generated from user_client2024/184
152 lines
4.4 KiB
Python
152 lines
4.4 KiB
Python
#!/usr/bin/env python
|
|
# coding: utf-8
|
|
|
|
# In[3]:
|
|
|
|
|
|
import pandas as pd
|
|
|
|
|
|
# In[4]:
|
|
|
|
|
|
from tms_data_interface import SQLQueryInterface
|
|
seq = SQLQueryInterface(schema="transactionschema")
|
|
|
|
|
|
# In[5]:
|
|
|
|
|
|
seq.execute_raw("show tables")
|
|
|
|
|
|
# In[6]:
|
|
|
|
|
|
query = """
|
|
select final.CUSTOMER_NUMBER_main as Focal_id,
|
|
final.Credit_transaction_amount,
|
|
final.SEGMENT,
|
|
final.RISK,
|
|
final.SAR_FLAG
|
|
from
|
|
(
|
|
(
|
|
select subquery.CUSTOMER_NUMBER_1 as CUSTOMER_NUMBER_main,
|
|
subquery.Credit_transaction_amount
|
|
from
|
|
(
|
|
(
|
|
select customer_number as CUSTOMER_NUMBER_1,
|
|
sum(transaction_amount) as Credit_transaction_amount
|
|
from
|
|
(
|
|
select *
|
|
from {trans_data} as trans_table
|
|
left join {acc_data} as acc_table
|
|
on trans_table.benef_account_number = acc_table.account_number
|
|
where trans_table.transaction_desc = 'WIRE RELATED TRANSACTION'
|
|
)
|
|
where account_number not in ('None')
|
|
group by 1
|
|
) credit
|
|
) subquery
|
|
) main left join
|
|
(
|
|
select subquery.CUSTOMER_NUMBER_3 as CUSTOMER_NUMBER_cust,
|
|
subquery.SEGMENT,
|
|
subquery.RISK,
|
|
case
|
|
when subquery.SAR_FLAG is NULL then 'N'
|
|
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[25]:
|
|
|
|
|
|
from tms_data_interface import SQLQueryInterface
|
|
|
|
class Scenario:
|
|
seq = SQLQueryInterface(schema="transactionschema")
|
|
|
|
def logic(self, **kwargs):
|
|
row_list = self.seq.execute_raw(query.format(trans_data="transaction10m",
|
|
cust_data="customer_data_v1",
|
|
acc_data="account_data_v1",
|
|
alert_data="alert_data_v1")
|
|
)
|
|
cols = ["Focal_id", "Total_Wire_Deposit_Amt",
|
|
"Segment", "Risk", "SAR_FLAG"]
|
|
|
|
df = pd.DataFrame(row_list, columns = cols)
|
|
df['Total_Wire_Deposit_Amt'] = df['Total_Wire_Deposit_Amt'].astype('int')
|
|
# df['Segment'] = 'Individual'
|
|
|
|
p98 = (
|
|
df.groupby("Segment")["Total_Wire_Deposit_Amt"]
|
|
.quantile(0.98)
|
|
.reset_index()
|
|
.rename(columns={"Total_Wire_Deposit_Amt": "P98_Value"})
|
|
)
|
|
print(p98)
|
|
|
|
# Merge percentile back to main dataframe
|
|
df = df.merge(p98, on="Segment", how="left")
|
|
|
|
# Step 2: Identify population above 98th percentile
|
|
high_pop = df["Total_Wire_Deposit_Amt"] > df["P98_Value"]
|
|
print(high_pop)
|
|
|
|
# Step 3: From this high-risk population, select 0.1% random sample
|
|
sample_fraction = 0.1 # 0.1%
|
|
high_pop_indices = df[high_pop].sample(frac=sample_fraction, random_state=42).index
|
|
|
|
# Step 4: Assign SAR_FLAG
|
|
df["SAR_FLAG"] = "N" # default for all
|
|
df.loc[high_pop_indices, "SAR_FLAG"] = "Y" # assign Y to random 0.1% above 98th percentile
|
|
|
|
return df
|
|
|
|
|
|
# In[28]:
|
|
|
|
|
|
# sen = Scenario()
|
|
# a = sen.logic()
|
|
|
|
|
|
# In[29]:
|
|
|
|
|
|
# a[a['SAR_FLAG'] == "Y"]
|
|
|
|
|
|
# In[ ]:
|
|
|
|
|
|
#tst cmt
|
|
|