diff options
Diffstat (limited to 'report/plot_factory.rb')
| -rw-r--r-- | report/plot_factory.rb | 161 |
1 files changed, 68 insertions, 93 deletions
diff --git a/report/plot_factory.rb b/report/plot_factory.rb index 2074ce5..6083d26 100644 --- a/report/plot_factory.rb +++ b/report/plot_factory.rb @@ -2,6 +2,10 @@ ENV['JAVA_HOME'] = "/usr/bin" unless ENV['JAVA_HOME'] ENV['PATH'] = ENV['JAVA_HOME']+":"+ENV['PATH'] unless ENV['PATH'].split(":").index(ENV['JAVA_HOME']) ENV['RANK_PLOTTER_JAR'] = "RankPlotter/RankPlotter.jar" unless ENV['RANK_PLOTTER_JAR'] +CONF_PLOT_RANGE = { :accuracy => [0.45,1.05], :true_positive_rate => [0.45,1.05],:true_negative_rate => [0.45,1.05], + :false_positive_rate => [0.45,1.05], :false_negative_rate => [0.45,1.05], :positive_predictive_value => [0.45,1.05], + :negative_predictive_value => [0.45,1.05], :r_square => [0, 1.05], :sample_correlation_coefficient => [0, 1.05] } + class Array def swap!(i,j) tmp = self[i] @@ -47,7 +51,6 @@ class Array end end - module Reports module PlotFactory @@ -81,9 +84,11 @@ module Reports y_i = valid_indices.collect{ |i| y_i[i] } end - names << ( name_attribute==:crossvalidation_fold ? "fold " : "" ) + v.send(name_attribute).to_s - x << x_i - y << y_i + if x_i.size>0 + names << ( name_attribute==:crossvalidation_fold ? "fold " : "" ) + v.send(name_attribute).to_s + x << x_i + y << y_i + end end names = [""] if names.size==1 @@ -130,31 +135,22 @@ module Reports end end - def self.confidence_plot_class_performance( validation_set, actual_accept_value, predicted_accept_value ) + def self.confidence_plot_class_performance( validation_set, performance_attribute, performance_accept_value ) true_class = nil - if actual_accept_value==nil and predicted_accept_value==nil - perf = "Accuracy" - elsif actual_accept_value!=nil - if validation_set.get_true_accept_value==actual_accept_value - perf = "True Positive Rate" - true_class = actual_accept_value - elsif validation_set.get_accept_values.size==2 and validation_set.get_true_accept_value==(validation_set.get_accept_values-[actual_accept_value])[0] - perf = "True Negative Rate" + if performance_accept_value==nil + perf = performance_attribute.to_s.nice_attr + else + invert_true_class = (validation_set.get_accept_values.size==2 and + validation_set.get_true_accept_value==(validation_set.get_accept_values-[performance_accept_value])[0]) + if invert_true_class && performance_attribute==:true_positive_rate + perf = :true_negative_rate.to_s.nice_attr true_class = validation_set.get_true_accept_value - else - perf = "True Positive Rate" - true_class = actual_accept_value - end - elsif predicted_accept_value!=nil - if validation_set.get_true_accept_value==predicted_accept_value - perf = "Positive Predictive Value" - true_class = predicted_accept_value - elsif validation_set.get_accept_values.size==2 and validation_set.get_true_accept_value==(validation_set.get_accept_values-[predicted_accept_value])[0] - perf = "Negative Predictive Value" + elsif invert_true_class && performance_attribute==:positive_predictive_value + perf = :negative_predictive_value.to_s.nice_attr true_class = validation_set.get_true_accept_value else - perf = "Positive Predictive Value" - true_class = predicted_accept_value + perf = performance_attribute.to_s.nice_attr + true_class = performance_accept_value end end title = perf+" vs Confidence Plot" @@ -162,12 +158,8 @@ module Reports {:title =>title, :performance => perf} end - - def self.create_confidence_plot( out_files, validation_set, actual_accept_value = nil, - predicted_accept_value = nil, split_set_attribute=nil, show_single_curves=false ) + def self.create_confidence_plot( out_files, validation_set, performance_attribute, performance_accept_value, split_set_attribute=nil, show_single_curves=false ) - raise "param combination not supported" if actual_accept_value!=nil and predicted_accept_value!=nil - out_files = [out_files] unless out_files.is_a?