diff --git a/Solutions.ipynb b/Solutions.ipynb
index 89aa338..e8b941e 100644
--- a/Solutions.ipynb
+++ b/Solutions.ipynb
@@ -2,91 +2,1531 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "bf32ae3b",
-   "metadata": {},
    "source": [
     "# Lab | Revisiting Machine Learning Case Study"
-   ]
+   ],
+   "metadata": {}
   },
   {
    "cell_type": "markdown",
-   "id": "73df37d0",
-   "metadata": {},
    "source": [
     "In this lab, you will use learningSet.csv file which you already have cloned in today's activities."
-   ]
+   ],
+   "metadata": {}
   },
   {
    "cell_type": "markdown",
-   "id": "5bbb5252",
-   "metadata": {},
    "source": [
     "### 1. Check for null values in all the columns"
-   ]
+   ],
+   "metadata": {}
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "dbe69e8b",
-   "metadata": {},
+   "execution_count": 1,
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')\n",
+    "pd.set_option('display.max_rows', 100)\n",
+    "\n"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "source": [
+    "data = pd.read_csv('learningSet.csv')\n",
+    "data"
+   ],
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "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>ODATEDW</th>\n",
+       "      <th>OSOURCE</th>\n",
+       "      <th>TCODE</th>\n",
+       "      <th>STATE</th>\n",
+       "      <th>ZIP</th>\n",
+       "      <th>MAILCODE</th>\n",
+       "      <th>PVASTATE</th>\n",
+       "      <th>DOB</th>\n",
+       "      <th>NOEXCH</th>\n",
+       "      <th>RECINHSE</th>\n",
+       "      <th>...</th>\n",
+       "      <th>TARGET_D</th>\n",
+       "      <th>HPHONE_D</th>\n",
+       "      <th>RFA_2R</th>\n",
+       "      <th>RFA_2F</th>\n",
+       "      <th>RFA_2A</th>\n",
+       "      <th>MDMAUD_R</th>\n",
+       "      <th>MDMAUD_F</th>\n",
+       "      <th>MDMAUD_A</th>\n",
+       "      <th>CLUSTER2</th>\n",
+       "      <th>GEOCODE2</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>8901</td>\n",
+       "      <td>GRI</td>\n",
+       "      <td>0</td>\n",
+       "      <td>IL</td>\n",
+       "      <td>61081</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>3712</td>\n",
+       "      <td>0</td>\n",
+       "      <td></td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>L</td>\n",
+       "      <td>4</td>\n",
+       "      <td>E</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>39.0</td>\n",
+       "      <td>C</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>9401</td>\n",
+       "      <td>BOA</td>\n",
+       "      <td>1</td>\n",
+       "      <td>CA</td>\n",
+       "      <td>91326</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>5202</td>\n",
+       "      <td>0</td>\n",
+       "      <td></td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>L</td>\n",
+       "      <td>2</td>\n",
+       "      <td>G</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>A</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>9001</td>\n",
+       "      <td>AMH</td>\n",
+       "      <td>1</td>\n",
+       "      <td>NC</td>\n",
+       "      <td>27017</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td></td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>L</td>\n",
+       "      <td>4</td>\n",
+       "      <td>E</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>60.0</td>\n",
+       "      <td>C</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>8701</td>\n",
+       "      <td>BRY</td>\n",
+       "      <td>0</td>\n",
+       "      <td>CA</td>\n",
+       "      <td>95953</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>2801</td>\n",
+       "      <td>0</td>\n",
+       "      <td></td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>L</td>\n",
+       "      <td>4</td>\n",
+       "      <td>E</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>41.0</td>\n",
+       "      <td>C</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>8601</td>\n",
+       "      <td></td>\n",
+       "      <td>0</td>\n",
+       "      <td>FL</td>\n",
+       "      <td>33176</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>2001</td>\n",
+       "      <td>0</td>\n",
+       "      <td>X</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>L</td>\n",
+       "      <td>2</td>\n",
+       "      <td>F</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>26.0</td>\n",
+       "      <td>A</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",
+       "      <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>95407</th>\n",
+       "      <td>9601</td>\n",
+       "      <td>ASE</td>\n",
+       "      <td>1</td>\n",
+       "      <td>AK</td>\n",
+       "      <td>99504</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td></td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>L</td>\n",
+       "      <td>1</td>\n",
+       "      <td>G</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>C</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>95408</th>\n",
