diff --git a/config.ini b/config.ini
new file mode 100644
index 0000000..5b7f968
--- /dev/null
+++ b/config.ini
@@ -0,0 +1,3 @@
+[data]
+; path to the local enron dataset
+; enron = <>
\ No newline at end of file
diff --git a/notebooks/data_explorer.ipynb b/notebooks/data_explorer.ipynb
new file mode 100644
index 0000000..8bcc5ef
--- /dev/null
+++ b/notebooks/data_explorer.ipynb
@@ -0,0 +1,1079 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['../config.ini']"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import glob\n",
+    "import re\n",
+    "from concurrent.futures import ThreadPoolExecutor\n",
+    "import email\n",
+    "\n",
+    "from utils.cleanup import remove_new_lines\n",
+    "from utils.data_fetch import LoadEnronData"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pois = ['kenneth.lay@enron.com', 'ken.rice@enron.com', 'raymond.bowen@enron.com', 'kevin.hannon@enron.com', 'jeff.skilling@enron.com', 'paula.rieker@enron.com', 'david.delainey@enron.com', 'scott.yeager@enron.com', 'rex.shelby@enron.com', 'tim.belden@enron.com', 'ben.glisan@enron.com', 'andrew.fastow@enron.com', 'richard.causey@enron.com', 'wes.colwell@enron.com', 'joe.hirko@enron.com', 'michael.kopper@enron.com', 'mark.koenig@enron.com', 'christopher.calger@enron.com']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = LoadEnronData()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# #get path from config -> [data] -> path assignment\n",
+    "# #make sure to change the path in config.ini to your local path\n",
+    "\n",
+    "# datapath = config['data']['enron']\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "# files = glob.glob(datapath + \"/**/*.\", recursive=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "# def process_email(file):\n",
+    "#         email_fields = {}\n",
+    "#         folder_user = file.split(datapath)[1].split('/')[0]\n",
+    "#         folder_name = file.split(datapath)[1].split('/')[1]\n",
+    "\n",
+    "#         email_fields['Folder-user'] = folder_user\n",
+    "#         email_fields['Folder-name'] = folder_name\n",
+    "\n",
+    "#         with open(file, \"rb\") as binary_file:\n",
+    "#             msg = email.message_from_binary_file(binary_file)\n",
+    "\n",
+    "#         # Extract fields from the email\n",
+    "#         for field in msg.keys():\n",
+    "#             email_fields[field] = msg[field]\n",
+    "\n",
+    "#         # Extract the email body\n",
+    "#         email_fields['Body'] = msg.get_payload()\n",
+    "\n",
+    "#         # print(f'Done with user {folder_user} and folder {folder_name}')\n",
+    "#         return email_fields\n",
+    "\n",
+    "# def get_email_df(files):\n",
+    "#     emails = []\n",
+    "#     with ThreadPoolExecutor(max_workers=8) as executor:  # Adjust max_workers as needed\n",
+    "#         results = list(executor.map(process_email, files))\n",
+    "#         emails.extend(results)\n",
+    "\n",
+    "#     return pd.DataFrame(emails)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# data = get_email_df(files)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "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>folder_user</th>\n",
+       "      <th>folder_name</th>\n",
+       "      <th>Message-ID</th>\n",
+       "      <th>Date</th>\n",
+       "      <th>From</th>\n",
+       "      <th>To</th>\n",
+       "      <th>Subject</th>\n",
+       "      <th>Mime-Version</th>\n",
+       "      <th>Content-Type</th>\n",
+       "      <th>Content-Transfer-Encoding</th>\n",
+       "      <th>...</th>\n",
+       "      <th>X-bcc</th>\n",
+       "      <th>X-Folder</th>\n",
+       "      <th>X-Origin</th>\n",
+       "      <th>X-FileName</th>\n",
+       "      <th>Body</th>\n",
+       "      <th>Cc</th>\n",
+       "      <th>Bcc</th>\n",
+       "      <th>Time</th>\n",
+       "      <th>Attendees</th>\n",
+       "      <th>Re</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>arnold-j</td>\n",
+       "      <td>notes_inbox</td>\n",
+       "      <td>&lt;17334447.1075857585446.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Thu, 16 Nov 2000 09:30:00 -0800 (PST)</td>\n",
+       "      <td>msagel@home.com</td>\n",
+       "      <td>jarnold@enron.com</td>\n",
+       "      <td>Status</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=ANSI_X3.4-1968</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\John_Arnold_Dec2000\\Notes Folders\\Notes inbox</td>\n",
+       "      <td>Arnold-J</td>\n",
+       "      <td>Jarnold.nsf</td>\n",
+       "      <td>John:\\n?\\nI'm not really sure what happened be...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>arnold-j</td>\n",
+       "      <td>notes_inbox</td>\n",
+       "      <td>&lt;19171686.1075857585034.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Fri, 8 Dec 2000 05:05:00 -0800 (PST)</td>\n",
+       "      <td>slafontaine@globalp.com</td>\n",
+       "      <td>john.arnold@enron.com</td>\n",
+       "      <td>re:summer inverses</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\John_Arnold_Dec2000\\Notes Folders\\Notes inbox</td>\n",
