Ajout KPI Alexis dans fonction

This commit is contained in:
Antoine JOUBREL 2024-02-11 22:54:40 +00:00
parent 63d11bbae8
commit 7154a1c82c

View File

@ -1702,7 +1702,7 @@
},
{
"cell_type": "code",
"execution_count": 34,
"execution_count": 69,
"id": "043303fe-e90f-4689-a2a9-5d690555a045",
"metadata": {},
"outputs": [],
@ -1719,6 +1719,12 @@
" prop_vente_internet = tickets_information_copy[tickets_information_copy['vente_internet'] == 1].groupby(['customer_id', 'event_type_id'])['ticket_id'].count().reset_index()\n",
" prop_vente_internet.rename(columns = {'ticket_id' : 'nb_tickets_internet'}, inplace = True)\n",
"\n",
" # Average amount\n",
" avg_amount = (tickets_information_copy.groupby([\"event_type_id\", 'name_event_types'])\n",
" .agg({\"amount\" : \"mean\"}).reset_index()\n",
" .rename(columns = {'amount' : 'avg_amount'}))\n",
"\n",
" \n",
" tickets_kpi = (tickets_information_copy[['event_type_id', 'customer_id', 'purchase_id' ,'ticket_id','supplier_name', 'purchase_date', 'amount', 'vente_internet']]\n",
" .groupby(['customer_id', 'event_type_id']) \n",
" .agg({'ticket_id': 'count', \n",
@ -1751,7 +1757,7 @@
" tickets_kpi = tickets_kpi.merge(prop_vente_internet, on = ['customer_id', 'event_type_id'], how = 'left')\n",
" tickets_kpi['nb_tickets_internet'] = tickets_kpi['nb_tickets_internet'].fillna(0)\n",
"\n",
" \n",
" tickets_kpi = tickets_kpi.merge(avg_amount, how='left', on= 'event_type_id')\n",
"\n",
" return tickets_kpi\n",
" "
@ -1759,7 +1765,7 @@
},
{
"cell_type": "code",
"execution_count": 35,
"execution_count": 70,
"id": "5882234a-1ed5-4269-87a6-0d75613476e3",
"metadata": {},
"outputs": [],
@ -1938,800 +1944,6 @@
"## Alexis' work"
]
},
{
"cell_type": "code",
"execution_count": 39,
"id": "273857e0-7112-4294-8ba6-3c39c5cbc13a",
"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>event_type_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",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>384226</td>\n",
" <td>194790</td>\n",
" <td>2686540.5</td>\n",
" <td>7</td>\n",
" <td>1</td>\n",
" <td>3262.190868</td>\n",
" <td>4.179306</td>\n",
" <td>3258.011562</td>\n",
" <td>51.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" <td>453242</td>\n",
" <td>228945</td>\n",
" <td>3248965.5</td>\n",
" <td>6</td>\n",
" <td>1</td>\n",
" <td>3698.198229</td>\n",
" <td>5.221840</td>\n",
" <td>3692.976389</td>\n",
" <td>2988.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>201750</td>\n",
" <td>107110</td>\n",
" <td>1459190.0</td>\n",
" <td>6</td>\n",
" <td>1</td>\n",
" <td>3803.369792</td>\n",
" <td>0.146331</td>\n",
" <td>3803.223461</td>\n",
" <td>9.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>6</td>\n",
" <td>217356</td>\n",
" <td>111786</td>\n",
" <td>1435871.5</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>2502.715509</td>\n",
" <td>1408.715532</td>\n",
" <td>1093.999977</td>\n",
" <td>5.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>143</td>\n",
" <td>143</td>\n",
" <td>0.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>2041.274549</td>\n",
" <td>1340.308160</td>\n",
" <td>700.966389</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" customer_id event_type_id nb_tickets nb_purchases total_amount \\\n",
"0 1 2 384226 194790 2686540.5 \n",
"1 1 4 453242 228945 3248965.5 \n",
"2 1 5 201750 107110 1459190.0 \n",
"3 1 6 217356 111786 1435871.5 \n",
"4 2 2 143 143 0.0 \n",
"\n",
