Module: PubliSci::Dataset::DataCube

Includes:
RDFParser
Included in:
PubliSci::DataSet::ORM::DataCube, PubliSci::DataSet::ORM::DataCube, Generators::Base, Readers::ARFF, Readers::Base, Readers::Dataframe, Readers::RCross, Readers::RMatrix
Defined in:
lib/publisci/dataset/data_cube.rb

Instance Method Summary collapse

Methods included from RDFParser

#add_node, #bnode_value, #encode_value, #get_ary, #get_hashes, #is_complex?, #is_uri?, #load_string, #observation_hash, #sanitize, #sanitize_hash, #strip_prefixes, #strip_uri, #to_literal, #to_resource, #turtle_indent

Instance Method Details

#abbreviate_known(turtle_string) ⇒ Object 



411
412
413
414
415
 
# File 'lib/publisci/dataset/data_cube.rb', line 411

def abbreviate_known(turtle_string)
  #debug method
  # puts turtle_string
  turtle_string.gsub(/<http:\/\/www\.rqtl\.org\/dc\/properties\/(\S+)>/, 'prop:\1').gsub(/<http:\/\/www.rqtl.org\/ns\/dc\/code\/(\S+)\/(\S+)>/, '<code/\1/\2>').gsub(/<http:\/\/www.rqtl.org\/dc\/dataset\/(\S+)\/code\/(\w+)>/, 'code:\2').gsub(/<http:\/\/www.rqtl.org\/dc\/dataset\/(\S+)\/code\/(\S+)>/, '<code/' + '\2' +'>')
end

#code_lists(codes, data, var, options = {}) ⇒ Object 



346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
 
# File 'lib/publisci/dataset/data_cube.rb', line 346

def code_lists(codes, data, var, options={})
  options = defaults().merge(options)
  rdf_measures, rdf_dimensions, rdf_codes  = generate_resources([], [], codes, options)
  data = encode_data(codes, data, var, options)
  lists = []
  rdf_codes.map{|code|
    if code[0] =~ /^<.+>$/
      refcode = code[0][1..-2]
    else
      refcode = code[0]
    end
    str = <<-EOF.unindent
      #{code[2]} a rdfs:Class, owl:Class;
        rdfs:subClassOf skos:Concept ;
        rdfs:label "Code list for #{strip_prefixes(strip_uri(code[1]))} - codelist class"@en;
        rdfs:comment "Specifies the #{strip_prefixes(strip_uri(code[1]))} for each observation";
        rdfs:seeAlso #{code[1]} .

      #{code[1]} a skos:ConceptScheme;
        skos:prefLabel "Code list for #{strip_prefixes(strip_uri(code[1]))} - codelist scheme"@en;
        rdfs:label "Code list for #{strip_prefixes(strip_uri(code[1]))} - codelist scheme"@en;
        skos:notation "CL_#{strip_prefixes(strip_uri(code[1])).upcase}";
        skos:note "Specifies the #{strip_prefixes(strip_uri(code[1]))} for each observation";
    EOF
    data[refcode].uniq.map{|value|
      unless value == nil && !options[:encode_nulls]
        str << "  skos:hasTopConcept #{to_resource(value,options)} ;\n"
      end
    }

    str << "  .\n\n"
    lists << str
  }

  lists
end

#component_gen(args, var, options = {}) ⇒ Object 



61
62
63
64
65
 
# File 'lib/publisci/dataset/data_cube.rb', line 61

def component_gen(args,var,options={})
  args = Array[args].flatten
  args = args.map{|arg| arg.gsub("prop:","cs:").gsub(%r{<#{options[:base_url]}/.+/(\w.+)>$},'cs:'+'\1')}
  args.map{|arg| arg.gsub(%r{<http://(.+)>},"<#{options[:base_url]}/dc/dataset/#{var}/cs/"+'\1'+'>')}
end

#component_specifications(measure_names, dimension_names, codes, var, options = {}) ⇒ Object 



171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
 
# File 'lib/publisci/dataset/data_cube.rb', line 171

def component_specifications(measure_names, dimension_names, codes, var, options={})
  options = defaults().merge(options)
  rdf_measures, rdf_dimensions, rdf_codes  = generate_resources(measure_names, dimension_names, codes, options)
  cs_dims = component_gen(rdf_dimensions,var,options)
  cs_meas = component_gen(rdf_measures,var,options)
  specs = []

    rdf_dimensions.each_with_index.map{|d,i|
    specs << <<-EOF.unindent
      #{cs_dims[i]} a qb:ComponentSpecification ;
        rdfs:label "#{strip_prefixes(strip_uri(dimension_names[i]))}" ;
        qb:dimension #{d} .

