qatest/49
1
0
Fork 0
generated from dhairya/scenario_template
Code Issues Pull Requests Packages Projects Releases Wiki Activity

System save at 04/10/2024 15:13 by qatest

Browse Source
This commit is contained in:
qatest 2024-10-04 09:43:50 +00:00
parent 59dd7358e7
commit 0180f5a475
3 changed files with 404 additions and 291 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

239
.ipynb_checkpoints/main-checkpoint.ipynb
View File

@ -3,115 +3,158 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "a46db93d-3d4e-40cb-a1e3-8b6b43b57461", "id": "393f184e-6bc6-44d0-bf4f-89610f05c1dc",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1599a219-9bf4-49d5-aed4-db58f6810c26",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"from datetime import datetime, timedelta\n",
"import pandas as pd\n",
"from tms_data_interface import SQLQueryInterface\n", "from tms_data_interface import SQLQueryInterface\n",
"\n", "seq = SQLQueryInterface()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b1272d9b-3219-4785-a5ba-516a8cad02c3",
"metadata": {},
"outputs": [],
"source": [
"seq.execute_raw(\"show tables\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f7df9028-84c1-47dd-82e6-161238532686",
"metadata": {},
"outputs": [],
"source": [
"query = \"\"\"\n", "query = \"\"\"\n",
"WITH time_windows AS (\n", " select final.CUSTOMER_NUMBER_main as Focal_id,\n",
" SELECT\n", " final.Credit_transaction_amount,\n",
" -- End time is the current trade time\n", " final.Total_no_of_credit_transactions,\n",
" date_time AS end_time,\n", " final.Debit_transaction_amount,\n",
"\n", " final.Total_no_of_debit_transactions,\n",
" -- Subtract seconds from the end_time using date_add() with negative integer interval\n", " final.Wash_Ratio,\n",
" date_add('second', -{time_window_s}, date_time) AS start_time,\n", " final.SEGMENT,\n",
"\n", " final.RISK,\n",
" -- Trade details\n", " final.SAR_FLAG\n",
" trade_price,\n", " from \n",
" trade_volume,\n", " (\n",
" trader_id,\n", " (\n",
"\n", " select subquery.CUSTOMER_NUMBER_1 as CUSTOMER_NUMBER_main,\n",
" -- Calculate minimum price within the time window\n", " subquery.Credit_transaction_amount,\n",
" MIN(trade_price) OVER (\n", " subquery.Total_no_of_credit_transactions,\n",
" ORDER BY date_time \n", " case\n",
" RANGE BETWEEN INTERVAL '{time_window_s}' SECOND PRECEDING AND CURRENT ROW\n", " when subquery.Debit_transaction_amount is NULL then 0\n",
" ) AS min_price,\n", " else Debit_transaction_amount\n",
"\n", " end as Debit_transaction_amount,\n",
" -- Calculate maximum price within the time window\n", " case\n",
" MAX(trade_price) OVER (\n", " when subquery.Total_no_of_debit_transactions is NULL then 0\n",
" ORDER BY date_time \n", " else Total_no_of_debit_transactions\n",
" RANGE BETWEEN INTERVAL '{time_window_s}' SECOND PRECEDING AND CURRENT ROW\n", " end as Total_no_of_debit_transactions,\n",
" ) AS max_price,\n", " case\n",
"\n", " when subquery.Debit_transaction_amount = 0\n",
" -- Calculate total trade volume within the time window\n", " or subquery.Debit_transaction_amount is NULL then 0\n",
