daru_lite 0.1.1 → 0.1.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.rubocop_todo.yml +35 -33
- 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 +138 -2353
- data/lib/daru_lite/index/index.rb +14 -1
- data/lib/daru_lite/index/multi_index.rb +9 -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 +409 -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 -3289
- data/spec/index/categorical_index_spec.rb +27 -8
- data/spec/index/index_spec.rb +21 -0
- data/spec/index/multi_index_spec.rb +85 -76
- 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 +86 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: fe2a3da2352dd68322a62e048c7870ad34f243a31bcd0cf18725b15583e4c5e8
|
4
|
+
data.tar.gz: 889d0714e1188240f43dc741f2b58b0ce3fe8731a07b39ee4d366f54ce301f6b
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 370f64692790e1661642c2e40ec4b56baa8fd8ac000be5623293013b169b7d96c0e5d5fe122801bbea40945761710b0b94c148fae27c67a42ab1825683416876
|
7
|
+
data.tar.gz: ebb89b2307548a0deaeda39e8e72a899a0f4e20c0e5a5ee16515c7aaea5ac95e8f7da3dc752b80a7dba64ec2f4e19717ba3703c06ee0793111c36da968ed5b02
|
data/.rubocop_todo.yml
CHANGED
@@ -1,11 +1,19 @@
|
|
1
1
|
# This configuration was generated by
|
2
2
|
# `rubocop --auto-gen-config`
|
3
|
-
# on
|
3
|
+
# on 2024-03-03 13:59:21 UTC using RuboCop version 1.60.2.
|
4
4
|
# The point is for the user to remove these configuration records
|
5
5
|
# one by one as the offenses are removed from the code base.
|
6
6
|
# Note that changes in the inspected code, or installation of new
|
7
7
|
# versions of RuboCop, may require this file to be generated again.
|
8
8
|
|
9
|
+
# Offense count: 1
|
10
|
+
# This cop supports safe autocorrection (--autocorrect).
|
11
|
+
# Configuration parameters: EnforcedStyle, IndentationWidth.
|
12
|
+
# SupportedStyles: aligned, indented
|
13
|
+
Layout/LineEndStringConcatenationIndentation:
|
14
|
+
Exclude:
|
15
|
+
- 'lib/daru_lite/data_frame/indexable.rb'
|
16
|
+
|
9
17
|
# Offense count: 1
|
10
18
|
# Configuration parameters: AllowComments.
|
11
19
|
Lint/EmptyClass:
|
@@ -13,6 +21,7 @@ Lint/EmptyClass:
|
|
13
21
|
- 'lib/daru_lite/accessors/mdarray_wrapper.rb'
|
14
22
|
|
15
23
|
# Offense count: 5
|
24
|
+
# Configuration parameters: AllowedParentClasses.
|
16
25
|
Lint/MissingSuper:
|
17
26
|
Exclude:
|
18
27
|
- 'lib/daru_lite/date_time/offsets.rb'
|
@@ -20,61 +29,50 @@ Lint/MissingSuper:
|
|
20
29
|
- 'lib/daru_lite/index/index.rb'
|
21
30
|
- 'lib/daru_lite/index/multi_index.rb'
|
22
31
|
|
23
|
-
# Offense count:
|
32
|
+
# Offense count: 5
|
33
|
+
# This cop supports safe autocorrection (--autocorrect).
|
24
34
|
# Configuration parameters: CheckForMethodsWithNoSideEffects.
|
25
35
|
Lint/Void:
|
26
36
|
Exclude:
|
27
37
|
- 'lib/daru_lite/category.rb'
|
28
|
-
- 'lib/daru_lite/
|
38
|
+
- 'lib/daru_lite/data_frame/indexable.rb'
|
29
39
|
- 'lib/daru_lite/vector.rb'
|
30
40
|
|
31
|
-
# Offense count:
|
32
|
-
# Configuration parameters: AllowedMethods, AllowedPatterns,
|
41
|
+
# Offense count: 41
|
42
|
+
# Configuration parameters: AllowedMethods, AllowedPatterns, CountRepeatedAttributes.
|
33
43
|
Metrics/AbcSize:
