Update
This commit is contained in:
parent
fb8535d13c
commit
19d91728f0
2375
Clean-Notebook.ipynb
2375
Clean-Notebook.ipynb
File diff suppressed because it is too large
Load Diff
|
|
@ -69,59 +69,6 @@
|
||||||
"fs.ls(BUCKET)"
|
"fs.ls(BUCKET)"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 3,
|
|
||||||
"id": "d60f6b27-00b4-4655-9325-79169d1e68df",
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"name": "stdout",
|
|
||||||
"output_type": "stream",
|
|
||||||
"text": [
|
|
||||||
"bdc2324-data/1\n",
|
|
||||||
"['bdc2324-data/1/1campaign_stats.csv', 'bdc2324-data/1/1campaigns.csv', 'bdc2324-data/1/1categories.csv', 'bdc2324-data/1/1countries.csv', 'bdc2324-data/1/1currencies.csv', 'bdc2324-data/1/1customer_target_mappings.csv', 'bdc2324-data/1/1customersplus.csv', 'bdc2324-data/1/1event_types.csv', 'bdc2324-data/1/1events.csv', 'bdc2324-data/1/1facilities.csv', 'bdc2324-data/1/1link_stats.csv', 'bdc2324-data/1/1pricing_formulas.csv', 'bdc2324-data/1/1product_packs.csv', 'bdc2324-data/1/1products.csv', 'bdc2324-data/1/1products_groups.csv', 'bdc2324-data/1/1purchases.csv', 'bdc2324-data/1/1representation_category_capacities.csv', 'bdc2324-data/1/1representations.csv', 'bdc2324-data/1/1seasons.csv', 'bdc2324-data/1/1structure_tag_mappings.csv', 'bdc2324-data/1/1suppliers.csv', 'bdc2324-data/1/1tags.csv', 'bdc2324-data/1/1target_types.csv', 'bdc2324-data/1/1targets.csv', 'bdc2324-data/1/1tickets.csv', 'bdc2324-data/1/1type_of_categories.csv', 'bdc2324-data/1/1type_of_pricing_formulas.csv', 'bdc2324-data/1/1type_ofs.csv']\n",
|
|
||||||
"bdc2324-data/2\n",
|
|
||||||
"['bdc2324-data/2/2campaign_stats.csv', 'bdc2324-data/2/2campaigns.csv', 'bdc2324-data/2/2categories.csv', 'bdc2324-data/2/2contribution_sites.csv', 'bdc2324-data/2/2contributions.csv', 'bdc2324-data/2/2countries.csv', 'bdc2324-data/2/2currencies.csv', 'bdc2324-data/2/2customer_target_mappings.csv', 'bdc2324-data/2/2customersplus.csv', 'bdc2324-data/2/2event_types.csv', 'bdc2324-data/2/2events.csv', 'bdc2324-data/2/2facilities.csv', 'bdc2324-data/2/2link_stats.csv', 'bdc2324-data/2/2pricing_formulas.csv', 'bdc2324-data/2/2product_packs.csv', 'bdc2324-data/2/2products.csv', 'bdc2324-data/2/2products_groups.csv', 'bdc2324-data/2/2purchases.csv', 'bdc2324-data/2/2representation_category_capacities.csv', 'bdc2324-data/2/2representations.csv', 'bdc2324-data/2/2seasons.csv', 'bdc2324-data/2/2structure_tag_mappings.csv', 'bdc2324-data/2/2suppliers.csv', 'bdc2324-data/2/2tags.csv', 'bdc2324-data/2/2target_types.csv', 'bdc2324-data/2/2targets.csv', 'bdc2324-data/2/2tickets.csv']\n",
|
|
||||||
"bdc2324-data/3\n",
|
|
||||||
"['bdc2324-data/3/3campaign_stats.csv', 'bdc2324-data/3/3campaigns.csv', 'bdc2324-data/3/3categories.csv', 'bdc2324-data/3/3consumptions.csv', 'bdc2324-data/3/3contribution_sites.csv', 'bdc2324-data/3/3contributions.csv', 'bdc2324-data/3/3countries.csv', 'bdc2324-data/3/3currencies.csv', 'bdc2324-data/3/3customer_target_mappings.csv', 'bdc2324-data/3/3customersplus.csv', 'bdc2324-data/3/3event_types.csv', 'bdc2324-data/3/3events.csv', 'bdc2324-data/3/3facilities.csv', 'bdc2324-data/3/3link_stats.csv', 'bdc2324-data/3/3pricing_formulas.csv', 'bdc2324-data/3/3product_packs.csv', 'bdc2324-data/3/3products.csv', 'bdc2324-data/3/3products_groups.csv', 'bdc2324-data/3/3purchases.csv', 'bdc2324-data/3/3representation_category_capacities.csv', 'bdc2324-data/3/3representations.csv', 'bdc2324-data/3/3seasons.csv', 'bdc2324-data/3/3structure_tag_mappings.csv', 'bdc2324-data/3/3suppliers.csv', 'bdc2324-data/3/3tags.csv', 'bdc2324-data/3/3target_types.csv', 'bdc2324-data/3/3targets.csv', 'bdc2324-data/3/3tickets.csv']\n",
|
|
||||||
"bdc2324-data/4\n",
|
|
||||||
