Update app.py

app.py

@@ -44,38 +44,61 @@ SEQ_LENGTH = 60  # Should match your training
 
 def fetch_stock_data(ticker, days=365):
     """
-    Load stock data from a local CSV file in the root folder.
-    Automatically detects 'Date' and 'Close' columns (case-insensitive).
+    Fetch stock data from a local CSV (handles multi-row headers)
+    or downloads from Yahoo Finance if not found.
+    Returns last `days` of data with standardized 'Price' column.
     """
     try:
         filename = f"{ticker.upper()}.csv"
         file_path = os.path.join(os.getcwd(), filename)
 
-        if not os.path.exists(file_path):
-            return None, f"Dataset file not found in root folder: {filename}"
+        # ✅ Load local dataset if it exists
+        if os.path.exists(file_path):
+            print(f"📂 Loading local dataset: {filename}")
 
-        df = pd.read_csv(file_path)
-        df.columns = [col.strip().lower() for col in df.columns]  # normalize column names
+            # Try reading while skipping bad header rows
+            df = pd.read_csv(file_path, skiprows=2)  # skip first two rows ("Ticker", "Date" lines)
+            df.rename(columns=lambda c: c.strip().lower(), inplace=True)
 
-        # Try to identify date and close columns
+            if 'date' not in df.columns:
+                # Maybe pandas treated first column as unnamed
+                df.rename(columns={df.columns[0]: 'date'}, inplace=True)
+
+        else:
+            print(f"🌐 Downloading {ticker} data from Yahoo Finance...")
+            end_date = datetime.now()
+            start_date = end_date - timedelta(days=days * 2)
+            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.to_csv(file_path)
+            print(f"💾 Saved downloaded dataset to: {file_path}")
+            df.reset_index(inplace=True)
+            df.rename(columns=lambda c: c.strip().lower(), inplace=True)
+
+        # ✅ Identify columns
         date_col = next((c for c in df.columns if 'date' in c or 'time' in c), None)
         close_col = next((c for c in df.columns if 'close' in c), None)
+        price_col = 'price' if 'price' in df.columns else close_col
 
-        if not date_col or not close_col:
-            return None, f"File must contain a date-like and close-like column in {filename}"
+        if not date_col or not price_col:
+            return None, f"Could not detect date or price/close column in {filename}"
 
-        # Convert to datetime and set index
-        df[date_col] = pd.to_datetime(df[date_col])
+        # ✅ Clean up and format
+        df[date_col] = pd.to_datetime(df[date_col], errors='coerce')
+        df.dropna(subset=[date_col, price_col], inplace=True)
         df.set_index(date_col, inplace=True)
         df.sort_index(inplace=True)
 
-        # Keep last `days`
+        # ✅ Keep last `days` of data
         end_date = df.index.max()
         start_date = end_date - timedelta(days=days)
         df = df.loc[df.index >= start_date]
 
-        # Keep only close price
-        df = df[[close_col]].copy()
+        # ✅ Final column cleanup
+        df = df[[price_col]].copy()
         df.columns = ['Price']
 
         return df, None
@@ -83,7 +106,6 @@ def fetch_stock_data(ticker, days=365):
     except Exception as e:
         return None, str(e)
 
-
 def make_arima_forecast(data, days):
     """Make ARIMA forecast"""
     try: