Update app.py

app.py

@@ -92,22 +92,132 @@ def get_historical_prices(symbol):
 
 def generate_summary(info, ratios):
     recommendation = "Hold"
-    if ratios['P/E Ratio'] < 15 and ratios['P/B Ratio'] < 2:
+    if ratios['P/E Ratio'] < 15 and ratios['P/B Ratio'] < 2 and ratios['PEG Ratio'] < 1.0 and ratios['Dividend Yield (%)'] > 2:
         recommendation = "Buy"
-    elif ratios['P/E Ratio'] > 30 and ratios['P/B Ratio'] > 5:
+    elif ratios['P/E Ratio'] > 30 and ratios['P/B Ratio'] > 5 and ratios['PEG Ratio'] > 2.0:
         recommendation = "Sell"
 
     prompt = (
-        f"Write a professional financial analysis about the company {info['Name']}. "
-        f"{info['Name']} operates in the {info['Industry']} industry within the {info['Sector']} sector. "
-        f"It has a market capitalization of approximately ${info['Market Cap']:,.2f}. "
-        f"The Price-to-Earnings (P/E) ratio is {ratios['P/E Ratio']:.2f}, "
-        f"Price-to-Sales (P/S) ratio is {ratios['P/S Ratio']:.2f}, "
-        f"Price-to-Book (P/B) ratio is {ratios['P/B Ratio']:.2f}, "
-        f"PEG ratio is {ratios['PEG Ratio']:.2f}, and dividend yield is {ratios['Dividend Yield (%)']:.2f}%. "
-        f"Based on these metrics, the recommended investment action is: {recommendation}."
+        f"Company: {info['Name']}\n"
+        f"Industry: {info['Industry']}\n"
+        f"Sector: {info['Sector']}\n"
+        f"Market Cap: ${info['Market Cap']:,.2f}\n"
+        f"P/E Ratio: {ratios['P/E Ratio']:.2f}\n"
+        f"P/S Ratio: {ratios['P/S Ratio']:.2f}\n"
+        f"P/B Ratio: {ratios['P/B Ratio']:.2f}\n"
+        f"PEG Ratio: {ratios['PEG Ratio']:.2f}\n"
+        f"Dividend Yield: {ratios['Dividend Yield (%)']:.2f}%\n"
+        f"\nProvide a financial analysis of this company based on the above information. Also mention the recommended investment action: {recommendation}."
     )
-    summary = summarizer(prompt, max_length=180, min_length=80, do_sample=False)[0]['summary_text']
+    summary = summarizer(prompt, max_length=220, min_length=100, do_sample=False)[0]['summary_text']
     return summary
 
 # (Rest of the code remains the same)
+def calculate_ratios(market_cap, total_revenue, price, dividend_amount, 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
+    dividend_yield = (dividend_amount / price) * 100 if price else 0
+    return {
+        'P/E Ratio': pe_ratio,
+        'P/S Ratio': ps_ratio,
+        'P/B Ratio': pb_ratio,
+        'PEG Ratio': peg_ratio,
+        'Dividend Yield (%)': dividend_yield
+    }
+
+def compare_to_sector(sector, ratios):
+    averages = sector_averages.get(sector, None)
+    if not averages:
+        return pd.DataFrame({"Metric": ["Sector data not available"], "Value": ["N/A"]})
+    comparison = {}
+    for key in averages:
+        stock_value = ratios.get(key, 0)
+        sector_value = averages[key]
+        comparison[key] = f"{stock_value:.2f} vs Sector Avg {sector_value:.2f}"
+    return pd.DataFrame({"Ratio": list(comparison.keys()), "Comparison": list(comparison.values())})
+
+def stock_research(symbol, assumed_eps=5.0, growth_rate=0.1, book_value=500000000):
+    if assumed_eps is None:
+        assumed_eps = 5.0
+    if growth_rate is None:
+        growth_rate = 0.1
+    if book_value is None:
+        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, None, None
+
+    ratios = calculate_ratios(info['Market Cap'], info['Total Revenue'], price, dividends['Dividend Amount'], assumed_eps, growth_rate, book_value)
+    summary = generate_summary(info, ratios)
+    sector_comp = compare_to_sector(info['Sector'], ratios)
+
+    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, sector_comp, fig
+
+def download_report(info_table, ratios_table, sector_comp, summary):
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".csv", mode='w') as f:
+        info_table.to_csv(f, index=False)
+        f.write("\n")
+        ratios_table.to_csv(f, index=False)
+        f.write("\n")
+        sector_comp.to_csv(f, index=False)
+        f.write("\nSummary\n")
+        f.write(summary)
+        file_path = f.name
+    return file_path
+
+# Gradio UI
+with gr.Blocks() as iface:
+    with gr.Row():
+        symbol = gr.Textbox(label="Stock Symbol (e.g., AAPL)", info="Ticker symbol of the company to analyze.")
+        eps = gr.Number(label="Assumed EPS", value=5.0, info="Earnings Per Share (EPS) for P/E calculation.")
+        growth = gr.Number(label="Assumed Growth Rate", value=0.1, info="Expected annual growth rate for PEG.")
+        book = gr.Number(label="Assumed Book Value", value=500000000, info="Total net assets for P/B calculation.")
+
+    with gr.Tabs():
+        with gr.Tab("AI Research Summary"):
+            output_summary = gr.Textbox()
+        with gr.Tab("Company Snapshot"):
+            output_info = gr.Dataframe()
+        with gr.Tab("Valuation Ratios"):
+            output_ratios = gr.Dataframe()
+        with gr.Tab("Sector Comparison"):
+            output_sector = gr.Dataframe()
+        with gr.Tab("Historical Price Chart"):
+            output_chart = gr.Plot()
+
+    submit_btn = gr.Button("Run Analysis")
+    download_btn = gr.Button("Download Report")
+    file_output = gr.File()
+
+    submit_btn.click(
+        fn=stock_research,
+        inputs=[symbol, eps, growth, book],
+        outputs=[output_summary, output_info, output_ratios, output_sector, output_chart]
+    )
+
+    download_btn.click(
+        fn=download_report,
+        inputs=[output_info, output_ratios, output_sector, output_summary],
+        outputs=file_output
+    )
+
+if __name__ == "__main__":
+    iface.launch()