Update app.py

app.py

@@ -5,42 +5,26 @@ import plotly.graph_objects as go
 
 CSV_URL = "https://gardenstatemls.stats.showingtime.com/infoserv/s-v1/kpou-Asg"
 
-def monte_carlo_live(T=1.0, steps=12, n_paths=100):
+def monte_carlo_live(T=1.0, steps=120, n_paths=1000):
     try:
-        # Load CSV and skip metadata
         df = pd.read_csv(CSV_URL, skiprows=9)
-        df = df.dropna(axis=1, how='all')  # Remove empty columns
-
-        # Use only first 2 columns: Date and Median Sales Price
+        df = df.dropna(axis=1, how='all')
         df = df.iloc[:, :2]
         df.columns = ['Date', 'Median Sales Price']
-
-        # Convert price to numeric after removing $ and commas
-        df['Median Sales Price'] = pd.to_numeric(
-            df['Median Sales Price'].replace('[\$,]', '', regex=True),
-            errors='coerce'
-        )
-
-        # Parse date with full month names like "January 2009"
+        df['Median Sales Price'] = pd.to_numeric(df['Median Sales Price'].replace('[\$,]', '', regex=True), errors='coerce')
         df['Date'] = pd.to_datetime(df['Date'], errors='coerce')
-
-        # Drop any rows with bad values
         df = df.dropna(subset=['Date', 'Median Sales Price'])
-
-        # Sort chronologically
         df = df.sort_values(by='Date')
 
-        # Calculate log returns
         prices = df['Median Sales Price'].values
         if len(prices) < 2:
             raise ValueError("Not enough valid price data after cleaning.")
         returns = np.diff(np.log(prices))
 
-        mu = np.mean(returns) * 12  # annualized return
-        sigma = np.std(returns) * np.sqrt(12)  # annualized volatility
-        S0 = prices[-1]  # latest price
+        mu = np.mean(returns) * 12
+        sigma = np.std(returns) * np.sqrt(12)
+        S0 = prices[-1]
 
-        # Monte Carlo simulation
         dt = T / steps
         paths = np.zeros((steps + 1, n_paths))
         paths[0] = S0
@@ -48,57 +32,69 @@ def monte_carlo_live(T=1.0, steps=12, n_paths=100):
             rand = np.random.normal(0, 1, n_paths)
             paths[t] = paths[t - 1] * np.exp((mu - 0.5 * sigma ** 2) * dt + sigma * np.sqrt(dt) * rand)
 
-        # Create time axis
         time = np.linspace(0, T, steps + 1)
 
-        # Plotly figure
-        fig = go.Figure()
-
+        forecast_fig = go.Figure()
         for i in range(n_paths):
-            fig.add_trace(go.Scatter(x=time, y=paths[:, i], mode='lines', line=dict(width=1), showlegend=False))
+            forecast_fig.add_trace(go.Scatter(x=time, y=paths[:, i], mode='lines', line=dict(width=1), showlegend=False))
 
-        # Mean and median paths
         mean_path = paths.mean(axis=1)
         median_path = np.median(paths, axis=1)
-        fig.add_trace(go.Scatter(x=time, y=mean_path, name='Mean Path', line=dict(width=3, dash='dash')))
-        fig.add_trace(go.Scatter(x=time, y=median_path, name='Median Path', line=dict(width=3, dash='dot')))
+        forecast_fig.add_trace(go.Scatter(x=time, y=mean_path, name='Mean Path', line=dict(width=3, dash='dash')))
+        forecast_fig.add_trace(go.Scatter(x=time, y=median_path, name='Median Path', line=dict(width=3, dash='dot')))
 
-        fig.update_layout(
+        forecast_fig.update_layout(
             title="Monte Carlo Simulation — Garden State MLS Median Sales Price Forecast",
             xaxis_title="Years Ahead",
             yaxis_title="Simulated Price ($)",
             height=600
         )
 
-        summary = f"Simulated {n_paths} paths from latest price ${S0:.2f}.\n" \
-                  f"Annualized Drift (μ): {mu * 100:.2f}%, Volatility (σ): {sigma * 100:.2f}%"
+        historical_fig = go.Figure()
+        historical_fig.add_trace(go.Scatter(x=df['Date'], y=df['Median Sales Price'], mode='lines+markers', name='Median Sales Price'))
+        historical_fig.update_layout(
+            title="Historical Median Sales Prices (Garden State MLS)",
+            xaxis_title="Date",
+            yaxis_title="Median Sales Price ($)",
+            height=500
+        )
+
+        summary = f"""**Simulation Summary**
+- Starting Price: ${S0:,.2f}
+- Simulated {n_paths} paths for {T:.1f} years
+- Annualized Drift (μ): {mu * 100:.2f}%
+- Annualized Volatility (σ): {sigma * 100:.2f}%"""
 
-        return fig, summary
+        return historical_fig, forecast_fig, summary
 
     except Exception as e:
-        fig = go.Figure()
-        fig.update_layout(title="Error", annotations=[{
+        err_fig = go.Figure()
+        err_fig.update_layout(title="Error", annotations=[{
             "text": str(e),
             "xref": "paper",
             "yref": "paper",
             "showarrow": False,
             "font": {"size": 16}
         }])
-        return fig, f"Error: {e}"
+        return err_fig, err_fig, f"Error: {e}"
 
 # Gradio UI
 with gr.Blocks() as demo:
-    gr.Markdown("## 📊 Monte Carlo Simulation: Live MLS Median Sales Price")
+    gr.Markdown("## 🏡 Monte Carlo Simulation: Garden State MLS Median Sales Price Forecast")
 
     with gr.Row():
-        years = gr.Slider(0.1, 5.0, value=1.0, step=0.1, label="Forecast Horizon (Years)")
-        steps = gr.Slider(12, 120, value=12, step=12, label="Time Steps")
-        paths = gr.Slider(10, 300, value=100, step=10, label="Number of Simulated Paths")
+        years = gr.Slider(0.1, 10.0, value=1.0, step=0.1, label="Forecast Horizon (Years)")
+        steps = gr.Slider(12, 240, value=120, step=12, label="Time Steps")
+        paths = gr.Slider(10, 2000, value=1000, step=10, label="Number of Simulated Paths")
 
     run_button = gr.Button("Run Simulation")
-    plot = gr.Plot()
-    summary = gr.Textbox(label="Simulation Summary")
 
-    run_button.click(monte_carlo_live, inputs=[years, steps, paths], outputs=[plot, summary])
+    with gr.Row():
+        historical_plot = gr.Plot(label="📈 Historical Prices")
+        simulation_plot = gr.Plot(label="🔮 Forecast Simulation")
+
+    summary = gr.Markdown(label="📝 Simulation Summary")
+
+    run_button.click(fn=monte_carlo_live, inputs=[years, steps, paths], outputs=[historical_plot, simulation_plot, summary])
 
 demo.launch()