diff --git a/Notebook_AR.ipynb b/Notebook_AR.ipynb
index 3371cf3..9de5bc6 100644
--- a/Notebook_AR.ipynb
+++ b/Notebook_AR.ipynb
@@ -10,7 +10,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 5,
    "id": "20eeb149-6618-4ef2-9cfd-ff062950f36c",
    "metadata": {},
    "outputs": [],
@@ -22,7 +22,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 6,
    "id": "30494c5e-9649-4fff-8708-617544188b20",
    "metadata": {},
    "outputs": [
@@ -46,7 +46,7 @@
        " 'bdc2324-data/9']"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -78,7 +78,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 7,
    "id": "f1cce705-46e1-42de-8e93-2ee15312d288",
    "metadata": {},
    "outputs": [],
@@ -88,7 +88,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 8,
    "id": "82d4db0e-0cd5-49af-a4d3-f17f54b1c03c",
    "metadata": {},
    "outputs": [
@@ -136,7 +136,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 9,
    "id": "65cb38ad-52ae-4266-85d8-c47d81b00283",
    "metadata": {},
    "outputs": [],
@@ -715,7 +715,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 10,
    "id": "590a132a-4f57-4ea3-a282-2ef913e4b753",
    "metadata": {},
    "outputs": [],
@@ -725,7 +725,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 11,
    "id": "0fbebfb7-a827-46b1-890b-86c9def7cdbb",
    "metadata": {},
    "outputs": [],
@@ -735,7 +735,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 12,
    "id": "b8aa5f8f-845e-4ee5-b80d-38b7061a94a2",
    "metadata": {},
    "outputs": [],
@@ -750,7 +750,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 13,
    "id": "2c478213-09ae-44ef-8c7c-125bcb571642",
    "metadata": {},
    "outputs": [],
@@ -768,7 +768,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 14,
    "id": "327e44b0-eb99-4022-b4ca-79548072f0f0",
    "metadata": {},
    "outputs": [],
@@ -781,6 +781,22 @@
     "    return percent_missing"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "10926def-267f-4e86-b2c9-72e27ff9a9df",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def process_df(df):\n",
+    "    df = remove_horodates(df)\n",
+    "    print(\"Number of columns : \", len(df.columns))\n",
+    "    df = order_columns_id(df)\n",
+    "    print(\"Columns : \", df.columns)\n",
+    "    print(\"Percent of NA for each column : \", percent_na(df))\n",
+    "    return df"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "98ac02cb-5295-47ca-99c6-99e622c5f388",
@@ -791,7 +807,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 15,
    "id": "862a7658-0602-4d94-bb58-d23774c00d32",
    "metadata": {},
    "outputs": [
@@ -961,7 +977,7 @@
        "4                 NaN  f1c4689bc47dee6f60b56d74b593dd46  "
       ]
      },
-     "execution_count": 32,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -974,7 +990,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 16,
    "id": "f0db8c51-2792-4d49-9b1a-d98ce0d9ea28",
    "metadata": {},
    "outputs": [
@@ -1127,7 +1143,7 @@
        "4     8.5          False          0.0          NaN                 NaN  "
       ]
      },
-     "execution_count": 33,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1142,7 +1158,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 17,
    "id": "a383474f-7da9-422c-bb69-3f0cc0b7053f",
    "metadata": {},
    "outputs": [
@@ -1172,7 +1188,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 18,
    "id": "460749ac-aa26-4216-8667-518546f72f72",
    "metadata": {},
    "outputs": [
@@ -1200,6 +1216,343 @@
     "percent_missing = products.isna().sum() * 100 / len(products)\n",
     "print(percent_missing)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ebcb48ab-adad-42e5-b5d7-7275771cd200",
+   "metadata": {},
+   "source": [
+    "#### Deep analysis of categories.csv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "3efce2b6-2d2f-4da9-98ed-1aae17da624c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "name_dataset = '1categories.csv'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "38aa39fd-58af-4fb8-98f2-4269dbaf35de",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "File path :  bdc2324-data/1/1categories.csv\n",
+      "Shape :  (27, 7)\n",
+      "Number of columns :  7\n"
+     ]
+    },
+    {
+     "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>name</th>\n",
+       "      <th>created_at</th>\n",
+       "      <th>updated_at</th>\n",
+       "      <th>extra_field</th>\n",
+       "      <th>quota</th>\n",
+       "      <th>identifier</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>30</td>\n",
+       "      <td>en nb entrées gr</td>\n",
+       "      <td>2020-09-03 13:21:20.019202+02:00</td>\n",
+       "      <td>2020-09-03 13:21:20.019202+02:00</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>849ab2791a14f5fc2bb4d87ab2b78bf6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>16</td>\n",
+       "      <td>indiv activité enfant</td>\n",
+       "      <td>2020-09-03 13:11:23.306968+02:00</td>\n",
+       "      <td>2020-09-03 13:11:23.306968+02:00</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>425fd2f01984cc4ba030c1be98f42c33</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>39</td>\n",
+       "      <td>indiv activité gr</td>\n",
+       "      <td>2020-09-03 13:21:20.029901+02:00</td>\n",
+       "      <td>2020-09-03 13:21:20.029901+02:00</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>9244dd3738788db0d22a5d0afe687b69</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1108</td>\n",
+       "      <td>groupe forfait adulte</td>\n",
+       "      <td>2020-09-19 02:06:43.145697+02:00</td>\n",
+       "      <td>2020-09-19 02:06:43.145697+02:00</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>3edda20c877a93b5ff883827238eb711</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>6</td>\n",
+       "      <td>groupe forfait entrées tr</td>\n",
+       "      <td>2020-09-03 13:11:23.264997+02:00</td>\n",
+       "      <td>2020-09-03 13:11:23.264997+02:00</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>ff48df4b2dd5a14116bf4d280b31621e</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     id                       name                        created_at  \\\n",
+       "0    30           en nb entrées gr  2020-09-03 13:21:20.019202+02:00   \n",
+       "1    16      indiv activité enfant  2020-09-03 13:11:23.306968+02:00   \n",
+       "2    39          indiv activité gr  2020-09-03 13:21:20.029901+02:00   \n",
+       "3  1108      groupe forfait adulte  2020-09-19 02:06:43.145697+02:00   \n",
+       "4     6  groupe forfait entrées tr  2020-09-03 13:11:23.264997+02:00   \n",
+       "\n",
+       "                         updated_at  extra_field  quota  \\\n",
+       "0  2020-09-03 13:21:20.019202+02:00          NaN    NaN   \n",
+       "1  2020-09-03 13:11:23.306968+02:00          NaN    NaN   \n",
+       "2  2020-09-03 13:21:20.029901+02:00          NaN    NaN   \n",
+       "3  2020-09-19 02:06:43.145697+02:00          NaN    NaN   \n",
+       "4  2020-09-03 13:11:23.264997+02:00          NaN    NaN   \n",
+       "\n",
+       "                         identifier  \n",
+       "0  849ab2791a14f5fc2bb4d87ab2b78bf6  \n",
+       "1  425fd2f01984cc4ba030c1be98f42c33  \n",
+       "2  9244dd3738788db0d22a5d0afe687b69  \n",
+       "3  3edda20c877a93b5ff883827238eb711  \n",
+       "4  ff48df4b2dd5a14116bf4d280b31621e  "
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = display_databases(name_dataset)\n",
+    "print(\"Number of columns : \", len(df.columns))\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "99eb6d14-8b4b-4d55-8fc7-ddf2726096f4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Number of columns :  5\n",
+      "Columns :  Index(['id', 'identifier', 'name', 'extra_field', 'quota'], dtype='object')\n",
+      "Percent of NA for each column :  id               0.000000\n",
+      "identifier       0.000000\n",
+      "name             3.703704\n",
+      "extra_field    100.000000\n",
+      "quota          100.000000\n",
+      "dtype: float64\n"
+     ]
+    },
+    {
+     "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>identifier</th>\n",
+       "      <th>name</th>\n",
+       "      <th>extra_field</th>\n",
+       "      <th>quota</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>30</td>\n",
+       "      <td>849ab2791a14f5fc2bb4d87ab2b78bf6</td>\n",
+       "      <td>en nb entrées gr</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>16</td>\n",
+       "      <td>425fd2f01984cc4ba030c1be98f42c33</td>\n",
+       "      <td>indiv activité enfant</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>39</td>\n",
+       "      <td>9244dd3738788db0d22a5d0afe687b69</td>\n",
+       "      <td>indiv activité gr</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>1108</td>\n",
+       "      <td>3edda20c877a93b5ff883827238eb711</td>\n",
+       "      <td>groupe forfait adulte</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>6</td>\n",
+       "      <td>ff48df4b2dd5a14116bf4d280b31621e</td>\n",
+       "      <td>groupe forfait entrées tr</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "     id                        identifier                       name  \\\n",
+       "0    30  849ab2791a14f5fc2bb4d87ab2b78bf6           en nb entrées gr   \n",
+       "1    16  425fd2f01984cc4ba030c1be98f42c33      indiv activité enfant   \n",
+       "2    39  9244dd3738788db0d22a5d0afe687b69          indiv activité gr   \n",
+       "3  1108  3edda20c877a93b5ff883827238eb711      groupe forfait adulte   \n",
+       "4     6  ff48df4b2dd5a14116bf4d280b31621e  groupe forfait entrées tr   \n",
+       "\n",
+       "   extra_field  quota  \n",
+       "0          NaN    NaN  \n",
+       "1          NaN    NaN  \n",
+       "2          NaN    NaN  \n",
+       "3          NaN    NaN  \n",
+       "4          NaN    NaN  "
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = process_df(df)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "c5f39cc9-dff8-452c-9a3e-9f7df81a8a19",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "id               int64\n",
+       "identifier      object\n",
+       "name            object\n",
+       "extra_field    float64\n",
+       "quota          float64\n",
+       "dtype: object"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.dtypes"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c4cb0b37-2262-45c0-97be-b12c503016e3",
+   "metadata": {},
+   "source": [
+    "#### Deep analysis of type_of_categories.csv"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3b4a3af9-ed12-43ec-b17e-fd425b238265",
+   "metadata": {},
+   "source": [
+    "#### Deep analysis of representation_category_capacities.csv"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "135966fb-aab1-48d7-bb4c-39a53ee643ca",
+   "metadata": {},
+   "source": [
+    "#### Deep analysis of representations.csv"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b480f39f-d5c7-4ded-8f64-ea8ac31f5db5",
+   "metadata": {},
+   "source": [
+    "#### Deep analysis of events.csv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2d52d6da-cca5-4abd-be05-2f00fd3eca8e",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {