1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
|
module OpenTox
module Algorithm
class Regression
def self.local_weighted_average substance, neighbors
weighted_sum = 0.0
sim_sum = 0.0
neighbors.each do |neighbor|
sim = neighbor["similarity"]
activities = neighbor["measurements"]
activities.each do |act|
weighted_sum += sim*act
sim_sum += sim
end if activities
end
sim_sum == 0 ? prediction = nil : prediction = weighted_sum/sim_sum
{:value => prediction}
end
def self.local_fingerprint_regression substance, neighbors, method='pls'#, method_params="sigma=0.05"
values = []
fingerprints = {}
weights = []
fingerprint_ids = neighbors.collect{|n| Compound.find(n["_id"]).fingerprint}.flatten.uniq.sort
neighbors.each do |n|
fingerprint = Substance.find(n["_id"]).fingerprint
activities = n["measurements"]
activities.each do |act|
values << act
weights << n["similarity"]
fingerprint_ids.each do |id|
fingerprints[id] ||= []
fingerprints[id] << fingerprint.include?(id)
end
end if activities
end
variables = []
data_frame = [values]
fingerprints.each do |k,v|
unless v.uniq.size == 1
data_frame << v.collect{|m| m ? "T" : "F"}
variables << k
end
end
if variables.empty?
prediction = local_weighted_average substance, neighbors
prediction[:warning] = "No variables for regression model. Using weighted average of similar substances."
prediction
else
substance_features = variables.collect{|f| substance.fingerprint.include?(f) ? "T" : "F"}
prediction = r_model_prediction method, data_frame, variables, weights, substance_features
if prediction.nil? or prediction[:value].nil?
prediction = local_weighted_average substance, neighbors
prediction[:warning] = "Could not create local PLS model. Using weighted average of similar substances."
prediction
else
prediction[:prediction_interval] = [prediction[:value]-1.96*prediction[:rmse], prediction[:value]+1.96*prediction[:rmse]]
prediction[:value] = prediction[:value]
prediction[:rmse] = prediction[:rmse]
prediction
end
end
end
#def self.local_physchem_regression(substance:, neighbors:, feature_id:, dataset_id:, method: 'pls')#, method_params="ncomp = 4"
def self.local_physchem_regression substance, neighbors, method='pls' #, method_params="ncomp = 4"
activities = []
weights = []
pc_ids = neighbors.collect{|n| n["common_descriptors"].collect{|d| d[:id]}}.flatten.uniq.sort
data_frame = []
data_frame[0] = []
neighbors.each_with_index do |n,i|
activities = n["measurements"]
activities.each do |act|
data_frame[0][i] = act
weights << n["similarity"]
n["common_descriptors"].each do |d|
j = pc_ids.index(d[:id])+1
data_frame[j] ||= []
data_frame[j][i] = d[:scaled_value]
end
end if activities
#(0..pc_ids.size+1).each do |j| # for R: fill empty values with NA
(0..pc_ids.size).each do |j| # for R: fill empty values with NA
data_frame[j] ||= []
data_frame[j][i] ||= "NA"
end
end
#remove_idx = []
#data_frame.each_with_index do |r,i|
#remove_idx << i if r.uniq.size == 1 # remove properties with a single value TODO: don't break R names assignment
#end
#p data_frame.size
#p pc_ids.size
#data_frame.delete_if.with_index { |_, index| remove_idx.include? index }
#pc_ids.delete_if.with_index { |_, index| remove_idx.include? index-1 }
#remove_idx.sort.reverse.each do |i|
#p i
#data_frame.delete_at i
#pc_ids.delete_at i
#end
#p data_frame.size
#p pc_ids.size
if pc_ids.empty?
prediction = local_weighted_average substance, neighbors
prediction[:warning] = "No variables for regression model. Using weighted average of similar substances."
prediction
else
query_descriptors = pc_ids.collect { |i| substance.scaled_values[i] }
remove_idx = []
query_descriptors.each_with_index do |v,i|
#remove_idx << i if v == "NA"
remove_idx << i unless v
end
remove_idx.sort.reverse.each do |i|
data_frame.delete_at i
pc_ids.delete_at i
query_descriptors.delete_at i
end
prediction = r_model_prediction method, data_frame, pc_ids.collect{|i| "\"#{i}\""}, weights, query_descriptors
if prediction.nil?
prediction = local_weighted_average substance, neighbors
prediction[:warning] = "Could not create local PLS model. Using weighted average of similar substances."
end
p prediction
prediction
end
end
def self.r_model_prediction method, training_data, training_features, training_weights, query_feature_values
R.assign "weights", training_weights
r_data_frame = "data.frame(#{training_data.collect{|r| "c(#{r.join(',')})"}.join(', ')})"
=begin
=end
rlib = File.expand_path(File.join(File.dirname(__FILE__),"..","R"))
File.open("tmp.R","w+"){|f|
f.puts "suppressPackageStartupMessages({
library(iterators,lib=\"#{rlib}\")
library(foreach,lib=\"#{rlib}\")
library(ggplot2,lib=\"#{rlib}\")
library(grid,lib=\"#{rlib}\")
library(gridExtra,lib=\"#{rlib}\")
library(pls,lib=\"#{rlib}\")
library(caret,lib=\"#{rlib}\")
library(doMC,lib=\"#{rlib}\")
registerDoMC(#{NR_CORES})
})"
f.puts "data <- #{r_data_frame}\n"
f.puts "weights <- c(#{training_weights.join(', ')})"
f.puts "features <- c(#{training_features.join(', ')})"
f.puts "names(data) <- append(c('activities'),features)" #
f.puts "model <- train(activities ~ ., data = data, method = '#{method}')"
f.puts "fingerprint <- data.frame(rbind(c(#{query_feature_values.join ','})))"
f.puts "names(fingerprint) <- features"
f.puts "prediction <- predict(model,fingerprint)"
}
R.eval "data <- #{r_data_frame}"
R.assign "features", training_features
p training_features.size
p R.eval("names(data)").to_ruby.size
begin
R.eval "names(data) <- append(c('activities'),features)" #
R.eval "model <- train(activities ~ ., data = data, method = '#{method}', na.action = na.pass)"
R.eval "fingerprint <- data.frame(rbind(c(#{query_feature_values.join ','})))"
R.eval "names(fingerprint) <- features"
R.eval "prediction <- predict(model,fingerprint)"
value = R.eval("prediction").to_f
rmse = R.eval("getTrainPerf(model)$TrainRMSE").to_f
r_squared = R.eval("getTrainPerf(model)$TrainRsquared").to_f
prediction_interval = value-1.96*rmse, value+1.96*rmse
{
:value => value,
:rmse => rmse,
:r_squared => r_squared,
:prediction_interval => prediction_interval
}
rescue
return nil
end
end
end
end
end
|
