diff --git a/your-code/.ipynb_checkpoints/main-checkpoint.ipynb b/your-code/.ipynb_checkpoints/main-checkpoint.ipynb
index 31724c5..afa35d2 100644
--- a/your-code/.ipynb_checkpoints/main-checkpoint.ipynb
+++ b/your-code/.ipynb_checkpoints/main-checkpoint.ipynb
@@ -9,10 +9,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "import pandas as pd"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -23,10 +25,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "import pymysql"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -37,10 +41,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "from sqlalchemy import create_engine"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -51,10 +57,208 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "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>id</th>\n",
+       "      <th>year</th>\n",
+       "      <th>month</th>\n",
+       "      <th>element</th>\n",
+       "      <th>d1</th>\n",
+       "      <th>d2</th>\n",
+       "      <th>d3</th>\n",
+       "      <th>d4</th>\n",
+       "      <th>d5</th>\n",
+       "      <th>d6</th>\n",
+       "      <th>...</th>\n",
+       "      <th>d22</th>\n",
+       "      <th>d23</th>\n",
+       "      <th>d24</th>\n",
+       "      <th>d25</th>\n",
+       "      <th>d26</th>\n",
+       "      <th>d27</th>\n",
+       "      <th>d28</th>\n",
+       "      <th>d29</th>\n",
+       "      <th>d30</th>\n",
+       "      <th>d31</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <td>0</td>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>1</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>27.8</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1</td>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>1</td>\n",
+       "      <td>tmin</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>14.5</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2</td>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>2</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>27.3</td>\n",
+       "      <td>24.1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>29.9</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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",
+       "      <td>3</td>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>2</td>\n",
+       "      <td>tmin</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>14.4</td>\n",
+       "      <td>14.4</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>10.7</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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",
+       "      <td>4</td>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>3</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>32.1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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>5 rows × 35 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "        id  year  month element  d1    d2    d3  d4    d5  d6  ...  d22   d23  \\\n",
+       "0  MX17004  2010      1    tmax NaN   NaN   NaN NaN   NaN NaN  ...  NaN   NaN   \n",
+       "1  MX17004  2010      1    tmin NaN   NaN   NaN NaN   NaN NaN  ...  NaN   NaN   \n",
+       "2  MX17004  2010      2    tmax NaN  27.3  24.1 NaN   NaN NaN  ...  NaN  29.9   \n",
+       "3  MX17004  2010      2    tmin NaN  14.4  14.4 NaN   NaN NaN  ...  NaN  10.7   \n",
+       "4  MX17004  2010      3    tmax NaN   NaN   NaN NaN  32.1 NaN  ...  NaN   NaN   \n",
+       "\n",
+       "   d24  d25  d26  d27  d28  d29   d30  d31  \n",
+       "0  NaN  NaN  NaN  NaN  NaN  NaN  27.8  NaN  \n",
+       "1  NaN  NaN  NaN  NaN  NaN  NaN  14.5  NaN  \n",
+       "2  NaN  NaN  NaN  NaN  NaN  NaN   NaN  NaN  \n",
+       "3  NaN  NaN  NaN  NaN  NaN  NaN   NaN  NaN  \n",
+       "4  NaN  NaN  NaN  NaN  NaN  NaN   NaN  NaN  \n",
+       "\n",
+       "[5 rows x 35 columns]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "engine = create_engine('mysql+pymysql://guest:relational@relational.fit.cvut.cz/stats')\n",
+    "df2 = pd.read_sql_table('users', con=engine) \n",
+    "#data=pd.read_csv(\"C:\\\\Users\\\\josea_000\\\\desktop\\\\data_labs\\\\lab-data-cleaning\\\\weather-raw.csv\")\n",
+    "#data.head(5)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -65,10 +269,60 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "userId      object\n",
+       "year         int64\n",
+       "month        int64\n",
+       "element     object\n",
+       "d1         float64\n",
+       "d2         float64\n",
+       "d3         float64\n",
+       "d4         float64\n",
+       "d5         float64\n",
+       "d6         float64\n",
+       "d7         float64\n",
+       "d8         float64\n",
+       "d9         float64\n",
+       "d10        float64\n",
+       "d11        float64\n",
+       "d12        float64\n",
+       "d13        float64\n",
+       "d14        float64\n",
+       "d15        float64\n",
+       "d16        float64\n",
+       "d17        float64\n",
+       "d18        float64\n",
+       "d19        float64\n",
+       "d20        float64\n",
+       "d21        float64\n",
+       "d22        float64\n",
+       "d23        float64\n",
+       "d24        float64\n",
+       "d25        float64\n",
+       "d26        float64\n",
+       "d27        float64\n",
+       "d28        float64\n",
+       "d29        float64\n",
+       "d30        float64\n",
+       "d31        float64\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.rename(columns={'id':'userId'}, inplace=True)\n",
+    "data.head(5)\n",
+    "data.dtypes"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -79,10 +333,144 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "df = pd.read_sql_table('posts', con=engine)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {
+    "scrolled": true
+   },
+   "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>Id</th>\n",
+       "      <th>Reputation</th>\n",
+       "      <th>CreationDate</th>\n",
+       "      <th>DisplayName</th>\n",
+       "      <th>LastAccessDate</th>\n",
+       "      <th>WebsiteUrl</th>\n",
+       "      <th>Location</th>\n",
+       "      <th>AboutMe</th>\n",
+       "      <th>Views</th>\n",
+       "      <th>UpVotes</th>\n",
+       "      <th>DownVotes</th>\n",
+       "      <th>AccountId</th>\n",
+       "      <th>Age</th>\n",
+       "      <th>ProfileImageUrl</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <td>0</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2010-07-19 06:55:26</td>\n",
+       "      <td>Community</td>\n",
+       "      <td>2010-07-19 06:55:26</td>\n",
+       "      <td>http://meta.stackexchange.com/</td>\n",
+       "      <td>on the server farm</td>\n",
+       "      <td>&lt;p&gt;Hi, I'm not really a person.&lt;/p&gt;\\n\\n&lt;p&gt;I'm ...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>None</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>101</td>\n",
+       "      <td>2010-07-19 14:01:36</td>\n",
+       "      <td>Geoff Dalgas</td>\n",
+       "      <td>2013-11-12 22:07:23</td>\n",
+       "      <td>http://stackoverflow.com</td>\n",
+       "      <td>Corvallis, OR</td>\n",
+       "      <td>&lt;p&gt;Developer on the StackOverflow team.  Find ...</td>\n",
+       "      <td>25</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>37.0</td>\n",
+       "      <td>None</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2</td>\n",
+       "      <td>3</td>\n",
+       "      <td>101</td>\n",
+       "      <td>2010-07-19 15:34:50</td>\n",
+       "      <td>Jarrod Dixon</td>\n",
+       "      <td>2014-08-08 06:42:58</td>\n",
+       "      <td>http://stackoverflow.com</td>\n",
+       "      <td>New York, NY</td>\n",
+       "      <td>&lt;p&gt;&lt;a href=\"http://blog.stackoverflow.com/2009...</td>\n",
+       "      <td>22</td>\n",
+       "      <td>19</td>\n",
+       "      <td>0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>35.0</td>\n",
+       "      <td>None</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Id  Reputation        CreationDate   DisplayName      LastAccessDate  \\\n",
+       "0  -1           1 2010-07-19 06:55:26     Community 2010-07-19 06:55:26   \n",
+       "1   2         101 2010-07-19 14:01:36  Geoff Dalgas 2013-11-12 22:07:23   \n",
+       "2   3         101 2010-07-19 15:34:50  Jarrod Dixon 2014-08-08 06:42:58   \n",
+       "\n",
+       "                       WebsiteUrl            Location  \\\n",
+       "0  http://meta.stackexchange.com/  on the server farm   \n",
+       "1        http://stackoverflow.com       Corvallis, OR   \n",
+       "2        http://stackoverflow.com        New York, NY   \n",
+       "\n",
+       "                                             AboutMe  Views  UpVotes  \\\n",
+       "0  <p>Hi, I'm not really a person.</p>\\n\\n<p>I'm ...      0     5007   \n",
+       "1  <p>Developer on the StackOverflow team.  Find ...     25        3   \n",
+       "2  <p><a href=\"http://blog.stackoverflow.com/2009...     22       19   \n",
+       "\n",
+       "   DownVotes  AccountId   Age ProfileImageUrl  \n",
+       "0       1920         -1   NaN            None  \n",
+       "1          0          2  37.0            None  \n",
+       "2          0          3  35.0            None  "
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head(1)\n",
+    "df2.head(3)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -93,10 +481,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "df.rename(columns={'Id':'postId','OwnerUserId':'userId'}, inplace=True)\n",
+    "df2.rename(columns={'Id':'userId'}, inplace=True)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -109,10 +500,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 23,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(91976, 5)"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "col_users=['userId','Reputation','Views','UpVotes','DownVotes']\n",
+    "col_posts=['postId','Score','userId','ViewCount','CommentCount']\n",
+    "users=df2[col_users]\n",
+    "posts=df[col_posts]\n",
+    "users.shape\n",
+    "posts.shape"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -124,10 +533,226 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "Union=pd.merge(users,posts,on='userId')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "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>userId</th>\n",
+       "      <th>Reputation</th>\n",
+       "      <th>Views</th>\n",
+       "      <th>UpVotes</th>\n",
+       "      <th>DownVotes</th>\n",
+       "      <th>postId</th>\n",
+       "      <th>Score</th>\n",
+       "      <th>ViewCount</th>\n",
+       "      <th>CommentCount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <td>0</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>2175</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>8576</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>8578</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>3</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>8981</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>4</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>8982</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\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",
+       "      <td>90579</td>\n",
+       "      <td>55734</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>115352</td>\n",
+       "      <td>0</td>\n",
+       "      <td>16.0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>90580</td>\n",
+       "      <td>55738</td>\n",
+       "      <td>11</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>115360</td>\n",
+       "      <td>2</td>\n",
+       "      <td>40.0</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>90581</td>\n",
+       "      <td>55742</td>\n",
+       "      <td>6</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>115366</td>\n",
+       "      <td>1</td>\n",
+       "      <td>17.0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>90582</td>\n",
+       "      <td>55744</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>115370</td>\n",
+       "      <td>1</td>\n",
+       "      <td>13.0</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>90583</td>\n",
+       "      <td>55746</td>\n",
+       "      <td>106</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>115376</td>\n",
+       "      <td>1</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>90584 rows × 9 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       userId  Reputation  Views  UpVotes  DownVotes  postId  Score  \\\n",
+       "0          -1           1      0     5007       1920    2175      0   \n",
+       "1          -1           1      0     5007       1920    8576      0   \n",
+       "2          -1           1      0     5007       1920    8578      0   \n",
+       "3          -1           1      0     5007       1920    8981      0   \n",
+       "4          -1           1      0     5007       1920    8982      0   \n",
+       "...       ...         ...    ...      ...        ...     ...    ...   \n",
+       "90579   55734           1      0        0          0  115352      0   \n",
+       "90580   55738          11      0        0          0  115360      2   \n",
+       "90581   55742           6      0        0          0  115366      1   \n",
+       "90582   55744           6      1        0          0  115370      1   \n",
+       "90583   55746         106      1        0          0  115376      1   \n",
+       "\n",
+       "       ViewCount  CommentCount  \n",
+       "0            NaN             0  \n",
+       "1            NaN             0  \n",
+       "2            NaN             0  \n",
+       "3            NaN             0  \n",
+       "4            NaN             0  \n",
+       "...          ...           ...  \n",
+       "90579       16.0             0  \n",
+       "90580       40.0             4  \n",
+       "90581       17.0             0  \n",
+       "90582       13.0             2  \n",
+       "90583        5.0             2  \n",
+       "\n",
+       "[90584 rows x 9 columns]"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "Union"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -138,10 +763,33 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 27,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "userId              0\n",
+       "Reputation          0\n",
+       "Views               0\n",
+       "UpVotes             0\n",
+       "DownVotes           0\n",
+       "postId              0\n",
+       "Score               0\n",
+       "ViewCount       48396\n",
+       "CommentCount        0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "Union.isnull().sum()\n",
+    "#There are 48,396 missing values in column 'ViewCount' "
+   ]
   },
   {
    "cell_type": "markdown",
@@ -153,10 +801,37 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 32,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "userId           55746.0\n",
+       "Reputation       87393.0\n",
+       "Views            20932.0\n",
+       "UpVotes          11442.0\n",
+       "DownVotes         1920.0\n",
+       "postId          115378.0\n",
+       "Score              192.0\n",
+       "ViewCount       175495.0\n",
+       "CommentCount        45.0\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#I would not erase all rows with missing values in column 'ViewCount' because data of other \n",
+    "#columns are useful too. Instead I would replace it with zeros and I would notice in the analysis\n",
+    "#that involve column 'ViewCount' that important fact and the lack of realiability of its conclusions.\n",
+    "\n",
+    "Union['ViewCount']=Union['ViewCount'].fillna(0)\n",
+    "Union.max()"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -167,10 +842,40 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 42,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "userId            int64\n",
+       "Reputation        int64\n",
+       "Views             int64\n",
+       "UpVotes           int64\n",
+       "DownVotes         int64\n",
+       "postId            int64\n",
+       "Score             int64\n",
+       "ViewCount       float64\n",
+       "CommentCount      int64\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 42,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#I think would be better that columns 'userId' and 'postId' were string data type because\n",
+    "#there won't be calculations on it and I would change the numerical type of the other columns from \n",
+    "#int64 or float to int32, I cannot see a number greater than 2,147,483,647 and it would be supposed \n",
+    "#increase speed processing.\n",
+    "Union.dtypes\n",
+    "to_string=['userId','postId']\n",
+    "to_int32=['Reputation','Views','UpVotes','DownVotes','Score','ViewCount','CommentCount']\n",
+    "Union[to_string].astype(str)\n",
+    "Union[to_int32].astype('int32')\n"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -196,7 +901,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.5"
+   "version": "3.7.4"
   }
  },
  "nbformat": 4,
diff --git a/your-code/main.ipynb b/your-code/main.ipynb
index 31724c5..afa35d2 100644
--- a/your-code/main.ipynb
+++ b/your-code/main.ipynb
@@ -9,10 +9,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "import pandas as pd"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -23,10 +25,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "import pymysql"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -37,10 +41,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "from sqlalchemy import create_engine"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -51,10 +57,208 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "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>id</th>\n",
+       "      <th>year</th>\n",
+       "      <th>month</th>\n",
+       "      <th>element</th>\n",
+       "      <th>d1</th>\n",
+       "      <th>d2</th>\n",
+       "      <th>d3</th>\n",
+       "      <th>d4</th>\n",
+       "      <th>d5</th>\n",
+       "      <th>d6</th>\n",
+       "      <th>...</th>\n",
+       "      <th>d22</th>\n",
+       "      <th>d23</th>\n",
+       "      <th>d24</th>\n",
+       "      <th>d25</th>\n",
+       "      <th>d26</th>\n",
+       "      <th>d27</th>\n",
+       "      <th>d28</th>\n",
+       "      <th>d29</th>\n",
+       "      <th>d30</th>\n",
+       "      <th>d31</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <td>0</td>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>1</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>27.8</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1</td>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>1</td>\n",
+       "      <td>tmin</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>14.5</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2</td>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>2</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>27.3</td>\n",
+       "      <td>24.1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>29.9</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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",
+       "      <td>3</td>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>2</td>\n",
+       "      <td>tmin</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>14.4</td>\n",
+       "      <td>14.4</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>10.7</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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",
+       "      <td>4</td>\n",
+       "      <td>MX17004</td>\n",
+       "      <td>2010</td>\n",
+       "      <td>3</td>\n",
+       "      <td>tmax</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>32.1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</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>5 rows × 35 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "        id  year  month element  d1    d2    d3  d4    d5  d6  ...  d22   d23  \\\n",
+       "0  MX17004  2010      1    tmax NaN   NaN   NaN NaN   NaN NaN  ...  NaN   NaN   \n",
+       "1  MX17004  2010      1    tmin NaN   NaN   NaN NaN   NaN NaN  ...  NaN   NaN   \n",
+       "2  MX17004  2010      2    tmax NaN  27.3  24.1 NaN   NaN NaN  ...  NaN  29.9   \n",
+       "3  MX17004  2010      2    tmin NaN  14.4  14.4 NaN   NaN NaN  ...  NaN  10.7   \n",
+       "4  MX17004  2010      3    tmax NaN   NaN   NaN NaN  32.1 NaN  ...  NaN   NaN   \n",
+       "\n",
+       "   d24  d25  d26  d27  d28  d29   d30  d31  \n",
+       "0  NaN  NaN  NaN  NaN  NaN  NaN  27.8  NaN  \n",
+       "1  NaN  NaN  NaN  NaN  NaN  NaN  14.5  NaN  \n",
+       "2  NaN  NaN  NaN  NaN  NaN  NaN   NaN  NaN  \n",
+       "3  NaN  NaN  NaN  NaN  NaN  NaN   NaN  NaN  \n",
+       "4  NaN  NaN  NaN  NaN  NaN  NaN   NaN  NaN  \n",
+       "\n",
+       "[5 rows x 35 columns]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "engine = create_engine('mysql+pymysql://guest:relational@relational.fit.cvut.cz/stats')\n",
+    "df2 = pd.read_sql_table('users', con=engine) \n",
+    "#data=pd.read_csv(\"C:\\\\Users\\\\josea_000\\\\desktop\\\\data_labs\\\\lab-data-cleaning\\\\weather-raw.csv\")\n",
+    "#data.head(5)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -65,10 +269,60 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "userId      object\n",
+       "year         int64\n",
+       "month        int64\n",
+       "element     object\n",
+       "d1         float64\n",
+       "d2         float64\n",
+       "d3         float64\n",
+       "d4         float64\n",
+       "d5         float64\n",
+       "d6         float64\n",
+       "d7         float64\n",
+       "d8         float64\n",
+       "d9         float64\n",
+       "d10        float64\n",
+       "d11        float64\n",
+       "d12        float64\n",
+       "d13        float64\n",
+       "d14        float64\n",
+       "d15        float64\n",
+       "d16        float64\n",
+       "d17        float64\n",
+       "d18        float64\n",
+       "d19        float64\n",
+       "d20        float64\n",
+       "d21        float64\n",
+       "d22        float64\n",
+       "d23        float64\n",
+       "d24        float64\n",
+       "d25        float64\n",
+       "d26        float64\n",
+       "d27        float64\n",
+       "d28        float64\n",
+       "d29        float64\n",
+       "d30        float64\n",
+       "d31        float64\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.rename(columns={'id':'userId'}, inplace=True)\n",
+    "data.head(5)\n",
+    "data.dtypes"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -79,10 +333,144 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "df = pd.read_sql_table('posts', con=engine)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {
+    "scrolled": true
+   },
+   "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>Id</th>\n",
+       "      <th>Reputation</th>\n",
+       "      <th>CreationDate</th>\n",
+       "      <th>DisplayName</th>\n",
+       "      <th>LastAccessDate</th>\n",
+       "      <th>WebsiteUrl</th>\n",
+       "      <th>Location</th>\n",
+       "      <th>AboutMe</th>\n",
+       "      <th>Views</th>\n",
+       "      <th>UpVotes</th>\n",
+       "      <th>DownVotes</th>\n",
+       "      <th>AccountId</th>\n",
+       "      <th>Age</th>\n",
+       "      <th>ProfileImageUrl</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <td>0</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2010-07-19 06:55:26</td>\n",
+       "      <td>Community</td>\n",
+       "      <td>2010-07-19 06:55:26</td>\n",
+       "      <td>http://meta.stackexchange.com/</td>\n",
+       "      <td>on the server farm</td>\n",
+       "      <td>&lt;p&gt;Hi, I'm not really a person.&lt;/p&gt;\\n\\n&lt;p&gt;I'm ...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>None</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>101</td>\n",
+       "      <td>2010-07-19 14:01:36</td>\n",
+       "      <td>Geoff Dalgas</td>\n",
+       "      <td>2013-11-12 22:07:23</td>\n",
+       "      <td>http://stackoverflow.com</td>\n",
+       "      <td>Corvallis, OR</td>\n",
+       "      <td>&lt;p&gt;Developer on the StackOverflow team.  Find ...</td>\n",
+       "      <td>25</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "      <td>37.0</td>\n",
+       "      <td>None</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2</td>\n",
+       "      <td>3</td>\n",
+       "      <td>101</td>\n",
+       "      <td>2010-07-19 15:34:50</td>\n",
+       "      <td>Jarrod Dixon</td>\n",
+       "      <td>2014-08-08 06:42:58</td>\n",
+       "      <td>http://stackoverflow.com</td>\n",
+       "      <td>New York, NY</td>\n",
+       "      <td>&lt;p&gt;&lt;a href=\"http://blog.stackoverflow.com/2009...</td>\n",
+       "      <td>22</td>\n",
+       "      <td>19</td>\n",
+       "      <td>0</td>\n",
+       "      <td>3</td>\n",
+       "      <td>35.0</td>\n",
+       "      <td>None</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Id  Reputation        CreationDate   DisplayName      LastAccessDate  \\\n",
+       "0  -1           1 2010-07-19 06:55:26     Community 2010-07-19 06:55:26   \n",
+       "1   2         101 2010-07-19 14:01:36  Geoff Dalgas 2013-11-12 22:07:23   \n",
+       "2   3         101 2010-07-19 15:34:50  Jarrod Dixon 2014-08-08 06:42:58   \n",
+       "\n",
+       "                       WebsiteUrl            Location  \\\n",
+       "0  http://meta.stackexchange.com/  on the server farm   \n",
+       "1        http://stackoverflow.com       Corvallis, OR   \n",
+       "2        http://stackoverflow.com        New York, NY   \n",
+       "\n",
+       "                                             AboutMe  Views  UpVotes  \\\n",
+       "0  <p>Hi, I'm not really a person.</p>\\n\\n<p>I'm ...      0     5007   \n",
+       "1  <p>Developer on the StackOverflow team.  Find ...     25        3   \n",
+       "2  <p><a href=\"http://blog.stackoverflow.com/2009...     22       19   \n",
+       "\n",
+       "   DownVotes  AccountId   Age ProfileImageUrl  \n",
+       "0       1920         -1   NaN            None  \n",
+       "1          0          2  37.0            None  \n",
+       "2          0          3  35.0            None  "
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.head(1)\n",
+    "df2.head(3)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -93,10 +481,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "df.rename(columns={'Id':'postId','OwnerUserId':'userId'}, inplace=True)\n",
+    "df2.rename(columns={'Id':'userId'}, inplace=True)"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -109,10 +500,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 23,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(91976, 5)"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "col_users=['userId','Reputation','Views','UpVotes','DownVotes']\n",
+    "col_posts=['postId','Score','userId','ViewCount','CommentCount']\n",
+    "users=df2[col_users]\n",
+    "posts=df[col_posts]\n",
+    "users.shape\n",
+    "posts.shape"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -124,10 +533,226 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "Union=pd.merge(users,posts,on='userId')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "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>userId</th>\n",
+       "      <th>Reputation</th>\n",
+       "      <th>Views</th>\n",
+       "      <th>UpVotes</th>\n",
+       "      <th>DownVotes</th>\n",
+       "      <th>postId</th>\n",
+       "      <th>Score</th>\n",
+       "      <th>ViewCount</th>\n",
+       "      <th>CommentCount</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <td>0</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>2175</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>8576</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>8578</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>3</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>8981</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>4</td>\n",
+       "      <td>-1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5007</td>\n",
+       "      <td>1920</td>\n",
+       "      <td>8982</td>\n",
+       "      <td>0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\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",
+       "      <td>90579</td>\n",
+       "      <td>55734</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>115352</td>\n",
+       "      <td>0</td>\n",
+       "      <td>16.0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>90580</td>\n",
+       "      <td>55738</td>\n",
+       "      <td>11</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>115360</td>\n",
+       "      <td>2</td>\n",
+       "      <td>40.0</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>90581</td>\n",
+       "      <td>55742</td>\n",
+       "      <td>6</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>115366</td>\n",
+       "      <td>1</td>\n",
+       "      <td>17.0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>90582</td>\n",
+       "      <td>55744</td>\n",
+       "      <td>6</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>115370</td>\n",
+       "      <td>1</td>\n",
+       "      <td>13.0</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>90583</td>\n",
+       "      <td>55746</td>\n",
+       "      <td>106</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>115376</td>\n",
+       "      <td>1</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>90584 rows × 9 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "       userId  Reputation  Views  UpVotes  DownVotes  postId  Score  \\\n",
+       "0          -1           1      0     5007       1920    2175      0   \n",
+       "1          -1           1      0     5007       1920    8576      0   \n",
+       "2          -1           1      0     5007       1920    8578      0   \n",
+       "3          -1           1      0     5007       1920    8981      0   \n",
+       "4          -1           1      0     5007       1920    8982      0   \n",
+       "...       ...         ...    ...      ...        ...     ...    ...   \n",
+       "90579   55734           1      0        0          0  115352      0   \n",
+       "90580   55738          11      0        0          0  115360      2   \n",
+       "90581   55742           6      0        0          0  115366      1   \n",
+       "90582   55744           6      1        0          0  115370      1   \n",
+       "90583   55746         106      1        0          0  115376      1   \n",
+       "\n",
+       "       ViewCount  CommentCount  \n",
+       "0            NaN             0  \n",
+       "1            NaN             0  \n",
+       "2            NaN             0  \n",
+       "3            NaN             0  \n",
+       "4            NaN             0  \n",
+       "...          ...           ...  \n",
+       "90579       16.0             0  \n",
+       "90580       40.0             4  \n",
+       "90581       17.0             0  \n",
+       "90582       13.0             2  \n",
+       "90583        5.0             2  \n",
+       "\n",
+       "[90584 rows x 9 columns]"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "Union"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -138,10 +763,33 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 27,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "userId              0\n",
+       "Reputation          0\n",
+       "Views               0\n",
+       "UpVotes             0\n",
+       "DownVotes           0\n",
+       "postId              0\n",
+       "Score               0\n",
+       "ViewCount       48396\n",
+       "CommentCount        0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "Union.isnull().sum()\n",
+    "#There are 48,396 missing values in column 'ViewCount' "
+   ]
   },
   {
    "cell_type": "markdown",
@@ -153,10 +801,37 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 32,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "userId           55746.0\n",
+       "Reputation       87393.0\n",
+       "Views            20932.0\n",
+       "UpVotes          11442.0\n",
+       "DownVotes         1920.0\n",
+       "postId          115378.0\n",
+       "Score              192.0\n",
+       "ViewCount       175495.0\n",
+       "CommentCount        45.0\n",
+       "dtype: float64"
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#I would not erase all rows with missing values in column 'ViewCount' because data of other \n",
+    "#columns are useful too. Instead I would replace it with zeros and I would notice in the analysis\n",
+    "#that involve column 'ViewCount' that important fact and the lack of realiability of its conclusions.\n",
+    "\n",
+    "Union['ViewCount']=Union['ViewCount'].fillna(0)\n",
+    "Union.max()"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -167,10 +842,40 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 42,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "userId            int64\n",
+       "Reputation        int64\n",
+       "Views             int64\n",
+       "UpVotes           int64\n",
+       "DownVotes         int64\n",
+       "postId            int64\n",
+       "Score             int64\n",
+       "ViewCount       float64\n",
+       "CommentCount      int64\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 42,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#I think would be better that columns 'userId' and 'postId' were string data type because\n",
+    "#there won't be calculations on it and I would change the numerical type of the other columns from \n",
+    "#int64 or float to int32, I cannot see a number greater than 2,147,483,647 and it would be supposed \n",
+    "#increase speed processing.\n",
+    "Union.dtypes\n",
+    "to_string=['userId','postId']\n",
+    "to_int32=['Reputation','Views','UpVotes','DownVotes','Score','ViewCount','CommentCount']\n",
+    "Union[to_string].astype(str)\n",
+    "Union[to_int32].astype('int32')\n"
+   ]
   },
   {
    "cell_type": "markdown",
@@ -196,7 +901,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.5"
+   "version": "3.7.4"
   }
  },
  "nbformat": 4,