|
34
44
|
Max: 34
|
35
45
|
|
36
|
-
# Offense count:
|
46
|
+
# Offense count: 5
|
37
47
|
# Configuration parameters: CountComments, CountAsOne.
|
38
48
|
Metrics/ClassLength:
|
39
|
-
Max:
|
49
|
+
Max: 188
|
40
50
|
|
41
51
|
# Offense count: 6
|
42
|
-
# Configuration parameters: AllowedMethods, AllowedPatterns
|
52
|
+
# Configuration parameters: AllowedMethods, AllowedPatterns.
|
43
53
|
Metrics/CyclomaticComplexity:
|
44
54
|
Max: 9
|
45
55
|
|
46
|
-
# Offense count:
|
47
|
-
# Configuration parameters: CountComments, CountAsOne,
|
56
|
+
# Offense count: 60
|
57
|
+
# Configuration parameters: CountComments, CountAsOne, AllowedMethods, AllowedPatterns.
|
48
58
|
Metrics/MethodLength:
|
49
59
|
Max: 15
|
50
60
|
|
51
|
-
# Offense count:
|
61
|
+
# Offense count: 4
|
52
62
|
# Configuration parameters: CountComments, CountAsOne.
|
53
63
|
Metrics/ModuleLength:
|
54
64
|
Max: 190
|
55
65
|
|
56
66
|
# Offense count: 4
|
57
|
-
# Configuration parameters: AllowedMethods, AllowedPatterns
|
67
|
+
# Configuration parameters: AllowedMethods, AllowedPatterns.
|
58
68
|
Metrics/PerceivedComplexity:
|
59
69
|
Max: 10
|
60
70
|
|
61
|
-
# Offense count:
|
71
|
+
# Offense count: 66
|
62
72
|
# Configuration parameters: MinNameLength, AllowNamesEndingInNumbers, AllowedNames, ForbiddenNames.
|
63
|
-
# AllowedNames: at, by, db, id, in, io, ip, of, on, os, pp, to
|
73
|
+
# AllowedNames: as, at, by, cc, db, id, if, in, io, ip, of, on, os, pp, to
|
64
74
|
Naming/MethodParameterName:
|
65
|
-
|
66
|
-
- 'lib/daru_lite/category.rb'
|
67
|
-
- 'lib/daru_lite/core/group_by.rb'
|
68
|
-
- 'lib/daru_lite/core/merge.rb'
|
69
|
-
- 'lib/daru_lite/core/query.rb'
|
70
|
-
- 'lib/daru_lite/dataframe.rb'
|
71
|
-
- 'lib/daru_lite/date_time/index.rb'
|
72
|
-
- 'lib/daru_lite/date_time/offsets.rb'
|
73
|
-
- 'lib/daru_lite/extensions/which_dsl.rb'
|
74
|
-
- 'lib/daru_lite/io/io.rb'
|
75
|
-
- 'lib/daru_lite/maths/statistics/dataframe.rb'
|
76
|
-
- 'lib/daru_lite/maths/statistics/vector.rb'
|
77
|
-
- 'lib/daru_lite/vector.rb'
|
75
|
+
Enabled: false
|
78
76
|
|
79
77
|
# Offense count: 5
|
80
78
|
# Configuration parameters: NamePrefix, ForbiddenPrefixes, AllowedMethods, MethodDefinitionMacros.
|
@@ -85,13 +83,14 @@ Naming/MethodParameterName:
|
|
85
83
|
Naming/PredicateName:
|
86
84
|
Exclude:
|
87
85
|
- 'spec/**/*'
|
88
|
-
- 'lib/daru_lite/
|
86
|
+
- 'lib/daru_lite/data_frame/missable.rb'
|
87
|
+
- 'lib/daru_lite/data_frame/queryable.rb'
|
89
88
|
- 'lib/daru_lite/vector.rb'
|
90
89
|
|
91
90
|
# Offense count: 5
|
92
91
|
Security/MarshalLoad:
|
93
92
|
Exclude:
|
94
|
-
- 'lib/daru_lite/
|
93
|
+
- 'lib/daru_lite/data_frame/i_o_able.rb'
|
95
94
|
- 'lib/daru_lite/date_time/index.rb'
|
96
95
|
- 'lib/daru_lite/index/index.rb'
|
97
96
|
- 'lib/daru_lite/io/io.rb'
|
@@ -102,7 +101,7 @@ Style/ClassVars:
|
|
102
101
|
Exclude:
|
103
102
|
- 'lib/daru_lite.rb'
|
104
103
|
|
105
|
-
# Offense count:
|
104
|
+
# Offense count: 58
|
106
105
|
# Configuration parameters: AllowedConstants.
|
107
106
|
Style/Documentation:
|
108
107
|
Enabled: false
|
@@ -113,6 +112,10 @@ Style/MapToHash:
|
|
113
112
|
Exclude:
|
114
113
|
- 'lib/daru_lite/category.rb'
|
115
114
|
- 'lib/daru_lite/core/group_by.rb'
|
115
|
+
- 'lib/daru_lite/data_frame/convertible.rb'
|
116
|
+
- 'lib/daru_lite/data_frame/duplicatable.rb'
|
117
|
+
- 'lib/daru_lite/data_frame/fetchable.rb'
|
118
|
+
- 'lib/daru_lite/data_frame/joinable.rb'
|
116
119
|
- 'lib/daru_lite/dataframe.rb'
|
117
120
|
|
118
121
|
# Offense count: 1
|
@@ -125,7 +128,7 @@ Style/MultilineBlockChain:
|
|
125
128
|
# AllowedMethods: respond_to_missing?
|
126
129
|
Style/OptionalBooleanParameter:
|
127
130
|
Exclude:
|
128
|
-
- 'lib/daru_lite/
|
131
|
+
- 'lib/daru_lite/data_frame/convertible.rb'
|
129
132
|
- 'lib/daru_lite/maths/statistics/vector.rb'
|
130
133
|
- 'lib/daru_lite/vector.rb'
|
131
134
|
|
@@ -133,5 +136,4 @@ Style/OptionalBooleanParameter:
|
|
133
136
|
# This cop supports unsafe autocorrection (--autocorrect-all).
|
134
137
|
Style/RedundantSelfAssignment:
|
135
138
|
Exclude:
|
136
|
-
- 'lib/daru_lite/
|
137
|
-
|
139
|
+
- 'lib/daru_lite/data_frame/joinable.rb'
|
@@ -0,0 +1,165 @@
|
|
1
|
+
module DaruLite
|
2
|
+
class DataFrame
|
3
|
+
module Aggregatable
|
4
|
+
# Group elements by vector to perform operations on them. Returns a
|
5
|
+
# DaruLite::Core::GroupBy object.See the DaruLite::Core::GroupBy docs for a detailed
|
6
|
+
# list of possible operations.
|
7
|
+
#
|
8
|
+
# == Arguments
|
9
|
+
#
|
10
|
+
# * vectors - An Array contatining names of vectors to group by.
|
11
|
+
#
|
12
|
+
# == Usage
|
13
|
+
#
|
14
|
+
# df = DaruLite::DataFrame.new({
|
15
|
+
# a: %w{foo bar foo bar foo bar foo foo},
|
16
|
+
# b: %w{one one two three two two one three},
|
17
|
+
# c: [1 ,2 ,3 ,1 ,3 ,6 ,3 ,8],
|
18
|
+
# d: [11 ,22 ,33 ,44 ,55 ,66 ,77 ,88]
|
19
|
+
# })
|
20
|
+
# df.group_by([:a,:b,:c]).groups
|
21
|
+
# #=> {["bar", "one", 2]=>[1],
|
22
|
+
# # ["bar", "three", 1]=>[3],
|
23
|
+
# # ["bar", "two", 6]=>[5],
|
24
|
+
# # ["foo", "one", 1]=>[0],
|
25
|
+
# # ["foo", "one", 3]=>[6],
|
26
|
+
# # ["foo", "three", 8]=>[7],
|
27
|
+
# # ["foo", "two", 3]=>[2, 4]}
|
28
|
+
def group_by(*vectors)
|
29
|
+
vectors.flatten!
|
30
|
+
missing = vectors - @vectors.to_a
|
31
|
+
raise(ArgumentError, "Vector(s) missing: #{missing.join(', ')}") unless missing.empty?
|
32
|
+
|
33
|
+
vectors = [@vectors.first] if vectors.empty?
|
34
|
+
|
35
|
+
DaruLite::Core::GroupBy.new(self, vectors)
|
36
|
+
end
|
37
|
+
|
38
|
+
# Function to use for aggregating the data.
|
39
|
+
#
|
40
|
+
# @param options [Hash] options for column, you want in resultant dataframe
|
41
|
+
#
|
42
|
+
# @return [DaruLite::DataFrame]
|
43
|
+
#
|
44
|
+
# @example
|
45
|
+
# df = DaruLite::DataFrame.new(
|
46
|
+
# {col: [:a, :b, :c, :d, :e], num: [52,12,07,17,01]})
|
47
|
+
# => #<DaruLite::DataFrame(5x2)>
|
48
|
+
# col num
|
49
|
+
# 0 a 52
|
50
|
+
# 1 b 12
|
51
|
+
# 2 c 7
|
52
|
+
# 3 d 17
|
53
|
+
# 4 e 1
|
54
|
+
#
|
55
|
+
# df.aggregate(num_100_times: ->(df) { (df.num*100).first })
|
56
|
+
# => #<DaruLite::DataFrame(5x1)>
|
57
|
+
# num_100_ti
|
58
|
+
# 0 5200
|
59
|
+
# 1 1200
|
60
|
+
# 2 700
|
61
|
+
# 3 1700
|
62
|
+
# 4 100
|
63
|
+
#
|
64
|
+
# When we have duplicate index :
|
65
|
+
#
|
66
|
+
# idx = DaruLite::CategoricalIndex.new [:a, :b, :a, :a, :c]
|
67
|
+
# df = DaruLite::DataFrame.new({num: [52,12,07,17,01]}, index: idx)
|
68
|
+
# => #<DaruLite::DataFrame(5x1)>
|
69
|
+
# num
|
70
|
+
# a 52
|
71
|
+
# b 12
|
72
|
+
# a 7
|
73
|
+
# a 17
|
74
|
+
# c 1
|
75
|
+
#
|
76
|
+
# df.aggregate(num: :mean)
|
77
|
+
# => #<DaruLite::DataFrame(3x1)>
|
78
|
+
# num
|
79
|
+
# a 25.3333333
|
80
|
+
# b 12
|
81
|
+
# c 1
|
82
|
+
#
|
83
|
+
# Note: `GroupBy` class `aggregate` method uses this `aggregate` method
|
84
|
+
# internally.
|
85
|
+
def aggregate(options = {}, multi_index_level = -1)
|
86
|
+
if block_given?
|
87
|
+
positions_tuples, new_index = yield(@index) # NOTE: use of yield is private for now
|
88
|
+
else
|
89
|
+
positions_tuples, new_index = group_index_for_aggregation(@index, multi_index_level)
|
90
|
+
end
|
91
|
+
|
92
|
+
colmn_value = aggregate_by_positions_tuples(options, positions_tuples)
|
93
|
+
|
94
|
+
DaruLite::DataFrame.new(colmn_value, index: new_index, order: options.keys)
|
95
|
+
end
|
96
|
+
|
97
|
+
def group_by_and_aggregate(*group_by_keys, **aggregation_map)
|
98
|
+
group_by(*group_by_keys).aggregate(aggregation_map)
|
99
|
+
end
|
100
|
+
|
101
|
+
private
|
102
|
+
|
103
|
+
def aggregate_by_positions_tuples(options, positions_tuples)
|
104
|
+
agg_over_vectors_only, options = cast_aggregation_options(options)
|
105
|
+
|
106
|
+
if agg_over_vectors_only
|
107
|
+
options.map do |vect_name, method|
|
108
|
+
vect = self[vect_name]
|
109
|
+
|
110
|
+
positions_tuples.map do |positions|
|
111
|
+
vect.apply_method_on_sub_vector(method, keys: positions)
|
112
|
+
end
|
113
|
+
end
|
114
|
+
else
|
115
|
+
methods = options.values
|
116
|
+
|
117
|
+
# NOTE: because we aggregate over rows, we don't have to re-get sub-dfs for each method (which is expensive)
|
118
|
+
rows = positions_tuples.map do |positions|
|
119
|
+
apply_method_on_sub_df(methods, keys: positions)
|
120
|
+
end
|
121
|
+
|
122
|
+
rows.transpose
|
123
|
+
end
|
124
|
+
end
|
125
|
+
|
126
|
+
# convert operations over sub-vectors to operations over sub-dfs when it improves perf
|
127
|
+
# note: we don't always "cast" because aggregation over a single vector / a few vector is faster
|
128
|
+
# than aggregation over (sub-)dfs
|
129
|
+
def cast_aggregation_options(options)
|
130
|
+
vects, non_vects = options.keys.partition { |k| @vectors.include?(k) }
|
131
|
+
|
132
|
+
over_vectors = true
|
133
|
+
|
134
|
+
if non_vects.any?
