diff --git a/.DS_Store b/.DS_Store
deleted file mode 100644
index 01222e6..0000000
Binary files a/.DS_Store and /dev/null differ
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..87620ac
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+.ipynb_checkpoints/
diff --git a/lab-dw-data-structuring-and-combining.ipynb b/lab-dw-data-structuring-and-combining.ipynb
index ec4e3f9..235315b 100644
--- a/lab-dw-data-structuring-and-combining.ipynb
+++ b/lab-dw-data-structuring-and-combining.ipynb
@@ -36,16 +36,984 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "492d06e3-92c7-4105-ac72-536db98d3244",
-   "metadata": {
-    "id": "492d06e3-92c7-4105-ac72-536db98d3244"
-   },
-   "outputs": [],
+   "execution_count": 1,
+   "id": "c56f21e2-c016-4f75-8324-150fe4ce18a5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "File 1 shape: (4008, 11)\n",
+      "File 2 shape: (996, 11)\n",
+      "File 3 shape: (7070, 11)\n",
+      "\n",
+      "File 1 columns:\n",
+      "['customer', 'state', 'gender', 'education', 'customer_lifetime_value', 'income', 'monthly_premium_auto', 'number_of_open_complaints', 'policy_type', 'vehicle_class', 'total_claim_amount']\n",
+      "\n",
+      "File 2 columns:\n",
+      "['customer', 'state', 'gender', 'education', 'customer_lifetime_value', 'income', 'monthly_premium_auto', 'number_of_open_complaints', 'total_claim_amount', 'policy_type', 'vehicle_class']\n",
+      "\n",
+      "File 3 columns:\n",
+      "['customer', 'state', 'customer_lifetime_value', 'education', 'gender', 'income', 'monthly_premium_auto', 'number_of_open_complaints', 'policy_type', 'total_claim_amount', 'vehicle_class']\n",
+      "\n",
+      "Columns missing from File 1:\n",
+      "[]\n",
+      "\n",
+      "Columns missing from File 2:\n",
+      "[]\n",
+      "\n",
+      "Columns missing from File 3:\n",
+      "[]\n",
+      "\n",
+      "Combined dataset shape before cleaning: (12074, 11)\n",
+      "\n",
+      "Missing values before cleaning:\n"
+     ]
+    },
+    {
+     "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>missing_values</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>gender</th>\n",
+       "      <td>3059</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>customer_lifetime_value</th>\n",
+       "      <td>2944</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>customer</th>\n",
+       "      <td>2937</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>state</th>\n",
+       "      <td>2937</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>education</th>\n",
+       "      <td>2937</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>income</th>\n",
+       "      <td>2937</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <td>2937</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <td>2937</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>policy_type</th>\n",
+       "      <td>2937</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>vehicle_class</th>\n",
+       "      <td>2937</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>total_claim_amount</th>\n",
+       "      <td>2937</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                           missing_values\n",
+       "gender                               3059\n",
+       "customer_lifetime_value              2944\n",
+       "customer                             2937\n",
+       "state                                2937\n",
+       "education                            2937\n",
+       "income                               2937\n",
+       "monthly_premium_auto                 2937\n",
+       "number_of_open_complaints            2937\n",
+       "policy_type                          2937\n",
+       "vehicle_class                        2937\n",
+       "total_claim_amount                   2937"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Missing values after cleaning:\n"
+     ]
+    },
+    {
+     "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>missing_values</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>customer</th>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>state</th>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>gender</th>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>education</th>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>customer_lifetime_value</th>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>income</th>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>policy_type</th>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>vehicle_class</th>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>total_claim_amount</th>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                           missing_values\n",
+       "customer                                0\n",
+       "state                                   0\n",
+       "gender                                  0\n",
+       "education                               0\n",
+       "customer_lifetime_value                 0\n",
+       "income                                  0\n",
+       "monthly_premium_auto                    0\n",
+       "number_of_open_complaints               0\n",
+       "policy_type                             0\n",
+       "vehicle_class                           0\n",
+       "total_claim_amount                      0"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Cleaning results:\n",
+      "Final shape: (9134, 11)\n",
+      "Duplicates removed: 3\n",
+      "Remaining duplicates: 0\n",
+      "Remaining missing values: 0\n",
+      "\n",
+      "Final columns:\n",
+      "['customer', 'state', 'gender', 'education', 'customer_lifetime_value', 'income', 'monthly_premium_auto', 'number_of_open_complaints', 'policy_type', 'vehicle_class', 'total_claim_amount']\n",
