{ "data_id": "26", "name": "nursery", "exact_name": "nursery", "version": 1, "version_label": "1", "description": "**Author**: \n**Source**: Unknown - \n**Please cite**: \n\n1. Title: Nursery Database\n \n 2. Sources:\n (a) Creator: Vladislav Rajkovic et al. (13 experts)\n (b) Donors: Marko Bohanec (marko.bohanec@ijs.si)\n Blaz Zupan (blaz.zupan@ijs.si)\n (c) Date: June, 1997\n \n 3. Past Usage:\n \n The hierarchical decision model, from which this dataset is\n derived, was first presented in \n \n M. Olave, V. Rajkovic, M. Bohanec: An application for admission in\n public school systems. In (I. Th. M. Snellen and W. B. H. J. van de\n Donk and J.-P. Baquiast, editors) Expert Systems in Public\n Administration, pages 145-160. Elsevier Science Publishers (North\n Holland)}, 1989.\n \n Within machine-learning, this dataset was used for the evaluation\n of HINT (Hierarchy INduction Tool), which was proved to be able to\n completely reconstruct the original hierarchical model. This,\n together with a comparison with C4.5, is presented in\n \n B. Zupan, M. Bohanec, I. Bratko, J. Demsar: Machine learning by\n function decomposition. ICML-97, Nashville, TN. 1997 (to appear)\n \n 4. Relevant Information Paragraph:\n \n Nursery Database was derived from a hierarchical decision model\n originally developed to rank applications for nursery schools. It\n was used during several years in 1980's when there was excessive\n enrollment to these schools in Ljubljana, Slovenia, and the\n rejected applications frequently needed an objective\n explanation. The final decision depended on three subproblems:\n occupation of parents and child's nursery, family structure and\n financial standing, and social and health picture of the family.\n The model was developed within expert system shell for decision\n making DEX (M. Bohanec, V. Rajkovic: Expert system for decision\n making. Sistemica 1(1), pp. 145-157, 1990.).\n \n The hierarchical model ranks nursery-school applications according\n to the following concept structure:\n \n NURSERY Evaluation of applications for nursery schools\n . EMPLOY Employment of parents and child's nursery\n . . parents Parents' occupation\n . . has_nurs Child's nursery\n . STRUCT_FINAN Family structure and financial standings\n . . STRUCTURE Family structure\n . . . form Form of the family\n . . . children Number of children\n . . housing Housing conditions\n . . finance Financial standing of the family\n . SOC_HEALTH Social and health picture of the family\n . . social Social conditions\n . . health Health conditions\n \n Input attributes are printed in lowercase. Besides the target\n concept (NURSERY) the model includes four intermediate concepts:\n EMPLOY, STRUCT_FINAN, STRUCTURE, SOC_HEALTH. Every concept is in\n the original model related to its lower level descendants by a set\n of examples (for these examples sets see \n http:\/\/www-ai.ijs.si\/BlazZupan\/nursery.html).\n \n The Nursery Database contains examples with the structural\n information removed, i.e., directly relates NURSERY to the eight input\n attributes: parents, has_nurs, form, children, housing, finance,\n social, health.\n \n Because of known underlying concept structure, this database may be\n particularly useful for testing constructive induction and\n structure discovery methods.\n \n 5. Number of Instances: 12960\n (instances completely cover the attribute space)\n \n 6. Number of Attributes: 8\n \n 7. Attribute Values:\n \n parents usual, pretentious, great_pret\n has_nurs proper, less_proper, improper, critical, very_crit\n form complete, completed, incomplete, foster\n children 1, 2, 3, more\n housing convenient, less_conv, critical\n finance convenient, inconv\n social non-prob, slightly_prob, problematic\n health recommended, priority, not_recom\n \n 8. Missing Attribute Values: none\n \n 9. Class Distribution (number of instances per class)\n \n class N N[%]\n ------------------------------\n not_recom 4320 (33.333 %)\n recommend 2 ( 0.015 %)\n very_recom 328 ( 2.531 %)\n priority 4266 (32.917 %)\n spec_prior 4044 (31.204 %)\n\n Information about the dataset\n CLASSTYPE: nominal\n CLASSINDEX: last", "format": "ARFF", "uploader": "Jan van Rijn", "uploader_id": 1, "visibility": "public", "creator": "Vladislav Rajkovic", "contributor": null, "date": "2014-04-06 23:21:23", "update_comment": null, "last_update": "2014-04-06 23:21:23", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/26\/dataset_26_nursery.arff", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 2210, "suggest": { "input": [ "nursery", "1. Title: Nursery Database 2. Sources: (a) Creator: Vladislav Rajkovic et al. (13 experts) (b) Donors: Marko Bohanec (marko.bohanec@ijs.si) Blaz Zupan (blaz.zupan@ijs.si) (c) Date: June, 1997 3. Past Usage: The hierarchical decision model, from which this dataset is derived, was first presented in M. Olave, V. Rajkovic, M. Bohanec: An application for admission in public school systems. In (I. Th. M. Snellen and W. B. H. J. van de Donk and J.