"비용 분류" 태그로 연결된 1개 게시물개의 게시물이 있습니다.

import pandas as pd
from datetime import datetime

def categorize_transaction(description, amount):
    rules = {
        'ADOBE': 'Expenses:Software:Subscriptions',
        'OFFICE DEPOT': 'Expenses:Office:Supplies',
        'FACEBOOK ADS': 'Expenses:Marketing:Advertising'
    }
    
    for vendor, category in rules.items():
        if vendor.lower() in description.lower():
            return category
    return 'Expenses:Uncategorized'

def generate_beancount_entry(row):
    date = row['date'].strftime('%Y-%m-%d')
    desc = row['description']
    amount = abs(float(row['amount']))
    category = categorize_transaction(desc, amount)
    
    return f'''
{date} * "{desc}"
    {category}                               {amount:.2f} USD
    Liabilities:CreditCard                  -{amount:.2f} USD
'''

import re

patterns = {
    r'(?i)aws.*cloud': 'Expenses:Cloud:AWS',
    r'(?i)(zoom|slack|notion).*subscription': 'Expenses:Software:Subscriptions',
    r'(?i)(uber|lyft|taxi)': 'Expenses:Travel:Transport',
    r'(?i)(marriott|hilton|airbnb)': 'Expenses:Travel:Accommodation'
}

def regex_categorize(description):
    for pattern, category in patterns.items():
        if re.search(pattern, description):
            return category
    return None

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
import re
from typing import List, Tuple

class ExpenseClassifier:
    def __init__(self):
        self.vectorizer = TfidfVectorizer()
        self.classifier = MultinomialNB()
    
    def parse_beancount_entries(self, beancount_text: str) -> List[Tuple[str, str]]:
        """Parse Beancount entries into (description, category) pairs."""
        entries = []
        for line in beancount_text.split('\n'):
            # Look for transaction descriptions
            if '* "' in line:
                desc = re.search('"(.+)"', line)
                if desc:
                    description = desc.group(1)
                    # Get the next line which should contain the expense category
                    next_line = next(filter(None, beancount_text.split('\n')[beancount_text.split('\n').index(line)+1:]))
                    if 'Expenses:' in next_line:
                        category = next_line.split()[0].strip()
                        entries.append((description, category))
        return entries
        
    def train(self, beancount_text: str):
        """Train the classifier using Beancount entries."""
        entries = self.parse_beancount_entries(beancount_text)
        if not entries:
            raise ValueError("No valid entries found in training data")
            
        descriptions, categories = zip(*entries)
        X = self.vectorizer.fit_transform(descriptions)
        self.classifier.fit(X, categories)
        
    def predict(self, description: str) -> str:
        """Predict category for a new transaction description."""
        X = self.vectorizer.transform([description])
        return self.classifier.predict(X)[0]

# Example usage with training data:
classifier = ExpenseClassifier()

training_data = """
2025-04-01 * "AWS Cloud Services Monthly Bill" 
    Expenses:Cloud:AWS                         150.00 USD
    Liabilities:CreditCard                   -150.00 USD

2025-04-02 * "Zoom Monthly Subscription"
    Expenses:Software:Subscriptions            14.99 USD
    Liabilities:CreditCard                    -14.99 USD
    
2025-04-03 * "AWS EC2 Instances"
    Expenses:Cloud:AWS                         250.00 USD
    Liabilities:CreditCard                    -250.00 USD

2025-04-04 * "Slack Annual Plan"
    Expenses:Software:Subscriptions           120.00 USD
    Liabilities:CreditCard                   -120.00 USD
"""

# Train the classifier
classifier.train(training_data)

# Test predictions
test_descriptions = [
    "AWS Lambda Services",
    "Zoom Webinar Add-on",
    "Microsoft Teams Subscription"
]

for desc in test_descriptions:
    predicted_category = classifier.predict(desc)
    print(f"Description: {desc}")
    print(f"Predicted Category: {predicted_category}\\n")