This commit is contained in:
Fanta RODRIGUE 2024-03-10 18:08:50 +00:00
parent 75664a33d7
commit a4d4803a1c

View File

@ -1509,7 +1509,7 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 66,
"id": "5fd56696-b479-46c7-8a59-fb8137db5fb5",
"metadata": {},
"outputs": [
@ -1519,7 +1519,7 @@
"array([10, 11, 12, 13, 14])"
]
},
"execution_count": 13,
"execution_count": 66,
"metadata": {},
"output_type": "execute_result"
}
@ -1533,7 +1533,7 @@
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": 71,
"id": "91c6e047-43d2-456c-81f1-087026eef4f0",
"metadata": {},
"outputs": [
@ -1753,7 +1753,7 @@
"[5 rows x 41 columns]"
]
},
"execution_count": 14,
"execution_count": 71,
"metadata": {},
"output_type": "execute_result"
}
@ -3902,7 +3902,7 @@
},
{
"cell_type": "code",
"execution_count": 94,
"execution_count": 70,
"id": "91b743c4-5473-41e1-b97e-cf06904f0fa8",
"metadata": {
"scrolled": true
@ -4013,7 +4013,7 @@
"9 14 1.0 17.561409"
]
},
"execution_count": 94,
"execution_count": 70,
"metadata": {},
"output_type": "execute_result"
}
@ -6546,6 +6546,38 @@
"print(\"Moustache superieure\",M_sup)#moustache sup\n"
]
},
{
"cell_type": "code",
"execution_count": 62,
"id": "c3adb0cd-8292-4c6f-9d4e-8352a6967022",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"customer_id int64\n",
"nb_tickets int64\n",
"nb_purchases int64\n",
"total_amount float64\n",
"nb_suppliers int64\n",
"vente_internet_max int64\n",
"purchase_date_min float64\n",
"purchase_date_max float64\n",
"time_between_purchase float64\n",
"nb_tickets_internet float64\n",
"number_compagny int64\n",
"dtype: object"
]
},
"execution_count": 62,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"products_purchased_reduced_spectacle.dtypes"
]
},
{
"cell_type": "markdown",
"id": "a63e6d13-429b-4b01-ad11-27e5eea68cbd",
@ -6560,7 +6592,7 @@
},
{
"cell_type": "code",
"execution_count": 46,
"execution_count": 86,
"id": "5a08b5a5-7d56-4543-945a-38f6219d831d",
"metadata": {},
"outputs": [
@ -6593,17 +6625,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"id": "20ce4a40-8f0d-40e8-91d3-b923670326cb",
"metadata": {},
"outputs": [],
"source": [
"#reprise du graphe de la repartition Chiffre d'affaire selon les compagnie de spectacle sur la base de train\n"
]
},
{
"cell_type": "code",
"execution_count": 44,
"execution_count": 87,
"id": "76e08ece-0b58-4b3a-abca-53e30ccc907b",
"metadata": {},
"outputs": [
@ -6662,7 +6684,17 @@
},
{
"cell_type": "code",
"execution_count": 45,
"execution_count": 88,
"id": "6b55de4b-913e-4bc1-b4f2-cc0b1824d0e2",
"metadata": {},
"outputs": [],
"source": [
"#graphe sur le taux de ticket acheté"
]
},
{
"cell_type": "code",
"execution_count": 89,
"id": "aacf2c34-f7ea-4d6e-935b-c5db01f03bbe",
"metadata": {},
"outputs": [
@ -6742,7 +6774,7 @@
"4 14 335741 125638.0 37.421107"
]
},
"execution_count": 45,
"execution_count": 89,
"metadata": {},
"output_type": "execute_result"
}
@ -6757,7 +6789,7 @@
},
{
"cell_type": "code",
"execution_count": 57,
"execution_count": 90,
"id": "f71bb53d-724b-454d-8743-305d20eec2b0",
"metadata": {},
"outputs": [
@ -6785,6 +6817,520 @@
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 94,
"id": "69aad59a-e93d-4edc-a559-8f2452d7f19d",
"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>customer_id</th>\n",
" <th>nb_tickets</th>\n",
" <th>nb_purchases</th>\n",
" <th>total_amount</th>\n",
" <th>nb_suppliers</th>\n",
" <th>vente_internet_max</th>\n",
" <th>purchase_date_min</th>\n",
" <th>purchase_date_max</th>\n",
" <th>time_between_purchase</th>\n",
" <th>nb_tickets_internet</th>\n",
" <th>...</th>\n",
" <th>gender_label</th>\n",
" <th>gender_female</th>\n",
" <th>gender_male</th>\n",
" <th>gender_other</th>\n",
" <th>country_fr</th>\n",
" <th>nb_campaigns</th>\n",
" <th>nb_campaigns_opened</th>\n",
" <th>time_to_open</th>\n",
" <th>y_has_purchased</th>\n",
" <th>number_company</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>10_299341</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>12.0</td>\n",
" <td>3.0</td>\n",
" <td>0 days 05:47:26.333333333</td>\n",
" <td>0.0</td>\n",
" <td>10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>10_63788</td>\n",
" <td>3.0</td>\n",
" <td>2.0</td>\n",
" <td>62.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>393.205891</td>\n",
" <td>281.017639</td>\n",
" <td>112.188252</td>\n",
" <td>3.0</td>\n",
" <td>...</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" <td>0 days 05:13:51</td>\n",
" <td>1.0</td>\n",
" <td>10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>10_759946</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>other</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>10_20653</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>11.0</td>\n",
" <td>10.0</td>\n",
" <td>1 days 00:45:54</td>\n",
" <td>0.0</td>\n",
" <td>10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>10_824705</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>other</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>10</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",
" <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",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>697292</th>\n",
" <td>14_119950</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>14</td>\n",
" </tr>\n",
" <tr>\n",
" <th>697293</th>\n",
" <td>14_938</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>14</td>\n",
" </tr>\n",
" <tr>\n",
" <th>697294</th>\n",
" <td>14_5004707</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" <td>2 days 16:42:51</td>\n",
" <td>0.0</td>\n",
" <td>14</td>\n",
" </tr>\n",
" <tr>\n",
" <th>697295</th>\n",
" <td>14_108184</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>other</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>14</td>\n",
" </tr>\n",
" <tr>\n",
" <th>697296</th>\n",
" <td>14_4663981</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>other</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>14</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>697297 rows × 41 columns</p>\n",
"</div>"
],
"text/plain": [
" customer_id nb_tickets nb_purchases total_amount nb_suppliers \\\n",
"0 10_299341 0.0 0.0 0.0 0.0 \n",
"1 10_63788 3.0 2.0 62.0 1.0 \n",
"2 10_759946 0.0 0.0 0.0 0.0 \n",
"3 10_20653 0.0 0.0 0.0 0.0 \n",
"4 10_824705 0.0 0.0 0.0 0.0 \n",
"... ... ... ... ... ... \n",
"697292 14_119950 0.0 0.0 0.0 0.0 \n",
"697293 14_938 0.0 0.0 0.0 0.0 \n",
"697294 14_5004707 0.0 0.0 0.0 0.0 \n",
"697295 14_108184 0.0 0.0 0.0 0.0 \n",
"697296 14_4663981 0.0 0.0 0.0 0.0 \n",
"\n",
" vente_internet_max purchase_date_min purchase_date_max \\\n",
"0 0.0 NaN NaN \n",
"1 1.0 393.205891 281.017639 \n",
"2 0.0 NaN NaN \n",
"3 0.0 NaN NaN \n",
"4 0.0 NaN NaN \n",
"... ... ... ... \n",
"697292 0.0 NaN NaN \n",
"697293 0.0 NaN NaN \n",
"697294 0.0 NaN NaN \n",
"697295 0.0 NaN NaN \n",
"697296 0.0 NaN NaN \n",
"\n",
" time_between_purchase nb_tickets_internet ... gender_label \\\n",
"0 NaN 0.0 ... male \n",
"1 112.188252 3.0 ... female \n",
"2 NaN 0.0 ... other \n",
"3 NaN 0.0 ... male \n",
"4 NaN 0.0 ... other \n",
"... ... ... ... ... \n",
"697292 NaN 0.0 ... male \n",
"697293 NaN 0.0 ... male \n",
"697294 NaN 0.0 ... male \n",
"697295 NaN 0.0 ... other \n",
"697296 NaN 0.0 ... other \n",
"\n",
" gender_female gender_male gender_other country_fr nb_campaigns \\\n",
"0 0 1 0 1.0 12.0 \n",
"1 1 0 0 1.0 3.0 \n",
"2 0 0 1 NaN 0.0 \n",
"3 0 1 0 1.0 11.0 \n",
"4 0 0 1 NaN 0.0 \n",
"... ... ... ... ... ... \n",
"697292 0 1 0 1.0 0.0 \n",
"697293 0 1 0 1.0 0.0 \n",
"697294 0 1 0 1.0 2.0 \n",
"697295 0 0 1 1.0 0.0 \n",
"697296 0 0 1 NaN 0.0 \n",
"\n",
" nb_campaigns_opened time_to_open y_has_purchased \\\n",
"0 3.0 0 days 05:47:26.333333333 0.0 \n",
"1 1.0 0 days 05:13:51 1.0 \n",
"2 0.0 NaN 0.0 \n",
"3 10.0 1 days 00:45:54 0.0 \n",
"4 0.0 NaN 0.0 \n",
"... ... ... ... \n",
"697292 0.0 NaN 0.0 \n",
"697293 0.0 NaN 0.0 \n",
"697294 1.0 2 days 16:42:51 0.0 \n",
"697295 0.0 NaN 0.0 \n",
"697296 0.0 NaN 0.0 \n",
"\n",
" number_company \n",
"0 10 \n",
"1 10 \n",
"2 10 \n",
"3 10 \n",
"4 10 \n",
"... ... \n",
"697292 14 \n",
"697293 14 \n",
"697294 14 \n",
"697295 14 \n",
"697296 14 \n",
"\n",
"[697297 rows x 41 columns]"
]
},
"execution_count": 94,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_set_spectacle"
]
},
{
"cell_type": "code",
"execution_count": 95,
"id": "86fa4d7f-9b5f-4487-beb8-eb23771f724c",
"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>number_company</th>\n",
" <th>nb_tickets</th>\n",
" <th>nb_tickets_internet</th>\n",
" <th>Taux_ticket_internet</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>10</td>\n",
" <td>17898.0</td>\n",
" <td>8874.0</td>\n",
" <td>49.580959</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>11</td>\n",
" <td>19999.0</td>\n",
" <td>5.0</td>\n",
" <td>0.025001</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>12</td>\n",
" <td>47120.0</td>\n",
" <td>0.0</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>13</td>\n",
" <td>1135835.0</td>\n",
" <td>119308.0</td>\n",
" <td>10.503990</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>14</td>\n",
" <td>61290.0</td>\n",
" <td>0.0</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" number_company nb_tickets nb_tickets_internet Taux_ticket_internet\n",
"0 10 17898.0 8874.0 49.580959\n",
"1 11 19999.0 5.0 0.025001\n",
"2 12 47120.0 0.0 0.000000\n",
"3 13 1135835.0 119308.0 10.503990\n",
"4 14 61290.0 0.0 0.000000"
]
},
"execution_count": 95,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Taux de ticket payé par internet selon les compagnies avec la base de train\n",
"\n",
"purchase_spectacle_train = train_set_spectacle.groupby(\"number_company\")[[\"nb_tickets\", \"nb_tickets_internet\"]].sum().reset_index()\n",
"purchase_spectacle_train[\"Taux_ticket_internet\"] = purchase_spectacle_train[\"nb_tickets_internet\"]*100 / purchase_spectacle_train[\"nb_tickets\"]\n",
"purchase_spectacle_train"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d11335b7-e35a-44c7-8ce4-661216978151",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 66,