diff --git a/.ipynb_checkpoints/main-checkpoint.ipynb b/.ipynb_checkpoints/main-checkpoint.ipynb index a083585..0632273 100644 --- a/.ipynb_checkpoints/main-checkpoint.ipynb +++ b/.ipynb_checkpoints/main-checkpoint.ipynb @@ -157,7 +157,7 @@ }, { "cell_type": "code", - "execution_count": 77, + "execution_count": 84, "id": "d220561a-34c9-48d2-8e2f-5d174a87540b", "metadata": { "tags": [] @@ -211,7 +211,7 @@ " )\n", "\n", " # Step 4: Randomly select 0.1% sample from high-risk population\n", - " sample_fraction = 0.1 # 0.1%\n", + " sample_fraction = 0.3 # 0.1%\n", " high_pop_indices = df[high_pop].sample(frac=sample_fraction, random_state=42).index\n", "\n", " # Step 5: Set SAR_FLAG values\n", @@ -222,7 +222,7 @@ }, { "cell_type": "code", - "execution_count": 83, + "execution_count": 85, "id": "2e5a0ea9-64cd-4a8d-9a5d-e5e7b36a401a", "metadata": { "tags": [] @@ -235,19 +235,286 @@ }, { "cell_type": "code", - "execution_count": 82, + "execution_count": 86, "id": "830c7ec3-9707-46db-9b27-ac4f9d46a03a", "metadata": { "tags": [] }, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
| \n", + " | Focal_id | \n", + "Credit_transaction_amount | \n", + "Total_no_of_credit_transactions | \n", + "Debit_transaction_amount | \n", + "Total_no_of_debit_transactions | \n", + "Wash_Ratio | \n", + "Segment | \n", + "Risk | \n", + "SAR_FLAG | \n", + "P90_Credit | \n", + "P90_Debit | \n", + "P90_Wash | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "PN489144 | \n", + "2830802741 | \n", + "2060 | \n", + "2847556186 | \n", + "1976 | \n", + "0.994117 | \n", + "Whole Sale Banking | \n", + "Low Risk | \n", + "N | \n", + "4.400246e+09 | \n", + "4.332448e+09 | \n", + "1.058020 | \n", + "
| 1 | \n", + "PN394780 | \n", + "2872685364 | \n", + "2029 | \n", + "2743931855 | \n", + "1999 | \n", + "1.046923 | \n", + "Whole Sale Banking | \n", + "Low Risk | \n", + "N | \n", + "4.400246e+09 | \n", + "4.332448e+09 | \n", + "1.058020 | \n", + "
| 2 | \n", + "PN195722 | \n", + "5604208368 | \n", + "3937 | \n", + "5557946505 | \n", + "4039 | \n", + "1.008324 | \n", + "SME | \n", + "Low Risk | \n", + "N | \n", + "4.532321e+09 | \n", + "4.534860e+09 | \n", + "1.062759 | \n", + "
| 3 | \n", + "PN652566 | \n", + "1630905248 | \n", + "1152 | \n", + "1686713614 | \n", + "1169 | \n", + "0.966913 | \n", + "Whole Sale Banking | \n", + "Low Risk | \n", + "N | \n", + "4.400246e+09 | \n", + "4.332448e+09 | \n", + "1.058020 | \n", + "
| 4 | \n", + "PN181960 | \n", + "2157634332 | \n", + "1613 | \n", + "2039953312 | \n", + "1552 | \n", + "1.057688 | \n", + "Corporate Banking | \n", + "Low Risk | \n", + "N | \n", + "5.021582e+09 | \n", + "5.003501e+09 | \n", + "1.063161 | \n", + "
| ... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "
| 10009 | \n", + "PN479491 | \n", + "31124877 | \n", + "246 | \n", + "23590191 | \n", + "357 | \n", + "1.319399 | \n", + "Private Banking | \n", + "Low Risk | \n", + "N | \n", + "4.461828e+07 | \n", + "3.176446e+07 | \n", + "1.760285 | \n", + "
| 10010 | \n", + "PN267550 | \n", + "36558708 | \n", + "260 | \n", + "27361057 | \n", + "366 | \n", + "1.336158 | \n", + "Priority Banking | \n", + "Low Risk | \n", + "N | \n", + "4.410392e+07 | \n", + "3.076443e+07 | \n", + "1.729168 | \n", + "
| 10011 | \n", + "PN293003 | \n", + "33990478 | \n", + "255 | \n", + "24465835 | \n", + "323 | \n", + "1.389304 | \n", + "Others | \n", + "Low Risk | \n", + "N | \n", + "6.334963e+07 | \n", + "4.223903e+07 | \n", + "1.740112 | \n", + "
| 10012 | \n", + "PN534105 | \n", + "39934813 | \n", + "278 | \n", + "28247858 | \n", + "403 | \n", + "1.413729 | \n", + "Others | \n", + "High Risk | \n", + "N | \n", + "6.334963e+07 | \n", + "4.223903e+07 | \n", + "1.740112 | \n", + "
| 10013 | \n", + "PN390430 | \n", + "36894062 | \n", + "257 | \n", + "29162252 | \n", + "371 | \n", + "1.265131 | \n", + "Private Banking | \n", + "Low Risk | \n", + "N | \n", + "4.461828e+07 | \n", + "3.176446e+07 | \n", + "1.760285 | \n", + "
10014 rows × 12 columns
\n", + "| \n", + " | Focal_id | \n", + "Credit_transaction_amount | \n", + "Total_no_of_credit_transactions | \n", + "Debit_transaction_amount | \n", + "Total_no_of_debit_transactions | \n", + "Wash_Ratio | \n", + "Segment | \n", + "Risk | \n", + "SAR_FLAG | \n", + "P90_Credit | \n", + "P90_Debit | \n", + "P90_Wash | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "PN489144 | \n", + "2830802741 | \n", + "2060 | \n", + "2847556186 | \n", + "1976 | \n", + "0.994117 | \n", + "Whole Sale Banking | \n", + "Low Risk | \n", + "N | \n", + "4.400246e+09 | \n", + "4.332448e+09 | \n", + "1.058020 | \n", + "
| 1 | \n", + "PN394780 | \n", + "2872685364 | \n", + "2029 | \n", + "2743931855 | \n", + "1999 | \n", + "1.046923 | \n", + "Whole Sale Banking | \n", + "Low Risk | \n", + "N | \n", + "4.400246e+09 | \n", + "4.332448e+09 | \n", + "1.058020 | \n", + "
| 2 | \n", + "PN195722 | \n", + "5604208368 | \n", + "3937 | \n", + "5557946505 | \n", + "4039 | \n", + "1.008324 | \n", + "SME | \n", + "Low Risk | \n", + "N | \n", + "4.532321e+09 | \n", + "4.534860e+09 | \n", + "1.062759 | \n", + "
| 3 | \n", + "PN652566 | \n", + "1630905248 | \n", + "1152 | \n", + "1686713614 | \n", + "1169 | \n", + "0.966913 | \n", + "Whole Sale Banking | \n", + "Low Risk | \n", + "N | \n", + "4.400246e+09 | \n", + "4.332448e+09 | \n", + "1.058020 | \n", + "
| 4 | \n", + "PN181960 | \n", + "2157634332 | \n", + "1613 | \n", + "2039953312 | \n", + "1552 | \n", + "1.057688 | \n", + "Corporate Banking | \n", + "Low Risk | \n", + "N | \n", + "5.021582e+09 | \n", + "5.003501e+09 | \n", + "1.063161 | \n", + "
| ... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "
| 10009 | \n", + "PN479491 | \n", + "31124877 | \n", + "246 | \n", + "23590191 | \n", + "357 | \n", + "1.319399 | \n", + "Private Banking | \n", + "Low Risk | \n", + "N | \n", + "4.461828e+07 | \n", + "3.176446e+07 | \n", + "1.760285 | \n", + "
| 10010 | \n", + "PN267550 | \n", + "36558708 | \n", + "260 | \n", + "27361057 | \n", + "366 | \n", + "1.336158 | \n", + "Priority Banking | \n", + "Low Risk | \n", + "N | \n", + "4.410392e+07 | \n", + "3.076443e+07 | \n", + "1.729168 | \n", + "
| 10011 | \n", + "PN293003 | \n", + "33990478 | \n", + "255 | \n", + "24465835 | \n", + "323 | \n", + "1.389304 | \n", + "Others | \n", + "Low Risk | \n", + "N | \n", + "6.334963e+07 | \n", + "4.223903e+07 | \n", + "1.740112 | \n", + "
| 10012 | \n", + "PN534105 | \n", + "39934813 | \n", + "278 | \n", + "28247858 | \n", + "403 | \n", + "1.413729 | \n", + "Others | \n", + "High Risk | \n", + "N | \n", + "6.334963e+07 | \n", + "4.223903e+07 | \n", + "1.740112 | \n", + "
| 10013 | \n", + "PN390430 | \n", + "36894062 | \n", + "257 | \n", + "29162252 | \n", + "371 | \n", + "1.265131 | \n", + "Private Banking | \n", + "Low Risk | \n", + "N | \n", + "4.461828e+07 | \n", + "3.176446e+07 | \n", + "1.760285 | \n", + "
10014 rows × 12 columns
\n", + "