def imagesAnnotate(file):
url = "https://vision.googleapis.com/v1/images:annotate?key=%s" % GOOGLE_API_KEY
payload = json.dumps({
"requests": [{
"image": {
"content": (base64.b64encode(file.read())).decode('UTF-8')
},
"features": [{
"type": "DOCUMENT_TEXT_DETECTION"
}],
"imageContext": {
"languageHints": ["en-t-i0-handwrit"]
}
}]
})
(status, response) = post(url, payload, verbose=False)
if status == requests.codes.ok:
if response["responses"][0] == {}:
return {"Text": "Unable to retrieve any information from the file"}
#return response["responses"][0]["textAnnotations"][0]["description"]
text = lsgapp.mergeNearByWords(response["responses"][0])
rcpt = receipt.Receipt(parser_config, text)
#print(rcpt.date)
return {
"Text": billText(rcpt),
"Company": rcpt.company,
"InvoiceDate": rcpt.date,
"InvoiceNo": rcpt.billno,
"InvoiceAmount": rcpt.sum
}
else:
return {"Text": "imageAnnotate error %s: %s" % (status, response)}
def read_in_receipt(file_name):
f = open(file_name, 'r')
reader = csv.reader(f)
groc_list = {}
for row in reader:
new_groc = groc.Groc(filter_name(row[0]), filter_mass(row[1]), (row[2]))
groc_list[new_groc.get_name()] = (new_groc.get_mass(), new_groc.get_price())
f.close()
new_receipt = receipt.Receipt(groc_list)
return new_receipt
def begin_session(self, user):
"""METHOD: The lifeblood of the ATM's functions.
>> begin_session(self, user)
PARAMETERS
@user: The card to begin the session.
RETURN
None.
"""
assert isinstance(user, card.Card)
try:
match = self.insert_card(user)
if not self.match_pin(match):
raise SystemExit(
"ERROR: Contact the administrator for assistance.\n")
except SystemExit:
raise
except:
match = None
if match is not None:
while True:
try:
choice = self.action_prompt()
print()
if choice == 1:
output = self.withdraw(match)
self._accounts.writeChanges("accounts.txt")
elif choice == 2:
output = self.deposit(match)
self._accounts.writeChanges("accounts.txt")
elif choice == 3:
output = receipt.Receipt(match, globals.ACTIONS[2],
None)
elif choice == 4:
pass # the user choose to quit
break
except ValueError as e:
if str(e) == "ERROR: Insufficient funds.\n":
print(str(e))
else:
raise
if choice != 4: print(output)
else:
sys.stderr.write("ERROR: Account not found.\n")
print("Thank you for choosing this ATM!")
def deposit(self, acct):
"""METHOD: The deposit function.
>> deposit(self, acct)
PARAMETERS
@acct: The account that has been matched.
RETURN
A Receipt object containing the ATM response.
"""
money = self.get_money(globals.ACTIONS[1])
acct.deposit(money)
return receipt.Receipt(acct, globals.ACTIONS[1], money)
def withdraw(self, acct):
"""METHOD: The withdrawal function.
>> withdraw(self, acct)
PARAMETERS
@acct: The account that has been matched.
RETURN
A Receipt object containing the ATM response.
"""
money = self.get_money(globals.ACTIONS[0])
acct.withdraw(money)
return receipt.Receipt(acct, globals.ACTIONS[0], money)
def get_salary_employee():
emp_id = input('Enter the employee ID: ')
first = input('Enter first name of the employee: ')
last = input('Enter last name of the employee: ')
salary = float(input('Enter the employees salary: '))
commission = float(input('Enter the employees commission rate(%): '))
dues = float(input('Enter the employees weekly dues: '))
employee_data = salariedemployee.SalariedEmployee(emp_id, first, last,
salary, commission, dues)
print('Enter the employees address.')
street = input('Street Address: ')
city = input('City: ')
state = input('State: ')
zipcode = input('Zip: ')
address_data = address.Address(street, city, state, zipcode)
print()
print('Enter the employee\'s sales data.')
