└── Main


/Main:
--------------------------------------------------------------------------------
 1 | import pytesseract
 2 | import pandas as pd
 3 | import matplotlib.pyplot as plt
 4 | from PIL import Image
 5 | 
 6 | def extract_amount(text):
 7 |     words = text.split()
 8 |     for word in words:
 9 |         if word.replace(".", "").isdigit():
10 |             return float(word)
11 |     return 0
12 | 
13 | def analyze_expenses(receipts):
14 |     categories = {"Food": 0, "Transport": 0, "Shopping": 0, "Other": 0}
15 |     
16 |     for receipt in receipts:
17 |         text = pytesseract.image_to_string(Image.open(receipt)).lower()
18 |         amount = extract_amount(text)
19 |         
20 |         if "food" in text or "restaurant" in text:
21 |             categories["Food"] += amount
22 |         elif "uber" in text or "bus" in text:
23 |             categories["Transport"] += amount
24 |         elif "shop" in text or "store" in text:
25 |             categories["Shopping"] += amount
26 |         else:
27 |             categories["Other"] += amount
28 | 
29 |     return categories
30 | 
31 | def plot_expenses(categories):
32 |     plt.bar(categories.keys(), categories.values(), color=["blue", "green", "red", "purple"])
33 |     plt.xlabel("Categories")
34 |     plt.ylabel("Amount Spent")
35 |     plt.title("Expense Analysis")
36 |     plt.show()
37 | 
38 | if __name__ == "__main__":
39 |     receipts = ["receipt1.jpg", "receipt2.jpg"]  # Replace with actual file names
40 |     expense_data = analyze_expenses(receipts)
41 |     print(expense_data)
42 |     plot_expenses(expense_data)
43 | 


--------------------------------------------------------------------------------