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
200
201
202
203
204
|
module OpenTox
module Validation
module ClassificationStatistics
def statistics
self.accept_values = model.prediction_feature.accept_values
self.confusion_matrix = Array.new(accept_values.size){Array.new(accept_values.size,0)}
self.weighted_confusion_matrix = Array.new(accept_values.size){Array.new(accept_values.size,0)}
true_rate = {}
predictivity = {}
nr_instances = 0
predictions.each do |cid,pred|
# TODO
# use predictions without probabilities (single neighbor)??
# use measured majority class??
if pred[:measurements].uniq.size == 1 and pred[:probabilities]
m = pred[:measurements].first
if pred[:value] == m
if pred[:value] == accept_values[0]
confusion_matrix[0][0] += 1
weighted_confusion_matrix[0][0] += pred[:probabilities][pred[:value]]
nr_instances += 1
elsif pred[:value] == accept_values[1]
confusion_matrix[1][1] += 1
weighted_confusion_matrix[1][1] += pred[:probabilities][pred[:value]]
nr_instances += 1
end
elsif pred[:value] != m
if pred[:value] == accept_values[0]
confusion_matrix[0][1] += 1
weighted_confusion_matrix[0][1] += pred[:probabilities][pred[:value]]
nr_instances += 1
elsif pred[:value] == accept_values[1]
confusion_matrix[1][0] += 1
weighted_confusion_matrix[1][0] += pred[:probabilities][pred[:value]]
nr_instances += 1
end
end
end
end
true_rate = {}
predictivity = {}
accept_values.each_with_index do |v,i|
true_rate[v] = confusion_matrix[i][i]/confusion_matrix[i].reduce(:+).to_f
predictivity[v] = confusion_matrix[i][i]/confusion_matrix.collect{|n| n[i]}.reduce(:+).to_f
end
confidence_sum = 0
weighted_confusion_matrix.each do |r|
r.each do |c|
confidence_sum += c
end
end
self.accuracy = (confusion_matrix[0][0]+confusion_matrix[1][1])/nr_instances.to_f
self.weighted_accuracy = (weighted_confusion_matrix[0][0]+weighted_confusion_matrix[1][1])/confidence_sum.to_f
$logger.debug "Accuracy #{accuracy}"
save
{
:accept_values => accept_values,
:confusion_matrix => confusion_matrix,
:weighted_confusion_matrix => weighted_confusion_matrix,
:accuracy => accuracy,
:weighted_accuracy => weighted_accuracy,
:true_rate => true_rate,
:predictivity => predictivity,
}
end
def confidence_plot
unless confidence_plot_id
tmpfile = "/tmp/#{id.to_s}_confidence.svg"
accuracies = []
confidences = []
correct_predictions = 0
incorrect_predictions = 0
predictions.each do |p|
p[:measurements].each do |db_act|
if p[:value]
p[:value] == db_act ? correct_predictions += 1 : incorrect_predictions += 1
accuracies << correct_predictions/(correct_predictions+incorrect_predictions).to_f
confidences << p[:confidence]
end
end
end
R.assign "accuracy", accuracies
R.assign "confidence", confidences
R.eval "image = qplot(confidence,accuracy)+ylab('accumulated accuracy')+scale_x_reverse()"
R.eval "ggsave(file='#{tmpfile}', plot=image)"
file = Mongo::Grid::File.new(File.read(tmpfile), :filename => "#{self.id.to_s}_confidence_plot.svg")
plot_id = $gridfs.insert_one(file)
update(:confidence_plot_id => plot_id)
end
$gridfs.find_one(_id: confidence_plot_id).data
end
end
module RegressionStatistics
def statistics
# TODO: predictions within prediction_interval
self.rmse = 0
self.mae = 0
x = []
y = []
predictions.each do |cid,pred|
if pred[:value] and pred[:measurements]
x << pred[:measurements].median
y << pred[:value]
error = pred[:value]-pred[:measurements].median
self.rmse += error**2
self.mae += error.abs
else
warnings << "No training activities for #{Compound.find(compound_id).smiles} in training dataset #{model.training_dataset_id}."
$logger.debug "No training activities for #{Compound.find(compound_id).smiles} in training dataset #{model.training_dataset_id}."
end
end
R.assign "measurement", x
R.assign "prediction", y
R.eval "r <- cor(measurement,prediction,use='pairwise')"
self.r_squared = R.eval("r").to_ruby**2
self.mae = self.mae/predictions.size
self.rmse = Math.sqrt(self.rmse/predictions.size)
$logger.debug "R^2 #{r_squared}"
$logger.debug "RMSE #{rmse}"
$logger.debug "MAE #{mae}"
save
{
:mae => mae,
:rmse => rmse,
:r_squared => r_squared,
}
end
def correlation_plot
unless correlation_plot_id
tmpfile = "/tmp/#{id.to_s}_correlation.pdf"
x = []
y = []
feature = Feature.find(predictions.first.last["prediction_feature_id"])
predictions.each do |sid,p|
x << p["value"]
y << p["measurements"].median
end
R.assign "measurement", x
R.assign "prediction", y
R.eval "all = c(measurement,prediction)"
R.eval "range = c(min(all), max(all))"
title = feature.name
title += "[#{feature.unit}]" if feature.unit and !feature.unit.blank?
R.eval "image = qplot(prediction,measurement,main='#{title}',xlab='Prediction',ylab='Measurement',asp=1,xlim=range, ylim=range)"
R.eval "image = image + geom_abline(intercept=0, slope=1)"
R.eval "ggsave(file='#{tmpfile}', plot=image)"
file = Mongo::Grid::File.new(File.read(tmpfile), :filename => "#{id.to_s}_correlation_plot.png")
plot_id = $gridfs.insert_one(file)
update(:correlation_plot_id => plot_id)
end
$gridfs.find_one(_id: correlation_plot_id).data
end
def worst_predictions n: 5, show_neigbors: true, show_common_descriptors: false
worst_predictions = predictions.sort_by{|sid,p| -(p["value"] - p["measurements"].median).abs}[0,n]
worst_predictions.collect do |p|
substance = Substance.find(p.first)
prediction = p[1]
if show_neigbors
neighbors = prediction["neighbors"].collect do |n|
common_descriptors = []
if show_common_descriptors
common_descriptors = n["common_descriptors"].collect do |d|
f=Feature.find(d)
{
:id => f.id.to_s,
:name => "#{f.name} (#{f.conditions})",
:p_value => d[:p_value],
:r_squared => d[:r_squared],
}
end
else
common_descriptors = n["common_descriptors"].size
end
{
:name => Substance.find(n["_id"]).name,
:id => n["_id"].to_s,
:common_descriptors => common_descriptors
}
end
else
neighbors = prediction["neighbors"].size
end
{
:id => substance.id.to_s,
:name => substance.name,
:feature => Feature.find(prediction["prediction_feature_id"]).name,
:error => (prediction["value"] - prediction["measurements"].median).abs,
:prediction => prediction["value"],
:measurements => prediction["measurements"],
:neighbors => neighbors
}
end
end
end
end
end
|