date = input('Enter today\'s date (MM/DD/YY): ')
sales = float(input('Please enter the employee\'s sales: '))
receipt_data = receipt.Receipt(
date, sales) # setup for loop to calc sales receipts over month
print()
salary_pay = (
salary / YEAR_SALARY_HOURS
) * SALARY_HOURS # needs to be updated to account for 5 week months
commission_pay = receipt_data.get_sales() * commission / COMMISSION_CONVERT
deposit = salary_pay + commission_pay - employee_data.get_weekly_dues()
print('Enter your bank account information.')
bank = input('Enter your bank name: ')
routing = input('Enter the routing number: ')
account = input('Enter the account number: ')
bank_data = bankaccount.BankAccount(bank, routing, account)
print()
print(str(employee_data.get_full_name()))
print(str(address_data.get_address()))
print('Depositing your monthly paycheck...')
print('Depositing $', format(deposit, ',.2f'), 'in', str(bank_data.get_bank_name()), 'Account Number:', \
str(bank_data.get_account_id()), 'using Routing Number:', \
str(bank_data.get_routing_number()), sep=' ')
print()
def filesAnnotate(file):
url = "https://vision.googleapis.com/v1/files:annotate?key=%s" % GOOGLE_API_KEY
payload = json.dumps({
"requests": [{
"inputConfig": {
"content": (base64.b64encode(file.read())).decode('UTF-8'),
"mimeType": "application/pdf"
},
"features": [{
"type": "DOCUMENT_TEXT_DETECTION"
}],
"imageContext": {
"languageHints": ["en-t-i0-handwrit"]
}
}]
})
(status, response) = post(url, payload, verbose=False)
if status == requests.codes.ok:
if response["responses"][0] == {}:
return {"Text": "Unable to retrieve any information from the file"}
text = ''
for page in response["responses"][0]["responses"]:
text += page["fullTextAnnotation"]["text"] + "\n"
#return text
rcpt = receipt.Receipt(parser_config, text)
#print(rcpt.date)
return {
"Text": text,
"Company": rcpt.company,
"InvoiceDate": rcpt.date,
"InvoiceNo": rcpt.billno,
"InvoiceAmount": rcpt.sum
}
else:
return {"Text": "filesAnnotate error %s: %s" % (status, response)}
def save(self):
for i in range(0, self.personnum):
if not self.personname[0].get():
tkinter.messagebox.showinfo("이름 입력", "모든 사람의 이름을 입력해주세요.")
break
if not self.personmenu[i].get():
tkinter.messagebox.showinfo(
"개인메뉴 가격 입력", "모든 개인메뉴 가격을 입력해주세요."
"\n개임메뉴가격이 없는 경우 0을 입력해주세요")
break
if not self.groupmenu.get():
tkinter.messagebox.showinfo(
"그룹메뉴 가격 입력", "그룹메뉴 가격을 입력해주세요."
"\n그룹메뉴가격이 없는 경우 0을 입력해주세요")
break
else:
self.ID = random.randint(1, 1000)
self.now = datetime.datetime.utcnow()
sqlCon = pymysql.connect(host="127.0.0.1",
user="******",
password="******",
database="dutchdb",
charset="utf8")
cur = sqlCon.cursor(pymysql.cursors.DictCursor)
cur.execute(
"INSERT INTO dutchdb VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)",
(
self.ID,
self.now.strftime('%Y-%m-%d %H:%M:%S'),
self.personnum, # 명수
self.personname[1 - 1].get(), # 이름1
self.personname[2 - 1].get(), # 이름2
self.personname[3 - 1].get(), # 이름3
self.personname[4 - 1].get(), # 이름4
self.personname[5 - 1].get(), # 이름5