" nb_suppliers vente_internet_max purchase_date_min purchase_date_max \\\n",
"0 7 1 3262.190868 4.179306 \n",
"1 6 1 3698.198229 5.221840 \n",
"2 6 1 3803.369792 0.146331 \n",
"3 5 1 2502.715509 1408.715532 \n",
"4 1 0 2041.274549 1340.308160 \n",
"\n",
" time_between_purchase nb_tickets_internet \n",
"0 3258.011562 51.0 \n",
"1 3692.976389 2988.0 \n",
"2 3803.223461 9.0 \n",
"3 1093.999977 5.0 \n",
"4 700.966389 0.0 "
]
},
"execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df1_tickets_kpi.head()"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "449731f3-340f-4648-8210-4622c7dbc174",
"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>event_type_id</th>\n",
" <th>name_event_types</th>\n",
" <th>avg_amount</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2</td>\n",
" <td>offre muséale individuel</td>\n",
" <td>6.150659</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4</td>\n",
" <td>spectacle vivant</td>\n",
" <td>7.762474</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>5</td>\n",
" <td>offre muséale groupe</td>\n",
" <td>4.452618</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>6</td>\n",
" <td>formule adhésion</td>\n",
" <td>6.439463</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" event_type_id name_event_types avg_amount\n",
"0 2 offre muséale individuel 6.150659\n",
"1 4 spectacle vivant 7.762474\n",
"2 5 offre muséale groupe 4.452618\n",
"3 6 formule adhésion 6.439463"
]
},
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"avg_amount = (df1_products_purchased_reduced.groupby([\"event_type_id\", 'name_event_types'])\n",
" .agg({\"amount\" : \"mean\"}).reset_index()\n",
" .rename(columns = {'amount' : 'avg_amount'}))\n",
"\n",
"avg_amount"
]
},
{
"cell_type": "code",
"execution_count": 41,
"id": "b54bd9e8-3cad-453b-8e58-bf6d047912eb",
"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>event_type_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>name_event_types</th>\n",
" <th>avg_amount</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>384226</td>\n",
" <td>194790</td>\n",
" <td>2686540.5</td>\n",
" <td>7</td>\n",
" <td>1</td>\n",
" <td>3262.190868</td>\n",
" <td>4.179306</td>\n",
" <td>3258.011562</td>\n",
" <td>51.0</td>\n",
" <td>offre muséale individuel</td>\n",
" <td>6.150659</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" <td>453242</td>\n",
" <td>228945</td>\n",
" <td>3248965.5</td>\n",
" <td>6</td>\n",
" <td>1</td>\n",
" <td>3698.198229</td>\n",
" <td>5.221840</td>\n",
" <td>3692.976389</td>\n",
" <td>2988.0</td>\n",
" <td>spectacle vivant</td>\n",
" <td>7.762474</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>1</td>\n",
" <td>5</td>\n",
" <td>201750</td>\n",
" <td>107110</td>\n",
" <td>1459190.0</td>\n",
" <td>6</td>\n",
" <td>1</td>\n",
" <td>3803.369792</td>\n",
" <td>0.146331</td>\n",
" <td>3803.223461</td>\n",
" <td>9.0</td>\n",
" <td>offre muséale groupe</td>\n",
" <td>4.452618</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>6</td>\n",
" <td>217356</td>\n",
" <td>111786</td>\n",
" <td>1435871.5</td>\n",
" <td>5</td>\n",
" <td>1</td>\n",
" <td>2502.715509</td>\n",
" <td>1408.715532</td>\n",
" <td>1093.999977</td>\n",
" <td>5.0</td>\n",
" <td>formule adhésion</td>\n",
" <td>6.439463</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2</td>\n",
" <td>2</td>\n",
" <td>143</td>\n",
" <td>143</td>\n",
" <td>0.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>2041.274549</td>\n",
" <td>1340.308160</td>\n",
" <td>700.966389</td>\n",
" <td>0.0</td>\n",
" <td>offre muséale individuel</td>\n",
" <td>6.150659</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" customer_id event_type_id nb_tickets nb_purchases total_amount \\\n",
"0 1 2 384226 194790 2686540.5 \n",
"1 1 4 453242 228945 3248965.5 \n",
"2 1 5 201750 107110 1459190.0 \n",
"3 1 6 217356 111786 1435871.5 \n",
"4 2 2 143 143 0.0 \n",
"\n",
" nb_suppliers vente_internet_max purchase_date_min purchase_date_max \\\n",
"0 7 1 3262.190868 4.179306 \n",
"1 6 1 3698.198229 5.221840 \n",
"2 6 1 3803.369792 0.146331 \n",
"3 5 1 2502.715509 1408.715532 \n",
"4 1 0 2041.274549 1340.308160 \n",
"\n",
" time_between_purchase nb_tickets_internet name_event_types \\\n",
"0 3258.011562 51.0 offre muséale individuel \n",
"1 3692.976389 2988.0 spectacle vivant \n",
"2 3803.223461 9.0 offre muséale groupe \n",
"3 1093.999977 5.0 formule adhésion \n",
"4 700.966389 0.0 offre muséale individuel \n",
"\n",
" avg_amount \n",
"0 6.150659 \n",
"1 7.762474 \n",
"2 4.452618 \n",
"3 6.439463 \n",
"4 6.150659 "
]
},
"execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df1_tickets_kpi = df1_tickets_kpi.merge(avg_amount, how='left', on= 'event_type_id')\n",
"df1_tickets_kpi.head()"
]
},
{
"cell_type": "code",
"execution_count": 42,
"id": "2d6afe74-2517-478b-a99c-da9c7bd2edd4",
"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>birthdate</th>\n",
" <th>street_id</th>\n",
" <th>is_partner</th>\n",
" <th>gender</th>\n",
" <th>is_email_true</th>\n",
" <th>opt_in</th>\n",
" <th>structure_id</th>\n",
" <th>profession</th>\n",
" <th>language</th>\n",
" <th>...</th>\n",
" <th>fidelity</th>\n",
" <th>average_purchase_delay</th>\n",
" <th>average_price_basket</th>\n",
" <th>average_ticket_basket</th>\n",
" <th>total_price</th>\n",
" <th>purchase_count</th>\n",
" <th>first_buying_date</th>\n",
" <th>country</th>\n",
" <th>age</th>\n",
" <th>tenant_id</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>12751</td>\n",
" <td>NaN</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaT</td>\n",
" <td>fr</td>\n",
" <td>NaN</td>\n",
" <td>1311</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>12825</td>\n",
" <td>NaN</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>2</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaT</td>\n",
" <td>fr</td>\n",
" <td>NaN</td>\n",
" <td>1311</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>11261</td>\n",
" <td>NaN</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaT</td>\n",
" <td>fr</td>\n",
" <td>NaN</td>\n",
" <td>1311</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>13071</td>\n",
" <td>NaN</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>2</td>\n",
" <td>True</td>\n",
" <td>True</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaT</td>\n",
" <td>fr</td>\n",
" <td>NaN</td>\n",
" <td>1311</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>653061</td>\n",
" <td>NaN</td>\n",
" <td>10</td>\n",
" <td>False</td>\n",
" <td>2</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaT</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1311</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>151861</th>\n",
" <td>295252</td>\n",
" <td>NaN</td>\n",
" <td>10</td>\n",
" <td>False</td>\n",
" <td>2</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaT</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1311</td>\n",
" </tr>\n",
" <tr>\n",