|
135
|
+
options = options.clone
|
136
|
+
|
137
|
+
vects.each do |name|
|
138
|
+
proc_on_vect = options[name].to_proc
|
139
|
+
options[name] = ->(sub_df) { proc_on_vect.call(sub_df[name]) }
|
140
|
+
end
|
141
|
+
|
142
|
+
over_vectors = false
|
143
|
+
end
|
144
|
+
|
145
|
+
[over_vectors, options]
|
146
|
+
end
|
147
|
+
|
148
|
+
def group_index_for_aggregation(index, multi_index_level = -1)
|
149
|
+
case index
|
150
|
+
when DaruLite::MultiIndex
|
151
|
+
groups_by_pos = DaruLite::Core::GroupBy.get_positions_group_for_aggregation(index, multi_index_level)
|
152
|
+
|
153
|
+
new_index = DaruLite::MultiIndex.from_tuples(groups_by_pos.keys).coerce_index
|
154
|
+
pos_tuples = groups_by_pos.values
|
155
|
+
when DaruLite::Index, DaruLite::CategoricalIndex
|
156
|
+
new_index = Array(index).uniq
|
157
|
+
pos_tuples = new_index.map { |idx| [*index.pos(idx)] }
|
158
|
+
else raise
|
159
|
+
end
|
160
|
+
|
161
|
+
[pos_tuples, new_index]
|
162
|
+
end
|
163
|
+
end
|
164
|
+
end
|
165
|
+
end
|
@@ -0,0 +1,140 @@
|
|
1
|
+
module DaruLite
|
2
|
+
class DataFrame
|
3
|
+
module Calculatable
|
4
|
+
# Sum all numeric/specified vectors in the DataFrame.
|
5
|
+
#
|
6
|
+
# Returns a new vector that's a containing a sum of all numeric
|
7
|
+
# or specified vectors of the DataFrame. By default, if the vector
|
8
|
+
# contains a nil, the sum is nil.
|
9
|
+
# With :skipnil argument set to true, nil values are assumed to be
|
10
|
+
# 0 (zero) and the sum vector is returned.
|
11
|
+
#
|
12
|
+
# @param args [Array] List of vectors to sum. Default is nil in which case
|
13
|
+
# all numeric vectors are summed.
|
14
|
+
#
|
15
|
+
# @option opts [Boolean] :skipnil Consider nils as 0. Default is false.
|
16
|
+
#
|
17
|
+
# @return Vector with sum of all vectors specified in the argument.
|
18
|
+
# If vecs parameter is empty, sum all numeric vector.
|
19
|
+
#
|
20
|
+
# @example
|
21
|
+
# df = DaruLite::DataFrame.new({
|
22
|
+
# a: [1, 2, nil],
|
23
|
+
# b: [2, 1, 3],
|
24
|
+
# c: [1, 1, 1]
|
25
|
+
# })
|
26
|
+
# => #<DaruLite::DataFrame(3x3)>
|
27
|
+
# a b c
|
28
|
+
# 0 1 2 1
|
29
|
+
# 1 2 1 1
|
30
|
+
# 2 nil 3 1
|
31
|
+
# df.vector_sum [:a, :c]
|
32
|
+
# => #<DaruLite::Vector(3)>
|
33
|
+
# 0 2
|
34
|
+
# 1 3
|
35
|
+
# 2 nil
|
36
|
+
# df.vector_sum
|
37
|
+
# => #<DaruLite::Vector(3)>
|
38
|
+
# 0 4
|
39
|
+
# 1 4
|
40
|
+
# 2 nil
|
41
|
+
# df.vector_sum skipnil: true
|
42
|
+
# => #<DaruLite::Vector(3)>
|
43
|
+
# c
|
44
|
+
# 0 4
|
45
|
+
# 1 4
|
46
|
+
# 2 4
|
47
|
+
#
|
48
|
+
def vector_sum(*args)
|
49
|
+
defaults = { vecs: nil, skipnil: false }
|
50
|
+
options = args.last.is_a?(::Hash) ? args.pop : {}
|
51
|
+
options = defaults.merge(options)
|
52
|
+
vecs = args[0] || options[:vecs]
|
53
|
+
skipnil = args[1] || options[:skipnil]
|
54
|
+
|
55
|
+
vecs ||= numeric_vectors
|
56
|
+
sum = DaruLite::Vector.new [0] * @size, index: @index, name: @name, dtype: @dtype
