diff --git a/.ipynb_checkpoints/Solutions-checkpoint.ipynb b/.ipynb_checkpoints/Solutions-checkpoint.ipynb
new file mode 100644
index 0000000..27531ed
--- /dev/null
+++ b/.ipynb_checkpoints/Solutions-checkpoint.ipynb
@@ -0,0 +1,579 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "8e88c40c-b872-41a6-9080-3fb1ed56102b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import datetime\n",
+    "import warnings\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "\n",
+    "pd.set_option('display.max_columns', None)\n",
+    "warnings.filterwarnings('ignore')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "b12acf4b-8181-46da-8767-2d460269e4e7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(\"/Users/spicasumampouw/IronSpica/activities/Unit_6/learningSet.csv\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bf32ae3b",
+   "metadata": {},
+   "source": [
+    "# Lab | Revisiting Machine Learning Case Study"
+   ]
+  },
+  {
+   "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."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5bbb5252",
+   "metadata": {},
+   "source": [
+    "### 1. Check for null values in all the columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "dbe69e8b",
+   "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>Column Name</th>\n",
+       "      <th>Unknown Values</th>\n",
+       "      <th>Data Types</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>414</th>\n",
+       "      <td>RDATE_5</td>\n",
+       "      <td>95403</td>\n",
+       "      <td>float64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>436</th>\n",
+       "      <td>RAMNT_5</td>\n",
+       "      <td>95403</td>\n",
+       "      <td>float64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>412</th>\n",
+       "      <td>RDATE_3</td>\n",
+       "      <td>95170</td>\n",
+       "      <td>float64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>434</th>\n",
+       "      <td>RAMNT_3</td>\n",
+       "      <td>95170</td>\n",
+       "      <td>float64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>413</th>\n",
+       "      <td>RDATE_4</td>\n",
+       "      <td>95131</td>\n",
+       "      <td>float64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>480</th>\n",
+       "      <td>GEOCODE2</td>\n",
+       "      <td>132</td>\n",
+       "      <td>object</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>479</th>\n",
+       "      <td>CLUSTER2</td>\n",
+       "      <td>132</td>\n",
+       "      <td>float64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>409</th>\n",
+       "      <td>NUMPROM</td>\n",
+       "      <td>0</td>\n",
+       "      <td>int64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>408</th>\n",
+       "      <td>MAXADATE</td>\n",
+       "      <td>0</td>\n",
+       "      <td>int64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>307</th>\n",
+       "      <td>AFC6</td>\n",
+       "      <td>0</td>\n",
+       "      <td>int64</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>95 rows × 3 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    Column Name  Unknown Values Data Types\n",
+       "414     RDATE_5           95403    float64\n",
+       "436     RAMNT_5           95403    float64\n",
+       "412     RDATE_3           95170    float64\n",
+       "434     RAMNT_3           95170    float64\n",
+       "413     RDATE_4           95131    float64\n",
+       "..          ...             ...        ...\n",
+       "480    GEOCODE2             132     object\n",
+       "479    CLUSTER2             132    float64\n",
+       "409     NUMPROM               0      int64\n",
+       "408    MAXADATE               0      int64\n",
+       "307        AFC6               0      int64\n",
+       "\n",
+       "[95 rows x 3 columns]"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "unk_lst = []\n",
+    "for col in df.columns:\n",
+    "    column_name = col\n",
+    "    unk_values = int(df[col].isnull().sum())\n",
+    "    unk_dtypes = df[col].dtypes\n",
+    "    unk_lst.append([column_name,unk_values,unk_dtypes])\n",
+    "    \n",
+    "unk_df = pd.DataFrame(unk_lst,columns=[\"Column Name\",\"Unknown Values\", \"Data Types\"])\n",
+    "unk_df.sort_values(\"Unknown Values\", ascending=False).iloc[:95]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "79a6bb89-abad-4499-9a04-60fc5082acc0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df.columns = [column.lower().replace(' ', '_') for column in df.columns]"
+   ]
+  },
+  {
+   "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"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "3a07b75a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#drop_list = df.drop(columns='OSOURCE', 'ZIP')\n",
+    "drop_list = ['osource', 'zip']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6a2470e4",
+   "metadata": {},
+   "source": [
+    "### 3. Identify columns that over 85% missing values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "2b6f01b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "percent_df = df.isna().sum().sort_values(ascending = False)*100/len(df)\n",
+    "percent_df = percent_df.reset_index()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "a8647cbd-d71f-422b-a667-611586586268",
+   "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>column_name</th>\n",
+       "      <th>percent</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>rdate_5</td>\n",
+       "      <td>99.990567</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>ramnt_5</td>\n",
+       "      <td>99.990567</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>rdate_3</td>\n",
+       "      <td>99.746363</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>ramnt_3</td>\n",
+       "      <td>99.746363</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>rdate_4</td>\n",
+       "      <td>99.705488</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>ramnt_4</td>\n",
+       "      <td>99.705488</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>ramnt_6</td>\n",
+       "      <td>99.186685</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>rdate_6</td>\n",
+       "      <td>99.186685</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>ramnt_15</td>\n",
+       "      <td>92.388798</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>rdate_15</td>\n",
+       "      <td>92.388798</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>rdate_23</td>\n",
+       "      <td>91.763091</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>ramnt_23</td>\n",
+       "      <td>91.763091</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>rdate_20</td>\n",
+       "      <td>91.732696</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>ramnt_20</td>\n",
+       "      <td>91.732696</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>ramnt_7</td>\n",
+       "      <td>90.677273</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>rdate_7</td>\n",
+       "      <td>90.677273</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>ramnt_17</td>\n",
+       "      <td>90.146942</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17</th>\n",
+       "      <td>rdate_17</td>\n",
+       "      <td>90.146942</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>18</th>\n",
+       "      <td>rdate_21</td>\n",
+       "      <td>90.029556</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>19</th>\n",
+       "      <td>ramnt_21</td>\n",
+       "      <td>90.029556</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>20</th>\n",
+       "      <td>ramnt_10</td>\n",
+       "      <td>89.035970</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>21</th>\n",
+       "      <td>rdate_10</td>\n",
+       "      <td>89.035970</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22</th>\n",
+       "      <td>rdate_13</td>\n",
+       "      <td>87.160944</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23</th>\n",
+       "      <td>ramnt_13</td>\n",
+       "      <td>87.160944</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>24</th>\n",
+       "      <td>numchld</td>\n",
+       "      <td>87.018404</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   column_name    percent\n",
+       "0      rdate_5  99.990567\n",
+       "1      ramnt_5  99.990567\n",
+       "2      rdate_3  99.746363\n",
+       "3      ramnt_3  99.746363\n",
+       "4      rdate_4  99.705488\n",
+       "5      ramnt_4  99.705488\n",
+       "6      ramnt_6  99.186685\n",
+       "7      rdate_6  99.186685\n",
+       "8     ramnt_15  92.388798\n",
+       "9     rdate_15  92.388798\n",
+       "10    rdate_23  91.763091\n",
+       "11    ramnt_23  91.763091\n",
+       "12    rdate_20  91.732696\n",
+       "13    ramnt_20  91.732696\n",
+       "14     ramnt_7  90.677273\n",
+       "15     rdate_7  90.677273\n",
+       "16    ramnt_17  90.146942\n",
+       "17    rdate_17  90.146942\n",
+       "18    rdate_21  90.029556\n",
+       "19    ramnt_21  90.029556\n",
+       "20    ramnt_10  89.035970\n",
+       "21    rdate_10  89.035970\n",
+       "22    rdate_13  87.160944\n",
+       "23    ramnt_13  87.160944\n",
+       "24     numchld  87.018404"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "percent_df.columns = ['column_name', 'percent']\n",
+    "above85 = percent_df[percent_df['percent'] >= 85]\n",
+    "above85\n",
+    "#above85['name'].unique()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "70865946",
+   "metadata": {},
+   "source": [
+    "### 4. Remove those columns from the dataframe"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "ca6c4d91",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i in above85['column_name']:\n",
+    "    drop_list.append(i)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "85a511c0-67b7-428b-a035-29248927def0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i in drop_list: \n",
+    "    df = df.drop(i, axis = 1)"
+   ]
+  },
+  {
+   "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",
+    "Note that there are a few null values in the column. We will first replace those null values using the code below:\n",
+    "\n",
+    "```python\n",
+    "print(categorical['GENDER'].value_counts())\n",
+    "categorical['GENDER'] = categorical['GENDER'].fillna('F')\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "b583feaa",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['F', 'M', ' ', 'C', 'U', 'J', 'A'], dtype=object)"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#data['gender'].value_counts()\n",
+    "df['gender'].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "b148fb95-d33f-44e1-8aa7-d1828914d5bf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['gender'] = df['gender'].fillna('F')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "376d39ed-3df9-48f5-b9a0-60dbdcf4f074",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "F        51277\n",
+       "M        39094\n",
+       "other     5041\n",
+       "Name: gender, dtype: int64"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['gender'] = df['gender'].fillna('F')\n",
+    "df['gender'] = df['gender'].apply(lambda x: x if x in ['M', 'F'] else 'other')\n",
+    "df['gender'].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "00f9bf63-f832-46f7-8077-39dcf941e877",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/Solutions.ipynb b/Solutions.ipynb
index 89aa338..fec1df4 100644
--- a/Solutions.ipynb
+++ b/Solutions.ipynb
@@ -1,5 +1,30 @@
 {
  "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "8e88c40c-b872-41a6-9080-3fb1ed56102b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import warnings\n",
+    "\n",
+    "pd.set_option('display.max_columns', None)\n",
+    "warnings.filterwarnings('ignore')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "b12acf4b-8181-46da-8767-2d460269e4e7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(\"/Users/spicasumampouw/IronSpica/activities/Unit_6/learningSet.csv\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "bf32ae3b",
@@ -26,11 +51,151 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 19,
    "id": "dbe69e8b",
    "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>Column Name</th>\n",
+       "      <th>Unknown Values</th>\n",
+       "      <th>Data Types</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>414</th>\n",
+       "      <td>RDATE_5</td>\n",
+       "      <td>95403</td>\n",
+       "      <td>float64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>436</th>\n",
+       "      <td>RAMNT_5</td>\n",
+       "      <td>95403</td>\n",
+       "      <td>float64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>412</th>\n",
+       "      <td>RDATE_3</td>\n",
+       "      <td>95170</td>\n",
+       "      <td>float64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>434</th>\n",
+       "      <td>RAMNT_3</td>\n",
+       "      <td>95170</td>\n",
+       "      <td>float64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>413</th>\n",
+       "      <td>RDATE_4</td>\n",
+       "      <td>95131</td>\n",
+       "      <td>float64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>480</th>\n",
+       "      <td>GEOCODE2</td>\n",
+       "      <td>132</td>\n",
+       "      <td>object</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>479</th>\n",
+       "      <td>CLUSTER2</td>\n",
+       "      <td>132</td>\n",
+       "      <td>float64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>409</th>\n",
+       "      <td>NUMPROM</td>\n",
+       "      <td>0</td>\n",
+       "      <td>int64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>408</th>\n",
+       "      <td>MAXADATE</td>\n",
+       "      <td>0</td>\n",
+       "      <td>int64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>307</th>\n",
+       "      <td>AFC6</td>\n",
+       "      <td>0</td>\n",
+       "      <td>int64</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>95 rows × 3 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    Column Name  Unknown Values Data Types\n",
+       "414     RDATE_5           95403    float64\n",
+       "436     RAMNT_5           95403    float64\n",
+       "412     RDATE_3           95170    float64\n",
+       "434     RAMNT_3           95170    float64\n",
+       "413     RDATE_4           95131    float64\n",
+       "..          ...             ...        ...\n",
+       "480    GEOCODE2             132     object\n",
+       "479    CLUSTER2             132    float64\n",
+       "409     NUMPROM               0      int64\n",
+       "408    MAXADATE               0      int64\n",
+       "307        AFC6               0      int64\n",
+       "\n",
+       "[95 rows x 3 columns]"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "unk_lst = []\n",
+    "for col in df.columns:\n",
+    "    column_name = col\n",
+    "    unk_values = int(df[col].isnull().sum())\n",
+    "    unk_dtypes = df[col].dtypes\n",
+    "    unk_lst.append([column_name,unk_values,unk_dtypes])\n",
+    "    \n",
+    "unk_df = pd.DataFrame(unk_lst,columns=[\"Column Name\",\"Unknown Values\", \"Data Types\"])\n",
+    "unk_df.sort_values(\"Unknown Values\", ascending=False).iloc[:95]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "79a6bb89-abad-4499-9a04-60fc5082acc0",
+   "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "df.columns = [column.lower().replace(' ', '_') for column in df.columns]"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -45,11 +210,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 21,
    "id": "3a07b75a",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "#drop_list = df.drop(columns='OSOURCE', 'ZIP')\n",
+    "drop_list = ['osource', 'zip']"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -61,11 +229,216 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 22,
    "id": "2b6f01b6",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "percent_df = df.isna().sum().sort_values(ascending = False)*100/len(df)\n",
+    "percent_df = percent_df.reset_index()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "a8647cbd-d71f-422b-a667-611586586268",
+   "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>column_name</th>\n",
+       "      <th>percent</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>rdate_5</td>\n",
+       "      <td>99.990567</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>ramnt_5</td>\n",
+       "      <td>99.990567</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>rdate_3</td>\n",
