cdk predictions fixed

1 files changed, 68 insertions, 2 deletions

diff --git a/bin/classification-summary.rb b/bin/classification-summary.rb
index a3e4172..c6755a1 100755
--- a/bin/classification-summary.rb
+++ b/bin/classification-summary.rb
@@ -1,4 +1,70 @@
 #!/usr/bin/env ruby
 require_relative "../lib/lazar"
-stat = ClassificationStatistics.new ARGV[0]
-stat.summary
+#stat = ClassificationStatistics.new ARGV[0]
+#stat.summary
+dir = File.join(File.dirname(ARGV[0]),"crossvalidation")
+folds = Dir[File.join(dir,"[0-9]*")]
+
+predictions = []
+tp=0
+tn=0
+fp=0
+fn=0
+n=0
+experimental = {}
+
+lines = File.readlines(File.join(ARGV[0])) 
+lines.shift
+lines.each do |line|
+  items = line.chomp.split(',')
+  experimental[items[0]] ||= []
+  experimental[items[0]] << items[1].to_i
+end
+
+File.open(File.join(dir,"predictions.csv"),"w+") do |f|
+  folds.each do |fold|
+    pred = File.readlines(File.join(fold,"test-prediction.csv")).collect{|row| row.chomp.split(",")}
+    pred.shift
+    pred.each do |prediction|
+      smi = prediction[0]
+      exp = experimental[smi]
+      unless exp.nil? or prediction[2].empty? or exp.empty?
+        p = prediction[2].to_i
+        n+=1
+        v = "NA"
+        exp.each do |e|
+          if p and e
+            if p == 1 and e == 1
+              v = "TP"
+              tp+=1
+            elsif p == 0 and e == 0
+              v = "TN"
+              tn+=1
+            elsif p == 1 and e == 0
+              v = "FP"
+              fp+=1
+            elsif p == 0 and e == 1
+              v = "FN"
+              fn+=1
+            end
+          end
+          predictions << v
+        end
+      f.puts([smi,v].join(","))
+      end
+    end
+  end
+end
+
+File.open(File.join(dir,"confusion-matrix.csv"),"w+") do |f|
+  f.puts "#{tp},#{fp}\n#{fn},#{tn}"
+end
+
+File.open(File.join(dir,"summary.csv"),"w+") do |f|
+  f.puts "accuracy,#{(tp+tn)/(tp+fp+tn+fn).to_f}"
+  f.puts "true_positive_rate,#{tp/(tp+fn).to_f}"
+  f.puts "true_negative_rate,#{tn/(tn+fp).to_f}"
+  f.puts "positive_predictive_value,#{tp/(tp+fp).to_f}"
+  f.puts "negative_predictive_value,#{tn/(tn+fn).to_f}"
+end
+