app.py

import pandas as pd
import numpy as np
import gradio as gr
import matplotlib.pyplot as plt
import requests
import os
from transformers import pipeline
import datetime

# Initialize Summarizer
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")

# Polygon API Key
POLYGON_API_KEY = os.getenv("POLYGON_API_KEY")

# Helper Functions
def get_company_info(symbol):
    url = f"https://api.polygon.io/v3/reference/tickers/{symbol}?apiKey={POLYGON_API_KEY}"
    try:
        response = requests.get(url)
        response.raise_for_status()
        data = response.json()['results']
        return {
            'Name': data.get('name', 'N/A'),
            'Industry': data.get('sic_description', 'N/A'),
            'Market Cap': data.get('market_cap', 0),
            'Total Revenue': data.get('total_employees', 0) * 100000  # Rough estimation
        }
    except Exception as e:
        print(f"DEBUG: Error fetching company info: {e}")
        return None

def get_current_price(symbol):
    url = f"https://api.polygon.io/v2/aggs/ticker/{symbol}/prev?adjusted=true&apiKey={POLYGON_API_KEY}"
    try:
        response = requests.get(url)
        response.raise_for_status()
        data = response.json()['results'][0]
        return float(data['c'])
    except Exception as e:
        print(f"DEBUG: Error fetching price: {e}")
        return None

def get_dividends(symbol):
    url = f"https://api.polygon.io/v3/reference/dividends?ticker={symbol}&apiKey={POLYGON_API_KEY}"
    try:
        response = requests.get(url)
        response.raise_for_status()
        data = response.json()['results'][0]
        return {
            'Dividend Amount': data.get('cash_amount', 0),
            'Ex-Dividend Date': data.get('ex_dividend_date', 'N/A')
        }
    except Exception as e:
        print(f"DEBUG: Error fetching dividends: {e}")
        return {'Dividend Amount': 0, 'Ex-Dividend Date': 'N/A'}

def get_historical_prices(symbol):
    end = datetime.date.today()
    start = end - datetime.timedelta(days=365)
    url = f"https://api.polygon.io/v2/aggs/ticker/{symbol}/range/1/day/{start}/{end}?adjusted=true&sort=asc&apiKey={POLYGON_API_KEY}"
    try:
        response = requests.get(url)
        response.raise_for_status()
        results = response.json()['results']
        dates = [datetime.datetime.fromtimestamp(r['t']/1000) for r in results]
        prices = [r['c'] for r in results]
        return dates, prices
    except Exception as e:
        print(f"DEBUG: Error fetching historical prices: {e}")
        return [], []

def calculate_ratios(market_cap, total_revenue, price, assumed_eps=5.0, growth_rate=0.1, book_value=500000000):
    pe_ratio = price / assumed_eps if assumed_eps else 0
    ps_ratio = market_cap / total_revenue if total_revenue else 0
    pb_ratio = market_cap / book_value if book_value else 0
    peg_ratio = pe_ratio / (growth_rate * 100) if growth_rate else 0
    return {
        'P/E Ratio': pe_ratio,
        'P/S Ratio': ps_ratio,
        'P/B Ratio': pb_ratio,
        'PEG Ratio': peg_ratio
    }

def generate_summary(info, ratios):
    text = (f"{info['Name']} operates in the {info['Industry']} sector. It has a market capitalization of "
            f"${info['Market Cap']:,.2f}. The company exhibits a P/E ratio of {ratios['P/E Ratio']:.2f}, "
            f"P/S ratio of {ratios['P/S Ratio']:.2f}, and P/B ratio of {ratios['P/B Ratio']:.2f}. "
            f"This suggests a {'potential undervaluation' if ratios['P/E Ratio'] < 20 else 'higher valuation'} relative to the market.")
    summary = summarizer(text, max_length=120, min_length=30, do_sample=False)[0]['summary_text']
    return summary

def stock_research(symbol, assumed_eps=5.0, growth_rate=0.1, book_value=500000000):
    info = get_company_info(symbol)
    price = get_current_price(symbol)
    dividends = get_dividends(symbol)
    dates, prices = get_historical_prices(symbol)

    if not info or not price:
        return "Error fetching stock information.", None, None, None

    ratios = calculate_ratios(info['Market Cap'], info['Total Revenue'], price, assumed_eps, growth_rate, book_value)
    summary = generate_summary(info, ratios)

    # Create historical price chart
    fig, ax = plt.subplots()
    ax.plot(dates, prices, label=f"{symbol} Price")
    ax.set_title(f"{symbol} Historical Price (1 Year)")
    ax.set_xlabel("Date")
    ax.set_ylabel("Price ($)")
    ax.legend()
    ax.grid(True)

    info_table = pd.DataFrame({"Metric": list(info.keys()), "Value": list(info.values())})
    ratios_table = pd.DataFrame({"Ratio": list(ratios.keys()), "Value": list(ratios.values())})

    return summary, info_table, ratios_table, fig

iface = gr.Interface(
    fn=stock_research,
    inputs=[
        gr.Textbox(label="Stock Symbol (e.g., AAPL)"),
        gr.Number(label="Assumed EPS (default 5.0)"),
        gr.Number(label="Assumed Growth Rate (e.g., 0.1 for 10%)"),
        gr.Number(label="Assumed Book Value ($, default 500M)")
    ],
    outputs=[
        gr.Textbox(label="AI Research Summary"),
        gr.Dataframe(label="Company Snapshot"),
        gr.Dataframe(label="Valuation Ratios"),
        gr.Plot(label="Historical Price Chart")
    ],
    title="AI-Powered Stock Researcher",
    description="Enter a stock symbol to get company info, valuation ratios, a 1-year price chart, and an AI-generated research summary based on live Polygon.io data."
)

if __name__ == "__main__":
    iface.launch()