def noiserank(input_dict):
"""Widget NoiseRank
:param input_dict:
:return:
"""
allnoise = {}
data = u.convert_dataset_from_scikit_to_orange(input_dict['data'])
for item in input_dict['noise']:
det_by = item['name']
for i in item['inds']:
if not allnoise.has_key(i):
allnoise[i] = {}
allnoise[i]['id'] = i
allnoise[i]['class'] = data[int(i)].getclass().value
allnoise[i]['by'] = []
allnoise[i]['by'].append(det_by)
print allnoise[i]['by']
from operator import itemgetter
outallnoise = sorted(allnoise.values(), key=itemgetter('id'))
outallnoise.sort(compareNoisyExamples)
output_dict = {}
output_dict['allnoise'] = outallnoise
output_dict['selection'] = {}
return output_dict
def noiserank(input_dict):
"""Widget NoiseRank
:param input_dict:
:return:
"""
allnoise = {}
data = u.convert_dataset_from_scikit_to_orange(input_dict['data'])
for item in input_dict['noise']:
det_by = item['name']
for i in item['inds']:
if not allnoise.has_key(i):
allnoise[i] = {}
allnoise[i]['id'] = i
allnoise[i]['class'] = data[int(i)].getclass().value
allnoise[i]['by'] = []
allnoise[i]['by'].append(det_by)
print allnoise[i]['by']
from operator import itemgetter
outallnoise = sorted(allnoise.values(), key=itemgetter('id'))
outallnoise.sort(compareNoisyExamples)
output_dict = {}
output_dict['allnoise'] = outallnoise
output_dict['selection'] = {}
return output_dict
def classification_filter(input_dict, widget):
import cf_noise_detection.noiseAlgorithms4lib as nalg
output_dict = {}
# output_dict['noise_dict']= noiseAlgorithms4lib.cf_decide(input_dict, widget)
orange_dataset = u.convert_dataset_from_scikit_to_orange(input_dict['data'])
output_dict['noise_dict']= nalg.cf_decide(input_dict['learner'], orange_dataset, int(input_dict['k_folds']), widget=None)
return output_dict
def saturation_filter(input_dict, widget):
import cf_noise_detection.noiseAlgorithms4lib as nalg
orange_dataset = u.convert_dataset_from_scikit_to_orange(input_dict['data'])
if not(input_dict['satur_type'] in ['normal', 'prune']):
raise Exception("Only 'normal' or 'prune' allowed for 'satur_type'.")
output_dict = {}
output_dict['noise_dict']= nalg.saturation_type(orange_dataset, input_dict['satur_type'], widget)
return output_dict
def classification_filter(input_dict, widget):
import cf_noise_detection.noiseAlgorithms4lib as nalg
output_dict = {}
# output_dict['noise_dict']= noiseAlgorithms4lib.cf_decide(input_dict, widget)
orange_dataset = u.convert_dataset_from_scikit_to_orange(
input_dict['data'])
output_dict['noise_dict'] = nalg.cf_decide(input_dict['learner'],
orange_dataset,
int(input_dict['k_folds']),
widget=None)
return output_dict
def saturation_filter(input_dict, widget):
import cf_noise_detection.noiseAlgorithms4lib as nalg
orange_dataset = u.convert_dataset_from_scikit_to_orange(
input_dict['data'])
if not (input_dict['satur_type'] in ['normal', 'prune']):
raise Exception("Only 'normal' or 'prune' allowed for 'satur_type'.")
output_dict = {}
output_dict['noise_dict'] = nalg.saturation_type(orange_dataset,
input_dict['satur_type'],
widget)
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
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
