{ "data_id": "1511", "name": "wholesale-customers", "exact_name": "wholesale-customers", "version": 1, "version_label": null, "description": "**Author**: Margarida G. M. S. Cardoso \n**Source**: UCI \n**Please cite**: Abreu, N. (2011). Analise do perfil do cliente Recheio e desenvolvimento de um sistema promocional. Mestrado em Marketing, ISCTE-IUL, Lisbon. \n\n* Title: \nWholesale customers Data Set \n\n* Abstract: \nThe data set refers to clients of a wholesale distributor. It includes the annual spending in monetary units (m.u.) on diverse product categories\n\n* Source: \nMargarida G. M. S. Cardoso, margarida.cardoso '@' iscte.pt, ISCTE-IUL, Lisbon, Portugal\n\n* Attribute Information:\n\n1) FRESH: annual spending (m.u.) on fresh products (Continuous); \n2) MILK: annual spending (m.u.) on milk products (Continuous); \n3) GROCERY: annual spending (m.u.)on grocery products (Continuous); \n4) FROZEN: annual spending (m.u.)on frozen products (Continuous) \n5) DETERGENTS_PAPER: annual spending (m.u.) on detergents and paper products (Continuous) \n6) DELICATESSEN: annual spending (m.u.)on and delicatessen products (Continuous); \n7) CHANNEL: customers' Channel - Horeca (Hotel\/Restaurant\/Caf\u00e9) or Retail channel (Nominal) \n8) REGION: customers' Region - Lisbon, Porto or Other (Nominal) \n\nDescriptive Statistics: \n\n(Minimum, Maximum, Mean, Std. Deviation) \nFRESH ( 3, 112151, 12000.30, 12647.329) \nMILK (55, 73498, 5796.27, 7380.377) \nGROCERY (3, 92780, 7951.28, 9503.163) \nFROZEN (25, 60869, 3071.93, 4854.673) \nDETERGENTS_PAPER (3, 40827, 2881.49, 4767.854) \nDELICATESSEN (3, 47943, 1524.87, 2820.106) \n\nREGION Frequency \nLisbon 77 \nOporto 47 \nOther Region 316 \nTotal 440 \n\nCHANNEL Frequency \nHoreca 298 \nRetail 142 \nTotal 440 \n\n\n* Relevant Papers:\n\nCardoso, Margarida G.M.S. (2013). Logical discriminant models \u00e2\u20ac\u201c Chapter 8 in Quantitative Modeling in Marketing and Management Edited by Luiz Moutinho and Kun-Huang Huarng. World Scientific. p. 223-253. ISBN 978-9814407717 \n\nJean-Patrick Baudry, Margarida Cardoso, Gilles Celeux, Maria Jos\u00c3\u00a9 Amorim, Ana Sousa Ferreira (2012). Enhancing the selection of a model-based clustering with external qualitative variables. RESEARCH REPORT N\u00c2\u00b0 8124, October 2012, Project-Team SELECT. INRIA Saclay - \u00c3\u017dle-de-France, Projet select, Universit\u00c3\u00a9 Paris-Sud 11 \n", "format": "ARFF", "uploader": "Rafael Gomes Mantovani", "uploader_id": 64, "visibility": "public", "creator": null, "contributor": null, "date": "2015-05-26 17:15:57", "update_comment": null, "last_update": "2015-11-11 13:32:22", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/1681131\/phpfKh1CO", "default_target_attribute": "Channel", "row_id_attribute": null, "ignore_attribute": null, "runs": 161, "suggest": { "input": [ "wholesale-customers", "* Title: Wholesale customers Data Set * Abstract: The data set refers to clients of a wholesale distributor. It includes the annual spending in monetary units (m.u.) on diverse product categories * Source: Margarida G. M. S. Cardoso, margarida.cardoso '@' iscte.pt, ISCTE-IUL, Lisbon, Portugal * Attribute Information: 1) FRESH: annual spending (m.u.) on