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 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 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 parseAddress(textList, file_model=None):
if (file_model):
clf_model = store.loadClassifier(file=file_model)
else:
clf_model = store.loadClassifier()
_time = []
templateList = []
print('=======================================================')
print('=> Address Parsing...')
for (i, text) in zip(range(len(textList)), textList):
print('==> Parsing text ' + str(i) + '...')
millis_S = int(round(time.time() * 1000))
ptemplates = templateSegment(text, nterm)
templates = templateFiler(clf_model, ptemplates)
millis_E = int(round(time.time() * 1000))
_time.append((millis_E - millis_S)/1000)
templateList.append(templates)
return (_time, templateList)
def parseAddress(textList, file_model=None):
if (file_model):
clf_model = store.loadClassifier(file=file_model)
else:
clf_model = store.loadClassifier()
_time = []
templateList = []
print('=======================================================')
print('=> Address Parsing...')
for (i, text) in zip(range(len(textList)), textList):
print('==> Parsing text ' + str(i) + '...')
millis_S = int(round(time.time() * 1000))
ptemplates = templateSegment(text, nterm)
templates = templateFiler(clf_model, ptemplates)
millis_E = int(round(time.time() * 1000))
_time.append((millis_E - millis_S) / 1000)
templateList.append(templates)
return (_time, templateList)
