Module: OpenTox::Validation::RegressionStatistics

Included in:
RegressionCrossValidation, RegressionLeaveOneOut, RegressionTrainTest
Defined in:
lib/validation-statistics.rb

Overview

Statistical evaluation of regression validations

Instance Attribute Summary collapse

Instance Method Summary collapse

Instance Attribute Details

#x ⇒ Object

Returns the value of attribute x.



115
116
117
 
# File 'lib/validation-statistics.rb', line 115

def x
  @x
end

#y ⇒ Object

Returns the value of attribute y.



115
116
117
 
# File 'lib/validation-statistics.rb', line 115

def y
  @y
end

Instance Method Details

#correlation_plot(format: "png") ⇒ Blob

Plot predicted vs measured values

Parameters:

  • format (String, nil) (defaults to: "png")

Returns:

  • (Blob) 


180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
 
# File 'lib/validation-statistics.rb', line 180

def correlation_plot format: "png"
  #unless correlation_plot_id
    #tmpfile = "/tmp/#{id.to_s}_correlation.#{format}"
    tmpdir = "/tmp"
    #p tmpdir
    FileUtils.mkdir_p tmpdir
    tmpfile = File.join(tmpdir,"#{id.to_s}_correlation.#{format}")
    x = []
    y = []
    feature = Feature.find(predictions.first.last["prediction_feature_id"])
    predictions.each do |sid,p|
      x << p["measurements"].median
      y << p["value"]
    end
    R.assign "measurement", x
    R.assign "prediction", y
    R.eval "all = c(measurement,prediction)"
    R.eval "range = c(min(all), max(all))"
    if feature.name.match /Net cell association/ # ad hoc fix for awkward units
      title = "log2(Net cell association [mL/ug(Mg)])"
    else
      title = feature.name
      title += "-log10(#{feature.unit})" if feature.unit and !feature.unit.blank?
    end
    R.eval "image = qplot(prediction,measurement,main='#{title}',xlab='Prediction',ylab='Measurement',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 => "#{id.to_s}_correlation_plot.#{format}")
    plot_id = $gridfs.insert_one(file)
    update(:correlation_plot_id => plot_id)
  #end
  $gridfs.find_one(_id: correlation_plot_id).data
end

#statistics ⇒ Hash

Get statistics

Returns:

  • (Hash) 


119
120
121
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
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
 
# File 'lib/validation-statistics.rb', line 119

def statistics
  self.warnings = []
  self.rmse = {:all =>0,:confidence_high => 0,:confidence_low => 0}
  self.r_squared  = {:all =>0,:confidence_high => 0,:confidence_low => 0}
  self.mae = {:all =>0,:confidence_high => 0,:confidence_low => 0}
  self.within_prediction_interval = {:all =>0,:confidence_high => 0,:confidence_low => 0}
  self.out_of_prediction_interval = {:all =>0,:confidence_high => 0,:confidence_low => 0}
  @x = {:all => [],:confidence_high => [],:confidence_low => []}
  @y = {:all => [],:confidence_high => [],:confidence_low => []}
  self.nr_predictions = {:all =>0,:confidence_high => 0,:confidence_low => 0}
  predictions.each do |cid,pred|
    !if pred[:value] and pred[:measurements] and !pred[:measurements].empty?
      insert_prediction pred, :all
      if pred[:confidence].match(/Similar/i)
        insert_prediction pred, :confidence_high
      elsif pred[:confidence].match(/Low/i)
        insert_prediction pred, :confidence_low
      end
    else
      trd_id = model.training_dataset_id
      smiles = Compound.find(cid).smiles
      self.warnings << "No training activities for #{smiles} in training dataset #{trd_id}."
      $logger.debug "No training activities for #{smiles} in training dataset #{trd_id}."
    end
  end
  [:all,:confidence_high,:confidence_low].each do |a|
    if @x[a].size > 2
      R.assign "measurement", @x[a]
      R.assign "prediction", @y[a]
      R.eval "r <- cor(measurement,prediction,use='pairwise')"
      self.r_squared[a] = R.eval("r").to_ruby**2
    else
      self.r_squared[a] = 0
    end
    if self.nr_predictions[a] > 0
      self.mae[a] = self.mae[a]/self.nr_predictions[a]
      self.rmse[a] = Math.sqrt(self.rmse[a]/self.nr_predictions[a])
    else
      self.mae[a] = nil
      self.rmse[a] = nil
    end
  end
  $logger.debug "R^2 #{r_squared}"
  $logger.debug "RMSE #{rmse}"
  $logger.debug "MAE #{mae}"
  $logger.debug "Nr predictions #{nr_predictions}"
  $logger.debug "#{within_prediction_interval} measurements within prediction interval"
  save
  {
    :mae => mae,
    :rmse => rmse,
    :r_squared => r_squared,
    :within_prediction_interval => self.within_prediction_interval,
    :out_of_prediction_interval => out_of_prediction_interval,
    :nr_predictions => nr_predictions,
  }
end

#worst_predictions ⇒ Hash

Get predictions with measurements outside of the prediction interval

Returns:

  • (Hash) 


216
217
218
219
220
221
222
223
224
225
226
227
228
229
 
# File 'lib/validation-statistics.rb', line 216

def worst_predictions
  worst_predictions = predictions.select do |sid,p|
    p["prediction_interval"] and p["value"] and (p["measurements"].max < p["prediction_interval"][0] or p["measurements"].min > p["prediction_interval"][1])
  end.compact.to_h
  worst_predictions.each do |sid,p|
    p["error"] = (p["value"] - p["measurements"].median).abs
    if p["measurements"].max < p["prediction_interval"][0]
      p["distance_prediction_interval"] = (p["measurements"].max - p["prediction_interval"][0]).abs
    elsif p["measurements"].min > p["prediction_interval"][1]
      p["distance_prediction_interval"] = (p["measurements"].min - p["prediction_interval"][1]).abs
    end
  end
  worst_predictions.sort_by{|sid,p| p["distance_prediction_interval"] }.to_h
end