diff --git a/.gitignore b/.gitignore
index 46fe01e..2807f81 100644
--- a/.gitignore
+++ b/.gitignore
@@ -103,3 +103,6 @@ venv.bak/
 
 # mypy
 .mypy_cache/
+
+# vscode stuff
+.vscode/
\ No newline at end of file
diff --git a/chapters/1 Introduction/Example 1 Email Spam .ipynb b/chapters/1 Introduction/Example 1 Email Spam .ipynb
new file mode 100644
index 0000000..691911d
--- /dev/null
+++ b/chapters/1 Introduction/Example 1 Email Spam .ipynb	
@@ -0,0 +1,415 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "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>test</th>\n",
+       "      <th>word_freq_make</th>\n",
+       "      <th>word_freq_address</th>\n",
+       "      <th>word_freq_all</th>\n",
+       "      <th>word_freq_3d</th>\n",
+       "      <th>word_freq_our</th>\n",
+       "      <th>word_freq_over</th>\n",
+       "      <th>word_freq_remove</th>\n",
+       "      <th>word_freq_internet</th>\n",
+       "      <th>word_freq_order</th>\n",
+       "      <th>...</th>\n",
+       "      <th>char_freq_;</th>\n",
+       "      <th>char_freq_(</th>\n",
+       "      <th>char_freq_[</th>\n",
+       "      <th>char_freq_!</th>\n",
+       "      <th>char_freq_$</th>\n",
+       "      <th>char_freq_#</th>\n",
+       "      <th>capital_run_length_average</th>\n",
+       "      <th>capital_run_length_longest</th>\n",
+       "      <th>capital_run_length_total</th>\n",
+       "      <th>spam</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.64</td>\n",
+       "      <td>0.64</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.32</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.778</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>3.756</td>\n",
+       "      <td>61</td>\n",
+       "      <td>278</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0</td>\n",
+       "      <td>0.21</td>\n",
+       "      <td>0.28</td>\n",
+       "      <td>0.50</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.14</td>\n",
+       "      <td>0.28</td>\n",
+       "      <td>0.21</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.132</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.372</td>\n",
+       "      <td>0.180</td>\n",
+       "      <td>0.048</td>\n",
+       "      <td>5.114</td>\n",
+       "      <td>101</td>\n",
+       "      <td>1028</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>1</td>\n",
+       "      <td>0.06</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.71</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.23</td>\n",
+       "      <td>0.19</td>\n",
+       "      <td>0.19</td>\n",
+       "      <td>0.12</td>\n",
+       "      <td>0.64</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.143</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.276</td>\n",
+       "      <td>0.184</td>\n",
+       "      <td>0.010</td>\n",
+       "      <td>9.821</td>\n",
+       "      <td>485</td>\n",
+       "      <td>2259</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.63</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.31</td>\n",
+       "      <td>0.63</td>\n",
+       "      <td>0.31</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.137</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.137</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>3.537</td>\n",
+       "      <td>40</td>\n",
+       "      <td>191</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>0</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.63</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.31</td>\n",
+       "      <td>0.63</td>\n",
+       "      <td>0.31</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.135</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.135</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>0.000</td>\n",
+       "      <td>3.537</td>\n",
+       "      <td>40</td>\n",
+       "      <td>191</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 59 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   test  word_freq_make  word_freq_address  word_freq_all  word_freq_3d  \\\n",
+       "0     1            0.00               0.64           0.64           0.0   \n",
+       "1     0            0.21               0.28           0.50           0.0   \n",
+       "2     1            0.06               0.00           0.71           0.0   \n",
+       "3     0            0.00               0.00           0.00           0.0   \n",
+       "4     0            0.00               0.00           0.00           0.0   \n",
+       "\n",
+       "   word_freq_our  word_freq_over  word_freq_remove  word_freq_internet  \\\n",
+       "0           0.32            0.00              0.00                0.00   \n",
+       "1           0.14            0.28              0.21                0.07   \n",
+       "2           1.23            0.19              0.19                0.12   \n",
+       "3           0.63            0.00              0.31                0.63   \n",
+       "4           0.63            0.00              0.31                0.63   \n",
+       "\n",
+       "   word_freq_order  ...  char_freq_;  char_freq_(  char_freq_[  char_freq_!  \\\n",
+       "0             0.00  ...         0.00        0.000          0.0        0.778   \n",
+       "1             0.00  ...         0.00        0.132          0.0        0.372   \n",
+       "2             0.64  ...         0.01        0.143          0.0        0.276   \n",
+       "3             0.31  ...         0.00        0.137          0.0        0.137   \n",
+       "4             0.31  ...         0.00        0.135          0.0        0.135   \n",
+       "\n",
+       "   char_freq_$  char_freq_#  capital_run_length_average  \\\n",
+       "0        0.000        0.000                       3.756   \n",
+       "1        0.180        0.048                       5.114   \n",
+       "2        0.184        0.010                       9.821   \n",
+       "3        0.000        0.000                       3.537   \n",
+       "4        0.000        0.000                       3.537   \n",
+       "\n",
+       "   capital_run_length_longest  capital_run_length_total  spam  \n",
+       "0                          61                       278     1  \n",
+       "1                         101                      1028     1  \n",
+       "2                         485                      2259     1  \n",
+       "3                          40                       191     1  \n",
+       "4                          40                       191     1  \n",
+       "\n",
+       "[5 rows x 59 columns]"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df_spam = pd.read_csv(\"../../data/Spam.txt\")\n",
+    "df_spam.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Index(['test', 'word_freq_make', 'word_freq_address', 'word_freq_all',\n",
+      "       'word_freq_3d', 'word_freq_our', 'word_freq_over', 'word_freq_remove',\n",
+      "       'word_freq_internet', 'word_freq_order', 'word_freq_mail',\n",
+      "       'word_freq_receive', 'word_freq_will', 'word_freq_people',\n",
+      "       'word_freq_report', 'word_freq_addresses', 'word_freq_free',\n",
+      "       'word_freq_business', 'word_freq_email', 'word_freq_you',\n",
+      "       'word_freq_credit', 'word_freq_your', 'word_freq_font', 'word_freq_000',\n",
+      "       'word_freq_money', 'word_freq_hp', 'word_freq_hpl', 'word_freq_george',\n",
+      "       'word_freq_650', 'word_freq_lab', 'word_freq_labs', 'word_freq_telnet',\n",
+      "       'word_freq_857', 'word_freq_data', 'word_freq_415', 'word_freq_85',\n",
+      "       'word_freq_technology', 'word_freq_1999', 'word_freq_parts',\n",
+      "       'word_freq_pm', 'word_freq_direct', 'word_freq_cs', 'word_freq_meeting',\n",
+      "       'word_freq_original', 'word_freq_project', 'word_freq_re',\n",
+      "       'word_freq_edu', 'word_freq_table', 'word_freq_conference',\n",
+      "       'char_freq_;', 'char_freq_(', 'char_freq_[', 'char_freq_!',\n",
+      "       'char_freq_$', 'char_freq_#', 'capital_run_length_average',\n",
+      "       'capital_run_length_longest', 'capital_run_length_total', 'spam'],\n",
+      "      dtype='object')\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(df_spam.columns)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['make', 'address', 'all', '3d', 'our', 'over', 'remove', 'internet', 'order', 'mail', 'receive', 'will', 'people', 'report', 'addresses', 'free', 'business', 'email', 'you', 'credit', 'your', 'font', '000', 'money', 'hp', 'hpl', 'george', '650', 'lab', 'labs', 'telnet', '857', 'data', '415', '85', 'technology', '1999', 'parts', 'pm', 'direct', 'cs', 'meeting', 'original', 'project', 're', 'edu', 'table', 'conference']\n"
+     ]
+    }
+   ],
+   "source": [
+    "words_feature = [word for word in df_spam.columns if 'word_freq' in word]\n",
+    "words = [word[10:] for word in words_feature]\n",
+    "# print(words_feature)\n",
+    "print(words)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "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>george</th>\n",
+       "      <th>you</th>\n",
+       "      <th>your</th>\n",
+       "      <th>hp</th>\n",
+       "      <th>free</th>\n",
+       "      <th>hpl</th>\n",
+       "      <th>our</th>\n",
+       "      <th>re</th>\n",
+       "      <th>edu</th>\n",
+       "      <th>remove</th>\n",
+       "      <th>000</th>\n",
+       "      <th>business</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>spam</th>\n",
+       "      <td>0.00</td>\n",
+       "      <td>2.26</td>\n",
+       "      <td>1.38</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.52</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.51</td>\n",
+       "      <td>0.13</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.28</td>\n",
+       "      <td>0.25</td>\n",
+       "      <td>0.29</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>email</th>\n",
+       "      <td>1.27</td>\n",
+       "      <td>1.27</td>\n",
+       "      <td>0.44</td>\n",
+       "      <td>0.90</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.43</td>\n",
+       "      <td>0.18</td>\n",
+       "      <td>0.42</td>\n",
+       "      <td>0.29</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.05</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       george  you  your   hp  free  hpl  our   re  edu  remove  000  business\n",
+       "spam     0.00 2.26  1.38 0.02  0.52 0.01 0.51 0.13 0.01    0.28 0.25      0.29\n",
+       "email    1.27 1.27  0.44 0.90  0.07 0.43 0.18 0.42 0.29    0.01 0.01      0.05"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "temp = df_spam[words_feature + ['spam']].groupby('spam').mean().sort_index(ascending=False)\n",
+    "temp.columns = words\n",
+    "temp.index = ['spam','email']\n",
+    "with pd.option_context(\"float_format\",'{:,.2f}'.format):\n",
+    "    display(temp[(temp.iloc[0] - temp.iloc[1]).abs().sort_values(ascending=False).index[:12]])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "interpreter": {
+   "hash": "58dd21b98941f49f3ff1e43b315fad01188084135da91d73015e8a9aac331f94"
+  },
+  "kernelspec": {
+   "display_name": "Python 3.9.5 64-bit ('env_esl': virtualenvwrapper)",
+   "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": "3.9.5"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
\ No newline at end of file