+       "      <td>9601</td>\n",
+       "      <td>DCD</td>\n",
+       "      <td>1</td>\n",
+       "      <td>TX</td>\n",
+       "      <td>77379</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>5001</td>\n",
+       "      <td>0</td>\n",
+       "      <td></td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>L</td>\n",
+       "      <td>1</td>\n",
+       "      <td>F</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>A</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>95409</th>\n",
+       "      <td>9501</td>\n",
+       "      <td>MBC</td>\n",
+       "      <td>1</td>\n",
+       "      <td>MI</td>\n",
+       "      <td>48910</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>3801</td>\n",
+       "      <td>0</td>\n",
+       "      <td></td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>L</td>\n",
+       "      <td>3</td>\n",
+       "      <td>E</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>34.0</td>\n",
+       "      <td>B</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>95410</th>\n",
+       "      <td>8601</td>\n",
+       "      <td>PRV</td>\n",
+       "      <td>0</td>\n",
+       "      <td>CA</td>\n",
+       "      <td>91320</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>4005</td>\n",
+       "      <td>0</td>\n",
+       "      <td>X</td>\n",
+       "      <td>...</td>\n",
+       "      <td>18.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>L</td>\n",
+       "      <td>4</td>\n",
+       "      <td>F</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>11.0</td>\n",
+       "      <td>A</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>95411</th>\n",
+       "      <td>8801</td>\n",
+       "      <td>MCC</td>\n",
+       "      <td>2</td>\n",
+       "      <td>NC</td>\n",
+       "      <td>28409</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>1801</td>\n",
+       "      <td>0</td>\n",
+       "      <td>X</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>L</td>\n",
+       "      <td>1</td>\n",
+       "      <td>G</td>\n",
+       "      <td>C</td>\n",
+       "      <td>1</td>\n",
+       "      <td>C</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>C</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>95412 rows × 481 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       ODATEDW OSOURCE  TCODE STATE    ZIP MAILCODE PVASTATE   DOB NOEXCH  \\\n",
+       "0         8901     GRI      0    IL  61081                    3712      0   \n",
+       "1         9401     BOA      1    CA  91326                    5202      0   \n",
+       "2         9001     AMH      1    NC  27017                       0      0   \n",
+       "3         8701     BRY      0    CA  95953                    2801      0   \n",
+       "4         8601              0    FL  33176                    2001      0   \n",
+       "...        ...     ...    ...   ...    ...      ...      ...   ...    ...   \n",
+       "95407     9601     ASE      1    AK  99504                       0      0   \n",
+       "95408     9601     DCD      1    TX  77379                    5001      0   \n",
+       "95409     9501     MBC      1    MI  48910                    3801      0   \n",
+       "95410     8601     PRV      0    CA  91320                    4005      0   \n",
+       "95411     8801     MCC      2    NC  28409                    1801      0   \n",
+       "\n",
+       "      RECINHSE  ... TARGET_D HPHONE_D RFA_2R RFA_2F RFA_2A MDMAUD_R  MDMAUD_F  \\\n",
+       "0               ...      0.0        0      L      4      E        X         X   \n",
+       "1               ...      0.0        0      L      2      G        X         X   \n",
+       "2               ...      0.0        1      L      4      E        X         X   \n",
+       "3               ...      0.0        1      L      4      E        X         X   \n",
+       "4            X  ...      0.0        1      L      2      F        X         X   \n",
+       "...        ...  ...      ...      ...    ...    ...    ...      ...       ...   \n",
+       "95407           ...      0.0        0      L      1      G        X         X   \n",
+       "95408           ...      0.0        1      L      1      F        X         X   \n",
+       "95409           ...      0.0        1      L      3      E        X         X   \n",
+       "95410        X  ...     18.0        1      L      4      F        X         X   \n",
+       "95411        X  ...      0.0        1      L      1      G        C         1   \n",
+       "\n",
+       "      MDMAUD_A CLUSTER2 GEOCODE2  \n",
+       "0            X     39.0        C  \n",
+       "1            X      1.0        A  \n",
+       "2            X     60.0        C  \n",
+       "3            X     41.0        C  \n",
+       "4            X     26.0        A  \n",
+       "...        ...      ...      ...  \n",
+       "95407        X     12.0        C  \n",