"['bdc2324-data/4/4campaign_stats.csv', 'bdc2324-data/4/4campaigns.csv', 'bdc2324-data/4/4categories.csv', 'bdc2324-data/4/4contribution_sites.csv', 'bdc2324-data/4/4contributions.csv', 'bdc2324-data/4/4countries.csv', 'bdc2324-data/4/4currencies.csv', 'bdc2324-data/4/4customer_target_mappings.csv', 'bdc2324-data/4/4customersplus.csv', 'bdc2324-data/4/4event_types.csv', 'bdc2324-data/4/4events.csv', 'bdc2324-data/4/4facilities.csv', 'bdc2324-data/4/4link_stats.csv', 'bdc2324-data/4/4pricing_formulas.csv', 'bdc2324-data/4/4product_packs.csv', 'bdc2324-data/4/4products.csv', 'bdc2324-data/4/4products_groups.csv', 'bdc2324-data/4/4purchases.csv', 'bdc2324-data/4/4representation_category_capacities.csv', 'bdc2324-data/4/4representations.csv', 'bdc2324-data/4/4seasons.csv', 'bdc2324-data/4/4structure_tag_mappings.csv', 'bdc2324-data/4/4suppliers.csv', 'bdc2324-data/4/4tags.csv', 'bdc2324-data/4/4target_types.csv', 'bdc2324-data/4/4targets.csv', 'bdc2324-data/4/4tickets.csv', 'bdc2324-data/4/4type_of_pricing_formulas.csv', 'bdc2324-data/4/4type_ofs.csv']\n",
|
|
||||||
"bdc2324-data/5\n",
|
|
||||||
"['bdc2324-data/5/5campaign_stats.csv', 'bdc2324-data/5/5campaigns.csv', 'bdc2324-data/5/5categories.csv', 'bdc2324-data/5/5consumptions.csv', 'bdc2324-data/5/5countries.csv', 'bdc2324-data/5/5currencies.csv', 'bdc2324-data/5/5customer_target_mappings.csv', 'bdc2324-data/5/5customersplus.csv', 'bdc2324-data/5/5event_types.csv', 'bdc2324-data/5/5events.csv', 'bdc2324-data/5/5facilities.csv', 'bdc2324-data/5/5link_stats.csv', 'bdc2324-data/5/5pricing_formulas.csv', 'bdc2324-data/5/5product_packs.csv', 'bdc2324-data/5/5products.csv', 'bdc2324-data/5/5products_groups.csv', 'bdc2324-data/5/5purchases.csv', 'bdc2324-data/5/5representation_category_capacities.csv', 'bdc2324-data/5/5representations.csv', 'bdc2324-data/5/5seasons.csv', 'bdc2324-data/5/5suppliers.csv', 'bdc2324-data/5/5target_types.csv', 'bdc2324-data/5/5targets.csv', 'bdc2324-data/5/5tickets.csv']\n",
|
|
||||||
"bdc2324-data/6\n",
|
|
||||||
"['bdc2324-data/6/6campaign_stats.csv', 'bdc2324-data/6/6campaigns.csv', 'bdc2324-data/6/6categories.csv', 'bdc2324-data/6/6consumptions.csv', 'bdc2324-data/6/6countries.csv', 'bdc2324-data/6/6currencies.csv', 'bdc2324-data/6/6customer_target_mappings.csv', 'bdc2324-data/6/6customersplus.csv', 'bdc2324-data/6/6event_types.csv', 'bdc2324-data/6/6events.csv', 'bdc2324-data/6/6facilities.csv', 'bdc2324-data/6/6link_stats.csv', 'bdc2324-data/6/6pricing_formulas.csv', 'bdc2324-data/6/6product_packs.csv', 'bdc2324-data/6/6products.csv', 'bdc2324-data/6/6products_groups.csv', 'bdc2324-data/6/6purchases.csv', 'bdc2324-data/6/6representation_category_capacities.csv', 'bdc2324-data/6/6representations.csv', 'bdc2324-data/6/6seasons.csv', 'bdc2324-data/6/6structure_tag_mappings.csv', 'bdc2324-data/6/6suppliers.csv', 'bdc2324-data/6/6tags.csv', 'bdc2324-data/6/6target_types.csv', 'bdc2324-data/6/6targets.csv', 'bdc2324-data/6/6tickets.csv', 'bdc2324-data/6/6type_of_pricing_formulas.csv', 'bdc2324-data/6/6type_ofs.csv']\n",
|
|
||||||
"bdc2324-data/7\n",
|
|
||||||
"['bdc2324-data/7/7campaign_stats.csv', 'bdc2324-data/7/7campaigns.csv', 'bdc2324-data/7/7categories.csv', 'bdc2324-data/7/7consumptions.csv', 'bdc2324-data/7/7countries.csv', 'bdc2324-data/7/7currencies.csv', 'bdc2324-data/7/7customer_target_mappings.csv', 'bdc2324-data/7/7customersplus.csv', 'bdc2324-data/7/7event_types.csv', 'bdc2324-data/7/7events.csv', 'bdc2324-data/7/7facilities.csv', 'bdc2324-data/7/7link_stats.csv', 'bdc2324-data/7/7pricing_formulas.csv', 'bdc2324-data/7/7product_packs.csv', 'bdc2324-data/7/7products.csv', 'bdc2324-data/7/7products_groups.csv', 'bdc2324-data/7/7purchases.csv', 'bdc2324-data/7/7representation_category_capacities.csv', 'bdc2324-data/7/7representation_types.csv', 'bdc2324-data/7/7representations.csv', 'bdc2324-data/7/7seasons.csv', 'bdc2324-data/7/7structure_tag_mappings.csv', 'bdc2324-data/7/7suppliers.csv', 'bdc2324-data/7/7tags.csv', 'bdc2324-data/7/7target_types.csv', 'bdc2324-data/7/7targets.csv', 'bdc2324-data/7/7tickets.csv', 'bdc2324-data/7/7type_of_categories.csv', 'bdc2324-data/7/7type_of_pricing_formulas.csv', 'bdc2324-data/7/7type_ofs.csv']\n",
|
|
||||||
"bdc2324-data/8\n",
|
|
||||||
"['bdc2324-data/8/8campaign_stats.csv', 'bdc2324-data/8/8campaigns.csv', 'bdc2324-data/8/8categories.csv', 'bdc2324-data/8/8countries.csv', 'bdc2324-data/8/8currencies.csv', 'bdc2324-data/8/8customer_target_mappings.csv', 'bdc2324-data/8/8customersplus.csv', 'bdc2324-data/8/8event_types.csv', 'bdc2324-data/8/8events.csv', 'bdc2324-data/8/8facilities.csv', 'bdc2324-data/8/8link_stats.csv', 'bdc2324-data/8/8pricing_formulas.csv', 'bdc2324-data/8/8product_packs.csv', 'bdc2324-data/8/8products.csv', 'bdc2324-data/8/8products_groups.csv', 'bdc2324-data/8/8purchases.csv', 'bdc2324-data/8/8representation_category_capacities.csv', 'bdc2324-data/8/8representations.csv', 'bdc2324-data/8/8seasons.csv', 'bdc2324-data/8/8suppliers.csv', 'bdc2324-data/8/8target_types.csv', 'bdc2324-data/8/8targets.csv', 'bdc2324-data/8/8tickets.csv', 'bdc2324-data/8/8type_of_categories.csv', 'bdc2324-data/8/8type_of_pricing_formulas.csv', 'bdc2324-data/8/8type_ofs.csv']\n",
|
|
||||||
"bdc2324-data/9\n",
|
|
||||||
"['bdc2324-data/9/9campaign_stats.csv', 'bdc2324-data/9/9campaigns.csv', 'bdc2324-data/9/9categories.csv', 'bdc2324-data/9/9countries.csv', 'bdc2324-data/9/9currencies.csv', 'bdc2324-data/9/9customer_target_mappings.csv', 'bdc2324-data/9/9customersplus.csv', 'bdc2324-data/9/9event_types.csv', 'bdc2324-data/9/9events.csv', 'bdc2324-data/9/9facilities.csv', 'bdc2324-data/9/9link_stats.csv', 'bdc2324-data/9/9pricing_formulas.csv', 'bdc2324-data/9/9product_packs.csv', 'bdc2324-data/9/9products.csv', 'bdc2324-data/9/9products_groups.csv', 'bdc2324-data/9/9purchases.csv', 'bdc2324-data/9/9representation_category_capacities.csv', 'bdc2324-data/9/9representations.csv', 'bdc2324-data/9/9seasons.csv', 'bdc2324-data/9/9suppliers.csv', 'bdc2324-data/9/9target_types.csv', 'bdc2324-data/9/9targets.csv', 'bdc2324-data/9/9tickets.csv']\n",
|
|
||||||
"bdc2324-data/10\n",
|
|
||||||
"['bdc2324-data/10/10campaign_stats.csv', 'bdc2324-data/10/10campaigns.csv', 'bdc2324-data/10/10categories.csv', 'bdc2324-data/10/10countries.csv', 'bdc2324-data/10/10currencies.csv', 'bdc2324-data/10/10customer_target_mappings.csv', 'bdc2324-data/10/10customersplus.csv', 'bdc2324-data/10/10event_types.csv', 'bdc2324-data/10/10events.csv', 'bdc2324-data/10/10facilities.csv', 'bdc2324-data/10/10link_stats.csv', 'bdc2324-data/10/10pricing_formulas.csv', 'bdc2324-data/10/10product_packs.csv', 'bdc2324-data/10/10products.csv', 'bdc2324-data/10/10products_groups.csv', 'bdc2324-data/10/10purchases.csv', 'bdc2324-data/10/10representation_category_capacities.csv', 'bdc2324-data/10/10representation_types.csv', 'bdc2324-data/10/10representations.csv', 'bdc2324-data/10/10seasons.csv', 'bdc2324-data/10/10suppliers.csv', 'bdc2324-data/10/10tags.csv', 'bdc2324-data/10/10target_types.csv', 'bdc2324-data/10/10targets.csv', 'bdc2324-data/10/10tickets.csv', 'bdc2324-data/10/10type_of_pricing_formulas.csv', 'bdc2324-data/10/10type_ofs.csv']\n",
|
|
||||||
"bdc2324-data/11\n",
|
|
||||||
"['bdc2324-data/11/11campaign_stats.csv', 'bdc2324-data/11/11campaigns.csv', 'bdc2324-data/11/11categories.csv', 'bdc2324-data/11/11countries.csv', 'bdc2324-data/11/11currencies.csv', 'bdc2324-data/11/11customer_target_mappings.csv', 'bdc2324-data/11/11customersplus.csv', 'bdc2324-data/11/11event_types.csv', 'bdc2324-data/11/11events.csv', 'bdc2324-data/11/11facilities.csv', 'bdc2324-data/11/11link_stats.csv', 'bdc2324-data/11/11pricing_formulas.csv', 'bdc2324-data/11/11product_packs.csv', 'bdc2324-data/11/11products.csv', 'bdc2324-data/11/11products_groups.csv', 'bdc2324-data/11/11purchases.csv', 'bdc2324-data/11/11representation_category_capacities.csv', 'bdc2324-data/11/11representations.csv', 'bdc2324-data/11/11seasons.csv', 'bdc2324-data/11/11structure_tag_mappings.csv', 'bdc2324-data/11/11suppliers.csv', 'bdc2324-data/11/11tags.csv', 'bdc2324-data/11/11target_types.csv', 'bdc2324-data/11/11targets.csv', 'bdc2324-data/11/11tickets.csv']\n",
|
|
||||||
"bdc2324-data/12\n",
|
|
||||||
