Update app.py

app.py

@@ -8,7 +8,7 @@ import matplotlib.pyplot as plt
 import gradio as gr
 from datetime import datetime
 
-# Step 1: Fetch stock data
+# Step 1: Fetch stock data from yfinance
 def fetch_stock_data(ticker, start_date, end_date):
     stock_data = yf.download(ticker, start=start_date, end=end_date)
     stock_data.reset_index(inplace=True)
@@ -46,46 +46,50 @@ def train_model(model, train_data, epochs=5):
     return model
 
 # Step 5: Predict future stock prices
-def predict_future(model, last_data, steps=90):
+def predict_future(model, last_data, scaler, steps=90):
     predictions = []
     input_data = last_data[-60:].reshape(1, -1)
-    
+
+    # Generate predictions for the future
     for _ in range(steps):
-        predicted_price = model.predict(input_data.reshape(1, 60, 1), verbose=0)
+        input_reshaped = input_data.reshape(1, 60, 1)
+        predicted_price = model.predict(input_reshaped, verbose=0)
         predictions.append(predicted_price[0][0])
         input_data = np.append(input_data[0][1:], predicted_price)
     
-    return predictions
+    predicted_prices = np.array(predictions).reshape(-1, 1)
+    predicted_prices = scaler.inverse_transform(predicted_prices)  # Reverse scaling
+    return predicted_prices
 
 # Step 6: Plot historical and predicted stock prices
-def plot_predictions(data, predicted_prices, scaler):
-    last_60_days = data['Close'][-60:].values.reshape(-1, 1)
-    predicted_prices = np.array(predicted_prices).reshape(-1, 1)
-    predicted_prices = scaler.inverse_transform(predicted_prices)
+def plot_predictions(data, predicted_prices):
+    last_60_days = data['Close'][-60:].values
 
-    # Create the plot
-    plt.figure(figsize=(14,6))
+    # Create a plot
+    plt.figure(figsize=(14, 6))
     
-    # Plot historical stock prices
+    # Plot historical prices
     plt.plot(data['Date'], data['Close'], label="Historical Prices", color='blue')
 
-    # Plot future predictions
-    future_dates = pd.date_range(start=data['Date'].iloc[-1], periods=len(predicted_prices)+1)[1:]
+    # Future dates for predicted prices
+    future_dates = pd.date_range(start=data['Date'].iloc[-1], periods=len(predicted_prices) + 1, freq='D')[1:]
+    
+    # Plot predicted prices
     plt.plot(future_dates, predicted_prices, label="Predicted Prices", color='orange')
 
     plt.title("Stock Price Prediction")
     plt.xlabel("Date")
-    plt.ylabel("Stock Price")
+    plt.ylabel("Stock Price (USD)")
     plt.legend()
     plt.grid()
 
-    # Save plot to file to ensure consistent rendering
+    # Save the plot to a file for Gradio to display
     plt.savefig("stock_prediction.png")
-    plt.close()  # Clear the plot to avoid overlap
+    plt.close()
     
-    return "stock_prediction.png"  # Return the file path for Gradio to display
+    return "stock_prediction.png"  # Return the file path for Gradio
 
-# Step 7: Gradio Interface Function
+# Step 7: Gradio interface function
 def stock_prediction_app(ticker, start_date_str, end_date_str):
     # Convert date strings to datetime objects
     start_date = datetime.strptime(start_date_str, "%Y-%m-%d").date()
@@ -101,18 +105,18 @@ def stock_prediction_app(ticker, start_date_str, end_date_str):
     model = build_model((60, 1))
     model = train_model(model, scaled_data)
     
-    # Predict future prices for the next 90 days
-    predicted_prices = predict_future(model, scaled_data)
+    # Predict future stock prices for the next 90 days
+    predicted_prices = predict_future(model, scaled_data, scaler)
     
-    # Plot historical and predicted prices
-    plot_path = plot_predictions(data, predicted_prices, scaler)
+    # Plot historical and predicted stock prices
+    plot_path = plot_predictions(data, predicted_prices)
     
-    return plot_path
+    return plot_path  # Return the plot file path
 
-# Step 8: Gradio UI Setup
+# Step 8: Gradio UI setup
 tickers = ["AAPL", "GOOGL", "MSFT", "AMZN", "TSLA", "META", "NFLX", "NVDA", "BABA", "BA"]
 
-# Create the Gradio interface using updated components
+# Define the Gradio interface
 ui = gr.Interface(
     fn=stock_prediction_app,
     inputs=[
@@ -120,10 +124,11 @@ ui = gr.Interface(
         gr.Textbox(label="Start Date (YYYY-MM-DD)"),
         gr.Textbox(label="End Date (YYYY-MM-DD)")
     ],
-    outputs=gr.Image(type="filepath"),  # Return the image file path (fixed here)
+    outputs=gr.Image(type="filepath"),  # Return the image file path for the plot
     title="Stock Prediction App",
     description="Select a stock ticker and date range to predict future prices."
 )
 
 # Launch the app
 ui.launch()
+