(Array) LOGGER.debug "creating confidence plot for '"+validation_set.size.to_s+"' validations, out-file:"+out_files.inspect @@ -178,7 +170,7 @@ module Reports performance = [] attribute_values.each do |value| begin - data = transform_confidence_predictions(validation_set.filter({split_set_attribute => value}), actual_accept_value, predicted_accept_value, false) + data = transform_confidence_predictions(validation_set.filter({split_set_attribute => value}), performance_attribute, performance_accept_value, false) names << split_set_attribute.to_s.nice_attr+" "+value.to_s confidence << data[:confidence][0] performance << data[:performance][0] @@ -186,31 +178,21 @@ module Reports LOGGER.warn "could not create confidence plot for "+value.to_s end end - #RubyPlot::plot_lines(out_file, "Percent Correct vs Confidence Plot", "Confidence", "Percent Correct", names, fp_rates, tp_rates ) out_files.each do |out_file| - case validation_set.unique_feature_type - when "classification" - info = confidence_plot_class_performance( validation_set, actual_accept_value, predicted_accept_value ) - RubyPlot::accuracy_confidence_plot(out_file, info[:title], "Confidence", info[:performance], names, confidence, performance) - when "regression" - RubyPlot::accuracy_confidence_plot(out_file, "RMSE vs Confidence Plot", "Confidence", "RMSE", names, confidence, performance, true) - end + info = confidence_plot_class_performance( validation_set, performance_attribute, performance_accept_value ) + RubyPlot::confidence_plot(out_file, info[:title], "Confidence", info[:performance], + names, confidence, performance, CONF_PLOT_RANGE[performance_attribute]) end else - data = transform_confidence_predictions(validation_set, actual_accept_value, predicted_accept_value, show_single_curves) - out_files.each do |out_file| - case validation_set.unique_feature_type - when "classification" - info = confidence_plot_class_performance( validation_set, actual_accept_value, predicted_accept_value ) - RubyPlot::accuracy_confidence_plot(out_file, info[:title], "Confidence", info[:performance], data[:names], data[:confidence], data[:performance]) - when "regression" - RubyPlot::accuracy_confidence_plot(out_file, "RMSE vs Confidence Plot", "Confidence", "RMSE", data[:names], data[:confidence], data[:performance], true) - end + data = transform_confidence_predictions(validation_set, performance_attribute, performance_accept_value, show_single_curves) + out_files.each do |out_file| + info = confidence_plot_class_performance( validation_set, performance_attribute, performance_accept_value ) + RubyPlot::confidence_plot(out_file, info[:title], "Confidence", info[:performance], + data[:names], data[:confidence], data[:performance], CONF_PLOT_RANGE[performance_attribute]) end end end - def self.create_bar_plot( out_files, validation_set, title_attribute, value_attributes ) out_files = [out_files] unless out_files.is_a?(Array) @@ -349,7 +331,11 @@ module Reports end - def self.transform_confidence_predictions(validation_set, actual_accept_value, predicted_accept_value, add_single_folds=false) + + def self.transform_confidence_predictions(validation_set, performance_attribute, performance_accept_value, add_single_folds) + + feature_type = validation_set.unique_feature_type + accept_values = validation_set.unique_feature_type=="classification" ? validation_set.get_accept_values : nil if (validation_set.size > 1) @@ -357,34 +343,37 @@ module Reports sum_confidence_values = { :predicted_values => [], :actual_values => [], :confidence_values => []} (0..validation_set.size-1).each do |i| - confidence_values = validation_set.get(i).get_predictions.get_prediction_values(actual_accept_value, predicted_accept_value) + confidence_values = validation_set.get(i).get_predictions.get_prediction_values(performance_attribute, performance_accept_value) sum_confidence_values[:predicted_values] += confidence_values[:predicted_values] sum_confidence_values[:confidence_values] += confidence_values[:confidence_values] sum_confidence_values[:actual_values] += confidence_values[:actual_values] if add_single_folds begin - pref_conf_rates = get_performance_confidence_rates(confidence_values) + perf_conf_rates = get_performance_confidence_rates(confidence_values, performance_attribute, performance_accept_value, + feature_type, accept_values) names << "fold "+i.to_s - performance << pref_conf_rates[:performance] - confidence << pref_conf_rates[:confidence] + performance << perf_conf_rates[:performance] + confidence << perf_conf_rates[:confidence] faint << true rescue LOGGER.warn "could not get confidence vals for fold "+i.to_s end end end - pref_conf_rates = get_performance_confidence_rates(sum_confidence_values, validation_set.unique_feature_type) + perf_conf_rates = get_performance_confidence_rates(sum_confidence_values, performance_attribute, performance_accept_value, + feature_type, accept_values) names << nil # "all" - performance << pref_conf_rates[:performance] - confidence << pref_conf_rates[:confidence] + performance << perf_conf_rates[:performance] + confidence << perf_conf_rates[:confidence] faint << false return { :names => names, :performance => performance, :confidence => confidence, :faint => faint } else - confidence_values = validation_set.validations[0].get_predictions.get_prediction_values(actual_accept_value, predicted_accept_value) - pref_conf_rates = get_performance_confidence_rates(confidence_values, validation_set.unique_feature_type) - return { :names => [""], :performance => [pref_conf_rates[:performance]], :confidence => [pref_conf_rates[:confidence]] } + confidence_values = validation_set.validations[0].get_predictions.get_prediction_values(performance_attribute, performance_accept_value) + perf_conf_rates = get_performance_confidence_rates(confidence_values, performance_attribute, performance_accept_value, + feature_type, accept_values) + return { :names => [""], :performance => [perf_conf_rates[:performance]], :confidence => [perf_conf_rates[:confidence]] } end end @@ -408,11 +397,11 @@ module Reports "True Positive Rate", plot_data ) end - def self.get_performance_confidence_rates(roc_values, feature_type) + def self.get_performance_confidence_rates(pred_values, performance_attribute, performance_accept_value, feature_type, accept_values) - c = roc_values[:confidence_values] - p = roc_values[:predicted_values] - a = roc_values[:actual_values] + c = pred_values[:confidence_values] + p = pred_values[:predicted_values] + a = pred_values[:actual_values] raise "no prediction values for confidence plot" if p.size==0 (0..p.size-2).each do |i| @@ -425,40 +414,26 @@ module Reports end end #puts c.inspect+"\n"+a.inspect+"\n"+p.inspect+"\n\n" - perf = [] conf = [] - - case feature_type - when "classification" - count = 0 - correct = 0 - (0..p.size-1).each do |i| - count += 1 - correct += 1 if p[i]==a[i] - if i>0 && (c[i]>=conf[-1]-0.00001) - perf.pop - conf.pop - end - perf << correct/count.to_f * 100 - conf << c[i] + predictions = nil + (0..p.size-1).each do |i| + # melt nearly identical confidence values to get a smoother graph + if i>0 && (c[i]>=conf[-1]-0.00001) + perf.pop + conf.pop end - when "regression" - count = 0 - sum_squared_error = 0 - (0..p.size-1).each do |i| - count += 1 - sum_squared_error += (p[i]-a[i])**2 - if i>0 && (c[i]>=conf[-1]-0.00001) - perf.pop - conf.pop - end - perf << Math.sqrt(sum_squared_error/count.to_f) - conf << c[i] + if (predictions == nil) + predictions = Lib::Predictions.new([p[i]],[a[i]],[c[i]],feature_type, accept_values) + else + predictions.update_stats(p[i], a[i], c[i]) end + + val = predictions.send(performance_attribute) + val = val[performance_accept_value] if val.is_a?(Hash) + perf << val + conf << c[i] end - #puts perf.inspect - return {:performance => perf,:confidence => conf} end |