"['bdc2324-data/12/12campaign_stats.csv', 'bdc2324-data/12/12campaigns.csv', 'bdc2324-data/12/12categories.csv', 'bdc2324-data/12/12consumptions.csv', 'bdc2324-data/12/12countries.csv', 'bdc2324-data/12/12currencies.csv', 'bdc2324-data/12/12customer_target_mappings.csv', 'bdc2324-data/12/12customersplus.csv', 'bdc2324-data/12/12event_types.csv', 'bdc2324-data/12/12events.csv', 'bdc2324-data/12/12facilities.csv', 'bdc2324-data/12/12link_stats.csv', 'bdc2324-data/12/12pricing_formulas.csv', 'bdc2324-data/12/12product_packs.csv', 'bdc2324-data/12/12products.csv', 'bdc2324-data/12/12products_groups.csv', 'bdc2324-data/12/12purchases.csv', 'bdc2324-data/12/12representation_category_capacities.csv', 'bdc2324-data/12/12representations.csv', 'bdc2324-data/12/12seasons.csv', 'bdc2324-data/12/12suppliers.csv', 'bdc2324-data/12/12target_types.csv', 'bdc2324-data/12/12targets.csv', 'bdc2324-data/12/12tickets.csv', 'bdc2324-data/12/12type_ofs.csv']\n",
|
|
||||||
"bdc2324-data/13\n",
|
|
||||||
"['bdc2324-data/13/13campaign_stats.csv', 'bdc2324-data/13/13campaigns.csv', 'bdc2324-data/13/13categories.csv', 'bdc2324-data/13/13countries.csv', 'bdc2324-data/13/13currencies.csv', 'bdc2324-data/13/13customer_target_mappings.csv', 'bdc2324-data/13/13customersplus.csv', 'bdc2324-data/13/13event_types.csv', 'bdc2324-data/13/13events.csv', 'bdc2324-data/13/13facilities.csv', 'bdc2324-data/13/13link_stats.csv', 'bdc2324-data/13/13pricing_formulas.csv', 'bdc2324-data/13/13product_packs.csv', 'bdc2324-data/13/13products.csv', 'bdc2324-data/13/13products_groups.csv', 'bdc2324-data/13/13purchases.csv', 'bdc2324-data/13/13representation_category_capacities.csv', 'bdc2324-data/13/13representation_types.csv', 'bdc2324-data/13/13representations.csv', 'bdc2324-data/13/13seasons.csv', 'bdc2324-data/13/13structure_tag_mappings.csv', 'bdc2324-data/13/13suppliers.csv', 'bdc2324-data/13/13tags.csv', 'bdc2324-data/13/13target_types.csv', 'bdc2324-data/13/13targets.csv', 'bdc2324-data/13/13tickets.csv']\n",
|
|
||||||
"bdc2324-data/14\n",
|
|
||||||
"['bdc2324-data/14/14campaign_stats.csv', 'bdc2324-data/14/14campaigns.csv', 'bdc2324-data/14/14categories.csv', 'bdc2324-data/14/14countries.csv', 'bdc2324-data/14/14currencies.csv', 'bdc2324-data/14/14customer_target_mappings.csv', 'bdc2324-data/14/14customersplus.csv', 'bdc2324-data/14/14event_types.csv', 'bdc2324-data/14/14events.csv', 'bdc2324-data/14/14facilities.csv', 'bdc2324-data/14/14link_stats.csv', 'bdc2324-data/14/14pricing_formulas.csv', 'bdc2324-data/14/14product_packs.csv', 'bdc2324-data/14/14products.csv', 'bdc2324-data/14/14products_groups.csv', 'bdc2324-data/14/14purchases.csv', 'bdc2324-data/14/14representation_category_capacities.csv', 'bdc2324-data/14/14representation_types.csv', 'bdc2324-data/14/14representations.csv', 'bdc2324-data/14/14seasons.csv', 'bdc2324-data/14/14suppliers.csv', 'bdc2324-data/14/14target_types.csv', 'bdc2324-data/14/14targets.csv', 'bdc2324-data/14/14tickets.csv', 'bdc2324-data/14/14type_of_categories.csv', 'bdc2324-data/14/14type_of_pricing_formulas.csv', 'bdc2324-data/14/14type_ofs.csv']\n",
|
|
||||||
"bdc2324-data/101\n",
|
|
||||||
"['bdc2324-data/101/101campaign_stats.csv', 'bdc2324-data/101/101campaigns.csv', 'bdc2324-data/101/101categories.csv', 'bdc2324-data/101/101contribution_sites.csv', 'bdc2324-data/101/101contributions.csv', 'bdc2324-data/101/101countries.csv', 'bdc2324-data/101/101currencies.csv', 'bdc2324-data/101/101customer_target_mappings.csv', 'bdc2324-data/101/101customersplus.csv', 'bdc2324-data/101/101event_types.csv', 'bdc2324-data/101/101events.csv', 'bdc2324-data/101/101facilities.csv', 'bdc2324-data/101/101link_stats.csv', 'bdc2324-data/101/101pricing_formulas.csv', 'bdc2324-data/101/101product_packs.csv', 'bdc2324-data/101/101products.csv', 'bdc2324-data/101/101products_groups.csv', 'bdc2324-data/101/101purchases.csv', 'bdc2324-data/101/101representation_category_capacities.csv', 'bdc2324-data/101/101representations.csv', 'bdc2324-data/101/101seasons.csv', 'bdc2324-data/101/101structure_tag_mappings.csv', 'bdc2324-data/101/101suppliers.csv', 'bdc2324-data/101/101tags.csv', 'bdc2324-data/101/101target_types.csv', 'bdc2324-data/101/101targets.csv', 'bdc2324-data/101/101tickets.csv', 'bdc2324-data/101/101tickets_1.csv', 'bdc2324-data/101/101type_of_pricing_formulas.csv', 'bdc2324-data/101/101type_ofs.csv']\n"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"# Liste des jeu de données par dossier\n",