|
57
|
+
vecs.inject(sum) { |memo, n| self[n].add(memo, skipnil: skipnil) }
|
58
|
+
end
|
59
|
+
|
60
|
+
# Calculate mean of the rows of the dataframe.
|
61
|
+
#
|
62
|
+
# == Arguments
|
63
|
+
#
|
64
|
+
# * +max_missing+ - The maximum number of elements in the row that can be
|
65
|
+
# zero for the mean calculation to happen. Default to 0.
|
66
|
+
def vector_mean(max_missing = 0)
|
67
|
+
# FIXME: in vector_sum we preserve created vector dtype, but
|
68
|
+
# here we are not. Is this by design or ...? - zverok, 2016-05-18
|
69
|
+
mean_vec = DaruLite::Vector.new [0] * @size, index: @index, name: "mean_#{@name}"
|
70
|
+
|
71
|
+
each_row_with_index.with_object(mean_vec) do |(row, i), memo|
|
72
|
+
memo[i] = row.indexes(*DaruLite::MISSING_VALUES).size > max_missing ? nil : row.mean
|
73
|
+
end
|
74
|
+
end
|
75
|
+
|
76
|
+
# Returns a vector, based on a string with a calculation based
|
77
|
+
# on vector.
|
78
|
+
#
|
79
|
+
# The calculation will be eval'ed, so you can put any variable
|
80
|
+
# or expression valid on ruby.
|
81
|
+
#
|
82
|
+
# For example:
|
83
|
+
# a = DaruLite::Vector.new [1,2]
|
84
|
+
# b = DaruLite::Vector.new [3,4]
|
85
|
+
# ds = DaruLite::DataFrame.new({:a => a,:b => b})
|
86
|
+
# ds.compute("a+b")
|
87
|
+
# => Vector [4,6]
|
88
|
+
def compute(text, &block)
|
89
|
+
return instance_eval(&block) if block
|
90
|
+
|
91
|
+
instance_eval(text)
|
92
|
+
end
|
93
|
+
|
94
|
+
# DSL for yielding each row and returning a DaruLite::Vector based on the
|
95
|
+
# value each run of the block returns.
|
96
|
+
#
|
97
|
+
# == Usage
|
98
|
+
#
|
99
|
+
# a1 = DaruLite::Vector.new([1, 2, 3, 4, 5, 6, 7])
|
100
|
+
# a2 = DaruLite::Vector.new([10, 20, 30, 40, 50, 60, 70])
|
101
|
+
# a3 = DaruLite::Vector.new([100, 200, 300, 400, 500, 600, 700])
|
102
|
+
# ds = DaruLite::DataFrame.new({ :a => a1, :b => a2, :c => a3 })
|
103
|
+
# total = ds.vector_by_calculation { a + b + c }
|
104
|
+
# # <DaruLite::Vector:82314050 @name = nil @size = 7 >
|
105
|
+
# # nil
|
106
|
+
# # 0 111
|
107
|
+
# # 1 222
|
108
|
+
# # 2 333
|
109
|
+
# # 3 444
|
110
|
+
# # 4 555
|
111
|
+
# # 5 666
|
112
|
+
# # 6 777
|
113
|
+
def vector_by_calculation(&block)
|
114
|
+
a = each_row.map { |r| r.instance_eval(&block) }
|
115
|
+
|
116
|
+
DaruLite::Vector.new a, index: @index
|
117
|
+
end
|
118
|
+
|
119
|
+
def vector_count_characters(vecs = nil)
|
120
|
+
vecs ||= @vectors.to_a
|
121
|
+
|
122
|
+
collect_rows do |row|
|
123
|
+
vecs.sum { |v| row[v].to_s.size }
|
124
|
+
end
|
125
|
+
end
|
126
|
+
|
127
|
+
# Generate a summary of this DataFrame based on individual vectors in the DataFrame
|
128
|
+
# @return [String] String containing the summary of the DataFrame
|
129
|
+
def summary
|
130
|
+
summary = "= #{name}"
|
131
|
+
summary << "\n Number of rows: #{nrows}"
|
132
|
+
@vectors.each do |v|
|
133
|
+
summary << "\n Element:[#{v}]\n"
|
134
|
+
summary << self[v].summary(1)