" SUM(trade_volume) OVER ( \n", " else subquery.Credit_transaction_amount / subquery.Debit_transaction_amount\n",
" ORDER BY date_time \n", " end as Wash_Ratio\n",
" RANGE BETWEEN INTERVAL '{time_window_s}' SECOND PRECEDING AND CURRENT ROW\n", " from \n",
" ) AS total_volume,\n", " (\n",
"\n", " (\n",
" -- Calculate participant's trade volume within the time window\n", " select customer_number as CUSTOMER_NUMBER_1, \n",
" SUM(CASE WHEN trader_id = trader_id THEN trade_volume ELSE 0 END) OVER (\n", " sum(transaction_amount) as Credit_transaction_amount, \n",
" PARTITION BY trader_id \n", " count(*) as Total_no_of_credit_transactions\n",
" ORDER BY date_time \n", " from \n",
" RANGE BETWEEN INTERVAL '{time_window_s}' SECOND PRECEDING AND CURRENT ROW\n", " (\n",
" ) AS participant_volume\n", " select * \n",
" FROM\n", " from {trans_data} as trans_table left join {acc_data} as acc_table\n",
" {trade_data_1b}\n", " on trans_table.benef_account_number = acc_table.account_number\n",
")\n", " )\n",
"SELECT\n", " where account_number not in ('None')\n",
" -- Select the time window details\n", " group by 1\n",
" start_time,\n", " ) credit left join\n",
" end_time,\n", " (\n",
"\n", " select customer_number as CUSTOMER_NUMBER_2, \n",
" -- Select the participant (trader) ID\n", " sum(transaction_amount) as Debit_transaction_amount, \n",
" trader_id AS \"Participant\",\n", " count(*) as Total_no_of_debit_transactions\n",
"\n", " from \n",
" -- Select the calculated min and max prices\n", " (\n",
" min_price,\n", " select * \n",
" max_price,\n", " from {trans_data} as trans_table left join {acc_data} as acc_table\n",
"\n", " on trans_table.orig_account_number = acc_table.account_number\n",
" -- Calculate the price change percentage\n", " )\n",
" (max_price - min_price) / NULLIF(min_price, 0) * 100 AS \"Price Change (%)\",\n", " where account_number not in ('None')\n",
"\n", " group by 1\n",
" -- Calculate the participant's volume as a percentage of total volume\n", " ) debit on credit.CUSTOMER_NUMBER_1 = debit.CUSTOMER_NUMBER_2 \n",
" (participant_volume / NULLIF(total_volume, 0)) * 100 AS \"Volume (%)\",\n", " ) subquery\n",
"\n", " ) main left join \n",
" -- Participant volume\n", " (\n",
" participant_volume,\n", " select subquery.CUSTOMER_NUMBER_3 as CUSTOMER_NUMBER_cust,\n",
"\n", " subquery.SEGMENT,\n",
" -- Select the total volume within the window\n", " subquery.RISK,\n",
" total_volume AS \"Total Volume\"\n", " case\n",
"FROM\n", " when subquery.SAR_FLAG is NULL then 'N'\n",
" time_windows\n", " else subquery.SAR_FLAG\n",
" end as SAR_FLAG \n",
" from\n",
" (\n",
" (\n",
" select customer_number as CUSTOMER_NUMBER_3, \n",
" business_segment as SEGMENT,\n",
" case\n",
" when RISK_CLASSIFICATION = 1 then 'Low Risk'\n",
" when RISK_CLASSIFICATION = 2 then 'Medium Risk'\n",
" when RISK_CLASSIFICATION = 3 then 'High Risk'\n",
" else 'Unknown Risk'\n",
" end AS RISK\n",
" from {cust_data}\n",
" ) cd left join\n",
" (\n",
" select customer_number as CUSTOMER_NUMBER_4, \n",
" sar_flag as SAR_FLAG\n",
" from {alert_data}\n",
" ) ad on cd.CUSTOMER_NUMBER_3 = ad.CUSTOMER_NUMBER_4\n",
" ) subquery\n",