+      "\n",
+      "Final data types:\n"
+     ]
+    },
+    {
+     "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>data_type</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>customer</th>\n",
+       "      <td>string</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>state</th>\n",
+       "      <td>string</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>gender</th>\n",
+       "      <td>string</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>education</th>\n",
+       "      <td>string</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>customer_lifetime_value</th>\n",
+       "      <td>Float64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>income</th>\n",
+       "      <td>int64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <td>float64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <td>int64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>policy_type</th>\n",
+       "      <td>string</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>vehicle_class</th>\n",
+       "      <td>string</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>total_claim_amount</th>\n",
+       "      <td>float64</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                          data_type\n",
+       "customer                     string\n",
+       "state                        string\n",
+       "gender                       string\n",
+       "education                    string\n",
+       "customer_lifetime_value     Float64\n",
+       "income                        int64\n",
+       "monthly_premium_auto        float64\n",
+       "number_of_open_complaints     int64\n",
+       "policy_type                  string\n",
+       "vehicle_class                string\n",
+       "total_claim_amount          float64"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "First 10 cleaned rows:\n"
+     ]
+    },
+    {
+     "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>customer</th>\n",
+       "      <th>state</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>education</th>\n",
+       "      <th>customer_lifetime_value</th>\n",
+       "      <th>income</th>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <th>policy_type</th>\n",
+       "      <th>vehicle_class</th>\n",
+       "      <th>total_claim_amount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>RB50392</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>7714.88</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1000.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>2.70</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>QZ44356</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>697953.59</td>\n",
+       "      <td>0</td>\n",
+       "      <td>94.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>1131.46</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>AI49188</td>\n",
+       "      <td>Nevada</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>1288743.17</td>\n",
+       "      <td>48767</td>\n",
+       "      <td>108.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>566.47</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>WW63253</td>\n",
+       "      <td>California</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>764586.18</td>\n",
+       "      <td>0</td>\n",
+       "      <td>106.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>SUV</td>\n",
+       "      <td>529.88</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>GA49547</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>High School or Below</td>\n",
+       "      <td>536307.65</td>\n",
+       "      <td>36357</td>\n",
+       "      <td>68.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>17.27</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>OC83172</td>\n",
+       "      <td>Oregon</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>825629.78</td>\n",
+       "      <td>62902</td>\n",
+       "      <td>69.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Two-Door Car</td>\n",
+       "      <td>159.38</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>XZ87318</td>\n",
+       "      <td>Oregon</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>College</td>\n",
+       "      <td>538089.86</td>\n",
+       "      <td>55350</td>\n",
+       "      <td>67.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>321.60</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>CF85061</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>Master</td>\n",
+       "      <td>721610.03</td>\n",
+       "      <td>0</td>\n",
+       "      <td>101.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>363.03</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>DY87989</td>\n",
+       "      <td>Oregon</td>\n",
+       "      <td>Male</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2412750.4</td>\n",
+       "      <td>14072</td>\n",
+       "      <td>71.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>511.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>BQ94931</td>\n",
+       "      <td>Oregon</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>College</td>\n",
+       "      <td>738817.81</td>\n",
+       "      <td>28812</td>\n",
+       "      <td>93.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>Special Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>425.53</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  customer       state  gender             education  customer_lifetime_value  \\\n",
+       "0  RB50392  Washington  Female                Master                  7714.88   \n",
+       "1  QZ44356     Arizona  Female              Bachelor                697953.59   \n",