+       "95408        X      2.0        A  \n",
+       "95409        X     34.0        B  \n",
+       "95410        X     11.0        A  \n",
+       "95411        C     12.0        C  \n",
+       "\n",
+       "[95412 rows x 481 columns]"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 2
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "source": [
+    "# check for all nulls in df\n",
+    "\n",
+    "nulls = pd.DataFrame(data.isna().sum()*100/len(data), columns=['percentage'])\n",
+    "nulls = nulls.sort_values('percentage', ascending = False).head(500)\n",
+    "nulls"
+   ],
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "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>percentage</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>RDATE_5</th>\n",
+       "      <td>99.990567</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_5</th>\n",
+       "      <td>99.990567</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_3</th>\n",
+       "      <td>99.746363</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_3</th>\n",
+       "      <td>99.746363</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_4</th>\n",
+       "      <td>99.705488</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ETHC3</th>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ETHC2</th>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ETHC1</th>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>HHD12</th>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>TPE11</th>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>481 rows × 1 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "         percentage\n",
+       "RDATE_5   99.990567\n",
+       "RAMNT_5   99.990567\n",
+       "RDATE_3   99.746363\n",
+       "RAMNT_3   99.746363\n",
+       "RDATE_4   99.705488\n",
+       "...             ...\n",
+       "ETHC3      0.000000\n",
+       "ETHC2      0.000000\n",
+       "ETHC1      0.000000\n",
+       "HHD12      0.000000\n",
+       "TPE11      0.000000\n",
+       "\n",
+       "[481 rows x 1 columns]"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 3
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "source": [
+    "# here i just made a new df for all the columns which have over 50% nulls so it's easier to analyse instead of having 480 rows we just have 60\n",
+    "lst = []\n",
+    "\n",
+    "for i,row in nulls.iterrows():\n",
+    "    if row['percentage'] > 50:\n",
+    "        lst.append(row)\n",
+    "        nulls_over50 = pd.DataFrame(lst)\n",
+    "        \n",
+    "\n"
+   ],
    "outputs": [],
-   "source": []
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "source": [
+    "nulls_over50[:100]"
+   ],
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "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>percentage</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>RDATE_5</th>\n",
+       "      <td>99.990567</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_5</th>\n",
+       "      <td>99.990567</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_3</th>\n",
+       "      <td>99.746363</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_3</th>\n",
+       "      <td>99.746363</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_4</th>\n",
+       "      <td>99.705488</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_4</th>\n",
+       "      <td>99.705488</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_6</th>\n",
+       "      <td>99.186685</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_6</th>\n",
+       "      <td>99.186685</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_15</th>\n",
+       "      <td>92.388798</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_15</th>\n",
+       "      <td>92.388798</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_23</th>\n",
+       "      <td>91.763091</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_23</th>\n",
+       "      <td>91.763091</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_20</th>\n",
+       "      <td>91.732696</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_20</th>\n",
+       "      <td>91.732696</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_7</th>\n",
+       "      <td>90.677273</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_7</th>\n",
+       "      <td>90.677273</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_17</th>\n",
+       "      <td>90.146942</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_17</th>\n",
+       "      <td>90.146942</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_21</th>\n",
+       "      <td>90.029556</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_21</th>\n",
+       "      <td>90.029556</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_10</th>\n",
+       "      <td>89.035970</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_10</th>\n",
+       "      <td>89.035970</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_13</th>\n",
+       "      <td>87.160944</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_13</th>\n",
+       "      <td>87.160944</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>NUMCHLD</th>\n",
+       "      <td>87.018404</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_11</th>\n",
+       "      <td>84.551209</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_11</th>\n",
+       "      <td>84.551209</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_19</th>\n",
+       "      <td>83.359535</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_19</th>\n",
+       "      <td>83.359535</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_9</th>\n",
+       "      <td>82.461326</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_9</th>\n",
+       "      <td>82.461326</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_24</th>\n",
+       "      <td>81.409047</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_24</th>\n",
+       "      <td>81.409047</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_18</th>\n",
+       "      <td>79.270951</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_18</th>\n",
+       "      <td>79.270951</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_22</th>\n",
+       "      <td>78.123297</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_22</th>\n",
+       "      <td>78.123297</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_8</th>\n",
+       "      <td>77.495493</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_8</th>\n",
+       "      <td>77.495493</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_14</th>\n",
+       "      <td>75.561774</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_14</th>\n",
+       "      <td>75.561774</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_12</th>\n",
+       "      <td>73.064185</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_12</th>\n",
+       "      <td>73.064185</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_16</th>\n",
+       "      <td>71.707961</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_16</th>\n",
+       "      <td>71.707961</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ADATE_15</th>\n",
+       "      <td>68.625540</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ADATE_23</th>\n",
+       "      <td>58.975810</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>MBCOLECT</th>\n",
+       "      <td>55.458433</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>MAGFAML</th>\n",
+       "      <td>55.395548</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>MBCRAFT</th>\n",
+       "      <td>55.395548</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>MBBOOKS</th>\n",
+       "      <td>55.395548</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>MAGFEM</th>\n",
+       "      <td>55.395548</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>MAGMALE</th>\n",
+       "      <td>55.395548</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>PUBGARDN</th>\n",
+       "      <td>55.395548</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>PUBCULIN</th>\n",
+       "      <td>55.395548</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>PUBHLTH</th>\n",
+       "      <td>55.395548</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>PUBDOITY</th>\n",
+       "      <td>55.395548</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>PUBNEWFN</th>\n",
+       "      <td>55.395548</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>PUBPHOTO</th>\n",
+       "      <td>55.395548</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>PUBOPP</th>\n",
+       "      <td>55.395548</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>MBGARDEN</th>\n",
+       "      <td>55.395548</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ADATE_20</th>\n",
+       "      <td>52.613927</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          percentage\n",
+       "RDATE_5    99.990567\n",
+       "RAMNT_5    99.990567\n",
+       "RDATE_3    99.746363\n",
+       "RAMNT_3    99.746363\n",
+       "RDATE_4    99.705488\n",
+       "RAMNT_4    99.705488\n",
+       "RAMNT_6    99.186685\n",
+       "RDATE_6    99.186685\n",
+       "RAMNT_15   92.388798\n",
+       "RDATE_15   92.388798\n",
+       "RDATE_23   91.763091\n",
+       "RAMNT_23   91.763091\n",
+       "RDATE_20   91.732696\n",
+       "RAMNT_20   91.732696\n",
+       "RAMNT_7    90.677273\n",
+       "RDATE_7    90.677273\n",
+       "RAMNT_17   90.146942\n",
+       "RDATE_17   90.146942\n",
+       "RDATE_21   90.029556\n",
+       "RAMNT_21   90.029556\n",
+       "RAMNT_10   89.035970\n",
+       "RDATE_10   89.035970\n",
+       "RDATE_13   87.160944\n",
+       "RAMNT_13   87.160944\n",
+       "NUMCHLD    87.018404\n",
+       "RDATE_11   84.551209\n",
+       "RAMNT_11   84.551209\n",
+       "RDATE_19   83.359535\n",
+       "RAMNT_19   83.359535\n",
+       "RAMNT_9    82.461326\n",
+       "RDATE_9    82.461326\n",
+       "RDATE_24   81.409047\n",
+       "RAMNT_24   81.409047\n",
+       "RAMNT_18   79.270951\n",
+       "RDATE_18   79.270951\n",
+       "RAMNT_22   78.123297\n",
+       "RDATE_22   78.123297\n",
+       "RAMNT_8    77.495493\n",
+       "RDATE_8    77.495493\n",
+       "RDATE_14   75.561774\n",
+       "RAMNT_14   75.561774\n",
+       "RAMNT_12   73.064185\n",
+       "RDATE_12   73.064185\n",
+       "RAMNT_16   71.707961\n",
+       "RDATE_16   71.707961\n",
+       "ADATE_15   68.625540\n",
+       "ADATE_23   58.975810\n",
+       "MBCOLECT   55.458433\n",
+       "MAGFAML    55.395548\n",
+       "MBCRAFT    55.395548\n",
+       "MBBOOKS    55.395548\n",
+       "MAGFEM     55.395548\n",
+       "MAGMALE    55.395548\n",
+       "PUBGARDN   55.395548\n",
+       "PUBCULIN   55.395548\n",
+       "PUBHLTH    55.395548\n",
+       "PUBDOITY   55.395548\n",
+       "PUBNEWFN   55.395548\n",
+       "PUBPHOTO   55.395548\n",
+       "PUBOPP     55.395548\n",
+       "MBGARDEN   55.395548\n",
+       "ADATE_20   52.613927"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 5
+    }
+   ],
+   "metadata": {}
   },
   {
    "cell_type": "markdown",
-   "id": "6febccdc",
-   "metadata": {},
    "source": [
     "### 2. Exclude the following variables by looking at the definitions. Create a new empty list called drop_list. We will append this list and then drop all the columns in this list later:\n",
     "\n",
     "- `OSOURCE` - symbol definitions not provided, too many categories\n",
     "- `ZIP CODE` - we are including state already\n"
-   ]
+   ],
+   "metadata": {}
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "3a07b75a",
-   "metadata": {},
+   "execution_count": 6,
+   "source": [
+    "drop_list = ['OSOURCE', 'ZIP']"
+   ],
    "outputs": [],
-   "source": []
+   "metadata": {}
   },
   {
    "cell_type": "markdown",
-   "id": "6a2470e4",
-   "metadata": {},
    "source": [
     "### 3. Identify columns that over 85% missing values"
-   ]
+   ],
+   "metadata": {}
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "2b6f01b6",
-   "metadata": {},
-   "outputs": [],
-   "source": []
+   "execution_count": 7,
+   "source": [
+    "# i will just use the same loop from above but change the threshold to 85\n",
+    "\n",
+    "lst = []\n",
+    "\n",
+    "for i,row in nulls.iterrows():\n",
+    "    if row['percentage'] > 85:\n",
+    "        lst.append(row)\n",
+    "        nulls_over85 = pd.DataFrame(lst)\n",
+    "\n",
+    "nulls_over85"
+   ],
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "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>percentage</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>RDATE_5</th>\n",
+       "      <td>99.990567</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_5</th>\n",
+       "      <td>99.990567</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_3</th>\n",
+       "      <td>99.746363</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_3</th>\n",
+       "      <td>99.746363</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_4</th>\n",
+       "      <td>99.705488</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_4</th>\n",
+       "      <td>99.705488</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_6</th>\n",
+       "      <td>99.186685</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_6</th>\n",
+       "      <td>99.186685</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_15</th>\n",
+       "      <td>92.388798</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_15</th>\n",
+       "      <td>92.388798</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_23</th>\n",
+       "      <td>91.763091</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_23</th>\n",
+       "      <td>91.763091</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_20</th>\n",
+       "      <td>91.732696</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_20</th>\n",
+       "      <td>91.732696</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_7</th>\n",
+       "      <td>90.677273</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_7</th>\n",
+       "      <td>90.677273</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_17</th>\n",
+       "      <td>90.146942</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_17</th>\n",
+       "      <td>90.146942</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_21</th>\n",
+       "      <td>90.029556</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_21</th>\n",
+       "      <td>90.029556</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_10</th>\n",
+       "      <td>89.035970</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_10</th>\n",
+       "      <td>89.035970</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RDATE_13</th>\n",
+       "      <td>87.160944</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>RAMNT_13</th>\n",
+       "      <td>87.160944</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>NUMCHLD</th>\n",
+       "      <td>87.018404</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          percentage\n",
+       "RDATE_5    99.990567\n",
+       "RAMNT_5    99.990567\n",
+       "RDATE_3    99.746363\n",
+       "RAMNT_3    99.746363\n",
+       "RDATE_4    99.705488\n",
+       "RAMNT_4    99.705488\n",
+       "RAMNT_6    99.186685\n",
+       "RDATE_6    99.186685\n",
+       "RAMNT_15   92.388798\n",
+       "RDATE_15   92.388798\n",
+       "RDATE_23   91.763091\n",
+       "RAMNT_23   91.763091\n",
+       "RDATE_20   91.732696\n",
+       "RAMNT_20   91.732696\n",
+       "RAMNT_7    90.677273\n",
+       "RDATE_7    90.677273\n",
+       "RAMNT_17   90.146942\n",
+       "RDATE_17   90.146942\n",
+       "RDATE_21   90.029556\n",
+       "RAMNT_21   90.029556\n",
+       "RAMNT_10   89.035970\n",
+       "RDATE_10   89.035970\n",
+       "RDATE_13   87.160944\n",
+       "RAMNT_13   87.160944\n",
+       "NUMCHLD    87.018404"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 7
+    }
+   ],
+   "metadata": {}
   },
   {
    "cell_type": "markdown",
-   "id": "70865946",
-   "metadata": {},
    "source": [
     "### 4. Remove those columns from the dataframe"
-   ]
+   ],
+   "metadata": {}
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "ca6c4d91",
-   "metadata": {},
-   "outputs": [],
-   "source": []
+   "execution_count": 8,
+   "source": [
+    "# have to swap the rows and columns so i can make a list of the columsn to drop\n",
+    "\n",
+    "to_delete = list(nulls_over85.transpose())\n",
+    "to_delete\n"
+   ],
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "['RDATE_5',\n",
+       " 'RAMNT_5',\n",
+       " 'RDATE_3',\n",
+       " 'RAMNT_3',\n",
+       " 'RDATE_4',\n",
+       " 'RAMNT_4',\n",
+       " 'RAMNT_6',\n",
+       " 'RDATE_6',\n",
+       " 'RAMNT_15',\n",
+       " 'RDATE_15',\n",
+       " 'RDATE_23',\n",
+       " 'RAMNT_23',\n",
+       " 'RDATE_20',\n",
+       " 'RAMNT_20',\n",
+       " 'RAMNT_7',\n",
+       " 'RDATE_7',\n",
+       " 'RAMNT_17',\n",
+       " 'RDATE_17',\n",
+       " 'RDATE_21',\n",
+       " 'RAMNT_21',\n",
+       " 'RAMNT_10',\n",
+       " 'RDATE_10',\n",
+       " 'RDATE_13',\n",
+       " 'RAMNT_13',\n",
+       " 'NUMCHLD']"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 8
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "source": [
+    "# drop cols and make new copy of df\n",
+    "\n",
+    "data_copy = data.drop(columns= [col for col in to_delete])\n",
+    "data_copy"
+   ],
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "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>ODATEDW</th>\n",
+       "      <th>OSOURCE</th>\n",
+       "      <th>TCODE</th>\n",
+       "      <th>STATE</th>\n",
+       "      <th>ZIP</th>\n",
+       "      <th>MAILCODE</th>\n",
+       "      <th>PVASTATE</th>\n",
+       "      <th>DOB</th>\n",
+       "      <th>NOEXCH</th>\n",
+       "      <th>RECINHSE</th>\n",
+       "      <th>...</th>\n",
+       "      <th>TARGET_D</th>\n",
+       "      <th>HPHONE_D</th>\n",
+       "      <th>RFA_2R</th>\n",
+       "      <th>RFA_2F</th>\n",
+       "      <th>RFA_2A</th>\n",
+       "      <th>MDMAUD_R</th>\n",
+       "      <th>MDMAUD_F</th>\n",
+       "      <th>MDMAUD_A</th>\n",
+       "      <th>CLUSTER2</th>\n",
+       "      <th>GEOCODE2</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>8901</td>\n",
+       "      <td>GRI</td>\n",
+       "      <td>0</td>\n",
+       "      <td>IL</td>\n",
+       "      <td>61081</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>3712</td>\n",
+       "      <td>0</td>\n",
+       "      <td></td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>L</td>\n",
+       "      <td>4</td>\n",
+       "      <td>E</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>39.0</td>\n",
+       "      <td>C</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>9401</td>\n",
+       "      <td>BOA</td>\n",
+       "      <td>1</td>\n",
+       "      <td>CA</td>\n",
+       "      <td>91326</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>5202</td>\n",
+       "      <td>0</td>\n",
+       "      <td></td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>L</td>\n",
+       "      <td>2</td>\n",
+       "      <td>G</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>A</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>9001</td>\n",
+       "      <td>AMH</td>\n",
+       "      <td>1</td>\n",
+       "      <td>NC</td>\n",
+       "      <td>27017</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td></td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>L</td>\n",
+       "      <td>4</td>\n",
+       "      <td>E</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>60.0</td>\n",
+       "      <td>C</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>8701</td>\n",
