In my bank system I have a set of customer accounts but for one name Adam Smith he has two accounts:
def load_bank_data(self):
# the customers in the bank system
account_no = 1234
customer_1 = CustomerAccount("Adam", "Smith", 14, "Wilcot Street", "Bath", "B5 5RT", account_no, "Current", 2500.00)
self.accounts_list.append(customer_1)
account_no += 5678
customer_2 = CustomerAccount("David", "White", 60, "Holburn Viaduct", "London", "EC1A 2FD", account_no, "Savings", 3200.00)
self.accounts_list.append(customer_2)
account_no += 3456
customer_3 = CustomerAccount("Alice", "Churchil", 55, "Cardigan Street", "Birmingham", "B4 7BD", account_no, "Current", 18000.00)
self.accounts_list.append(customer_3)
account_no += 6789
customer_4 = CustomerAccount("Ali", "Abdallah", 44, "Churchill Way West", "Basingstoke", "RG21 6YR", account_no, "Savings", 40.00)
self.accounts_list.append(customer_4)
account_no += 1987
customer_5 = CustomerAccount("Adam", "Smith", 44, "Churchill Way West", "Basingstoke", "RG21 6YR", account_no, "Savings", 5000.00)
self.accounts_list.append(customer_5)
I created a function so when many customer accounts under the same first and last name have been found, it should add all those bank account balances together and print out the final total. (The input is where I type the customer to find multiple accounts for:
def sum_of_all_money(self):
try:
find_customer = input("Enter the surname of the customer to find total sum of money for: ")
for find_customer in self.accounts_list:
find_customer = find_customer.get_balance() + find_customer.get_balance()
print(find_customer)
except SyntaxError as e:
print(e)
This is only just finding one Adam Smith account at the bottom as customer 5 but it doesn't detect the other Adam Smith account as customer 1 and it just adds customer 5 twice giving me an output of 1000.00 which isn't right, what am I doing wrong?
Your code has some flaws, currently it will only loop over your list and always overwrite find_customer with the current balance of the customer * 2.
You need to filter for the right name which was input, try it like this:
try:
find_customer = input("Enter the surname of the customer to find total sum of money for: ")
find_customer_balance = 0
for customer in self.accounts_list:
if customer.get_surname() == find_customer:
find_customer_balance += customer.get_balance()
print(find_customer)
print(find_customer_balance)
except SyntaxError as e:
print(e)
Related
I am trying to extract the Name, License No., Date Of Issue and Validity from an Image I processed using Pytesseract. I am quite a lot confused with regex but still went through few documentations and codes over the web.
I got till here:
import pytesseract
import cv2
import re
import cv2
from PIL import Image
import numpy as np
import datetime
from dateutil.relativedelta import relativedelta
def driver_license(filename):
"""
This function will handle the core OCR processing of images.
"""
i = cv2.imread(filename)
newdata=pytesseract.image_to_osd(i)
angle = re.search('(?<=Rotate: )\d+', newdata).group(0)
angle = int(angle)
i = Image.open(filename)
if angle != 0:
#with Image.open("ro2.jpg") as i:
rot_angle = 360 - angle
i = i.rotate(rot_angle, expand="True")
i.save(filename)
i = cv2.imread(filename)
# Convert to gray
i = cv2.cvtColor(i, cv2.COLOR_BGR2GRAY)
# Apply dilation and erosion to remove some noise
kernel = np.ones((1, 1), np.uint8)
i = cv2.dilate(i, kernel, iterations=1)
i = cv2.erode(i, kernel, iterations=1)
txt = pytesseract.image_to_string(i)
print(txt)
text = []
data = {
'firstName': None,
'lastName': None,
'age': None,
'documentNumber': None
}
c = 0
print(txt)
#Splitting lines
lines = txt.split('\n')
for lin in lines:
c = c + 1
s = lin.strip()
s = s.replace('\n','')
if s:
s = s.rstrip()
s = s.lstrip()
text.append(s)
try:
if re.match(r".*Name|.*name|.*NAME", s):
name = re.sub('[^a-zA-Z]+', ' ', s)
name = name.replace('Name', '')
name = name.replace('name', '')
name = name.replace('NAME', '')
name = name.replace(':', '')
name = name.rstrip()
name = name.lstrip()
nmlt = name.split(" ")
data['firstName'] = " ".join(nmlt[:len(nmlt)-1])
data['lastName'] = nmlt[-1]
if re.search(r"[a-zA-Z][a-zA-Z]-\d{13}", s):
data['documentNumber'] = re.search(r'[a-zA-Z][a-zA-Z]-\d{13}', s)
data['documentNumber'] = data['documentNumber'].group().replace('-', '')
if not data['firstName']:
name = lines[c]
name = re.sub('[^a-zA-Z]+', ' ', name)
name = name.rstrip()
name = name.lstrip()
nmlt = name.split(" ")
data['firstName'] = " ".join(nmlt[:len(nmlt)-1])
data['lastName'] = nmlt[-1]
if re.search(r"[a-zA-Z][a-zA-Z]\d{2} \d{11}", s):
data['documentNumber'] = re.search(r'[a-zA-Z][a-zA-Z]\d{2} \d{11}', s)
data['documentNumber'] = data['documentNumber'].group().replace(' ', '')
if not data['firstName']:
name = lines[c]
name = re.sub('[^a-zA-Z]+', ' ', name)
name = name.rstrip()
name = name.lstrip()
nmlt = name.split(" ")
data['firstName'] = " ".join(nmlt[:len(nmlt)-1])
data['lastName'] = nmlt[-1]
if re.match(r".*DOB|.*dob|.*Dob", s):
yob = re.sub('[^0-9]+', ' ', s)
yob = re.search(r'\d\d\d\d', yob)
data['age'] = datetime.datetime.now().year - int(yob.group())
except:
pass
print(data)
I need to extract the Validity and Issue Date as well. But not getting anywhere near it. Also, I have seen using regex shortens the code like a lot so is there any better optimal way for it?
My input data is a string somewhat like this:
Transport Department Government of NCT of Delhi
Licence to Drive Vehicles Throughout India
Licence No. : DL-0820100052000 (P) R
N : PARMINDER PAL SINGH GILL
: SHRI DARSHAN SINGH GILL
DOB: 10/05/1966 BG: U
Address :
104 SHARDA APPTT WEST ENCLAVE
PITAMPURA DELHI 110034
Auth to Drive Date of Issue
M.CYL. 24/02/2010
LMV-NT 24/02/2010
(Holder's Sig natu re)
Issue Date : 20/05/2016
Validity(NT) : 19/05/2021 : c
Validity(T) : NA Issuing Authority
InvCarrNo : NA NWZ-I, WAZIRPUR
Or like this:
in
Transport Department Government of NCT of Delhi
Licence to Drive Vehicles Throughout India
2
Licence No. : DL-0320170595326 () WN
Name : AZAZ AHAMADSIDDIQUIE
s/w/D : SALAHUDDIN ALI
____... DOB: 26/12/1992 BG: O+
\ \ Address:
—.~J ~—; ROO NO-25 AMK BOYS HOSTEL, J.
— NAGAR, DELHI 110025
Auth to Drive Date of Issue
M.CYL. 12/12/2017
4 wt 4
Iseue Date: 12/12/2017 a
falidity(NT) < 2037
Validity(T) +: NA /
Inv CarrNo : NA te sntian sana
Note: In the second example you wouldn't get the validity, will optimise the OCR for later. Any proper guide which can help me with regex which is a bit simpler would be good.
You can use this pattern: (?<=KEY\s*:\s*)\b[^\n]+ and replace KEY with one of the issues of the date, License No. and others.
Also for this pattern, you need to use regex library.
