generated from user_client2024/58
409 lines
14 KiB
Plaintext
409 lines
14 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 21,
|
||
"id": "e706cfb0-2234-4c4c-95d8-d1968f656aa0",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"from datetime import datetime, timedelta\n",
|
||
"import pandas as pd\n",
|
||
"from tms_data_interface import SQLQueryInterface\n",
|
||
"\n",
|
||
"query = \"\"\"\n",
|
||
"SELECT \n",
|
||
" n.TRADER_ID,\n",
|
||
" n.trade_time_window,\n",
|
||
" n.net_volume,\n",
|
||
" n.order_count, -- Include number of orders\n",
|
||
" COALESCE(t.total_trade_volume, 0) AS total_trade_volume,\n",
|
||
" CASE \n",
|
||
" WHEN COALESCE(t.total_trade_volume, 0) > 0 THEN n.net_volume / t.total_trade_volume\n",
|
||
" ELSE 0 -- or another value to indicate no trades\n",
|
||
" END AS order_trade_ratio,\n",
|
||
" CASE \n",
|
||
" WHEN net_volume_all.total_net_volume_all > 0 THEN \n",
|
||
" (n.net_volume / net_volume_all.total_net_volume_all) * 100 \n",
|
||
" ELSE 0 \n",
|
||
" END AS volume_percentage -- Calculate volume percentage\n",
|
||
"FROM (\n",
|
||
" -- Step 2: Subquery for net_order_volume\n",
|
||
" SELECT \n",
|
||
" o.TRADER_ID,\n",
|
||
" t.DATE_TIME AS trade_time_window,\n",
|
||
" SUM(CASE \n",
|
||
" WHEN o.ORDER_STATUS = 'New' THEN o.ORDER_VOLUME\n",
|
||
" WHEN o.ORDER_STATUS = 'Cancelled' THEN -o.ORDER_VOLUME\n",
|
||
" WHEN o.ORDER_STATUS = 'Fulfilled' THEN -o.ORDER_VOLUME\n",
|
||
" ELSE 0 END\n",
|
||
" ) AS net_volume,\n",
|
||
" COUNT(o.ORDER_ID) AS order_count -- Count the number of orders\n",
|
||
" FROM {order_10m} o\n",
|
||
" JOIN {trade_data_1b} t\n",
|
||
" ON o.TRADER_ID = t.TRADER_ID\n",
|
||
" WHERE o.SIDE = 'buy'\n",
|
||
" AND o.DATE_TIME BETWEEN t.DATE_TIME - INTERVAL '{time_window_s}' SECOND AND t.DATE_TIME\n",
|
||
" GROUP BY o.TRADER_ID, t.DATE_TIME\n",
|
||
") AS n\n",
|
||
"LEFT JOIN (\n",
|
||
" -- Step 6: Subquery for total_trade_volume (opposite side trades after spoofing)\n",
|
||
" SELECT \n",
|
||
" t.TRADER_ID,\n",
|
||
" t.DATE_TIME,\n",
|
||
" SUM(t.TRADE_VOLUME) AS total_trade_volume\n",
|
||
" FROM (\n",
|
||
" -- Step 5: Subquery for relevant_trades\n",
|
||
" SELECT t1.*\n",
|
||
" FROM {trade_data_1b} t1\n",
|
||
" WHERE t1.TRADE_SIDE = 'buy'\n",
|
||
" AND EXISTS (\n",
|
||
" SELECT 1\n",
|
||
" FROM {trade_data_1b} t2\n",
|
||
" WHERE t2.TRADER_ID = t1.TRADER_ID\n",
|
||
" AND t2.DATE_TIME BETWEEN t1.DATE_TIME - INTERVAL '{time_window_s}' SECOND AND t1.DATE_TIME\n",
|
||
" )\n",
|
||
" ) AS t\n",
|
||
" GROUP BY t.DATE_TIME, t.TRADER_ID\n",
|
||
") AS t \n",
|
||
"ON n.TRADER_ID = t.TRADER_ID AND n.trade_time_window = t.DATE_TIME\n",
|
||
"\n",
|
||
"-- New subquery for total net volume for all traders in the same time window\n",
|
||
"LEFT JOIN (\n",
|
||
" SELECT \n",
|
||
" t.DATE_TIME AS trade_time_window,\n",
|
||
" SUM(CASE \n",
|
||
" WHEN o.ORDER_STATUS = 'New' THEN o.ORDER_VOLUME\n",
|
||
" WHEN o.ORDER_STATUS = 'Cancelled' THEN -o.ORDER_VOLUME\n",
|
||
" WHEN o.ORDER_STATUS = 'Fulfilled' THEN -o.ORDER_VOLUME\n",
|
||
" ELSE 0 END\n",
|
||
" ) AS total_net_volume_all\n",
|
||
" FROM {order_10m} o\n",
|
||
" JOIN {trade_data_1b} t\n",
|
||
" ON o.TRADER_ID = t.TRADER_ID\n",
|
||
" WHERE o.SIDE = 'buy'\n",
|
||
" AND o.DATE_TIME BETWEEN t.DATE_TIME - INTERVAL '{time_window_s}' SECOND AND t.DATE_TIME\n",
|
||
" GROUP BY t.DATE_TIME\n",
|
||
") AS net_volume_all\n",
|
||
"ON n.trade_time_window = net_volume_all.trade_time_window\n",
|
||
"\n",
|
||
"ORDER BY n.trade_time_window\n",
|
||
"\"\"\"\n",
|
||
"\n",
|
||
"\n",
|
||
"from tms_data_interface import SQLQueryInterface\n",
|
||
"\n",
|
||
"class Scenario:\n",
|
||
" seq = SQLQueryInterface(schema=\"trade_schema\")\n",
|
||
" def logic(self, **kwargs):\n",
|
||
" validation_window = kwargs.get('validation_window')\n",
|
||
" spoofing_side = kwargs.get('buy')\n",
|
||
" time_window_s = int(validation_window/1000)\n",
|
||
" query_start_time = datetime.now()\n",
|
||
" print(\"Query start time :\",query_start_time)\n",
|
||
" row_list = self.seq.execute_raw(query.format(trade_data_1b=\"trade_10m_v3\",\n",
|
||
" order_10m = 'order_10m',\n",
|
||
" time_window_s = time_window_s)\n",
|
||
" )\n",
|
||
" cols = [\n",
|
||
" 'Focal_id',\n",
|
||
" 'trade_time_window',\n",
|
||
" 'net_volume',\n",
|
||
" 'order_count',\n",
|
||
" 'total_trade_volume',\n",
|
||
" 'order_trade_ratio',\n",
|
||
" 'volume_percentage'\n",
|
||
" ]\n",
|
||
" final_scenario_df = pd.DataFrame(row_list, columns = cols)\n",
|
||
" final_scenario_df['Segment'] = 'Default'\n",
|
||
" final_scenario_df['SAR_FLAG'] = 'N'\n",
|
||
" final_scenario_df['Risk'] = 'Low Risk'\n",
|
||
" final_scenario_df.dropna(inplace=True)\n",
|
||
" # final_scenario_df['RUN_DATE'] = final_scenario_df['END_DATE']\n",
|
||
" return final_scenario_df\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 22,
|
||
"id": "b5c4307f-bc35-47e2-b680-fd1df2168d6c",
|
||
"metadata": {
|
||
"tags": []
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Query start time : 2024-10-14 07:40:43.846637\n"
|
||
]
|
||
},
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"<div>\n",
|
||
"<style scoped>\n",
|
||
" .dataframe tbody tr th:only-of-type {\n",
|
||
" vertical-align: middle;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe tbody tr th {\n",
|
||
" vertical-align: top;\n",
|
||
" }\n",
|
||
"\n",
|
||
" .dataframe thead th {\n",
|
||
" text-align: right;\n",
|
||
" }\n",
|
||
"</style>\n",
|
||
"<table border=\"1\" class=\"dataframe\">\n",
|
||
" <thead>\n",
|
||
" <tr style=\"text-align: right;\">\n",
|
||
" <th></th>\n",
|
||
" <th>focal_ID</th>\n",
|
||
" <th>trade_time_window</th>\n",
|
||
" <th>net_volume</th>\n",
|
||
" <th>order_count</th>\n",
|
||
" <th>total_trade_volume</th>\n",
|
||
" <th>order_trade_ratio</th>\n",
|
||
" <th>volume_percentage</th>\n",
|
||
" <th>Segment</th>\n",
|
||
" <th>SAR_FLAG</th>\n",
|
||
" <th>Risk</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>3097728207</td>\n",
|
||
" <td>2024-01-01 00:03:00</td>\n",
|
||
" <td>-92.0</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>92</td>\n",
|
||
" <td>-1.0</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" <td>Default</td>\n",
|
||
" <td>N</td>\n",
|
||
" <td>Low Risk</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>3228645322</td>\n",
|
||
" <td>2024-01-01 00:06:00</td>\n",
|
||
" <td>-689.0</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>689</td>\n",
|
||
" <td>-1.0</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" <td>Default</td>\n",
|
||
" <td>N</td>\n",
|
||
" <td>Low Risk</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>2701872727</td>\n",
|
||
" <td>2024-01-01 00:09:00</td>\n",
|
||
" <td>-42.0</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>42</td>\n",
|
||
" <td>-1.0</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" <td>Default</td>\n",
|
||
" <td>N</td>\n",
|
||
" <td>Low Risk</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>1659056655</td>\n",
|
||
" <td>2024-01-01 00:11:00</td>\n",
|
||
" <td>-167.0</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>167</td>\n",
|
||
" <td>-1.0</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" <td>Default</td>\n",
|
||
" <td>N</td>\n",
|
||
" <td>Low Risk</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>1661288887</td>\n",
|
||
" <td>2024-01-01 00:13:00</td>\n",
|
||
" <td>-756.0</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>756</td>\n",
|
||
" <td>-1.0</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" <td>Default</td>\n",
|
||
" <td>N</td>\n",
|
||
" <td>Low Risk</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>...</th>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>95</th>\n",
|
||
" <td>1945772682</td>\n",
|
||
" <td>2024-01-01 00:43:00</td>\n",
|
||
" <td>-854.0</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>854</td>\n",
|
||
" <td>-1.0</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" <td>Default</td>\n",
|
||
" <td>N</td>\n",
|
||
" <td>Low Risk</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>96</th>\n",
|
||
" <td>2137478041</td>\n",
|
||
" <td>2024-01-01 00:43:00</td>\n",
|
||
" <td>-926.0</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>926</td>\n",
|
||
" <td>-1.0</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" <td>Default</td>\n",
|
||
" <td>N</td>\n",
|
||
" <td>Low Risk</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>97</th>\n",
|
||
" <td>7138329164</td>\n",
|
||
" <td>2024-01-01 00:43:00</td>\n",
|
||
" <td>-433.0</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>433</td>\n",
|
||
" <td>-1.0</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" <td>Default</td>\n",
|
||
" <td>N</td>\n",
|
||
" <td>Low Risk</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>98</th>\n",
|
||
" <td>1867007441</td>\n",
|
||
" <td>2024-01-01 00:43:00</td>\n",
|
||
" <td>-626.0</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>626</td>\n",
|
||
" <td>-1.0</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" <td>Default</td>\n",
|
||
" <td>N</td>\n",
|
||
" <td>Low Risk</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>99</th>\n",
|
||
" <td>2347906349</td>\n",
|
||
" <td>2024-01-01 00:43:00</td>\n",
|
||
" <td>-69.0</td>\n",
|
||
" <td>1</td>\n",
|
||
" <td>69</td>\n",
|
||
" <td>-1.0</td>\n",
|
||
" <td>0.0</td>\n",
|
||
" <td>Default</td>\n",
|
||
" <td>N</td>\n",
|
||
" <td>Low Risk</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"<p>100 rows × 10 columns</p>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" focal_ID trade_time_window net_volume order_count \\\n",
|
||
"0 3097728207 2024-01-01 00:03:00 -92.0 1 \n",
|
||
"1 3228645322 2024-01-01 00:06:00 -689.0 1 \n",
|
||
"2 2701872727 2024-01-01 00:09:00 -42.0 1 \n",
|
||
"3 1659056655 2024-01-01 00:11:00 -167.0 1 \n",
|
||
"4 1661288887 2024-01-01 00:13:00 -756.0 1 \n",
|
||
".. ... ... ... ... \n",
|
||
"95 1945772682 2024-01-01 00:43:00 -854.0 1 \n",
|
||
"96 2137478041 2024-01-01 00:43:00 -926.0 1 \n",
|
||
"97 7138329164 2024-01-01 00:43:00 -433.0 1 \n",
|
||
"98 1867007441 2024-01-01 00:43:00 -626.0 1 \n",
|
||
"99 2347906349 2024-01-01 00:43:00 -69.0 1 \n",
|
||
"\n",
|
||
" total_trade_volume order_trade_ratio volume_percentage Segment \\\n",
|
||
"0 92 -1.0 0.0 Default \n",
|
||
"1 689 -1.0 0.0 Default \n",
|
||
"2 42 -1.0 0.0 Default \n",
|
||
"3 167 -1.0 0.0 Default \n",
|
||
"4 756 -1.0 0.0 Default \n",
|
||
".. ... ... ... ... \n",
|
||
"95 854 -1.0 0.0 Default \n",
|
||
"96 926 -1.0 0.0 Default \n",
|
||
"97 433 -1.0 0.0 Default \n",
|
||
"98 626 -1.0 0.0 Default \n",
|
||
"99 69 -1.0 0.0 Default \n",
|
||
"\n",
|
||
" SAR_FLAG Risk \n",
|
||
"0 N Low Risk \n",
|
||
"1 N Low Risk \n",
|
||
"2 N Low Risk \n",
|
||
"3 N Low Risk \n",
|
||
"4 N Low Risk \n",
|
||
".. ... ... \n",
|
||
"95 N Low Risk \n",
|
||
"96 N Low Risk \n",
|
||
"97 N Low Risk \n",
|
||
"98 N Low Risk \n",
|
||
"99 N Low Risk \n",
|
||
"\n",
|
||
"[100 rows x 10 columns]"
|
||
]
|
||
},
|
||
"execution_count": 22,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"# scenario = Scenario()\n",
|
||
"# scenario.logic(validation_window=300000)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "36b1b24a-aeca-4d22-a2b3-6e04aca31695",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": "Python 3 (ipykernel)",
|
||
"language": "python",
|
||
"name": "python3"
|
||
},
|
||
"language_info": {
|
||
"codemirror_mode": {
|
||
"name": "ipython",
|
||
"version": 3
|
||
},
|
||
"file_extension": ".py",
|
||
"mimetype": "text/x-python",
|
||
"name": "python",
|
||
"nbconvert_exporter": "python",
|
||
"pygments_lexer": "ipython3",
|
||
"version": "3.11.8"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
}
|