def main():
main_data = get_json_data('res/db4')
random.shuffle(main_data)
tagged = [d for d in main_data if d["tags"]]
untagged = [d for d in main_data if not d["tags"]]
N = len(tagged)
untagged = untagged[:N] #TODO: remove
print(N)
train_data = tagged[:-N / 10]
test_data = tagged[-N / 10:]
path = os.getcwd()
at = AutoTag(os.path.join(path, 'res'))
tags = at.get_tags()
print(tags)
print('classifying')
at.classify(train_data, tags=tags)
print("testing")
print(at.test(test_data))
tagged = [d for d in main_data if '231' in d["tags"]]
untagged = [d for d in main_data if '231' not in d["tags"]][:100]
print(len(tagged))
print(at.get_most_informative_features_from_data(tagged, untagged, 10))
def main():
main_data = get_json_data('res/db4')
random.shuffle(main_data)
tagged = [d for d in main_data if d["tags"]]
untagged = [d for d in main_data if not d["tags"]]
N = len(tagged)
untagged = untagged[:N]#TODO: remove
print(N)
train_data = tagged[:-N/10]
test_data = tagged[-N/10:]
path = os.getcwd()
at = AutoTag(os.path.join(path, 'res'))
tags = at.get_tags()
print(tags)
print('classifying')
at.classify(train_data, tags=tags)
print("testing")
print(at.test(test_data))
tagged = [d for d in main_data if '231' in d["tags"]]
untagged = [d for d in main_data if '231' not in d["tags"]][:100]
print(len(tagged))
print(at.get_most_informative_features_from_data(tagged, untagged, 10))
def svm_predict():
'''
预测准确度
Returns:
预测结果
'''
args = {
'predict_x': None
}
acq = ['predict_x']
types = {
'predict_x': [list, list, float]
}
args = get_json_data(raw=request.get_data(as_text=True), args=args)
missed_arg = check_aquired_args(args=args, acqs=acq)
if missed_arg is not None:
return json.dumps({'state': 'fail', 'msg': '缺少必要参数'})
args = type_format(args=args, types=types)
clf = get_trained_svm()
if clf is None:
return json.dumps({'state': 'fail', 'msg': '模型尚未训练'})
rs = predict(clf, args['predict_x'])
return json.dumps({'state': 'done', 'result': rs.tolist()})
class Global:
USER_DIR = None
CONV = get_json_data("conv.json")
LANG = "DE"
BOT = None
def update_corpus_ids(doc_id):
corpus_ids_file = "./visualization/corpus/corpus_ids.json"
corpus_ids = get_json_data(corpus_ids_file) if os.path.isfile(
corpus_ids_file) else []
if doc_id not in corpus_ids:
corpus_ids = [doc_id] + corpus_ids
save_to_json(corpus_ids_file, corpus_ids)
print('corpus ids updated: %s' % doc_id)
def main():
#root = r"D:\python\competition\dataset\tile_round1_train_20201231"
root = "/home/user/dataset/tile_round1_train_20201231"
json_file = "train_annos.json"
images_dir = "train_imgs"
save_path = "/home/user/dataset/tile_round1_split"
# divide_size = [128, 128] # [h, w]
# stride = [120, 120] # [h, w]
# max_num = 1000
#divide_size = [640, 640] # [h, w]
divide_size = [416, 416]
overlap_ratio = 0.2
stride = [
int(divide_size[0] * (1 - overlap_ratio)),
int(divide_size[1] * (1 - overlap_ratio))
] # [h, w]
max_num = 1000000
if not os.path.exists(save_path):
os.mkdir(save_path)
save_path = check_or_make_dir(save_path,
"size{}X{}".format(divide_size[0],
divide_size[1]),
mkdir=True)
images_dir_path = os.path.join(root, images_dir)
json_file_path = os.path.join(root, json_file)
images_name = os.listdir(images_dir_path)
json_data = get_json_data(json_file_path)
images_data = json_data_to_images_data(json_data)
random.shuffle(images_name)
p = Pool(12) # clw modify: origin is 4
for i, img_name in enumerate(tqdm(images_name)):
if max_num != -1:
if i >= max_num:
continue
try:
# deal_one_image(img_name, images_data, images_dir_path, divide_size, stride, save_path)
p.apply_async(deal_one_image,
args=(
img_name,
images_data,
images_dir_path,
divide_size,
stride,
save_path,
))
except Exception as e:
print(e, img_name)
continue
p.close()
p.join()
generate_val_dataset(save_path, p=0.2) #
def fetch_details(self):
jf = get_json_data(URL_MATCHES_DETAIL % self.detailID)
details = jf[0]
for key in IYMS_ORDER:
self.ratios.append(parse_float(details[key]))
for key in SK_ORDER:
self.ratios.append(parse_float(details[key]))
def fetch_details(self):
jf = get_json_data(URL_MATCHES_DETAIL % self.detailID)
details = jf[0]
for key in IYMS_ORDER:
self.ratios.append(parse_float(details[key]))
for key in SK_ORDER:
self.ratios.append(parse_float(details[key]))
def hk_freq(data_dir, hk_dir):
print('hk freq')
data = get_json_data(data_dir)
at = AutoTag()
for entry in data:
entry['text'] = clean_text(entry['text'])
if not os.path.isdir(hk_dir):
os.mkdir(hk_dir)
with open(hk_dir + 'total', 'w') as f:
pass
word_count = at.count_data(
[w for entry in data for w in entry['text'].split()], hk_dir + 'total')
words = [w.encode('utf-8') for w, c in word_count if c > 40]
with open(hk_dir + 'freqs.csv', 'wb') as csvfile:
# data_encoded = [w.encode('utf-8') for w,c in word_count if c > 40]
w = csv.writer(csvfile,
delimiter=',',
quotechar='"',
quoting=csv.QUOTE_MINIMAL)
w.writerow([u'HK'] + words)
# csvfile.write(','.join([u'HK']+words) + '\n')
hkwords = {}
data_json = get_json(data_dir)
for json_entry in data_json:
if json_entry['model'] != "facebook_feeds.facebook_feed":
continue
name = json_entry['fields']['name']
print(name)
if not name:
continue
name = name.encode('utf-8')
word_count = at.count_data([
w for entry in data
for w in entry['text'].split() if entry["feed"] == json_entry['pk']
], hk_dir + name)
word_dict = {w.encode('utf-8'): c for w, c in word_count}
hkwords[name] = []
for word in words:
if word not in word_dict:
hkwords[name].append(str(0))
else:
hkwords[name].append(str(word_dict[word]))
with open(hk_dir + 'freqs.csv', 'a') as csvfile:
writer = csv.writer(csvfile, delimiter=',')
# writer = csv.writer(csvfile, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
writer.writerow([name] + hkwords[name])
with open(hk_dir + 'freqs_t.csv', 'a') as csvfile:
writer = csv.writer(csvfile,
delimiter=',',
quotechar='"',
quoting=csv.QUOTE_MINIMAL)
for name in hkwords:
writer.writerow([name] + hkwords[name])
def __getBlocks(self, site):
if os.path.isfile('%s/blocks_%s'%(self.__tmpdirectory, site)):
unpopularBlocks = get_json_data_from_file('%s/blocks_%s'%(self.__tmpdirectory, site))
return unpopularBlocks
else:
url = 'http://cms-popularity-prod.cern.ch/popdb/victorinterface/popdbcombine/?sitename=%s' %(site)
unpopularBlocks = get_json_data(url)
dumpTemporaryInfo(unpopularBlocks, self.__tmpdirectory, 'blocks_%s'%(site))
return unpopularBlocks
def test_correct_dict(self):
test_dict = {
'username': '******',
'password': '******'
}
with self.app as c:
c.get(
'/api/igpost',
json=test_dict
)
response = utils.get_json_data()
self.assertEqual(response, test_dict)