Code:
import regex
text1 = """
Transport Department Government of NCT of Delhi
Licence to Drive Vehicles Throughout India
Licence No. : DL-0820100052000 (P) R
N : PARMINDER PAL SINGH GILL
: SHRI DARSHAN SINGH GILL
DOB: 10/05/1966 BG: U
Address :
104 SHARDA APPTT WEST ENCLAVE
PITAMPURA DELHI 110034
Auth to Drive Date of Issue
M.CYL. 24/02/2010
LMV-NT 24/02/2010
(Holder's Sig natu re)
Issue Date : 20/05/2016
Validity(NT) : 19/05/2021 : c
Validity(T) : NA Issuing Authority
InvCarrNo : NA NWZ-I, WAZIRPUR
"""
for key in ('Issue Date', 'Licence No\.', 'N', 'Validity\(NT\)'):
print(regex.findall(fr"(?<={key}\s*:\s*)\b[^\n]+", text1, regex.IGNORECASE))
Output:
['20/05/2016']
['DL-0820100052000 (P) R']
['PARMINDER PAL SINGH GILL']
['19/05/2021 : c']
You can also use re with a single regex based on alternation that will capture your keys and values:
import re
text = "Transport Department Government of NCT of Delhi\nLicence to Drive Vehicles Throughout India\n\nLicence No. : DL-0820100052000 (P) R\nN : PARMINDER PAL SINGH GILL\n\n: SHRI DARSHAN SINGH GILL\n\nDOB: 10/05/1966 BG: U\nAddress :\n\n104 SHARDA APPTT WEST ENCLAVE\nPITAMPURA DELHI 110034\n\n\n\nAuth to Drive Date of Issue\nM.CYL. 24/02/2010\nLMV-NT 24/02/2010\n\n(Holder's Sig natu re)\n\nIssue Date : 20/05/2016\nValidity(NT) : 19/05/2021 : c\nValidity(T) : NA Issuing Authority\nInvCarrNo : NA NWZ-I, WAZIRPUR"
search_phrases = ['Issue Date', 'Licence No.', 'N', 'Validity(NT)']
reg = r"\b({})\s*:\W*(.+)".format( "|".join(sorted(map(re.escape, search_phrases), key=len, reverse=True)) )
print(re.findall(reg, text, re.IGNORECASE))
Output of this short online Python demo:
[('Licence No.', 'DL-0820100052000 (P) R'), ('N', 'PARMINDER PAL SINGH GILL'), ('Issue Date', '20/05/2016'), ('Validity(NT)', '19/05/2021 : c')]
The regex is
\b(Validity\(NT\)|Licence\ No\.|Issue\ Date|N)\s*:\W*(.+)
See its online demo.
Details:
map(re.escape, search_phrases) - escapes all special chars in your search phrases to be used as literal texts in a regex (else, . will match any chars, ? won't match a ? char, etc.)
sorted(..., key=len, reverse=True) - sorts the search phrases by length in descending order (to get longer matches first)
"|".join(...) - creates an alternation pattern, a|b|c|...
r"\b({})\s*:\W*(.+)".format( ... ) - creates the final regex.
Regex details
\b - a word boundary (NOTE: replace with (?m)^ if your matches occur at the beginning of a line)
(Validity\(NT\)|Licence\ No\.|Issue\ Date|N) - Group 1: one of the search phrases
\s* - zero or more whitespaces
: - a colon
\W* - zero or more non-word chars
(.+) - (capturing) Group 2: one or more chars other than line break chars, as many as possible.
