daru_lite 0.1 → 0.1.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.github/ISSUE_TEMPLATE/bug_report.md +38 -0
- data/.github/ISSUE_TEMPLATE/feature_request.md +20 -0
- data/.github/workflows/ci.yml +20 -0
- data/.rubocop_todo.yml +35 -33
- data/README.md +19 -115
- data/daru_lite.gemspec +1 -0
- data/lib/daru_lite/data_frame/aggregatable.rb +165 -0
- data/lib/daru_lite/data_frame/calculatable.rb +140 -0
- data/lib/daru_lite/data_frame/convertible.rb +107 -0
- data/lib/daru_lite/data_frame/duplicatable.rb +64 -0
- data/lib/daru_lite/data_frame/fetchable.rb +301 -0
- data/lib/daru_lite/data_frame/filterable.rb +144 -0
- data/lib/daru_lite/data_frame/i_o_able.rb +179 -0
- data/lib/daru_lite/data_frame/indexable.rb +168 -0
- data/lib/daru_lite/data_frame/iterable.rb +339 -0
- data/lib/daru_lite/data_frame/joinable.rb +152 -0
- data/lib/daru_lite/data_frame/missable.rb +75 -0
- data/lib/daru_lite/data_frame/pivotable.rb +108 -0
- data/lib/daru_lite/data_frame/queryable.rb +67 -0
- data/lib/daru_lite/data_frame/setable.rb +109 -0
- data/lib/daru_lite/data_frame/sortable.rb +241 -0
- data/lib/daru_lite/dataframe.rb +142 -2355
- data/lib/daru_lite/index/index.rb +13 -0
- data/lib/daru_lite/maths/statistics/vector.rb +1 -1
- data/lib/daru_lite/vector/aggregatable.rb +9 -0
- data/lib/daru_lite/vector/calculatable.rb +78 -0
- data/lib/daru_lite/vector/convertible.rb +77 -0
- data/lib/daru_lite/vector/duplicatable.rb +17 -0
- data/lib/daru_lite/vector/fetchable.rb +175 -0
- data/lib/daru_lite/vector/filterable.rb +128 -0
- data/lib/daru_lite/vector/indexable.rb +77 -0
- data/lib/daru_lite/vector/iterable.rb +95 -0
- data/lib/daru_lite/vector/joinable.rb +17 -0
- data/lib/daru_lite/vector/missable.rb +124 -0
- data/lib/daru_lite/vector/queryable.rb +45 -0
- data/lib/daru_lite/vector/setable.rb +47 -0
- data/lib/daru_lite/vector/sortable.rb +113 -0
- data/lib/daru_lite/vector.rb +36 -932
- data/lib/daru_lite/version.rb +1 -1
- data/spec/data_frame/aggregatable_example.rb +65 -0
- data/spec/data_frame/buildable_example.rb +109 -0
- data/spec/data_frame/calculatable_example.rb +135 -0
- data/spec/data_frame/convertible_example.rb +180 -0
- data/spec/data_frame/duplicatable_example.rb +111 -0
- data/spec/data_frame/fetchable_example.rb +476 -0
- data/spec/data_frame/filterable_example.rb +250 -0
- data/spec/data_frame/indexable_example.rb +221 -0
- data/spec/data_frame/iterable_example.rb +465 -0
- data/spec/data_frame/joinable_example.rb +106 -0
- data/spec/data_frame/missable_example.rb +47 -0
- data/spec/data_frame/pivotable_example.rb +297 -0