+       "      <td>Arnold-J</td>\n",
+       "      <td>Jarnold.nsf</td>\n",
+       "      <td>i suck-hope youve made more money in natgas la...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>arnold-j</td>\n",
+       "      <td>notes_inbox</td>\n",
+       "      <td>&lt;29887033.1075857630725.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Tue, 15 May 2001 09:43:00 -0700 (PDT)</td>\n",
+       "      <td>iceoperations@intcx.com</td>\n",
+       "      <td>icehelpdesk@intcx.com, internalmarketing@intcx...</td>\n",
+       "      <td>The WTI Bullet swap contracts</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\John_Arnold_Jun2001\\Notes Folders\\Notes inbox</td>\n",
+       "      <td>Arnold-J</td>\n",
+       "      <td>Jarnold.nsf</td>\n",
+       "      <td>Hi,\\n\\n\\n  Following the e-mail you have rece...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>arnold-j</td>\n",
+       "      <td>notes_inbox</td>\n",
+       "      <td>&lt;29084893.1075849630138.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Mon, 27 Nov 2000 01:49:00 -0800 (PST)</td>\n",
+       "      <td>jeff.youngflesh@enron.com</td>\n",
+       "      <td>anthony.gilmore@enron.com, colleen.koenig@enro...</td>\n",
+       "      <td>Invitation: EBS/GSS Meeting w/Bristol Babcock ...</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\John_Arnold_Nov2001\\Notes Folders\\Notes inbox</td>\n",
+       "      <td>ARNOLD-J</td>\n",
+       "      <td>jarnold.nsf</td>\n",
+       "      <td>Conference Room TBD.  \\n\\nThis meeting will be...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>arnold-j</td>\n",
+       "      <td>notes_inbox</td>\n",
+       "      <td>&lt;30248874.1075857584813.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Tue, 12 Dec 2000 09:33:00 -0800 (PST)</td>\n",
+       "      <td>caroline.abramo@enron.com</td>\n",
+       "      <td>mike.grigsby@enron.com</td>\n",
+       "      <td>Harvard Mgmt</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\John_Arnold_Dec2000\\Notes Folders\\Notes inbox</td>\n",
+       "      <td>Arnold-J</td>\n",
+       "      <td>Jarnold.nsf</td>\n",
+       "      <td>Mike- I have their trader coming into the offi...</td>\n",
+       "      <td>john.arnold@enron.com</td>\n",
+       "      <td>john.arnold@enron.com</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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>517395</th>\n",
+       "      <td>scholtes-d</td>\n",
+       "      <td>stf</td>\n",
+       "      <td>&lt;18618854.1075840028791.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Thu, 11 Oct 2001 09:39:47 -0700 (PDT)</td>\n",
+       "      <td>jodi.droll@xcelenergy.com</td>\n",
+       "      <td>isas@wscc.com</td>\n",
+       "      <td>RE: Scheduling Time constant</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\ExMerge - Scholtes, Diana\\STF\\Current issues</td>\n",
+       "      <td>SCHOLTES-D</td>\n",
+       "      <td></td>\n",
+       "      <td>I (PSCO TP &amp; CA) agree with Don.  I thought we...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>517396</th>\n",
+       "      <td>scholtes-d</td>\n",
+       "      <td>stf</td>\n",
+       "      <td>&lt;14350892.1075840028690.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Wed, 17 Oct 2001 16:11:39 -0700 (PDT)</td>\n",
+       "      <td>mark.hackney@aps.com</td>\n",
+       "      <td>isas@wscc.com</td>\n",
+       "      <td>FW: Standards Announcement - October 17, 2001</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\ExMerge - Scholtes, Diana\\STF\\Current issues</td>\n",
+       "      <td>SCHOLTES-D</td>\n",
+       "      <td></td>\n",
+       "      <td>FYI!!\\n\\n-----Original Message-----\\nFrom: Bar...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>517397</th>\n",
+       "      <td>scholtes-d</td>\n",
+       "      <td>stf</td>\n",
+       "      <td>&lt;21704474.1075840029683.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Fri, 6 Apr 2001 01:42:00 -0700 (PDT)</td>\n",
+       "      <td>paul.rice@pacificorp.com</td>\n",
+       "      <td>isas@wscc.com</td>\n",
+       "      <td>Late tags</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\ExMerge - Scholtes, Diana\\STF\\E-TAG</td>\n",
+       "      <td>SCHOLTES-D</td>\n",
+       "      <td></td>\n",
+       "      <td>Nothing is easy is it??  At the risk of the cr...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>517398</th>\n",
+       "      <td>scholtes-d</td>\n",
+       "      <td>stf</td>\n",
+       "      <td>&lt;9367927.1075840029633.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Mon, 9 Apr 2001 23:11:00 -0700 (PDT)</td>\n",
+       "      <td>gjcarter@bpa.gov</td>\n",
+       "      <td>'hara@enron.com, khara@avistaenergy.com, cara....</td>\n",
+       "      <td>RE: BCHA Automatic Denial/Approval</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\ExMerge - Scholtes, Diana\\STF\\E-TAG</td>\n",
+       "      <td>SCHOLTES-D</td>\n",
+       "      <td></td>\n",
+       "      <td>I think you are right on! In addition, I would...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>517399</th>\n",
