From 1f20e6ff2cfdcdf1900567577b3022fa83b710bc Mon Sep 17 00:00:00 2001
From: ajoubrel-ensae <antoine.joubrel@ensae.fr>
Date: Mon, 1 Jan 2024 12:31:02 +0000
Subject: [PATCH] Update

---
 Notebook_AJ.ipynb | 95 ++++++++++++++++-------------------------------
 1 file changed, 31 insertions(+), 64 deletions(-)

diff --git a/Notebook_AJ.ipynb b/Notebook_AJ.ipynb
index 0b73ffc..f61e733 100644
--- a/Notebook_AJ.ipynb
+++ b/Notebook_AJ.ipynb
@@ -124,7 +124,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 4,
    "id": "ba9d04ad-6cc1-4bac-b1a0-44bedfb09763",
    "metadata": {},
    "outputs": [],
@@ -148,7 +148,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 5,
    "id": "cacaecc1-4d8a-4e20-8cd3-b452cf17db56",
    "metadata": {},
    "outputs": [],
@@ -161,7 +161,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 6,
    "id": "2ec4b583-dc64-43e9-b3ae-6bbaee0bc135",
    "metadata": {},
    "outputs": [
@@ -192,28 +192,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 7,
    "id": "77894273-b3e5-4f29-bd63-9f4df8082b9b",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "0          2021-03-28 18:01:09+02:00\n",
-       "1          2021-03-28 18:01:09+02:00\n",
-       "2          2021-03-28 18:00:59+02:00\n",
-       "3          2021-03-28 18:00:59+02:00\n",
-       "4          2021-03-28 18:01:06+02:00\n",
-       "                     ...            \n",
-       "6214803    2023-10-23 11:32:33+02:00\n",
-       "6214804    2023-10-23 11:32:49+02:00\n",
-       "6214805    2023-10-23 11:33:28+02:00\n",
-       "6214806    2023-10-23 11:31:53+02:00\n",
-       "6214807    2023-10-23 11:33:54+02:00\n",
-       "Name: sent_at, Length: 6214808, dtype: object"
+       "0         2021-03-28 16:01:09+00:00\n",
+       "1         2021-03-28 16:01:09+00:00\n",
+       "2         2021-03-28 16:00:59+00:00\n",
+       "3         2021-03-28 16:00:59+00:00\n",
+       "4         2021-03-28 16:01:06+00:00\n",
+       "                     ...           \n",
+       "6214803   2023-10-23 09:32:33+00:00\n",
+       "6214804   2023-10-23 09:32:49+00:00\n",
+       "6214805   2023-10-23 09:33:28+00:00\n",
+       "6214806   2023-10-23 09:31:53+00:00\n",
+       "6214807   2023-10-23 09:33:54+00:00\n",
+       "Name: sent_at, Length: 6214808, dtype: datetime64[ns, UTC]"
       ]
      },
-     "execution_count": 26,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -232,7 +232,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": 8,
    "id": "4223c873-cbd3-46d1-ac96-c9a3b9e97092",
    "metadata": {},
    "outputs": [
@@ -240,7 +240,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_426/4118060109.py:9: DtypeWarning: Columns (20) have mixed types. Specify dtype option on import or set low_memory=False.\n",
+      "/tmp/ipykernel_1362/4118060109.py:9: DtypeWarning: Columns (20) have mixed types. Specify dtype option on import or set low_memory=False.\n",
       "  customers_plus_2 = pd.read_csv(file_in, sep=\",\")\n"
      ]
     }
@@ -259,7 +259,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 10,
    "id": "460f853a-68c0-42a7-9877-b83d3aaec813",
    "metadata": {},
    "outputs": [
@@ -280,81 +280,48 @@
        "      dtype='object')"
       ]
      },
-     "execution_count": 39,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "customers_plus.columns"
+    "customers_plus_1.columns"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": null,
    "id": "d5a9398f-72fc-4548-9f53-b20b372144b2",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "(151866, 43)"
-      ]
-     },
-     "execution_count": 43,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "customers_plus.shape"
+    "customers_plus_1.shape"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": null,
    "id": "7467ddbe-0bd4-44cc-8a16-84aa41853638",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "151866"
-      ]
-     },
-     "execution_count": 52,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "customers_plus_1['id'].nunique()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": null,
    "id": "e15f05f8-3a89-4fc3-84a9-dae70e168440",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "275622"
-      ]
-     },
-     "execution_count": 53,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "customers_plus_2['id'].nunique()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": null,
    "id": "b40a653e-013f-48d0-8b57-0284587b36c5",
    "metadata": {},
    "outputs": [],
@@ -445,7 +412,7 @@
     }
    ],
    "source": [
-    "print(customers_plus.isna().mean()*100)"
+    "pd.DataFrame(customers_plus_1.isna().mean()*100)"
    ]
   }
  ],