Module: OpenTox::Algorithm::Neighbors

Defined in:
lib/utils.rb,
lib/algorithm.rb

Overview

neighbors

Class Method Summary collapse

Class Method Details

.get_confidence(params) ⇒ Object

Get confidence. @param Required keys: :sims, :acts @return Confidence



241
242
243
244
245
246
 
# File 'lib/utils.rb', line 241

def self.get_confidence(params)
  conf = params[:sims].inject{|sum,x| sum + x }
  confidence = conf/params[:sims].size
  LOGGER.debug "Confidence is: '" + confidence.to_s + "'."
  return confidence
end

.local_svm_classification(params) ⇒ Numeric

Local support vector regression from neighbors

Parameters:

  • params (Hash) —

    Keys ‘:props, :acts, :sims, :min_train_performance` are required

Returns:

  • (Numeric) —

    A prediction value.



334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
 
# File 'lib/algorithm.rb', line 334

def self.local_svm_classification(params)

  begin
    confidence = 0.0
    prediction = nil

    LOGGER.debug "Local SVM."
    if params[:acts].size>0
      if params[:props]
        n_prop = params[:props][0].collect
        q_prop = params[:props][1].collect
        props = [ n_prop, q_prop ]
      end
      acts = params[:acts].collect
      acts = acts.collect{|v| "Val" + v.to_s} # Convert to string for R to recognize classification
      prediction = local_svm_prop( props, acts, params[:min_train_performance]) # params[:props].nil? signals non-prop setting
      prediction = prediction.sub(/Val/,"") if prediction # Convert back to Float
      confidence = 0.0 if prediction.nil?
      LOGGER.debug "Prediction is: '" + prediction.to_s + "'."
      confidence = get_confidence({:sims => params[:sims][1], :acts => params[:acts]})
    end
    {:prediction => prediction, :confidence => confidence}
  rescue Exception => e
    LOGGER.debug "#{e.class}: #{e.message}"
    LOGGER.debug "Backtrace:\n\t#{e.backtrace.join("\n\t")}"
  end

end

.local_svm_prop(props, acts, min_train_performance) ⇒ Numeric

Local support vector prediction from neighbors. Uses propositionalized setting. Not to be called directly (use local_svm_regression or local_svm_classification).

Parameters:

  • props, (Array) —

    propositionalization of neighbors and query structure e.g. [ Array_for_q, two-nested-Arrays_for_n ]

  • acts, (Array) —

    activities for neighbors.

  • min_train_performance, (Float) —

    parameter to control censoring

Returns:

  • (Numeric) —

    A prediction value.



372
373
374
375
376
377
378
379
380
381
382
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
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
 
# File 'lib/algorithm.rb', line 372

def self.local_svm_prop(props, acts, min_train_performance)

  LOGGER.debug "Local SVM (Propositionalization / Kernlab Kernel)."
  n_prop = props[0] # is a matrix, i.e. two nested Arrays.
  q_prop = props[1] # is an Array.

  prediction = nil
  if Algorithm::zero_variance? acts
    prediction = acts[0]
  else
    #LOGGER.debug gram_matrix.to_yaml
    @r = RinRuby.new(false,false) # global R instance leads to Socket errors after a large number of requests
    @r.eval "set.seed(1)"
    @r.eval "suppressPackageStartupMessages(library('caret'))" # requires R packages "caret" and "kernlab"
    @r.eval "suppressPackageStartupMessages(library('doMC'))" # requires R packages "multicore"
    @r.eval "registerDoMC()" # switch on parallel processing
    begin

      # set data
      LOGGER.debug "Setting R data ..."
      @r.n_prop = n_prop.flatten
      @r.n_prop_x_size = n_prop.size
      @r.n_prop_y_size = n_prop[0].size
      @r.y = acts
      @r.q_prop = q_prop
      #@r.eval "y = matrix(y)"
      @r.eval "prop_matrix = matrix(n_prop, n_prop_x_size, n_prop_y_size, byrow=T)"
      @r.eval "q_prop = matrix(q_prop, 1, n_prop_y_size, byrow=T)"

      # prepare data
      LOGGER.debug "Preparing R data ..."
      @r.eval "if (class(y) == 'character') { y = factor(y); suppressPackageStartupMessages(library('class')) }" # For classification