" ) cust_alert on cust_alert.CUSTOMER_NUMBER_cust = main.CUSTOMER_NUMBER_main\n",
" ) final\n",
"\"\"\"\n", "\"\"\"\n",
"\n", "\n"
"\n", ]
},
{
"cell_type": "code",
"execution_count": null,
"id": "361ae64c-dc41-456d-93e4-f7d8b211dce4",
"metadata": {},
"outputs": [],
"source": [
"from tms_data_interface import SQLQueryInterface\n", "from tms_data_interface import SQLQueryInterface\n",
"\n", "\n",
"class Scenario:\n", "class Scenario:\n",
" seq = SQLQueryInterface(schema=\"qa_schema\")\n", " seq = SQLQueryInterface()\n",
"\n",
" def logic(self, **kwargs):\n", " def logic(self, **kwargs):\n",
" validation_window = kwargs.get('validation_window')\n", " row_list = self.seq.execute_raw(query.format(trans_data=\"trans_data_10mv5_latest\",\n",
" time_window_s = int(validation_window/1000)\n", " cust_data=\"customer_v1\",\n",
" query_start_time = datetime.now()\n", " acc_data=\"account_v1\",\n",
" print(\"Query start time :\",query_start_time)\n", " alert_data=\"alert_v1\")\n",
" row_list = self.seq.execute_raw(query.format(trade_data_1b=\"qa_table_test\",\n",
" time_window_s = time_window_s)\n",
" )\n", " )\n",
" cols = [\n", " cols = [\"Focal_id\", \"Credit_transaction_amount\",\n",
" 'START_DATE_TIME',\n", " \"Total_no_of_credit_transactions\",\n",
" 'END_DATE_TIME',\n", " \"Debit_transaction_amount\", \"Total_no_of_debit_transactions\",\n",
" 'Focal_id',\n", " \"Wash_Ratio\",\n",
" 'MIN_PRICE',\n", " \"Segment\", \"Risk\", \"SAR_FLAG\"]\n",
" 'MAX_PRICE',\n", " df = pd.DataFrame(row_list, columns = cols)\n",
" 'PRICE_CHANGE_PCT',\n", " return df"
" 'PARTICIPANT_VOLUME_PCT',\n",
" 'PARTICIPANT_VOLUME',\n",
" 'TOTAL_VOLUME',\n",
" ]\n",
" final_scenario_df = pd.DataFrame(row_list, columns = cols)\n",
" final_scenario_df['PARTICIPANT_VOLUME_PCT'] = final_scenario_df['PARTICIPANT_VOLUME']/\\\n",
" final_scenario_df['TOTAL_VOLUME'] * 100\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"
] ]
} }
], ],

239
main.ipynb
View File

@ -3,115 +3,158 @@
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "a46db93d-3d4e-40cb-a1e3-8b6b43b57461", "id": "393f184e-6bc6-44d0-bf4f-89610f05c1dc",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1599a219-9bf4-49d5-aed4-db58f6810c26",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"from datetime import datetime, timedelta\n",
"import pandas as pd\n",
"from tms_data_interface import SQLQueryInterface\n", "from tms_data_interface import SQLQueryInterface\n",
"\n", "seq = SQLQueryInterface()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b1272d9b-3219-4785-a5ba-516a8cad02c3",
"metadata": {},
"outputs": [],
"source": [
"seq.execute_raw(\"show tables\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f7df9028-84c1-47dd-82e6-161238532686",
"metadata": {},
"outputs": [],
"source": [
"query = \"\"\"\n", "query = \"\"\"\n",
"WITH time_windows AS (\n", " select final.CUSTOMER_NUMBER_main as Focal_id,\n",
" SELECT\n", " final.Credit_transaction_amount,\n",
" -- End time is the current trade time\n", " final.Total_no_of_credit_transactions,\n",
" date_time AS end_time,\n", " final.Debit_transaction_amount,\n",
"\n", " final.Total_no_of_debit_transactions,\n",
