Update app.py

app.py

@@ -8,6 +8,27 @@ from sklearn.preprocessing import StandardScaler
 from sklearn.model_selection import train_test_split
 import gradio as gr
 import os
+import time
+from fastapi import FastAPI, BackgroundTasks
+from fastapi.middleware.cors import CORSMiddleware
+import asyncio
+
+# FastAPI app
+app = FastAPI()
+
+# Add CORS middleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Global variables
+model = None
+scaler = None
+latest_report = "Initializing..."
 
 # Define the Dataset class
 class BankNiftyDataset(Dataset):
@@ -43,7 +64,8 @@ class LSTMModel(nn.Module):
         return out
 
 # Function to train the model
-def train_model(model, train_loader, val_loader, num_epochs=10):
+def train_model(train_loader, val_loader, num_epochs=10):
+    global model
     criterion = nn.MSELoss()
     optimizer = optim.Adam(model.parameters(), lr=0.001)
     
@@ -97,6 +119,8 @@ def generate_report(predictions, actual_values, signals):
 
 # Function to process data and make predictions
 def predict():
+    global model, scaler, latest_report
+
     # Load the pre-existing CSV file
     csv_path = 'BANKNIFTY_OPTION_CHAIN_data.csv'
     if not os.path.exists(csv_path):
@@ -104,8 +128,11 @@ def predict():
 
     # Load and preprocess data
     data = pd.read_csv(csv_path)
-    scaler = StandardScaler()
-    scaled_data = scaler.fit_transform(data[['open', 'high', 'low', 'close', 'volume', 'oi']])
+    if scaler is None:
+        scaler = StandardScaler()
+        scaled_data = scaler.fit_transform(data[['open', 'high', 'low', 'close', 'volume', 'oi']])
+    else:
+        scaled_data = scaler.transform(data[['open', 'high', 'low', 'close', 'volume', 'oi']])
     data[['open', 'high', 'low', 'close', 'volume', 'oi']] = scaled_data
 
     # Split data
@@ -120,11 +147,13 @@ def predict():
     val_loader = DataLoader(val_dataset, batch_size=32, shuffle=False)
 
     # Initialize and train the model
-    input_dim = 6
-    hidden_dim = 64
-    output_dim = len(target_cols)
-    model = LSTMModel(input_dim, hidden_dim, output_dim)
-    train_model(model, train_loader, val_loader)
+    if model is None:
+        input_dim = 6
+        hidden_dim = 64
+        output_dim = len(target_cols)
+        model = LSTMModel(input_dim, hidden_dim, output_dim)
+
+    train_model(train_loader, val_loader)
 
     # Make predictions
     model.eval()
@@ -138,18 +167,40 @@ def predict():
 
     # Generate signals and report
     signals = generate_signals(predictions, actual_values)
-    report = generate_report(predictions, actual_values, signals)
+    latest_report = generate_report(predictions, actual_values, signals)
 
-    return report
+    return latest_report
+
+# Background task to update the model and report
+async def update_model_and_report():
+    global latest_report
+    while True:
+        latest_report = predict()
+        await asyncio.sleep(3600)  # Update every hour
+
+# Startup event to begin the background task
+@app.on_event("startup")
+async def startup_event():
+    background_tasks = BackgroundTasks()
+    background_tasks.add_task(update_model_and_report)
+    await background_tasks()
+
+# Gradio interface
+def gradio_interface():
+    return latest_report
 
-# Set up the Gradio interface
 iface = gr.Interface(
-    fn=predict,
+    fn=gradio_interface,
     inputs=None,
-    outputs=gr.Textbox(label="Prediction Report"),
+    outputs=gr.Textbox(label="Latest Prediction Report"),
     title="BankNifty Option Chain Predictor",
-    description="Click 'Submit' to generate predictions and trading signals based on the pre-loaded BankNifty option chain data."
+    description="This app automatically generates and updates predictions and trading signals based on the latest BankNifty option chain data."
 )
 
-# Launch the app
-iface.launch()
+# Combine FastAPI and Gradio
+app = gr.mount_gradio_app(app, iface, path="/")
+
+# Run the FastAPI app
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=7860)