+       "      <td>scholtes-d</td>\n",
+       "      <td>stf</td>\n",
+       "      <td>&lt;9368661.1075840029659.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Mon, 9 Apr 2001 21:55:00 -0700 (PDT)</td>\n",
+       "      <td>khara@avistaenergy.com</td>\n",
+       "      <td>cara.semperger@enron.com, demetrios.fotiou@bch...</td>\n",
+       "      <td>FW: BCHA Automatic Denial/Approval</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\ExMerge - Scholtes, Diana\\STF\\E-TAG</td>\n",
+       "      <td>SCHOLTES-D</td>\n",
+       "      <td></td>\n",
+       "      <td>\\n\\n&gt;  -----Original Message-----\\n&gt; From: \\tH...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>517400 rows × 23 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       folder_user  folder_name  \\\n",
+       "0         arnold-j  notes_inbox   \n",
+       "1         arnold-j  notes_inbox   \n",
+       "2         arnold-j  notes_inbox   \n",
+       "3         arnold-j  notes_inbox   \n",
+       "4         arnold-j  notes_inbox   \n",
+       "...            ...          ...   \n",
+       "517395  scholtes-d          stf   \n",
+       "517396  scholtes-d          stf   \n",
+       "517397  scholtes-d          stf   \n",
+       "517398  scholtes-d          stf   \n",
+       "517399  scholtes-d          stf   \n",
+       "\n",
+       "                                           Message-ID  \\\n",
+       "0       <17334447.1075857585446.JavaMail.evans@thyme>   \n",
+       "1       <19171686.1075857585034.JavaMail.evans@thyme>   \n",
+       "2       <29887033.1075857630725.JavaMail.evans@thyme>   \n",
+       "3       <29084893.1075849630138.JavaMail.evans@thyme>   \n",
+       "4       <30248874.1075857584813.JavaMail.evans@thyme>   \n",
+       "...                                               ...   \n",
+       "517395  <18618854.1075840028791.JavaMail.evans@thyme>   \n",
+       "517396  <14350892.1075840028690.JavaMail.evans@thyme>   \n",
+       "517397  <21704474.1075840029683.JavaMail.evans@thyme>   \n",
+       "517398   <9367927.1075840029633.JavaMail.evans@thyme>   \n",
+       "517399   <9368661.1075840029659.JavaMail.evans@thyme>   \n",
+       "\n",
+       "                                         Date                       From  \\\n",
+       "0       Thu, 16 Nov 2000 09:30:00 -0800 (PST)            msagel@home.com   \n",
+       "1        Fri, 8 Dec 2000 05:05:00 -0800 (PST)    slafontaine@globalp.com   \n",
+       "2       Tue, 15 May 2001 09:43:00 -0700 (PDT)    iceoperations@intcx.com   \n",
+       "3       Mon, 27 Nov 2000 01:49:00 -0800 (PST)  jeff.youngflesh@enron.com   \n",
+       "4       Tue, 12 Dec 2000 09:33:00 -0800 (PST)  caroline.abramo@enron.com   \n",
+       "...                                       ...                        ...   \n",
+       "517395  Thu, 11 Oct 2001 09:39:47 -0700 (PDT)  jodi.droll@xcelenergy.com   \n",
+       "517396  Wed, 17 Oct 2001 16:11:39 -0700 (PDT)       mark.hackney@aps.com   \n",
+       "517397   Fri, 6 Apr 2001 01:42:00 -0700 (PDT)   paul.rice@pacificorp.com   \n",
+       "517398   Mon, 9 Apr 2001 23:11:00 -0700 (PDT)           gjcarter@bpa.gov   \n",
+       "517399   Mon, 9 Apr 2001 21:55:00 -0700 (PDT)     khara@avistaenergy.com   \n",
+       "\n",
+       "                                                       To  \\\n",
+       "0                                       jarnold@enron.com   \n",
+       "1                                   john.arnold@enron.com   \n",
+       "2       icehelpdesk@intcx.com, internalmarketing@intcx...   \n",
+       "3       anthony.gilmore@enron.com, colleen.koenig@enro...   \n",
+       "4                                  mike.grigsby@enron.com   \n",
+       "...                                                   ...   \n",
+       "517395                                      isas@wscc.com   \n",
+       "517396                                      isas@wscc.com   \n",
+       "517397                                      isas@wscc.com   \n",
+       "517398  'hara@enron.com, khara@avistaenergy.com, cara....   \n",
+       "517399  cara.semperger@enron.com, demetrios.fotiou@bch...   \n",
+       "\n",
+       "                                                  Subject Mime-Version  \\\n",
+       "0                                                  Status          1.0   \n",
+       "1                                      re:summer inverses          1.0   \n",
+       "2                           The WTI Bullet swap contracts          1.0   \n",
+       "3       Invitation: EBS/GSS Meeting w/Bristol Babcock ...          1.0   \n",
+       "4                                            Harvard Mgmt          1.0   \n",
+       "...                                                   ...          ...   \n",
+       "517395                       RE: Scheduling Time constant          1.0   \n",
+       "517396      FW: Standards Announcement - October 17, 2001          1.0   \n",
+       "517397                                          Late tags          1.0   \n",
+       "517398                 RE: BCHA Automatic Denial/Approval          1.0   \n",
+       "517399                 FW: BCHA Automatic Denial/Approval          1.0   \n",
+       "\n",
+       "                              Content-Type Content-Transfer-Encoding  ...  \\\n",
+       "0       text/plain; charset=ANSI_X3.4-1968                      7bit  ...   \n",
+       "1             text/plain; charset=us-ascii                      7bit  ...   \n",
+       "2             text/plain; charset=us-ascii                      7bit  ...   \n",
+       "3             text/plain; charset=us-ascii                      7bit  ...   \n",
+       "4             text/plain; charset=us-ascii                      7bit  ...   \n",
+       "...                                    ...                       ...  ...   \n",
+       "517395        text/plain; charset=us-ascii                      7bit  ...   \n",
+       "517396        text/plain; charset=us-ascii                      7bit  ...   \n",
+       "517397        text/plain; charset=us-ascii                      7bit  ...   \n",
+       "517398        text/plain; charset=us-ascii                      7bit  ...   \n",
+       "517399        text/plain; charset=us-ascii                      7bit  ...   \n",
+       "\n",
+       "       X-bcc                                        X-Folder    X-Origin  \\\n",
+       "0             \\John_Arnold_Dec2000\\Notes Folders\\Notes inbox    Arnold-J   \n",
+       "1             \\John_Arnold_Dec2000\\Notes Folders\\Notes inbox    Arnold-J   \n",
+       "2             \\John_Arnold_Jun2001\\Notes Folders\\Notes inbox    Arnold-J   \n",
+       "3             \\John_Arnold_Nov2001\\Notes Folders\\Notes inbox    ARNOLD-J   \n",
+       "4             \\John_Arnold_Dec2000\\Notes Folders\\Notes inbox    Arnold-J   \n",
+       "...      ...                                             ...         ...   \n",
+       "517395         \\ExMerge - Scholtes, Diana\\STF\\Current issues  SCHOLTES-D   \n",
+       "517396         \\ExMerge - Scholtes, Diana\\STF\\Current issues  SCHOLTES-D   \n",
+       "517397                  \\ExMerge - Scholtes, Diana\\STF\\E-TAG  SCHOLTES-D   \n",
+       "517398                  \\ExMerge - Scholtes, Diana\\STF\\E-TAG  SCHOLTES-D   \n",
+       "517399                  \\ExMerge - Scholtes, Diana\\STF\\E-TAG  SCHOLTES-D   \n",
+       "\n",
+       "         X-FileName                                               Body  \\\n",
+       "0       Jarnold.nsf  John:\\n?\\nI'm not really sure what happened be...   \n",
+       "1       Jarnold.nsf  i suck-hope youve made more money in natgas la...   \n",
+       "2       Jarnold.nsf   Hi,\\n\\n\\n  Following the e-mail you have rece...   \n",
+       "3       jarnold.nsf  Conference Room TBD.  \\n\\nThis meeting will be...   \n",
+       "4       Jarnold.nsf  Mike- I have their trader coming into the offi...   \n",
+       "...             ...                                                ...   \n",
+       "517395               I (PSCO TP & CA) agree with Don.  I thought we...   \n",
+       "517396               FYI!!\\n\\n-----Original Message-----\\nFrom: Bar...   \n",
+       "517397               Nothing is easy is it??  At the risk of the cr...   \n",
+       "517398               I think you are right on! In addition, I would...   \n",
+       "517399               \\n\\n>  -----Original Message-----\\n> From: \\tH...   \n",
+       "\n",
+       "                           Cc                    Bcc Time Attendees   Re  \n",
+       "0                         NaN                    NaN  NaN       NaN  NaN  \n",
+       "1                         NaN                    NaN  NaN       NaN  NaN  \n",
+       "2                         NaN                    NaN  NaN       NaN  NaN  \n",
+       "3                         NaN                    NaN  NaN       NaN  NaN  \n",
+       "4       john.arnold@enron.com  john.arnold@enron.com  NaN       NaN  NaN  \n",
+       "...                       ...                    ...  ...       ...  ...  \n",
+       "517395                    NaN                    NaN  NaN       NaN  NaN  \n",
+       "517396                    NaN                    NaN  NaN       NaN  NaN  \n",
+       "517397                    NaN                    NaN  NaN       NaN  NaN  \n",
+       "517398                    NaN                    NaN  NaN       NaN  NaN  \n",
+       "517399                    NaN                    NaN  NaN       NaN  NaN  \n",
+       "\n",
+       "[517400 rows x 23 columns]"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'<19171686.1075857585034.JavaMail.evans@thyme>\\r\\nDate: Fri, 8 Dec 2000 05:05:00 -0800 (PST)\\r\\nFrom: slafontaine@globalp.com\\r\\nTo: john.arnold@enron.com\\r\\nSubject: re:summer inverses\\r\\nMime-Version: 1.0\\r\\nContent-Type: text/plain; charset=us-ascii\\r\\nContent-Transfer-Encoding: 7bit\\r\\nX-From: slafontaine@globalp.com\\r\\nX-To: John.Arnold@enron.com\\r\\nX-cc: \\r\\nX-bcc: \\r\\nX-Folder: \\\\John_Arnold_Dec2000\\\\Notes Folders\\\\Notes inbox\\r\\nX-Origin: Arnold-J\\r\\nX-FileName: Jarnold.nsf\\r\\n\\r\\ni suck-hope youve made more money in natgas last 3 weeks than i have. mkt shud\\nbe getting bearish feb forward-cuz we already have the weather upon us-fuel\\nswitching and the rest shud invert the whole curve not just dec cash to jan \\nand\\nfeb forward???? have a good weekend john\\n'"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# data['ID'].tolist()[1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data.to_csv('~/Local/datasets/enron_data.csv', index=False, sep=',', lineterminator='\\n')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "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>folder_user</th>\n",
+       "      <th>folder_name</th>\n",
+       "      <th>Message-ID</th>\n",
+       "      <th>Date</th>\n",
+       "      <th>From</th>\n",
+       "      <th>To</th>\n",
+       "      <th>Subject</th>\n",
+       "      <th>Mime-Version</th>\n",
+       "      <th>Content-Type</th>\n",
+       "      <th>Content-Transfer-Encoding</th>\n",
+       "      <th>...</th>\n",
+       "      <th>X-bcc</th>\n",
+       "      <th>X-Folder</th>\n",
+       "      <th>X-Origin</th>\n",
+       "      <th>X-FileName</th>\n",
+       "      <th>Body</th>\n",
+       "      <th>Cc</th>\n",
+       "      <th>Bcc</th>\n",
+       "      <th>Time</th>\n",
+       "      <th>Attendees</th>\n",
+       "      <th>Re</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>arnold-j</td>\n",
+       "      <td>notes_inbox</td>\n",
+       "      <td>&lt;17334447.1075857585446.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Thu, 16 Nov 2000 09:30:00 -0800 (PST)</td>\n",
+       "      <td>msagel@home.com</td>\n",
+       "      <td>jarnold@enron.com</td>\n",
+       "      <td>Status</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=ANSI_X3.4-1968</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\John_Arnold_Dec2000\\Notes Folders\\Notes inbox</td>\n",
+       "      <td>Arnold-J</td>\n",
+       "      <td>Jarnold.nsf</td>\n",
+       "      <td>John:\\n?\\nI'm not really sure what happened be...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>arnold-j</td>\n",
+       "      <td>notes_inbox</td>\n",
+       "      <td>&lt;19171686.1075857585034.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Fri, 8 Dec 2000 05:05:00 -0800 (PST)</td>\n",
+       "      <td>slafontaine@globalp.com</td>\n",
+       "      <td>john.arnold@enron.com</td>\n",
+       "      <td>re:summer inverses</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\John_Arnold_Dec2000\\Notes Folders\\Notes inbox</td>\n",
+       "      <td>Arnold-J</td>\n",
+       "      <td>Jarnold.nsf</td>\n",
+       "      <td>i suck-hope youve made more money in natgas la...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>arnold-j</td>\n",
+       "      <td>notes_inbox</td>\n",
+       "      <td>&lt;29887033.1075857630725.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Tue, 15 May 2001 09:43:00 -0700 (PDT)</td>\n",
+       "      <td>iceoperations@intcx.com</td>\n",
+       "      <td>icehelpdesk@intcx.com, internalmarketing@intcx...</td>\n",
+       "      <td>The WTI Bullet swap contracts</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\John_Arnold_Jun2001\\Notes Folders\\Notes inbox</td>\n",
+       "      <td>Arnold-J</td>\n",
+       "      <td>Jarnold.nsf</td>\n",
+       "      <td>Hi,\\n\\n\\n  Following the e-mail you have rece...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>arnold-j</td>\n",
+       "      <td>notes_inbox</td>\n",
+       "      <td>&lt;29084893.1075849630138.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Mon, 27 Nov 2000 01:49:00 -0800 (PST)</td>\n",
+       "      <td>jeff.youngflesh@enron.com</td>\n",
+       "      <td>anthony.gilmore@enron.com, colleen.koenig@enro...</td>\n",
+       "      <td>Invitation: EBS/GSS Meeting w/Bristol Babcock ...</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\John_Arnold_Nov2001\\Notes Folders\\Notes inbox</td>\n",
+       "      <td>ARNOLD-J</td>\n",
+       "      <td>jarnold.nsf</td>\n",
+       "      <td>Conference Room TBD.  \\n\\nThis meeting will be...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>arnold-j</td>\n",
+       "      <td>notes_inbox</td>\n",
+       "      <td>&lt;30248874.1075857584813.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Tue, 12 Dec 2000 09:33:00 -0800 (PST)</td>\n",
+       "      <td>caroline.abramo@enron.com</td>\n",
+       "      <td>mike.grigsby@enron.com</td>\n",
+       "      <td>Harvard Mgmt</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\John_Arnold_Dec2000\\Notes Folders\\Notes inbox</td>\n",
+       "      <td>Arnold-J</td>\n",
+       "      <td>Jarnold.nsf</td>\n",
+       "      <td>Mike- I have their trader coming into the offi...</td>\n",
+       "      <td>john.arnold@enron.com</td>\n",
+       "      <td>john.arnold@enron.com</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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>517395</th>\n",
+       "      <td>scholtes-d</td>\n",
+       "      <td>stf</td>\n",
+       "      <td>&lt;18618854.1075840028791.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Thu, 11 Oct 2001 09:39:47 -0700 (PDT)</td>\n",
+       "      <td>jodi.droll@xcelenergy.com</td>\n",