" <th>151862</th>\n",
" <td>295271</td>\n",
" <td>NaN</td>\n",
" <td>10</td>\n",
" <td>False</td>\n",
" <td>2</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaT</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1311</td>\n",
" </tr>\n",
" <tr>\n",
" <th>151863</th>\n",
" <td>295275</td>\n",
" <td>NaN</td>\n",
" <td>10</td>\n",
" <td>False</td>\n",
" <td>2</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>NaT</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1311</td>\n",
" </tr>\n",
" <tr>\n",
" <th>151864</th>\n",
" <td>295366</td>\n",
" <td>NaN</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>2</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>3.0</td>\n",
" <td>33.0</td>\n",
" <td>3.0</td>\n",
" <td>33.0</td>\n",
" <td>1</td>\n",
" <td>2021-05-26 17:20:37+00:00</td>\n",
" <td>fr</td>\n",
" <td>NaN</td>\n",
" <td>1311</td>\n",
" </tr>\n",
" <tr>\n",
" <th>151865</th>\n",
" <td>295368</td>\n",
" <td>NaN</td>\n",
" <td>2</td>\n",
" <td>False</td>\n",
" <td>2</td>\n",
" <td>True</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>6.0</td>\n",
" <td>22.0</td>\n",
" <td>2.0</td>\n",
" <td>22.0</td>\n",
" <td>1</td>\n",
" <td>2021-05-26 17:35:38+00:00</td>\n",
" <td>fr</td>\n",
" <td>NaN</td>\n",
" <td>1311</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>151866 rows × 25 columns</p>\n",
"</div>"
],
"text/plain": [
" customer_id birthdate street_id is_partner gender is_email_true \\\n",
"0 12751 NaN 2 False 1 True \n",
"1 12825 NaN 2 False 2 True \n",
"2 11261 NaN 2 False 1 True \n",
"3 13071 NaN 2 False 2 True \n",
"4 653061 NaN 10 False 2 True \n",
"... ... ... ... ... ... ... \n",
"151861 295252 NaN 10 False 2 True \n",
"151862 295271 NaN 10 False 2 True \n",
"151863 295275 NaN 10 False 2 True \n",
"151864 295366 NaN 2 False 2 True \n",
"151865 295368 NaN 2 False 2 True \n",
"\n",
" opt_in structure_id profession language ... fidelity \\\n",
"0 True NaN NaN NaN ... 0 \n",
"1 True NaN NaN NaN ... 0 \n",
"2 True NaN NaN NaN ... 0 \n",
"3 True NaN NaN NaN ... 0 \n",
"4 False NaN NaN NaN ... 0 \n",
"... ... ... ... ... ... ... \n",
"151861 False NaN NaN NaN ... 0 \n",
"151862 False NaN NaN NaN ... 0 \n",
"151863 False NaN NaN NaN ... 0 \n",
"151864 False NaN NaN NaN ... 1 \n",
"151865 False NaN NaN NaN ... 1 \n",
"\n",
" average_purchase_delay average_price_basket average_ticket_basket \\\n",
"0 NaN NaN NaN \n",
"1 NaN NaN NaN \n",
"2 NaN NaN NaN \n",
"3 NaN NaN NaN \n",
"4 NaN NaN NaN \n",
"... ... ... ... \n",
"151861 NaN NaN NaN \n",
"151862 NaN NaN NaN \n",
"151863 NaN NaN NaN \n",
"151864 3.0 33.0 3.0 \n",
"151865 6.0 22.0 2.0 \n",
"\n",
" total_price purchase_count first_buying_date country age \\\n",
"0 NaN 0 NaT fr NaN \n",
"1 NaN 0 NaT fr NaN \n",
"2 NaN 0 NaT fr NaN \n",
"3 NaN 0 NaT fr NaN \n",
"4 NaN 0 NaT NaN NaN \n",
"... ... ... ... ... ... \n",
"151861 NaN 0 NaT NaN NaN \n",
"151862 NaN 0 NaT NaN NaN \n",
"151863 NaN 0 NaT NaN NaN \n",
"151864 33.0 1 2021-05-26 17:20:37+00:00 fr NaN \n",
"151865 22.0 1 2021-05-26 17:35:38+00:00 fr NaN \n",
"\n",
" tenant_id \n",
"0 1311 \n",
"1 1311 \n",
"2 1311 \n",
"3 1311 \n",
"4 1311 \n",
"... ... \n",
"151861 1311 \n",
"151862 1311 \n",
"151863 1311 \n",
"151864 1311 \n",
"151865 1311 \n",
"\n",
"[151866 rows x 25 columns]"
]
},
"execution_count": 42,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df1_customerplus_clean"
]
},
{
"cell_type": "code",
"execution_count": 43,