def __hasCustodialCopy(self, blockname):
url = 'https://cmsweb.cern.ch/phedex/datasvc/json/prod/blockreplicas?custodial=y&complete=y&block=%s' % (
blockname)
url = url.replace('#', '%23')
self.__logger.debug(url)
replicas = get_json_data(url)
'''
replicas = {
"phedex":{
"request_version":"2.1.8",
"request_timestamp":1311755259.31146,
"instance":"prod",
"request_call":"blockreplicas",
"request_url":"http://cmsweb.cern.ch:7001/phedex/datasvc/json/prod/blockreplicas",
"request_date":"2011-07-27 08:27:39 UTC",
"block":[
{
"bytes":"67095800951",
"files":"32",
"is_open":"n",
"name":"/ZJetsToNuNu_Pt-100_7TeV-herwigpp/Summer11-START311_V2-v1/GEN-SIM#7f6b861b-2263-4854-8abf-d096d35d9f1a",
"id":"2576551",
"replica":[
{
"bytes":"67095800951",
"files":"32",
"node":"T1_IT_CNAF_MSS",
"time_create":"1311331011",
"time_update":"1311610457.398",
"group":"DataOps",
"node_id":"8",
"custodial":"y",
"se":"storm-fe-cms.cr.cnaf.infn.it",
"subscribed":"y",
"complete":"y"}]}],
"call_time":"0.05906"}}
'''
try:
if replicas['phedex']['block'][0]['replica']:
return True
except KeyError:
self.__logger.warning(
'Block %s excepted with KeyError. replicas = %s' %
(blockname, replicas))
return False
except IndexError:
self.__logger.warning(
'Block %s excepted with IndexError. replicas = %s' %
(blockname, replicas))
return False
return False
def __hasCustodialCopy(self, blockname):
url = "https://cmsweb.cern.ch/phedex/datasvc/json/prod/blockreplicas?custodial=y&complete=y&block=%s" % (
blockname
)
url = url.replace("#", "%23")
self.__logger.debug(url)
replicas = get_json_data(url)
"""
replicas = {
"phedex":{
"request_version":"2.1.8",
"request_timestamp":1311755259.31146,
"instance":"prod",
"request_call":"blockreplicas",
"request_url":"http://cmsweb.cern.ch:7001/phedex/datasvc/json/prod/blockreplicas",
"request_date":"2011-07-27 08:27:39 UTC",
"block":[
{
"bytes":"67095800951",
"files":"32",
"is_open":"n",
"name":"/ZJetsToNuNu_Pt-100_7TeV-herwigpp/Summer11-START311_V2-v1/GEN-SIM#7f6b861b-2263-4854-8abf-d096d35d9f1a",
"id":"2576551",
"replica":[
{
"bytes":"67095800951",
"files":"32",
"node":"T1_IT_CNAF_MSS",
"time_create":"1311331011",
"time_update":"1311610457.398",
"group":"DataOps",
"node_id":"8",
"custodial":"y",
"se":"storm-fe-cms.cr.cnaf.infn.it",
"subscribed":"y",
"complete":"y"}]}],
"call_time":"0.05906"}}
"""
try:
if replicas["phedex"]["block"][0]["replica"]:
return True
except KeyError:
self.__logger.warning("Block %s excepted with KeyError. replicas = %s" % (blockname, replicas))
return False
except IndexError:
self.__logger.warning("Block %s excepted with IndexError. replicas = %s" % (blockname, replicas))
return False
return False
def hk_freq(data_dir, hk_dir):
print("hk freq")
data = get_json_data(data_dir)
at = AutoTag()
for entry in data:
entry["text"] = clean_text(entry["text"])
if not os.path.isdir(hk_dir):
os.mkdir(hk_dir)
with open(hk_dir + "total", "w") as f:
pass
word_count = at.count_data([w for entry in data for w in entry["text"].split()], hk_dir + "total")
words = [w.encode("utf-8") for w, c in word_count if c > 40]
with open(hk_dir + "freqs.csv", "wb") as csvfile:
# data_encoded = [w.encode('utf-8') for w,c in word_count if c > 40]
w = csv.writer(csvfile, delimiter=",", quotechar='"', quoting=csv.QUOTE_MINIMAL)
