Class: Statsample::Multiset

Inherits:
Object show all
Defined in:
lib/statsample/multiset.rb

Overview

Multiset joins multiple dataset with the same fields and vectors but with different number of cases. This is the base class for stratified and cluster sampling estimation

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(fields) ⇒ Multiset

To create a multiset

  • Multiset.new(%wf2 f3) # define only fields

[View source] [View on GitHub]

12
13
14
15
 
# File 'lib/statsample/multiset.rb', line 12

def initialize(fields)
  @fields=fields
  @datasets={}
end

Instance Attribute Details

#datasets ⇒ Object (readonly)

Array with Daru::DataFrame

[View on GitHub]

9
10
11
 
# File 'lib/statsample/multiset.rb', line 9

def datasets
  @datasets
end

#fields ⇒ Object (readonly)

Name of fields

[View on GitHub]

7
8
9
 
# File 'lib/statsample/multiset.rb', line 7

def fields
  @fields
end

Class Method Details

.new_empty_vectors(fields, ds_names) ⇒ Object

[View source] [View on GitHub]

16
17
18
19
20
21
22
23
 
# File 'lib/statsample/multiset.rb', line 16

def self.new_empty_vectors(fields,ds_names) 
  ms = Multiset.new(fields)
  ds_names.each do |d|
    ms.add_dataset(d, Daru::DataFrame.new({}, order: fields))
  end

  ms
end

Instance Method Details

#[](i) ⇒ Object

[View source] [View on GitHub]

84
85
86
 
# File 'lib/statsample/multiset.rb', line 84

def [](i)
  @datasets[i]
end

#add_dataset(key, ds) ⇒ Object

[View source] [View on GitHub]

61
62
63
64
65
66
67
 
# File 'lib/statsample/multiset.rb', line 61

def add_dataset(key,ds)
  if ds.vectors.to_a != @fields
    raise ArgumentError, "Dataset(#{ds.vectors.to_a.to_s})must have the same fields of the Multiset(#{@fields})"
  else
    @datasets[key] = ds
  end
end

#collect_vector(field) ⇒ Object

[View source] [View on GitHub]

76
77
78
 
# File 'lib/statsample/multiset.rb', line 76

def collect_vector(field)
  @datasets.collect { |k,v| yield k, v[field] }
end

#datasets_names ⇒ Object

[View source] [View on GitHub]

53
54
55
 
# File 'lib/statsample/multiset.rb', line 53

def datasets_names
  @datasets.keys.sort
end

#each(&block) ⇒ Object

[View source] [View on GitHub]

88
89
90
91
92
93
 
# File 'lib/statsample/multiset.rb', line 88

def each(&block)
  @datasets.each {|k,ds|
    next if ds.nrows == 0
    block.call(k,ds)
  }
end

#each_vector(field) ⇒ Object

[View source] [View on GitHub]

80
81
82
 
# File 'lib/statsample/multiset.rb', line 80

def each_vector(field)
  @datasets.each { |k,v| yield k, v[field] }
end

#n_datasets ⇒ Object

[View source] [View on GitHub]

57
58
59
 
# File 'lib/statsample/multiset.rb', line 57

def n_datasets
  @datasets.size
end

#sum_field(field) ⇒ Object

[View source] [View on GitHub]

68
69
70
71
72
73
74
75
 
# File 'lib/statsample/multiset.rb', line 68

def sum_field(field)
  @datasets.inject(0) {|a,da|
    stratum_name = da[0]
    vector       = da[1][field]
    val          = yield stratum_name,vector
    a + val
  }
end

#union(&block) ⇒ Object

Generate a new dataset as a union of partial dataset If block given, this is applied to each dataset before union

[View source] [View on GitHub]

26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
 
# File 'lib/statsample/multiset.rb', line 26

def union(&block)
  union_field={}
  types={}
  names={}
  labels={}
  each do |k,ds|
    if block
      ds = ds.dup
      yield k,ds
    end
    @fields.each do |f|
      union_field[f] ||= Array.new
      union_field[f].concat(ds[f].to_a)
      types[f]  ||= ds[f].type
      names[f]  ||= ds[f].name
      labels[f] ||= ds[f].index.to_a
    end
  end
  
  @fields.each do |f|
    union_field[f] = Daru::Vector.new(union_field[f], name: names[f])
  end

  ds_union = Daru::DataFrame.new(union_field, order: @fields)
  ds_union
end