fresh products (Continuous); 2) MILK: annual spending (m.u.) on milk products (Continuous); 3) GROCERY: annual spending (m.u.)on grocery products " ], "weight": 5 }, "qualities": { "NumberOfInstances": 440, "NumberOfFeatures": 9, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 7, "NumberOfSymbolicFeatures": 2, "REPTreeDepth3Kappa": 0.7887884606378496, "DecisionStumpKappa": 0.8101380813953489, "MaxMeansOfNumericAtts": 12000.297727272726, "MinMutualInformation": 0.00731333291057, "Quartile2SkewnessOfNumericAtts": 3.6318506306913623, "RandomTreeDepth1AUC": 0.8597929861045468, "Dimensionality": 0.020454545454545454, "MaxMutualInformation": 0.00731333291057, "MinNominalAttDistinctValues": 2, "PercentageOfBinaryFeatures": 11.11111111111111, "Quartile2StdDevOfNumericAtts": 4854.673332592367, "RandomTreeDepth1ErrRate": 0.125, "EquivalentNumberOfAtts": 124.06417925790393, "MaxNominalAttDistinctValues": 3, "MinSkewnessOfNumericAtts": -1.283626930042065, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": 1.127716631510294, "RandomTreeDepth1Kappa": 0.7156286721504113, "J48.00001.AUC": 0.8808842990830892, "MaxSkewnessOfNumericAtts": 11.151586478906099, "MinStdDevOfNumericAtts": 0.7742724492300995, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 54.689280697372475, "AutoCorrelation": 0.6150341685649203, "RandomTreeDepth2AUC": 0.8597929861045468, "J48.00001.ErrRate": 0.10681818181818181, "MaxStdDevOfNumericAtts": 12647.328865076894, "MinorityClassPercentage": 32.27272727272727, "PercentageOfNumericFeatures": 77.77777777777779, "Quartile3MeansOfNumericAtts": 7951.277272727267, "CfsSubsetEval_DecisionStumpAUC": 0.89266471311088, "RandomTreeDepth2ErrRate": 0.125, "J48.00001.Kappa": 0.7551967422699939, "MeanAttributeEntropy": 1.127716631510294, "MinorityClassSize": 142, "PercentageOfSymbolicFeatures": 22.22222222222222, "Quartile3MutualInformation": 0.00731333291057, "CfsSubsetEval_DecisionStumpErrRate": 0.09545454545454546, "RandomTreeDepth2Kappa": 0.7156286721504113, "J48.0001.AUC": 0.8808842990830892, "MeanKurtosisOfNumericAtts": 43.059150023887035, "NaiveBayesAUC": 0.9188554297106619, "Quartile1AttributeEntropy": 1.127716631510294, "Quartile3SkewnessOfNumericAtts": 5.907985692455953, "CfsSubsetEval_DecisionStumpKappa": 0.7855949508074995, "RandomTreeDepth3AUC": 0.8597929861045468, "J48.0001.ErrRate": 0.10681818181818181, "MeanMeansOfNumericAtts": 4746.95422077922, "NaiveBayesErrRate": 0.11136363636363636, "Quartile1KurtosisOfNumericAtts": 11.536408493056028, "Quartile3StdDevOfNumericAtts": 9503.162828994346, "CfsSubsetEval_NaiveBayesAUC": 0.89266471311088, "RandomTreeDepth3ErrRate": 0.125, "J48.0001.Kappa": 0.7551967422699939, "MeanMutualInformation": 0.00731333291057, "NaiveBayesKappa": 0.7428803129323094, "Quartile1MeansOfNumericAtts": 1524.8704545454557, "REPTreeDepth1AUC": 0.9388292844314208, "CfsSubsetEval_NaiveBayesErrRate": 0.09545454545454546, "RandomTreeDepth3Kappa": 0.7156286721504113, "J48.001.AUC": 0.8808842990830892, "MeanNoiseToSignalRatio": 153.20009526441754, "NumberOfBinaryFeatures": 1, "Quartile1MutualInformation": 0.00731333291057, "REPTreeDepth1ErrRate": 0.09318181818181819, "CfsSubsetEval_NaiveBayesKappa": 0.7855949508074995, "CfsSubsetEval_kNN1NAUC": 