected.to be_a query_bool_class }
|
210
|
+
its(:to_a) { is_expected.to eq [true, false, true, false, false] }
|
211
|
+
end
|
212
|
+
end
|
213
|
+
|
214
|
+
context "#mteq" do
|
215
|
+
context "scalar" do
|
216
|
+
subject { dv.mteq 'd' }
|
217
|
+
|
218
|
+
it { is_expected.to be_a query_bool_class }
|
219
|
+
its(:to_a) { is_expected.to eq [true, true, true, false, false] }
|
220
|
+
end
|
221
|
+
|
222
|
+
context "vector" do
|
223
|
+
subject { dv.mteq comp }
|
224
|
+
|
225
|
+
it { is_expected.to be_a query_bool_class }
|
226
|
+
its(:to_a) { is_expected.to eq [true, true, true, false, true] }
|
227
|
+
end
|
228
|
+
end
|
229
|
+
|
230
|
+
# context "#in" do
|
231
|
+
# subject { dv.in ['b', 'd'] }
|
232
|
+
# it { is_expected.to be_a query_bool_class }
|
233
|
+
# its(:to_a) { is_expected.to eq [false, true, true, true, true] }
|
234
|
+
# end
|
235
|
+
end
|
236
|
+
end
|
237
|
+
end
|
238
|
+
|
239
|
+
describe "where clause" do
|
240
|
+
context DaruLite::DataFrame do
|
241
|
+
before do
|
242
|
+
@df = DaruLite::DataFrame.new({
|
243
|
+
number: [1,2,3,4,5,6,Float::NAN],
|
244
|
+
sym: [:one, :two, :three, :four, :five, :six, :seven],
|
245
|
+
names: ['sameer', 'john', 'james', 'omisha', 'priyanka', 'shravan',nil]
|
246
|
+
})
|
247
|
+
end
|
248
|
+
|
249
|
+
it "accepts simple single eq statement" do
|
250
|
+
answer = DaruLite::DataFrame.new({
|
251
|
+
number: [4],
|
252
|
+
sym: [:four],
|
253
|
+
names: ['omisha']
|
254
|
+
}, index: DaruLite::Index.new([3])
|
255
|
+
)
|
256
|
+
expect(@df.where(@df[:number].eq(4))).to eq(answer)
|
257
|
+
end
|
258
|
+
|
259
|
+
it "accepts somewhat complex comparison operator chaining" do
|
260
|
+
answer = DaruLite::DataFrame.new({
|
261
|
+
number: [3,4],
|
262
|
+
sym: [:three, :four],
|
263
|
+
names: ['james', 'omisha']
|
264
|
+
}, index: DaruLite::Index.new([2,3]))
|
265
|
+
expect(
|
266
|
+
@df.where (@df[:names].eq('james') | @df[:sym].eq(:four))
|
267
|
+
).to eq(answer)
|
268
|
+
end
|
269
|
+
|
270
|
+
let(:dv) { DaruLite::Vector.new([1,11,32,Float::NAN,nil]) }
|
271
|
+
it "handles empty data" do
|
272
|
+
expect(dv.where(dv.lt(14))).to eq(DaruLite::Vector.new([1,11]))
|
273
|
+
end
|
274
|
+
|
275
|
+
it "does not give SystemStackError" do
|
276
|
+
v = DaruLite::Vector.new [1]*300_000
|
277
|
+
expect { v.where v.eq(1) }.not_to raise_error
|
278
|
+
end
|
279
|
+
end
|
280
|
+
|
281
|
+
context DaruLite::Vector do
|
282
|
+
context "non-categorical type" do
|
283
|
+
before do
|
284
|
+
@vector = DaruLite::Vector.new([2,5,1,22,51,4,nil,Float::NAN])
|
285
|
+
end
|
286
|
+
|
287
|
+
it "accepts a simple single statement" do
|
288
|
+
expect(@vector.where(@vector.lt(10))).to eq(
|
289
|
+
DaruLite::Vector.new([2,5,1,4], index: DaruLite::Index.new([0,1,2,5])))
|
290
|
+
end
|
291
|
+
|
292
|
+
it "accepts somewhat complex operator chaining" do
|
293
|
+
expect(@vector.where((@vector.lt(6) | @vector.eq(51)))).to eq(
