def exc():
# 5. Test
tmp = store.loadTermData()
termList = {'X': [i[0] for i in tmp], 'y': [int(i[1]) for i in tmp]}
print('=======================================================')
print('=> Term Classifying...')
if (file_model):
clf = store.loadClassifier(file=file_model)
else:
clf = store.loadClassifier()
results = []
for i in range(len(termList['X'])):
preprocessd_term = preprocess(termList['X'][i])
X = np.asarray([extractFeatureText(termList['X'][i])])
results.append(clf.predict(X)[0].tolist() + clf.predict_proba(X)[0].tolist() +
['', preprocessd_term] + X[0].tolist())
titles = ['TestCase', 'Term', 'Label', 'Predicted Label', 'Name Score', 'Address Score', 'Phone Score', '', 'Preprocessed_Term'] + \
feature_names
tacc = sum([1 for (y1, y2) in zip(termList['y'], [result[0] for result in results]) if (y1 == y2)]) / len(termList['y'])
if (file_model):
store.saveTermTestResults(tacc, titles, termList, results, file=file_model + '_' + file_term_classify_result)
else:
store.saveTermTestResults(tacc, titles, termList, results, file=timeManage.getTime() + '_' + file_term_classify_result)
return tacc
def exc():
# 5. Test
tmp = store.loadTermData()
termList = {'X': [i[0] for i in tmp], 'y': [int(i[1]) for i in tmp]}
print('=======================================================')
print('=> Term Classifying...')
if (file_model):
clf = store.loadClassifier(file=file_model)
else:
clf = store.loadClassifier()
results = []
for i in range(len(termList['X'])):
preprocessd_term = preprocess(termList['X'][i])
X = np.asarray([extractFeatureText(termList['X'][i], getFeatureNames())])
y_hat = clf.predict(X)[0].tolist()[0]
results.append(clf.predict(X)[0].tolist() + clf.predict_proba(X)[0].tolist() +
[1 if (y_hat != termList['y'][i]) else 0, preprocessd_term] + X[0].tolist())
titles = ['TestCase', 'Term', 'Label', 'Predicted Label', 'Name Score', 'Address Score', 'Phone Score', 'Error', 'Preprocessed_Term'] + \
getFeatureNames()
tacc = sum([1 for (y1, y2) in zip(termList['y'], [result[0] for result in results]) if (y1 == y2)]) / len(termList['y'])
if (file_model):
store.saveTermTestResults(tacc, titles, termList, results, file=file_model + '_' + file_term_classify_result)
else:
store.saveTermTestResults(tacc, titles, termList, results, file=timeManage.getTime() + '_' + file_term_classify_result)
return tacc
def test(feature_func, preprocessing_func):
# 4. Test
termList = store.loadTermData()
print('=======================================================')
print('=> Term Classifying...')
# _time, templateList = sg.parseAddress(termList, feature_func, preprocessing_func)
clf = store.loadClassifier()
results = []
for i in range(len(termList['X'])):
preprocessd_term = eval('preprocessing(termList[\'X\'][i])')
X = np.asarray([
extractFeatureText(feature_func, preprocessing_func,
termList['X'][i])
])
results.append(
clf.predict(X)[0].tolist() + clf.predict_proba(X)[0].tolist() +
['', preprocessd_term] + X[0].tolist())
titles = ['TestCase', 'Term', 'Label', 'Predicted Label', 'Name Score', 'Address Score', 'Phone Score', '', 'Preprocessed_Term'] + \
feature_names
store.saveTermTestResults(titles, termList, results)
def exc():
alpha = 0.05
tt = norm.isf(alpha / 2)
modelInfos, modelDict = store.loadAllModel()
groups = models.groupModels(modelInfos, modelDict)
data = [['#', 'Learning Rate', 'Learning Rule', 'N_Iter', 'Features', 'Avg_Mean_Distance', 'Avg_Var_Distance',
'alpha', 'H0: Avg_Mean_Distance = 0']]
tmp = store.loadTermData()
termList = {'X': [i[0] for i in tmp], 'y': [int(i[1]) for i in tmp]}
for i, igroup in zip(range(len(groups)), groups):
if (len(igroup['models'].keys()) >= 2):
feature_manager.updateFeatureList(igroup['group-info']['features'])
_X = np.asarray([extractFeatureText(term, getFeatureNames()) for term in termList['X']])
d, v = models.checkModelConvergence(igroup['models'], _X)
t = d / math.sqrt(v)
data.append([
i,
igroup['group-info']['learning_rate'],
igroup['group-info']['learning_rule'],
igroup['group-info']['n_iter'],
str(igroup['group-info']['features']),
d,
v,
alpha,
'Accept' if abs(t) < tt else 'Reject'
])
# ================================
workbook = xlsxwriter.Workbook(folder_model + '/' + file_model_result)
store.writeSheet(workbook.add_worksheet('original'), data)
workbook.close()
from libs import store, models
from libs.features import *
from config import *
import xlsxwriter
modelInfos, modelDict = store.loadAllModel()
groups = models.groupModels(modelInfos, modelDict)
data = [['#', 'Learning Rate', 'Learning Rule', 'N_Iter', 'Avg_Mean_Distance', 'Avg_Var_Distance',
'alpha', 'H0: Avg_Mean_Distance = 0', 'P(distance < ' + str(delta_threshold) + ')',
'p(Accept H0: mean_1 = mean_2)']]
tmp = store.loadTermData()
termList = {'X': [i[0] for i in tmp], 'y': [int(i[1]) for i in tmp]}
_X = np.asarray([extractFeatureText(term, getFeatureNames()) for term in termList['X']])
workbook_d = xlsxwriter.Workbook(folder_model + '/' + file_model_details)
store.writeSheet(workbook_d.add_worksheet('GroupInfo'),
[['Group', 'Learning_Rate', 'Learning_Rule', 'n_Iter']] + \
[[i,
g['group-info']['learning_rate'],
g['group-info']['learning_rule'],
g['group-info']['n_iter']] for i, g in zip(range(len(groups)), groups)]
)
for i, igroup in zip(range(len(groups)), groups):
results = models.checkModelConvergence(igroup['models'], _X)
store.writeSheet(workbook_d.add_worksheet('Group' + str(i)), results['data'])
from libs.features import *
from config import *
import xlsxwriter
modelInfos, modelDict = store.loadAllModel()
groups = models.groupModels(modelInfos, modelDict)
data = [[
'#', 'Learning Rate', 'Learning Rule', 'N_Iter', 'Avg_Mean_Distance',
'Avg_Var_Distance', 'alpha', 'H0: Avg_Mean_Distance = 0',
'P(distance < ' + str(delta_threshold) + ')',
'p(Accept H0: mean_1 = mean_2)'
]]
tmp = store.loadTermData()
termList = {'X': [i[0] for i in tmp], 'y': [int(i[1]) for i in tmp]}
_X = np.asarray(
[extractFeatureText(term, getFeatureNames()) for term in termList['X']])
workbook_d = xlsxwriter.Workbook(folder_model + '/' + file_model_details)
store.writeSheet(workbook_d.add_worksheet('GroupInfo'),
[['Group', 'Learning_Rate', 'Learning_Rule', 'n_Iter']] + \
[[i,
g['group-info']['learning_rate'],
g['group-info']['learning_rule'],
g['group-info']['n_iter']] for i, g in zip(range(len(groups)), groups)]
)
for i, igroup in zip(range(len(groups)), groups):
results = models.checkModelConvergence(igroup['models'], _X)