Class: OpenTox::Algorithm::Caret

Inherits:
Object
  • Object
show all
Defined in:
lib/caret.rb,
lib/caret-classification.rb

Overview

Ruby interface for the R caret package Caret model list: topepo.github.io/caret/modelList.html

Class Method Summary collapse

Class Method Details

.create_model_and_predict(dependent_variables:, independent_variables:, weights:, method:, query_variables:) ⇒ Hash

Create a local R caret model and make a prediction



15
16
17
18
19
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
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
 
# File 'lib/caret.rb', line 15

def self.create_model_and_predict dependent_variables:, independent_variables:, weights:, method:, query_variables:
  remove = []
  # remove independent_variables with single values
  independent_variables.each_with_index { |values,i| remove << i if values.uniq.size == 1}
  remove.sort.reverse.each do |i|
    independent_variables.delete_at i
    query_variables.delete_at i
  end
  if independent_variables.flatten.uniq == ["NA"] or independent_variables.flatten.uniq == [] 
    prediction = Algorithm::Regression::weighted_average dependent_variables:dependent_variables, weights:weights
    prediction[:warnings] = ["No variables for regression model, using weighted average of similar substances (no prediction interval available)."]
  elsif
    dependent_variables.size < 3
    prediction = Algorithm::Regression::weighted_average dependent_variables:dependent_variables, weights:weights
    prediction[:warnings] = ["Insufficient number of neighbors (#{dependent_variables.size}) for regression model, using weighted average of similar substances (no prediction interval available)."]
  else
    dependent_variables.each_with_index do |v,i| 
      dependent_variables[i] = to_r(v)
    end
    independent_variables.each_with_index do |c,i| 
      c.each_with_index do |v,j|
        independent_variables[i][j] = to_r(v)
      end
    end
    query_variables.each_with_index do |v,i| 
      query_variables[i] = to_r(v)
    end
    begin
      R.assign "weights", weights
      r_data_frame = "data.frame(#{([dependent_variables]+independent_variables).collect{|r| "c(#{r.join(',')})"}.join(', ')})"
      R.eval "data <- #{r_data_frame}"
      R.assign "features", (0..independent_variables.size-1).to_a
      R.eval "names(data) <- append(c('activities'),features)" #
      R.eval "model <- train(activities ~ ., data = data, method = '#{method}', na.action = na.pass, allowParallel=TRUE)"
    rescue => e
      $logger.debug "R caret model creation error for:"
      $logger.debug dependent_variables
      $logger.debug independent_variables
      prediction = Algorithm::Regression::weighted_average dependent_variables:dependent_variables, weights:weights
      prediction[:warnings] ||= []
      prediction[:warnings] << "R caret model creation error, using weighted average of similar substances (no prediction interval available)."
      return prediction
    end
    begin
      R.eval "query <- data.frame(rbind(c(#{query_variables.join ','})))"
      R.eval "names(query) <- features" 
      R.eval "prediction <- predict(model,query)"
      value = R.eval("prediction").to_f
      rmse = R.eval("getTrainPerf(model)$TrainRMSE").to_f
      r_squared = R.eval("getTrainPerf(model)$TrainRsquared").to_f
      prediction_interval = value-1.96*rmse, value+1.96*rmse
      prediction = {
        :value => value,
        :rmse => rmse,
        :r_squared => r_squared,
        :prediction_interval => prediction_interval
      }
    rescue => e
      $logger.debug "R caret prediction error for:"
      $logger.debug self.inspect
      prediction = Algorithm::Regression::weighted_average dependent_variables:dependent_variables, weights:weights
      prediction[:warnings] << "R caret prediction error, using weighted average of similar substances (no prediction interval available)."
      return prediction
    end
    if prediction.nil? or prediction[:value].nil?
      prediction = Algorithm::Regression::weighted_average dependent_variables:dependent_variables, weights:weights
      prediction[:warnings] << "Empty R caret prediction, using weighted average of similar substances (no prediction interval available)."
    end
  end
  prediction

end

.method_missing(sym, *args, &block) ⇒ Object

Call caret methods dynamically, e.g. Caret.pls



89
90
91
92
 
# File 'lib/caret.rb', line 89

def self.method_missing(sym, *args, &block)
  args.first[:method] = sym.to_s
  self.create_model_and_predict args.first
end

.to_r(v) ⇒ Object

Convert Ruby values to R values



95
96
97
98
99
100
 
# File 'lib/caret.rb', line 95

def self.to_r v
  return "F" if v == false
  return "T" if v == true
  return nil if v.is_a? Float and v.nan?
  v
end