Update app.py

app.py

@@ -2,100 +2,120 @@ import gradio as gr
 import pandas as pd
 import torch
 import plotly.graph_objects as go
+from plotly.subplots import make_subplots
 import numpy as np
 import yfinance as yf
 from timesfm import TimesFm
 
-# Initialize Google TimesFM
-# We use the 200M model which is optimized for Hugging Face Free Tier
+# Initialize Google TimesFM with updated API arguments
+# Note: 'context_len' changed to 'context_length', etc.
 tfm = TimesFm(
-    context_len=512,
-    horizon_len=128,
+    context_length=512,
+    horizon_length=128,
     input_patch_len=32,
     output_patch_len=128,
     num_layers=20,
     model_dims=1280,
-    backend="cpu", # Change to "gpu" if your Space has a GPU
+    backend="cpu",
 )
 
 tfm.load_from_checkpoint(repo_id="google/timesfm-1.0-200m")
 
 def get_tradingview_plot(df, forecast_df, ticker):
-    fig = go.Figure()
+    # Create subplots: Chart on top (80%), Volume on bottom (20%)
+    fig = make_subplots(rows=2, cols=1, shared_xaxes=True, 
+                        vertical_spacing=0.03, subplot_titles=(f'{ticker} Analysis', ''), 
+                        row_width=[0.2, 0.8])
 
-    # Historical Price (Professional Blue)
+    # 1. Main Price Line
     fig.add_trace(go.Scatter(
         x=df.index, y=df['Close'],
-        name='Historical',
+        name='Historical Close',
         line=dict(color='#2962FF', width=2)
-    ))
+    ), row=1, col=1)
 
-    # TimesFM Forecast (Dotted Red)
+    # 2. TimesFM Forecast (Dotted Projection)
     fig.add_trace(go.Scatter(
         x=forecast_df['ds'], y=forecast_df['timesfm'],
-        name='TimesFM Forecast',
+        name='AI Forecast',
         line=dict(color='#F23645', width=3, dash='dot')
-    ))
+    ), row=1, col=1)
 
-    # Add TradingView Styling
+    # 3. Volume Profile (Bars)
+    fig.add_trace(go.Bar(
+        x=df.index, y=df['Volume'],
+        name='Volume',
+        marker_color='#26a69a',
+        opacity=0.5
+    ), row=2, col=1)
+
+    # Professional Dark Theme Styling
     fig.update_layout(
         template='plotly_dark',
         hovermode="x unified",
         paper_bgcolor='#131722',
         plot_bgcolor='#131722',
+        showlegend=True,
         margin=dict(l=10, r=10, t=50, b=10),
-        xaxis=dict(showgrid=True, gridcolor='#2a2e39'),
-        yaxis=dict(showgrid=True, gridcolor='#2a2e39', side='right'),
-        legend=dict(yanchor="top", y=0.99, xanchor="left", x=0.01)
+        legend=dict(orientation="h", yanchor="bottom", y=1.02, xanchor="right", x=1)
     )
+    
+    fig.update_xaxes(showgrid=True, gridcolor='#2a2e39', rangeslider_visible=False)
+    fig.update_yaxes(showgrid=True, gridcolor='#2a2e39', side='right')
+    
     return fig
 
 def run_analysis(ticker, horizon):
-    # Fetch Data
-    df = yf.download(ticker, period="1y")
-    if df.empty: return None, "Invalid Ticker"
-    
-    # TimesFM expects a specific format: unique_id, ds (date), y (value)
-    # We create a simple dataframe for the model
-    input_df = pd.DataFrame({
-        'unique_id': [ticker],
-        'ds': df.index,
-        'y': df['Close'].values
-    })
-
-    # Execute Forecast
-    # freq: 0 for daily, 1 for weekly, 2 for monthly
-    forecast_df, _ = tfm.forecast_on_df(
-        inputs=input_df,
-        freq="D", 
-        value_name="y"
-    )
+    try:
+        df = yf.download(ticker, period="1y")
+        if df.empty: return None, "⚠️ Invalid Ticker"
+        
+        # Format for TimesFM
+        input_df = pd.DataFrame({
+            'unique_id': [ticker],
+            'ds': df.index,
+            'y': df['Close'].values
+        })
 
-    # Filter forecast to the user-selected horizon
-    forecast_df = forecast_df.head(horizon)
-    
-    # Calculate professional metrics
-    current_price = df['Close'].iloc[-1]
-    final_pred = forecast_df['timesfm'].iloc[-1]
-    change_pct = ((final_pred - current_price) / current_price) * 100
-    
-    status = "BULLISH" if change_pct > 0 else "BEARISH"
-    signal_text = f"{status} ({change_pct:+.2f}%)"
+        # Execute Forecast
+        forecast_df, _ = tfm.forecast_on_df(
+            inputs=input_df,
+            freq="D", 
+            value_name="y"
+        )
 
-    fig = get_tradingview_plot(df, forecast_df, ticker)
-    
-    return fig, signal_text
+        forecast_df = forecast_df.head(horizon)
+        
+        # Calculate Signals
+        current_price = df['Close'].iloc[-1]
+        final_pred = forecast_df['timesfm'].iloc[-1]
+        change_pct = ((final_pred - current_price) / current_price) * 100
+        
+        signal = "STRONG BUY" if change_pct > 5 else "BUY" if change_pct > 0 else "SELL"
+        signal_color = "#00ff88" if "BUY" in signal else "#ff4444"
+        
+        fig = get_tradingview_plot(df, forecast_df, ticker)
+        
+        html_signal = f"<h2 style='color: {signal_color}; text-align: center;'>{signal} ({change_pct:+.2f}%)</h2>"
+        
+        return fig, html_signal
+    except Exception as e:
+        return None, f"Error: {str(e)}"
 
-# Professional UI Template
-with gr.Blocks(theme=gr.themes.Default(), css=".gradio-container {background-color: #131722;}") as demo:
-    gr.Markdown("<h1 style='text-align: center; color: white;'>G-TIMES QUANT TERMINAL</h1>")
+# Professional Layout
+with gr.Blocks(theme=gr.themes.Default(), css=".gradio-container {background-color: #131722; color: white;}") as demo:
+    gr.HTML("<h1 style='text-align: center; color: #2962FF; font-family: sans-serif;'>G-TIMES QUANT TERMINAL</h1>")
     
     with gr.Row():
         with gr.Column(scale=1):
-            ticker_input = gr.Textbox(label="Ticker Symbol", value="NVDA")
-            horizon_slider = gr.Slider(5, 128, value=30, label="Forecast Horizon")
-            analyze_btn = gr.Button("RUN MODELS", variant="primary")
-            output_signal = gr.Label(label="Market Signal")
+            with gr.Box():
+                ticker_input = gr.Textbox(label="Ticker Symbol", value="NVDA")
+                horizon_slider = gr.Slider(5, 128, value=30, label="Forecast Horizon (Days)")
+                analyze_btn = gr.Button("RUN QUANT ANALYSIS", variant="primary")
+            
+            output_signal = gr.HTML(label="Market Signal")
+            gr.Markdown("---")
+            gr.Markdown("### Terminal Info\n- **Model**: Google TimesFM-1.0\n- **Backend**: CPU PyTorch\n- **Freq**: Daily Close")
             
         with gr.Column(scale=4):
             plot_output = gr.Plot()