transaction.py

# transaction.py
import re
from constants import BUSINESS_SUFFIXES, BANK_TERMS, US_STATES
from nltk.corpus import stopwords
import nltk

nltk.download('punkt', quiet=True)
nltk.download('stopwords', quiet=True)

class Transaction:
    def __init__(self, **kwargs):
        for key, value in kwargs.items():
            setattr(self, key, value)
        self.cleaned_memo = self.clean_memo() if hasattr(self, 'memo') else None
        self.cleaned_name = self.clean_name() if hasattr(self, 'name') else None
        self.matching_steps = {}
        self.predicted_category = None

    def clean_memo(self):
        if not hasattr(self, 'memo') or not isinstance(self.memo, str):
            return None
        memo = self.memo
        memo = re.sub(r'https?://\S+', '', memo)
        memo = re.sub(r'\S+@\S+', '', memo)
        tokens = memo.split()
        stop_words = set(stopwords.words('english'))
        tokens = [word for word in tokens if word.lower() not in stop_words and len(word) > 2 and not self.is_location(word) and not self.is_transaction_detail(word)]
        tokens = [word for word in tokens if word.upper() not in BUSINESS_SUFFIXES]
        return ' '.join(tokens)

    def clean_name(self):
        if not hasattr(self, 'name') or not isinstance(self.name, str):
            return None
        tokens = self.name.split()
        tokens = [word for word in tokens if not self.is_location(word) and word.upper() not in BANK_TERMS and word.upper() not in BUSINESS_SUFFIXES]
        return ' '.join(tokens)

    @staticmethod
    def is_location(word):
        common_city_names = {'LAS', 'NEW', 'SAN', 'LOS', 'SAINT', 'ST'}
        return word.upper() in US_STATES or word.upper() in common_city_names

    @staticmethod
    def is_transaction_detail(word):
        return word.isdigit() or sum(c.isdigit() for c in word) / len(word) > 0.5