+       "2  AI49188      Nevada  Female              Bachelor               1288743.17   \n",
+       "3  WW63253  California    Male              Bachelor                764586.18   \n",
+       "4  GA49547  Washington    Male  High School or Below                536307.65   \n",
+       "5  OC83172      Oregon  Female              Bachelor                825629.78   \n",
+       "6  XZ87318      Oregon  Female               College                538089.86   \n",
+       "7  CF85061     Arizona    Male                Master                721610.03   \n",
+       "8  DY87989      Oregon    Male              Bachelor                2412750.4   \n",
+       "9  BQ94931      Oregon  Female               College                738817.81   \n",
+       "\n",
+       "   income  monthly_premium_auto  number_of_open_complaints     policy_type  \\\n",
+       "0       0                1000.0                          0   Personal Auto   \n",
+       "1       0                  94.0                          0   Personal Auto   \n",
+       "2   48767                 108.0                          0   Personal Auto   \n",
+       "3       0                 106.0                          0  Corporate Auto   \n",
+       "4   36357                  68.0                          0   Personal Auto   \n",
+       "5   62902                  69.0                          0   Personal Auto   \n",
+       "6   55350                  67.0                          0  Corporate Auto   \n",
+       "7       0                 101.0                          0  Corporate Auto   \n",
+       "8   14072                  71.0                          0  Corporate Auto   \n",
+       "9   28812                  93.0                          0    Special Auto   \n",
+       "\n",
+       "   vehicle_class  total_claim_amount  \n",
+       "0  Four-Door Car                2.70  \n",
+       "1  Four-Door Car             1131.46  \n",
+       "2   Two-Door Car              566.47  \n",
+       "3            SUV              529.88  \n",
+       "4  Four-Door Car               17.27  \n",
+       "5   Two-Door Car              159.38  \n",
+       "6  Four-Door Car              321.60  \n",
+       "7  Four-Door Car              363.03  \n",
+       "8  Four-Door Car              511.20  \n",
+       "9  Four-Door Car              425.53  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Numerical summary:\n"
+     ]
+    },
+    {
+     "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>customer_lifetime_value</th>\n",
+       "      <th>income</th>\n",
+       "      <th>monthly_premium_auto</th>\n",
+       "      <th>number_of_open_complaints</th>\n",
+       "      <th>total_claim_amount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>9134.0</td>\n",
+       "      <td>9134.00</td>\n",
+       "      <td>9134.00</td>\n",
+       "      <td>9134.00</td>\n",
+       "      <td>9134.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>181937.9</td>\n",
+       "      <td>37824.85</td>\n",
+       "      <td>110.39</td>\n",
+       "      <td>0.38</td>\n",
+       "      <td>430.48</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>440903.85</td>\n",
+       "      <td>30359.23</td>\n",
+       "      <td>581.47</td>\n",
+       "      <td>0.91</td>\n",
+       "      <td>289.62</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>1898.01</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>61.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>4650.06</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>68.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>266.96</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>7714.88</td>\n",
+       "      <td>34240.00</td>\n",
+       "      <td>83.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>377.50</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>26131.72</td>\n",
+       "      <td>62446.50</td>\n",
+       "      <td>109.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>546.05</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>5816655.35</td>\n",
+       "      <td>99981.00</td>\n",
+       "      <td>35354.00</td>\n",
+       "      <td>5.00</td>\n",
+       "      <td>2893.24</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       customer_lifetime_value    income  monthly_premium_auto  \\\n",
+       "count                   9134.0   9134.00               9134.00   \n",
+       "mean                  181937.9  37824.85                110.39   \n",
+       "std                  440903.85  30359.23                581.47   \n",
+       "min                    1898.01      0.00                 61.00   \n",
+       "25%                    4650.06      0.00                 68.00   \n",
+       "50%                    7714.88  34240.00                 83.00   \n",
+       "75%                   26131.72  62446.50                109.00   \n",
+       "max                 5816655.35  99981.00              35354.00   \n",
+       "\n",
+       "       number_of_open_complaints  total_claim_amount  \n",
+       "count                    9134.00             9134.00  \n",
+       "mean                        0.38              430.48  \n",
+       "std                         0.91              289.62  \n",
+       "min                         0.00                0.10  \n",
+       "25%                         0.00              266.96  \n",
+       "50%                         0.00              377.50  \n",
+       "75%                         0.00              546.05  \n",
+       "max                         5.00             2893.24  "
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Categorical summary:\n"
+     ]
+    },
+    {
+     "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>customer</th>\n",
+       "      <th>state</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>education</th>\n",
+       "      <th>policy_type</th>\n",
+       "      <th>vehicle_class</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>9134</td>\n",
+       "      <td>9134</td>\n",
+       "      <td>9134</td>\n",
+       "      <td>9134</td>\n",
+       "      <td>9134</td>\n",
+       "      <td>9134</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>unique</th>\n",
+       "      <td>9056</td>\n",
+       "      <td>5</td>\n",
+       "      <td>2</td>\n",
+       "      <td>5</td>\n",
+       "      <td>3</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>top</th>\n",
+       "      <td>GA49547</td>\n",
+       "      <td>California</td>\n",
+       "      <td>Female</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>freq</th>\n",
+       "      <td>2</td>\n",
+       "      <td>3150</td>\n",
+       "      <td>4726</td>\n",
+       "      <td>2742</td>\n",
+       "      <td>6790</td>\n",
+       "      <td>4640</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       customer       state  gender education    policy_type  vehicle_class\n",
+       "count      9134        9134    9134      9134           9134           9134\n",
+       "unique     9056           5       2         5              3              4\n",
+       "top     GA49547  California  Female  Bachelor  Personal Auto  Four-Door Car\n",
+       "freq          2        3150    4726      2742           6790           4640"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Cleaned dataset saved as cleaned_customer_data.csv\n"
+     ]
+    }
+   ],
    "source": [
-    "# Your code goes here"
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from IPython.display import display\n",
+    "\n",
+    "url1 = \"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file1.csv\"\n",
+    "url2 = \"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file2.csv\"\n",
+    "url3 = \"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/file3.csv\"\n",
+    "\n",
+    "df1 = pd.read_csv(url1)\n",
+    "df2 = pd.read_csv(url2)\n",
+    "df3 = pd.read_csv(url3)\n",
+    "\n",
+    "def standardize_columns(dataframe):\n",
+    "    dataframe = dataframe.copy()\n",
+    "    dataframe.columns = dataframe.columns.str.strip().str.lower().str.replace(\" \", \"_\", regex=False)\n",
+    "    dataframe = dataframe.rename(columns={\"st\": \"state\"})\n",
+    "    return dataframe\n",
+    "\n",
+    "df1 = standardize_columns(df1)\n",
+    "df2 = standardize_columns(df2)\n",
+    "df3 = standardize_columns(df3)\n",
+    "\n",
+    "print(\"File 1 shape:\", df1.shape)\n",
+    "print(\"File 2 shape:\", df2.shape)\n",
+    "print(\"File 3 shape:\", df3.shape)\n",
+    "\n",
+    "print(\"\\nFile 1 columns:\")\n",
+    "print(df1.columns.tolist())\n",
+    "\n",
+    "print(\"\\nFile 2 columns:\")\n",
+    "print(df2.columns.tolist())\n",
+    "\n",
+    "print(\"\\nFile 3 columns:\")\n",
+    "print(df3.columns.tolist())\n",
+    "\n",
+    "all_columns = sorted(set(df1.columns) | set(df2.columns) | set(df3.columns))\n",
+    "\n",
+    "print(\"\\nColumns missing from File 1:\")\n",
+    "print(sorted(set(all_columns) - set(df1.columns)))\n",
+    "\n",
+    "print(\"\\nColumns missing from File 2:\")\n",
+    "print(sorted(set(all_columns) - set(df2.columns)))\n",
+    "\n",
+    "print(\"\\nColumns missing from File 3:\")\n",
+    "print(sorted(set(all_columns) - set(df3.columns)))\n",
+    "\n",
+    "df = pd.concat([df1, df2, df3], ignore_index=True, sort=False)\n",
+    "\n",
+    "print(\"\\nCombined dataset shape before cleaning:\", df.shape)\n",
+    "\n",
+    "print(\"\\nMissing values before cleaning:\")\n",
+    "display(df.isnull().sum().sort_values(ascending=False).to_frame(\"missing_values\"))\n",
+    "\n",
+    "df = df.dropna(how=\"all\").reset_index(drop=True)\n",
+    "\n",
+    "text_columns = df.select_dtypes(include=[\"object\", \"string\"]).columns\n",
+    "\n",
+    "for column in text_columns:\n",
+    "    df[column] = df[column].astype(\"string\").str.strip()\n",
+    "\n",
+    "if \"gender\" in df.columns:\n",
+    "    df[\"gender\"] = df[\"gender\"].str.lower().replace({\n",
+    "        \"m\": \"Male\",\n",
+    "        \"male\": \"Male\",\n",
+    "        \"f\": \"Female\",\n",
+    "        \"female\": \"Female\",\n",
+    "        \"femal\": \"Female\"\n",
+    "    })\n",
+    "\n",
+    "if \"state\" in df.columns:\n",
+    "    df[\"state\"] = df[\"state\"].replace({\n",
+    "        \"AZ\": \"Arizona\",\n",
+    "        \"Cali\": \"California\",\n",
+    "        \"WA\": \"Washington\"\n",
+    "    })\n",
+    "\n",
+    "if \"education\" in df.columns:\n",
+    "    df[\"education\"] = df[\"education\"].replace({\n",
+    "        \"Bachelors\": \"Bachelor\"\n",
+    "    })\n",
+    "\n",
+    "if \"vehicle_class\" in df.columns:\n",
+    "    df[\"vehicle_class\"] = df[\"vehicle_class\"].replace({\n",
+    "        \"Sports Car\": \"Luxury\",\n",
+    "        \"Luxury SUV\": \"Luxury\",\n",
+    "        \"Luxury Car\": \"Luxury\"\n",
+    "    })\n",
+    "\n",
+    "if \"customer_lifetime_value\" in df.columns:\n",
+    "    df[\"customer_lifetime_value\"] = pd.to_numeric(\n",
+    "        df[\"customer_lifetime_value\"].astype(\"string\").str.replace(\"%\", \"\", regex=False).str.replace(\",\", \"\", regex=False),\n",
+    "        errors=\"coerce\"\n",
+    "    )\n",
+    "\n",
+    "def clean_complaints(value):\n",
+    "    if pd.isna(value):\n",
+    "        return np.nan\n",
+    "\n",
+    "    value = str(value).strip()\n",
+    "\n",
+    "    if \"/\" in value:\n",
+    "        parts = value.split(\"/\")\n",
+    "        if len(parts) > 1:\n",
+    "            return pd.to_numeric(parts[1], errors=\"coerce\")\n",
+    "\n",
+    "    return pd.to_numeric(value, errors=\"coerce\")\n",
+    "\n",
+    "if \"number_of_open_complaints\" in df.columns:\n",
+    "    df[\"number_of_open_complaints\"] = df[\"number_of_open_complaints\"].apply(clean_complaints)\n",
+    "\n",
+    "numeric_columns = [\"income\", \"monthly_premium_auto\", \"total_claim_amount\"]\n",
+    "\n",
+    "for column in numeric_columns:\n",
+    "    if column in df.columns:\n",
+    "        df[column] = pd.to_numeric(df[column], errors=\"coerce\")\n",
+    "\n",
+    "categorical_columns = df.select_dtypes(include=[\"object\", \"string\"]).columns\n",
+    "\n",
+    "for column in categorical_columns:\n",
+    "    mode_value = df[column].mode(dropna=True)\n",
+    "    if not mode_value.empty:\n",
+    "        df[column] = df[column].fillna(mode_value.iloc[0])\n",
+    "\n",
+    "numeric_columns_to_fill = [\n",
+    "    \"customer_lifetime_value\",\n",
+    "    \"income\",\n",
+    "    \"monthly_premium_auto\",\n",
+    "    \"number_of_open_complaints\",\n",
+    "    \"total_claim_amount\"\n",
+    "]\n",
+    "\n",
+    "for column in numeric_columns_to_fill:\n",
+    "    if column in df.columns:\n",
+    "        df[column] = df[column].fillna(df[column].median())\n",
+    "\n",
+    "duplicates_before = df.duplicated().sum()\n",
+    "\n",
+    "df = df.drop_duplicates().reset_index(drop=True)\n",
+    "\n",
+    "decimal_columns = [\"customer_lifetime_value\", \"monthly_premium_auto\", \"total_claim_amount\"]\n",
+    "\n",
+    "for column in decimal_columns:\n",
+    "    if column in df.columns:\n",
+    "        df[column] = df[column].round(2)\n",
+    "\n",
+    "if \"income\" in df.columns:\n",
+    "    df[\"income\"] = df[\"income\"].round().astype(int)\n",
+    "\n",
+    "if \"number_of_open_complaints\" in df.columns:\n",
+    "    df[\"number_of_open_complaints\"] = df[\"number_of_open_complaints\"].round().astype(int)\n",
+    "\n",
+    "print(\"\\nMissing values after cleaning:\")\n",
+    "display(df.isnull().sum().sort_values(ascending=False).to_frame(\"missing_values\"))\n",
+    "\n",
+    "print(\"\\nCleaning results:\")\n",
+    "print(\"Final shape:\", df.shape)\n",
+    "print(\"Duplicates removed:\", duplicates_before)\n",
+    "print(\"Remaining duplicates:\", df.duplicated().sum())\n",
+    "print(\"Remaining missing values:\", df.isnull().sum().sum())\n",
+    "\n",
+    "print(\"\\nFinal columns:\")\n",
+    "print(df.columns.tolist())\n",
+    "\n",
+    "print(\"\\nFinal data types:\")\n",
+    "display(df.dtypes.to_frame(\"data_type\"))\n",
+    "\n",
+    "print(\"\\nFirst 10 cleaned rows:\")\n",
+    "display(df.head(10))\n",
+    "\n",
+    "print(\"\\nNumerical summary:\")\n",
+    "display(df.describe().round(2))\n",
+    "\n",
+    "print(\"\\nCategorical summary:\")\n",
+    "display(df.describe(include=[\"object\", \"string\"]))\n",
+    "\n",
+    "df.to_csv(\"cleaned_customer_data.csv\", index=False)\n",
+    "\n",
+    "print(\"\\nCleaned dataset saved as cleaned_customer_data.csv\")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "33075a50-53a1-46ff-ba48-dd656d91fad1",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "markdown",
    "id": "31b8a9e7-7db9-4604-991b-ef6771603e57",
@@ -72,14 +1040,571 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "aa10d9b0-1c27-4d3f-a8e4-db6ab73bfd26",
    "metadata": {
     "id": "aa10d9b0-1c27-4d3f-a8e4-db6ab73bfd26"
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dataset shape: (10910, 27)\n"
+     ]
+    },
+    {
+     "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>unnamed:_0</th>\n",
+       "      <th>customer</th>\n",
+       "      <th>state</th>\n",
+       "      <th>customer_lifetime_value</th>\n",
+       "      <th>response</th>\n",
+       "      <th>coverage</th>\n",
+       "      <th>education</th>\n",
+       "      <th>effective_to_date</th>\n",
+       "      <th>employmentstatus</th>\n",
+       "      <th>gender</th>\n",
+       "      <th>...</th>\n",
+       "      <th>number_of_policies</th>\n",
+       "      <th>policy_type</th>\n",
+       "      <th>policy</th>\n",
+       "      <th>renew_offer_type</th>\n",
+       "      <th>sales_channel</th>\n",
+       "      <th>total_claim_amount</th>\n",
+       "      <th>vehicle_class</th>\n",
+       "      <th>vehicle_size</th>\n",
+       "      <th>vehicle_type</th>\n",
+       "      <th>month</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>DK49336</td>\n",
+       "      <td>Arizona</td>\n",
+       "      <td>4809.216960</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2011-02-18</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>...</td>\n",
+       "      <td>9</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L3</td>\n",
+       "      <td>Offer3</td>\n",
+       "      <td>Agent</td>\n",
+       "      <td>292.800000</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "      <td>A</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>1</td>\n",
+       "      <td>KX64629</td>\n",
+       "      <td>California</td>\n",
+       "      <td>2228.525238</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2011-01-18</td>\n",
+       "      <td>Unemployed</td>\n",
+       "      <td>F</td>\n",
+       "      <td>...</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L3</td>\n",
+       "      <td>Offer4</td>\n",
+       "      <td>Call Center</td>\n",
+       "      <td>744.924331</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "      <td>A</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2</td>\n",
+       "      <td>LZ68649</td>\n",
+       "      <td>Washington</td>\n",