I have a pandas dataframe having data in each row like below
Joel Thompson / Tracy K. Smith</h2>
</div>
<div>
<p>New work (World Premiere–New York Philharmonic Commission)
How would I filter this so I can get results to work with like this:
name : Joel Thompson, Tracy K. Smith
information : New work (World Premiere–New York Philharmonic Commission)
You should try to use the split function for string variables. You can do this this way :
#Get your row in a string variable text
text = "Joel Thompson / Tracy K. Smith</h2></div><div><p>New work (World Premiere–New York Philharmonic Commission)"
#Extracting the name
Names_string = text.split("</h2>")[0]
Names_list = Names_string.split(" / ")
#Extracting information
Information = text.split("<p>")[-1]
result = {
"name" : Names_list,
'information' : Information
}
print(result)
It will display this :
{'name': ['Joel Thompson', 'Tracy K. Smith'], 'information': 'New work (World Premiere–New York Philharmonic Commission)'}
You should make it a function this way :
def getDictFromRow(text):
#Extracting the name
Names_string = text.split("</h2>")[0]
Names_list = Names_string.split(" / ")
#Extracting information
Information = text.split("<p>")[-1]
result = {
"name" : Names_list,
'information' : Information
}
return result
print(getDictFromRow("Joel Thompson / Tracy K. Smith</h2></div><div><p>New work (World Premiere–New York Philharmonic Commission)"))
I want to receive payment in euro but receiving in usd.
I made a website for France country, we need to accept money in euro currency but getting in usd by Stripe using django
Here is the code for stripe
if request.method == "POST":
payment_type = request.POST["payment_type"]
amount_dues = request.POST["amount_dues"]
amount1 = request.POST["amount"]
amount2 = amount1.split("€")
amount = float(amount2[0])
email1 = request.POST["email"]
paid_amount = amount
customer = stripe.Customer.create(
email=request.POST["email"],
name=request.POST["nickname"],
source=request.POST["stripeToken"],
address={
"city": "kfhdksh",
"country": "France",
"line1": "566d ihflks",
"postal_code": "77140",
"state": "lfjkshkjsk",
},
)
int_amount = amount * 100
int_amount = int(int_amount)
charge = stripe.Charge.create(
customer=customer,
amount=int_amount,
currency="eur",
description="charges for ride of Customer Id = "
+ str(myid),
)
return redirect(reverse("success", args=[amount]))
Please help in getting currency in euro
What can I change in code or in stripe setting
`list1 = ["Arizona","Atlanta","Baltimore","Buffalo","Carolina","Chicago",
"Cincinnati","Cleveland","Dallas","Denver","Detroit","Green Bay","Houston",
"Indianapolis","Jacksonville","Kansas City","L.A. Chargers","L.A. Rams",
"Miami","Minnesota","New England","New Orleans","NY Giants","NY Jets",
"Oakland","Philadelphia","Pittsburgh","San Francisco","Seattle",
"Tampa Bay","Tennessee","Washington"]
a = "New Orleans at Oakland"
k = a.find("at")
print (k)
for n in range(0,31):
# b = list1[n]
# print(b[0:k-1]+" "+a[0:k-1])
idx = a.find(list1[n], 0, k-1)
if idx > 0:
print(n)
break
print ("awa team at index" + str(n+1))
for n in range(0,31):
idx = a.find(list1[n], k+2, len(a))
if idx > 0:
print(n)
break
print ("hom team at index" + str(n+1))`
I just started python 2 days ago and I cannot get this to work completely. The program finds the team in the second for loop correctly, but doesn't find the team in the first for loop. I put in the statements that are commented out to see if the strings were somehow truncated, but they are correct. Can anyone tell me what is wrong here?
There's no need to brute force the search. Python has methods that accomplish what you need.