self.personname[6 - 1].get(), # 이름6
self.personmenu[1 - 1].get(), # 메뉴1
self.personmenu[2 - 1].get(), # 메뉴2
self.personmenu[3 - 1].get(), # 메뉴3
self.personmenu[4 - 1].get(), # 메뉴4
self.personmenu[5 - 1].get(), # 메뉴5
self.personmenu[6 - 1].get(), # 메뉴6
self.groupmenu.get(),
self.inputLocation.get(), # 장소
self.inputMenu.get(), # 그룹메뉴가격
self.RadioVariety_1.get()))
sqlCon.commit()
sqlCon.close()
inputm = [
self.inputLocation.get(),
self.inputMenu.get(),
[
self.personname[1 - 1].get(),
self.personmenu[1 - 1].get()
],
[
self.personname[2 - 1].get(),
self.personmenu[2 - 1].get()
],
[
self.personname[3 - 1].get(),
self.personmenu[3 - 1].get()
],
[
self.personname[4 - 1].get(),
self.personmenu[4 - 1].get()
],
[
self.personname[5 - 1].get(),
self.personmenu[5 - 1].get()
],
[
self.personname[6 - 1].get(),
self.personmenu[6 - 1].get()
],
self.groupmenu.get(),
self.RadioVariety_1.get()
]
Move = receipt.Receipt(self.menu, inputm, self.personnum,
self.ID)
break
def receipt(self,
prefix,
receiptId,
dateTime,
sumA,
sumB,
sumC,
sumD,
sumE,
sigSystem,
dummy=False,
reversal=False,
override=dict()):
algorithm = algorithms.ALGORITHMS[prefix]
dateTimeStr = dateTime.strftime("%Y-%m-%dT%H:%M:%S")
# replacing '.' with ',' because reference does it too, still weird
sumAStr = ("%.2f" % sumA).replace('.', ',')
sumBStr = ("%.2f" % sumB).replace('.', ',')
sumCStr = ("%.2f" % sumC).replace('.', ',')
sumDStr = ("%.2f" % sumD).replace('.', ',')
sumEStr = ("%.2f" % sumE).replace('.', ',')
regularRec = receipt.Receipt(sigSystem.zda, self.registerId, receiptId,
dateTimeStr, sumAStr, sumBStr, sumCStr,
sumDStr, sumEStr, '', sigSystem.serial,
'')
rec = MangledReceipt(regularRec, override)
if 'turnoverCounterSize' in override:
self.turnoverCounterSize = override['turnoverCounterSize']
encTurnoverCounter = None
if dummy:
encTurnoverCounter = b'TRA'
if 'turnoverCounter' in override:
self.turnoverCounter = int(override['turnoverCounter'])
else:
# TODO: check if counter can still be represented with
# given size
self.turnoverCounter += int(
round((sumA + sumB + sumC + sumD + sumE) * 100))
if 'turnoverCounter' in override:
self.turnoverCounter = int(override['turnoverCounter'])
if reversal:
encTurnoverCounter = b'STO'
else:
if not algorithm.verifyKey(self.key):
raise Exception(_("Invalid key."))
encTurnoverCounter = algorithm.encryptTurnoverCounter(
rec, self.turnoverCounter, self.key,
self.turnoverCounterSize)
encTurnoverCounter = base64.b64encode(encTurnoverCounter)
encTurnoverCounter = encTurnoverCounter.decode("utf-8")
if 'encTurnoverCounter' not in override:
rec.encTurnoverCounter = encTurnoverCounter
previousChain = algorithm.chain(rec, self.lastReceiptSig)
if 'previousChain' not in override:
rec.previousChain = base64.b64encode(previousChain).decode("utf-8")
prefix = override.get('algorithmPrefix', prefix)
jwsString = sigSystem.sign(rec.toPayloadString(prefix), algorithm)
self.lastReceiptSig = jwsString
header, payload, signature = jwsString.split('.')
header = base64.urlsafe_b64decode(
utils.restoreb64padding(header).encode('utf-8')).decode('utf-8')
rec.sign(header, signature)
if 'header' in override:
rec.header = override['header']
if 'signature' in override:
rec.signature = override['signature']
return rec
def main(args):
fileNames = os.listdir(trainTextDir)
fileNames = [i for i in fileNames if (i.endswith('.json'))]
for fileName in fileNames:
with open(os.path.join(trainTextDir, fileName)) as text_json:
text_data = json.load(text_json)
text_data = tx.filterGarbage(text_data)
tx.calculateAngles(text_data)
tx.calculateCenterPoints(text_data)
text_lines = tx.createLines(text_data)
with open(
os.path.join(trainLabelsDir,
fileName.split('_')[0] +
'_labels.json')) as ground_truth_json:
truth = json.load(ground_truth_json)
truth = tx.removeSwedishLetters(truth)
receipt = rc.Receipt(fileName, text_lines, truth)
receipts.append(receipt)
f = open('./data/test/test.txt', "r")
for line in f:
testFilePaths.append(line[:-1])
test_reciepts = []
for receipt in receipts:
if receipt.path in testFilePaths:
test_reciepts.append(receipt)
if args[1] == 'plot_bert':
d1 = pd.DataFrame(
{
'train synthetic 10000': plot.train_10000_v2,
'validation synthetic 10000': plot.val_10000_v2
},
index=range(1, 31))
d2 = pd.DataFrame(
{
'train synthetic 1000': plot.train_1000,
'validation synthetic 1000': plot.val_1000
},
index=range(1, 31))
d3 = pd.DataFrame(
{
'train real data': plot.train,
'validation real data': plot.val
},
index=range(1, 31))
data = pd.concat([d1, d2, d3], axis=1)
sns.set_style("darkgrid")
ax = sns.lineplot(data=data)
ax.set(xlabel='epoch', ylabel='loss')
plt.show()
if args[1] == 'plot_lstm':
f1 = open('/Users/markolazic/Desktop/sroie-task3/data/trainLoss.txt',
'r')
f2 = open('/Users/markolazic/Desktop/sroie-task3/data/valLoss.txt',
'r')
f3 = open(
'/Users/markolazic/Desktop/sroie-task3/data/trainLoss1000.txt',
'r')
f4 = open('/Users/markolazic/Desktop/sroie-task3/data/valLoss1000.txt',
'r')
f5 = open(
'/Users/markolazic/Desktop/sroie-task3/data/trainLoss10000.txt',
'r')
f6 = open(
'/Users/markolazic/Desktop/sroie-task3/data/valLoss10000.txt', 'r')
f1Lines = f1.readlines()
f2Lines = f2.readlines()
f3Lines = f3.readlines()
f4Lines = f4.readlines()
f5Lines = f5.readlines()
f6Lines = f6.readlines()
train_loss = []
for line in f1Lines:
train_loss.append(float(line[:-1]))
val_loss = []
for line in f2Lines:
val_loss.append(float(line[:-1]))
train_loss1000 = []
for line in f3Lines:
train_loss1000.append(float(line[:-1]))
val_loss1000 = []
for line in f4Lines:
val_loss1000.append(float(line[:-1]))
train_loss10000 = []
for line in f5Lines:
train_loss10000.append(float(line[:-1]))
val_loss10000 = []
for line in f6Lines:
val_loss10000.append(float(line[:-1]))
d1 = pd.DataFrame(
{
'train synthetic 10000': train_loss10000,
'validation synthetic 10000': val_loss10000
},
index=range(1, 2001))
d2 = pd.DataFrame(
{
'train synthetic 1000': train_loss1000,
'validation synthetic 1000': val_loss1000
},
index=range(1, 2001))
d3 = pd.DataFrame(
{
'train real data': train_loss,
'validation real data': val_loss
},
index=range(1, 2001))
data = pd.concat([d1, d2, d3], axis=1)
data = data.rolling(100).mean()
sns.set_style("darkgrid")
ax = sns.lineplot(data=data)
ax.set(xlabel='epoch', ylabel='loss')
plt.show()
if args[1] == 'create_data_statistics':
stats = util.create_data_statistics(receipts, 'vendor')
for k, v in sorted(stats.items(),
reverse=True,
key=lambda item: item[1]):
print(k, '---', v)
if args[1] == 'generate_gcn_data':
test_data_dict = {}
train_data_dict = {}
for i, receipt in enumerate(receipts):
if receipt.path in testFilePaths:
test_data_dict[i] = data_gen.generateWordClasses(receipt)
else:
train_data_dict[i] = data_gen.generateWordClasses(
receipt, correcting=False)
gcn.create(receipts, testFilePaths)
if args[1] == 'create_result':
path = './data/results/10000_synt'