" -- Subtract seconds from the end_time using date_add() with negative integer interval\n", " final.Wash_Ratio,\n",
" date_add('second', -{time_window_s}, date_time) AS start_time,\n", " final.SEGMENT,\n",
"\n", " final.RISK,\n",
" -- Trade details\n", " final.SAR_FLAG\n",
" trade_price,\n", " from \n",
" trade_volume,\n", " (\n",
" trader_id,\n", " (\n",
"\n", " select subquery.CUSTOMER_NUMBER_1 as CUSTOMER_NUMBER_main,\n",
" -- Calculate minimum price within the time window\n", " subquery.Credit_transaction_amount,\n",
" MIN(trade_price) OVER (\n", " subquery.Total_no_of_credit_transactions,\n",
" ORDER BY date_time \n", " case\n",
" RANGE BETWEEN INTERVAL '{time_window_s}' SECOND PRECEDING AND CURRENT ROW\n", " when subquery.Debit_transaction_amount is NULL then 0\n",
" ) AS min_price,\n", " else Debit_transaction_amount\n",
"\n", " end as Debit_transaction_amount,\n",
" -- Calculate maximum price within the time window\n", " case\n",
" MAX(trade_price) OVER (\n", " when subquery.Total_no_of_debit_transactions is NULL then 0\n",
" ORDER BY date_time \n", " else Total_no_of_debit_transactions\n",
" RANGE BETWEEN INTERVAL '{time_window_s}' SECOND PRECEDING AND CURRENT ROW\n", " end as Total_no_of_debit_transactions,\n",
" ) AS max_price,\n", " case\n",
"\n", " when subquery.Debit_transaction_amount = 0\n",
" -- Calculate total trade volume within the time window\n", " or subquery.Debit_transaction_amount is NULL then 0\n",
" SUM(trade_volume) OVER ( \n", " else subquery.Credit_transaction_amount / subquery.Debit_transaction_amount\n",
" ORDER BY date_time \n", " end as Wash_Ratio\n",
" RANGE BETWEEN INTERVAL '{time_window_s}' SECOND PRECEDING AND CURRENT ROW\n", " from \n",
" ) AS total_volume,\n", " (\n",
"\n", " (\n",
" -- Calculate participant's trade volume within the time window\n", " select customer_number as CUSTOMER_NUMBER_1, \n",
" SUM(CASE WHEN trader_id = trader_id THEN trade_volume ELSE 0 END) OVER (\n", " sum(transaction_amount) as Credit_transaction_amount, \n",
" PARTITION BY trader_id \n", " count(*) as Total_no_of_credit_transactions\n",
" ORDER BY date_time \n", " from \n",
" RANGE BETWEEN INTERVAL '{time_window_s}' SECOND PRECEDING AND CURRENT ROW\n", " (\n",
" ) AS participant_volume\n", " select * \n",
" FROM\n", " from {trans_data} as trans_table left join {acc_data} as acc_table\n",
" {trade_data_1b}\n", " on trans_table.benef_account_number = acc_table.account_number\n",
")\n", " )\n",
"SELECT\n", " where account_number not in ('None')\n",
" -- Select the time window details\n", " group by 1\n",
" start_time,\n", " ) credit left join\n",
" end_time,\n", " (\n",
"\n", " select customer_number as CUSTOMER_NUMBER_2, \n",
" -- Select the participant (trader) ID\n", " sum(transaction_amount) as Debit_transaction_amount, \n",
" trader_id AS \"Participant\",\n", " count(*) as Total_no_of_debit_transactions\n",
"\n", " from \n",
" -- Select the calculated min and max prices\n", " (\n",
" min_price,\n", " select * \n",
" max_price,\n", " from {trans_data} as trans_table left join {acc_data} as acc_table\n",
"\n", " on trans_table.orig_account_number = acc_table.account_number\n",
