feat: Enhance stock screening with daily data filtering and intraday validation

src/screener/t_sunnyband.py

@@ -31,7 +31,6 @@ def get_stock_data(ticker: str, start_date: datetime, end_date: datetime, interv
     """Fetch stock data from the database"""
     client = create_client()
     
-    # Select appropriate table based on interval
     if interval == "daily":
         table = "stock_prices_daily"
         date_col = "date"
@@ -59,19 +58,20 @@ def get_stock_data(ticker: str, start_date: datetime, end_date: datetime, interv
         }
         minutes = minutes_map[interval]
         
+        # Get 5-minute bars and resample them to the desired interval
         query = f"""
             SELECT 
-                fromUnixTimestamp({date_col}) as date,
+                fromUnixTimestamp(intDiv({date_col}, 300) * 300) as interval_start,
-                open,
+                min(open) as open,
-                high,
+                max(high) as high,
-                low,
+                min(low) as low,
-                close,
+                argMax(close, {date_col}) as close,
-                volume
+                sum(volume) as volume
             FROM stock_db.{table}
             WHERE ticker = '{ticker}'
             AND {date_col} BETWEEN toUnixTimestamp('{start_date.date()}') AND toUnixTimestamp('{end_date.date()}')
-            AND (toMinute(fromUnixTimestamp({date_col})) % {minutes}) = 0
+            GROUP BY interval_start
-            ORDER BY date ASC
+            ORDER BY interval_start ASC
         """
     
     try:
@@ -84,6 +84,23 @@ def get_stock_data(ticker: str, start_date: datetime, end_date: datetime, interv
             result.result_rows,
             columns=['date', 'open', 'high', 'low', 'close', 'volume']
         )
+        
+        if interval != "daily" and interval != "5min":
+            # Resample to desired interval
+            df.set_index('date', inplace=True)
+            minutes = minutes_map[interval]
+            rule = f'{minutes}T'
+            
+            df = df.resample(rule).agg({
+                'open': 'first',
+                'high': 'max',
+                'low': 'min',
+                'close': 'last',
+                'volume': 'sum'
+            }).dropna()
+            
+            df.reset_index(inplace=True)
+            
         return df
     except Exception as e:
         print(f"Error fetching data for {ticker}: {str(e)}")
@@ -93,34 +110,43 @@ def get_valid_tickers(min_price: float, max_price: float, min_volume: int, inter
     """Get tickers that meet the price and volume criteria"""
     client = create_client()
     yesterday = (datetime.now() - timedelta(days=1)).date()
-    today = datetime.now().date()
     
-    if interval == "daily":
+    # First get valid tickers from daily data
-        table = "stock_prices_daily"
+    daily_query = f"""
-        date_col = "date"
-        date_condition = f"{date_col} = '{yesterday}'"
-    else:
-        table = "stock_prices"
-        date_col = "window_start"
-        # Get today's trading hours timestamp range (9:30 AM to 4:00 PM EST)
-        market_open = int(datetime.combine(today, datetime.strptime("09:30", "%H:%M").time()).timestamp())
-        market_close = int(datetime.combine(today, datetime.strptime("16:00", "%H:%M").time()).timestamp())
-        date_condition = f"{date_col} BETWEEN {market_open} AND {market_close}"
-    
-    query = f"""
         SELECT DISTINCT ticker
-        FROM stock_db.{table}
+        FROM stock_db.stock_prices_daily
-        WHERE {date_condition}
+        WHERE date = '{yesterday}'
         AND close BETWEEN {min_price} AND {max_price}
         AND volume >= {min_volume}
         ORDER BY ticker ASC
     """
     
     try:
-        result = client.query(query)
+        result = client.query(daily_query)
         tickers = [row[0] for row in result.result_rows]
-        print(f"Found {len(tickers)} stocks matching price and volume criteria")
+        print(f"\nFound {len(tickers)} stocks matching price and volume criteria")
+        
+        if interval != "daily":
+            # Now verify these tickers have intraday data today
+            today = datetime.now().date()
+            market_open = int(datetime.combine(today, datetime.strptime("09:30", "%H:%M").time()).timestamp())
+            market_close = int(datetime.combine(today, datetime.strptime("16:00", "%H:%M").time()).timestamp())
+            
+            intraday_query = f"""
+                SELECT DISTINCT ticker
+                FROM stock_db.stock_prices
+                WHERE ticker IN ({','.join([f"'{t}'" for t in tickers])})
+                AND window_start BETWEEN {market_open} AND {market_close}
+                GROUP BY ticker
+                HAVING count() >= 10  -- Ensure we have enough data points
+            """
+            
+            result = client.query(intraday_query)
+            tickers = [row[0] for row in result.result_rows]
+            print(f"Of those, {len(tickers)} have recent intraday data")
+            
         return tickers
+        
     except Exception as e:
         print(f"Error fetching tickers: {str(e)}")
         return []