|
|
||||||
"for i in range(1, 15):\n",
|
|
||||||
" FILE_PATH_S3 = BUCKET + \"/\" + str(i)\n",
|
|
||||||
" print(FILE_PATH_S3)\n",
|
|
||||||
" print(fs.ls(FILE_PATH_S3))\n",
|
|
||||||
"print(BUCKET + \"/101\")\n",
|
|
||||||
"print(fs.ls(BUCKET + \"/101\"))"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": 4,
|
"execution_count": 4,
|
||||||
|
|
@ -416,6 +363,440 @@
|
||||||
"source": [
|
"source": [
|
||||||
"pd.DataFrame(customers_plus_1.isna().mean()*100)"
|
"pd.DataFrame(customers_plus_1.isna().mean()*100)"
|
||||||
]
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 11,
|
||||||
|
"id": "6f6ce60d-0912-497d-9108-330acccef394",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"# Chargement de toutes les données\n",
|
||||||
|
"liste_base = ['customer_target_mappings', 'customersplus', 'target_types', 'tags', 'events', 'tickets', 'representations', 'purchases', 'products']\n",
|
||||||
|
"\n",
|
||||||
|
"for nom_base in liste_base:\n",
|
||||||
|
" FILE_PATH_S3 = 'bdc2324-data/11/11' + nom_base + '.csv'\n",
|
||||||
|
" with fs.open(FILE_PATH_S3, mode=\"rb\") as file_in:\n",
|
||||||
|
" globals()[nom_base] = pd.read_csv(file_in, sep=\",\")"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 12,
|
||||||
|
"id": "fa8ee17d-5092-40ac-8a0a-3790b016dd4e",
|
||||||
|
"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>id</th>\n",
|
||||||
|
" <th>lastname</th>\n",
|
||||||
|
" <th>firstname</th>\n",
|
||||||
|
" <th>birthdate</th>\n",
|
||||||
|
" <th>email</th>\n",
|
||||||
|
" <th>street_id</th>\n",
|
||||||
|
" <th>created_at</th>\n",
|
||||||
|
" <th>updated_at</th>\n",
|
||||||
|
" <th>civility</th>\n",
|
||||||
|
" <th>is_partner</th>\n",
|
||||||
|
" <th>...</th>\n",
|
||||||
|
" <th>tenant_id</th>\n",
|
||||||
|
" <th>id_x</th>\n",
|
||||||
|
" <th>customer_id</th>\n",
|
||||||
|
" <th>purchase_date</th>\n",
|
||||||
|
" <th>type_of</th>\n",
|
||||||
|
" <th>is_from_subscription</th>\n",
|
||||||
|
" <th>amount</th>\n",
|
||||||
|
" <th>is_full_price</th>\n",
|
||||||
|
" <th>start_date_time</th>\n",
|
||||||
|
" <th>event_name</th>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" </thead>\n",
|
||||||
|
" <tbody>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>0</th>\n",
|
||||||
|
" <td>405082</td>\n",
|
||||||
|
" <td>lastname405082</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>6</td>\n",
|
||||||
|
" <td>2023-01-12 06:30:31.197484+01:00</td>\n",
|
||||||
|
" <td>2023-01-12 06:30:31.197484+01:00</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>...</td>\n",
|
||||||
|
" <td>1556</td>\n",
|
||||||
|
" <td>992423</td>\n",
|
||||||
|
" <td>405082</td>\n",
|
||||||
|
" <td>2023-01-11 17:08:41+01:00</td>\n",
|
||||||
|
" <td>3</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>13.0</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>2023-02-06 20:00:00+01:00</td>\n",
|
||||||
|
" <td>zaide</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>1</th>\n",
|
||||||
|
" <td>405082</td>\n",
|
||||||
|
" <td>lastname405082</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>6</td>\n",
|
||||||
|
" <td>2023-01-12 06:30:31.197484+01:00</td>\n",
|
||||||
|
" <td>2023-01-12 06:30:31.197484+01:00</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>...</td>\n",
|
||||||
|
" <td>1556</td>\n",
|
||||||
|
" <td>992423</td>\n",
|
||||||
|
" <td>405082</td>\n",
|
||||||
|
" <td>2023-01-11 17:08:41+01:00</td>\n",
|
||||||
|
" <td>3</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>13.0</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>2023-02-06 20:00:00+01:00</td>\n",
|
||||||
|
" <td>zaide</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>2</th>\n",
|
||||||
|
" <td>411168</td>\n",
|
||||||
|