|
135
|
+
end
|
136
|
+
summary
|
137
|
+
end
|
138
|
+
end
|
139
|
+
end
|
140
|
+
end
|
@@ -0,0 +1,107 @@
|
|
1
|
+
module DaruLite
|
2
|
+
class DataFrame
|
3
|
+
module Convertible
|
4
|
+
# Create a sql, basen on a given Dataset
|
5
|
+
#
|
6
|
+
# == Arguments
|
7
|
+
#
|
8
|
+
# * table - String specifying name of the table that will created in SQL.
|
9
|
+
# * charset - Character set. Default is "UTF8".
|
10
|
+
#
|
11
|
+
# @example
|
12
|
+
#
|
13
|
+
# ds = DaruLite::DataFrame.new({
|
14
|
+
# :id => DaruLite::Vector.new([1,2,3,4,5]),
|
15
|
+
# :name => DaruLite::Vector.new(%w{Alex Peter Susan Mary John})
|
16
|
+
# })
|
17
|
+
# ds.create_sql('names')
|
18
|
+
# #=>"CREATE TABLE names (id INTEGER,\n name VARCHAR (255)) CHARACTER SET=UTF8;"
|
19
|
+
#
|
20
|
+
def create_sql(table, charset = 'UTF8')
|
21
|
+
sql = "CREATE TABLE #{table} ("
|
22
|
+
fields = vectors.to_a.collect do |f|
|
23
|
+
v = self[f]
|
24
|
+
"#{f} #{v.db_type}"
|
25
|
+
end
|
26
|
+
|
27
|
+
sql + fields.join(",\n ") + ") CHARACTER SET=#{charset};"
|
28
|
+
end
|
29
|
+
|
30
|
+
# Returns the dataframe. This can be convenient when the user does not
|
31
|
+
# know whether the object is a vector or a dataframe.
|
32
|
+
# @return [self] the dataframe
|
33
|
+
def to_df
|
34
|
+
self
|
35
|
+
end
|
36
|
+
|
37
|
+
# Convert all vectors of type *:numeric* into a Matrix.
|
38
|
+
def to_matrix
|
39
|
+
Matrix.columns each_vector.select(&:numeric?).map(&:to_a)
|
40
|
+
end
|
41
|
+
|
42
|
+
# Converts the DataFrame into an array of hashes where key is vector name
|
43
|
+
# and value is the corresponding element. The 0th index of the array contains
|
44
|
+
# the array of hashes while the 1th index contains the indexes of each row
|
45
|
+
# of the dataframe. Each element in the index array corresponds to its row
|
46
|
+
# in the array of hashes, which has the same index.
|
47
|
+
def to_a
|
48
|
+
[each_row.map(&:to_h), @index.to_a]
|
49
|
+
end
|
50
|
+
|
51
|
+
# Convert to json. If no_index is false then the index will NOT be included
|
52
|
+
# in the JSON thus created.
|
53
|
+
def to_json(no_index = true)
|
54
|
+
if no_index
|
55
|
+
to_a[0].to_json
|
56
|
+
else
|
57
|
+
to_a.to_json
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
# Converts DataFrame to a hash (explicit) with keys as vector names and values as
|
62
|
+
# the corresponding vectors.
|
63
|
+
def to_h
|
64
|
+
@vectors
|
65
|
+
.each_with_index
|
66
|
+
.map { |vec_name, idx| [vec_name, @data[idx]] }.to_h
|
67
|
+
end
|
68
|
+
|
69
|
+
# Convert to html for IRuby.
|
70
|
+
def to_html(threshold = DaruLite.max_rows)
|
71
|
+
table_thead = to_html_thead
|
72
|
+
table_tbody = to_html_tbody(threshold)
|
73
|
+
path = if index.is_a?(MultiIndex)
|
74
|
+
File.expand_path('../iruby/templates/dataframe_mi.html.erb', __dir__)
|
75
|
+
else
|
76
|
+
File.expand_path('../iruby/templates/dataframe.html.erb', __dir__)
|
77
|
+
end
|
78
|
+
ERB.new(File.read(path).strip).result(binding)
|
79
|
+
end
|
80
|
+
|
81
|
+
def to_html_thead
|
82
|
+
table_thead_path =
|
83
|
+
if index.is_a?(MultiIndex)
|
84
|
+
File.expand_path('../iruby/templates/dataframe_mi_thead.html.erb', __dir__)
|
85
|
+
else
|
86
|
+
File.expand_path('../iruby/templates/dataframe_thead.html.erb', __dir__)
|
87
|
+
end
|
88
|
+
ERB.new(File.read(table_thead_path).strip).result(binding)
|
89
|
+
end
|
90
|
+
|
91
|
+
def to_html_tbody(threshold = DaruLite.max_rows)
|
92
|
+
threshold ||= @size
|
93
|
+
table_tbody_path =
|
94
|
+
if index.is_a?(MultiIndex)
|
95
|
+
File.expand_path('../iruby/templates/dataframe_mi_tbody.html.erb', __dir__)
|
96
|
+
else
|
97
|
+
File.expand_path('../iruby/templates/dataframe_tbody.html.erb', __dir__)
|
98
|
+
end
|
99
|
+
ERB.new(File.read(table_tbody_path).strip).result(binding)
|
100
|
+
end
|
101
|
+
|
102
|
+
def to_s
|
103
|
+
"#<#{self.class}#{": #{@name}" if @name}(#{nrows}x#{ncols})>"