" -- Calculate the price change percentage\n", " )\n",
" (max_price - min_price) / NULLIF(min_price, 0) * 100 AS \"Price Change (%)\",\n", " where account_number not in ('None')\n",
"\n", " group by 1\n",
" -- Calculate the participant's volume as a percentage of total volume\n", " ) debit on credit.CUSTOMER_NUMBER_1 = debit.CUSTOMER_NUMBER_2 \n",
" (participant_volume / NULLIF(total_volume, 0)) * 100 AS \"Volume (%)\",\n", " ) subquery\n",
"\n", " ) main left join \n",
" -- Participant volume\n", " (\n",
" participant_volume,\n", " select subquery.CUSTOMER_NUMBER_3 as CUSTOMER_NUMBER_cust,\n",
"\n", " subquery.SEGMENT,\n",
" -- Select the total volume within the window\n", " subquery.RISK,\n",
" total_volume AS \"Total Volume\"\n", " case\n",
"FROM\n", " when subquery.SAR_FLAG is NULL then 'N'\n",
" time_windows\n", " else subquery.SAR_FLAG\n",
" end as SAR_FLAG \n",
" from\n",
" (\n",
" (\n",
" select customer_number as CUSTOMER_NUMBER_3, \n",
" business_segment as SEGMENT,\n",
" case\n",
" when RISK_CLASSIFICATION = 1 then 'Low Risk'\n",
" when RISK_CLASSIFICATION = 2 then 'Medium Risk'\n",
" when RISK_CLASSIFICATION = 3 then 'High Risk'\n",
" else 'Unknown Risk'\n",
" end AS RISK\n",
" from {cust_data}\n",
" ) cd left join\n",
" (\n",
" select customer_number as CUSTOMER_NUMBER_4, \n",
" sar_flag as SAR_FLAG\n",
" from {alert_data}\n",
" ) ad on cd.CUSTOMER_NUMBER_3 = ad.CUSTOMER_NUMBER_4\n",
" ) subquery\n",
" ) cust_alert on cust_alert.CUSTOMER_NUMBER_cust = main.CUSTOMER_NUMBER_main\n",
" ) final\n",
"\"\"\"\n", "\"\"\"\n",
"\n", "\n"
"\n", ]
},
{
"cell_type": "code",
"execution_count": null,
"id": "361ae64c-dc41-456d-93e4-f7d8b211dce4",
"metadata": {},
"outputs": [],
"source": [
"from tms_data_interface import SQLQueryInterface\n", "from tms_data_interface import SQLQueryInterface\n",
"\n", "\n",
"class Scenario:\n", "class Scenario:\n",
" seq = SQLQueryInterface(schema=\"qa_schema\")\n", " seq = SQLQueryInterface()\n",
"\n",
" def logic(self, **kwargs):\n", " def logic(self, **kwargs):\n",
" validation_window = kwargs.get('validation_window')\n", " row_list = self.seq.execute_raw(query.format(trans_data=\"trans_data_10mv5_latest\",\n",
" time_window_s = int(validation_window/1000)\n", " cust_data=\"customer_v1\",\n",
" query_start_time = datetime.now()\n", " acc_data=\"account_v1\",\n",
" print(\"Query start time :\",query_start_time)\n", " alert_data=\"alert_v1\")\n",
" row_list = self.seq.execute_raw(query.format(trade_data_1b=\"qa_table_test\",\n",
" time_window_s = time_window_s)\n",
" )\n", " )\n",
" cols = [\n", " cols = [\"Focal_id\", \"Credit_transaction_amount\",\n",
" 'START_DATE_TIME',\n", " \"Total_no_of_credit_transactions\",\n",
" 'END_DATE_TIME',\n", " \"Debit_transaction_amount\", \"Total_no_of_debit_transactions\",\n",
" 'Focal_id',\n", " \"Wash_Ratio\",\n",
" 'MIN_PRICE',\n", " \"Segment\", \"Risk\", \"SAR_FLAG\"]\n",
" 'MAX_PRICE',\n", " df = pd.DataFrame(row_list, columns = cols)\n",
" 'PRICE_CHANGE_PCT',\n", " return df"
" 'PARTICIPANT_VOLUME_PCT',\n",
" 'PARTICIPANT_VOLUME',\n",
" 'TOTAL_VOLUME',\n",
" ]\n",