list1 = ["Arizona", "Atlanta", "Baltimore", "Buffalo", "Carolina", "Chicago",
"Cincinnati", "Cleveland", "Dallas", "Denver", "Detroit", "Green Bay", "Houston",
"Indianapolis", "Jacksonville", "Kansas City", "L.A. Chargers", "L.A. Rams",
"Miami", "Minnesota", "New England", "New Orleans", "NY Giants", "NY Jets",
"Oakland", "Philadelphia", "Pittsburgh", "San Francisco", "Seattle",
"Tampa Bay", "Tennessee", "Washington"]
a = "New Orleans at Oakland"
# Create a list of the teams involved in the game
teams = a.split(" at ")
# Iterate through the teams involved in the game
for team in teams:
# The index() method returns the lowest index in list that obj appears
index = list1.index(team)
# If the the team was found then index is valid
if index:
print(index)
print(list1[index])
if you just want to have the index, you can use the .index() you do not have to "loop"
Example code:
list1 = ["Arizona","Atlanta","Baltimore","Buffalo","Carolina","Chicago",
"Cincinnati","Cleveland","Dallas","Denver","Detroit","Green Bay","Houston",
"Indianapolis","Jacksonville","Kansas City","L.A. Chargers","L.A. Rams",
"Miami","Minnesota","New England","New Orleans","NY Giants","NY Jets",
"Oakland","Philadelphia","Pittsburgh","San Francisco","Seattle",
"Tampa Bay","Tennessee","Washington"]
a = "New Orleans at Oakland"
a = a.split(' at ')
idx_home_team = list1.index(a[0])
idx_away_team = list1.index(a[1])
print(idx_home_team, idx_away_team)
I have a simple data entry form that writes the inputs to a csv file. Everything seems to be working ok, except that there are extra columns being added to the file in the process somewhere, seems to be during the user input phase. Here is the code:
import pandas as pd
#adds all spreadsheets into one list
Batteries= ["MAT0001.csv","MAT0002.csv", "MAT0003.csv", "MAT0004.csv",
"MAT0005.csv", "MAT0006.csv", "MAT0007.csv", "MAT0008.csv"]
#User selects battery to log
choice = (int(input("Which battery? (1-8):")))
def choosebattery(c):
done = False
while not done:
if(c in range(1,9)):
return Batteries[c]
done = True
else:
print('Sorry, selection must be between 1-8')
cfile = choosebattery(choice)
cbat = pd.read_csv(cfile)
#Collect Cycle input
print ("Enter Current Cycle")
response = None
while response not in {"Y", "N", "y", "n"}:
response = input("Please enter Y or N: ")
cy = response
#Charger input
print ("Enter Current Charger")
response = None
while response not in {"SC-G", "QS", "Bosca", "off", "other"}:
response = input("Please enter one: 'SC-G', 'QS', 'Bosca', 'off', 'other'")
if response == "other":
explain = input("Please explain")
ch = response + ":" + explain
else:
ch = response
#Location
print ("Enter Current Location")
response = None
while response not in {"Rack 1", "Rack 2", "Rack 3", "Rack 4", "EV001", "EV002", "EV003", "EV004", "Floor", "other"}:
response = input("Please enter one: 'Rack 1 - 4', 'EV001 - 004', 'Floor' or 'other'")
if response == "other":
explain = input("Please explain")
lo = response + ":" + explain
else:
lo = response
#Voltage
done = False
while not done:
choice = (float(input("Enter Current Voltage:")))
modchoice = choice * 10
if(modchoice in range(500,700)):
vo = choice
done = True
else:
print('Sorry, selection must be between 50 and 70')
#add inputs to current battery dataframe
log = pd.DataFrame([[cy,ch,lo,vo]],columns=["Cycle", "Charger", "Location", "Voltage"])
clog = pd.concat([cbat,log], axis=0)
clog.to_csv(cfile, index = False)
pd.read_csv(cfile)
And I receive:
Out[18]:
Charger Cycle Location Unnamed: 0 Voltage
0 off n Floor NaN 50.0
Where is the "Unnamed" column coming from?
There's an 'unnamed' column coming from your csv. The reason most likely is that the lines in your input csv files end with a comma (i.e. your separator), so pandas interprets that as an additional (nameless) column. If that's the case, check whether your lines end with your separator. For example, if your files are separated by commas:
Column1,Column2,Column3,
val_11, val12, val12,
...
Into:
Column1,Column2,Column3
val_11, val12, val12
...
Alternatively, try specifying the index column explicitly as in this answer. I believe some of the confusion stems from pandas concat reordering your columns .