diff options
author | gebele <gebele@in-silico.ch> | 2016-12-12 09:15:48 +0000 |
---|---|---|
committer | gebele <gebele@in-silico.ch> | 2016-12-12 09:15:48 +0000 |
commit | da086fad5b45c0d7b59feb40d0108ac620613933 (patch) | |
tree | 7e9cf8c9332e30552ab255ee9b30e04e904977b4 /lib/classification.rb | |
parent | 32a16d99b51642cac8e75f90c43753d8d05ab770 (diff) | |
parent | 4570f11444bc10da88d849e9a2812e95a8933c8a (diff) |
merged development
Diffstat (limited to 'lib/classification.rb')
-rw-r--r-- | lib/classification.rb | 36 |
1 files changed, 14 insertions, 22 deletions
diff --git a/lib/classification.rb b/lib/classification.rb index 0202940..e8c179f 100644 --- a/lib/classification.rb +++ b/lib/classification.rb @@ -3,32 +3,24 @@ module OpenTox class Classification - def self.weighted_majority_vote compound, params - neighbors = params[:neighbors] - weighted_sum = {} - sim_sum = 0.0 - confidence = 0.0 - neighbors.each do |row| - sim = row["tanimoto"] - row["features"][params[:prediction_feature_id].to_s].each do |act| - weighted_sum[act] ||= 0 - weighted_sum[act] += sim - end + def self.weighted_majority_vote dependent_variables:, independent_variables:nil, weights:, query_variables: + class_weights = {} + dependent_variables.each_with_index do |v,i| + class_weights[v] ||= [] + class_weights[v] << weights[i] unless v.nil? end - case weighted_sum.size - when 1 - return {:value => weighted_sum.keys.first, :confidence => weighted_sum.values.first/neighbors.size.abs} - when 2 - sim_sum = weighted_sum[weighted_sum.keys[0]] - sim_sum -= weighted_sum[weighted_sum.keys[1]] - sim_sum > 0 ? prediction = weighted_sum.keys[0] : prediction = weighted_sum.keys[1] - confidence = (sim_sum/neighbors.size).abs - return {:value => prediction,:confidence => confidence} - else - bad_request_error "Cannot predict more than 2 classes, multinomial classifications is not yet implemented. Received classes were: '#{weighted.sum.keys}'" + probabilities = {} + class_weights.each do |a,w| + probabilities[a] = w.sum/weights.sum end + 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} end + end + end end |