" <td>lastname411168</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>6</td>\n",
|
||||||
|
" <td>2023-03-17 06:30:35.431967+01:00</td>\n",
|
||||||
|
" <td>2023-03-17 06:30:35.431967+01:00</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>...</td>\n",
|
||||||
|
" <td>1556</td>\n",
|
||||||
|
" <td>1053934</td>\n",
|
||||||
|
" <td>411168</td>\n",
|
||||||
|
" <td>2023-03-16 16:23:10+01:00</td>\n",
|
||||||
|
" <td>3</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>62.0</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>2023-03-19 16:00:00+01:00</td>\n",
|
||||||
|
" <td>luisa miller</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>3</th>\n",
|
||||||
|
" <td>411168</td>\n",
|
||||||
|
" <td>lastname411168</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>6</td>\n",
|
||||||
|
" <td>2023-03-17 06:30:35.431967+01:00</td>\n",
|
||||||
|
" <td>2023-03-17 06:30:35.431967+01:00</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>...</td>\n",
|
||||||
|
" <td>1556</td>\n",
|
||||||
|
" <td>1053934</td>\n",
|
||||||
|
" <td>411168</td>\n",
|
||||||
|
" <td>2023-03-16 16:23:10+01:00</td>\n",
|
||||||
|
" <td>3</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>62.0</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>2023-03-19 16:00:00+01:00</td>\n",
|
||||||
|
" <td>luisa miller</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>4</th>\n",
|
||||||
|
" <td>4380</td>\n",
|
||||||
|
" <td>lastname4380</td>\n",
|
||||||
|
" <td>firstname4380</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>2021-04-22 14:51:55.432952+02:00</td>\n",
|
||||||
|
" <td>2022-04-14 11:41:33.738500+02:00</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>...</td>\n",
|
||||||
|
" <td>1556</td>\n",
|
||||||
|
" <td>1189141</td>\n",
|
||||||
|
" <td>4380</td>\n",
|
||||||
|
" <td>2020-11-26 13:12:53+01:00</td>\n",
|
||||||
|
" <td>3</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>51.3</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>2020-12-01 20:00:00+01:00</td>\n",
|
||||||
|
" <td>iphigenie en tauride</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>318964</th>\n",
|
||||||
|
" <td>19095</td>\n",
|
||||||
|
" <td>lastname19095</td>\n",
|
||||||
|
" <td>firstname19095</td>\n",
|
||||||
|
" <td>1979-07-16</td>\n",
|
||||||
|
" <td>email19095</td>\n",
|
||||||
|
" <td>6</td>\n",
|
||||||
|
" <td>2021-04-22 15:06:30.120537+02:00</td>\n",
|
||||||
|
" <td>2023-09-12 18:27:36.904104+02:00</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>...</td>\n",
|
||||||
|
" <td>1556</td>\n",
|
||||||
|
" <td>1090839</td>\n",
|
||||||
|
" <td>19095</td>\n",
|
||||||
|
" <td>2019-05-19 21:18:36+02:00</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>4.5</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>2019-05-27 20:00:00+02:00</td>\n",
|
||||||
|
" <td>entre femmes</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>318965</th>\n",
|
||||||
|
" <td>19095</td>\n",
|
||||||
|
" <td>lastname19095</td>\n",
|
||||||
|
" <td>firstname19095</td>\n",
|
||||||
|
" <td>1979-07-16</td>\n",
|
||||||
|
" <td>email19095</td>\n",
|
||||||
|
" <td>6</td>\n",
|
||||||
|
" <td>2021-04-22 15:06:30.120537+02:00</td>\n",
|
||||||
|
" <td>2023-09-12 18:27:36.904104+02:00</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>...</td>\n",
|
||||||
|
" <td>1556</td>\n",
|
||||||
|
" <td>1090839</td>\n",
|
||||||
|
" <td>19095</td>\n",
|
||||||
|
" <td>2019-05-19 21:18:36+02:00</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>4.5</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>2019-05-27 20:00:00+02:00</td>\n",
|
||||||
|
" <td>entre femmes</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>318966</th>\n",
|
||||||
|
" <td>19095</td>\n",
|
||||||
|
" <td>lastname19095</td>\n",
|
||||||
|
" <td>firstname19095</td>\n",
|
||||||
|
" <td>1979-07-16</td>\n",
|
||||||
|
" <td>email19095</td>\n",
|
||||||
|
" <td>6</td>\n",
|
||||||
|
" <td>2021-04-22 15:06:30.120537+02:00</td>\n",
|
||||||
|
" <td>2023-09-12 18:27:36.904104+02:00</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>...</td>\n",
|
||||||
|
" <td>1556</td>\n",
|
||||||
|
" <td>1090839</td>\n",
|
||||||
|
" <td>19095</td>\n",
|
||||||
|
" <td>2019-05-19 21:18:36+02:00</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>4.5</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>2019-05-27 20:00:00+02:00</td>\n",
|
||||||
|
" <td>entre femmes</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>318967</th>\n",
|
||||||
|
" <td>19095</td>\n",
|
||||||
|
" <td>lastname19095</td>\n",
|
||||||
|
" <td>firstname19095</td>\n",
|
||||||
|
" <td>1979-07-16</td>\n",
|
||||||
|
" <td>email19095</td>\n",
|
||||||
|
" <td>6</td>\n",
|
||||||
|
" <td>2021-04-22 15:06:30.120537+02:00</td>\n",
|
||||||
|
" <td>2023-09-12 18:27:36.904104+02:00</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>...</td>\n",
|
||||||
|
" <td>1556</td>\n",
|
||||||
|
" <td>1244277</td>\n",
|
||||||
|
" <td>19095</td>\n",
|
||||||
|
" <td>2019-12-31 11:04:07+01:00</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>5.5</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>2020-02-03 20:00:00+01:00</td>\n",
|
||||||
|
" <td>a boire et a manger</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" <tr>\n",
|
||||||
|
" <th>318968</th>\n",
|
||||||
|
" <td>19095</td>\n",
|
||||||
|
" <td>lastname19095</td>\n",
|
||||||
|
" <td>firstname19095</td>\n",
|
||||||
|
" <td>1979-07-16</td>\n",
|
||||||
|
" <td>email19095</td>\n",
|
||||||
|
" <td>6</td>\n",
|
||||||
|
" <td>2021-04-22 15:06:30.120537+02:00</td>\n",
|
||||||
|
" <td>2023-09-12 18:27:36.904104+02:00</td>\n",
|
||||||
|
" <td>NaN</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>...</td>\n",
|
||||||
|
" <td>1556</td>\n",
|
||||||
|
" <td>1244277</td>\n",
|
||||||
|
" <td>19095</td>\n",
|
||||||
|
" <td>2019-12-31 11:04:07+01:00</td>\n",
|
||||||
|
" <td>1</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>5.5</td>\n",
|
||||||
|
" <td>False</td>\n",
|
||||||
|
" <td>2020-02-03 20:00:00+01:00</td>\n",
|
||||||
|
" <td>a boire et a manger</td>\n",
|
||||||
|
" </tr>\n",
|
||||||
|
" </tbody>\n",
|
||||||
|
"</table>\n",
|
||||||
|
"<p>318969 rows × 52 columns</p>\n",
|
||||||
|
"</div>"
|
||||||
|
],
|
||||||
|
"text/plain": [
|
||||||
|
" id lastname firstname birthdate email \\\n",
|
||||||
|
"0 405082 lastname405082 NaN NaN NaN \n",
|
||||||
|
"1 405082 lastname405082 NaN NaN NaN \n",
|
||||||
|
"2 411168 lastname411168 NaN NaN NaN \n",
|
||||||
|
"3 411168 lastname411168 NaN NaN NaN \n",
|
||||||
|
"4 4380 lastname4380 firstname4380 NaN NaN \n",
|
||||||
|
"... ... ... ... ... ... \n",
|
||||||
|
"318964 19095 lastname19095 firstname19095 1979-07-16 email19095 \n",
|
||||||
|
"318965 19095 lastname19095 firstname19095 1979-07-16 email19095 \n",
|
||||||
|
"318966 19095 lastname19095 firstname19095 1979-07-16 email19095 \n",
|
||||||
|
"318967 19095 lastname19095 firstname19095 1979-07-16 email19095 \n",
|
||||||
|
"318968 19095 lastname19095 firstname19095 1979-07-16 email19095 \n",
|
||||||
|
"\n",
|
||||||
|
" street_id created_at \\\n",
|
||||||
|
"0 6 2023-01-12 06:30:31.197484+01:00 \n",
|
||||||
|
"1 6 2023-01-12 06:30:31.197484+01:00 \n",
|
||||||
|
"2 6 2023-03-17 06:30:35.431967+01:00 \n",
|
||||||
|
"3 6 2023-03-17 06:30:35.431967+01:00 \n",
|
||||||
|
"4 1 2021-04-22 14:51:55.432952+02:00 \n",
|
||||||
|
"... ... ... \n",
|
||||||
|
"318964 6 2021-04-22 15:06:30.120537+02:00 \n",
|
||||||
|
"318965 6 2021-04-22 15:06:30.120537+02:00 \n",
|
||||||
|
"318966 6 2021-04-22 15:06:30.120537+02:00 \n",
|
||||||
|
"318967 6 2021-04-22 15:06:30.120537+02:00 \n",
|
||||||
|
"318968 6 2021-04-22 15:06:30.120537+02:00 \n",
|
||||||
|
"\n",
|
||||||
|
" updated_at civility is_partner ... \\\n",
|
||||||
|
"0 2023-01-12 06:30:31.197484+01:00 NaN False ... \n",
|
||||||
|
"1 2023-01-12 06:30:31.197484+01:00 NaN False ... \n",
|
||||||
|
"2 2023-03-17 06:30:35.431967+01:00 NaN False ... \n",
|
||||||
|
"3 2023-03-17 06:30:35.431967+01:00 NaN False ... \n",
|
||||||
|
