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 +1,140 @@
|
|
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
|
@@ -0,0 +1,301 @@
|
|
1
|
+
module DaruLite
|
2
|
+
class DataFrame
|
3
|
+
module Fetchable
|
4
|
+
# Access row or vector. Specify name of row/vector followed by axis(:row, :vector).
|
5
|
+
# Defaults to *:vector*. Use of this method is not recommended for accessing
|
6
|
+
# rows. Use df.row[:a] for accessing row with index ':a'.
|
7
|
+
def [](*names)
|
8
|
+
axis = extract_axis(names, :vector)
|
9
|
+
dispatch_to_axis axis, :access, *names
|
10
|
+
end
|
11
|
+
|
12
|
+
# Retrive rows by positions
|
13
|
+
# @param [Array<Integer>] positions of rows to retrive
|
14
|
+
# @return [DaruLite::Vector, DaruLite::DataFrame] vector for single position and dataframe for multiple positions
|
15
|
+
# @example
|
16
|
+
# df = DaruLite::DataFrame.new({
|
17
|
+
# a: [1, 2, 3],
|
18
|
+
# b: ['a', 'b', 'c']
|
19
|
+
# })
|
20
|
+
# df.row_at 1, 2
|
21
|
+
# # => #<DaruLite::DataFrame(2x2)>
|
22
|
+
# # a b
|
23
|
+
# # 1 2 b
|
24
|
+
# # 2 3 c
|
25
|
+
def row_at(*positions)
|
26
|
+
original_positions = positions
|
27
|
+
positions = coerce_positions(*positions, nrows)
|
28
|
+
validate_positions(*positions, nrows)
|
29
|
+
|
30
|
+
if positions.is_a? Integer
|
31
|
+
row = get_rows_for([positions])
|
32
|
+
DaruLite::Vector.new(row, index: @vectors, name: @index.at(positions))
|
33
|
+
else
|
34
|
+
new_rows = get_rows_for(original_positions)
|
35
|
+
DaruLite::DataFrame.new(
|
36
|
+
new_rows,
|
37
|
+
index: @index.at(*original_positions),
|
38
|
+
order: @vectors,
|
39
|
+
name: @name
|
40
|
+
)
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
# Retrive vectors by positions
|
45
|
+
# @param [Array<Integer>] positions of vectors to retrive
|
46
|
+
# @return [DaruLite::Vector, DaruLite::DataFrame] vector for single position and dataframe for multiple positions
|
47
|
+
# @example
|
48
|
+
# df = DaruLite::DataFrame.new({
|
49
|
+
# a: [1, 2, 3],
|
50
|
+
# b: ['a', 'b', 'c']
|
51
|
+
# })
|
52
|
+
# df.at 0
|
53
|
+
# # => #<DaruLite::Vector(3)>
|
54
|
+
# # a
|
55
|
+
# # 0 1
|
56
|
+
# # 1 2
|
57
|
+
# # 2 3
|
58
|
+
def at(*positions)
|
59
|
+
if AXES.include? positions.last
|
60
|
+
axis = positions.pop
|
61
|
+
return row_at(*positions) if axis == :row
|
62
|
+
end
|
63
|
+
|
64
|
+
original_positions = positions
|
65
|
+
positions = coerce_positions(*positions, ncols)
|
66
|
+
validate_positions(*positions, ncols)
|
67
|
+
|
68
|
+
if positions.is_a? Integer
|
69
|
+
@data[positions].dup
|
70
|
+
else
|
71
|
+
DaruLite::DataFrame.new positions.map { |pos| @data[pos].dup },
|
72
|
+
index: @index,
|
73
|
+
order: @vectors.at(*original_positions),
|
74
|
+
name: @name
|
75
|
+
end
|
76
|
+
end
|
77
|
+
|
78
|
+
# The first ten elements of the DataFrame
|
79
|
+
#
|
80
|
+
# @param [Fixnum] quantity (10) The number of elements to display from the top.
|
81
|
+
def head(quantity = 10)
|
82
|
+
row.at 0..(quantity - 1)
