diff --git a/Traitement_Fanta.ipynb b/Traitement_Fanta.ipynb index c373bd7..de6fb2a 100644 --- a/Traitement_Fanta.ipynb +++ b/Traitement_Fanta.ipynb @@ -10,7 +10,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 1, "id": "ae3af8e6-ced8-4994-8877-fa98d4297cc0", "metadata": {}, "outputs": [], @@ -29,7 +29,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 2, "id": "b6035982-9ff4-4013-9792-2d50e10db3d1", "metadata": {}, "outputs": [ @@ -66,7 +66,7 @@ " 'bdc2324-data/1/1type_ofs.csv']" ] }, - "execution_count": 4, + "execution_count": 2, "metadata": {}, "output_type": "execute_result" } @@ -84,7 +84,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 3, "id": "b86c935d-124f-453f-80dd-83ea6770d09c", "metadata": {}, "outputs": [], @@ -94,7 +94,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 4, "id": "f6d0b27c-0ecd-406b-b042-6c3802dd68fd", "metadata": {}, "outputs": [ @@ -102,7 +102,7 @@ "name": "stderr", "output_type": "stream", "text": [ - "/tmp/ipykernel_432/1008972637.py:5: DtypeWarning: Columns (1) have mixed types. Specify dtype option on import or set low_memory=False.\n", + "/tmp/ipykernel_447/1008972637.py:5: DtypeWarning: Columns (1) have mixed types. Specify dtype option on import or set low_memory=False.\n", " globals()[nom_base] = pd.read_csv(file_in, sep=\",\")\n" ] } @@ -117,7 +117,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 5, "id": "2a6b5e22-3370-457f-83b7-dd1e13663229", "metadata": {}, "outputs": [ @@ -127,7 +127,7 @@ "'bdc2324-data/1/1type_ofs.csv'" ] }, - "execution_count": 7, + "execution_count": 5, "metadata": {}, "output_type": "execute_result" } @@ -190,7 +190,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 6, "id": "e0c67c01-e837-4772-b070-d1be0d895a36", "metadata": {}, "outputs": [ @@ -206,7 +206,7 @@ "dtype: int64" ] }, - "execution_count": 8, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -219,7 +219,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 7, "id": "3eaffaa6-1164-4ee9-a671-8b5eb3df797d", "metadata": {}, "outputs": [ @@ -387,7 +387,7 @@ "[568 rows x 6 columns]" ] }, - "execution_count": 10, + "execution_count": 7, "metadata": {}, "output_type": "execute_result" } @@ -398,7 +398,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 8, "id": "57298669-8d55-40d5-a5aa-4c5df984eec7", "metadata": {}, "outputs": [ @@ -414,7 +414,7 @@ "dtype: object" ] }, - "execution_count": 9, + "execution_count": 8, "metadata": {}, "output_type": "execute_result" } @@ -427,7 +427,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 9, "id": "c11850cb-8833-44c0-a11d-9695d620a42b", "metadata": {}, "outputs": [ @@ -471,7 +471,7 @@ "Index: []" ] }, - "execution_count": 12, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -491,7 +491,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 10, "id": "89909175-6734-4e8e-8632-d6f8ca812388", "metadata": {}, "outputs": [ @@ -510,7 +510,7 @@ "dtype: int64" ] }, - "execution_count": 14, + "execution_count": 10, "metadata": {}, "output_type": "execute_result" } @@ -523,7 +523,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 11, "id": "6a187170-96c4-48d2-9568-b270f67e2c27", "metadata": {}, "outputs": [ @@ -542,7 +542,7 @@ "dtype: object" ] }, - "execution_count": 15, + "execution_count": 11, "metadata": {}, "output_type": "execute_result" } @@ -555,7 +555,7 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 12, "id": "2fba2cb0-a6a4-43b2-a854-3be07939c28b", "metadata": {}, "outputs": [ @@ -602,7 +602,7 @@ "Index: []" ] }, - "execution_count": 17, + "execution_count": 12, "metadata": {}, "output_type": "execute_result" } @@ -622,7 +622,7 @@ }, { "cell_type": "code", - "execution_count": 21, + "execution_count": 13, "id": "3383a773-0817-4b23-84e7-8d5d0c74b179", "metadata": {}, "outputs": [ @@ -803,7 +803,7 @@ "[556 rows x 6 columns]" ] }, - "execution_count": 21, + "execution_count": 13, "metadata": {}, "output_type": "execute_result" } @@ -814,7 +814,7 @@ }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 14, "id": "d8130c73-6c5f-45b1-93ae-db7679c8ca56", "metadata": {}, "outputs": [ @@ -830,7 +830,7 @@ "dtype: float64" ] }, - "execution_count": 20, + "execution_count": 14, "metadata": {}, "output_type": "execute_result" } @@ -843,7 +843,7 @@ }, { "cell_type": "code", - "execution_count": 22, + "execution_count": 15, "id": "44f1dbfd-c3cf-464b-9877-f37fcc61da92", "metadata": {}, "outputs": [ @@ -859,7 +859,7 @@ "dtype: object" ] }, - "execution_count": 22, + "execution_count": 15, "metadata": {}, "output_type": "execute_result" } @@ -872,7 +872,7 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 16, "id": "6784b41b-da74-4fae-832e-16641ae710c1", "metadata": {}, "outputs": [ @@ -916,7 +916,7 @@ "Index: []" ] }, - "execution_count": 23, + "execution_count": 16, "metadata": {}, "output_type": "execute_result" } @@ -936,7 +936,7 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 17, "id": "e36b07a7-4f0b-4711-86a0-12a1d8158eef", "metadata": {}, "outputs": [ @@ -952,7 +952,7 @@ "dtype: float64" ] }, - "execution_count": 24, + "execution_count": 17, "metadata": {}, "output_type": "execute_result" } @@ -965,7 +965,7 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 18, "id": "8707396a-f86b-476d-a9f9-c39f8de1d02e", "metadata": {}, "outputs": [ @@ -981,7 +981,7 @@ "dtype: object" ] }, - "execution_count": 25, + "execution_count": 18, "metadata": {}, "output_type": "execute_result" } @@ -994,7 +994,7 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 19, "id": "4b102bd3-924b-43da-8915-be7664c23f97", "metadata": {}, "outputs": [ @@ -1038,7 +1038,7 @@ "Index: []" ] }, - "execution_count": 26, + "execution_count": 19, "metadata": {}, "output_type": "execute_result" } @@ -1058,7 +1058,7 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 20, "id": "968beb24-f70c-4eb6-8b1e-4b04bc7fe9c9", "metadata": {}, "outputs": [ @@ -1082,7 +1082,7 @@ "dtype: float64" ] }, - "execution_count": 28, + "execution_count": 20, "metadata": {}, "output_type": "execute_result" } @@ -1095,7 +1095,7 @@ }, { "cell_type": "code", - "execution_count": 29, + "execution_count": 21, "id": "15bc6ac6-67e8-4e2c-9641-7ee8bb2581a3", "metadata": {}, "outputs": [ @@ -1119,7 +1119,7 @@ "dtype: object" ] }, - "execution_count": 29, + "execution_count": 21, "metadata": {}, "output_type": "execute_result" } @@ -1130,6 +1130,208 @@ "products.dtypes" ] }, + { + "cell_type": "code", + "execution_count": 22, + "id": "7daa4f1a-e429-4daf-a2e1-1e311b487e09", + "metadata": {}, + "outputs": [], + "source": [ + "#dic_prod_princing=['type_of_pricing_formulas','products_groups','pricing_formulas','product_packs','products']" + ] + }, + { + "cell_type": "code", + "execution_count": 26, + "id": "dc12b746-6708-4708-826a-acb5a8e665a1", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idnamecreated_atupdated_atextra_fieldidentifier
041909visite mécènes 1h302022-07-08 07:08:26.802266+02:002022-07-08 07:08:26.802266+02:00NaN21d4b0043c12b21952b0797d140991a1
1502entree mucem tp( expo picasso)2020-09-03 13:43:59.816765+02:002022-02-18 15:57:55.792581+01:00NaN223b09e6c3f1f75dbf8df019af97a555
2504nombre de personnes cinema2020-09-03 13:43:59.818198+02:002021-01-25 19:16:05.187114+01:00NaNba33b7b6d225a75d713a356b49c4d915
3117spectacle tarif e famille tr2020-09-03 13:21:21.400249+02:002023-03-13 11:30:29.525335+01:00NaNa00b61ad933518856f86e63ca91a5750
41496billet nb famille mecene 1a2020-09-03 14:29:33.320952+02:002021-01-25 19:23:06.816402+01:00NaN7f6013803c242253a5ccde80f780984f
.....................
551529billet nb expo gr2020-09-03 13:43:59.835944+02:002022-02-18 15:57:55.792581+01:00NaN7d888e42abe101fc8b21dc88948c8b74
5523153nb pers visite scolaire rep2020-09-03 16:32:37.068864+02:002022-02-18 15:57:55.792581+01:00NaN3cf21731c25eee650d5b232ee4780563
5535847visite scolaire rep1h002021-06-09 18:10:49.742531+02:002022-02-18 15:55:03.576236+01:00NaNa7bb5a6892d55f0d5ee4ce5786ae5fc6
5545840france billet - entree ts2021-06-09 18:10:49.737576+02:002022-02-18 16:16:00.199543+01:00NaN4c53016fc65847646f600eff853593e5
5555863france billet - entree tp2021-06-09 18:12:49.269924+02:002022-02-18 16:16:00.199543+01:00NaN90e642c0e1ef6bc9f2bc43089798de00
\n", + "

556 rows × 6 columns

\n", + "
" + ], + "text/plain": [ + " id name created_at \\\n", + "0 41909 visite mécènes 1h30 2022-07-08 07:08:26.802266+02:00 \n", + "1 502 entree mucem tp( expo picasso) 2020-09-03 13:43:59.816765+02:00 \n", + "2 504 nombre de personnes cinema 2020-09-03 13:43:59.818198+02:00 \n", + "3 117 spectacle tarif e famille tr 2020-09-03 13:21:21.400249+02:00 \n", + "4 1496 billet nb famille mecene 1a 2020-09-03 14:29:33.320952+02:00 \n", + ".. ... ... ... \n", + "551 529 billet nb expo gr 2020-09-03 13:43:59.835944+02:00 \n", + "552 3153 nb pers visite scolaire rep 2020-09-03 16:32:37.068864+02:00 \n", + "553 5847 visite scolaire rep1h00 2021-06-09 18:10:49.742531+02:00 \n", + "554 5840 france billet - entree ts 2021-06-09 18:10:49.737576+02:00 \n", + "555 5863 france billet - entree tp 2021-06-09 18:12:49.269924+02:00 \n", + "\n", + " updated_at extra_field \\\n", + "0 2022-07-08 07:08:26.802266+02:00 NaN \n", + "1 2022-02-18 15:57:55.792581+01:00 NaN \n", + "2 2021-01-25 19:16:05.187114+01:00 NaN \n", + "3 2023-03-13 11:30:29.525335+01:00 NaN \n", + "4 2021-01-25 19:23:06.816402+01:00 NaN \n", + ".. ... ... \n", + "551 2022-02-18 15:57:55.792581+01:00 NaN \n", + "552 2022-02-18 15:57:55.792581+01:00 NaN \n", + "553 2022-02-18 15:55:03.576236+01:00 NaN \n", + "554 2022-02-18 16:16:00.199543+01:00 NaN \n", + "555 2022-02-18 16:16:00.199543+01:00 NaN \n", + "\n", + " identifier \n", + "0 21d4b0043c12b21952b0797d140991a1 \n", + "1 223b09e6c3f1f75dbf8df019af97a555 \n", + "2 ba33b7b6d225a75d713a356b49c4d915 \n", + "3 a00b61ad933518856f86e63ca91a5750 \n", + "4 7f6013803c242253a5ccde80f780984f \n", + ".. ... \n", + "551 7d888e42abe101fc8b21dc88948c8b74 \n", + "552 3cf21731c25eee650d5b232ee4780563 \n", + "553 a7bb5a6892d55f0d5ee4ce5786ae5fc6 \n", + "554 4c53016fc65847646f600eff853593e5 \n", + "555 90e642c0e1ef6bc9f2bc43089798de00 \n", + "\n", + "[556 rows x 6 columns]" + ] + }, + "execution_count": 26, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "pricing_formulas" + ] + }, { "cell_type": "markdown", "id": "46aad10f-8530-410e-872b-bb253c553a46", @@ -1141,9 +1343,899 @@ { "cell_type": "code", "execution_count": null, + "id": "a4c3edd1-6d58-4c57-b3e4-0ef3529f6b8c", + "metadata": {}, + "outputs": [], + "source": [ + "#dic_prod_princing=['type_of_pricing_formulas','products_groups','pricing_formulas','product_packs','products']" + ] + }, + { + "cell_type": "code", + "execution_count": 32, "id": "eac537e1-bbad-45bc-a85c-12b675da1088", "metadata": {}, "outputs": [], + "source": [ + "#Merge1 entre products et pricing_formulas\n", + "base1=products.merge(pricing_formulas, how='outer', left_on= 'pricing_formula_id', right_on= 'id', suffixes = (\"_products\", \"_pricing_formula\"))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "7dd0bdae-c1c5-44ba-a446-42b28def2343", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": 36, + "id": "75be3a30-3114-432d-87d6-697533c3c871", + "metadata": {}, + "outputs": [], + "source": [ + "#Merge2 entre products et pricing_formulas\n", + "base2=base1.merge(products_groups, how='outer', left_on= 'pricing_formula_id', right_on= 'id', suffixes = (\"_merge2\", \"_product_group\"))" + ] + }, + { + "cell_type": "code", + "execution_count": 37, + "id": "13f4e606-3678-476c-8b8f-9d3f1123e563", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
id_productsamountis_full_pricerepresentation_id_merge2pricing_formula_id_merge2created_at_productsupdated_at_productscategory_id_merge2apply_priceproducts_group_id...identifier_pricing_formulaidpercent_pricemax_pricemin_pricecategory_id_product_grouppricing_formula_id_product_grouprepresentation_id_product_groupcreated_atupdated_at
010682.09.0False914.0114.02020-09-03 14:09:43.119798+02:002020-09-03 14:09:43.119798+02:0041.00.010655.0...039003ae0b0cd2df183786804b713470114.0100.00.00.016.079.038.02020-09-03 13:21:21.456941+02:002020-09-03 13:21:21.456941+02:00
123519.09.0False866.0114.02020-09-03 15:01:05.950869+02:002020-09-03 15:01:05.950869+02:0041.00.023460.0...039003ae0b0cd2df183786804b713470114.0100.00.00.016.079.038.02020-09-03 13:21:21.456941+02:002020-09-03 13:21:21.456941+02:00
23703.09.0False1949.0114.02020-09-03 13:44:01.666354+02:002020-09-03 13:44:01.666354+02:0041.00.03690.0...039003ae0b0cd2df183786804b713470114.0100.00.00.016.079.038.02020-09-03 13:21:21.456941+02:002020-09-03 13:21:21.456941+02:00
323527.09.0False5573.0114.02020-09-03 15:01:05.958931+02:002020-09-03 15:01:05.958931+02:0041.00.023468.0...039003ae0b0cd2df183786804b713470114.0100.00.00.016.079.038.02020-09-03 13:21:21.456941+02:002020-09-03 13:21:21.456941+02:00
43712.09.0False509.0114.02020-09-03 13:44:01.675588+02:002020-09-03 13:44:01.675588+02:0041.00.03699.0...039003ae0b0cd2df183786804b713470114.0100.00.00.016.079.038.02020-09-03 13:21:21.456941+02:002020-09-03 13:21:21.456941+02:00
..................................................................
187391NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN...NaN404833.0100.00.00.02.04.0188494.02023-10-31 06:06:49.074426+01:002023-10-31 06:06:49.074426+01:00
187392NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN...NaN404834.0100.00.00.05.02799.0188494.02023-10-31 06:06:49.075541+01:002023-10-31 06:06:49.075541+01:00
187393NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN...NaN404835.0100.00.00.05.05676.0188494.02023-10-31 06:06:49.077170+01:002023-10-31 06:06:49.077170+01:00
187394NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN...NaN404836.0100.00.00.05.032.0189434.02023-10-31 06:06:49.079215+01:002023-10-31 06:06:49.079215+01:00
187395NaNNaNNaNNaNNaNNaNNaNNaNNaNNaN...NaN404837.0100.00.00.01.06656.0189434.02023-10-31 06:06:49.081039+01:002023-10-31 06:06:49.081039+01:00
\n", + "

187396 rows × 29 columns

\n", + "
" + ], + "text/plain": [ + " id_products amount is_full_price representation_id_merge2 \\\n", + "0 10682.0 9.0 False 914.0 \n", + "1 23519.0 9.0 False 866.0 \n", + "2 3703.0 9.0 False 1949.0 \n", + "3 23527.0 9.0 False 5573.0 \n", + "4 3712.0 9.0 False 509.0 \n", + "... ... ... ... ... \n", + "187391 NaN NaN NaN NaN \n", + "187392 NaN NaN NaN NaN \n", + "187393 NaN NaN NaN NaN \n", + "187394 NaN NaN NaN NaN \n", + "187395 NaN NaN NaN NaN \n", + "\n", + " pricing_formula_id_merge2 created_at_products \\\n", + "0 114.0 2020-09-03 14:09:43.119798+02:00 \n", + "1 114.0 2020-09-03 15:01:05.950869+02:00 \n", + "2 114.0 2020-09-03 13:44:01.666354+02:00 \n", + "3 114.0 2020-09-03 15:01:05.958931+02:00 \n", + "4 114.0 2020-09-03 13:44:01.675588+02:00 \n", + "... ... ... \n", + "187391 NaN NaN \n", + "187392 NaN NaN \n", + "187393 NaN NaN \n", + "187394 NaN NaN \n", + "187395 NaN NaN \n", + "\n", + " updated_at_products category_id_merge2 apply_price \\\n", + "0 2020-09-03 14:09:43.119798+02:00 41.0 0.0 \n", + "1 2020-09-03 15:01:05.950869+02:00 41.0 0.0 \n", + "2 2020-09-03 13:44:01.666354+02:00 41.0 0.0 \n", + "3 2020-09-03 15:01:05.958931+02:00 41.0 0.0 \n", + "4 2020-09-03 13:44:01.675588+02:00 41.0 0.0 \n", + "... ... ... ... \n", + "187391 NaN NaN NaN \n", + "187392 NaN NaN NaN \n", + "187393 NaN NaN NaN \n", + "187394 NaN NaN NaN \n", + "187395 NaN NaN NaN \n", + "\n", + " products_group_id ... identifier_pricing_formula id \\\n", + "0 10655.0 ... 039003ae0b0cd2df183786804b713470 114.0 \n", + "1 23460.0 ... 039003ae0b0cd2df183786804b713470 114.0 \n", + "2 3690.0 ... 039003ae0b0cd2df183786804b713470 114.0 \n", + "3 23468.0 ... 039003ae0b0cd2df183786804b713470 114.0 \n", + "4 3699.0 ... 039003ae0b0cd2df183786804b713470 114.0 \n", + "... ... ... ... ... \n", + "187391 NaN ... NaN 404833.0 \n", + "187392 NaN ... NaN 404834.0 \n", + "187393 NaN ... NaN 404835.0 \n", + "187394 NaN ... NaN 404836.0 \n", + "187395 NaN ... NaN 404837.0 \n", + "\n", + " percent_price max_price min_price category_id_product_group \\\n", + "0 100.0 0.0 0.0 16.0 \n", + "1 100.0 0.0 0.0 16.0 \n", + "2 100.0 0.0 0.0 16.0 \n", + "3 100.0 0.0 0.0 16.0 \n", + "4 100.0 0.0 0.0 16.0 \n", + "... ... ... ... ... \n", + "187391 100.0 0.0 0.0 2.0 \n", + "187392 100.0 0.0 0.0 5.0 \n", + "187393 100.0 0.0 0.0 5.0 \n", + "187394 100.0 0.0 0.0 5.0 \n", + "187395 100.0 0.0 0.0 1.0 \n", + "\n", + " pricing_formula_id_product_group representation_id_product_group \\\n", + "0 79.0 38.0 \n", + "1 79.0 38.0 \n", + "2 79.0 38.0 \n", + "3 79.0 38.0 \n", + "4 79.0 38.0 \n", + "... ... ... \n", + "187391 4.0 188494.0 \n", + "187392 2799.0 188494.0 \n", + "187393 5676.0 188494.0 \n", + "187394 32.0 189434.0 \n", + "187395 6656.0 189434.0 \n", + "\n", + " created_at updated_at \n", + "0 2020-09-03 13:21:21.456941+02:00 2020-09-03 13:21:21.456941+02:00 \n", + "1 2020-09-03 13:21:21.456941+02:00 2020-09-03 13:21:21.456941+02:00 \n", + "2 2020-09-03 13:21:21.456941+02:00 2020-09-03 13:21:21.456941+02:00 \n", + "3 2020-09-03 13:21:21.456941+02:00 2020-09-03 13:21:21.456941+02:00 \n", + "4 2020-09-03 13:21:21.456941+02:00 2020-09-03 13:21:21.456941+02:00 \n", + "... ... ... \n", + "187391 2023-10-31 06:06:49.074426+01:00 2023-10-31 06:06:49.074426+01:00 \n", + "187392 2023-10-31 06:06:49.075541+01:00 2023-10-31 06:06:49.075541+01:00 \n", + "187393 2023-10-31 06:06:49.077170+01:00 2023-10-31 06:06:49.077170+01:00 \n", + "187394 2023-10-31 06:06:49.079215+01:00 2023-10-31 06:06:49.079215+01:00 \n", + "187395 2023-10-31 06:06:49.081039+01:00 2023-10-31 06:06:49.081039+01:00 \n", + "\n", + "[187396 rows x 29 columns]" + ] + }, + "execution_count": 37, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "base2" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "id": "053a4829-b0e7-4c8f-80b2-e57e99cdcedc", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
id_productsamountis_full_pricerepresentation_idpricing_formula_idcreated_at_productsupdated_at_productscategory_idapply_priceproducts_group_idproduct_pack_idextra_field_productsamount_consumptionidentifier_productsid_pricing_formulanamecreated_at_pricing_formulaupdated_at_pricing_formulaextra_field_pricing_formulaidentifier_pricing_formula
0106829.0False9141142020-09-03 14:09:43.119798+02:002020-09-03 14:09:43.119798+02:00410.0106551NaNNaN35c88f2db8a63d7474e46eb8ca9260e7114visite guidée indiv tr2020-09-03 13:21:21.397923+02:002022-02-18 15:57:55.792581+01:00NaN039003ae0b0cd2df183786804b713470
14789.5False2731312020-09-03 13:21:22.711773+02:002020-09-03 13:21:22.711773+02:0010.04711NaNNaN8a179671ab198e570e6a104c4451379f131billet mucem tp - picasso2020-09-03 13:21:21.410521+02:002022-02-18 15:57:55.792581+01:00NaN916c92362b8e7767715bc966de43e32b
22087311.5False2751372020-09-03 14:46:33.589030+02:002020-09-03 14:46:33.589030+02:0010.0208251NaNNaNee83779ce29e67ad251e40234b426d6a137billet mucem tp - pic. + guide2020-09-03 13:21:21.414922+02:002022-02-18 15:57:55.792581+01:00NaN91dd2ee46f5f2d78af989019ebd60a60
31571428.0False8251992022-01-28 19:29:23.525722+01:002022-01-28 19:29:23.525722+01:0050.01567731NaNNaNd865383579314b791aa4bcf3fb418f179billet mucem ts2020-09-03 13:11:23.997074+02:002022-02-18 15:57:55.792581+01:00NaN37532348a1f1ef1cb916c55ebaf8345c
413418.5False9932020-09-03 13:29:30.773089+02:002020-09-03 13:29:30.773089+02:0010.011751NaNNaNf1c4689bc47dee6f60b56d74b593dd4693billet mucem tr + guide2020-09-03 13:21:21.382586+02:002022-02-18 15:57:55.792581+01:00NaN722a8610e4391c27f2ec6f1224b42b3d
...............................................................