+       "      <td>BRY</td>\n",
+       "      <td>0</td>\n",
+       "      <td>CA</td>\n",
+       "      <td>95953</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>2801</td>\n",
+       "      <td>0</td>\n",
+       "      <td></td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>L</td>\n",
+       "      <td>4</td>\n",
+       "      <td>E</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>41.0</td>\n",
+       "      <td>C</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>8601</td>\n",
+       "      <td></td>\n",
+       "      <td>0</td>\n",
+       "      <td>FL</td>\n",
+       "      <td>33176</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>2001</td>\n",
+       "      <td>0</td>\n",
+       "      <td>X</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>L</td>\n",
+       "      <td>2</td>\n",
+       "      <td>F</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>26.0</td>\n",
+       "      <td>A</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",
+       "      <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>95407</th>\n",
+       "      <td>9601</td>\n",
+       "      <td>ASE</td>\n",
+       "      <td>1</td>\n",
+       "      <td>AK</td>\n",
+       "      <td>99504</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td></td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>L</td>\n",
+       "      <td>1</td>\n",
+       "      <td>G</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>C</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>95408</th>\n",
+       "      <td>9601</td>\n",
+       "      <td>DCD</td>\n",
+       "      <td>1</td>\n",
+       "      <td>TX</td>\n",
+       "      <td>77379</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>5001</td>\n",
+       "      <td>0</td>\n",
+       "      <td></td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>L</td>\n",
+       "      <td>1</td>\n",
+       "      <td>F</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>A</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>95409</th>\n",
+       "      <td>9501</td>\n",
+       "      <td>MBC</td>\n",
+       "      <td>1</td>\n",
+       "      <td>MI</td>\n",
+       "      <td>48910</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>3801</td>\n",
+       "      <td>0</td>\n",
+       "      <td></td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>L</td>\n",
+       "      <td>3</td>\n",
+       "      <td>E</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>34.0</td>\n",
+       "      <td>B</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>95410</th>\n",
+       "      <td>8601</td>\n",
+       "      <td>PRV</td>\n",
+       "      <td>0</td>\n",
+       "      <td>CA</td>\n",
+       "      <td>91320</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>4005</td>\n",
+       "      <td>0</td>\n",
+       "      <td>X</td>\n",
+       "      <td>...</td>\n",
+       "      <td>18.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>L</td>\n",
+       "      <td>4</td>\n",
+       "      <td>F</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>X</td>\n",
+       "      <td>11.0</td>\n",
+       "      <td>A</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>95411</th>\n",
+       "      <td>8801</td>\n",
+       "      <td>MCC</td>\n",
+       "      <td>2</td>\n",
+       "      <td>NC</td>\n",
+       "      <td>28409</td>\n",
+       "      <td></td>\n",
+       "      <td></td>\n",
+       "      <td>1801</td>\n",
+       "      <td>0</td>\n",
+       "      <td>X</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1</td>\n",
+       "      <td>L</td>\n",
+       "      <td>1</td>\n",
+       "      <td>G</td>\n",
+       "      <td>C</td>\n",
+       "      <td>1</td>\n",
+       "      <td>C</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>C</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>95412 rows × 456 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       ODATEDW OSOURCE  TCODE STATE    ZIP MAILCODE PVASTATE   DOB NOEXCH  \\\n",
+       "0         8901     GRI      0    IL  61081                    3712      0   \n",
+       "1         9401     BOA      1    CA  91326                    5202      0   \n",
+       "2         9001     AMH      1    NC  27017                       0      0   \n",
+       "3         8701     BRY      0    CA  95953                    2801      0   \n",
+       "4         8601              0    FL  33176                    2001      0   \n",
+       "...        ...     ...    ...   ...    ...      ...      ...   ...    ...   \n",
+       "95407     9601     ASE      1    AK  99504                       0      0   \n",
+       "95408     9601     DCD      1    TX  77379                    5001      0   \n",
+       "95409     9501     MBC      1    MI  48910                    3801      0   \n",
+       "95410     8601     PRV      0    CA  91320                    4005      0   \n",
