diff --git a/Traitement_Fanta.ipynb b/Traitement_Fanta.ipynb index de6fb2a..c4e77d9 100644 --- a/Traitement_Fanta.ipynb +++ b/Traitement_Fanta.ipynb @@ -1352,463 +1352,20 @@ }, { "cell_type": "code", - "execution_count": 32, + "execution_count": 74, "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\"))" + "base1=products.merge(pricing_formulas, how='left', left_on= 'pricing_formula_id', right_on= 'id', suffixes = (\"_products\", \"_pricing_formula\"))" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 75, "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": { @@ -1969,271 +1526,479 @@ " NaN\n", " 722a8610e4391c27f2ec6f1224b42b3d\n", " \n", - " \n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " ...\n", - " \n", - " \n", - " 94798\n", - " 388554\n", - " 0.0\n", - " False\n", - " 181331\n", - " 3153\n", - " 2023-04-05 03:34:01.850415+02:00\n", - " 2023-04-05 03:34:01.850415+02:00\n", - " 9\n", - " 0.0\n", - " 387862\n", - " 1\n", - " NaN\n", - " NaN\n", - " 64147cc47279f4b1b76814b9f7f20619\n", - " 3153\n", - " nb pers visite scolaire rep\n", - " 2020-09-03 16:32:37.068864+02:00\n", - " 2022-02-18 15:57:55.792581+01:00\n", - " NaN\n", - " 3cf21731c25eee650d5b232ee4780563\n", - " \n", - " \n", - " 94799\n", - " 388555\n", - " 0.0\n", - " False\n", - " 181331\n", - " 20441\n", - " 2023-04-05 03:34:01.853121+02:00\n", - " 2023-04-05 03:34:01.853121+02:00\n", - " 17\n", - " 0.0\n", - " 387863\n", - " 1\n", - " NaN\n", - " NaN\n", - " 93ec10028cfa7557a8788dd2fb4f6a17\n", - " 20441\n", - " visite scolaire rep1h30\n", - " 2021-12-17 05:15:30.142593+01:00\n", - " 2022-02-18 15:55:03.576236+01:00\n", - " NaN\n", - " 6844d69dcb1178aa9e04567bce71df1f\n", - " \n", - " \n", - " 94800\n", - " 388556\n", - " 70.0\n", - " False\n", - " 181332\n", - " 17798\n", - " 2023-04-05 03:34:01.855466+02:00\n", - " 2023-04-05 03:34:01.855466+02:00\n", - " 17\n", - " 0.0\n", - " 387864\n", - " 1\n", - " NaN\n", - " NaN\n", - " a0cc8e58412502e24e38dfeded032485\n", - " 17798\n", - " visite scolaire 1h30\n", - " 2021-09-30 08:15:49.172362+02:00\n", - " 2022-02-18 15:55:03.576236+01:00\n", - " NaN\n", - " cfa6ba42e14f2a170a0fc566a183fe94\n", - " \n", - " \n", - " 94801\n", - " 388557\n", - " 0.0\n", - " False\n", - " 181332\n", - " 3126\n", - " 2023-04-05 03:34:01.857441+02:00\n", - " 2023-04-05 03:34:01.857441+02:00\n", - " 9\n", - " 0.0\n", - " 387865\n", - " 1\n", - " NaN\n", - " NaN\n", - " 94532a14d98637ac9ee2b7d9aedad188\n", - " 3126\n", - " nb pers visite scolaire\n", - " 2020-09-03 16:31:39.822413+02:00\n", - " 2022-02-18 15:57:55.792581+01:00\n", - " NaN\n", - " ab5dbcde8e5e1fce29737070bce06799\n", - " \n", - " \n", - " 94802\n", - " 388526\n", - " 5.0\n", - " False\n", - " 181318\n", - " 96\n", - " 2023-04-04 06:06:31.784073+02:00\n", - " 2023-04-04 06:06:31.784073+02:00\n", - " 39\n", - " 0.0\n", - " 387834\n", - " 1\n", - " NaN\n", - " NaN\n", - " 4c1ee03106e34585d57d96da5e7c5f50\n", - " 96\n", - " visite guidée indiv tu\n", - " 2020-09-03 13:21:21.384812+02:00\n", - " 2022-02-18 15:57:55.792581+01:00\n", - " NaN\n", - " 62fd9a5b40c116e45eda51222d135dfd\n", - " \n", " \n", "\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", + " id_products amount is_full_price representation_id pricing_formula_id \\\n", + "0 10682 9.0 False 914 114 \n", + "1 478 9.5 False 273 131 \n", + "2 20873 11.5 False 275 137 \n", + "3 157142 8.0 False 82519 9 \n", + "4 1341 8.5 False 9 93 \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", + " created_at_products updated_at_products \\\n", + "0 2020-09-03 14:09:43.119798+02:00 2020-09-03 14:09:43.119798+02:00 \n", + "1 2020-09-03 13:21:22.711773+02:00 2020-09-03 13:21:22.711773+02:00 \n", + "2 2020-09-03 14:46:33.589030+02:00 2020-09-03 14:46:33.589030+02:00 \n", + "3 2022-01-28 19:29:23.525722+01:00 2022-01-28 19:29:23.525722+01:00 \n", + "4 2020-09-03 13:29:30.773089+02:00 2020-09-03 13:29:30.773089+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", + " category_id apply_price products_group_id product_pack_id \\\n", + "0 41 0.0 10655 1 \n", + "1 1 0.0 471 1 \n", + "2 1 0.0 20825 1 \n", + "3 5 0.0 156773 1 \n", + "4 1 0.0 1175 1 \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", + " extra_field_products amount_consumption identifier_products \\\n", + "0 NaN NaN 35c88f2db8a63d7474e46eb8ca9260e7 \n", + "1 NaN NaN 8a179671ab198e570e6a104c4451379f \n", + "2 NaN NaN ee83779ce29e67ad251e40234b426d6a \n", + "3 NaN NaN d865383579314b791aa4bcf3fb418f17 \n", + "4 NaN NaN f1c4689bc47dee6f60b56d74b593dd46 \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", + " 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", - " 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", + " 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", - " 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]" + " 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 " ] }, - "execution_count": 24, + "execution_count": 75, "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 = (\"\", \"\"))" + "base1.head(5)" + ] + }, + { + "cell_type": "code", + "execution_count": 77, + "id": "d8ef07cf-29a3-40fb-a3d7-bf32a729c053", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "id 0\n", + "percent_price 0\n", + "max_price 0\n", + "min_price 0\n", + "category_id 0\n", + "pricing_formula_id 0\n", + "representation_id 0\n", + "created_at 0\n", + "updated_at 0\n", + "dtype: int64" + ] + }, + "execution_count": 77, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "products_groups.isna().sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 78, + "id": "75be3a30-3114-432d-87d6-697533c3c871", + "metadata": {}, + "outputs": [], + "source": [ + "#Merge2 entre base1 et products_groups\n", + "base2=base1.merge(products_groups, how='left', left_on= 'id_pricing_formula', right_on= 'id', suffixes = (\"_merge2\", \"_product_group\"))" + ] + }, + { + "cell_type": "code", + "execution_count": 81, + "id": "34a169c6-07a8-4ac3-a9e1-d7e7461f7310", + "metadata": {}, + "outputs": [], + "source": [ + "#Merge3 entre base2 et type_of_pricing_formulas\n", + "base3=base2.merge(type_of_pricing_formulas, how='left', left_on= 'id_pricing_formula', right_on= 'pricing_formula_id', suffixes = (\"_merge3\", \"_type_of_pricing_f\"))" + ] + }, + { + "cell_type": "code", + "execution_count": 82, + "id": "508a8082-da34-4d2f-bfa9-9ca7703c3fda", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "id 0\n", + "type_of_id 0\n", + "pricing_formula_id 0\n", + "created_at 0\n", + "updated_at 0\n", + "identifier 0\n", + "dtype: int64" + ] + }, + "execution_count": 82, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "type_of_pricing_formulas.isna().sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 83, + "id": "0e255d11-57eb-47ca-afd3-31f59b8d8822", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "id 0\n", + "amount 0\n", + "is_full_price 0\n", + "representation_id 0\n", + "pricing_formula_id 0\n", + "created_at 0\n", + "updated_at 0\n", + "category_id 0\n", + "apply_price 0\n", + "products_group_id 0\n", + "product_pack_id 0\n", + "extra_field 94803\n", + "amount_consumption 94803\n", + "identifier 0\n", + "dtype: int64" + ] + }, + "execution_count": 83, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "products.isna().sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 84, + "id": "3f034e65-1b33-4908-b7e6-60660ef251c6", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "id 0\n", + "name 1\n", + "type_of 0\n", + "created_at 0\n", + "updated_at 0\n", + "identifier 0\n", + "dtype: int64" + ] + }, + "execution_count": 84, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "product_packs.isna().sum()" + ] + }, + { + "cell_type": "code", + "execution_count": 85, + "id": "f44f40d2-5304-4931-b7e6-fcc06b2657b6", + "metadata": {}, + "outputs": [], + "source": [ + "#Merge4 entre base3 et type_of_pricing_formulas\n", + "base4=base3.merge(product_packs, how='left', left_on= 'product_pack_id', right_on= 'id', suffixes = (\"_merge4\", \"_product_pack\"))" + ] + }, + { + "cell_type": "code", + "execution_count": 87, + "id": "a28772c3-7bc1-46b4-acc8-1388dc60ec98", + "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", + "
id_productsamountis_full_pricerepresentation_id_merge2pricing_formula_id_merge2created_at_productsupdated_at_productscategory_id_merge2apply_priceproducts_group_id...pricing_formula_idcreated_at_type_of_pricing_fupdated_at_type_of_pricing_fidentifier_merge4idname_product_packtype_ofcreated_atupdated_atidentifier_product_pack
0106829.0False9141142020-09-03 14:09:43.119798+02:002020-09-03 14:09:43.119798+02:00410.010655...114.02021-02-15 17:02:27.395376+01:002021-02-15 17:02:27.395376+01:003706121eb9f43b635bef1433c06f679c1NaN02020-09-03 13:11:24.501197+02:002020-09-03 13:11:24.501197+02:00a764b4bf13a360c7ac2a35ec4ca96c95
14789.5False2731312020-09-03 13:21:22.711773+02:002020-09-03 13:21:22.711773+02:0010.0471...131.02021-02-05 11:52:05.923905+01:002021-02-05 11:52:05.923905+01:000aceb248607671792298436004b952751NaN02020-09-03 13:11:24.501197+02:002020-09-03 13:11:24.501197+02:00a764b4bf13a360c7ac2a35ec4ca96c95
22087311.5False2751372020-09-03 14:46:33.589030+02:002020-09-03 14:46:33.589030+02:0010.020825...137.02021-02-05 11:52:05.939898+01:002021-02-05 11:52:05.939898+01:0093002d4637331edd81ffc28b6e8e89c01NaN02020-09-03 13:11:24.501197+02:002020-09-03 13:11:24.501197+02:00a764b4bf13a360c7ac2a35ec4ca96c95
31571428.0False8251992022-01-28 19:29:23.525722+01:002022-01-28 19:29:23.525722+01:0050.0156773...9.02021-02-05 11:52:06.107939+01:002021-02-05 11:52:06.107939+01:007d0b25bdfff9f366da8be820608c81911NaN02020-09-03 13:11:24.501197+02:002020-09-03 13:11:24.501197+02:00a764b4bf13a360c7ac2a35ec4ca96c95
413418.5False9932020-09-03 13:29:30.773089+02:002020-09-03 13:29:30.773089+02:0010.01175...93.02021-02-05 11:52:06.004162+01:002021-02-05 11:52:06.004162+01:001dbb0795e8f47cb75ba7cdb08c06be5f1NaN02020-09-03 13:11:24.501197+02:002020-09-03 13:11:24.501197+02:00a764b4bf13a360c7ac2a35ec4ca96c95
\n", + "

5 rows × 41 columns

\n", + "
" + ], + "text/plain": [ + " id_products amount is_full_price representation_id_merge2 \\\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", + " pricing_formula_id_merge2 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", + " updated_at_products category_id_merge2 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", + " products_group_id ... pricing_formula_id \\\n", + "0 10655 ... 114.0 \n", + "1 471 ... 131.0 \n", + "2 20825 ... 137.0 \n", + "3 156773 ... 9.0 \n", + "4 1175 ... 93.0 \n", + "\n", + " created_at_type_of_pricing_f updated_at_type_of_pricing_f \\\n", + "0 2021-02-15 17:02:27.395376+01:00 2021-02-15 17:02:27.395376+01:00 \n", + "1 2021-02-05 11:52:05.923905+01:00 2021-02-05 11:52:05.923905+01:00 \n", + "2 2021-02-05 11:52:05.939898+01:00 2021-02-05 11:52:05.939898+01:00 \n", + "3 2021-02-05 11:52:06.107939+01:00 2021-02-05 11:52:06.107939+01:00 \n", + "4 2021-02-05 11:52:06.004162+01:00 2021-02-05 11:52:06.004162+01:00 \n", + "\n", + " identifier_merge4 id name_product_pack type_of \\\n", + "0 3706121eb9f43b635bef1433c06f679c 1 NaN 0 \n", + "1 0aceb248607671792298436004b95275 1 NaN 0 \n", + "2 93002d4637331edd81ffc28b6e8e89c0 1 NaN 0 \n", + "3 7d0b25bdfff9f366da8be820608c8191 1 NaN 0 \n", + "4 1dbb0795e8f47cb75ba7cdb08c06be5f 1 NaN 0 \n", + "\n", + " created_at updated_at \\\n", + "0 2020-09-03 13:11:24.501197+02:00 2020-09-03 13:11:24.501197+02:00 \n", + "1 2020-09-03 13:11:24.501197+02:00 2020-09-03 13:11:24.501197+02:00 \n", + "2 2020-09-03 13:11:24.501197+02:00 2020-09-03 13:11:24.501197+02:00 \n", + "3 2020-09-03 13:11:24.501197+02:00 2020-09-03 13:11:24.501197+02:00 \n", + "4 2020-09-03 13:11:24.501197+02:00 2020-09-03 13:11:24.501197+02:00 \n", + "\n", + " identifier_product_pack \n", + "0 a764b4bf13a360c7ac2a35ec4ca96c95 \n", + "1 a764b4bf13a360c7ac2a35ec4ca96c95 \n", + "2 a764b4bf13a360c7ac2a35ec4ca96c95 \n", + "3 a764b4bf13a360c7ac2a35ec4ca96c95 \n", + "4 a764b4bf13a360c7ac2a35ec4ca96c95 \n", + "\n", + "[5 rows x 41 columns]" + ] + }, + "execution_count": 87, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "base4.head(5)" ] }, { "cell_type": "code", "execution_count": null, - "id": "bad94144-2474-49dd-9133-ab6082565ff1", + "id": "03442997-806f-4285-a139-3bad46bb4522", + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d22a0d75-53c5-4b54-9060-c9e7c307fb13", "metadata": {}, "outputs": [], "source": []