|
83
|
+
end
|
84
|
+
alias first head
|
85
|
+
|
86
|
+
# The last ten elements of the DataFrame
|
87
|
+
#
|
88
|
+
# @param [Fixnum] quantity (10) The number of elements to display from the bottom.
|
89
|
+
def tail(quantity = 10)
|
90
|
+
start = [-quantity, -size].max
|
91
|
+
row.at start..-1
|
92
|
+
end
|
93
|
+
alias last tail
|
94
|
+
|
95
|
+
# Extract a dataframe given row indexes or positions
|
96
|
+
# @param keys [Array] can be positions (if by_position is true) or indexes (if by_position if false)
|
97
|
+
# @return [DaruLite::Dataframe]
|
98
|
+
def get_sub_dataframe(keys, by_position: true)
|
99
|
+
return DaruLite::DataFrame.new({}) if keys == []
|
100
|
+
|
101
|
+
keys = @index.pos(*keys) unless by_position
|
102
|
+
|
103
|
+
sub_df = row_at(*keys)
|
104
|
+
sub_df = sub_df.to_df.transpose if sub_df.is_a?(DaruLite::Vector)
|
105
|
+
|
106
|
+
sub_df
|
107
|
+
end
|
108
|
+
|
109
|
+
def get_vector_anyways(v)
|
110
|
+
@vectors.include?(v) ? self[v].to_a : Array.new(size)
|
111
|
+
end
|
112
|
+
|
113
|
+
# @param indexes [Array] index(s) at which row tuples are retrieved
|
114
|
+
# @return [Array] returns array of row tuples at given index(s)
|
115
|
+
# @example Using DaruLite::Index
|
116
|
+
# df = DaruLite::DataFrame.new({
|
117
|
+
# a: [1, 2, 3],
|
118
|
+
# b: ['a', 'a', 'b']
|
119
|
+
# })
|
120
|
+
#
|
121
|
+
# df.access_row_tuples_by_indexs(1,2)
|
122
|
+
# # => [[2, "a"], [3, "b"]]
|
123
|
+
#
|
124
|
+
# df.index = DaruLite::Index.new([:one,:two,:three])
|
125
|
+
# df.access_row_tuples_by_indexs(:one,:three)
|
126
|
+
# # => [[1, "a"], [3, "b"]]
|
127
|
+
#
|
128
|
+
# @example Using DaruLite::MultiIndex
|
129
|
+
# mi_idx = DaruLite::MultiIndex.from_tuples [
|
130
|
+
# [:a,:one,:bar],
|
131
|
+
# [:a,:one,:baz],
|
132
|
+
# [:b,:two,:bar],
|
133
|
+
# [:a,:two,:baz],
|
134
|
+
# ]
|
135
|
+
# df_mi = DaruLite::DataFrame.new({
|
136
|
+
# a: 1..4,
|
137
|
+
# b: 'a'..'d'
|
138
|
+
# }, index: mi_idx )
|
139
|
+
#
|
140
|
+
# df_mi.access_row_tuples_by_indexs(:b, :two, :bar)
|
141
|
+
# # => [[3, "c"]]
|
142
|
+
# df_mi.access_row_tuples_by_indexs(:a)
|
143
|
+
# # => [[1, "a"], [2, "b"], [4, "d"]]
|
144
|
+
def access_row_tuples_by_indexs(*indexes)
|
145
|
+
return get_sub_dataframe(indexes, by_position: false).map_rows(&:to_a) if
|
146
|
+
@index.is_a?(DaruLite::MultiIndex)
|
147
|
+
|
148
|
+
positions = @index.pos(*indexes)
|
149
|
+
if positions.is_a? Numeric
|
150
|
+
row = get_rows_for([positions])
|
151
|
+
row.first.is_a?(Array) ? row : [row]
|
152
|
+
else
|
153
|
+
new_rows = get_rows_for(indexes, by_position: false)
|
154
|
+
indexes.map { |index| new_rows.map { |r| r[index] } }
|
155
|
+
end
|
156
|
+
end
|
157
|
+
|
158
|
+
# Split the dataframe into many dataframes based on category vector
|
159
|
+
# @param [object] cat_name name of category vector to split the dataframe
|
160
|
+
# @return [Array] array of dataframes split by category with category vector
|
161
|
+
# used to split not included
|
162
|
+
# @example
|
163
|
+
# df = DaruLite::DataFrame.new({
|
164
|
+
# a: [1, 2, 3],
|
165
|
+
# b: ['a', 'a', 'b']
|
166
|
+
# })
|
167
|
+
# df.to_category :b
|
168
|
+
# df.split_by_category :b
|
169
|
+
# # => [#<DaruLite::DataFrame: a (2x1)>
|
170
|
+
# # a
|
171
|
+
# # 0 1
|
172
|
+
# # 1 2,
|
173
|
+
# # #<DaruLite::DataFrame: b (1x1)>
|
174
|
+
# # a
|
175
|
+
# # 2 3]
|
176
|
+
def split_by_category(cat_name)
|
177
|
+
cat_dv = self[cat_name]
|
178
|
+
raise ArgumentError, "#{cat_name} is not a category vector" unless
|
179
|
+
cat_dv.category?
|
180
|
+
|
181
|
+
cat_dv.categories.map do |cat|
|
182
|
+
where(cat_dv.eq cat)
|
183
|
+
.rename(cat)
|
184
|
+
.delete_vector cat_name
|
185
|
+
end
|
186
|
+
end
|
187
|
+
|
188
|
+
# Return the indexes of all the numeric vectors. Will include vectors with nils
|
189
|
+
# alongwith numbers.
|
190
|
+
def numeric_vectors
|
191
|
+
# FIXME: Why _with_index ?..
|
192
|
+
each_vector_with_index
|
193
|
+
.select { |vec, _i| vec.numeric? }
|
194
|
+
.map(&:last)
