Class: Pest::DataSet::NArray

Inherits:
Object
  • Object
show all
Includes:
Pest::DataSet
Defined in:
lib/pest/data_set/narray.rb

Instance Attribute Summary collapse

Attributes included from Pest::DataSet

#data, #variables

Class Method Summary collapse

Instance Method Summary collapse

Methods included from Pest::DataSet

#==, #destroy, #except, included, #save

Constructor Details

#initialize(*args) ⇒ NArray

Returns a new instance of NArray.



43
44
45
46
 
# File 'lib/pest/data_set/narray.rb', line 43

def initialize(*args)
  super *args
  @variable_array = variables.to_a.sort
end

Instance Attribute Details

#variable_array ⇒ Object (readonly)

Returns the value of attribute variable_array.



41
42
43
 
# File 'lib/pest/data_set/narray.rb', line 41

def variable_array
  @variable_array
end

Class Method Details

.from_csv(file, args = {}) ⇒ Object 



28
29
30
31
32
33
34
35
36
37
38
39
 
# File 'lib/pest/data_set/narray.rb', line 28

def self.from_csv(file, args={})
  args = {:col_sep => "\t", :headers => true, :converters => :all}.merge args
  csv_data = CSV.read(file, args).map(&:to_hash)

  data_set = new(
    csv_data.first.keys.to_set,
    NMatrix.to_na(csv_data.map(&:values)).transpose
  )
  # Ensure the ordering matches what's in the CSV
  data_set.instance_variable_set(:@variable_array, csv_data.first.keys)
  data_set
end

.from_file(file) ⇒ Object 



24
25
26
 
# File 'lib/pest/data_set/narray.rb', line 24

def self.from_file(file)
  from_csv(file)
end

.from_hash(hash) ⇒ Object 



15
16
17
18
19
20
21
22
 
# File 'lib/pest/data_set/narray.rb', line 15

def self.from_hash(hash)
  data_set = new(
    hash.keys.to_set, 
    NMatrix.to_na(hash.values)
  )
  data_set.instance_variable_set(:@variable_array, hash.keys)
  data_set
end

.translators ⇒ Object 



6
7
8
9
10
11
12
13
 
# File 'lib/pest/data_set/narray.rb', line 6

def self.translators
  {
    Hash    => :from_hash,
    File    => :from_file,
    String  => :from_file,
    Symbol  => :from_file
  }
end

Instance Method Details

#+(other) ⇒ Object

Return the union of self and other



79
80
81
82
83
84
85
86
87
88
 
# File 'lib/pest/data_set/narray.rb', line 79

def +(other)
  unless other.variables == variables
    raise ArgumentError, "DataSets have different variables"
  end

  union = self.class.new
  union.variables = variables
  union.data = NMatrix[*(data.transpose.to_a + other.data.transpose.to_a)].transpose
  union
end

#[](*args) ⇒ Object

Return a subset of the data with the same variables, but only the vectors specified by i



63
64
65
66
67
68
69
70
71
72
73
74
 
# File 'lib/pest/data_set/narray.rb', line 63

def [](*args)
  unless args.any?
    raise ArgumentError, "Indices not specified"
  end

  args.map do |arg|
    subset = self.class.new
    subset.variables = self.variables
    subset.data = self.data[arg,true]
    subset
  end.inject(:+)
end

#dup ⇒ Object 



112
113
114
115
116
 
# File 'lib/pest/data_set/narray.rb', line 112

def dup
  instance = self.class.new( variables.dup, data.dup)
  instance.instance_variable_set(:@variable_array, variable_array)
  instance
end

#each(&block) ⇒ Object 



106
107
108
109
110
 
# File 'lib/pest/data_set/narray.rb', line 106

def each(&block)
  (0..length-1).to_a.each do |i|
    yield data[i,true].transpose.to_a.first
  end
end

#length ⇒ Object 



56
57
58
 
# File 'lib/pest/data_set/narray.rb', line 56

def length
  data.shape[0]
end

#merge(other) ⇒ Object 



118
119
120
 
# File 'lib/pest/data_set/narray.rb', line 118

def merge(other)
  dup.merge!(other)
end

#merge!(other) ⇒ Object

Raises:

  • (ArgumentError) 


122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
 
# File 'lib/pest/data_set/narray.rb', line 122

def merge!(other)
  other = self.class.from_hash(other) if other.kind_of?(::Hash)
  raise ArgumentError, "Lengths must be the same" if other.length != length

  # Merge the variables.  Existing variables should be updated,
  # new variables should be appended to the hash in the same order
  # as they appear in other
  @variable_array += (other.variables - variables).to_a
  @variables += other.variables

  # Create the new data array, should be the size of the merged variables
  # by the number of vectors
  new_data = ::NArray.object(length, variables.length)

  # Copy over the data from self (as if we had extended self.data to the
  # right to allow for the new data)
  new_data[true, 0..data.shape[1]-1] = data

  # Merge in other's data, using the indices of other's variables as the
  # slice keys
  other.variables.each do |variable|
    new_data[true, variable_array.index(variable)] = other.pick(variable).to_a.flatten
  end

  self.data = new_data
  self
end

#pick(*args) ⇒ Object

Return a subset of the data with the same vectors, but only the variables specified in args



93
94
95
96
97
98
99
100
101
102
103
104
 
# File 'lib/pest/data_set/narray.rb', line 93

def pick(*args)
  unless args.any?
    raise ArgumentError, "You didn't specify any variables to pick"
  end

  picked_indices = args.map do |variable|
    raise ArgumentError, "Dataset doesn't include #{variable}" unless variables.include?(variable)
    self.variable_array.index(variable)
  end

  self.class.new(args, self.data[true, picked_indices] )
end

#to_hash ⇒ Object 



48
49
50
51
52
53
54
 
# File 'lib/pest/data_set/narray.rb', line 48

def to_hash
  hash = {}
  variable_array.each_index do |i|
    hash[variable_array[i]] = data[true,i].to_a[0]
  end
  hash
end