update cron job

app/cron_options_net_flow.py

@@ -24,82 +24,81 @@ def calculate_moving_average(data, window_size):
     moving_avg = (cumsum[window_size - 1:] - np.concatenate(([0], cumsum[:-window_size]))) / window_size
     return moving_avg.tolist()
 
-def calculate_net_flow(data, window_size=20):
-    date_data = defaultdict(lambda: {'price': [], 'netCall': 0, 'netPut': 0})
 
+def calculate_net_flow(data):
+    date_data = defaultdict(lambda: {'price': [], 'netCall': 0, 'netPut': 0})
     for item in data:
-        date = item['date']
+        date_str = item['date']
+        time_str = item['time']
+        datetime_str = f"{date_str} {time_str}"
+        
+        # Parse the combined date and time into a datetime object
+        date_time = datetime.strptime(datetime_str, '%Y-%m-%d %H:%M:%S')
+        
         try:
             premium = float(item['cost_basis'])
-            date_data[date]['price'].append(float(item['underlying_price']))
+            date_data[date_time]['price'].append(round(float(item['underlying_price']), 2))
-            #date_data[date]['volume'] += volume
-
             if item['put_call'] == 'CALL':
                 if item['execution_estimate'] == 'AT_ASK':
-                    date_data[date]['netCall'] += premium
+                    date_data[date_time]['netCall'] += premium
                 elif item['execution_estimate'] == 'AT_BID':
-                    date_data[date]['netCall'] -= premium
+                    date_data[date_time]['netCall'] -= premium
             elif item['put_call'] == 'PUT':
                 if item['execution_estimate'] == 'AT_ASK':
-                    date_data[date]['netPut'] -= premium
+                    date_data[date_time]['netPut'] -= premium
                 elif item['execution_estimate'] == 'AT_BID':
-                    date_data[date]['netPut'] += premium
+                    date_data[date_time]['netPut'] += premium
         except:
             pass
-            #volume = int(item['volume'])
 
     # Calculate average underlying price and format the results
     result = []
-    for date, values in date_data.items():
+    for date_time, values in date_data.items():
-        avg_price = sum(values['price']) / len(values['price'])
-        #volume = values['volume']
-
-        # Change sign of volume if netPut > netCall
-        #if values['netPut'] > values['netCall']:
-        #    volume = -volume
-
         result.append({
-            'date': date,
+            'date': date_time.strftime('%Y-%m-%d %H:%M:%S'),
-            'price': round(avg_price, 2),
+            'price': sum(values['price']) / len(values['price']) if values['price'] else 0,
             'netCall': int(values['netCall']),
             'netPut': int(values['netPut']),
-            #'volume': int(volume)
         })
-    sorted_data = sorted(result, key=lambda x: datetime.strptime(x['date'], '%Y-%m-%d'))
 
+    sorted_data = sorted(result, key=lambda x: datetime.strptime(x['date'], '%Y-%m-%d %H:%M:%S'))
 
-    # Calculate moving averages
+    # Compute 30-minute interval averages
-    netCall_values = [item['netCall'] for item in sorted_data]
+    interval_data = defaultdict(lambda: {'price': [], 'netCall': [], 'netPut': []})
-    netPut_values = [item['netPut'] for item in sorted_data]
+    for item in sorted_data:
+        date_time = datetime.strptime(item['date'], '%Y-%m-%d %H:%M:%S')
+        interval_start = date_time.replace(minute=date_time.minute // 120 * 120, second=0)
         
-    netCall_ma = calculate_moving_average(netCall_values, window_size)
+        interval_data[interval_start]['price'].append(item['price'])
-    netPut_ma = calculate_moving_average(netPut_values, window_size)
+        interval_data[interval_start]['netCall'].append(item['netCall'])
+        interval_data[interval_start]['netPut'].append(item['netPut'])
 
-    # Add moving averages to the result and remove None values
+    # Calculate averages for each 30-minute interval
-    filtered_data = []
+    averaged_data = []
-
+    for interval_start, values in interval_data.items():
-    # Add moving averages to the result
+        if values['price']:
-    filtered_data = []
+            averaged_data.append({
-    for i, item in enumerate(sorted_data):
+                'date': interval_start.strftime('%Y-%m-%d %H:%M:%S'),
-        if i >= window_size - 1:
+                #'price': sum(values['price']) / len(values['price']) ,
-            item['netCall'] = int(netCall_ma[i - window_size + 1])
+                'netCall': sum(values['netCall']) if values['netCall'] else 0,
-            item['netPut'] = int(netPut_ma[i - window_size + 1])
+                'netPut': sum(values['netPut']) if values['netPut'] else 0,
-            filtered_data.append(item)
+            })
-
-    return filtered_data
 
+    # Sort the averaged data by interval start time
+    averaged_data.sort(key=lambda x: datetime.strptime(x['date'], '%Y-%m-%d %H:%M:%S'))
 
+    return averaged_data
 
 def get_data(symbol):
     try:
         end_date = date.today()
-        start_date = end_date - timedelta(200)
+        start_date = end_date - timedelta(10)
 
         end_date_str = end_date.strftime('%Y-%m-%d')
         start_date_str = start_date.strftime('%Y-%m-%d')
 
         res_list = []
-        for page in range(0, 100):
+        for page in range(0, 1000):
             try:
                 data = fin.options_activity(company_tickers=symbol, page=page, pagesize=1000, date_from=start_date_str, date_to=end_date_str)
                 data = ujson.loads(fin.output(data))['option_activity']
@@ -107,8 +106,7 @@ def get_data(symbol):
             except:
                 break
 
-        res_filtered = [{key: value for key, value in item.items() if key in ['ticker','date','execution_estimate', 'underlying_price', 'put_call', 'cost_basis']} for item in res_list]
+        res_filtered = [{key: value for key, value in item.items() if key in ['ticker','time','date','execution_estimate', 'underlying_price', 'put_call', 'cost_basis']} for item in res_list]
-
         
         #Save raw data for each ticker for options page stack bar chart
         ticker_filtered_data = [entry for entry in res_filtered if entry['ticker'] == symbol]
@@ -126,7 +124,7 @@ def get_data(symbol):
 try:
     stock_con = sqlite3.connect('stocks.db')
     stock_cursor = stock_con.cursor()
-    stock_cursor.execute("SELECT DISTINCT symbol FROM stocks WHERE symbol NOT LIKE '%.%'")
+    stock_cursor.execute("SELECT DISTINCT symbol FROM stocks WHERE marketCap >500E6 AND symbol NOT LIKE '%.%'")
     stock_symbols = [row[0] for row in stock_cursor.fetchall()]
 
     etf_con = sqlite3.connect('etf.db')