+       "      <td>14947.917300</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Basic</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-02-10</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L3</td>\n",
+       "      <td>Offer3</td>\n",
+       "      <td>Call Center</td>\n",
+       "      <td>480.000000</td>\n",
+       "      <td>SUV</td>\n",
+       "      <td>Medsize</td>\n",
+       "      <td>A</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>3</td>\n",
+       "      <td>XL78013</td>\n",
+       "      <td>Oregon</td>\n",
+       "      <td>22332.439460</td>\n",
+       "      <td>Yes</td>\n",
+       "      <td>Extended</td>\n",
+       "      <td>College</td>\n",
+       "      <td>2011-01-11</td>\n",
+       "      <td>Employed</td>\n",
+       "      <td>M</td>\n",
+       "      <td>...</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>Corporate L3</td>\n",
+       "      <td>Offer2</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>484.013411</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "      <td>A</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>4</td>\n",
+       "      <td>QA50777</td>\n",
+       "      <td>Oregon</td>\n",
+       "      <td>9025.067525</td>\n",
+       "      <td>No</td>\n",
+       "      <td>Premium</td>\n",
+       "      <td>Bachelor</td>\n",
+       "      <td>2011-01-17</td>\n",
+       "      <td>Medical Leave</td>\n",
+       "      <td>F</td>\n",
+       "      <td>...</td>\n",
+       "      <td>7</td>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>Personal L2</td>\n",
+       "      <td>Offer1</td>\n",
+       "      <td>Branch</td>\n",
+       "      <td>707.925645</td>\n",
+       "      <td>Four-Door Car</td>\n",
+       "      <td>Medsize</td>\n",
+       "      <td>A</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 27 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   unnamed:_0 customer       state  customer_lifetime_value response  \\\n",
+       "0           0  DK49336     Arizona              4809.216960       No   \n",
+       "1           1  KX64629  California              2228.525238       No   \n",
+       "2           2  LZ68649  Washington             14947.917300       No   \n",
+       "3           3  XL78013      Oregon             22332.439460      Yes   \n",
+       "4           4  QA50777      Oregon              9025.067525       No   \n",
+       "\n",
+       "   coverage education effective_to_date employmentstatus gender  ...  \\\n",
+       "0     Basic   College        2011-02-18         Employed      M  ...   \n",
+       "1     Basic   College        2011-01-18       Unemployed      F  ...   \n",
+       "2     Basic  Bachelor        2011-02-10         Employed      M  ...   \n",
+       "3  Extended   College        2011-01-11         Employed      M  ...   \n",
+       "4   Premium  Bachelor        2011-01-17    Medical Leave      F  ...   \n",
+       "\n",
+       "   number_of_policies     policy_type        policy  renew_offer_type  \\\n",
+       "0                   9  Corporate Auto  Corporate L3            Offer3   \n",
+       "1                   1   Personal Auto   Personal L3            Offer4   \n",
+       "2                   2   Personal Auto   Personal L3            Offer3   \n",
+       "3                   2  Corporate Auto  Corporate L3            Offer2   \n",
+       "4                   7   Personal Auto   Personal L2            Offer1   \n",
+       "\n",
+       "   sales_channel  total_claim_amount  vehicle_class  vehicle_size  \\\n",
+       "0          Agent          292.800000  Four-Door Car       Medsize   \n",
+       "1    Call Center          744.924331  Four-Door Car       Medsize   \n",
+       "2    Call Center          480.000000            SUV       Medsize   \n",
+       "3         Branch          484.013411  Four-Door Car       Medsize   \n",
+       "4         Branch          707.925645  Four-Door Car       Medsize   \n",
+       "\n",
+       "  vehicle_type month  \n",
+       "0            A     2  \n",
+       "1            A     1  \n",
+       "2            A     2  \n",
+       "3            A     1  \n",
+       "4            A     1  \n",
+       "\n",
+       "[5 rows x 27 columns]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "from IPython.display import display\n",
+    "\n",
+    "url = \"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/marketing_customer_analysis_clean.csv\"\n",
+    "\n",
+    "df = pd.read_csv(url)\n",
+    "\n",
+    "print(\"Dataset shape:\", df.shape)\n",
+    "\n",
+    "display(\n",
+    "    df.head()\n",
+    ")\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "48cc4648-de99-424f-ba53-db9c346ad834",
+   "metadata": {},
+   "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>sales_channel</th>\n",
+       "      <th>total_revenue</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Agent</td>\n",
+       "      <td>1810226.82</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Branch</td>\n",
+       "      <td>1301204.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Call Center</td>\n",
+       "      <td>926600.82</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Web</td>\n",
+       "      <td>706600.04</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  sales_channel  total_revenue\n",
+       "0         Agent     1810226.82\n",
+       "1        Branch     1301204.00\n",
+       "2   Call Center      926600.82\n",
+       "3           Web      706600.04"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The sales channel with the highest total revenue is Agent with 1,810,226.82.\n",
+      "The sales channel with the lowest total revenue is Web with 706,600.04.\n",
+      "The revenue difference between the highest and lowest sales channels is 1,103,626.78.\n"
