Module: OpenTox::Validation::RegressionStatistics

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

Overview

Statistical evaluation of regression validations

Instance Method Summary collapse

Instance Method Details

#correlation_plot(format: "png") ⇒ Blob

Plot predicted vs measured values

Parameters:

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

Returns:

  • (Blob) 


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
198
199
200
 
# File 'lib/validation-statistics.rb', line 172

def correlation_plot format: "png"
  unless correlation_plot_id
    tmpfile = "/tmp/#{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 += " [#{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

#percent_within_prediction_interval ⇒ Float

Get percentage of measurements within the prediction interval

Returns:



165
166
167
 
# File 'lib/validation-statistics.rb', line 165

def percent_within_prediction_interval
  100*within_prediction_interval.to_f/(within_prediction_interval+out_of_prediction_interval)
end

#statistics ⇒ Hash

Get statistics

Returns:

  • (Hash) 


113
114
115
116
117
118
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
 
# File 'lib/validation-statistics.rb', line 113

def statistics
  self.warnings = []
  self.rmse = 0
  self.mae = 0
  self.within_prediction_interval = 0
  self.out_of_prediction_interval = 0
  x = []
  y = []
  predictions.each do |cid,pred|
    if pred[:value] and pred[:measurements] 
      x << pred[:measurements].median
      y << pred[:value]
      error = pred[:value]-pred[:measurements].median
      self.rmse += error**2
      self.mae += error.abs
      if pred[:prediction_interval]
        if pred[:measurements].median >= pred[:prediction_interval][0] and pred[:measurements].median <= pred[:prediction_interval][1]
          self.within_prediction_interval += 1
        else
          self.out_of_prediction_interval += 1
        end
      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
  R.assign "measurement", x
  R.assign "prediction", y
  R.eval "r <- cor(measurement,prediction,use='pairwise')"
  self.r_squared = R.eval("r").to_ruby**2
  self.mae = self.mae/predictions.size
  self.rmse = Math.sqrt(self.rmse/predictions.size)
  $logger.debug "R^2 #{r_squared}"
  $logger.debug "RMSE #{rmse}"
  $logger.debug "MAE #{mae}"
  $logger.debug "#{percent_within_prediction_interval.round(2)}% of measurements within prediction interval"
  $logger.debug "#{warnings}"
  save
  {
    :mae => mae,
    :rmse => rmse,
    :r_squared => r_squared,
    :within_prediction_interval => within_prediction_interval,
    :out_of_prediction_interval => out_of_prediction_interval,
  }
end

#worst_predictions ⇒ Hash

Get predictions with measurements outside of the prediction interval

Returns:

  • (Hash) 


204
205
206
207
208
209
210
211
212
213
214
215
216
217
 
# File 'lib/validation-statistics.rb', line 204

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