- data/spec/data_frame/queryable_example.rb +92 -0
- data/spec/data_frame/setable_example.rb +482 -0
- data/spec/data_frame/sortable_example.rb +350 -0
- data/spec/dataframe_spec.rb +181 -3243
- data/spec/index/index_spec.rb +8 -0
- data/spec/vector/aggregatable_example.rb +27 -0
- data/spec/vector/calculatable_example.rb +82 -0
- data/spec/vector/convertible_example.rb +126 -0
- data/spec/vector/duplicatable_example.rb +48 -0
- data/spec/vector/fetchable_example.rb +463 -0
- data/spec/vector/filterable_example.rb +165 -0
- data/spec/vector/indexable_example.rb +201 -0
- data/spec/vector/iterable_example.rb +111 -0
- data/spec/vector/joinable_example.rb +25 -0
- data/spec/vector/missable_example.rb +88 -0
- data/spec/vector/queryable_example.rb +91 -0
- data/spec/vector/setable_example.rb +300 -0
- data/spec/vector/sortable_example.rb +242 -0
- data/spec/vector_spec.rb +111 -1805
- metadata +102 -3
- data/.github/ISSUE_TEMPLATE.md +0 -18
@@ -0,0 +1,297 @@
|
|
1
|
+
shared_examples_for 'a pivotable DataFrame' do
|
2
|
+
describe "#pivot_table" do
|
3
|
+
let(:df) do
|
4
|
+
DaruLite::DataFrame.new({
|
5
|
+
a: ['foo' , 'foo', 'foo', 'foo', 'foo', 'bar', 'bar', 'bar', 'bar'],
|
6
|
+
b: ['one' , 'one', 'one', 'two', 'two', 'one', 'one', 'two', 'two'],
|
7
|
+
c: ['small','large','large','small','small','large','small','large','small'],
|
8
|
+
d: [1,2,2,3,3,4,5,6,7],
|
9
|
+
e: [2,4,4,6,6,8,10,12,14]
|
10
|
+
})
|
11
|
+
end
|
12
|
+
|
13
|
+
it "creates row index as per (single) index argument and default aggregates to mean" do
|
14
|
+
expect(df.pivot_table(index: [:a])).to eq(DaruLite::DataFrame.new({
|
15
|
+
d: [5.5,2.2],
|
16
|
+
e: [11.0,4.4]
|
17
|
+
}, index: ['bar', 'foo']))
|
18
|
+
end
|
19
|
+
|
20
|
+
it "creates row index as per (double) index argument and default aggregates to mean" do
|
21
|
+
agg_mi = DaruLite::MultiIndex.from_tuples(
|
22
|
+
[
|
23
|
+
['bar', 'large'],
|
24
|
+
['bar', 'small'],
|
25
|
+
['foo', 'large'],
|
26
|
+
['foo', 'small']
|
27
|
+
]
|
28
|
+
)
|
29
|
+
expect(df.pivot_table(index: [:a, :c]).round(2)).to eq(DaruLite::DataFrame.new({
|
30
|
+
d: [5.0 , 6.0, 2.0, 2.33],
|
31
|
+
e: [10.0, 12.0, 4.0, 4.67]
|
32
|
+
}, index: agg_mi))
|
33
|
+
end
|
34
|
+
|
35
|
+
it "creates row and vector index as per (single) index and (single) vectors args" do
|
36
|
+
agg_vectors = DaruLite::MultiIndex.from_tuples([
|
37
|
+
[:d, 'one'],
|
38
|
+
[:d, 'two'],
|
39
|
+
[:e, 'one'],
|
40
|
+
[:e, 'two']
|
41
|
+
])
|
42
|
+
agg_index = DaruLite::MultiIndex.from_tuples(
|
43
|
+
[
|
44
|
+
['bar'],
|
45
|
+
['foo']
|
46
|