|
104
|
+
end
|
105
|
+
end
|
106
|
+
end
|
107
|
+
end
|
@@ -0,0 +1,64 @@
|
|
1
|
+
module DaruLite
|
2
|
+
class DataFrame
|
3
|
+
module Duplicatable
|
4
|
+
extend Gem::Deprecate
|
5
|
+
|
6
|
+
# Duplicate the DataFrame entirely.
|
7
|
+
#
|
8
|
+
# == Arguments
|
9
|
+
#
|
10
|
+
# * +vectors_to_dup+ - An Array specifying the names of Vectors to
|
11
|
+
# be duplicated. Will duplicate the entire DataFrame if not specified.
|
12
|
+
def dup(vectors_to_dup = nil)
|
13
|
+
vectors_to_dup ||= @vectors.to_a
|
14
|
+
|
15
|
+
src = vectors_to_dup.map { |vec| @data[@vectors.pos(vec)].dup }
|
16
|
+
new_order = DaruLite::Index.new(vectors_to_dup)
|
17
|
+
|
18
|
+
DaruLite::DataFrame.new src, order: new_order, index: @index.dup, name: @name, clone: true
|
19
|
+
end
|
20
|
+
|
21
|
+
# Only clone the structure of the DataFrame.
|
22
|
+
def clone_structure
|
23
|
+
DaruLite::DataFrame.new([], order: @vectors.dup, index: @index.dup, name: @name)
|
24
|
+
end
|
25
|
+
|
26
|
+
# Returns a 'view' of the DataFrame, i.e the object ID's of vectors are
|
27
|
+
# preserved.
|
28
|
+
#
|
29
|
+
# == Arguments
|
30
|
+
#
|
31
|
+
# +vectors_to_clone+ - Names of vectors to clone. Optional. Will return
|
32
|
+
# a view of the whole data frame otherwise.
|
33
|
+
def clone(*vectors_to_clone)
|
34
|
+
vectors_to_clone.flatten! if ArrayHelper.array_of?(vectors_to_clone, Array)
|
35
|
+
vectors_to_clone = @vectors.to_a if vectors_to_clone.empty?
|
36
|
+
|
37
|
+
h = vectors_to_clone.map { |vec| [vec, self[vec]] }.to_h
|
38
|
+
DaruLite::DataFrame.new(h, clone: false, order: vectors_to_clone, name: @name)
|
39
|
+
end
|
40
|
+
|
41
|
+
# Returns a 'shallow' copy of DataFrame if missing data is not present,
|
42
|
+
# or a full copy of only valid data if missing data is present.
|
43
|
+
def clone_only_valid
|
44
|
+
if include_values?(*DaruLite::MISSING_VALUES)
|
45
|
+
reject_values(*DaruLite::MISSING_VALUES)
|
46
|
+
else
|
47
|
+
clone
|
48
|
+
end
|
49
|
+
end
|
50
|
+
|
51
|
+
# Creates a new duplicate dataframe containing only rows
|
52
|
+
# without a single missing value.
|
53
|
+
def dup_only_valid(vecs = nil)
|
54
|
+
rows_with_nil = @data.map { |vec| vec.indexes(*DaruLite::MISSING_VALUES) }
|
55
|
+
.inject(&:concat)
|
56
|
+
.uniq
|
57
|
+
|
58
|
+
row_indexes = @index.to_a
|
59
|
+
(vecs.nil? ? self : dup(vecs)).row[*(row_indexes - rows_with_nil)]
|
60
|
+
end
|
61
|
+
deprecate :dup_only_valid, :reject_values, 2016, 10
|
62
|
+
end
|
63
|
+
end
|
64
|
+
end
|