0.89266471311088, "StdvNominalAttDistinctValues": 0.7071067811865476, "J48.001.ErrRate": 0.10681818181818181, "MeanNominalAttDistinctValues": 2.5, "Quartile1SkewnessOfNumericAtts": 2.5613227519279333, "REPTreeDepth1Kappa": 0.7887884606378496, "CfsSubsetEval_kNN1NErrRate": 0.09545454545454546, "kNN1NAUC": 0.8686785140372437, "J48.001.Kappa": 0.7551967422699939, "MeanSkewnessOfNumericAtts": 4.230043166220242, "Quartile1StdDevOfNumericAtts": 2820.1059373693975, "REPTreeDepth2AUC": 0.9388292844314208, "CfsSubsetEval_kNN1NKappa": 0.7855949508074995, "kNN1NErrRate": 0.12045454545454545, "MajorityClassPercentage": 67.72727272727272, "MeanStdDevOfNumericAtts": 5996.325265565326, "Quartile2AttributeEntropy": 1.127716631510294, "REPTreeDepth2ErrRate": 0.09318181818181819, "ClassEntropy": 0.9073226451896848, "kNN1NKappa": 0.7279641640614063, "MajorityClassSize": 298, "MinAttributeEntropy": 1.127716631510294, "Quartile2KurtosisOfNumericAtts": 20.91467039091964, "REPTreeDepth2Kappa": 0.7887884606378496, "REPTreeDepth3AUC": 0.9388292844314208, "DecisionStumpAUC": 0.9147840060497211, "MaxAttributeEntropy": 1.127716631510294, "MinKurtosisOfNumericAtts": -0.10011083477068317, "Quartile2MeansOfNumericAtts": 3071.9318181818194, "REPTreeDepth3ErrRate": 0.09318181818181819, "DecisionStumpErrRate": 0.08636363636363636, "MaxKurtosisOfNumericAtts": 170.69493933454055, "MinMeansOfNumericAtts": 2.5431818181818167, "Quartile2MutualInformation": 0.00731333291057 }, "tags": [ { "uploader": "38960", "tag": "Chemistry" }, { "uploader": "38960", "tag": "Life Science" }, { "uploader": "3886", "tag": "mf_less_than_80" }, { "uploader": "3886", "tag": "study_123" }, { "uploader": "64", "tag": "study_52" }, { "uploader": "64", "tag": "study_7" }, { "uploader": "4209", "tag": "study_88" } ], "features": [ { "name": "Channel", "index": "7", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "1", "2" ], [ [ "298", "0" ], [ "0", "142" ] ] ] }, { "name": "V1", "index": "0", "type": "numeric", "distinct": "3", "missing": "0", "min": "1", "max": "3", "mean": "3", "stdev": "1" }, { "name": "V2", "index": "1", "type": "numeric", "distinct": "433", "missing": "0", "min": "3", "max": "112151", "mean": "12000", "stdev": "12647" }, { "name": "V3", "index": "2", "type": "numeric", "distinct": "421", "missing": "0", "min": "55", "max": "73498", "mean": "5796", "stdev": "7380" }, { "name": "V4", "index": "3", "type": "numeric", "distinct": "430", "missing": "0", "min": "3", "max": "92780", "mean": "7951", "stdev": "9503" }, { "name": "V5", "index": "4", "type": "numeric", "distinct": "426", "missing": "0", "min": "25", "max": "60869", "mean": "3072", "stdev": "4855" }, { "name": "V6", "index": "5", "type": "numeric", "distinct": "417", "missing": "0", "min": "3", "max": "40827", "mean": "2881", "stdev": "4768" }, { "name": "V7", "index": "6", "type": "numeric", "distinct": "403", "missing": "0", "min": "3", "max": "47943", "mean": "1525", "stdev": "2820" }, { "name": "Region", "index": "8", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "59", "18" ], [ "28", "19" ], [ "211", "105" ] ] ] } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 0, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 0 }