+       "      <td>isas@wscc.com</td>\n",
+       "      <td>RE: Scheduling Time constant</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\ExMerge - Scholtes, Diana\\STF\\Current issues</td>\n",
+       "      <td>SCHOLTES-D</td>\n",
+       "      <td></td>\n",
+       "      <td>I (PSCO TP &amp; CA) agree with Don.  I thought we...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>517396</th>\n",
+       "      <td>scholtes-d</td>\n",
+       "      <td>stf</td>\n",
+       "      <td>&lt;14350892.1075840028690.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Wed, 17 Oct 2001 16:11:39 -0700 (PDT)</td>\n",
+       "      <td>mark.hackney@aps.com</td>\n",
+       "      <td>isas@wscc.com</td>\n",
+       "      <td>FW: Standards Announcement - October 17, 2001</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\ExMerge - Scholtes, Diana\\STF\\Current issues</td>\n",
+       "      <td>SCHOLTES-D</td>\n",
+       "      <td></td>\n",
+       "      <td>FYI!!\\n\\n-----Original Message-----\\nFrom: Bar...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>517397</th>\n",
+       "      <td>scholtes-d</td>\n",
+       "      <td>stf</td>\n",
+       "      <td>&lt;21704474.1075840029683.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Fri, 6 Apr 2001 01:42:00 -0700 (PDT)</td>\n",
+       "      <td>paul.rice@pacificorp.com</td>\n",
+       "      <td>isas@wscc.com</td>\n",
+       "      <td>Late tags</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\ExMerge - Scholtes, Diana\\STF\\E-TAG</td>\n",
+       "      <td>SCHOLTES-D</td>\n",
+       "      <td></td>\n",
+       "      <td>Nothing is easy is it??  At the risk of the cr...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>517398</th>\n",
+       "      <td>scholtes-d</td>\n",
+       "      <td>stf</td>\n",
+       "      <td>&lt;9367927.1075840029633.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Mon, 9 Apr 2001 23:11:00 -0700 (PDT)</td>\n",
+       "      <td>gjcarter@bpa.gov</td>\n",
+       "      <td>'hara@enron.com, khara@avistaenergy.com, cara....</td>\n",
+       "      <td>RE: BCHA Automatic Denial/Approval</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\ExMerge - Scholtes, Diana\\STF\\E-TAG</td>\n",
+       "      <td>SCHOLTES-D</td>\n",
+       "      <td></td>\n",
+       "      <td>I think you are right on! In addition, I would...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>517399</th>\n",
+       "      <td>scholtes-d</td>\n",
+       "      <td>stf</td>\n",
+       "      <td>&lt;9368661.1075840029659.JavaMail.evans@thyme&gt;</td>\n",
+       "      <td>Mon, 9 Apr 2001 21:55:00 -0700 (PDT)</td>\n",
+       "      <td>khara@avistaenergy.com</td>\n",
+       "      <td>cara.semperger@enron.com, demetrios.fotiou@bch...</td>\n",
+       "      <td>FW: BCHA Automatic Denial/Approval</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>text/plain; charset=us-ascii</td>\n",
+       "      <td>7bit</td>\n",
+       "      <td>...</td>\n",
+       "      <td></td>\n",
+       "      <td>\\ExMerge - Scholtes, Diana\\STF\\E-TAG</td>\n",
+       "      <td>SCHOLTES-D</td>\n",
+       "      <td></td>\n",
+       "      <td>\\n\\n&gt;  -----Original Message-----\\n&gt; From: \\tH...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>517400 rows × 23 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       folder_user  folder_name  \\\n",
+       "0         arnold-j  notes_inbox   \n",
+       "1         arnold-j  notes_inbox   \n",
+       "2         arnold-j  notes_inbox   \n",
+       "3         arnold-j  notes_inbox   \n",
+       "4         arnold-j  notes_inbox   \n",
+       "...            ...          ...   \n",
+       "517395  scholtes-d          stf   \n",
+       "517396  scholtes-d          stf   \n",
+       "517397  scholtes-d          stf   \n",
+       "517398  scholtes-d          stf   \n",
+       "517399  scholtes-d          stf   \n",
+       "\n",
+       "                                           Message-ID  \\\n",
+       "0       <17334447.1075857585446.JavaMail.evans@thyme>   \n",
+       "1       <19171686.1075857585034.JavaMail.evans@thyme>   \n",
+       "2       <29887033.1075857630725.JavaMail.evans@thyme>   \n",
+       "3       <29084893.1075849630138.JavaMail.evans@thyme>   \n",
+       "4       <30248874.1075857584813.JavaMail.evans@thyme>   \n",
+       "...                                               ...   \n",
+       "517395  <18618854.1075840028791.JavaMail.evans@thyme>   \n",
+       "517396  <14350892.1075840028690.JavaMail.evans@thyme>   \n",
+       "517397  <21704474.1075840029683.JavaMail.evans@thyme>   \n",
+       "517398   <9367927.1075840029633.JavaMail.evans@thyme>   \n",
+       "517399   <9368661.1075840029659.JavaMail.evans@thyme>   \n",
+       "\n",
+       "                                         Date                       From  \\\n",
+       "0       Thu, 16 Nov 2000 09:30:00 -0800 (PST)            msagel@home.com   \n",
+       "1        Fri, 8 Dec 2000 05:05:00 -0800 (PST)    slafontaine@globalp.com   \n",
+       "2       Tue, 15 May 2001 09:43:00 -0700 (PDT)    iceoperations@intcx.com   \n",