test_dict_path = os.path.join(path, 'res_dict.pth')
res_dict = torch.load(test_dict_path)
result = list(res_dict.items())
res_list = []
for i, (_, (labels, words)) in enumerate(result):
res = extract(labels, words)
res_list.append(res)
calculateMetrics(test_reciepts, res_list, writeToFile=True, path=path)
if args[1] == 'generate_word_data':
generateSynthetic = False
if args[2] and util.isInt(args[2]):
generateSynthetic = True
number = int(args[2])
train_data_dict = {}
test_data_dict = {}
for i, receipt in enumerate(receipts):
if receipt.path in testFilePaths:
test_data_dict[i] = data_gen.generateWordClasses(receipt)
else:
train_data_dict[i] = data_gen.generateWordClasses(
receipt, correcting=False)
train_receipts = []
for r in receipts:
if r.path not in testFilePaths:
train_receipts.append(r)
if generateSynthetic:
synthetic = generateSintheticData(train_receipts, number)
for i, (words, labels) in enumerate(synthetic):
train_data_dict[i + len(receipts)] = (words, labels)
'''
vocab = data_gen.createVocabulary(receipts + synthetic)
f=open('./data/synt_vocab.txt',"w+")
for w in vocab:
f.write(w + '\n')
f.write('[UNK]' + '\n')
f.write('[CLS]' + '\n')
f.write('[SEP]' + '\n')
f.write('[MASK]' + '\n')
f.close()
'''
torch.save(train_data_dict, "./data/synt_10000_train_data_dict.pth")
torch.save(test_data_dict, "./data/synt_test_data_dict.pth")
if args[1] == 'oracle':
for i, receipt in enumerate(test_reciepts):
_ = data_gen.generateWordClasses(receipt)
oracle(test_reciepts)
if args[1] == 'rule_based':
for receipt in test_reciepts:
predict(receipt)
calculateRuleBasedAccuracy(test_reciepts)
if args[1] == 'create_lstm_result':
result_jsons = os.listdir(lstmResultDir)
result_jsons = [i for i in result_jsons if (i.endswith('.json'))]
result_jsons.sort(key=lambda r: int(r.split('.')[0]))
results_dicts = []
for fileName in result_jsons:
with open(os.path.join(lstmResultDir, fileName)) as text_json:
text_data = json.load(text_json)
results_dicts += [text_data]
calculateLSTMaccuracy(test_reciepts, results_dicts)
elif args[1] == 'create_char_data':
generateSynthetic = True
number = 10000
train_data_dict = {}
test_data_dict = {}
for i, receipt in enumerate(receipts):
if receipt.path in testFilePaths:
test_data_dict[i] = data_gen.generateCharClasses(
receipt, includeProducts=True)
else:
train_data_dict[i] = data_gen.generateCharClasses(
receipt, includeProducts=True)
if generateSynthetic:
VOCAB = ascii_uppercase + digits + punctuation + " \t\n"
for r in receipts:
data_gen.generateWordClasses(r)
synthetic = generateSintheticData(receipts, number)
for i, (words, labels) in enumerate(synthetic):
t_new_words = ''
t_new_labels = []
for w, l in zip(words, labels):
t_new_words += w.upper() + ' '
t_new_labels += [
util.getClassInt(l) for i in range(len(w))
] + [0]
new_words = ''
new_labels = []
for index in range(len(t_new_words)):
if t_new_words[index] in VOCAB:
new_words += t_new_words[index]
new_labels.append(t_new_labels[index])
new_words = new_words[0:-1]
new_labels = new_labels[0:-1]
for i in range(1, len(new_words) - 1):
if new_labels[i] == 0 and new_labels[i -
1] == new_labels[i +
1]:
new_labels[i] = new_labels[i - 1]
train_data_dict[len(receipts) + i] = (new_words, new_labels)
print(train_data_dict)
torch.save(
train_data_dict,
"/Users/markolazic/Desktop/sroie-task3/data/train_char_data_prod_synt10000.pth"
)
torch.save(
test_data_dict,
"/Users/markolazic/Desktop/sroie-task3/data/test_char_data_prod_synt10000.pth"
)
def to_receipt(self):
Move = receipt.Receipt(self.menu)
#coding=utf-8
import receipt
if __name__ == '__main__':
DATA = {
"merchid": 1484901323,
"devid": "123",
"amount": 1,
"authcode": "286579303676489102",
"orderinfo": "111"
}
APPID = "12345"
APPKEY = '12345'
GATEWAYURL = "http://api.test.shuwang.info/receipt/rest"
receiptpay = receipt.Receipt(GATEWAYURL, APPID, APPKEY)
response = receiptpay.scan_authcode(DATA)
