def run(entry_path, set_path, en_path, de_path, _set):
entryset = p.load(open(entry_path))
nmt = NMT(entryset, _set) # translate to german
entryset = nmt.postprocess()
entryset = order.run(entryset, 'de') # order german
# referring expressions
entryset = reg.run(entryset, 'en')
lexsize, templates, templates_de, entities, references = stats.run(
entryset)
# run xml generator
parser.run_generator(entryset=entryset,
input_dir=set_path,
output_dir=en_path,
lng='en')
parser.run_generator(entryset=entryset,
input_dir=set_path,
output_dir=de_path,
lng='de')
# extract and generate templates based on sentence segmentation
en_temp = template.run(entryset)
json.dump(en_temp,
open(os.path.join(en_path, 'templates.json'), 'w'),
indent=4,
separators=(',', ': '))
de_temp = template.run(entryset, 'de')
json.dump(de_temp,
open(os.path.join(de_path, 'templates.json'), 'w'),
indent=4,
separators=(',', ': '))
return lexsize, templates, templates_de, entities, references
't_dayOfWeek_train', 'current_local_flow_train',
'stack_local_flow_train', 'global_flow_train'
]
]
param_dict['test_data'] = [
data[name] for name in [
'g_hour_test', 'g_dayOfWeek_test', 't_hour_test',
't_dayOfWeek_test', 'current_local_flow_test',
'stack_local_flow_test', 'global_flow_test'
]
]
param_dict['train_ground'] = data['ground_truth_train']
param_dict['test_ground'] = data['ground_truth_test']
param_dict['max'], param_dict['min'] = mmn._max, mmn._min
param_dict['start_time'], param_dict['end_time'] = data[
'predict_time_test'][0], data['predict_time_test'][-1]
# special, add one model parameter for different map size
param_dict['model'][2][
'width'] = 32 if param_dict['dataset'] == 'bj_taxi' else 16
param_dict['model'][2][
'height'] = 32 if param_dict['dataset'] == 'bj_taxi' else 8
print('\n Load data elapsed time : %.3f seconds\n' % (time.time() - ts))
print('=' * 30)
# ===============================================================
template.run(param_dict)
def image_to_text(str):
img = cv2.imread(str, 0)
# img = cv2.resize(img, (50, 50), interpolation=cv2.INTER_CUBIC)
with open('KNNClassifier.pkl', 'rb') as f:
clf2 = pickle.load(f)
with open('ExtraTreesClassifier.pkl', 'rb') as f:
clf1 = pickle.load(f)
with open('MPLClassifier4.pkl', 'rb') as f:
clf3 = pickle.load(f)
with open('scaler4.pkl', 'rb') as f:
scaler = pickle.load(f)
list_chars = template.run(img)
# print(len(list_chars))
# print(len(list_chars[0]))
ret_str = ""
for word_list in list_chars:
chars = []
for char_img in word_list:
datas = get_data(char_img)
# util.display_image(char_img)
chars.append(datas)
chars = scaler.transform(chars)
out_vec1 = clf1.predict(chars)
out_vec2 = clf2.predict(chars)
out_vec3 = clf3.predict(chars)
x1 = ""
for vec in out_vec1:
cnt = 0
for i in vec:
cnt = cnt + 1
if i == 1:
break
val = ""
if cnt < 11:
cnt = cnt - 1
val = chr(48 + cnt)
elif cnt > 10 and cnt < 37:
cnt = cnt - 11
val = chr(65 + cnt)
else:
cnt -= 37
val = chr(97 + cnt)
x1 = x1 + val
x2 = ""
for vec in out_vec2:
cnt = 0
for i in vec:
cnt = cnt + 1
if i == 1:
break
val = ""
if cnt < 11:
cnt = cnt - 1
val = chr(48 + cnt)
elif cnt > 10 and cnt < 37:
cnt = cnt - 11
val = chr(65 + cnt)
else:
cnt -= 37
val = chr(97 + cnt)
x2 = x2 + val
x3 = ""
for vec in out_vec3:
cnt = 0
for i in vec:
cnt = cnt + 1
if i == 1:
break
val = ""
if cnt < 11:
cnt = cnt - 1
val = chr(48 + cnt)
elif cnt > 10 and cnt < 37:
cnt = cnt - 11
val = chr(65 + cnt)
else:
cnt -= 37
val = chr(97 + cnt)
x3 = x3 + val
finalx = ""
for i in range(0, len(x1)):
l = []
if x1[i] != 'z':
l.append(x1[i])
if x2[i] != 'z':
l.append(x2[i])
if x3[i] != 'z':
l.append(x3[i])
if len(l) == 0:
finalx += 'z'
else:
finalx += l[0]
ret_str += finalx
ret_str += " "
return ret_str