" final_scenario_df = pd.DataFrame(row_list, columns = cols)\n",
" final_scenario_df['PARTICIPANT_VOLUME_PCT'] = final_scenario_df['PARTICIPANT_VOLUME']/\\\n",
" final_scenario_df['TOTAL_VOLUME'] * 100\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"
] ]
} }
], ],

217
main.py
View File

@ -4,109 +4,136 @@
# In[ ]: # In[ ]:
from datetime import datetime, timedelta
import pandas as pd import pandas as pd
# In[ ]:
from tms_data_interface import SQLQueryInterface from tms_data_interface import SQLQueryInterface
seq = SQLQueryInterface()
# In[ ]:
seq.execute_raw("show tables")
# In[ ]:
query = """ query = """
WITH time_windows AS ( select final.CUSTOMER_NUMBER_main as Focal_id,
SELECT final.Credit_transaction_amount,
-- End time is the current trade time final.Total_no_of_credit_transactions,
date_time AS end_time, final.Debit_transaction_amount,
final.Total_no_of_debit_transactions,
-- Subtract seconds from the end_time using date_add() with negative integer interval final.Wash_Ratio,
date_add('second', -{time_window_s}, date_time) AS start_time, final.SEGMENT,
final.RISK,
-- Trade details final.SAR_FLAG
trade_price, from
trade_volume, (
trader_id, (
select subquery.CUSTOMER_NUMBER_1 as CUSTOMER_NUMBER_main,
-- Calculate minimum price within the time window subquery.Credit_transaction_amount,
MIN(trade_price) OVER ( subquery.Total_no_of_credit_transactions,
ORDER BY date_time case
RANGE BETWEEN INTERVAL '{time_window_s}' SECOND PRECEDING AND CURRENT ROW when subquery.Debit_transaction_amount is NULL then 0
) AS min_price, else Debit_transaction_amount
end as Debit_transaction_amount,
-- Calculate maximum price within the time window case
MAX(trade_price) OVER ( when subquery.Total_no_of_debit_transactions is NULL then 0
ORDER BY date_time else Total_no_of_debit_transactions
RANGE BETWEEN INTERVAL '{time_window_s}' SECOND PRECEDING AND CURRENT ROW end as Total_no_of_debit_transactions,
) AS max_price, case
when subquery.Debit_transaction_amount = 0
-- Calculate total trade volume within the time window or subquery.Debit_transaction_amount is NULL then 0
SUM(trade_volume) OVER ( else subquery.Credit_transaction_amount / subquery.Debit_transaction_amount
ORDER BY date_time end as Wash_Ratio
RANGE BETWEEN INTERVAL '{time_window_s}' SECOND PRECEDING AND CURRENT ROW from
) AS total_volume, (
(
-- Calculate participant's trade volume within the time window select customer_number as CUSTOMER_NUMBER_1,
SUM(CASE WHEN trader_id = trader_id THEN trade_volume ELSE 0 END) OVER ( sum(transaction_amount) as Credit_transaction_amount,
PARTITION BY trader_id count(*) as Total_no_of_credit_transactions
ORDER BY date_time from
RANGE BETWEEN INTERVAL '{time_window_s}' SECOND PRECEDING AND CURRENT ROW (
) AS participant_volume select *
FROM from {trans_data} as trans_table left join {acc_data} as acc_table
{trade_data_1b} on trans_table.benef_account_number = acc_table.account_number
) )
SELECT where account_number not in ('None')
-- Select the time window details group by 1
start_time, ) credit left join
end_time, (
select customer_number as CUSTOMER_NUMBER_2,