+       "95411     8801     MCC      2    NC  28409                    1801      0   \n",
+       "\n",
+       "      RECINHSE  ... TARGET_D HPHONE_D RFA_2R RFA_2F RFA_2A MDMAUD_R  MDMAUD_F  \\\n",
+       "0               ...      0.0        0      L      4      E        X         X   \n",
+       "1               ...      0.0        0      L      2      G        X         X   \n",
+       "2               ...      0.0        1      L      4      E        X         X   \n",
+       "3               ...      0.0        1      L      4      E        X         X   \n",
+       "4            X  ...      0.0        1      L      2      F        X         X   \n",
+       "...        ...  ...      ...      ...    ...    ...    ...      ...       ...   \n",
+       "95407           ...      0.0        0      L      1      G        X         X   \n",
+       "95408           ...      0.0        1      L      1      F        X         X   \n",
+       "95409           ...      0.0        1      L      3      E        X         X   \n",
+       "95410        X  ...     18.0        1      L      4      F        X         X   \n",
+       "95411        X  ...      0.0        1      L      1      G        C         1   \n",
+       "\n",
+       "      MDMAUD_A CLUSTER2 GEOCODE2  \n",
+       "0            X     39.0        C  \n",
+       "1            X      1.0        A  \n",
+       "2            X     60.0        C  \n",
+       "3            X     41.0        C  \n",
+       "4            X     26.0        A  \n",
+       "...        ...      ...      ...  \n",
+       "95407        X     12.0        C  \n",
+       "95408        X      2.0        A  \n",
+       "95409        X     34.0        B  \n",
+       "95410        X     11.0        A  \n",
+       "95411        C     12.0        C  \n",
+       "\n",
+       "[95412 rows x 456 columns]"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 19
+    }
+   ],
+   "metadata": {}
   },
   {
    "cell_type": "markdown",
-   "id": "7bbcf161",
-   "metadata": {},
    "source": [
     "### 5. Reduce the number of categories in the column GENDER. The column should only have either \"M\" for males, \"F\" for females, and \"other\" for all the rest\n",
     "\n",
@@ -96,22 +1536,123 @@
     "print(categorical['GENDER'].value_counts())\n",
     "categorical['GENDER'] = categorical['GENDER'].fillna('F')\n",
     "```"
-   ]
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "source": [
+    "data_copy['GENDER'] = data_copy['GENDER'].fillna('F')"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "source": [
+    "data_copy['GENDER'].value_counts()"
+   ],
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "F    51277\n",
+       "M    39094\n",
+       "      2957\n",
+       "U     1715\n",
+       "J      365\n",
+       "A        2\n",
+       "C        2\n",
+       "Name: GENDER, dtype: int64"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 21
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "source": [
+    "# some rows are blanks not nulls so need can't use the fillna function\n",
+    "\n",
+    "data_copy['GENDER'].isna().sum()"
+   ],
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "0"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 22
+    }
+   ],
+   "metadata": {}
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "b583feaa",
-   "metadata": {},
+   "execution_count": 23,
+   "source": [
+    "replace = {\n",
+    "    'U': \"other\",\n",
+    "    'J' : \"other\",\n",
+    "    'A' : \"other\",\n",
+    "    'C' : \"other\",\n",
+    "    ' ' : \"other\"\n",
+    "}\n",
+    "\n",
+    "data_copy[\"GENDER\"] = data_copy[\"GENDER\"].replace(replace)\n",
+    "\n"
+   ],
    "outputs": [],
-   "source": []
+   "metadata": {}
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "i tried to do the above with a for loop but still don't really understand how to loop through dataframes :(\n",
+    "in this case using a dictionary is ok because there are only 5 values to replace but if there were more a loop would be more efficient."
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "source": [
+    "# now other has replaced all the non M or F rows\n",
+    "\n",
+    "data_copy['GENDER'].value_counts()"
+   ],
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "F        51277\n",
+       "M        39094\n",
+       "other     5041\n",
+       "Name: GENDER, dtype: int64"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 24
+    }
+   ],
+   "metadata": {}
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
+   "name": "python3",
+   "display_name": "Python 3.8.8 64-bit ('base': conda)"
   },
   "language_info": {
    "codemirror_mode": {
@@ -123,9 +1664,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.5"
+   "version": "3.8.8"
+  },
+  "interpreter": {
+   "hash": "f27e873c37e1f1555e60b9534290287a99b02cba69d8f829668ffeb66728ce50"
   }
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}
\ No newline at end of file