+
]
|
47
|
+
)
|
48
|
+
|
49
|
+
expect(df.pivot_table(index: [:a], vectors: [:b]).round(2)).to eq(
|
50
|
+
DaruLite::DataFrame.new(
|
51
|
+
[
|
52
|
+
[4.5, 1.67],
|
53
|
+
[6.5, 3.0],
|
54
|
+
[9.0, 3.33],
|
55
|
+
[13, 6]
|
56
|
+
], order: agg_vectors, index: agg_index)
|
57
|
+
)
|
58
|
+
end
|
59
|
+
|
60
|
+
it "creates row and vector index as per (single) index and (double) vector args" do
|
61
|
+
agg_vectors = DaruLite::MultiIndex.from_tuples(
|
62
|
+
[
|
63
|
+
[:d, 'one', 'large'],
|
64
|
+
[:d, 'one', 'small'],
|
65
|
+
[:d, 'two', 'large'],
|
66
|
+
[:d, 'two', 'small'],
|
67
|
+
[:e, 'one', 'large'],
|
68
|
+
[:e, 'one', 'small'],
|
69
|
+
[:e, 'two', 'large'],
|
70
|
+
[:e, 'two', 'small']
|
71
|
+
]
|
72
|
+
)
|
73
|
+
|
74
|
+
agg_index = DaruLite::MultiIndex.from_tuples(
|
75
|
+
[
|
76
|
+
['bar'],
|
77
|
+
['foo']
|
78
|
+
]
|
79
|
+
)
|
80
|
+
|
81
|
+
expect(df.pivot_table(index: [:a], vectors: [:b, :c])).to eq(DaruLite::DataFrame.new(
|
82
|
+
[
|
83
|
+
[4.0,2.0],
|
84
|
+
[5.0,1.0],
|
85
|
+
[6.0,nil],
|
86
|
+
[7.0,3.0],
|
87
|
+
[8.0,4.0],
|
88
|
+
[10.0,2.0],
|
89
|
+
[12.0,nil],
|
90
|
+
[14.0,6.0]
|
91
|
+
], order: agg_vectors, index: agg_index
|
92
|
+
))
|
93
|
+
end
|
94
|
+
|
95
|
+
it "creates row and vector index with (double) index and (double) vector args" do
|
96
|
+
agg_index = DaruLite::MultiIndex.from_tuples([
|
97
|
+
['bar', 4],
|
98
|
+
['bar', 5],
|
99
|
+
['bar', 6],
|
100
|
+
['bar', 7],
|
101
|
+
['foo', 1],
|
102
|
+
['foo', 2],
|
103
|
+
['foo', 3]
|
104
|
+
])
|
105
|
+
|
106
|
+
agg_vectors = DaruLite::MultiIndex.from_tuples([
|
107
|
+
[:e, 'one', 'large'],
|
108
|
+
[:e, 'one', 'small'],
|
109
|
+
[:e, 'two', 'large'],
|
110
|
+
[:e, 'two', 'small']
|
111
|
+
])
|
112
|
+
|
113
|
+
expect(df.pivot_table(index: [:a, :d], vectors: [:b, :c])).to eq(
|
114
|
+
DaruLite::DataFrame.new(
|
115
|
+
[
|
116
|
+
[8 ,nil,nil,nil,nil, 4,nil],
|
117
|
+
[nil, 10,nil,nil, 2,nil,nil],
|
118
|
+
[nil,nil, 12,nil,nil,nil,nil],
|
119
|
+
[nil,nil,nil, 14,nil,nil, 6],
|
120
|
+
], index: agg_index, order: agg_vectors)
|
121
|
+
)
|
122
|
+
end
|
123
|
+
|
124
|
+
it "only aggregates over the vector specified in the values argument" do
|
125
|
+
agg_vectors = DaruLite::MultiIndex.from_tuples(
|
126
|
+
[
|
127
|
+
[:e, 'one', 'large'],
|
128
|
+
[:e, 'one', 'small'],
|
129
|
+
[:e, 'two', 'large'],
|
130
|
+
[:e, 'two', 'small']
|
131
|
+
]
|
132
|
+
)
|
133
|
+
agg_index = DaruLite::MultiIndex.from_tuples(
|
134
|
+
[
|
135
|
+
['bar'],
|
136
|
+
['foo']
|
137
|
+
]
|
138
|
+
)
|
139
|
+