      @r.eval <<-EOR
        rem = nearZeroVar(prop_matrix)
        if (length(rem) > 0) {
          prop_matrix = prop_matrix[,-rem,drop=F]
          q_prop = q_prop[,-rem,drop=F]
        }
        rem = findCorrelation(cor(prop_matrix))
        if (length(rem) > 0) {
          prop_matrix = prop_matrix[,-rem,drop=F]
          q_prop = q_prop[,-rem,drop=F]
        }
      EOR

      # model + support vectors
      LOGGER.debug "Creating R SVM model ..."
      @r.eval <<-EOR
        model = train(prop_matrix,y,method="svmradial",tuneLength=8,trControl=trainControl(method="LGOCV",number=10),preProcess=c("center", "scale"))
        perf = ifelse ( class(y)!='numeric', max(model$results$Accuracy), model$results[which.min(model$results$RMSE),]$Rsquared )
      EOR


      # prediction
      LOGGER.debug "Predicting ..."
      @r.eval "p = predict(model,q_prop)"
      @r.eval "if (class(y)!='numeric') p = as.character(p)"
      prediction = @r.p

      # censoring
      prediction = nil if ( @r.perf.nan? || @r.perf < min_train_performance )
      LOGGER.debug "Performance: #{sprintf("%.2f", @r.perf)}"
    rescue Exception => e
      LOGGER.debug "#{e.class}: #{e.message}"
      LOGGER.debug "Backtrace:\n\t#{e.backtrace.join("\n\t")}"
    end
    @r.quit # free R
  end
  prediction
end

.local_svm_regression(params) ⇒ Numeric

Local support vector regression from neighbors

Parameters:

  • params (Hash) —

    Keys ‘:props, :acts, :sims, :min_train_performance` are required

Returns:

  • (Numeric) —

    A prediction value.



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
 
# File 'lib/algorithm.rb', line 302

def self.local_svm_regression(params)

  begin
    confidence = 0.0
    prediction = nil

    LOGGER.debug "Local SVM."
    if params[:acts].size>0
      if params[:props]
        n_prop = params[:props][0].collect
        q_prop = params[:props][1].collect
        props = [ n_prop, q_prop ]
      end
      acts = params[:acts].collect
      prediction = local_svm_prop( props, acts, params[:min_train_performance]) # params[:props].nil? signals non-prop setting
      prediction = nil if (!prediction.nil? && prediction.infinite?)
      LOGGER.debug "Prediction is: '" + prediction.to_s + "'."
      confidence = get_confidence({:sims => params[:sims][1], :acts => params[:acts]})
      confidence = 0.0 if prediction.nil?
    end
    {:prediction => prediction, :confidence => confidence}
  rescue Exception => e
    LOGGER.debug "#{e.class}: #{e.message}"
    LOGGER.debug "Backtrace:\n\t#{e.backtrace.join("\n\t")}"
  end

end

.weighted_majority_vote(params) ⇒ Numeric

Classification with majority vote from neighbors weighted by similarity

Parameters:

  • params (Hash) —

    Keys ‘:acts, :sims, :value_map` are required

Returns:

  • (Numeric) —

    A prediction value.



258
259
260
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
 
# File 'lib/algorithm.rb', line 258

def self.weighted_majority_vote(params)

  neighbor_contribution = 0.0
  confidence_sum = 0.0
  confidence = 0.0
  prediction = nil

  LOGGER.debug "Weighted Majority Vote Classification."

  params[:acts].each_index do |idx|
    neighbor_weight = params[:sims][1][idx]
    neighbor_contribution += params[:acts][idx] * neighbor_weight
    if params[:value_map].size == 2 # AM: provide compat to binary classification: 1=>false 2=>true
      case params[:acts][idx]
      when 1
        confidence_sum -= neighbor_weight
      when 2
        confidence_sum += neighbor_weight
      end
    else
      confidence_sum += neighbor_weight
    end
  end
  if params[:value_map].size == 2 
    if confidence_sum >= 0.0
      prediction = 2 unless params[:acts].size==0
    elsif confidence_sum < 0.0
      prediction = 1 unless params[:acts].size==0
    end
  else 
    prediction = (neighbor_contribution/confidence_sum).round  unless params[:acts].size==0  # AM: new multinomial prediction
  end 

  LOGGER.debug "Prediction is: '" + prediction.to_s + "'." unless prediction.nil?
  confidence = (confidence_sum/params[:acts].size).abs if params[:acts].size > 0
  LOGGER.debug "Confidence is: '" + confidence.to_s + "'." unless prediction.nil?
  return {:prediction => prediction, :confidence => confidence.abs}
end