78/main.ipynb
2024-10-09 04:10:27 +00:00

308 lines
10 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"id": "e706cfb0-2234-4c4c-95d8-d1968f656aa0",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import pandas as pd\n",
"\n",
"query = \"\"\"\n",
" select final.CUSTOMER_NUMBER_main as Focal_id,\n",
" CAST(final.Cash_deposit_total AS DECIMAL(18, 2)) AS Cash_deposit_total,\n",
" final.Cash_deposit_count,\n",
" final.SEGMENT,\n",
" final.RISK,\n",
" final.SAR_FLAG\n",
"from \n",
"(\n",
" (\n",
" select subquery.CUSTOMER_NUMBER_1 as CUSTOMER_NUMBER_main,\n",
" subquery.Cash_deposit_total,\n",
" subquery.Cash_deposit_count\n",
" from \n",
" (\n",
" select customer_number as CUSTOMER_NUMBER_1, \n",
" sum(transaction_amount) as Cash_deposit_total, \n",
" count(*) as Cash_deposit_count\n",
" from \n",
" (\n",
" select * \n",
" from {trans_data} trans_table \n",
" left join {acc_data} acc_table\n",
" on trans_table.benef_account_number = acc_table.account_number\n",
" ) trans\n",
" where account_number not in ('None')\n",
" and transaction_desc = 'CASH RELATED TRANSACTION'\n",
" group by customer_number\n",
" ) subquery\n",
" ) main \n",
" left join \n",
" (\n",
" select cd.CUSTOMER_NUMBER_3 as CUSTOMER_NUMBER_cust,\n",
" cd.SEGMENT,\n",
" cd.RISK,\n",
" case\n",
" when ad.SAR_FLAG is NULL then 'N'\n",
" else ad.SAR_FLAG\n",
" end as SAR_FLAG \n",
" from\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 \n",
" left join\n",
" (\n",
" select customer_number as CUSTOMER_NUMBER_4, \n",
" sar_flag as SAR_FLAG\n",
" from {alert_data}\n",
" ) ad \n",
" on cd.CUSTOMER_NUMBER_3 = ad.CUSTOMER_NUMBER_4\n",
" ) as cust_alert\n",
" on cust_alert.CUSTOMER_NUMBER_cust = main.CUSTOMER_NUMBER_main\n",
") as final\n",
"\"\"\"\n",
"\n",
"from tms_data_interface import SQLQueryInterface\n",
"\n",
"class Scenario:\n",
" seq = SQLQueryInterface(schema=\"transactionschema\")\n",
"\n",
" def logic(self, **kwargs):\n",
" row_list = self.seq.execute_raw(query.format(trans_data=\"transaction10m\",\n",
" cust_data=\"customer_data_v1\",\n",
" acc_data=\"account_data_v1\",\n",
" alert_data=\"alert_data_v1\")\n",
" )\n",
" cols = [\"Focal_id\", \"Cash_deposit_total\", \"Cash_deposit_count\",\n",
" \"Segment\", \"Risk\", \"SAR_FLAG\"]\n",
" df = pd.DataFrame(row_list, columns = cols)\n",
" df[\"Cash_deposit_total\"] = df[\"Cash_deposit_total\"].astype(float)\n",
" return df"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "1f20337b-8116-47e5-8743-1ba41e2df819",
"metadata": {
"tags": []
},
"outputs": [
{
"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>Cash_deposit_total</th>\n",
" <th>Cash_deposit_count</th>\n",
" <th>Segment</th>\n",
" <th>Risk</th>\n",
" <th>SAR_FLAG</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>PN469304</td>\n",
" <td>8049952.0</td>\n",
" <td>141</td>\n",
" <td>Mass Market</td>\n",
" <td>High Risk</td>\n",
" <td>N</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>PN605743</td>\n",
" <td>9766101.0</td>\n",
" <td>175</td>\n",
" <td>Others</td>\n",
" <td>Low Risk</td>\n",
" <td>N</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>PN399215</td>\n",
" <td>8469943.0</td>\n",
" <td>164</td>\n",
" <td>Mass Market</td>\n",
" <td>Low Risk</td>\n",
" <td>N</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>PN175020</td>\n",
" <td>17724959.0</td>\n",
" <td>313</td>\n",
" <td>Others</td>\n",
" <td>Low Risk</td>\n",
" <td>N</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>PN345085</td>\n",
" <td>7518628.0</td>\n",
" <td>124</td>\n",
" <td>Others</td>\n",
" <td>Medium Risk</td>\n",
" <td>N</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",
" </tr>\n",
" <tr>\n",
" <th>9005</th>\n",
" <td>PN660329</td>\n",
" <td>8528178.0</td>\n",
" <td>141</td>\n",
" <td>Others</td>\n",
" <td>Low Risk</td>\n",
" <td>N</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9006</th>\n",
" <td>PN336833</td>\n",
" <td>8475036.0</td>\n",
" <td>150</td>\n",
" <td>Others</td>\n",
" <td>Low Risk</td>\n",
" <td>N</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9007</th>\n",
" <td>PN428534</td>\n",
" <td>7871170.0</td>\n",
" <td>129</td>\n",
" <td>Priority Banking</td>\n",
" <td>Low Risk</td>\n",
" <td>N</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9008</th>\n",
" <td>PN101660</td>\n",
" <td>8450309.0</td>\n",
" <td>142</td>\n",
" <td>Mass Market</td>\n",
" <td>Low Risk</td>\n",
" <td>N</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9009</th>\n",
" <td>PN198641</td>\n",
" <td>8690226.0</td>\n",
" <td>166</td>\n",
" <td>Others</td>\n",
" <td>Low Risk</td>\n",
" <td>N</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>9010 rows × 6 columns</p>\n",
"</div>"
],
"text/plain": [
" Focal_id Cash_deposit_total Cash_deposit_count Segment \\\n",
"0 PN469304 8049952.0 141 Mass Market \n",
"1 PN605743 9766101.0 175 Others \n",
"2 PN399215 8469943.0 164 Mass Market \n",
"3 PN175020 17724959.0 313 Others \n",
"4 PN345085 7518628.0 124 Others \n",
"... ... ... ... ... \n",
"9005 PN660329 8528178.0 141 Others \n",
"9006 PN336833 8475036.0 150 Others \n",
"9007 PN428534 7871170.0 129 Priority Banking \n",
"9008 PN101660 8450309.0 142 Mass Market \n",
"9009 PN198641 8690226.0 166 Others \n",
"\n",
" Risk SAR_FLAG \n",
"0 High Risk N \n",
"1 Low Risk N \n",
"2 Low Risk N \n",
"3 Low Risk N \n",
"4 Medium Risk N \n",
"... ... ... \n",
"9005 Low Risk N \n",
"9006 Low Risk N \n",
"9007 Low Risk N \n",
"9008 Low Risk N \n",
"9009 Low Risk N \n",
"\n",
"[9010 rows x 6 columns]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# sen = Scenario()\n",
"# sen.logic()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6de62b37-00d1-4c88-b27b-9a70e05add91",
"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
}