      EOF
    }

    rdf_measures.each_with_index.map{|n,i|
      specs << <<-EOF.unindent
        #{cs_meas[i]} a qb:ComponentSpecification ;
          rdfs:label "#{strip_prefixes(strip_uri(measure_names[i]))}" ;
          qb:measure #{n} .

        EOF
    }

  specs
end

#concept_codes(codes, data, var, options = {}) ⇒ Object 



383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
 
# File 'lib/publisci/dataset/data_cube.rb', line 383

def concept_codes(codes, data, var, options={})
  options = defaults().merge(options)
  rdf_measures, rdf_dimensions, rdf_codes  = generate_resources([], [], codes, options)
  concepts = []
  data = encode_data(codes, data, var, options)
  rdf_codes.map{|code|
    if code[0] =~ /^<.+>$/
      refcode = code[0][1..-2]
    else
      refcode = code[0]
    end
    data[refcode].uniq.each_with_index{|value,i|
      unless value == nil && !options[:encode_nulls]
      concepts << <<-EOF.unindent
        #{to_resource(value,options)} a skos:Concept, #{code[2]};
          skos:topConceptOf #{code[1]} ;
          skos:prefLabel "#{strip_uri(value)}" ;
          skos:inScheme #{code[1]} .

      EOF
      end
    }
  }

  concepts
end

#data_structure_definition(measures, dimensions, codes, var, options = {}) ⇒ Object 



141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
 
# File 'lib/publisci/dataset/data_cube.rb', line 141

def data_structure_definition(measures,dimensions,codes,var,options={})
  var = sanitize([var]).first
  options = defaults().merge(options)
  rdf_measures, rdf_dimensions, rdf_codes  = generate_resources(measures, dimensions, codes, options)
  cs_dims = component_gen(rdf_dimensions,var,options)  #rdf_dimensions.map{|d| d.gsub('prop:','cs:')}
  cs_meas = component_gen(rdf_measures,var,options) #rdf_measures.map!{|m| m.gsub('prop:','cs:')}
  str = "ns:dsd-#{var} a qb:DataStructureDefinition;\n"
  cs_dims.map{|d|
    str << "  qb:component #{d} ;\n"
  }

  cs_meas.map{|m|
    str << "  qb:component #{m} ;\n"
  }
  str[-2]='.'
  str<<"\n"
  str
end

#dataset(var, options = {}) ⇒ Object 



160
161
162
163
164
165
166
167
168
169
 
# File 'lib/publisci/dataset/data_cube.rb', line 160

def dataset(var,options={})
  var = sanitize([var]).first
  options = defaults().merge(options)
  <<-EOF.unindent
  ns:dataset-#{var} a qb:DataSet ;
    rdfs:label "#{var}"@en ;
    qb:structure ns:dsd-#{var} .

  EOF
end

#defaults ⇒ Object 



12
13
14
15
16
17
18
 
# File 'lib/publisci/dataset/data_cube.rb', line 12

def defaults
{
  type: :dataframe,
  encode_nulls: false,
  base_url: "http://example.org",
}
end

#dimension_properties(dimensions, codes, var, options = {}) ⇒ Object 



199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
 
# File 'lib/publisci/dataset/data_cube.rb', line 199

def dimension_properties(dimensions, codes, var, options={})
  options = defaults().merge(options)
  rdf_measures, rdf_dimensions, rdf_codes  = generate_resources([], dimensions, codes, options)
  props = []

  dimension_codes = rdf_codes.map{|c|
    if c[0]=~/^<http:/
      c[0][1..-2]
    else
      c[0]
    end
  }

  rdf_dimensions.each_with_index{|d,i|
    if dimension_codes.include?(dimensions[i])

      code = rdf_codes[dimension_codes.index(dimensions[i])]
      props << <<-EOF.unindent
      #{d} a rdf:Property, qb:DimensionProperty ;
        rdfs:label "#{strip_prefixes(strip_uri(d))}"@en ;
        qb:codeList #{code[1]} ;
        rdfs:range #{code[2]} .