"4 2022-04-14 11:41:33.738500+02:00 NaN False ... \n",
|
||||||
|
"... ... ... ... ... \n",
|
||||||
|
"318964 2023-09-12 18:27:36.904104+02:00 NaN False ... \n",
|
||||||
|
"318965 2023-09-12 18:27:36.904104+02:00 NaN False ... \n",
|
||||||
|
"318966 2023-09-12 18:27:36.904104+02:00 NaN False ... \n",
|
||||||
|
"318967 2023-09-12 18:27:36.904104+02:00 NaN False ... \n",
|
||||||
|
"318968 2023-09-12 18:27:36.904104+02:00 NaN False ... \n",
|
||||||
|
"\n",
|
||||||
|
" tenant_id id_x customer_id purchase_date type_of \\\n",
|
||||||
|
"0 1556 992423 405082 2023-01-11 17:08:41+01:00 3 \n",
|
||||||
|
"1 1556 992423 405082 2023-01-11 17:08:41+01:00 3 \n",
|
||||||
|
"2 1556 1053934 411168 2023-03-16 16:23:10+01:00 3 \n",
|
||||||
|
"3 1556 1053934 411168 2023-03-16 16:23:10+01:00 3 \n",
|
||||||
|
"4 1556 1189141 4380 2020-11-26 13:12:53+01:00 3 \n",
|
||||||
|
"... ... ... ... ... ... \n",
|
||||||
|
"318964 1556 1090839 19095 2019-05-19 21:18:36+02:00 1 \n",
|
||||||
|
"318965 1556 1090839 19095 2019-05-19 21:18:36+02:00 1 \n",
|
||||||
|
"318966 1556 1090839 19095 2019-05-19 21:18:36+02:00 1 \n",
|
||||||
|
"318967 1556 1244277 19095 2019-12-31 11:04:07+01:00 1 \n",
|
||||||
|
"318968 1556 1244277 19095 2019-12-31 11:04:07+01:00 1 \n",
|
||||||
|
"\n",
|
||||||
|
" is_from_subscription amount is_full_price start_date_time \\\n",
|
||||||
|
"0 False 13.0 False 2023-02-06 20:00:00+01:00 \n",
|
||||||
|
"1 False 13.0 False 2023-02-06 20:00:00+01:00 \n",
|
||||||
|
"2 False 62.0 False 2023-03-19 16:00:00+01:00 \n",
|
||||||
|
"3 False 62.0 False 2023-03-19 16:00:00+01:00 \n",
|
||||||
|
"4 False 51.3 False 2020-12-01 20:00:00+01:00 \n",
|
||||||
|
"... ... ... ... ... \n",
|
||||||
|
"318964 False 4.5 False 2019-05-27 20:00:00+02:00 \n",
|
||||||
|
"318965 False 4.5 False 2019-05-27 20:00:00+02:00 \n",
|
||||||
|
"318966 False 4.5 False 2019-05-27 20:00:00+02:00 \n",
|
||||||
|
"318967 False 5.5 False 2020-02-03 20:00:00+01:00 \n",
|
||||||
|
"318968 False 5.5 False 2020-02-03 20:00:00+01:00 \n",
|
||||||
|
"\n",
|
||||||
|
" event_name \n",
|
||||||
|
"0 zaide \n",
|
||||||
|
"1 zaide \n",
|
||||||
|
"2 luisa miller \n",
|
||||||
|
"3 luisa miller \n",
|
||||||
|
"4 iphigenie en tauride \n",
|
||||||
|
"... ... \n",
|
||||||
|
"318964 entre femmes \n",
|
||||||
|
"318965 entre femmes \n",
|
||||||
|
"318966 entre femmes \n",
|
||||||
|
"318967 a boire et a manger \n",
|
||||||
|
"318968 a boire et a manger \n",
|
||||||
|
"\n",
|
||||||
|
"[318969 rows x 52 columns]"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 12,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"# Jointure\n",
|
||||||
|
"merge_1 = pd.merge(purchases, tickets, left_on='id', right_on='purchase_id', how='inner')[['id_x', 'customer_id','product_id', 'purchase_date', 'type_of', 'is_from_subscription']]\n",
|
||||||
|
"merge_2 = pd.merge(products, merge_1, left_on='id', right_on='product_id', how='inner')[['id_x', 'customer_id', 'representation_id', 'purchase_date', 'type_of', 'is_from_subscription', 'amount', 'is_full_price']]\n",
|
||||||
|
"merge_3 = pd.merge(representations, merge_2, left_on='id', right_on='representation_id', how='inner')[['id_x', 'customer_id', 'event_id', 'purchase_date', 'type_of', 'is_from_subscription', 'amount', 'is_full_price', 'start_date_time']]\n",
|
||||||
|
"merge_4 = pd.merge(events, merge_3, left_on='id', right_on='event_id', how='inner')[['id_x', 'customer_id', 'purchase_date', 'type_of', 'is_from_subscription', 'amount', 'is_full_price', 'start_date_time', 'name']]\n",
|
||||||
|
"merge_4 = merge_4.rename(columns={'name': 'event_name'})\n",
|
||||||
|
"df_customer_event = pd.merge(customersplus, merge_4, left_on = 'id', right_on = 'customer_id', how = 'inner')[['id_x', 'purchase_date', 'type_of', 'is_from_subscription', 'amount', 'is_full_price', 'start_date_time', 'event_name']]\n",
|
||||||
|
"df_customer_event"
|
||||||
|
]
|
||||||
}
|
}
|
||||||
],
|
],
|
||||||
"metadata": {
|
"metadata": {
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue
Block a user