From 1ec5b8743f35fdce36b1b8d2c67a72da7ad621e8 Mon Sep 17 00:00:00 2001 From: frodrigue-ensae Date: Tue, 5 Mar 2024 01:44:01 +0000 Subject: [PATCH] code --- code_base_train_test.ipynb | 464 +++++-------------------------------- 1 file changed, 55 insertions(+), 409 deletions(-) diff --git a/code_base_train_test.ipynb b/code_base_train_test.ipynb index b7e6578..23cdb2d 100644 --- a/code_base_train_test.ipynb +++ b/code_base_train_test.ipynb @@ -310,7 +310,50 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 10, + "id": "f8546992-f425-4d1e-ad75-ad26a8052a18", + "metadata": {}, + "outputs": [ + { + "ename": "NameError", + "evalue": "name 'projet' is not defined", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[0;32mIn[10], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mprojet\u001b[49m\u001b[38;5;241m-\u001b[39mbdc2324\u001b[38;5;241m-\u001b[39mteam1\u001b[38;5;241m/\u001b[39mGeneralization\u001b[38;5;241m/\u001b[39mmusique\u001b[38;5;241m/\u001b[39mTrain_test\n", + "\u001b[0;31mNameError\u001b[0m: name 'projet' is not defined" + ] + } + ], + "source": [ + "projet-bdc2324-team1/Generalization/musique/Train_test" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "0dd34710-6da2-4438-9e1d-0ac092c1d28c", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "(343126, 41)" + ] + }, + "execution_count": 12, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "dataset_train.shape" + ] + }, + { + "cell_type": "code", + "execution_count": 9, "id": "a3bfeeb6-2db0-4f1d-866c-8721343e97c5", "metadata": {}, "outputs": [ @@ -361,7 +404,7 @@ "dtype: float64" ] }, - "execution_count": 6, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -372,422 +415,25 @@ }, { "cell_type": "code", - "execution_count": 7, - "id": "a4c4e994-231b-4467-aa1b-0a5283c59dd5", + "execution_count": 8, + "id": "75f9a672-641f-49a2-a8d6-7673845506f5", "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", - "
customer_idnb_ticketsnb_purchasestotal_amountnb_suppliersvente_internet_maxpurchase_date_minpurchase_date_maxtime_between_purchasenb_tickets_internet...gender_labelgender_femalegender_malegender_othercountry_frhas_tagsnb_campaignsnb_campaigns_openedtime_to_openy_has_purchased
014_12.02.070.01.01.01464.9384491464.9380210.0004282.0...other0011.009.01.00 days 00:36:13NaN
114_27.03.0145.02.01.01466.030116365.3350001100.6951167.0...male0101.019.04.00 days 02:30:09.250000NaN
214_32.02.070.01.01.01476.9078941476.9076620.0002312.0...female1001.006.01.00 days 20:58:45NaN
314_42.02.032.01.01.01465.9078941465.9074650.0004282.0...male0101.006.00.0NaTNaN
414_52.02.070.01.01.01465.3738661465.3738190.0000462.0...female1001.007.00.0NaTNaN
..................................................................