+       "      <td>99.746363</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>ramnt_3</td>\n",
+       "      <td>99.746363</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>rdate_4</td>\n",
+       "      <td>99.705488</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>ramnt_4</td>\n",
+       "      <td>99.705488</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>ramnt_6</td>\n",
+       "      <td>99.186685</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>rdate_6</td>\n",
+       "      <td>99.186685</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>ramnt_15</td>\n",
+       "      <td>92.388798</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>rdate_15</td>\n",
+       "      <td>92.388798</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>rdate_23</td>\n",
+       "      <td>91.763091</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>ramnt_23</td>\n",
+       "      <td>91.763091</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>rdate_20</td>\n",
+       "      <td>91.732696</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>ramnt_20</td>\n",
+       "      <td>91.732696</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>ramnt_7</td>\n",
+       "      <td>90.677273</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>rdate_7</td>\n",
+       "      <td>90.677273</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>ramnt_17</td>\n",
+       "      <td>90.146942</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17</th>\n",
+       "      <td>rdate_17</td>\n",
+       "      <td>90.146942</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>18</th>\n",
+       "      <td>rdate_21</td>\n",
+       "      <td>90.029556</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>19</th>\n",
+       "      <td>ramnt_21</td>\n",
+       "      <td>90.029556</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>20</th>\n",
+       "      <td>ramnt_10</td>\n",
+       "      <td>89.035970</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>21</th>\n",
+       "      <td>rdate_10</td>\n",
+       "      <td>89.035970</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22</th>\n",
+       "      <td>rdate_13</td>\n",
+       "      <td>87.160944</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23</th>\n",
+       "      <td>ramnt_13</td>\n",
+       "      <td>87.160944</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>24</th>\n",
+       "      <td>numchld</td>\n",
+       "      <td>87.018404</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   column_name    percent\n",
+       "0      rdate_5  99.990567\n",
+       "1      ramnt_5  99.990567\n",
+       "2      rdate_3  99.746363\n",
+       "3      ramnt_3  99.746363\n",
+       "4      rdate_4  99.705488\n",
+       "5      ramnt_4  99.705488\n",
+       "6      ramnt_6  99.186685\n",
+       "7      rdate_6  99.186685\n",
+       "8     ramnt_15  92.388798\n",
+       "9     rdate_15  92.388798\n",
+       "10    rdate_23  91.763091\n",
+       "11    ramnt_23  91.763091\n",
+       "12    rdate_20  91.732696\n",
+       "13    ramnt_20  91.732696\n",
+       "14     ramnt_7  90.677273\n",
+       "15     rdate_7  90.677273\n",
+       "16    ramnt_17  90.146942\n",
+       "17    rdate_17  90.146942\n",
+       "18    rdate_21  90.029556\n",
+       "19    ramnt_21  90.029556\n",
+       "20    ramnt_10  89.035970\n",
+       "21    rdate_10  89.035970\n",
+       "22    rdate_13  87.160944\n",
+       "23    ramnt_13  87.160944\n",
+       "24     numchld  87.018404"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "percent_df.columns = ['column_name', 'percent']\n",
+    "above85 = percent_df[percent_df['percent'] >= 85]\n",
+    "above85\n",
+    "#above85['name'].unique()"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -77,11 +450,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 24,
    "id": "ca6c4d91",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "for i in above85['column_name']:\n",
+    "    drop_list.append(i)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "85a511c0-67b7-428b-a035-29248927def0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i in drop_list: \n",
+    "    df = df.drop(i, axis = 1)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -100,9 +487,67 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 26,
    "id": "b583feaa",
    "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['F', 'M', ' ', 'C', 'U', 'J', 'A'], dtype=object)"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#data['gender'].value_counts()\n",
+    "df['gender'].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "b148fb95-d33f-44e1-8aa7-d1828914d5bf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['gender'] = df['gender'].fillna('F')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "376d39ed-3df9-48f5-b9a0-60dbdcf4f074",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "F        51277\n",
+       "M        39094\n",
+       "other     5041\n",
+       "Name: gender, dtype: int64"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['gender'] = df['gender'].fillna('F')\n",
+    "df['gender'] = df['gender'].apply(lambda x: x if x in ['M', 'F'] else 'other')\n",
+    "df['gender'].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "00f9bf63-f832-46f7-8077-39dcf941e877",
+   "metadata": {},
    "outputs": [],
    "source": []
   }
@@ -123,7 +568,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.5"
+   "version": "3.8.8"
   }
  },
  "nbformat": 4,