data_processor.py

import pandas as pd
import re

def standardize_columns(df):
    df.columns = df.columns.str.lower().str.strip()
    return df


def clean_description(text):
    text = str(text).capitalize()

    # Remove currency words
    text = re.sub(r'\b(pkr|usd|rs)\b', '', text)

    # Remove numbers
    text = re.sub(r'\d+', '', text)

    # Remove special characters
    text = re.sub(r'[^a-zA-Z\s]', ' ', text)

    # Remove extra spaces
    text = re.sub(r'\s+', ' ', text).strip()

    return text


def process_csv(df):

    df = standardize_columns(df)

    required_cols = ["date", "spent_on", "importance", "amount"]

    for col in required_cols:
        if col not in df.columns:
            raise ValueError(
                "CSV must contain: date, spent_on, importance, amount"
            )

    # Parse date
    df["date"] = pd.to_datetime(df["date"], errors="coerce")

    # Clean description properly
    df["spent_on"] = df["spent_on"].apply(clean_description)

    # Normalize importance
    df["importance"] = (
        df["importance"]
        .astype(str)
        .str.lower()
        .str.strip()
    )

    # Standardize importance categories
    importance_map = {
        "optional": "Optional",
        "survival": "Essential",
        "obligation": "Essential",
        "investment": "Investment"
    }

    df["importance"] = df["importance"].map(importance_map).fillna("Optional")

    # Ensure numeric amount
    df["amount"] = pd.to_numeric(df["amount"], errors="coerce")

    # Drop invalid rows
    df = df.dropna(subset=["date", "amount"])

    return df