947983885540.0False18133131532023-04-05 03:34:01.850415+02:002023-04-05 03:34:01.850415+02:0090.03878621NaNNaN64147cc47279f4b1b76814b9f7f206193153nb pers visite scolaire rep2020-09-03 16:32:37.068864+02:002022-02-18 15:57:55.792581+01:00NaN3cf21731c25eee650d5b232ee4780563
947993885550.0False181331204412023-04-05 03:34:01.853121+02:002023-04-05 03:34:01.853121+02:00170.03878631NaNNaN93ec10028cfa7557a8788dd2fb4f6a1720441visite scolaire rep1h302021-12-17 05:15:30.142593+01:002022-02-18 15:55:03.576236+01:00NaN6844d69dcb1178aa9e04567bce71df1f
9480038855670.0False181332177982023-04-05 03:34:01.855466+02:002023-04-05 03:34:01.855466+02:00170.03878641NaNNaNa0cc8e58412502e24e38dfeded03248517798visite scolaire 1h302021-09-30 08:15:49.172362+02:002022-02-18 15:55:03.576236+01:00NaNcfa6ba42e14f2a170a0fc566a183fe94
948013885570.0False18133231262023-04-05 03:34:01.857441+02:002023-04-05 03:34:01.857441+02:0090.03878651NaNNaN94532a14d98637ac9ee2b7d9aedad1883126nb pers visite scolaire2020-09-03 16:31:39.822413+02:002022-02-18 15:57:55.792581+01:00NaNab5dbcde8e5e1fce29737070bce06799
948023885265.0False181318962023-04-04 06:06:31.784073+02:002023-04-04 06:06:31.784073+02:00390.03878341NaNNaN4c1ee03106e34585d57d96da5e7c5f5096visite guidée indiv tu2020-09-03 13:21:21.384812+02:002022-02-18 15:57:55.792581+01:00NaN62fd9a5b40c116e45eda51222d135dfd
\n", + "

94803 rows × 20 columns

\n", + "
" + ], + "text/plain": [ + " id_products amount is_full_price representation_id \\\n", + "0 10682 9.0 False 914 \n", + "1 478 9.5 False 273 \n", + "2 20873 11.5 False 275 \n", + "3 157142 8.0 False 82519 \n", + "4 1341 8.5 False 9 \n", + "... ... ... ... ... \n", + "94798 388554 0.0 False 181331 \n", + "94799 388555 0.0 False 181331 \n", + "94800 388556 70.0 False 181332 \n", + "94801 388557 0.0 False 181332 \n", + "94802 388526 5.0 False 181318 \n", + "\n", + " pricing_formula_id created_at_products \\\n", + "0 114 2020-09-03 14:09:43.119798+02:00 \n", + "1 131 2020-09-03 13:21:22.711773+02:00 \n", + "2 137 2020-09-03 14:46:33.589030+02:00 \n", + "3 9 2022-01-28 19:29:23.525722+01:00 \n", + "4 93 2020-09-03 13:29:30.773089+02:00 \n", + "... ... ... \n", + "94798 3153 2023-04-05 03:34:01.850415+02:00 \n", + "94799 20441 2023-04-05 03:34:01.853121+02:00 \n", + "94800 17798 2023-04-05 03:34:01.855466+02:00 \n", + "94801 3126 2023-04-05 03:34:01.857441+02:00 \n", + "94802 96 2023-04-04 06:06:31.784073+02:00 \n", + "\n", + " updated_at_products category_id apply_price \\\n", + "0 2020-09-03 14:09:43.119798+02:00 41 0.0 \n", + "1 2020-09-03 13:21:22.711773+02:00 1 0.0 \n", + "2 2020-09-03 14:46:33.589030+02:00 1 0.0 \n", + "3 2022-01-28 19:29:23.525722+01:00 5 0.0 \n", + "4 2020-09-03 13:29:30.773089+02:00 1 0.0 \n", + "... ... ... ... \n", + "94798 2023-04-05 03:34:01.850415+02:00 9 0.0 \n", + "94799 2023-04-05 03:34:01.853121+02:00 17 0.0 \n", + "94800 2023-04-05 03:34:01.855466+02:00 17 0.0 \n", + "94801 2023-04-05 03:34:01.857441+02:00 9 0.0 \n", + "94802 2023-04-04 06:06:31.784073+02:00 39 0.0 \n", + "\n", + " products_group_id product_pack_id extra_field_products \\\n", + "0 10655 1 NaN \n", + "1 471 1 NaN \n", + "2 