w.writerow([u"HK"] + words)
# csvfile.write(','.join([u'HK']+words) + '\n')
hkwords = {}
data_json = get_json(data_dir)
for json_entry in data_json:
if json_entry["model"] != "facebook_feeds.facebook_feed":
continue
name = json_entry["fields"]["name"]
print(name)
if not name:
continue
name = name.encode("utf-8")
word_count = at.count_data(
[w for entry in data for w in entry["text"].split() if entry["feed"] == json_entry["pk"]], hk_dir + name
)
word_dict = {w.encode("utf-8"): c for w, c in word_count}
hkwords[name] = []
for word in words:
if word not in word_dict:
hkwords[name].append(str(0))
else:
hkwords[name].append(str(word_dict[word]))
with open(hk_dir + "freqs.csv", "a") as csvfile:
writer = csv.writer(csvfile, delimiter=",")
# writer = csv.writer(csvfile, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
writer.writerow([name] + hkwords[name])
with open(hk_dir + "freqs_t.csv", "a") as csvfile:
writer = csv.writer(csvfile, delimiter=",", quotechar='"', quoting=csv.QUOTE_MINIMAL)
for name in hkwords:
writer.writerow([name] + hkwords[name])
def hk_freq(data_dir, hk_dir):
print('hk freq')
data = get_json_data(data_dir)
at = AutoTag()
for entry in data:
entry['text'] = clean_text(entry['text'])
if not os.path.isdir(hk_dir):
os.mkdir(hk_dir)
with open(hk_dir+'total', 'w') as f:
pass
word_count = at.count_data([w for entry in data for w in entry['text'].split()],hk_dir+'total')
words = [w.encode('utf-8') for w,c in word_count if c > 40]
with open(hk_dir+'freqs.csv', 'wb') as csvfile:
# data_encoded = [w.encode('utf-8') for w,c in word_count if c > 40]
w = csv.writer(csvfile, delimiter = ',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
w.writerow([u'HK']+words)
# csvfile.write(','.join([u'HK']+words) + '\n')
hkwords = {}
data_json = get_json(data_dir)
for json_entry in data_json:
if json_entry['model'] != "facebook_feeds.facebook_feed":
continue
name = json_entry['fields']['name']
print(name)
if not name:
continue
name = name.encode('utf-8')
word_count = at.count_data([w for entry in data for w in entry['text'].split() if entry["feed"] == json_entry['pk']],hk_dir+name)
word_dict = {w.encode('utf-8'):c for w,c in word_count}
hkwords[name] = []
for word in words:
if word not in word_dict:
hkwords[name].append(str(0))
else:
hkwords[name].append(str(word_dict[word]))
with open(hk_dir+'freqs.csv', 'a') as csvfile:
writer = csv.writer(csvfile, delimiter=',')
# writer = csv.writer(csvfile, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
writer.writerow([name]+hkwords[name])
with open(hk_dir+'freqs_t.csv', 'a') as csvfile:
writer = csv.writer(csvfile, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
for name in hkwords:
writer.writerow([name]+hkwords[name])
def get_authors(rg_paper_id):
"""Get authors for paper with rg_paper_id"""
logger.debug("Get authors for paper.")
ref_url = _AUTHORSLISTDATA.format(rg_paper_id, 0, 100)
url = _FULLURL.format(_HOST, ref_url)
try:
req_result = utils.get_json_data(url, _PROXY_OBJ.get_cur_proxy())
logger.debug("Parse host answer from json.")
dict_req_result = json.loads(req_result)
except BaseException:
logger.warn(traceback.format_exc())
return None
success = dict_req_result['success']
logger.debug("Status=%s." % success)
if success:
logger.debug("Data is correct and parse is successfuly.")
return dict_req_result['result']['loadedItems']
logger.debug("Data is not correct.")
return None
def get_auth_info(rg_account_id):
"""Get info about author with account_id"""
logger.debug("Downloading the auth info.")
ref_url = _AUTHORDATA.format(rg_account_id)
url = _FULLURL.format(_HOST, ref_url)
try:
req_result = utils.get_json_data(url, _PROXY_OBJ.get_cur_proxy())
logger.debug("Parse host answer from json.")
dict_req_result = json.loads(req_result)
except BaseException:
logger.warn(traceback.format_exc())
return None
success = dict_req_result['success']
logger.debug("Status=%s." % success)
if success:
logger.debug("Data is correct and parse is successfuly.")
return dict_req_result['result']['data']
logger.debug("Data is not correct.")
return None
def svm_train():
'''
Returns:
acc: 在测试集上的精度
'''
#参数及默认值
args = {
'train_x': None, 'train_y': None,
'C': 1.0, 'kernel': 'rbf', 'degree': 3, 'gamma': 'auto', 'coef0': 0.0,
'shrinking': True, 'probability': False, 'tol': 0.001, 'cache_size': 200,
'class_weight': None, 'verbose': False, 'max_iter': -1,
'decision_function_shape': 'ovr', 'random_state': None,
'test_size':0.1
}
#必须参数, 不要在arg中给必须参数赋默认值
acq = ['train_x', 'train_y']
#参数限制暂时不写
lim = []
#参数类型，注意，这里忽略了同时可以为str或者float的参数， 例如gamma
#对于list的参数，第一个元素表示本身，第二个表示第一维索引的元素类型，以此类推
types ={
'train_x': [list, list, float], 'train_y':[list, float],
'C': float, 'kernel': str, 'degree': int, 'coef0': float,
'shrinking': bool, 'probability': bool, 'tol': float, 'cache_size': int,
'class_weight': str, 'verbose': bool, 'max_iter': int, 'decision_function_shape': str, 'random_state': int,
'test_size': float
}
args = get_json_data(raw=request.get_data(as_text=True), args=args)
if args is None:
return json.dumps({'state': 'fail', 'msg': '未接收到任何json数据'}, ensure_ascii=False)
missed_arg = check_aquired_args(args, acq)
if missed_arg is not None:
return json.dumps({'state': 'fail', 'msg': '缺少必须参数'}, ensure_ascii=False)
args = type_format(args=args, types=types)
clf=get_svm(**args)
acc = train(clf, x=args['train_x'], y= args['train_y'], test_size=args['test_size'], max_iter= args['max_iter'])
return json.dumps({'state': 'done', 'acc': acc})
def get_referring_papers(rg_paper_id):
"""Get references dict for paper with rg_paper_id"""
logger.debug("Downloading the list of referring articles.")
ref_url = _PUBREFERENCESDATA.format(rg_paper_id)
url = _FULLURL.format(_HOST, ref_url)
try:
req_result = utils.get_json_data(url, _PROXY_OBJ.get_cur_proxy())
logger.debug("Parse host answer from json.")
dict_req_result = json.loads(req_result)
except BaseException:
logger.warn(traceback.format_exc())
return None
success = dict_req_result['success']
logger.debug("Status=%s." % success)
if success:
logger.debug("Data is correct and parse is successfuly.")
return dict_req_result['result']['state'][
'publicliteratureReferences']['itemEntities']
logger.debug("Data is not correct.")
return None
def __get_groupusage_values(self):
url = "https://cmsweb.cern.ch/phedex/datasvc/json/prod/groupusage"
groupusage_aux = get_json_data(url)
groupusage = {}
#Massage information to make it more accessible
for site_dic in groupusage_aux['phedex']['node']:
site = site_dic["name"]
groupusage[site]={}
for group_dic in site_dic['group']:
group = group_dic["name"]
try:
groupusage[site][group]={"dest_bytes": int(group_dic["dest_bytes"]),
"node_bytes": int(group_dic["node_bytes"])}
except:
self.__logger.error('Incomplete information for group %s in site %s in %s' %(group, site, url))
return groupusage
class TestHRMLogin(unittest.TestCase):
@classmethod
def setUpClass(cls) -> None:
cls.login_api = LoginApi()
@classmethod
def tearDownClass(cls) -> None:
...
def setUp(self) -> None:
...
def tearDown(self) -> None:
...
