app.py

import streamlit as st
import pdfplumber
import pandas as pd

# Define category mapping based on transaction keywords
CATEGORY_MAPPING = {
    "Groceries": ["Walmart", "Kroger", "Whole Foods", "Costco", "Trader Joe", "Safeway"],
    "Dining": ["McDonald's", "Starbucks", "Chipotle", "Subway", "Domino", "Pizza", "Burger", "Restaurant"],
    "Utilities": ["Verizon", "AT&T", "T-Mobile", "Sprint", "Comcast", "Xfinity", "Con Edison", "Electric", "Water", "Gas"],
    "Rent": ["Apartment", "Rent", "Landlord", "Lease"],
    "Entertainment": ["Netflix", "Spotify", "Amazon Prime", "Hulu", "Disney", "Cinema"],
    "Transport": ["Uber", "Lyft", "MetroCard", "Gas Station", "Shell", "Chevron"],
    "Healthcare": ["Pharmacy", "CVS", "Walgreens", "Doctor", "Hospital", "Dental"],
    "Shopping": ["Amazon", "Best Buy", "Target", "Walmart", "Ebay", "Retail"],
    "Other": []
}

# Function to classify transactions based on description
def classify_transaction(description):
    description = str(description).lower()
    for category, keywords in CATEGORY_MAPPING.items():
        if any(keyword.lower() in description for keyword in keywords):
            return category
    return "Other"

# Function to process uploaded PDF and categorize transactions
def process_pdf(file):
    if file is None:
        st.error("No file uploaded.")
        return None
    
    # Extract text from PDF
    with pdfplumber.open(file) as pdf:
        text = "\n".join([page.extract_text() for page in pdf.pages if page.extract_text()])

    # Extract transactions (Modify based on statement format)
    lines = text.split("\n")
    transactions = [line for line in lines if any(char.isdigit() for char in line)]  

    # Convert to DataFrame
    df = pd.DataFrame([line.split()[:3] for line in transactions], columns=["Date", "Description", "Amount"])

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

    # Ensure no missing descriptions
    df["Description"] = df["Description"].fillna("Unknown")

    # Apply classification
    df["Category"] = df["Description"].apply(classify_transaction)

    # Summarize total spending per category
    category_summary = df.groupby("Category")["Amount"].sum().reset_index()

    return df, category_summary  # Return full transactions and summary

# Streamlit UI
st.title("📄 Credit Card Statement Classifier")
st.write("Upload a **PDF bank/credit card statement**, and this app will categorize transactions and show your spending summary.")

uploaded_file = st.file_uploader("Upload PDF", type=["pdf"])

if uploaded_file is not None:
    st.success("✅ File uploaded successfully!")
    
    # Process and display transactions
    df_result, category_summary = process_pdf(uploaded_file)
    
    if df_result is not None:
        st.write("### 📊 Classified Transactions:")
        st.dataframe(df_result)  # Display detailed transactions
        
        st.write("### 💰 Spending Summary by Category:")
        st.dataframe(category_summary)  # Display spending summary