def cf_run(learner, data, k_folds, name, widget=None):
"""Runs a classification filter
:param learner: WekaClassifier
:param data: Orange dataset
:param k_folds:
:param name:
:param timeout:
:param widget:
:return:
"""
somelearner = learner
print somelearner
noisyIndices = []
selection = orange.MakeRandomIndicesCV(data, folds=k_folds)
count_noisy = [0] * k_folds
for test_fold in range(k_folds):
# train_data = wsutil.client.arff_to_weka_instances(arff = train_arffstr, class_index = data.domain.index(data.domain.classVar))['instances']
train_data = convert_dataset_from_orange_to_scikit(
data.select(selection, test_fold, negate=1))
test_inds = [
i for i in range(len(selection)) if selection[i] == test_fold
]
# test_data = wsutil.client.arff_to_weka_instances(arff = test_arffstr, class_index = data.domain.index(data.domain.classVar))['instances']
test_data = convert_dataset_from_orange_to_scikit(
data.select(selection, test_fold))
#print "\t\t", "Learned on", len(train_data), "examples"
#file.flush()
print "before cl build"
# classifier = wseval.client.build_classifier(learner = somelearner, instances = train_data)['classifier']
learner.build_classifier(train_data)
print "after cl build"
# eval_test_data = wseval.client.apply_classifier(classifier = classifier, instances = test_data)
scikit_dataset_predicted = learner.apply_classifier(test_data)
print "after apply"
for i in range(len(scikit_dataset_predicted.target)):
#print "Test data length:", len(test_data), "Test inds length:", len(test_inds), "Eval Test data length:", len(eval_test_data)
# print i, "v for zanki", eval_test_data[i]['classes'], data[test_inds[i]].getclass()
# if eval_test_data[i]['classes'] != unicode(data[test_inds[i]].getclass()):
if scikit_dataset_predicted.target[
i] != scikit_dataset_predicted.targetPredicted[i]:
# selection_filter[int(example[meta_id].value)] = 0
noisyIndices.append(test_inds[i])
count_noisy[test_fold] += 1
# END test_data
if not (widget is None):
widget.progress = int((test_fold + 1) * 1.0 / k_folds * 100)
widget.save()
# END test_fold
return {'inds': sorted(noisyIndices), 'name': get_weka_name(name)}
def cf_run(learner, data, k_folds, name, widget=None):
"""Runs a classification filter
:param learner: WekaClassifier
:param data: Orange dataset
:param k_folds:
:param name:
:param timeout:
:param widget:
:return:
"""
somelearner = learner
print somelearner
noisyIndices = []
selection = orange.MakeRandomIndicesCV(data, folds=k_folds)
count_noisy = [0]*k_folds
for test_fold in range(k_folds):
# train_data = wsutil.client.arff_to_weka_instances(arff = train_arffstr, class_index = data.domain.index(data.domain.classVar))['instances']
train_data = convert_dataset_from_orange_to_scikit( data.select(selection, test_fold, negate=1) )
test_inds = [i for i in range(len(selection)) if selection[i] == test_fold ]
# test_data = wsutil.client.arff_to_weka_instances(arff = test_arffstr, class_index = data.domain.index(data.domain.classVar))['instances']
test_data = convert_dataset_from_orange_to_scikit( data.select(selection, test_fold) )
#print "\t\t", "Learned on", len(train_data), "examples"
#file.flush()
print "before cl build"
# classifier = wseval.client.build_classifier(learner = somelearner, instances = train_data)['classifier']
learner.build_classifier(train_data)
print "after cl build"
# eval_test_data = wseval.client.apply_classifier(classifier = classifier, instances = test_data)
scikit_dataset_predicted = learner.apply_classifier(test_data)
print "after apply"
for i in range(len(scikit_dataset_predicted.target)):
#print "Test data length:", len(test_data), "Test inds length:", len(test_inds), "Eval Test data length:", len(eval_test_data)
# print i, "v for zanki", eval_test_data[i]['classes'], data[test_inds[i]].getclass()
# if eval_test_data[i]['classes'] != unicode(data[test_inds[i]].getclass()):
if scikit_dataset_predicted.target[i] != scikit_dataset_predicted.targetPredicted[i]:
# selection_filter[int(example[meta_id].value)] = 0
noisyIndices.append(test_inds[i])
count_noisy[test_fold] += 1
# END test_data
if not(widget is None):
widget.progress = int((test_fold+1)*1.0/k_folds*100)
widget.save()
# END test_fold
return {'inds': sorted(noisyIndices), 'name': get_weka_name(name)}
def add_class_noise(input_dict):
"""Widget Add Class Noise
"""
data_scikit = input_dict['data']
if not(d.is_target_nominal(data_scikit)):
raise Exception("Widget Add Class Noise accepts only datasets with nominal class!")
data = u.convert_dataset_from_scikit_to_orange(data_scikit)
import cf_noise_detection.noiseAlgorithms4lib as nalg
noise_indices, orange_data = nalg.add_class_noise(data, input_dict['noise_level'], input_dict['rnd_seed'])
data = u.convert_dataset_from_orange_to_scikit(orange_data)
output_dict = {'noise_inds':noise_indices, 'noisy_data': data}
return output_dict
def noiserank_select(postdata,input_dict, output_dict):
try:
output_dict['indices']= outselection = [int(i) for i in postdata['selected']]
# data = input_dict['data']
data = u.convert_dataset_from_scikit_to_orange(input_dict['data'])
selection = [0]*len(data)
for i in outselection:
selection[i] = 1
outdata = data.select(selection, 1)
data_scikit = u.convert_dataset_from_orange_to_scikit(outdata)
output_dict['selection'] = data_scikit
except KeyError:
output_dict['selection'] = None
return output_dict
def add_class_noise(input_dict):
"""Widget Add Class Noise
"""
data_scikit = input_dict['data']
if not (d.is_target_nominal(data_scikit)):
raise Exception(
"Widget Add Class Noise accepts only datasets with nominal class!")
data = u.convert_dataset_from_scikit_to_orange(data_scikit)
import cf_noise_detection.noiseAlgorithms4lib as nalg
noise_indices, orange_data = nalg.add_class_noise(
data, input_dict['noise_level'], input_dict['rnd_seed'])
data = u.convert_dataset_from_orange_to_scikit(orange_data)
output_dict = {'noise_inds': noise_indices, 'noisy_data': data}
return output_dict
def noiserank_select(postdata, input_dict, output_dict):
try:
output_dict['indices'] = outselection = [
int(i) for i in postdata['selected']
]
# data = input_dict['data']
data = u.convert_dataset_from_scikit_to_orange(input_dict['data'])
selection = [0] * len(data)
for i in outselection:
selection[i] = 1
outdata = data.select(selection, 1)
data_scikit = u.convert_dataset_from_orange_to_scikit(outdata)
output_dict['selection'] = data_scikit
except KeyError:
output_dict['selection'] = None
return output_dict