@parameterized.expand(utils.get_json_data())
def test01_login(self, mobile, pwd, http_code, success, code, message):
response = self.login_api.login(mobile, pwd)
json_data = response.json()
logging.info("登陆测试返回的数据为{}".format(json_data))
utils.assert_common(self, response, http_code, success, code, message)
def download_set(json_path: str, save_folder: str, log_path: str):
logging.basicConfig(filename=log_path, level=logging.ERROR)
images, _ = get_json_data(json_path)
reg = re.compile('image/(\w+)')
if not os.path.exists(save_folder):
os.makedirs(save_folder)
with concurrent.futures.ThreadPoolExecutor(max_workers=cpu_count() *
8) as executor:
futures = []
for data in images:
url_str = data['url'][0]
img_id = data['image_id']
futures.append(
executor.submit(
partial(download_image, url_str, save_folder, img_id,
reg)))
[future.result() for future in tqdm(futures)]
return
def __get_nodeusage_values(self):
url = "https://cmsweb.cern.ch/phedex/datasvc/json/prod/nodeusage"
nodeusage_aux = get_json_data(url)
nodeusage = {}
#Massage information to make it more accessible
for site_dic in nodeusage_aux['phedex']['node']:
site = site_dic["name"]
try:
nodeusage[site]={"src_node_bytes": int(site_dic["src_node_bytes"]),
"nonsrc_node_bytes": int(site_dic["nonsrc_node_bytes"]),
"noncust_dest_bytes": int(site_dic["noncust_dest_bytes"]),
"noncust_node_bytes": int(site_dic["noncust_node_bytes"]),
"cust_node_bytes": int(site_dic["cust_node_bytes"]),
"cust_dest_bytes": int(site_dic["cust_dest_bytes"])
}
except:
self.__logger.error('Incomplete information for site %s in %s' %(site, url))
return nodeusage
def get_info_from_RIS(rg_paper_id):
"""Get RIS file for paper with rg_paper_id"""
logger.debug(
"Downloading RIS data about paper. RGID={0}.".format(rg_paper_id))
data = utils.get_json_data(
_FULLURL.format(_HOST, _PUBRISDATA.format(rg_paper_id)),
_PROXY_OBJ.get_cur_proxy()).replace("\r", "")
logger.debug("RIS file:\n%s" % data)
logger.debug("Parse RIS data.")
res = None
try:
if data is None:
logger.debug("RIS data is empty.")
return res
datalines = data.split("\n")
RISgenerator = RISparser.read(datalines)
res = next(RISgenerator)
if "doi" in res and not utils.is_doi(res["doi"]):
res.pop("doi")
res["RIS"] = data
except BaseException:
logger.warn(traceback.format_exc())
return res
def __get_groupusage_values(self):
url = "https://cmsweb.cern.ch/phedex/datasvc/json/prod/groupusage"
groupusage_aux = get_json_data(url)
groupusage = {}
#Massage information to make it more accessible
for site_dic in groupusage_aux['phedex']['node']:
site = site_dic["name"]
groupusage[site] = {}
for group_dic in site_dic['group']:
group = group_dic["name"]
try:
groupusage[site][group] = {
"dest_bytes": int(group_dic["dest_bytes"]),
"node_bytes": int(group_dic["node_bytes"])
}
except:
self.__logger.error(
'Incomplete information for group %s in site %s in %s'
% (group, site, url))
return groupusage
def __get_nodeusage_values(self):
url = "https://cmsweb.cern.ch/phedex/datasvc/json/prod/nodeusage"
nodeusage_aux = get_json_data(url)
nodeusage = {}
#Massage information to make it more accessible
for site_dic in nodeusage_aux['phedex']['node']:
site = site_dic["name"]
try:
nodeusage[site] = {
"src_node_bytes": int(site_dic["src_node_bytes"]),
"nonsrc_node_bytes": int(site_dic["nonsrc_node_bytes"]),
"noncust_dest_bytes": int(site_dic["noncust_dest_bytes"]),
"noncust_node_bytes": int(site_dic["noncust_node_bytes"]),
"cust_node_bytes": int(site_dic["cust_node_bytes"]),
"cust_dest_bytes": int(site_dic["cust_dest_bytes"])
}
except:
self.__logger.error(
'Incomplete information for site %s in %s' % (site, url))
return nodeusage
serial_number_length = len(
str(int(first_serial_number) +
scratch_codes_count).zfill(first_serial_number_length))
scratch_codes = scratch.generate(serial_number_length, hash_type,
hash_length, scratch_codes_count)
write_json_data(scratch_codes, filename)
else:
print('Неправильное имя файла.')
if mode == '2':
filename = input(
'Введите имя файла, откуда будут взяты скретч-коды для проверки: ')
if os.path.isfile(filename):
scratch_codes = get_json_data(filename)
serial_number_length = len(
str(int(first_serial_number) +
len(scratch_codes)).zfill(first_serial_number_length))
scratch.create_activated_codes_table()
checked_codes, right_codes = scratch.check(scratch_codes,
serial_number_length,
hash_type, hash_length)
if right_codes:
scratch.add_new_codes(right_codes)
print(checked_codes)
else:
print('Неправильное имя файла.')
for i, (x, y, w, h) in enumerate(faces):
cv.putText(img, predictions[i], (x, y - 10), cv.FONT_HERSHEY_SIMPLEX,
0.5, (0, 255, 0), 2)
cv.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2)
cv.imwrite('img_with_boxes.jpg', img)
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--image_path",
help="path to image from GoT",
type=str)
parser.add_argument("-t",
"--test",
help="run test on 5 sample images",
type=bool,
default=False)
args = parser.parse_args()
tf.logging.set_verbosity(tf.logging.ERROR)
data = get_json_data('GoT_Face_Labelling_Ep7.json')
predict_fn = tf.contrib.predictor.from_saved_model(
"trained/trained_0/1531036933/")
if args.test:
run_test(predict_fn)
else:
run_predict_image(image_file=args.image_path, predict_fn=predict_fn)
def json_data():
return Response(get_json_data(), mimetype='application/json')
def get_binary_text_ROI(gray):
parameters = get_json_data()
threshold_width = float(parameters["threshold_width"]["value"])
threshold_height = float(parameters["threshold_height"]["value"])
mser = cv2.MSER_create()
mser.setMaxArea(800)
contours, bboxes = mser.detectRegions(gray)
(height, width) = gray.shape[:2]
coords = []
contours = sorted(contours, key=contour_rec_ara, reverse=True)
for c in contours:
bbox = cv2.boundingRect(c)
x, y, w, h = bbox
if x > width * threshold_width and y < height * threshold_height and float(
w / h) <= 1 and w < width / 15 and h < height / 15 and not_inside(bbox, coords):
coords.append(c)
canvas = np.zeros_like(gray)
for cnt in coords:
xx = cnt[:, 0]
yy = cnt[:, 1]
color = 255
canvas[yy, xx] = color
cv2.imshow("canvas1",canvas)
im2, contours, hierarchy = cv2.findContours(canvas.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contour_info_list = []
center_points = []
for cnt in contours:
x, y, w, h = cv2.boundingRect(cnt)
cnt = cv2.convexHull(cnt)
shape = detect(cnt)
if shape != "unidentified":
center_points.append([int(x + w / 2), int(y + h / 2)])
contour_dict = {}
contour_dict["rect"] = [x, y, w, h]
contour_dict["contour"] = cnt
contour_dict["shape"] = shape
contour_dict["center"] = [int(x + w / 2), int(y + h / 2)]
contour_info_list.append(contour_dict)
### Use RANSAC to find the line of center points
num_centers = find_region_RANSAC(center_points, "", 800)
### find the container no. position.Remove the forground not in num_centers.
if len(num_centers) == 0:
return canvas
index = num_centers.shape[0] - 1
for item in contour_info_list:
if not is_point_in(item["center"], num_centers):
rect = item["rect"]
canvas[rect[1]:rect[1] + rect[3], rect[0]:rect[0] + rect[2]] = 0
else:
if np.array_equal(item["center"], num_centers[index]) and item["shape"] == "square":
canvas = remove_rect(canvas, item["contour"])
##Get image patch
x_left = num_centers[0][0]
x_right = num_centers[num_centers.shape[0] - 1][0]
tmp_centers = num_centers[num_centers[:, 1].argsort()]
y_top = tmp_centers[0][1]
y_bottom = tmp_centers[tmp_centers.shape[0] - 1][1]
#print("num_centers:", x_left, x_right, y_top, y_bottom)
#print(tmp_centers)
canvas = canvas[y_top - 18:y_bottom+18, x_left-18:x_right+18]
return canvas
def json_data():
return Response(get_json_data(), mimetype='application/json')
x.execute(query)
query = """DELETE FROM tbl_Results WHERE weekID<>%d AND weekID<>%d""" % (
today_id, (today_id - 1))
x.execute(query)
query = """DELETE FROM tbl_Ratios WHERE weekID<>%d AND weekID<>%d""" % (
today_id, (today_id - 1))
x.execute(query)
DB_CONN.commit()
query = """SELECT matchID FROM tbl_MatchInfo WHERE weekID=%d AND was_played=False""" % (
today_id - 1)
results = x.execute(query)
matches_previous = {}
if results:
j = get_json_data(URL_MATCHES % (today_id - 1))
matches_previous = {
j['m'][i]['d']: j['m'][i]['m']
for i in range(len(j['m']))
}
query = """SELECT matchID FROM tbl_MatchInfo WHERE weekID=%d AND was_played=True""" % today_id
x.execute(query)
results = [row[0] for row in x.fetchall()]
j = get_json_data(URL_MATCHES % today_id)
matches_last = {j['m'][i]['d']: j['m'][i]['m'] for i in range(len(j['m']))}
all_matches = concat(matches_previous.values() + matches_last.values())
for md in concat(matches_previous.values()):
x = DB_CONN.cursor()
query = """DELETE FROM tbl_MatchInfo WHERE weekID<>%d AND weekID<>%d""" % (today_id, (today_id -1))
x.execute(query)
query = """DELETE FROM tbl_Results WHERE weekID<>%d AND weekID<>%d""" % (today_id, (today_id -1))
x.execute(query)
query = """DELETE FROM tbl_Ratios WHERE weekID<>%d AND weekID<>%d""" % (today_id, (today_id -1))
x.execute(query)
DB_CONN.commit()
query = """SELECT matchID FROM tbl_MatchInfo WHERE weekID=%d AND was_played=False""" % (today_id -1)
results = x.execute(query)
matches_previous = {}
if results:
j = get_json_data(URL_MATCHES % (today_id - 1))
matches_previous = {j['m'][i]['d']: j['m'][i]['m'] for i in range(len(j['m']))}
query = """SELECT matchID FROM tbl_MatchInfo WHERE weekID=%d AND was_played=True""" % today_id
x.execute(query)
results = [row[0] for row in x.fetchall()]
j = get_json_data(URL_MATCHES % today_id)
matches_last = {j['m'][i]['d']: j['m'][i]['m'] for i in range(len(j['m']))}
all_matches = concat(matches_previous.values() + matches_last.values())
for md in concat(matches_previous.values()):
match = Match(md, weekid=today_id - 1)
match.save_all()