Class: OpenTox::RegressionLeaveOneOutValidation

Inherits:
LeaveOneOutValidation show all
Defined in:
lib/leave-one-out-validation.rb

Instance Method Summary collapse

Methods inherited from LeaveOneOutValidation

create, #model

Instance Method Details

#correlation_plot ⇒ Object 



174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
 
# File 'lib/leave-one-out-validation.rb', line 174

def correlation_plot
  unless correlation_plot_id
    tmpfile = "/tmp/#{id.to_s}_correlation.svg"
    predicted_values = []
    measured_values = []
    predictions.each do |pred|
      pred[:database_activities].each do |activity|
        if pred[:value]
          predicted_values << pred[:value]
          measured_values << activity
        end
      end
    end
    attributes = Model::Lazar.find(self.model_id).attributes
    attributes.delete_if{|key,_| key.match(/_id|_at/) or ["_id","creator","name"].include? key}
    attributes = attributes.values.collect{|v| v.is_a?(String) ? v.sub(/OpenTox::/,'') : v}.join("\n")
    R.assign "measurement", measured_values
    R.assign "prediction", predicted_values
    R.eval "all = c(-log(measurement),-log(prediction))"
    R.eval "range = c(min(all), max(all))"
    R.eval "image = qplot(-log(prediction),-log(measurement),main='#{self.name}',asp=1,xlim=range, ylim=range)"
    R.eval "image = image + geom_abline(intercept=0, slope=1)"
    R.eval "ggsave(file='#{tmpfile}', plot=image)"
    file = Mongo::Grid::File.new(File.read(tmpfile), :filename => "#{self.id.to_s}_correlation_plot.svg")
    plot_id = $gridfs.insert_one(file)
    update(:correlation_plot_id => plot_id)
  end
  $gridfs.find_one(_id: correlation_plot_id).data
end

#statistics ⇒ Object 



135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
 
# File 'lib/leave-one-out-validation.rb', line 135

def statistics
  confidence_sum = 0
  predicted_values = []
  measured_values = []
  predictions.each do |pred|
    pred[:database_activities].each do |activity|
      if pred[:value]
        predicted_values << pred[:value]
        measured_values << activity
        error = Math.log10(pred[:value])-Math.log10(activity)
        self.rmse += error**2
        #self.weighted_rmse += pred[:confidence]*error**2
        self.mae += error.abs
        #self.weighted_mae += pred[:confidence]*error.abs
        #confidence_sum += pred[:confidence]
      end
    end
    if pred[:database_activities].empty?
      warnings << "No training activities for #{Compound.find(compound_id).smiles} in training dataset #{model.training_dataset_id}."
      $logger.debug "No training activities for #{Compound.find(compound_id).smiles} in training dataset #{model.training_dataset_id}."
    end
  end
  R.assign "measurement", measured_values
  R.assign "prediction", predicted_values
  R.eval "r <- cor(-log(measurement),-log(prediction),use='complete')"
  r = R.eval("r").to_ruby

  self.mae = self.mae/predictions.size
  #self.weighted_mae = self.weighted_mae/confidence_sum
  self.rmse = Math.sqrt(self.rmse/predictions.size)
  #self.weighted_rmse = Math.sqrt(self.weighted_rmse/confidence_sum)
  self.r_squared = r**2
  self.finished_at = Time.now
  save
  $logger.debug "R^2 #{r**2}"
  $logger.debug "RMSE #{rmse}"
  $logger.debug "MAE #{mae}"
end