feat: Add time interval resampling to stock data fetching

src/utils/data_utils.py

@@ -61,30 +61,24 @@ def save_signals_to_csv(signals: list, scanner_name: str) -> None:
 
 def get_stock_data(ticker: str, start_date: datetime, end_date: datetime, interval: str) -> pd.DataFrame:
     """
-    Fetch stock data from the database with enhanced fallback logic
+    Fetch and resample stock data based on the chosen interval
     
     Args:
         ticker (str): Stock ticker symbol
         start_date (datetime): Start date for data fetch
         end_date (datetime): End date for data fetch
-        interval (str): Time interval for data ('daily', '5min', etc.)
+        interval (str): Time interval for data ('daily', '5min', '15min', '30min', '1hour')
         
     Returns:
-        pd.DataFrame: DataFrame with OHLCV data
+        pd.DataFrame: Resampled DataFrame with OHLCV data
     """
     try:
         client = create_client()
         
-        # Expand window to 90 days for more data robustness
+        # Expand window to get enough data for calculations
         start_date = start_date - timedelta(days=90)
         
-        # First try primary data source
+        # Base query to get raw data at finest granularity
-        if interval == "daily":
-            table = "stock_prices_daily"
-        else:
-            table = "stock_prices"
-        
-        # Unified query format
         query = f"""
             SELECT 
                 toDateTime(window_start/1000000000) as date,
@@ -104,50 +98,10 @@ def get_stock_data(ticker: str, start_date: datetime, end_date: datetime, interv
         
         result = client.query(query)
         
-        # Fallback to intraday data if needed
-        if not result.result_rows and interval == "daily":
-            print(f"⚠️ No daily data for {ticker}, resampling from intraday data")
-            intraday_query = f"""
-                SELECT
-                    toDateTime(window_start/1000000000) as date,
-                    first_value(open) AS open,
-                    max(high) AS high,
-                    min(low) AS low,
-                    last_value(close) AS close,
-                    sum(volume) AS volume
-                FROM stock_db.stock_prices
-                WHERE ticker = '{ticker}'
-                AND window_start BETWEEN 
-                    {int(start_date.timestamp() * 1e9)} AND 
-                    {int(end_date.timestamp() * 1e9)}
-                AND toYear(toDateTime(window_start/1000000000)) <= toYear(now())
-                AND toYear(toDateTime(window_start/1000000000)) >= (toYear(now()) - 1)
-                GROUP BY date
-                ORDER BY date ASC
-            """
-            result = client.query(intraday_query)
-            
-        # Fallback to different intervals if still empty    
-        if not result.result_rows:
-            print(f"⚠️ No {interval} data for {ticker}, trying weekly")
-            weekly_query = f"""
-                SELECT
-                    toStartOfWeek(window_start) AS date,
-                    first_value(open) AS open,
-                    max(high) AS high,
-                    min(low) AS low,
-                    last_value(close) AS close,
-                    sum(volume) AS volume
-                FROM stock_db.stock_prices
-                WHERE ticker = '{ticker}'
-                GROUP BY date
-                ORDER BY date ASC
-            """
-            result = client.query(weekly_query)
-            
         if not result.result_rows:
             return pd.DataFrame()
             
+        # Create base DataFrame
         df = pd.DataFrame(
             result.result_rows,
             columns=['date', 'open', 'high', 'low', 'close', 'volume']
@@ -158,18 +112,50 @@ def get_stock_data(ticker: str, start_date: datetime, end_date: datetime, interv
         for col in numeric_columns:
             df[col] = pd.to_numeric(df[col], errors='coerce')
 
+        # Convert date column
+        df['date'] = pd.to_datetime(df['date'])
+        
+        # Set date as index for resampling
+        df.set_index('date', inplace=True)
+        
+        # Resample based on interval
+        if interval == 'daily':
+            rule = '1D'
+        elif interval == '5min':
+            rule = '5T'
+        elif interval == '15min':
+            rule = '15T'
+        elif interval == '30min':
+            rule = '30T'
+        elif interval == '1hour':
+            rule = '1H'
+        else:
+            rule = '1D'  # Default to daily
+            
+        resampled = df.resample(rule).agg({
+            'open': 'first',
+            'high': 'max',
+            'low': 'min',
+            'close': 'last',
+            'volume': 'sum'
+        }).dropna()
+        
+        # Reset index to get date as column
+        resampled.reset_index(inplace=True)
+        
+        # Filter to requested date range
+        mask = (resampled['date'] >= start_date + timedelta(days=89)) & (resampled['date'] <= end_date)
+        resampled = resampled.loc[mask]
+        
         # Handle null values
-        if df['close'].isnull().any():
+        if resampled['close'].isnull().any():
             print(f"Warning: Found null values in close prices")
-            df = df.dropna(subset=['close'])
+            resampled = resampled.dropna(subset=['close'])
 
-        if df.empty or 'close' not in df.columns:
+        if resampled.empty or 'close' not in resampled.columns:
             return pd.DataFrame()
             
-        if df['date'].dtype == object:
+        return resampled
-            df['date'] = pd.to_datetime(df['date'])
-            
-        return df
 
     except Exception as e:
         print(f"Error fetching {ticker} data: {str(e)}")