+     ]
+    }
+   ],
+   "source": [
+    "sales_channel_revenue = (\n",
+    "    pd.pivot_table(\n",
+    "        df,\n",
+    "        index=\"sales_channel\",\n",
+    "        values=\"total_claim_amount\",\n",
+    "        aggfunc=\"sum\"\n",
+    "    )\n",
+    "    .rename(\n",
+    "        columns={\n",
+    "            \"total_claim_amount\": \"total_revenue\"\n",
+    "        }\n",
+    "    )\n",
+    "    .sort_values(\n",
+    "        \"total_revenue\",\n",
+    "        ascending=False\n",
+    "    )\n",
+    "    .round(2)\n",
+    "    .reset_index()\n",
+    ")\n",
+    "\n",
+    "display(\n",
+    "    sales_channel_revenue\n",
+    ")\n",
+    "\n",
+    "top_channel = sales_channel_revenue.iloc[0]\n",
+    "\n",
+    "lowest_channel = sales_channel_revenue.iloc[-1]\n",
+    "\n",
+    "difference = (\n",
+    "    top_channel[\"total_revenue\"]\n",
+    "    - lowest_channel[\"total_revenue\"]\n",
+    ")\n",
+    "\n",
+    "print(\n",
+    "    f\"The sales channel with the highest total revenue is \"\n",
+    "    f\"{top_channel['sales_channel']} with \"\n",
+    "    f\"{top_channel['total_revenue']:,.2f}.\"\n",
+    ")\n",
+    "\n",
+    "print(\n",
+    "    f\"The sales channel with the lowest total revenue is \"\n",
+    "    f\"{lowest_channel['sales_channel']} with \"\n",
+    "    f\"{lowest_channel['total_revenue']:,.2f}.\"\n",
+    ")\n",
+    "\n",
+    "print(\n",
+    "    f\"The revenue difference between the highest and lowest \"\n",
+    "    f\"sales channels is {difference:,.2f}.\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "8a4ddcf2-6001-49a2-b677-207c8f7e624c",
+   "metadata": {},
+   "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>gender</th>\n",
+       "      <th>F</th>\n",
+       "      <th>M</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>education</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>Bachelor</th>\n",
+       "      <td>7874.27</td>\n",
+       "      <td>7703.60</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>College</th>\n",
+       "      <td>7748.82</td>\n",
+       "      <td>8052.46</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Doctor</th>\n",
+       "      <td>7328.51</td>\n",
+       "      <td>7415.33</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>High School or Below</th>\n",
+       "      <td>8675.22</td>\n",
+       "      <td>8149.69</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Master</th>\n",
+       "      <td>8157.05</td>\n",
+       "      <td>8168.83</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "gender                      F        M\n",
+       "education                             \n",
+       "Bachelor              7874.27  7703.60\n",
+       "College               7748.82  8052.46\n",
+       "Doctor                7328.51  7415.33\n",
+       "High School or Below  8675.22  8149.69\n",
+       "Master                8157.05  8168.83"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The segment with the highest average customer lifetime value is F customers with High School or Below education at 8,675.22.\n",
+      "The segment with the lowest average customer lifetime value is F customers with Doctor education at 7,328.51.\n",
+      "\n",
+      "Overall average customer lifetime value by gender\n"
+     ]
+    },
+    {
+     "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>average_customer_lifetime_value</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>gender</th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>F</th>\n",
+       "      <td>8071.11</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>M</th>\n",
+       "      <td>7963.04</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "        average_customer_lifetime_value\n",
+       "gender                                 \n",
+       "F                               8071.11\n",
+       "M                               7963.04"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
-    "# Your code goes here"
+    "avg_clv_by_education_gender = pd.pivot_table(\n",
+    "    df,\n",
+    "    index=\"education\",\n",
+    "    columns=\"gender\",\n",
+    "    values=\"customer_lifetime_value\",\n",
+    "    aggfunc=\"mean\"\n",
+    ").round(2)\n",
+    "\n",
+    "display(\n",
+    "    avg_clv_by_education_gender\n",
+    ")\n",
+    "\n",
+    "clv_segments = (\n",
+    "    avg_clv_by_education_gender\n",
+    "    .stack()\n",
+    "    .sort_values(ascending=False)\n",
+    ")\n",
+    "\n",
+    "highest_education = clv_segments.index[0][0]\n",
+    "highest_gender = clv_segments.index[0][1]\n",
+    "highest_value = clv_segments.iloc[0]\n",
+    "\n",
+    "lowest_education = clv_segments.index[-1][0]\n",
+    "lowest_gender = clv_segments.index[-1][1]\n",
+    "lowest_value = clv_segments.iloc[-1]\n",
+    "\n",
+    "print(\n",
+    "    f\"The segment with the highest average customer lifetime \"\n",
+    "    f\"value is {highest_gender} customers with \"\n",
+    "    f\"{highest_education} education at {highest_value:,.2f}.\"\n",
+    ")\n",
+    "\n",
+    "print(\n",
+    "    f\"The segment with the lowest average customer lifetime \"\n",
+    "    f\"value is {lowest_gender} customers with \"\n",
+    "    f\"{lowest_education} education at {lowest_value:,.2f}.\"\n",
+    ")\n",
+    "\n",
+    "gender_averages = (\n",
+    "    df.groupby(\"gender\")\n",
+    "    [\"customer_lifetime_value\"]\n",
+    "    .mean()\n",
+    "    .round(2)\n",
+    "    .sort_values(ascending=False)\n",
+    "    .to_frame(\"average_customer_lifetime_value\")\n",
+    ")\n",
+    "\n",
+    "print(\"\\nOverall average customer lifetime value by gender\")\n",
+    "\n",
+    "display(\n",
+    "    gender_averages\n",