20825 1 NaN \n", + "3 156773 1 NaN \n", + "4 1175 1 NaN \n", + "... ... ... ... \n", + "94798 387862 1 NaN \n", + "94799 387863 1 NaN \n", + "94800 387864 1 NaN \n", + "94801 387865 1 NaN \n", + "94802 387834 1 NaN \n", + "\n", + " amount_consumption identifier_products \\\n", + "0 NaN 35c88f2db8a63d7474e46eb8ca9260e7 \n", + "1 NaN 8a179671ab198e570e6a104c4451379f \n", + "2 NaN ee83779ce29e67ad251e40234b426d6a \n", + "3 NaN d865383579314b791aa4bcf3fb418f17 \n", + "4 NaN f1c4689bc47dee6f60b56d74b593dd46 \n", + "... ... ... \n", + "94798 NaN 64147cc47279f4b1b76814b9f7f20619 \n", + "94799 NaN 93ec10028cfa7557a8788dd2fb4f6a17 \n", + "94800 NaN a0cc8e58412502e24e38dfeded032485 \n", + "94801 NaN 94532a14d98637ac9ee2b7d9aedad188 \n", + "94802 NaN 4c1ee03106e34585d57d96da5e7c5f50 \n", + "\n", + " id_pricing_formula name \\\n", + "0 114 visite guidée indiv tr \n", + "1 131 billet mucem tp - picasso \n", + "2 137 billet mucem tp - pic. + guide \n", + "3 9 billet mucem ts \n", + "4 93 billet mucem tr + guide \n", + "... ... ... \n", + "94798 3153 nb pers visite scolaire rep \n", + "94799 20441 visite scolaire rep1h30 \n", + "94800 17798 visite scolaire 1h30 \n", + "94801 3126 nb pers visite scolaire \n", + "94802 96 visite guidée indiv tu \n", + "\n", + " created_at_pricing_formula updated_at_pricing_formula \\\n", + "0 2020-09-03 13:21:21.397923+02:00 2022-02-18 15:57:55.792581+01:00 \n", + "1 2020-09-03 13:21:21.410521+02:00 2022-02-18 15:57:55.792581+01:00 \n", + "2 2020-09-03 13:21:21.414922+02:00 2022-02-18 15:57:55.792581+01:00 \n", + "3 2020-09-03 13:11:23.997074+02:00 2022-02-18 15:57:55.792581+01:00 \n", + "4 2020-09-03 13:21:21.382586+02:00 2022-02-18 15:57:55.792581+01:00 \n", + "... ... ... \n", + "94798 2020-09-03 16:32:37.068864+02:00 2022-02-18 15:57:55.792581+01:00 \n", + "94799 2021-12-17 05:15:30.142593+01:00 2022-02-18 15:55:03.576236+01:00 \n", + "94800 2021-09-30 08:15:49.172362+02:00 2022-02-18 15:55:03.576236+01:00 \n", + "94801 2020-09-03 16:31:39.822413+02:00 2022-02-18 15:57:55.792581+01:00 \n", + "94802 2020-09-03 13:21:21.384812+02:00 2022-02-18 15:57:55.792581+01:00 \n", + "\n", + " extra_field_pricing_formula identifier_pricing_formula \n", + "0 NaN 039003ae0b0cd2df183786804b713470 \n", + "1 NaN 916c92362b8e7767715bc966de43e32b \n", + "2 NaN 91dd2ee46f5f2d78af989019ebd60a60 \n", + "3 NaN 37532348a1f1ef1cb916c55ebaf8345c \n", + "4 NaN 722a8610e4391c27f2ec6f1224b42b3d \n", + "... ... ... \n", + "94798 NaN 3cf21731c25eee650d5b232ee4780563 \n", + "94799 NaN 6844d69dcb1178aa9e04567bce71df1f \n", + "94800 NaN cfa6ba42e14f2a170a0fc566a183fe94 \n", + "94801 NaN ab5dbcde8e5e1fce29737070bce06799 \n", + "94802 NaN 62fd9a5b40c116e45eda51222d135dfd \n", + "\n", + "[94803 rows x 20 columns]" + ] + }, + "execution_count": 24, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#Merge2 entre products et pricing_formulas\n", + "base2=base1.merge(pricing_formulas, how='left', left_on= 'id_pricing_formula', right_on= 'id', suffixes = (\"\", \"\"))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "bad94144-2474-49dd-9133-ab6082565ff1", + "metadata": {}, + "outputs": [], "source": [] } ],