From 5f0be70e698e2fe3e53fb582b1978fd16868b7f8 Mon Sep 17 00:00:00 2001
From: user_client2024 <shalini.v@solytics-partners.com>
Date: Thu, 27 Nov 2025 07:09:21 +0000
Subject: [PATCH] System save at 27/11/2025 12:39 by user_client2024

---
 .ipynb_checkpoints/main-checkpoint.ipynb | 279 ++++++++++++++++++++++-
 main.ipynb                               | 279 ++++++++++++++++++++++-
 main.py                                  |  10 +-
 3 files changed, 551 insertions(+), 17 deletions(-)

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": [
+       "<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>Credit_transaction_amount</th>\n",
+       "      <th>Total_no_of_credit_transactions</th>\n",
+       "      <th>Debit_transaction_amount</th>\n",
+       "      <th>Total_no_of_debit_transactions</th>\n",
+       "      <th>Wash_Ratio</th>\n",
+       "      <th>Segment</th>\n",
+       "      <th>Risk</th>\n",
+       "      <th>SAR_FLAG</th>\n",
+       "      <th>P90_Credit</th>\n",
+       "      <th>P90_Debit</th>\n",
+       "      <th>P90_Wash</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>PN489144</td>\n",
+       "      <td>2830802741</td>\n",
+       "      <td>2060</td>\n",
+       "      <td>2847556186</td>\n",
+       "      <td>1976</td>\n",
+       "      <td>0.994117</td>\n",
+       "      <td>Whole Sale Banking</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>4.400246e+09</td>\n",
+       "      <td>4.332448e+09</td>\n",
+       "      <td>1.058020</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>PN394780</td>\n",
+       "      <td>2872685364</td>\n",
+       "      <td>2029</td>\n",
+       "      <td>2743931855</td>\n",
+       "      <td>1999</td>\n",
+       "      <td>1.046923</td>\n",
+       "      <td>Whole Sale Banking</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>4.400246e+09</td>\n",
+       "      <td>4.332448e+09</td>\n",
+       "      <td>1.058020</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>PN195722</td>\n",
+       "      <td>5604208368</td>\n",
+       "      <td>3937</td>\n",
+       "      <td>5557946505</td>\n",
+       "      <td>4039</td>\n",
+       "      <td>1.008324</td>\n",
+       "      <td>SME</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>4.532321e+09</td>\n",
+       "      <td>4.534860e+09</td>\n",
+       "      <td>1.062759</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>PN652566</td>\n",
+       "      <td>1630905248</td>\n",
+       "      <td>1152</td>\n",
+       "      <td>1686713614</td>\n",
+       "      <td>1169</td>\n",
+       "      <td>0.966913</td>\n",
+       "      <td>Whole Sale Banking</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>4.400246e+09</td>\n",
+       "      <td>4.332448e+09</td>\n",
+       "      <td>1.058020</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>PN181960</td>\n",
+       "      <td>2157634332</td>\n",
+       "      <td>1613</td>\n",
+       "      <td>2039953312</td>\n",
+       "      <td>1552</td>\n",
+       "      <td>1.057688</td>\n",
+       "      <td>Corporate Banking</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>5.021582e+09</td>\n",
+       "      <td>5.003501e+09</td>\n",
+       "      <td>1.063161</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",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10009</th>\n",
+       "      <td>PN479491</td>\n",
+       "      <td>31124877</td>\n",
+       "      <td>246</td>\n",
+       "      <td>23590191</td>\n",
+       "      <td>357</td>\n",
+       "      <td>1.319399</td>\n",
+       "      <td>Private Banking</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>4.461828e+07</td>\n",
+       "      <td>3.176446e+07</td>\n",
+       "      <td>1.760285</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10010</th>\n",
+       "      <td>PN267550</td>\n",
+       "      <td>36558708</td>\n",
+       "      <td>260</td>\n",
+       "      <td>27361057</td>\n",
+       "      <td>366</td>\n",
+       "      <td>1.336158</td>\n",
+       "      <td>Priority Banking</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>4.410392e+07</td>\n",
+       "      <td>3.076443e+07</td>\n",
+       "      <td>1.729168</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10011</th>\n",
+       "      <td>PN293003</td>\n",
+       "      <td>33990478</td>\n",
+       "      <td>255</td>\n",
+       "      <td>24465835</td>\n",
+       "      <td>323</td>\n",
+       "      <td>1.389304</td>\n",
+       "      <td>Others</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>6.334963e+07</td>\n",
+       "      <td>4.223903e+07</td>\n",
+       "      <td>1.740112</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10012</th>\n",
+       "      <td>PN534105</td>\n",
+       "      <td>39934813</td>\n",
+       "      <td>278</td>\n",
+       "      <td>28247858</td>\n",
+       "      <td>403</td>\n",
+       "      <td>1.413729</td>\n",
+       "      <td>Others</td>\n",
+       "      <td>High Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>6.334963e+07</td>\n",
+       "      <td>4.223903e+07</td>\n",
+       "      <td>1.740112</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10013</th>\n",
+       "      <td>PN390430</td>\n",
+       "      <td>36894062</td>\n",
+       "      <td>257</td>\n",
+       "      <td>29162252</td>\n",
+       "      <td>371</td>\n",
+       "      <td>1.265131</td>\n",
+       "      <td>Private Banking</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>4.461828e+07</td>\n",
+       "      <td>3.176446e+07</td>\n",
+       "      <td>1.760285</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>10014 rows × 12 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       Focal_id  Credit_transaction_amount  Total_no_of_credit_transactions  \\\n",
+       "0      PN489144                 2830802741                             2060   \n",
+       "1      PN394780                 2872685364                             2029   \n",
+       "2      PN195722                 5604208368                             3937   \n",
+       "3      PN652566                 1630905248                             1152   \n",
+       "4      PN181960                 2157634332                             1613   \n",
+       "...         ...                        ...                              ...   \n",
+       "10009  PN479491                   31124877                              246   \n",
+       "10010  PN267550                   36558708                              260   \n",
+       "10011  PN293003                   33990478                              255   \n",
+       "10012  PN534105                   39934813                              278   \n",
+       "10013  PN390430                   36894062                              257   \n",
+       "\n",
+       "       Debit_transaction_amount  Total_no_of_debit_transactions  Wash_Ratio  \\\n",
+       "0                    2847556186                            1976    0.994117   \n",
+       "1                    2743931855                            1999    1.046923   \n",
+       "2                    5557946505                            4039    1.008324   \n",
+       "3                    1686713614                            1169    0.966913   \n",
+       "4                    2039953312                            1552    1.057688   \n",
+       "...                         ...                             ...         ...   \n",
+       "10009                  23590191                             357    1.319399   \n",
+       "10010                  27361057                             366    1.336158   \n",
+       "10011                  24465835                             323    1.389304   \n",
+       "10012                  28247858                             403    1.413729   \n",
+       "10013                  29162252                             371    1.265131   \n",
+       "\n",
+       "                  Segment       Risk SAR_FLAG    P90_Credit     P90_Debit  \\\n",
+       "0      Whole Sale Banking   Low Risk        N  4.400246e+09  4.332448e+09   \n",
+       "1      Whole Sale Banking   Low Risk        N  4.400246e+09  4.332448e+09   \n",
+       "2                     SME   Low Risk        N  4.532321e+09  4.534860e+09   \n",
+       "3      Whole Sale Banking   Low Risk        N  4.400246e+09  4.332448e+09   \n",
+       "4       Corporate Banking   Low Risk        N  5.021582e+09  5.003501e+09   \n",
+       "...                   ...        ...      ...           ...           ...   \n",
+       "10009     Private Banking   Low Risk        N  4.461828e+07  3.176446e+07   \n",
+       "10010    Priority Banking   Low Risk        N  4.410392e+07  3.076443e+07   \n",
+       "10011              Others   Low Risk        N  6.334963e+07  4.223903e+07   \n",
+       "10012              Others  High Risk        N  6.334963e+07  4.223903e+07   \n",
+       "10013     Private Banking   Low Risk        N  4.461828e+07  3.176446e+07   \n",
+       "\n",
+       "       P90_Wash  \n",
+       "0      1.058020  \n",
+       "1      1.058020  \n",
+       "2      1.062759  \n",
+       "3      1.058020  \n",
+       "4      1.063161  \n",
+       "...         ...  \n",
+       "10009  1.760285  \n",
+       "10010  1.729168  \n",
+       "10011  1.740112  \n",
+       "10012  1.740112  \n",
+       "10013  1.760285  \n",
+       "\n",
+       "[10014 rows x 12 columns]"
+      ]
+     },
+     "execution_count": 86,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "# a"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 81,
+   "execution_count": 88,
    "id": "150bb5ce-6be1-44fc-a606-6d375354626d",
    "metadata": {
     "tags": []
diff --git a/main.ipynb b/main.ipynb
index a083585..0632273 100644
--- a/main.ipynb
+++ b/main.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": [
+       "<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>Credit_transaction_amount</th>\n",
+       "      <th>Total_no_of_credit_transactions</th>\n",
+       "      <th>Debit_transaction_amount</th>\n",
+       "      <th>Total_no_of_debit_transactions</th>\n",
+       "      <th>Wash_Ratio</th>\n",
+       "      <th>Segment</th>\n",
+       "      <th>Risk</th>\n",
+       "      <th>SAR_FLAG</th>\n",
+       "      <th>P90_Credit</th>\n",
+       "      <th>P90_Debit</th>\n",
+       "      <th>P90_Wash</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>PN489144</td>\n",
+       "      <td>2830802741</td>\n",
+       "      <td>2060</td>\n",
+       "      <td>2847556186</td>\n",
+       "      <td>1976</td>\n",
+       "      <td>0.994117</td>\n",
+       "      <td>Whole Sale Banking</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>4.400246e+09</td>\n",
+       "      <td>4.332448e+09</td>\n",
+       "      <td>1.058020</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>PN394780</td>\n",
+       "      <td>2872685364</td>\n",
+       "      <td>2029</td>\n",
+       "      <td>2743931855</td>\n",
+       "      <td>1999</td>\n",
+       "      <td>1.046923</td>\n",
+       "      <td>Whole Sale Banking</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>4.400246e+09</td>\n",
+       "      <td>4.332448e+09</td>\n",
+       "      <td>1.058020</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>PN195722</td>\n",
+       "      <td>5604208368</td>\n",
+       "      <td>3937</td>\n",
+       "      <td>5557946505</td>\n",
+       "      <td>4039</td>\n",
+       "      <td>1.008324</td>\n",
+       "      <td>SME</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>4.532321e+09</td>\n",
+       "      <td>4.534860e+09</td>\n",
+       "      <td>1.062759</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>PN652566</td>\n",
+       "      <td>1630905248</td>\n",
+       "      <td>1152</td>\n",
+       "      <td>1686713614</td>\n",
+       "      <td>1169</td>\n",
+       "      <td>0.966913</td>\n",
+       "      <td>Whole Sale Banking</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>4.400246e+09</td>\n",
+       "      <td>4.332448e+09</td>\n",
+       "      <td>1.058020</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>PN181960</td>\n",
+       "      <td>2157634332</td>\n",
+       "      <td>1613</td>\n",
+       "      <td>2039953312</td>\n",
+       "      <td>1552</td>\n",
+       "      <td>1.057688</td>\n",
+       "      <td>Corporate Banking</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>5.021582e+09</td>\n",
+       "      <td>5.003501e+09</td>\n",
+       "      <td>1.063161</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",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10009</th>\n",
+       "      <td>PN479491</td>\n",
+       "      <td>31124877</td>\n",
+       "      <td>246</td>\n",
+       "      <td>23590191</td>\n",
+       "      <td>357</td>\n",
+       "      <td>1.319399</td>\n",
+       "      <td>Private Banking</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>4.461828e+07</td>\n",
+       "      <td>3.176446e+07</td>\n",
+       "      <td>1.760285</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10010</th>\n",
+       "      <td>PN267550</td>\n",
+       "      <td>36558708</td>\n",
+       "      <td>260</td>\n",
+       "      <td>27361057</td>\n",
+       "      <td>366</td>\n",
+       "      <td>1.336158</td>\n",
+       "      <td>Priority Banking</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>4.410392e+07</td>\n",
+       "      <td>3.076443e+07</td>\n",
+       "      <td>1.729168</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10011</th>\n",
+       "      <td>PN293003</td>\n",
+       "      <td>33990478</td>\n",
+       "      <td>255</td>\n",
+       "      <td>24465835</td>\n",
+       "      <td>323</td>\n",
+       "      <td>1.389304</td>\n",
+       "      <td>Others</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>6.334963e+07</td>\n",
+       "      <td>4.223903e+07</td>\n",
+       "      <td>1.740112</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10012</th>\n",
+       "      <td>PN534105</td>\n",
+       "      <td>39934813</td>\n",
+       "      <td>278</td>\n",
+       "      <td>28247858</td>\n",
+       "      <td>403</td>\n",
+       "      <td>1.413729</td>\n",
+       "      <td>Others</td>\n",
+       "      <td>High Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>6.334963e+07</td>\n",
+       "      <td>4.223903e+07</td>\n",
+       "      <td>1.740112</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10013</th>\n",
+       "      <td>PN390430</td>\n",
+       "      <td>36894062</td>\n",
+       "      <td>257</td>\n",
+       "      <td>29162252</td>\n",
+       "      <td>371</td>\n",
+       "      <td>1.265131</td>\n",
+       "      <td>Private Banking</td>\n",
+       "      <td>Low Risk</td>\n",
+       "      <td>N</td>\n",
+       "      <td>4.461828e+07</td>\n",
+       "      <td>3.176446e+07</td>\n",
+       "      <td>1.760285</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>10014 rows × 12 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       Focal_id  Credit_transaction_amount  Total_no_of_credit_transactions  \\\n",
+       "0      PN489144                 2830802741                             2060   \n",
+       "1      PN394780                 2872685364                             2029   \n",
+       "2      PN195722                 5604208368                             3937   \n",
+       "3      PN652566                 1630905248                             1152   \n",
+       "4      PN181960                 2157634332                             1613   \n",
+       "...         ...                        ...                              ...   \n",
+       "10009  PN479491                   31124877                              246   \n",
+       "10010  PN267550                   36558708                              260   \n",
+       "10011  PN293003                   33990478                              255   \n",
+       "10012  PN534105                   39934813                              278   \n",
+       "10013  PN390430                   36894062                              257   \n",
+       "\n",
+       "       Debit_transaction_amount  Total_no_of_debit_transactions  Wash_Ratio  \\\n",
+       "0                    2847556186                            1976    0.994117   \n",
+       "1                    2743931855                            1999    1.046923   \n",
+       "2                    5557946505                            4039    1.008324   \n",
+       "3                    1686713614                            1169    0.966913   \n",
+       "4                    2039953312                            1552    1.057688   \n",
+       "...                         ...                             ...         ...   \n",
+       "10009                  23590191                             357    1.319399   \n",
+       "10010                  27361057                             366    1.336158   \n",
+       "10011                  24465835                             323    1.389304   \n",
+       "10012                  28247858                             403    1.413729   \n",
+       "10013                  29162252                             371    1.265131   \n",
+       "\n",
+       "                  Segment       Risk SAR_FLAG    P90_Credit     P90_Debit  \\\n",
+       "0      Whole Sale Banking   Low Risk        N  4.400246e+09  4.332448e+09   \n",
+       "1      Whole Sale Banking   Low Risk        N  4.400246e+09  4.332448e+09   \n",
+       "2                     SME   Low Risk        N  4.532321e+09  4.534860e+09   \n",
+       "3      Whole Sale Banking   Low Risk        N  4.400246e+09  4.332448e+09   \n",
+       "4       Corporate Banking   Low Risk        N  5.021582e+09  5.003501e+09   \n",
+       "...                   ...        ...      ...           ...           ...   \n",
+       "10009     Private Banking   Low Risk        N  4.461828e+07  3.176446e+07   \n",
+       "10010    Priority Banking   Low Risk        N  4.410392e+07  3.076443e+07   \n",
+       "10011              Others   Low Risk        N  6.334963e+07  4.223903e+07   \n",
+       "10012              Others  High Risk        N  6.334963e+07  4.223903e+07   \n",
+       "10013     Private Banking   Low Risk        N  4.461828e+07  3.176446e+07   \n",
+       "\n",
+       "       P90_Wash  \n",
+       "0      1.058020  \n",
+       "1      1.058020  \n",
+       "2      1.062759  \n",
+       "3      1.058020  \n",
+       "4      1.063161  \n",
+       "...         ...  \n",
+       "10009  1.760285  \n",
+       "10010  1.729168  \n",
+       "10011  1.740112  \n",
+       "10012  1.740112  \n",
+       "10013  1.760285  \n",
+       "\n",
+       "[10014 rows x 12 columns]"
+      ]
+     },
+     "execution_count": 86,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "# a"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 81,
+   "execution_count": 88,
    "id": "150bb5ce-6be1-44fc-a606-6d375354626d",
    "metadata": {
     "tags": []
diff --git a/main.py b/main.py
index 71fc2fc..205b8b8 100644
--- a/main.py
+++ b/main.py
@@ -114,7 +114,7 @@ query = """
 """
 
 
-# In[77]:
+# In[84]:
 
 
 from tms_data_interface import SQLQueryInterface
@@ -164,7 +164,7 @@ class Scenario:
         )
 
         # Step 4: Randomly select 0.1% sample from high-risk population
-        sample_fraction = 0.1  # 0.1%
+        sample_fraction = 0.3  # 0.1%
         high_pop_indices = df[high_pop].sample(frac=sample_fraction, random_state=42).index
 
         # Step 5: Set SAR_FLAG values
@@ -173,20 +173,20 @@ class Scenario:
         return df
 
 
-# In[83]:
+# In[85]:
 
 
 # sen = Scenario()
 # a = sen.logic()
 
 
-# In[82]:
+# In[86]:
 
 
 # a
 
 
-# In[81]:
+# In[88]:
 
 
 # a[a["SAR_FLAG"] == "Y"]