diff --git a/2_DataCleaningAndWrangling/Data_Wrangling_WHO.ipynb b/2_DataCleaningAndWrangling/Data_Wrangling_WHO.ipynb
index 2bc5f6a..355e034 100644
--- a/2_DataCleaningAndWrangling/Data_Wrangling_WHO.ipynb
+++ b/2_DataCleaningAndWrangling/Data_Wrangling_WHO.ipynb
@@ -131,7 +131,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -171,14 +171,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 106,
    "metadata": {},
    "outputs": [],
    "source": [
     "# Read the file from my computer\"\n",
     "#NOTE: Change the path to much yours\n",
-    "my_path = \"/Users/mary-tziraki/git/TeamCoders_Event_Based_Model/2_DataCleaningAndWrangling/who_suicide_statistics_modified3.csv\"\n",
-    "data_raw = pd.read_csv(my_path, header=None)"
+    "my_path = \"./who_suicide_statistics_modified3.csv\"\n",
+    "data_raw = pd.read_csv(my_path)"
    ]
   },
   {
@@ -190,7 +190,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 107,
    "metadata": {
     "scrolled": true
    },
@@ -216,30 +216,19 @@
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
-       "      <th>0</th>\n",
-       "      <th>1</th>\n",
-       "      <th>2</th>\n",
-       "      <th>3</th>\n",
-       "      <th>4</th>\n",
-       "      <th>5</th>\n",
-       "      <th>6</th>\n",
-       "      <th>7</th>\n",
+       "      <th>country</th>\n",
+       "      <th>year</th>\n",
+       "      <th>sex</th>\n",
+       "      <th>age</th>\n",
+       "      <th>suicides_no</th>\n",
+       "      <th>population</th>\n",
+       "      <th>HDI for year</th>\n",
+       "      <th>gdp_for_year ($)</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
-       "      <td>country</td>\n",
-       "      <td>year</td>\n",
-       "      <td>sex</td>\n",
-       "      <td>age</td>\n",
-       "      <td>suicides_no</td>\n",
-       "      <td>population</td>\n",
-       "      <td>HDI for year</td>\n",
-       "      <td>gdp_for_year ($)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
        "      <td>Albania</td>\n",
        "      <td>1987</td>\n",
        "      <td>male</td>\n",
@@ -250,7 +239,7 @@
        "      <td>2,156,624,900</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>2</th>\n",
+       "      <th>1</th>\n",
        "      <td>Albania</td>\n",
        "      <td>1987</td>\n",
        "      <td>male</td>\n",
@@ -261,7 +250,7 @@
        "      <td>2,156,624,900</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>3</th>\n",
+       "      <th>2</th>\n",
        "      <td>Albania</td>\n",
        "      <td>1987</td>\n",
        "      <td>female</td>\n",
@@ -272,7 +261,7 @@
        "      <td>2,156,624,900</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>4</th>\n",
+       "      <th>3</th>\n",
        "      <td>Albania</td>\n",
        "      <td>1987</td>\n",
        "      <td>male</td>\n",
@@ -282,33 +271,125 @@
        "      <td>NaN</td>\n",
        "      <td>2,156,624,900</td>\n",
        "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Albania</td>\n",
+       "      <td>1987</td>\n",
+       "      <td>male</td>\n",
+       "      <td>25-34 years</td>\n",
+       "      <td>9</td>\n",
+       "      <td>274300</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2,156,624,900</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27835</th>\n",
+       "      <td>Belgium</td>\n",
+       "      <td>2011</td>\n",
+       "      <td>female</td>\n",
+       "      <td>25-34 years</td>\n",
+       "      <td>6</td>\n",
+       "      <td>707535</td>\n",
+       "      <td>0.886</td>\n",
+       "      <td>527,008,453,887</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27836</th>\n",
+       "      <td>Thailand</td>\n",
+       "      <td>2016</td>\n",
+       "      <td>male</td>\n",
+       "      <td>75+ years</td>\n",
+       "      <td>152</td>\n",
+       "      <td>1124052</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>411,755,164,833</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27837</th>\n",
+       "      <td>Netherlands</td>\n",
+       "      <td>1998</td>\n",
+       "      <td>female</td>\n",
+       "      <td>15-24 years</td>\n",
+       "      <td>21</td>\n",
+       "      <td>934500</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>432,476,116,419</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27838</th>\n",
+       "      <td>Grenada</td>\n",
+       "      <td>2002</td>\n",
+       "      <td>female</td>\n",
+       "      <td>5-14 years</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>11760</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>540,336,926</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27839</th>\n",
+       "      <td>Mexico</td>\n",
+       "      <td>1988</td>\n",
+       "      <td>female</td>\n",
+       "      <td>75+ years</td>\n",
+       "      <td>7</td>\n",
+       "      <td>614000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>183,144,164,357</td>\n",
+       "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
+       "<p>27840 rows × 8 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "         0     1       2            3            4           5             6  \\\n",
-       "0  country  year     sex          age  suicides_no  population  HDI for year   \n",
-       "1  Albania  1987    male  15-24 years           21      312900           NaN   \n",
-       "2  Albania  1987    male  35-54 years           16      308000           NaN   \n",
-       "3  Albania  1987  female  15-24 years           14      289700           NaN   \n",
-       "4  Albania  1987    male    75+ years            1       21800           NaN   \n",
+       "           country  year     sex          age suicides_no  population  \\\n",
+       "0          Albania  1987    male  15-24 years          21      312900   \n",
+       "1          Albania  1987    male  35-54 years          16      308000   \n",
+       "2          Albania  1987  female  15-24 years          14      289700   \n",
+       "3          Albania  1987    male    75+ years           1       21800   \n",
+       "4          Albania  1987    male  25-34 years           9      274300   \n",
+       "...            ...   ...     ...          ...         ...         ...   \n",
+       "27835      Belgium  2011  female  25-34 years           6      707535   \n",
+       "27836     Thailand  2016    male    75+ years         152     1124052   \n",
+       "27837  Netherlands  1998  female  15-24 years          21      934500   \n",
+       "27838      Grenada  2002  female   5-14 years         NaN       11760   \n",
+       "27839       Mexico  1988  female    75+ years           7      614000   \n",
        "\n",
-       "                    7  \n",
-       "0   gdp_for_year ($)   \n",
-       "1       2,156,624,900  \n",
-       "2       2,156,624,900  \n",
-       "3       2,156,624,900  \n",
-       "4       2,156,624,900  "
+       "       HDI for year  gdp_for_year ($)   \n",
+       "0               NaN      2,156,624,900  \n",
+       "1               NaN      2,156,624,900  \n",
+       "2               NaN      2,156,624,900  \n",
+       "3               NaN      2,156,624,900  \n",
+       "4               NaN      2,156,624,900  \n",
+       "...             ...                ...  \n",
+       "27835         0.886    527,008,453,887  \n",
+       "27836           NaN    411,755,164,833  \n",
+       "27837           NaN    432,476,116,419  \n",
+       "27838           NaN        540,336,926  \n",
+       "27839           NaN    183,144,164,357  \n",
+       "\n",
+       "[27840 rows x 8 columns]"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 107,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "data_raw.head()"
+    "data_raw"
    ]
   },
   {
@@ -1317,7 +1398,32 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "country  year  sex   age   suicides_no  population  HDI for year   gdp_for_year ($) \n",
+       "True     True  True  True  True         True        False         True                  16357\n",
+       "                                                    True          True                   7218\n",
+       "                           False        True        False         True                   3115\n",
+       "                                                    True          True                   1150\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "(~data_raw.isnull()).value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
    "metadata": {
     "scrolled": true
    },
@@ -1364,18 +1470,17 @@
     }
    ],
    "source": [
-    "for column in missing_data.columns.values.tolist():\n",
+    "missing_data = data_raw.isnull()\n",
+    "for column in data_raw.columns:\n",
     "    print(column)\n",
-    "    print (missing_data[column].value_counts())\n",
-    "    print(\"\") "
+    "    print(missing_data[column].value_counts())\n",
+    "    print() "
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 10,
-   "metadata": {
-    "scrolled": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -1440,6 +1545,409 @@
     "A regular expression is a special sequence of characters that helps you match or find other strings or sets of strings, using a specialized syntax held in a pattern."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "suicides = data_raw['suicides_no']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 90,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['Null', 'Unknown'], dtype=object)"
+      ]
+     },
+     "execution_count": 90,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data_raw['suicides_no'][data_raw['suicides_no'].str.isdigit() == False].unique()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "metadata": {
+    "collapsed": true,
+    "jupyter": {
+     "outputs_hidden": true
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "ename": "ValueError",
+     "evalue": "Unable to parse string \"Null\" at position 0",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
+      "\u001b[0;32m~/Documents/.config/packman/miniconda3/envs/teaching/lib/python3.8/site-packages/pandas/_libs/lib.pyx\u001b[0m in \u001b[0;36mpandas._libs.lib.maybe_convert_numeric\u001b[0;34m()\u001b[0m\n",
+      "\u001b[0;31mValueError\u001b[0m: Unable to parse string \"Null\"",
+      "\nDuring handling of the above exception, another exception occurred:\n",
+      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
+      "\u001b[0;32m/tmp/ipykernel_91720/1399709450.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0msuicides2\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msuicides\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_numeric\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[0;32m~/Documents/.config/packman/miniconda3/envs/teaching/lib/python3.8/site-packages/pandas/core/series.py\u001b[0m in \u001b[0;36mapply\u001b[0;34m(self, func, convert_dtype, args, **kwargs)\u001b[0m\n\u001b[1;32m   4355\u001b[0m         \u001b[0mdtype\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mfloat64\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   4356\u001b[0m         \"\"\"\n\u001b[0;32m-> 4357\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mSeriesApply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mconvert_dtype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   4358\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   4359\u001b[0m     def _reduce(\n",
+      "\u001b[0;32m~/Documents/.config/packman/miniconda3/envs/teaching/lib/python3.8/site-packages/pandas/core/apply.py\u001b[0m in \u001b[0;36mapply\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   1041\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply_str\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1042\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1043\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply_standard\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1044\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1045\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0magg\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/Documents/.config/packman/miniconda3/envs/teaching/lib/python3.8/site-packages/pandas/core/apply.py\u001b[0m in \u001b[0;36mapply_standard\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   1096\u001b[0m                 \u001b[0;31m# List[Union[Callable[..., Any], str]]]]]\"; expected\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1097\u001b[0m                 \u001b[0;31m# \"Callable[[Any], Any]\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1098\u001b[0;31m                 mapped = lib.map_infer(\n\u001b[0m\u001b[1;32m   1099\u001b[0m                     \u001b[0mvalues\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1100\u001b[0m                     \u001b[0mf\u001b[0m\u001b[0;34m,\u001b[0m  \u001b[0;31m# type: ignore[arg-type]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m~/Documents/.config/packman/miniconda3/envs/teaching/lib/python3.8/site-packages/pandas/_libs/lib.pyx\u001b[0m in \u001b[0;36mpandas._libs.lib.map_infer\u001b[0;34m()\u001b[0m\n",
+      "\u001b[0;32m~/Documents/.config/packman/miniconda3/envs/teaching/lib/python3.8/site-packages/pandas/core/tools/numeric.py\u001b[0m in \u001b[0;36mto_numeric\u001b[0;34m(arg, errors, downcast)\u001b[0m\n\u001b[1;32m    181\u001b[0m         \u001b[0mcoerce_numeric\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0merrors\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32min\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;34m\"ignore\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"raise\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    182\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 183\u001b[0;31m             values, _ = lib.maybe_convert_numeric(\n\u001b[0m\u001b[1;32m    184\u001b[0m                 \u001b[0mvalues\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcoerce_numeric\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcoerce_numeric\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    185\u001b[0m             )\n",
+      "\u001b[0;32m~/Documents/.config/packman/miniconda3/envs/teaching/lib/python3.8/site-packages/pandas/_libs/lib.pyx\u001b[0m in \u001b[0;36mpandas._libs.lib.maybe_convert_numeric\u001b[0;34m()\u001b[0m\n",
+      "\u001b[0;31mValueError\u001b[0m: Unable to parse string \"Null\" at position 0"
+     ]
+    }
+   ],
+   "source": [
+    "suicides2 = suicides.apply(pd.to_numeric)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 60,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "suicides2 = suicides.apply(pd.to_numeric, errors='coerce')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 66,
+   "metadata": {
+    "collapsed": true,
+    "jupyter": {
+     "outputs_hidden": true
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[nan 'Null' 'Unknown']\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(data_raw['suicides_no'][suicides2.isna()].unique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 112,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ages = data_raw['age'].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 113,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "map_ages = {'5-14 years': 0, \n",
+    "            '15-24 years': 1,\n",
+    "            '25-34 years': 2, \n",
+    "            '35-54 years': 3,\n",
+    "            '55-74 years': 4,\n",
+    "            '75+ years': 5}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 116,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data_raw['age_index'] = data_raw['age'].map(map_ages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 104,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data_raw['age'] = pd.to_numeric((data_raw['age'].str[:2]).str.replace('-', ''))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 117,
+   "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>country</th>\n",
+       "      <th>year</th>\n",
+       "      <th>sex</th>\n",
+       "      <th>age</th>\n",
+       "      <th>suicides_no</th>\n",
+       "      <th>population</th>\n",
+       "      <th>HDI for year</th>\n",
+       "      <th>gdp_for_year ($)</th>\n",
+       "      <th>age_index</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>Albania</td>\n",
+       "      <td>1987</td>\n",
+       "      <td>female</td>\n",
+       "      <td>5-14 years</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>311000</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2,156,624,900</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Albania</td>\n",
+       "      <td>1987</td>\n",
+       "      <td>female</td>\n",
+       "      <td>15-24 years</td>\n",
+       "      <td>14</td>\n",
+       "      <td>289700</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2,156,624,900</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>Albania</td>\n",
+       "      <td>1987</td>\n",
+       "      <td>female</td>\n",
+       "      <td>25-34 years</td>\n",
+       "      <td>4</td>\n",
+       "      <td>257200</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2,156,624,900</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>Albania</td>\n",
+       "      <td>1987</td>\n",
+       "      <td>female</td>\n",
+       "      <td>35-54 years</td>\n",
+       "      <td>6</td>\n",
+       "      <td>278800</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2,156,624,900</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>Albania</td>\n",
+       "      <td>1987</td>\n",
+       "      <td>female</td>\n",
+       "      <td>55-74 years</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>144600</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2,156,624,900</td>\n",
+       "      <td>4</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",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27812</th>\n",
+       "      <td>Uzbekistan</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>male</td>\n",
+       "      <td>15-24 years</td>\n",
+       "      <td>347</td>\n",
+       "      <td>3126905</td>\n",
+       "      <td>0.675</td>\n",
+       "      <td>63,067,077,179</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27809</th>\n",
+       "      <td>Uzbekistan</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>male</td>\n",
+       "      <td>25-34 years</td>\n",
+       "      <td>318</td>\n",
+       "      <td>2739150</td>\n",
+       "      <td>0.675</td>\n",
+       "      <td>63,067,077,179</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27808</th>\n",
+       "      <td>Uzbekistan</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>male</td>\n",
+       "      <td>35-54 years</td>\n",
+       "      <td>519</td>\n",
+       "      <td>3421300</td>\n",
+       "      <td>0.675</td>\n",
+       "      <td>63,067,077,179</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27811</th>\n",
+       "      <td>Uzbekistan</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>male</td>\n",
+       "      <td>55-74 years</td>\n",
+       "      <td>144</td>\n",
+       "      <td>1271111</td>\n",
+       "      <td>0.675</td>\n",
+       "      <td>63,067,077,179</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27813</th>\n",
+       "      <td>Uzbekistan</td>\n",
+       "      <td>2014</td>\n",
+       "      <td>male</td>\n",
+       "      <td>75+ years</td>\n",
+       "      <td>17</td>\n",
+       "      <td>224995</td>\n",
+       "      <td>0.675</td>\n",
+       "      <td>63,067,077,179</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>27840 rows × 9 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          country  year     sex          age suicides_no  population  \\\n",
+       "9         Albania  1987  female   5-14 years         NaN      311000   \n",
+       "2         Albania  1987  female  15-24 years          14      289700   \n",
+       "7         Albania  1987  female  25-34 years           4      257200   \n",
+       "6         Albania  1987  female  35-54 years           6      278800   \n",
+       "10        Albania  1987  female  55-74 years         NaN      144600   \n",
+       "...           ...   ...     ...          ...         ...         ...   \n",
+       "27812  Uzbekistan  2014    male  15-24 years         347     3126905   \n",
+       "27809  Uzbekistan  2014    male  25-34 years         318     2739150   \n",
+       "27808  Uzbekistan  2014    male  35-54 years         519     3421300   \n",
+       "27811  Uzbekistan  2014    male  55-74 years         144     1271111   \n",
+       "27813  Uzbekistan  2014    male    75+ years          17      224995   \n",
+       "\n",
+       "       HDI for year  gdp_for_year ($)   age_index  \n",
+       "9               NaN      2,156,624,900          0  \n",
+       "2               NaN      2,156,624,900          1  \n",
+       "7               NaN      2,156,624,900          2  \n",
+       "6               NaN      2,156,624,900          3  \n",
+       "10              NaN      2,156,624,900          4  \n",
+       "...             ...                ...        ...  \n",
+       "27812         0.675     63,067,077,179          1  \n",
+       "27809         0.675     63,067,077,179          2  \n",
+       "27808         0.675     63,067,077,179          3  \n",
+       "27811         0.675     63,067,077,179          4  \n",
+       "27813         0.675     63,067,077,179          5  \n",
+       "\n",
+       "[27840 rows x 9 columns]"
+      ]
+     },
+     "execution_count": 117,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data_raw.sort_values(['country', 'year', 'sex', 'age_index'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 97,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'18'"
+      ]
+     },
+     "execution_count": 97,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "this_var = \"18-33 age\"\n",
+    "this_var[:2]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data_raw['age'].str.extract"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data_raw['age'].str.extract"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data_raw['age'].str.find"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 12,
@@ -2743,9 +3251,7 @@
   {
    "cell_type": "code",
    "execution_count": 21,
-   "metadata": {
-    "scrolled": false
-   },
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -5007,7 +5513,7 @@
  "metadata": {
   "anaconda-cloud": {},
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -5021,7 +5527,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.8"
+   "version": "3.8.12"
   }
  },
  "nbformat": 4,