expect(df.pivot_table(index: [:a], vectors: [:b, :c], values: :e)).to eq(
|
140
|
+
DaruLite::DataFrame.new(
|
141
|
+
[
|
142
|
+
[8, 4],
|
143
|
+
[10, 2],
|
144
|
+
[12,nil],
|
145
|
+
[14, 6]
|
146
|
+
], order: agg_vectors, index: agg_index
|
147
|
+
)
|
148
|
+
)
|
149
|
+
|
150
|
+
agg_vectors = DaruLite::MultiIndex.from_tuples(
|
151
|
+
[
|
152
|
+
[:d, 'one'],
|
153
|
+
[:d, 'two'],
|
154
|
+
[:e, 'one'],
|
155
|
+
[:e, 'two']
|
156
|
+
]
|
157
|
+
)
|
158
|
+
expect(df.pivot_table(index: [:a], vectors: [:b], values: [:d, :e])).to eq(
|
159
|
+
DaruLite::DataFrame.new(
|
160
|
+
[
|
161
|
+
[4.5, 5.0/3],
|
162
|
+
[6.5, 3.0],
|
163
|
+
[9.0, 10.0/3],
|
164
|
+
[13.0, 6.0]
|
165
|
+
], order: agg_vectors, index: agg_index
|
166
|
+
)
|
167
|
+
)
|
168
|
+
end
|
169
|
+
|
170
|
+
it "overrides default aggregate function to aggregate over sum" do
|
171
|
+
agg_vectors = DaruLite::MultiIndex.from_tuples(
|
172
|
+
[
|
173
|
+
[:e, 'one', 'large'],
|
174
|
+
[:e, 'one', 'small'],
|
175
|
+
[:e, 'two', 'large'],
|
176
|
+
[:e, 'two', 'small']
|
177
|
+
]
|
178
|
+
)
|
179
|
+
agg_index = DaruLite::MultiIndex.from_tuples(
|
180
|
+
[
|
181
|
+
['bar'],
|
182
|
+
['foo']
|
183
|
+
]
|
184
|
+
)
|
185
|
+
expect(df.pivot_table(index: [:a], vectors: [:b, :c], values: :e, agg: :sum)).to eq(
|
186
|
+
DaruLite::DataFrame.new(
|
187
|
+
[
|
188
|
+
[8, 8],
|
189
|
+
[10, 2],
|
190
|
+
[12,nil],
|
191
|
+
[14, 12]
|
192
|
+
], order: agg_vectors, index: agg_index
|
193
|
+
)
|
194
|
+
)
|
195
|
+
end
|
196
|
+
|
197
|
+
it "raises error if no non-numeric vectors are present" do
|
198
|
+
df = DaruLite::DataFrame.new({a: ['a', 'b', 'c'], b: ['b', 'e', 'd']})
|
199
|
+
expect {
|
200
|
+
df.pivot_table(index: [:a])
|
201
|
+
}.to raise_error
|
202
|
+
end
|
203
|
+
|
204
|
+
it "raises error if atleast a row index is not specified" do
|
205
|
+
expect {
|
206
|
+
df.pivot_table
|
207
|
+
}.to raise_error
|
208
|
+
end
|
209
|
+
|
210
|
+
it "aggregates when nils are present in value vector" do
|
211
|
+
df = DaruLite::DataFrame.new({
|
212
|
+
a: ['foo' , 'foo', 'foo', 'foo', 'foo', 'bar', 'bar', 'bar', 'ice'],
|
213
|
+
b: ['one' , 'one', 'one', 'two', 'two', 'one', 'one', 'two', 'two'],
|
214
|
+
c: ['small','large','large','small','small','large','small','large','small'],
|
215
|
+
d: [1,2,2,3,3,4,5,6,7],
|
216
|
+
e: [2,nil,4,6,6,8,10,12,nil]
|
217
|
+
})
|
218
|
+
|
219
|
+
expect(df.pivot_table index: [:a]).to eq(
|
220
|
+
DaruLite::DataFrame.new({
|
221
|
+
d: [5.0, 2.2, 7],
|
222
|
+
e: [10.0, 4.5, nil]
|
223
|
+
}, index: DaruLite::Index.new(['bar', 'foo', 'ice'])))
|
224
|
+
end
|
225
|
+
|
226
|
+
it "works when nils are present in value vector" do
|
227
|
+
df = DaruLite::DataFrame.new({
|
228
|
+
a: ['foo' , 'foo', 'foo', 'foo', 'foo', 'bar', 'bar', 'bar', 'ice'],
|
229
|
+
b: ['one' , 'one', 'one', 'two', 'two', 'one', 'one', 'two', 'two'],
|
230
|
+
c: ['small','large','large','small','small','large','small','large','small'],
|
231
|
+
d: [1,2,2,3,3,4,5,6,7],
|
232
|
+
e: [2,nil,4,6,6,8,10,12,nil]
|
233
|
+
})
|
234
|
+
|
235
|
+
agg_vectors = DaruLite::MultiIndex.from_tuples(
|
236
|
+
[
|
237
|
+
[:e, 'one'],
|
238
|
+
[:e, 'two']
|
239
|
+
]
|
240
|
+
)
|
241
|
+
|
242
|
+
agg_index = DaruLite::MultiIndex.from_tuples(
|
243
|
+
[
|
244
|
+
['bar'],
|
245
|
+
['foo'],
|
246
|
+
['ice']
|
247
|
+
]
|
248
|
+
)
|
249
|
+
|
250
|
+
expect(df.pivot_table index: [:a], vectors: [:b], values: :e).to eq(
|
251
|
+
DaruLite::DataFrame.new(
|
252
|
+
[
|
253
|
+
[9, 3, nil],
|
254
|
+
[12, 6, nil]
|
255
|
+
], order: agg_vectors, index: agg_index
|
256
|
+
)
|
257
|
+
)
|
258
|
+
end
|
259
|
+
|
260
|
+
it 'performs date pivoting' do
|
261
|
+
categories = %i[jan feb mar apr may jun jul aug sep oct nov dec]
|
262
|
+
df = DaruLite::DataFrame.rows([
|
263
|
+
[2014, 2, 1600.0, 20.0],
|
264
|
+
[2014, 3, 1680.0, 21.0],
|
265
|
+
[2016, 2, 1600.0, 20.0],
|
266
|
+
[2016, 4, 1520.0, 19.0],
|
267
|
+
], order: [:year, :month, :visitors, :days])
|
268
|
+
df[:averages] = df[:visitors] / df[:days]
|
269
|
+
df[:month] = df[:month].map{|i| categories[i - 1]}
|
270
|
+
actual = df.pivot_table(index: :month, vectors: [:year], values: :averages)
|
271
|
+
|
272
|
+
# NB: As you can see, there are some "illogical" parts:
|
273
|
+
# months are sorted lexicographically, then made into multi-index
|
274
|
+
# with one-element-per-tuple, then order of columns is dependent
|
275
|
+
# on which month is lexicographically first (its apr, so, apr-2016
|
276
|
+
# is first row to gather, so 2016 is first column).
|
277
|
+
#
|
278
|
+
# All of it is descendance of our group_by implementation (which
|
279
|
+
# always sorts results & always make array keys). I hope that fixing
|
280
|
+
# group_by, even to the extend described at https://github.com/v0dro/daru/issues/152,
|
281
|
+
# will be fix this case also.
|
282
|
+
expected =
|
283
|
+
DaruLite::DataFrame.new(
|
284
|
+
[
|
285
|
+
[80.0, 80.0, nil],
|
286
|
+
[nil, 80.0, 80.0],
|
287
|
+
], index: DaruLite::MultiIndex.from_tuples([[:apr], [:feb], [:mar]]),
|
288
|
+
order: DaruLite::MultiIndex.from_tuples([[:averages, 2016], [:averages, 2014]])
|
289
|
+
)
|
290
|
+
# Comparing their parts previous to full comparison allows to
|
291
|
+
# find complicated differences.
|
292
|
+
expect(actual.vectors).to eq expected.vectors
|
293
|
+
expect(actual.index).to eq expected.index
|
294
|
+
expect(actual).to eq expected
|
295
|
+
end
|
296
|
+
end
|
297
|
+
end
|
@@ -0,0 +1,92 @@
|
|
1
|
+
shared_examples_for 'a queryable DataFrame' do
|
2
|
+
describe '#include_values?' do
|
3
|
+
let(:df) do
|
4
|
+
DaruLite::DataFrame.new({
|
5
|
+
a: [1, 2, 3, 4, Float::NAN, 6, 1],
|
6
|
+
b: [:a, :b, nil, Float::NAN, nil, 3, 5],
|
7
|
+
c: ['a', 6, 3, 4, 3, 5, 3],
|
8
|
+
d: [1, 2, 3, 5, 1, 2, 5]
|
9
|
+
})
|
10
|
+
end
|
11
|
+
before { df.to_category :b }
|
12
|
+
|
13
|
+
context 'true' do
|
14
|
+
it { expect(df.include_values? nil).to eq true }
|
15
|
+
it { expect(df.include_values? Float::NAN).to eq true }
|
16
|
+
it { expect(df.include_values? nil, Float::NAN).to eq true }
|
17
|
+
it { expect(df.include_values? 1, 30).to eq true }
|
18
|
+
end
|
19
|
+
|
20
|
+
context 'false' do
|
21
|
+
it { expect(df[:a, :c].include_values? nil).to eq false }
|
22
|
+
it { expect(df[:c, :d].include_values? Float::NAN).to eq false }
|
23
|
+
it { expect(df[:c, :d].include_values? nil, Float::NAN).to eq false }
|
24
|
+
it { expect(df.include_values? 10, 20).to eq false }
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
|
29
|
+
describe "#any?" do
|
30
|
+
let(:df) do
|
31
|
+
DaruLite::DataFrame.new(
|
32
|
+
{
|
33
|
+
a: [1,2,3,4,5],
|
34
|
+
b: [10,20,30,40,50],
|
35
|
+
c: [11,22,33,44,55]
|
36
|
+
}
|
37
|
+
)
|
38
|
+
end
|
39
|
+
|
40
|
+
it "returns true if any one of the vectors satisfy condition" do
|
41
|
+
expect(df.any? { |v| v[0] == 1 }).to eq(true)
|
42
|
+
end
|
43
|
+
|
44
|
+
it "returns false if none of the vectors satisfy the condition" do
|
45
|
+
expect(df.any? { |v| v.mean > 100 }).to eq(false)
|
46
|
+
end
|
47
|
+
|
48
|
+
it "returns true if any one of the rows satisfy condition" do
|
49
|
+
expect(df.any?(:row) { |r| r[:a] == 1 and r[:c] == 11 }).to eq(true)
|
50
|
+
end
|
51
|
+
|
52
|
+
it "returns false if none of the rows satisfy the condition" do
|
53
|
+
expect(df.any?(:row) { |r| r.mean > 100 }).to eq(false)
|
54
|
+
end
|
55
|
+
|
56
|
+
it 'fails on unknown axis' do
|
57
|
+
expect { df.any?(:kitten) { |r| r.mean > 100 } }.to raise_error ArgumentError, /axis/
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
describe "#all?" do
|
62
|
+
let(:df) do
|
63
|
+
DaruLite::DataFrame.new(
|
64
|
+
{
|
65
|
+
a: [1,2,3,4,5],
|
66
|
+
b: [10,20,30,40,50],
|
67
|
+
c: [11,22,33,44,55]
|
68
|
+
}
|
69
|
+
)
|
70
|
+
end
|
71
|
+
|
72
|
+
it "returns true if all of the vectors satisfy condition" do
|
73
|
+
expect(df.all? { |v| v.mean < 40 }).to eq(true)
|
74
|
+
end
|
75
|
+
|
76
|
+
it "returns false if any one of the vectors does not satisfy condition" do
|
77
|
+
expect(df.all? { |v| v.mean == 30 }).to eq(false)
|
78
|
+
end
|
79
|
+
|
80
|
+
it "returns true if all of the rows satisfy condition" do
|
81
|
+
expect(df.all?(:row) { |r| r.mean < 70 }).to eq(true)
|
82
|
+
end
|
83
|
+
|
84
|
+
it "returns false if any one of the rows does not satisfy condition" do
|
85
|
+
expect(df.all?(:row) { |r| r.mean == 30 }).to eq(false)
|
86
|
+
end
|
87
|
+
|
88
|
+
it 'fails on unknown axis' do
|
89
|
+
expect { df.all?(:kitten) { |r| r.mean > 100 } }.to raise_error ArgumentError, /axis/
|
90
|
+
end
|
91
|
+
end
|
92
|
+
end
|