def train(X, y, set_id):
EM_result = {}
for ex in xrange(len(no_of_expert_groups)):
#generate expert #self.Training_instances = self.N - self.Testing_instanceswrong percentage
#60% good:40 % bad
EM_result[ex] = {}
for missing_percent in pmissing:
print "For group ", ex
expert_wrong_percentage = []
for i in xrange(int(no_of_expert_groups[ex]*expert_bads)):
#bads
num = 0.90 #((random()%0.5) + 0.5) % 1.0
expert_wrong_percentage.append(num)
for i in xrange(int(no_of_expert_groups[ex]*expert_goods)):
#goods
num = 0.30 #random()%0.5
expert_wrong_percentage.append(num)
crowds_EM = None
failed = 0
iterations = 0
total_iter = 10
while iterations < total_iter :
try:
crowds_EM = Crowds_EM( X, y, min_class_label, max_class_label, expert_wrong_percentage, verbose= verbose_output, synthetic=synthetic_data, missing=missing_data, percent_missing=missing_percent)
#crowds_EM.run_EM_missing()
crowds_EM.run()
except Exception,e:
#Rerunning ...
import traceback
print traceback.print_exc()
failed+=1
try:
crowds_EM = Crowds_EM( X, y, min_class_label, max_class_label, expert_wrong_percentage, verbose= verbose_output, synthetic=synthetic_data, missing=missing_data, percent_missing=missing_percent)
#crowds_EM.run_EM_missing()
crowds_EM.run()
except Exception,e:
failed+=1
pass
else :
EM_result[ex][missing_percent] = crowds_EM.results
break
else :
EM_result[ex][missing_percent] = crowds_EM.results
break
#print "iteration :" , iterations
iterations+=1
def train(X, y, set_id):
EM_result = {}
for ex in xrange(len(no_of_expert_groups)):
print "For group ", ex
expert_wrong_percentage = []
for i in xrange(int(no_of_expert_groups[ex] * expert_bads)):
# bads
num = 0.90 # ((random()%0.5) + 0.5) % 1.0
expert_wrong_percentage.append(num)
for i in xrange(int(no_of_expert_groups[ex] * expert_goods)):
# goods
num = 0.30 # random()%0.5
expert_wrong_percentage.append(num)
crowds_EM = None
failed = 0
iterations = 0
total_iter = 10
while iterations < total_iter:
try:
crowds_EM = Crowds_EM(
X, y, min_class_label, max_class_label, expert_wrong_percentage, verbose=verbose_output
)
crowds_EM.run()
except Exception, e:
# Rerunning ...
import traceback
print traceback.print_exc()
failed += 1
try:
crowds_EM = Crowds_EM(
X, y, min_class_label, max_class_label, expert_wrong_percentage, verbose=verbose_output
)
crowds_EM.run()
except Exception, e:
failed += 1
pass
else:
crowds_EM.results[""]
EM_result[ex] = crowds_EM.results
break
else:
EM_result[ex] = crowds_EM.results
break
iterations += 1
#!/usr/bin/env python
import sys
sys.path.append('../src/')
import numpy as np
from crowds_EM import Crowds_EM
from pprint import pprint
np.seterr(all='raise')
#alpha - sensitivity of experts
#beta - specificity of experts
dataset_filename = '../dataset/dataset_breastcancer'
delimiter_char = ','
skiprow_no = 0 #The first row corresponds to feature names, so it can be skipped
expert_wrong_percentage = [0.10, 0.90, 0.90] # expert y manipulation wrong percentage
min_class_label = 0
max_class_label = 1
data = np.loadtxt(dataset_filename, delimiter=delimiter_char, skiprows=(skiprow_no)) #load the dataset
crowds_EM = Crowds_EM( data, min_class_label, max_class_label, expert_wrong_percentage, verbose= True)
crowds_EM.run()
pprint (crowds_EM.results)
crowds_EM.visualize()
#!/usr/bin/env python
import sys
sys.path.append('../src/')
import numpy as np
from crowds_EM import Crowds_EM
np.seterr(all='raise')
#alpha - sensitivity of experts
#beta - specificity of experts
dataset_filename = '../dataset/dataset_abalone'
delimiter_char = ','
skiprow_no = 0 #The first row corresponds to feature names, so it can be skipped
expert_wrong_percentage = [0.10, 0.90, 0.10, 0.20, 0.10, 0.80, 0.20, 0.30,0.90, 0.90, 0.80] # expert y manipulation wrong percentage
min_class_label = 5
max_class_label = 15
data = np.loadtxt(dataset_filename, delimiter=delimiter_char, skiprows=(skiprow_no)) #load the dataset
crowds_EM = Crowds_EM( data, min_class_label, max_class_label, expert_wrong_percentage, verbose= True)
crowds_EM.run()