34312114_68847480.00.00.00.00.0NaNNaNNaN0.0...male0101.000.00.0NaTNaN
34312214_68847490.00.00.00.00.0NaNNaNNaN0.0...male0101.000.00.0NaTNaN
34312314_68847500.00.00.00.00.0NaNNaNNaN0.0...male0101.000.00.0NaTNaN
34312414_68847510.00.00.00.00.0NaNNaNNaN0.0...female1001.000.00.0NaTNaN
34312514_68847530.00.00.00.00.0NaNNaNNaN0.0...male0101.000.00.0NaTNaN
\n", - "

343126 rows Ă— 41 columns

\n", - "
" - ], - "text/plain": [ - " customer_id nb_tickets nb_purchases total_amount nb_suppliers \\\n", - "0 14_1 2.0 2.0 70.0 1.0 \n", - "1 14_2 7.0 3.0 145.0 2.0 \n", - "2 14_3 2.0 2.0 70.0 1.0 \n", - "3 14_4 2.0 2.0 32.0 1.0 \n", - "4 14_5 2.0 2.0 70.0 1.0 \n", - "... ... ... ... ... ... \n", - "343121 14_6884748 0.0 0.0 0.0 0.0 \n", - "343122 14_6884749 0.0 0.0 0.0 0.0 \n", - "343123 14_6884750 0.0 0.0 0.0 0.0 \n", - "343124 14_6884751 0.0 0.0 0.0 0.0 \n", - "343125 14_6884753 0.0 0.0 0.0 0.0 \n", - "\n", - " vente_internet_max purchase_date_min purchase_date_max \\\n", - "0 1.0 1464.938449 1464.938021 \n", - "1 1.0 1466.030116 365.335000 \n", - "2 1.0 1476.907894 1476.907662 \n", - "3 1.0 1465.907894 1465.907465 \n", - "4 1.0 1465.373866 1465.373819 \n", - "... ... ... ... \n", - "343121 0.0 NaN NaN \n", - "343122 0.0 NaN NaN \n", - "343123 0.0 NaN NaN \n", - "343124 0.0 NaN NaN \n", - "343125 0.0 NaN NaN \n", - "\n", - " time_between_purchase nb_tickets_internet ... gender_label \\\n", - "0 0.000428 2.0 ... other \n", - "1 1100.695116 7.0 ... male \n", - "2 0.000231 2.0 ... female \n", - "3 0.000428 2.0 ... male \n", - "4 0.000046 2.0 ... female \n", - "... ... ... ... ... \n", - "343121 NaN 0.0 ... male \n", - "343122 NaN 0.0 ... male \n", - "343123 NaN 0.0 ... male \n", - "343124 NaN 0.0 ... female \n", - "343125 NaN 0.0 ... male \n", - "\n", - " gender_female gender_male gender_other country_fr has_tags \\\n", - "0 0 0 1 1.0 0 \n", - "1 0 1 0 1.0 1 \n", - "2 1 0 0 1.0 0 \n", - "3 0 1 0 1.0 0 \n", - "4 1 0 0 1.0 0 \n", - "... ... ... ... ... ... \n", - "343121 0 1 0 1.0 0 \n", - "343122 0 1 0 1.0 0 \n", - "343123 0 1 0 1.0 0 \n", - "343124 1 0 0 1.0 0 \n", - "343125 0 1 0 1.0 0 \n", - "\n", - " nb_campaigns nb_campaigns_opened time_to_open \\\n", - "0 9.0 1.0 0 days 00:36:13 \n", - "1 9.0 4.0 0 days 02:30:09.250000 \n", - "2 6.0 1.0 0 days 20:58:45 \n", - "3 6.0 0.0 NaT \n", - "4 7.0 0.0 NaT \n", - "... ... ... ... \n", - "343121 0.0 0.0 NaT \n", - "343122 0.0 0.0 NaT \n", - "343123 0.0 0.0 NaT \n", - "343124 0.0 0.0 NaT \n", - "343125 0.0 0.0 NaT \n", - "\n", - " y_has_purchased \n", - "0 NaN \n", - "1 NaN \n", - "2 NaN \n", - "3 NaN \n", - "4 NaN \n", - "... ... \n", - "343121 NaN \n", - "343122 NaN \n", - "343123 NaN \n", - "343124 NaN \n", - "343125 NaN \n", - "\n", - "[343126 rows x 41 columns]" - ] - }, - "execution_count": 7, - "metadata": {}, - "output_type": "execute_result" - } - ], + "outputs": [], "source": [ - "dataset_test" + "#Creation de la variable dependante fictive: 1 si l'individu a effectué un achat au cours de la periode de train et 0 sinon\n", + "\n", + "dataset_train_modif=dataset_train\n" ] }, { "cell_type": "code", "execution_count": null, - "id": "75f9a672-641f-49a2-a8d6-7673845506f5", + "id": "c121c1e2-d8e4-4b93-a882-9385581b63c9", "metadata": {}, "outputs": [], - "source": [] + "source": [ + "dataset_train_modif[\"" + ] } ], "metadata": {