app.py

import logging
import os
import time
import torch
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer
import pandas as pd
import re
import numpy as np
import json

# Set up logging
logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
logger = logging.getLogger(__name__)

# Define device (force CPU for Spaces free tier)
device = torch.device("cpu")
logger.info(f"Using device: {device}")

# Load dataset at startup
csv_path = "flat-ui__data-Sun Jul 06 2025.csv"
try:
    df = pd.read_csv(csv_path)
    df['Date'] = pd.to_datetime(df['Date'])
    df = df.sort_values('Date')
    df['Return'] = df['SP500'].pct_change(12) * 100
    df['Real Return'] = df['Real Price'].pct_change(12) * 100
    logger.info("Loaded dataset successfully")
except Exception as e:
    logger.error(f"Error loading dataset: {e}")
    df = None

# Response cache with financial data entries
response_cache = {
    "hi": "Hello! I'm FinChat, your financial advisor. How can I help with investing?",
    "hello": "Hello! I'm FinChat, your financial advisor. How can I help with investing?",
    "hey": "Hi there! Ready to discuss investment goals with FinChat?",
    "what is better individual stocks or etfs?": (
        "Here’s a comparison of individual stocks vs. ETFs:\n"
        "1. **Individual Stocks**: High returns possible (e.g., Apple up 80% in 2020) but riskier due to lack of diversification. Require active research.\n"
        "2. **ETFs**: Diversify risk by tracking indices (e.g., SPY, S&P 500, ~12% avg. return 2015–2024). Lower fees and less research needed.\n"
        "3. **Recommendation**: Beginners should start with ETFs; experienced investors may add stocks.\n"
        "Consult a financial planner."
    ),
    "is $100 per month enough to invest?": (
        "Yes, $100 per month is enough to start investing. Here’s why and how:\n"
        "1. **Feasibility**: Brokerages like Fidelity have no minimums, and commission-free trading eliminates fees.\n"
        "2. **Options**: Buy fractional shares of ETFs (e.g., SPY, ~$622/share in 2025) with $100.\n"
        "3. **Strategy**: Use dollar-cost averaging to invest monthly, reducing market timing risks.\n"
        "4. **Growth**: At 10% annual return, $100 monthly could grow to ~$41,000 in 20 years.\n"
        "5. **Tips**: Ensure an emergency fund; diversify.\n"
        "Consult a financial planner."
    ),
    "can i invest $100 a month?": (
        "Yes, $100 a month is sufficient. Here’s how:\n"
        "1. **Brokerage**: Open an account with Fidelity or Vanguard (no minimums).\n"
        "2. **Investments**: Buy fractional shares of ETFs like SPY ($100 buys ~0.16 shares in 2025).\n"
        "3. **Approach**: Use dollar-cost averaging for steady growth.\n"
        "4. **Long-Term**: At 10% return, $100 monthly could reach ~$41,000 in 20 years.\n"
        "5. **Tips**: Prioritize an emergency fund and diversify.\n"
        "Consult a financial planner."
    ),
    "hi, give me step-by-step investing advice": (
        "Here’s a step-by-step guide to start investing:\n"
        "1. Open a brokerage account (e.g., Fidelity, Vanguard) if 18 or older.\n"
        "2. Deposit an affordable amount, like $100, after an emergency fund.\n"
        "3. Research and buy an ETF (e.g., SPY) using Yahoo Finance.\n"
        "4. Monitor monthly and enable dividend reinvesting.\n"
        "5. Use dollar-cost averaging ($100 monthly) to reduce risk.\n"
        "6. Diversify across sectors.\n"
        "Consult a financial planner."
    ),
    "hi, pretend you are a financial advisor. now tell me how can i start investing in stock market?": (
        "Here’s a guide to start investing:\n"
        "1. Learn from Investopedia or 'The Intelligent Investor.'\n"
        "2. Set goals (e.g., retirement) and assess risk.\n"
        "3. Choose a brokerage (Fidelity, Vanguard).\n"
        "4. Start with ETFs (e.g., SPY) or mutual funds.\n"
        "5. Use dollar-cost averaging ($100-$500 monthly).\n"
        "6. Diversify and monitor.\n"
        "Consult a financial planner."
    ),
    "do you have a list of companies you recommend?": (
        "I can’t recommend specific companies without data. Try ETFs like SPY (S&P 500, ~12% avg. return 2015–2024) or QQQ (tech). "
        "Research stocks like Apple (AAPL, ~80% return in 2020) or Johnson & Johnson on Yahoo Finance.\n"
        "Consult a financial planner."
    ),
    "how do i start investing in stocks?": (
        "Learn from Investopedia. Set goals and assess risk. Open a brokerage account (Fidelity, Vanguard) "
        "and start with ETFs (e.g., SPY, ~12% avg. return 2015–2024). Consult a financial planner."
    ),
    "what's the difference between stocks and bonds?": (
        "Stocks are company ownership with high risk and growth potential (e.g., S&P 500 ~12% avg. return 2015–2024). Bonds are loans to companies/governments "
        "with lower risk and steady interest. Diversify for balance."
    ),
    "how much should i invest?": (
        "Invest what you can afford after expenses and an emergency fund. Start with $100-$500 monthly "
        "in ETFs like SPY (~12% avg. return 2015–2024). Consult a financial planner."
    ),
    "what is dollar-cost averaging?": (
        "Dollar-cost averaging is investing a fixed amount regularly (e.g., $100 monthly) in ETFs, "
        "reducing risk by spreading purchases over time."
    ),
    "give me few investing idea": (
        "Here are investing ideas:\n"
        "1. Open a brokerage account (e.g., Fidelity) if 18 or older.\n"
        "2. Deposit $100 or what you can afford.\n"
        "3. Buy a researched ETF (e.g., SPY, ~12% avg. return 2015–2024) or index fund.\n"
        "4. Check regularly and enable dividend reinvesting.\n"
        "5. Use dollar-cost averaging (e.g., monthly buys).\n"
        "Consult a financial planner."
    ),
    "give me investing tips": (
        "Here are investing tips:\n"
        "1. Educate yourself with Investopedia or books.\n"
        "2. Open a brokerage account (e.g., Vanguard).\n"
        "3. Start small with ETFs like SPY (~12% avg. return 2015–2024).\n"
        "4. Invest regularly using dollar-cost averaging.\n"
        "5. Diversify to manage risk.\n"
        "Consult a financial planner."
    ),
    "how to start investing": (
        "Here’s how to start investing:\n"
        "1. Study basics on Investopedia.\n"
        "2. Open a brokerage account (e.g., Fidelity).\n"
        "3. Deposit $100 or more after securing savings.\n"
        "4. Buy an ETF like SPY (~12% avg. return 2015–2024) after research.\n"
        "5. Invest monthly with dollar-cost averaging.\n"
        "Consult a financial planner."
    ),
    "investing advice": (
        "Here’s investing advice:\n"
        "1. Learn basics from Investopedia.\n"
        "2. Open a brokerage account (e.g., Vanguard).\n"
        "3. Start with $100 in an ETF like SPY (~12% avg. return 2015–2024).\n"
        "4. Use dollar-cost averaging for regular investments.\n"
        "5. Monitor and diversify your portfolio.\n"
        "Consult a financial planner."
    ),
    "steps to invest": (
        "Here are steps to invest:\n"
        "1. Educate yourself using Investopedia.\n"
        "2. Open a brokerage account (e.g., Fidelity).\n"
        "3. Deposit an initial $100 after savings.\n"
        "4. Buy an ETF like SPY (~12% avg. return 2015–2024) after research.\n"
        "5. Use dollar-cost averaging monthly.\n"
        "Consult a financial planner."
    ),
    "what is the s&p 500 index fund average growth rate?": (
        "The S&P 500 index fund’s average annual return is approximately 10–12% over the long term (1927–2025), including dividends, based on historical data. "
        "For example, from 2015 to 2024, it averaged ~12.2% annually. Returns vary yearly due to market conditions. Consult a financial planner."
    ),
    "what was the s&p 500 return in 2020?": (
        "The S&P 500 returned approximately 16.3% in 2020, including dividends, driven by recovery from the COVID-19 market crash."
    ),
    "what was the s&p 500 return in 2022?": (
        "The S&P 500 returned approximately -18.1% in 2022, impacted by high inflation and interest rate hikes."
    ),
    "what is the average annual growth rate of the s&p 500 from 2000 to 2010?": (
        "The S&P 500’s average annual growth rate from 2000 to 2010 was approximately 0.4%, including dividends, impacted by the dot-com crash and 2008 financial crisis."
    ),
    "what is the average annual growth rate of the s&p 500 from 2011 to 2016?": (
        "The S&P 500’s average annual growth rate from 2011 to 2016 was approximately 12.7%, including dividends, driven by post-financial crisis recovery."
    ),
    "what will my return be in 10 years if i invest $5000 into s&p 500 right now?": (
        "Assuming a 10% average annual return, a $5,000 investment in the S&P 500 would grow to approximately $12,974 in 10 years with annual compounding. "
        "This is based on the historical average return of 10–12% (1927–2025). Future returns vary and are not guaranteed. Consult a financial planner."
    ),
    "what was the 1-year average annual growth rate of the s&p 500 from 2020?": (
        "The S&P 500 returned approximately 16.3% in 2020, including dividends, driven by recovery from the COVID-19 market crash."
    ),
    "what was the 3-year average annual growth rate of the s&p 500 from 2018?": (
        "The S&P 500’s average annual growth rate from 2018 to 2020 was approximately 10.2%, including dividends, based on historical data."
    ),
    "what was the 5-year average annual growth rate of the s&p 500 from 2016?": (
        "The S&P 500’s average annual growth rate from 2016 to 2020 was approximately 13.6%, including dividends, driven by strong market recovery."
    ),
    "what is the average return rate of the s&p 500 in the past 10 years?": (
        "The S&P 500’s average annual return rate from 2015 to 2024 was approximately 12.2%, including dividends, based on historical data."
    )
}

# Load persistent cache
cache_file = "cache.json"
try:
    if os.path.exists(cache_file):
        with open(cache_file, 'r') as f:
            response_cache.update(json.load(f))
        logger.info("Loaded persistent cache from cache.json")
except Exception as e:
    logger.warning(f"Failed to load cache.json: {e}")

# Load model and tokenizer (use fine-tuned model if available)
model_name = "./finetuned_model" if os.path.exists("./finetuned_model") else "distilgpt2"
try:
    logger.info(f"Loading tokenizer for {model_name}")
    tokenizer = AutoTokenizer.from_pretrained(model_name, clean_up_tokenization_spaces=False)
    tokenizer.pad_token = tokenizer.eos_token
    logger.info(f"Loading model {model_name}")
    with torch.inference_mode():
        model = AutoModelForCausalLM.from_pretrained(
            model_name,
            torch_dtype=torch.float16,
            low_cpu_mem_usage=True
        ).to(device)
    logger.info(f"Successfully