-- Select the participant (trader) ID sum(transaction_amount) as Debit_transaction_amount,
trader_id AS "Participant", count(*) as Total_no_of_debit_transactions
from
-- Select the calculated min and max prices (
min_price, select *
max_price, from {trans_data} as trans_table left join {acc_data} as acc_table
on trans_table.orig_account_number = acc_table.account_number
-- Calculate the price change percentage )
(max_price - min_price) / NULLIF(min_price, 0) * 100 AS "Price Change (%)", where account_number not in ('None')
group by 1
-- Calculate the participant's volume as a percentage of total volume ) debit on credit.CUSTOMER_NUMBER_1 = debit.CUSTOMER_NUMBER_2
(participant_volume / NULLIF(total_volume, 0)) * 100 AS "Volume (%)", ) subquery
) main left join
-- Participant volume (
participant_volume, select subquery.CUSTOMER_NUMBER_3 as CUSTOMER_NUMBER_cust,
subquery.SEGMENT,
-- Select the total volume within the window subquery.RISK,
total_volume AS "Total Volume" case
FROM when subquery.SAR_FLAG is NULL then 'N'
time_windows else subquery.SAR_FLAG
end as SAR_FLAG
from
(
(
select customer_number as CUSTOMER_NUMBER_3,
business_segment as SEGMENT,
case
when RISK_CLASSIFICATION = 1 then 'Low Risk'
when RISK_CLASSIFICATION = 2 then 'Medium Risk'
when RISK_CLASSIFICATION = 3 then 'High Risk'
else 'Unknown Risk'
end AS RISK
from {cust_data}
) cd left join
(
select customer_number as CUSTOMER_NUMBER_4,
sar_flag as SAR_FLAG
from {alert_data}
) ad on cd.CUSTOMER_NUMBER_3 = ad.CUSTOMER_NUMBER_4
) subquery
) cust_alert on cust_alert.CUSTOMER_NUMBER_cust = main.CUSTOMER_NUMBER_main
) final
""" """
# In[ ]:
from tms_data_interface import SQLQueryInterface from tms_data_interface import SQLQueryInterface
class Scenario: class Scenario:
seq = SQLQueryInterface(schema="qa_schema") seq = SQLQueryInterface()
def logic(self, **kwargs):
validation_window = kwargs.get('validation_window') def logic(self, **kwargs):
time_window_s = int(validation_window/1000) row_list = self.seq.execute_raw(query.format(trans_data="trans_data_10mv5_latest",
query_start_time = datetime.now() cust_data="customer_v1",
print("Query start time :",query_start_time) acc_data="account_v1",
row_list = self.seq.execute_raw(query.format(trade_data_1b="qa_table_test", alert_data="alert_v1")
time_window_s = time_window_s) )
) cols = ["Focal_id", "Credit_transaction_amount",
cols = [ "Total_no_of_credit_transactions",
'START_DATE_TIME', "Debit_transaction_amount", "Total_no_of_debit_transactions",
'END_DATE_TIME', "Wash_Ratio",
'Focal_id', "Segment", "Risk", "SAR_FLAG"]
'MIN_PRICE', df = pd.DataFrame(row_list, columns = cols)
'MAX_PRICE', return df
'PRICE_CHANGE_PCT',
'PARTICIPANT_VOLUME_PCT',
'PARTICIPANT_VOLUME',
'TOTAL_VOLUME',
]
final_scenario_df = pd.DataFrame(row_list, columns = cols)
final_scenario_df['PARTICIPANT_VOLUME_PCT'] = final_scenario_df['PARTICIPANT_VOLUME']/\
final_scenario_df['TOTAL_VOLUME'] * 100
final_scenario_df['Segment'] = 'Default'
final_scenario_df['SAR_FLAG'] = 'N'
final_scenario_df['Risk'] = 'Low Risk'
final_scenario_df.dropna(inplace=True)
# final_scenario_df['RUN_DATE'] = final_scenario_df['END_DATE']
return final_scenario_df