Update app.py

app.py

@@ -10,6 +10,8 @@ from prophet import Prophet
 from tensorflow import keras
 from sklearn.preprocessing import MinMaxScaler
 import warnings
+import os
+from datetime import datetime, timedelta
 warnings.filterwarnings('ignore')
 
 # Load your saved models (update paths as needed)
@@ -39,20 +41,54 @@ def load_models():
 arima_model, prophet_model, lstm_model, scaler = load_models()
 SEQ_LENGTH = 60  # Should match your training
 
+
 def fetch_stock_data(ticker, days=365):
-    """Fetch stock data from Yahoo Finance"""
+    """
+    Load stock data from a local CSV file in the project root folder.
+    If the file doesn't exist, returns an error message.
+
+    Parameters:
+        ticker (str): Stock ticker symbol (used as filename prefix)
+        days (int): Number of days of recent data to keep (optional)
+
+    Returns:
+        tuple: (DataFrame, error_message)
+    """
     try:
-        end_date = datetime.now()
+        # Construct the file path (e.g., ./AAPL.csv)
+        filename = f"{ticker.upper()}.csv"
+        file_path = os.path.join(os.getcwd(), filename)
+
+        # Check if file exists
+        if not os.path.exists(file_path):
+            return None, f"Dataset file not found in root folder: {filename}"
+
+        # Load dataset
+        df = pd.read_csv(file_path)
+
+        # Ensure 'Date' and 'Close' columns exist
+        if 'Date' not in df.columns or 'Close' not in df.columns:
+            return None, f"File must contain 'Date' and 'Close' columns in {filename}"
+
+        # Parse dates and set index
+        df['Date'] = pd.to_datetime(df['Date'])
+        df.set_index('Date', inplace=True)
+
+        # Keep only recent `days`
+        end_date = df.index.max()
         start_date = end_date - timedelta(days=days)
-        df = yf.download(ticker, start=start_date, end=end_date, progress=False)
-        if df.empty:
-            return None, f"No data found for ticker: {ticker}"
+        df = df.loc[df.index >= start_date]
+
+        # Rename column for consistency
         df = df[['Close']].copy()
         df.columns = ['Price']
+
         return df, None
+
     except Exception as e:
         return None, str(e)
 
+
 def make_arima_forecast(data, days):
     """Make ARIMA forecast"""
     try: