From bdc6b5b40437896384561d74a510560e9e592364 Mon Sep 17 00:00:00 2001 From: "helma@in-silico.ch" Date: Tue, 9 Oct 2018 18:20:27 +0200 Subject: tentative random forest classification: hangs unpredictably during caret model generation/optimization for some (inorganic?) compounds. --- lib/classification.rb | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'lib/classification.rb') diff --git a/lib/classification.rb b/lib/classification.rb index a875903..2668e4a 100644 --- a/lib/classification.rb +++ b/lib/classification.rb @@ -19,6 +19,7 @@ module OpenTox probabilities[a] = w.sum/weights.sum end # DG: hack to ensure always two probability values + # TODO: does not work for arbitrary feature names FIX!! if probabilities.keys.uniq.size == 1 missing_key = probabilities.keys.uniq[0].match(/^non/) ? probabilities.keys.uniq[0].sub(/non-/,"") : "non-"+probabilities.keys.uniq[0] probabilities[missing_key] = 0.0 @@ -26,7 +27,7 @@ module OpenTox probabilities = probabilities.collect{|a,p| [a,weights.max*p]}.to_h p_max = probabilities.collect{|a,p| p}.max prediction = probabilities.key(p_max) - {:value => prediction,:probabilities => probabilities} + {:value => prediction,:probabilities => probabilities,:warnings => []} end end -- cgit v1.2.3