|
195
|
+
end
|
196
|
+
|
197
|
+
def numeric_vector_names
|
198
|
+
@vectors.select { |v| self[v].numeric? }
|
199
|
+
end
|
200
|
+
|
201
|
+
# Return a DataFrame of only the numerical Vectors. If clone: false
|
202
|
+
# is specified as option, only a *view* of the Vectors will be
|
203
|
+
# returned. Defaults to clone: true.
|
204
|
+
def only_numerics(opts = {})
|
205
|
+
cln = opts[:clone] != false
|
206
|
+
arry = numeric_vectors.map { |v| self[v] }
|
207
|
+
|
208
|
+
order = Index.new(numeric_vectors)
|
209
|
+
DaruLite::DataFrame.new(arry, clone: cln, order: order, index: @index)
|
210
|
+
end
|
211
|
+
|
212
|
+
private
|
213
|
+
|
214
|
+
def access_vector(*names)
|
215
|
+
if names.first.is_a?(Range)
|
216
|
+
dup(@vectors.subset(names.first))
|
217
|
+
elsif @vectors.is_a?(MultiIndex)
|
218
|
+
access_vector_multi_index(*names)
|
219
|
+
else
|
220
|
+
access_vector_single_index(*names)
|
221
|
+
end
|
222
|
+
end
|
223
|
+
|
224
|
+
def access_vector_multi_index(*names)
|
225
|
+
pos = @vectors[names]
|
226
|
+
|
227
|
+
return @data[pos] if pos.is_a?(Integer)
|
228
|
+
|
229
|
+
new_vectors = pos.map { |tuple| @data[@vectors[tuple]] }
|
230
|
+
|
231
|
+
pos = pos.drop_left_level(names.size) if names.size < @vectors.width
|
232
|
+
|
233
|
+
DaruLite::DataFrame.new(new_vectors, index: @index, order: pos)
|
234
|
+
end
|
235
|
+
|
236
|
+
def access_vector_single_index(*names)
|
237
|
+
if names.count < 2
|
238
|
+
begin
|
239
|
+
pos = @vectors.is_a?(DaruLite::DateTimeIndex) ? @vectors[names.first] : @vectors.pos(names.first)
|
240
|
+
rescue IndexError
|
241
|
+
raise IndexError, "Specified vector #{names.first} does not exist"
|
242
|
+
end
|
243
|
+
return @data[pos] if pos.is_a?(Numeric)
|
244
|
+
|
245
|
+
names = pos
|
246
|
+
end
|
247
|
+
|
248
|
+
new_vectors = names.map { |name| [name, @data[@vectors.pos(name)]] }.to_h
|
249
|
+
|
250
|
+
order = names.is_a?(Array) ? DaruLite::Index.new(names) : names
|
251
|
+
DaruLite::DataFrame.new(new_vectors, order: order, index: @index, name: @name)
|
252
|
+
end
|
253
|
+
|
254
|
+
def access_row(*indexes)
|
255
|
+
positions = @index.pos(*indexes)
|
256
|
+
|
257
|
+
if positions.is_a? Numeric
|
258
|
+
row = get_rows_for([positions])
|
259
|
+
DaruLite::Vector.new row, index: @vectors, name: indexes.first
|
260
|
+
else
|
261
|
+
new_rows = get_rows_for(indexes, by_position: false)
|
262
|
+
DaruLite::DataFrame.new new_rows, index: @index.subset(*indexes), order: @vectors
|
263
|
+
end
|
264
|
+
end
|
265
|
+
|
266
|
+
# @param keys [Array] can be an array of positions (if by_position is true) or indexes (if by_position if false)
|
267
|
+
# because of coercion by DaruLite::Vector#at and DaruLite::Vector#[], can return either an Array of
|
268
|
+
# values (representing a row) or an array of Vectors (that can be seen as rows)
|
269
|
+
def get_rows_for(keys, by_position: true)
|
270
|
+
raise unless keys.is_a?(Array)
|
271
|
+
|
272
|
+
if by_position
|
273
|
+
pos = keys
|
274
|
+
@data.map { |vector| vector.at(*pos) }
|
275
|
+
else
|
276
|
+
# TODO: for now (2018-07-27), it is different than using
|
277
|
+
# get_rows_for(@index.pos(*keys))
|
278
|
+
# because DaruLite::Vector#at and DaruLite::Vector#[] don't handle DaruLite::MultiIndex the same way
|
279
|
+
indexes = keys
|
280
|
+
@data.map { |vec| vec[*indexes] }
|
281
|
+
end
|
282
|
+
end
|
283
|
+
|
284
|
+
# coerce ranges, integers and array in appropriate ways
|
285
|
+
def coerce_positions(*positions, size)
|
286
|
+
if positions.size == 1
|
287
|
+
case positions.first
|
288
|
+
when Integer
|
289
|
+
positions.first
|
290
|
+
when Range
|
291
|
+
size.times.to_a[positions.first]
|
292
|
+
else
|
293
|
+
raise ArgumentError, 'Unknown position type.'
|
294
|
+
end
|
295
|
+
else
|
296
|
+
positions
|
297
|
+
end
|
298
|
+
end
|
299
|
+
end
|
300
|
+
end
|
301
|
+
end
|