+    ")"
    ]
   },
   {
@@ -130,15 +1655,268 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "id": "3a069e0b-b400-470e-904d-d17582191be4",
    "metadata": {
     "id": "3a069e0b-b400-470e-904d-d17582191be4"
    },
-   "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>Policy Type</th>\n",
+       "      <th>Month</th>\n",
+       "      <th>Number of Complaints</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>January</td>\n",
+       "      <td>443</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>February</td>\n",
+       "      <td>385</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>January</td>\n",
+       "      <td>1728</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>February</td>\n",
+       "      <td>1454</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Special Auto</td>\n",
+       "      <td>January</td>\n",
+       "      <td>87</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>Special Auto</td>\n",
+       "      <td>February</td>\n",
+       "      <td>95</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      Policy Type     Month  Number of Complaints\n",
+       "0  Corporate Auto   January                   443\n",
+       "1  Corporate Auto  February                   385\n",
+       "2   Personal Auto   January                  1728\n",
+       "3   Personal Auto  February                  1454\n",
+       "4    Special Auto   January                    87\n",
+       "5    Special Auto  February                    95"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Month with the highest number of complaints for each policy type\n"
+     ]
+    },
+    {
+     "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>Policy Type</th>\n",
+       "      <th>Month</th>\n",
+       "      <th>Number of Complaints</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Corporate Auto</td>\n",
+       "      <td>January</td>\n",
+       "      <td>443</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Personal Auto</td>\n",
+       "      <td>January</td>\n",
+       "      <td>1728</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Special Auto</td>\n",
+       "      <td>February</td>\n",
+       "      <td>95</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      Policy Type     Month  Number of Complaints\n",
+       "0  Corporate Auto   January                   443\n",
+       "1   Personal Auto   January                  1728\n",
+       "2    Special Auto  February                    95"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The highest complaint total was recorded for Personal Auto during January, with 1728 complaints.\n"
+     ]
+    }
+   ],
    "source": [
-    "# Your code goes here"
+    "df[\"effective_to_date\"] = pd.to_datetime(\n",
+    "    df[\"effective_to_date\"],\n",
+    "    errors=\"coerce\"\n",
+    ")\n",
+    "\n",
+    "df[\"number_of_open_complaints\"] = pd.to_numeric(\n",
+    "    df[\"number_of_open_complaints\"],\n",
+    "    errors=\"coerce\"\n",
+    ").fillna(0)\n",
+    "\n",
+    "month_order = [\n",
+    "    \"January\",\n",
+    "    \"February\",\n",
+    "    \"March\",\n",
+    "    \"April\",\n",
+    "    \"May\",\n",
+    "    \"June\",\n",
+    "    \"July\",\n",
+    "    \"August\",\n",
+    "    \"September\",\n",
+    "    \"October\",\n",
+    "    \"November\",\n",
+    "    \"December\"\n",
+    "]\n",
+    "\n",
+    "df[\"month\"] = pd.Categorical(\n",
+    "    df[\"effective_to_date\"].dt.month_name(),\n",
+    "    categories=month_order,\n",
+    "    ordered=True\n",
+    ")\n",
+    "\n",
+    "complaints_long = (\n",
+    "    df.groupby(\n",
+    "        [\"policy_type\", \"month\"],\n",
+    "        observed=True,\n",
+    "        as_index=False\n",
+    "    )\n",
+    "    [\"number_of_open_complaints\"]\n",
+    "    .sum()\n",
+    "    .rename(\n",
+    "        columns={\n",
+    "            \"policy_type\": \"Policy Type\",\n",
+    "            \"month\": \"Month\",\n",
+    "            \"number_of_open_complaints\": \"Number of Complaints\"\n",
+    "        }\n",
+    "    )\n",
+    "    .sort_values(\n",
+    "        [\"Policy Type\", \"Month\"]\n",
+    "    )\n",
+    "    .reset_index(drop=True)\n",
+    ")\n",
+    "\n",
+    "complaints_long[\"Number of Complaints\"] = (\n",
+    "    complaints_long[\"Number of Complaints\"]\n",
+    "    .round()\n",
+    "    .astype(int)\n",
+    ")\n",
+    "\n",
+    "display(\n",
+    "    complaints_long\n",
+    ")\n",
+    "\n",
+    "highest_complaint_rows = (\n",
+    "    complaints_long.loc[\n",
+    "        complaints_long\n",
+    "        .groupby(\"Policy Type\")\n",
+    "        [\"Number of Complaints\"]\n",
+    "        .idxmax()\n",
+    "    ]\n",
+    "    .sort_values(\"Policy Type\")\n",
+    "    .reset_index(drop=True)\n",
+    ")\n",
+    "\n",
+    "print(\n",
+    "    \"Month with the highest number of complaints \"\n",
+    "    \"for each policy type\"\n",
+    ")\n",
+    "\n",
+    "display(\n",
+    "    highest_complaint_rows\n",
+    ")\n",
+    "\n",
+    "overall_highest = complaints_long.loc[\n",
+    "    complaints_long[\"Number of Complaints\"].idxmax()\n",
+    "]\n",
+    "\n",
+    "print(\n",
+    "    f\"The highest complaint total was recorded for \"\n",
+    "    f\"{overall_highest['Policy Type']} during \"\n",
+    "    f\"{overall_highest['Month']}, with \"\n",
+    "    f\"{overall_highest['Number of Complaints']} complaints.\"\n",
+    ")"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "af4a9169-da9a-497a-bc22-5f79ac53225f",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -160,7 +1938,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.13.14"
   }
  },
  "nbformat": 4,