From 08e5768e9a446db8ab95152d2e9403a0e635ec63 Mon Sep 17 00:00:00 2001
From: Christoph Helma <helma@in-silico.ch>
Date: Mon, 8 Mar 2021 17:41:26 +0100
Subject: cdk predictions fixed

---
 bin/crossvalidation-folds.rb | 54 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)
 create mode 100755 bin/crossvalidation-folds.rb

(limited to 'bin/crossvalidation-folds.rb')

diff --git a/bin/crossvalidation-folds.rb b/bin/crossvalidation-folds.rb
new file mode 100755
index 0000000..0c765f7
--- /dev/null
+++ b/bin/crossvalidation-folds.rb
@@ -0,0 +1,54 @@
+#!/usr/bin/env ruby
+require_relative "../lib/lazar"
+model = Model.new ARGV[0]
+ARGV[1] ? folds = ARGV[1].to_i : folds = 10
+nr_instances = model.train.size
+indices = (0..nr_instances-1).to_a.shuffle
+mid = (nr_instances/folds)
+start = 0
+0.upto(folds-1) do |i|
+  fork do
+    # split train data
+    puts "Creating fold #{i}"
+    last = start+mid
+    last = last-1 unless nr_instances%folds > i
+    test_idxs = indices[start..last] || []
+    idxs = {
+      :train => indices-test_idxs,
+      :test => test_idxs
+    }
+    start = last+1
+    # write training/test data
+    cv_dir = File.join(File.dirname(ARGV[0]),"crossvalidation",i.to_s)
+    idxs.each do |t,idx|
+      file = File.join(cv_dir,t.to_s+".csv")
+      `mkdir -p #{File.dirname file}`
+      case t
+      when :train
+        File.open(file,"w+") do |f|
+          f.puts (["Canonical SMILES",model.dependent_variable_name] + model.independent_variable_names).join(",")
+          idx.collect{|i| model.train[i]}.each do |t|
+            f.puts t.join(",")
+          end
+        end
+      when :test
+        File.open(file,"w+") do |f|
+          f.puts (["Canonical SMILES"] + model.independent_variable_names).join(",")
+          idx.collect{|i| model.train[i]}.each do |t|
+            t.delete_at(1)
+            f.puts t.join(",")
+          end
+        end
+        file = File.join(cv_dir,t.to_s+"-experimental.csv")
+        File.open(file,"w+") do |f|
+          f.puts (["Canonical SMILES", model.dependent_variable_name]).join(",")
+          idx.collect{|i| model.train[i]}.each do |t|
+            # TODO fix
+            f.puts t[0..1].join(",")
+          end
+        end
+      end
+    end
+    Process.waitall
+  end
+end
-- 
cgit v1.2.3