Update app.py

app.py

@@ -10,7 +10,6 @@ from datetime import datetime, timedelta
 import joblib
 import os
 import re
-import matplotlib.dates as mdates
 
 # Define stock tickers
 STOCK_TICKERS = [
@@ -63,7 +62,7 @@ def preprocess_data(data: pd.DataFrame) -> (np.ndarray, np.ndarray):
     for i in range(1, 6):
         data[f'Close_{i}'] = data['Close'].shift(i)
 
-    # Example of adding a 7-day moving average
+    # Add a 7-day moving average
     data['MA_7'] = data['Close'].rolling(window=7).mean()
 
     # Drop rows with any NaN values
@@ -116,10 +115,12 @@ def make_prediction(model: RandomForestRegressor, recent_data: pd.DataFrame) ->
     # Use the last 5 days' close prices as features
     recent_close = recent_data['Close'].values[-5:]
     recent_ma7 = recent_data['MA_7'].values[-1]  # Latest 7-day moving average
+
+    # Prepare feature array
     if len(recent_close) < 5 or np.isnan(recent_ma7):
         raise ValueError("Not enough data to make a prediction.")
 
-    # Prepare feature array
+    # Prepare feature for the model
     X_new = np.append(recent_close[::-1], recent_ma7).reshape(1, -1)  # Reverse to match feature order
     predicted_price = model.predict(X_new)[0]
     return predicted_price
@@ -207,7 +208,7 @@ def stock_prediction_app(ticker: str, start_date: str, end_date: str):
     try:
         X, y = preprocess_data(data)
     except Exception as e:
-        return f"Error in preprocessing data: {e}", "N/A", "N/A", "Error", None
+        return f"Error in preprocessing data: {e}", highest_price, lowest_price, "Error", None
 
     if len(X) == 0:
         return f"{percentage_change:.2f}%", highest_price, lowest_price, "No Prediction", None
@@ -229,56 +230,48 @@ def stock_prediction_app(ticker: str, start_date: str, end_date: str):
     decision = buy_or_sell(current_price, predicted_price)
 
     # Plotting historical prices and predicted tomorrow's price
-    plt.figure(figsize=(12, 6))
-    plt.plot(data.index, data['Close'], label='Historical Close Price', color='blue')
+    plt.figure(figsize=(10,5))
+    plt.plot(data['Close'], label='Historical Close Price', color='blue')
 
     # Add predicted price for tomorrow
     tomorrow_date = data.index[-1] + timedelta(days=1)
     # Ensure tomorrow is a business day
-    while tomorrow_date.weekday() >= 5:  # Saturday=5, Sunday=6
+    while tomorrow_date.weekday() >= 5:  # Saturday or Sunday
         tomorrow_date += timedelta(days=1)
 
-    plt.scatter(tomorrow_date, predicted_price, color='red', label='Predicted Close Price (Tomorrow)', zorder=5)
-
-    # Formatting the x-axis with better date formatting
-    plt.gca().xaxis.set_major_locator(mdates.AutoDateLocator())
-    plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%Y-%m-%d'))
-    plt.xticks(rotation=45)
-
-    plt.title(f'{ticker} Price Prediction for Tomorrow')
+    plt.scatter(tomorrow_date, predicted_price, color='red', label='Predicted Price for Tomorrow', zorder=5)
+    plt.title(f'Stock Price Prediction for {ticker}')
     plt.xlabel('Date')
-    plt.ylabel('Price ($)')
+    plt.ylabel('Price')
+    plt.xticks(rotation=45)
     plt.legend()
-    plt.grid(True, linestyle='--', alpha=0.5)
-    plt.tight_layout()
+    plt.grid()
 
-    # Create the figure
-    fig = plt.gcf()
+    # Save plot to a file and return
+    plot_path = f'{ticker}_prediction_plot.png'
+    plt.savefig(plot_path)
     plt.close()
 
-    # Formatting outputs
-    percentage_change_str = f"{percentage_change:.2f}%"
-
-    return percentage_change_str, highest_price, lowest_price, decision, fig
+    return f"{percentage_change:.2f}%", highest_price, lowest_price, decision, plot_path
 
-# Define the Gradio interface
+# Gradio interface
 iface = gr.Interface(
     fn=stock_prediction_app,
     inputs=[
         gr.Dropdown(choices=STOCK_TICKERS, label="Select Stock Ticker"),
-        gr.Textbox(label="Enter Start Date (YYYY-MM-DD)", placeholder="e.g., 2020-01-01"),
-        gr.Textbox(label="Enter End Date (YYYY-MM-DD)", placeholder="e.g., 2023-09-30")
+        gr.Textbox(label="Start Date (YYYY-MM-DD)", placeholder="2023-01-01"),
+        gr.Textbox(label="End Date (YYYY-MM-DD)", placeholder="2023-10-01"),
     ],
     outputs=[
         gr.Textbox(label="Percentage Change"),
-        gr.Number(label="Highest Closing Price"),
-        gr.Number(label="Lowest Closing Price"),
+        gr.Number(label="Highest Price"),
+        gr.Number(label="Lowest Price"),
         gr.Textbox(label="Decision (Buy/Sell)"),
-        gr.Plot(label="Stock Performance")
+        gr.Image(label="Stock Price Prediction Plot"),
     ],
-    title="Stock Prediction App",
-    description="Predict whether to buy or sell a stock based on historical data. Please enter dates in YYYY-MM-DD format."
+    title="Stock Price Prediction App",
+    description="Predict stock prices and get buy/sell recommendations."
 )
 
-# Launch the interface
+# Launch the Gradio app
 iface.launch()