|
294
|
+
DaruLite::Vector.new([2,5,1,51,4], index: DaruLite::Index.new([0,1,2,4,5])))
|
295
|
+
end
|
296
|
+
end
|
297
|
+
|
298
|
+
context "categorical type" do
|
299
|
+
let(:dv) { DaruLite::Vector.new ['a', 'c', 'x', 'x', 'c'],
|
300
|
+
categories: ['a', 'x', 'c'], type: :category }
|
301
|
+
|
302
|
+
context "simple single statement" do
|
303
|
+
subject { dv.where(dv.lt('x')) }
|
304
|
+
|
305
|
+
it { is_expected.to be_a DaruLite::Vector }
|
306
|
+
its(:type) { is_expected.to eq :category }
|
307
|
+
its(:to_a) { is_expected.to eq ['a'] }
|
308
|
+
its(:'index.to_a') { is_expected.to eq [0] }
|
309
|
+
end
|
310
|
+
|
311
|
+
context "complex operator chaining" do
|
312
|
+
subject { dv.where((dv.lt('x') | dv.eq('c'))) }
|
313
|
+
|
314
|
+
it { is_expected.to be_a DaruLite::Vector }
|
315
|
+
its(:type) { is_expected.to eq :category }
|
316
|
+
its(:to_a) { is_expected.to eq ['a', 'c', 'c'] }
|
317
|
+
its(:'index.to_a') { is_expected.to eq [0, 1, 4] }
|
318
|
+
end
|
319
|
+
|
320
|
+
context "preserve categories" do
|
321
|
+
subject { dv.where((dv.lt('x') | dv.eq('c'))) }
|
322
|
+
|
323
|
+
it { is_expected.to be_a DaruLite::Vector }
|
324
|
+
its(:type) { is_expected.to eq :category }
|
325
|
+
its(:to_a) { is_expected.to eq ['a', 'c', 'c'] }
|
326
|
+
its(:'index.to_a') { is_expected.to eq [0, 1, 4] }
|
327
|
+
its(:categories) { is_expected.to eq ['a', 'x', 'c'] }
|
328
|
+
end
|
329
|
+
end
|
330
|
+
|
331
|
+
it "preserves name" do
|
332
|
+
named_vector = DaruLite::Vector.new([1,2,3], name: 'named')
|
333
|
+
expect(named_vector.where(named_vector.lteq(2)).name).to eq('named')
|
334
|
+
end
|
335
|
+
end
|
336
|
+
end
|
337
|
+
|
338
|
+
describe "apply_where" do
|
339
|
+
context "matches regexp with block input" do
|
340
|
+
subject { dv.apply_where(dv.match /weeks/) { |x| "#{x.split.first.to_i * 7} days" } }
|
341
|
+
|
342
|
+
let(:dv) { DaruLite::Vector.new ['3 days', '5 weeks', '2 weeks'] }
|
343
|
+
|
344
|
+
it { is_expected.to eq(DaruLite::Vector.new ['3 days', '35 days', '14 days']) }
|
345
|
+
end
|
346
|
+
end
|
347
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe '#error' do
|
4
|
+
context 'by default' do
|
5
|
+
it { expect { DaruLite.error('test') }.to output("test\n").to_stderr_from_any_process }
|
6
|
+
end
|
7
|
+
|
8
|
+
context 'when set to nil' do
|
9
|
+
before { DaruLite.error_stream = nil }
|
10
|
+
it { expect { DaruLite.error('test') }.not_to output('test').to_stderr_from_any_process }
|
11
|
+
end
|
12
|
+
|
13
|
+
context 'when set to instance of custom class' do
|
14
|
+
let(:custom_stream) { double(puts: nil) }
|
15
|
+
before { DaruLite.error_stream = custom_stream }
|
16
|
+
|
17
|
+
it 'calls puts' do
|
18
|
+
expect { DaruLite.error('test') }.not_to output('test').to_stderr_from_any_process
|
19
|
+
expect(custom_stream).to have_received(:puts).with('test')
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|