+       "3       Mon, 27 Nov 2000 01:49:00 -0800 (PST)  jeff.youngflesh@enron.com   \n",
+       "4       Tue, 12 Dec 2000 09:33:00 -0800 (PST)  caroline.abramo@enron.com   \n",
+       "...                                       ...                        ...   \n",
+       "517395  Thu, 11 Oct 2001 09:39:47 -0700 (PDT)  jodi.droll@xcelenergy.com   \n",
+       "517396  Wed, 17 Oct 2001 16:11:39 -0700 (PDT)       mark.hackney@aps.com   \n",
+       "517397   Fri, 6 Apr 2001 01:42:00 -0700 (PDT)   paul.rice@pacificorp.com   \n",
+       "517398   Mon, 9 Apr 2001 23:11:00 -0700 (PDT)           gjcarter@bpa.gov   \n",
+       "517399   Mon, 9 Apr 2001 21:55:00 -0700 (PDT)     khara@avistaenergy.com   \n",
+       "\n",
+       "                                                       To  \\\n",
+       "0                                       jarnold@enron.com   \n",
+       "1                                   john.arnold@enron.com   \n",
+       "2       icehelpdesk@intcx.com, internalmarketing@intcx...   \n",
+       "3       anthony.gilmore@enron.com, colleen.koenig@enro...   \n",
+       "4                                  mike.grigsby@enron.com   \n",
+       "...                                                   ...   \n",
+       "517395                                      isas@wscc.com   \n",
+       "517396                                      isas@wscc.com   \n",
+       "517397                                      isas@wscc.com   \n",
+       "517398  'hara@enron.com, khara@avistaenergy.com, cara....   \n",
+       "517399  cara.semperger@enron.com, demetrios.fotiou@bch...   \n",
+       "\n",
+       "                                                  Subject Mime-Version  \\\n",
+       "0                                                  Status          1.0   \n",
+       "1                                      re:summer inverses          1.0   \n",
+       "2                           The WTI Bullet swap contracts          1.0   \n",
+       "3       Invitation: EBS/GSS Meeting w/Bristol Babcock ...          1.0   \n",
+       "4                                            Harvard Mgmt          1.0   \n",
+       "...                                                   ...          ...   \n",
+       "517395                       RE: Scheduling Time constant          1.0   \n",
+       "517396      FW: Standards Announcement - October 17, 2001          1.0   \n",
+       "517397                                          Late tags          1.0   \n",
+       "517398                 RE: BCHA Automatic Denial/Approval          1.0   \n",
+       "517399                 FW: BCHA Automatic Denial/Approval          1.0   \n",
+       "\n",
+       "                              Content-Type Content-Transfer-Encoding  ...  \\\n",
+       "0       text/plain; charset=ANSI_X3.4-1968                      7bit  ...   \n",
+       "1             text/plain; charset=us-ascii                      7bit  ...   \n",
+       "2             text/plain; charset=us-ascii                      7bit  ...   \n",
+       "3             text/plain; charset=us-ascii                      7bit  ...   \n",
+       "4             text/plain; charset=us-ascii                      7bit  ...   \n",
+       "...                                    ...                       ...  ...   \n",
+       "517395        text/plain; charset=us-ascii                      7bit  ...   \n",
+       "517396        text/plain; charset=us-ascii                      7bit  ...   \n",
+       "517397        text/plain; charset=us-ascii                      7bit  ...   \n",
+       "517398        text/plain; charset=us-ascii                      7bit  ...   \n",
+       "517399        text/plain; charset=us-ascii                      7bit  ...   \n",
+       "\n",
+       "       X-bcc                                        X-Folder    X-Origin  \\\n",
+       "0             \\John_Arnold_Dec2000\\Notes Folders\\Notes inbox    Arnold-J   \n",
+       "1             \\John_Arnold_Dec2000\\Notes Folders\\Notes inbox    Arnold-J   \n",
+       "2             \\John_Arnold_Jun2001\\Notes Folders\\Notes inbox    Arnold-J   \n",
+       "3             \\John_Arnold_Nov2001\\Notes Folders\\Notes inbox    ARNOLD-J   \n",
+       "4             \\John_Arnold_Dec2000\\Notes Folders\\Notes inbox    Arnold-J   \n",
+       "...      ...                                             ...         ...   \n",
+       "517395         \\ExMerge - Scholtes, Diana\\STF\\Current issues  SCHOLTES-D   \n",
+       "517396         \\ExMerge - Scholtes, Diana\\STF\\Current issues  SCHOLTES-D   \n",
+       "517397                  \\ExMerge - Scholtes, Diana\\STF\\E-TAG  SCHOLTES-D   \n",
+       "517398                  \\ExMerge - Scholtes, Diana\\STF\\E-TAG  SCHOLTES-D   \n",
+       "517399                  \\ExMerge - Scholtes, Diana\\STF\\E-TAG  SCHOLTES-D   \n",
+       "\n",
+       "         X-FileName                                               Body  \\\n",
+       "0       Jarnold.nsf  John:\\n?\\nI'm not really sure what happened be...   \n",
+       "1       Jarnold.nsf  i suck-hope youve made more money in natgas la...   \n",
+       "2       Jarnold.nsf   Hi,\\n\\n\\n  Following the e-mail you have rece...   \n",
+       "3       jarnold.nsf  Conference Room TBD.  \\n\\nThis meeting will be...   \n",
+       "4       Jarnold.nsf  Mike- I have their trader coming into the offi...   \n",
+       "...             ...                                                ...   \n",
+       "517395               I (PSCO TP & CA) agree with Don.  I thought we...   \n",
+       "517396               FYI!!\\n\\n-----Original Message-----\\nFrom: Bar...   \n",
+       "517397               Nothing is easy is it??  At the risk of the cr...   \n",
+       "517398               I think you are right on! In addition, I would...   \n",
+       "517399               \\n\\n>  -----Original Message-----\\n> From: \\tH...   \n",
+       "\n",
+       "                           Cc                    Bcc Time Attendees   Re  \n",
+       "0                         NaN                    NaN  NaN       NaN  NaN  \n",
+       "1                         NaN                    NaN  NaN       NaN  NaN  \n",
+       "2                         NaN                    NaN  NaN       NaN  NaN  \n",
+       "3                         NaN                    NaN  NaN       NaN  NaN  \n",
+       "4       john.arnold@enron.com  john.arnold@enron.com  NaN       NaN  NaN  \n",
+       "...                       ...                    ...  ...       ...  ...  \n",
+       "517395                    NaN                    NaN  NaN       NaN  NaN  \n",
+       "517396                    NaN                    NaN  NaN       NaN  NaN  \n",
+       "517397                    NaN                    NaN  NaN       NaN  NaN  \n",
+       "517398                    NaN                    NaN  NaN       NaN  NaN  \n",
+       "517399                    NaN                    NaN  NaN       NaN  NaN  \n",
+       "\n",
+       "[517400 rows x 23 columns]"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "ethical-fraud-detector-V2FuArT3-py3.10",
+   "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": "3.10.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/utils/__init__,py b/utils/__init__,py
new file mode 100644
index 0000000..e69de29
diff --git a/utils/cleanup.py b/utils/cleanup.py
new file mode 100644
index 0000000..2c3f505
--- /dev/null
+++ b/utils/cleanup.py
@@ -0,0 +1,18 @@
+import re
+
+def remove_new_lines(
+    text: str,
+):
+    """Remove new lines from text
+
+    Args:
+        text (str): text to remove new lines from
+    
+    Returns:
+        text (str): text with new lines removed
+    """
+    text = re.sub(r'\r\n', ' ', text)
+    text = re.sub(r'\n', ' ', text)
+    text = re.sub(r'\r', ' ', text)
+    return text
+    
\ No newline at end of file
diff --git a/utils/data_fetch.py b/utils/data_fetch.py
new file mode 100644
index 0000000..a8f456f
--- /dev/null
+++ b/utils/data_fetch.py
@@ -0,0 +1,76 @@
+import pandas as pd
+import glob
+import email
+from concurrent.futures import ThreadPoolExecutor
+
+#read config.ini file
+import configparser
+config = configparser.ConfigParser()
+config.read('../config.ini')
+
+
+class LoadEnronData:
+    def __call__(
+        self,
+        datapath: str | None = None,
+    ):
+        """Load the Enron email data
+
+        Note: 
+            To run this, please specify the local path to enron dataset in config.ini. 
+            Download path for enron dataset: https://www.cs.cmu.edu/~enron/enron_mail_20150507.tar.gz
+        
+        Args:
+            datapath (str, optional): Path to the Enron email data. Defaults to None.
+
+        Returns:
+            email_df (pd.DataFrame): DataFrame containing the email data
+        """
+        self.datapath = datapath
+
+        if self.datapath is None:
+            self.datapath = config['data']['enron']
+        
+        # Get all the email files
+        files = glob.glob(datapath + "/**/*.", recursive=True)
+
+        # Get the email fields
+        email_df = self.get_email_df(files)
+
+        return email_df
+    
+    def process_email(
+        self,
+        file: str,
+    ):
+        email_fields = {}
+        folder_user = file.split(self.datapath)[1].split('/')[0]
+        folder_name = file.split(self.datapath)[1].split('/')[1]
+
+        email_fields['Folder-User'] = folder_user
+        email_fields['Folder_Name'] = folder_name
+
+        with open(file, "rb") as binary_file:
+            msg = email.message_from_binary_file(binary_file)
+
+        # Extract fields from the email
+        for field in msg.keys():
+            email_fields[field] = msg[field]
+
+        # Extract the email body
+        email_fields['Body'] = msg.get_payload()
+
+        # print(f'Done with user {folder_user} and folder {folder_name}')
+        return email_fields
+
+    def get_email_df(
+        self,
+        files
+    ):
+        emails = []
+
+        with ThreadPoolExecutor(max_workers=8) as executor:  # Adjust max_workers as needed
+            results = list(executor.map(self.process_email, files))
+            emails.extend(results)
+
+        return pd.DataFrame(emails)