      EOF
    else
      props << <<-EOF.unindent
      #{d} a rdf:Property, qb:DimensionProperty ;
        rdfs:label "#{strip_prefixes(strip_uri(d))}"@en ;
      EOF
      if options[:ranges] && options[:ranges][dimension[i]]
        props.last << "\n  rdfs:range #{options[:ranges][dimensions[i]]} .\n\n"
      else
        props.last[-2] = ".\n"
      end
    end
    }

  props
end

#encode_data(codes, data, var, options = {}) ⇒ Object 



67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
 
# File 'lib/publisci/dataset/data_cube.rb', line 67

def encode_data(codes,data,var,options={})
  codes = sanitize(codes)
  new_data = {}
  data.map{|k,v|
    if codes.include? k
      new_data[k] = v.map{|val|
        if val =~ /^http:\/\//
          "<#{val}>"
        elsif val =~ /^[a-zA-z]+:[a-zA-z]+$/
          val
        else
          "<code/#{k.downcase}/#{sanitize(val).first}>"
        end
      }
    else
      new_data[k] = v
    end
  }
  new_data
end

#generate(measures, dimensions, codes, data, observation_labels, var, options = {}) ⇒ Object 



98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
 
# File 'lib/publisci/dataset/data_cube.rb', line 98

def generate(measures, dimensions, codes, data, observation_labels, var, options={})
  # dimensions = sanitize(dimensions)
  # codes = sanitize(codes)
  # measures = sanitize(measures)
  var = sanitize([var]).first
  data = sanitize_hash(data)

  str = prefixes(var,options)
  str << data_structure_definition(measures, dimensions, codes, var, options)
  str << dataset(var, options)
  component_specifications(measures, dimensions, codes, var, options).map{ |c| str << c }
  dimension_properties(dimensions, codes, var, options).map{|p| str << p}
  measure_properties(measures, var, options).map{|p| str << p}
  code_lists(codes, data, var, options).map{|l| str << l}
  concept_codes(codes, data, var, options).map{|c| str << c}
  observations(measures, dimensions, codes, data, observation_labels, var, options).map{|o| str << o}
  str
end

#generate_resources(measures, dimensions, codes, options = {}) ⇒ Object 



20
21
22
23
24
25
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
52
53
54
55
56
57
58
59
 
# File 'lib/publisci/dataset/data_cube.rb', line 20

def generate_resources(measures, dimensions, codes, options={})
  newm = measures.map {|m|
    if m =~ /^http:\/\//
      "<#{m}>"
    elsif m =~ /^[a-zA-z]+:[a-zA-z]+$/
      m
    else
      "prop:#{m}"
    end
  }

  newc = []

  newd = dimensions.map{|d|
      if d =~ /^http:\/\//
        "<#{d}>"
      elsif d =~ /^[a-zA-z]+:[a-zA-z]+$/
        d
      else
        "prop:#{d}"
      end
  }

  if codes.first.is_a? Array
    newc = codes.map{|c|
      c.map{|el|
        if el =~ /^http:\/\//
          "<#{el}>"
        else
          el
        end
      }
    }
  else
    newc = codes.map{|c|
        ["#{sanitize(c).first}","code:#{sanitize(c).first.downcase}","code:#{sanitize(c).first.downcase.capitalize}"]
    }
  end
  [newm, newd, newc]
end

#measure_properties(measures, var, options = {}) ⇒ Object 



239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
 
# File 'lib/publisci/dataset/data_cube.rb', line 239

def measure_properties(measures, var, options={})
  options = defaults().merge(options)
  rdf_measures = generate_resources(measures, [], [], options)[0]
  props = []

  rdf_measures.each_with_index{ |m,i|

    props <<  <<-EOF.unindent
    #{m} a rdf:Property, qb:MeasureProperty ;
      rdfs:label "#{strip_prefixes(strip_uri(m))}"@en ;
    EOF

    if options[:ranges] && options[:ranges][measures[i]]
      props.last << "  rdfs:range #{options[:ranges][measures[i]]} .\n\n"
    else
      props.last[-2] = ".\n"
    end
  }

  props
end

#observations(measures, dimensions, codes, data, observation_labels, var, options = {}) ⇒ Object 



261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
 
# File 'lib/publisci/dataset/data_cube.rb', line 261

def observations(measures, dimensions, codes, data, observation_labels, var, options={})
  var = sanitize([var]).first
  measures = sanitize(measures)
  dimensions = sanitize(dimensions)

  data.each{|k,v| data[k]=Array(v)}
  observation_labels = Array(observation_labels)
  options = defaults().merge(options)

  rdf_measures, rdf_dimensions, rdf_codes  = generate_resources(measures, dimensions, codes, options)
  data = encode_data(codes, data, var, options)
  obs = []

  dimension_codes = rdf_codes.map{|c|
    if c[0]=~/^<http:/
      c[0][1..-2]
    else
      c[0]
    end
  }

  observation_labels.each_with_index.map{|r, i|
    # contains_nulls = false
    str = <<-EOF.unindent
    ns:obs#{r} a qb:Observation ;
      qb:dataSet ns:dataset-#{var} ;
    EOF

    str << "  rdfs:label \"#{r}\" ;\n" unless options[:no_labels]

    obs_index = 0
    obs_nodes = []

    dimensions.each_with_index{|d,j|
      contains_nulls = (data[d][i] == nil)

      unless contains_nulls && !options[:encode_nulls]
        if is_complex?(data[d][i])
          str << "  #{rdf_dimensions[j]} #{add_node(obs_index,add_node(r))} ;\n"
          obs_nodes << encode_value(data[d][i], options, obs_index, add_node(r))
        else
          str << "  #{rdf_dimensions[j]} #{encode_value(data[d][i], options)} ;\n"
        end
      end

      obs_index += 1
    }

    measures.each_with_index{|m,j|
      contains_nulls = (data[m][i] == nil)

      unless contains_nulls && !options[:encode_nulls]
        if is_complex?(data[m][i])
          str << "  #{rdf_measures[j]} #{add_node(obs_index,add_node(r))} ;\n"
          val = encode_value(data[m][i], options, obs_index, add_node(r))

          if val.last.is_a? Array
            unless val.last.last[-2] == "."
              val.last.last << ".\n"
            end
          end
          
          obs_nodes << val 
        else
          str << "  #{rdf_measures[j]} #{encode_value(data[m][i], options)} ;\n"
        end
      end

      obs_index += 1
    }

    str << "  .\n\n"

    if obs_nodes.size > 0
      flatted = obs_nodes.flatten
      str << turtle_indent(flatted.join("\n"))
      str << "  \n\n"
    end

    obs << str

  }
  obs
end

#prefixes(var, options = {}) ⇒ Object 



117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
 
# File 'lib/publisci/dataset/data_cube.rb', line 117

def prefixes(var, options={})
  var = sanitize([var]).first
  options = defaults().merge(options)
  base = options[:base_url]
  <<-EOF.unindent
  @base <#{base}/dc/dataset/#{var}/> .
  @prefix ns:    <#{base}/dc/dataset/#{var}/> .
  @prefix qb:    <http://purl.org/linked-data/cube#> .
  @prefix rdf:   <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
  @prefix rdfs:  <http://www.w3.org/2000/01/rdf-schema#> .
  @prefix prop:  <#{base}/properties/> .
  @prefix dct:   <http://purl.org/dc/terms/> .
  @prefix xsd:   <http://www.w3.org/2001/XMLSchema#> .
  @prefix cs:    <#{base}/dc/dataset/#{var}/cs/> .
  @prefix code:  <#{base}/dc/dataset/#{var}/code/> .
  @prefix owl:   <http://www.w3.org/2002/07/owl#> .
  @prefix skos:  <http://www.w3.org/2004/02/skos/core#> .
  @prefix foaf:     <http://xmlns.com/foaf/0.1/> .
  @prefix org:      <http://www.w3.org/ns/org#> .
  @prefix prov:     <http://www.w3.org/ns/prov#> .

  EOF
end

#vocabulary(vocab, options = {}) ⇒ Object 



88
89
90
91
92
93
94
95
96
 
# File 'lib/publisci/dataset/data_cube.rb', line 88

def vocabulary(vocab,options={})
  if vocab.is_a?(String) && vocab =~ /^http:\/\//
    RDF::Vocabulary.new(vocab)
  elsif RDF.const_defined? vocab.to_sym && RDF.const_get(vocab.to_sym).inspect =~ /^RDF::Vocabulary/
    RDF.const_get(vocab)
  else
    nil
  end
end