-P. Baquiast, editors) Expert Systems in Public Adminis " ], "weight": 5 }, "qualities": { "NumberOfInstances": 12960, "NumberOfFeatures": 9, "NumberOfClasses": 5, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 0, "NumberOfSymbolicFeatures": 9, "Quartile2AttributeEntropy": 1.584962500721156, "REPTreeDepth2ErrRate": 0.05725308641975309, "CfsSubsetEval_kNN1NKappa": 0.9349793625484052, "kNN1NErrRate": 0.03726851851851852, "MajorityClassPercentage": 33.33333333333333, "MeanStdDevOfNumericAtts": null, "Quartile2KurtosisOfNumericAtts": null, "REPTreeDepth2Kappa": 0.9160673294275798, "ClassEntropy": 1.7164959001837932, "kNN1NKappa": 0.9451442926080802, "MajorityClassSize": 4320, "MinAttributeEntropy": 1, "Quartile2MeansOfNumericAtts": null, "REPTreeDepth3AUC": 0.9888642005084899, "DecisionStumpAUC": 0.8283949995939037, "MaxAttributeEntropy": 2.321928094887362, "MinKurtosisOfNumericAtts": null, "Quartile2MutualInformation": 0.020917320958445, "REPTreeDepth3ErrRate": 0.05725308641975309, "DecisionStumpErrRate": 0.3375, "MaxKurtosisOfNumericAtts": null, "MinMeansOfNumericAtts": null, "Quartile2SkewnessOfNumericAtts": null, "REPTreeDepth3Kappa": 0.9160673294275798, "DecisionStumpKappa": 0.49585062240663896, "MaxMeansOfNumericAtts": null, "MinMutualInformation": 0.0043331270252, "PercentageOfBinaryFeatures": 11.11111111111111, "Quartile2StdDevOfNumericAtts": null, "RandomTreeDepth1AUC": 0.9595310356534613, "Dimensionality": 0.0006944444444444445, "MaxMutualInformation": 0.95877496046997, "MinNominalAttDistinctValues": 2, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": 2, "RandomTreeDepth1ErrRate": 0.07461419753086419, "EquivalentNumberOfAtts": 10.630221276614535, "MaxNominalAttDistinctValues": 5, "MinSkewnessOfNumericAtts": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": null, "AutoCorrelation": 0.2393703217840883, "RandomTreeDepth1Kappa": 0.8908430891355607, "J48.00001.AUC": 0.9904979286753883, "MaxSkewnessOfNumericAtts": null, "MinStdDevOfNumericAtts": null, "PercentageOfNumericFeatures": 0, "Quartile3MeansOfNumericAtts": null, "CfsSubsetEval_DecisionStumpAUC": 0.9904979286753883, "RandomTreeDepth2AUC": 0.9595310356534613, "J48.00001.ErrRate": 0.04429012345679012, "MaxStdDevOfNumericAtts": null, "MinorityClassPercentage": 0.015432098765432098, "PercentageOfSymbolicFeatures": 100, "Quartile3MutualInformation": 0.16557061224186498, "CfsSubsetEval_DecisionStumpErrRate": 0.04429012345679012, "RandomTreeDepth2ErrRate": 0.07461419753086419, "J48.00001.Kappa": 0.9349793625484052, "MeanAttributeEntropy": 1.7077222622214983, "MinorityClassSize": 2, "Quartile1AttributeEntropy": 1.584962500721156, "Quartile3SkewnessOfNumericAtts": null, "CfsSubsetEval_DecisionStumpKappa": 0.9349793625484052, "RandomTreeDepth2Kappa": 0.8908430891355607, "J48.0001.AUC": 0.9904979286753883, "MeanKurtosisOfNumericAtts": null, "NaiveBayesAUC": 0.9815006876170533, "Quartile1KurtosisOfNumericAtts": null, "Quartile3StdDevOfNumericAtts": null, "CfsSubsetEval_NaiveBayesAUC": 0.9904979286753883, "RandomTreeDepth3AUC": 0.9595310356534613, "J48.0001.ErrRate": 0.04429012345679012, "MeanMeansOfNumericAtts": null, "NaiveBayesErrRate": 0.09753086419753086, "Quartile1MeansOfNumericAtts": null, "REPTreeDepth1AUC": 0.9888642005084899, "CfsSubsetEval_NaiveBayesErrRate": 0.04429012345679012, "RandomTreeDepth3ErrRate": 0.07461419753086419, "J48.0001.Kappa": 0.9349793625484052, "MeanMutualInformation": 0.16147320507428375, "NaiveBayesKappa": 0.8555371372288022, "Quartile1MutualInformation": 0.0071510516553575, "REPTreeDepth1ErrRate": 0.05725308641975309, "CfsSubsetEval_NaiveBayesKappa": 0.9349793625484052, "RandomTreeDepth3Kappa": 0.8908430891355607, "J48.001.AUC": 0.9904979286753883, "MeanNoiseToSignalRatio": 9.575886330093477, "NumberOfBinaryFeatures": 1, "Quartile1SkewnessOfNumericAtts": null, "REPTreeDepth1Kappa": 0.9160673294275798, "CfsSubsetEval_kNN1NAUC": 0.9904979286753883, "StdvNominalAttDistinctValues": 1.0137937550497031, "J48.001.ErrRate": 0.04429012345679012, "MeanNominalAttDistinctValues": 3.5555555555555554, "Quartile1StdDevOfNumericAtts": null, "REPTreeDepth2AUC": 0.9888642005084899, "CfsSubsetEval_kNN1NErrRate": 0.04429012345679012, "kNN1NAUC": 0.9962435772659771, "J48.001.Kappa": 0.9349793625484052, "MeanSkewnessOfNumericAtts": null }, "tags": [ { "uploader": "38960", "tag": "Education" }, { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "2", "tag": "study_1" }, { "uploader": "1", "tag": "study_37" }, { "uploader": "1", "tag": "study_41" }, { "uploader": "64", "tag": "study_7" }, { "uploader": "1856", "tag": "study_70" }, { "uploader": "1", "tag": "uci" } ], "features": [ { "name": "class", "index": "8", "type": "nominal", "distinct": "5", "missing": "0", "target": "1", "distr": [ [ "not_recom", "recommend", "very_recom", "priority", "spec_prior" ], [ [ "4320", "0", "0", "0", "0" ], [ "0", "2", "0", "0", "0" ], [ "0", "0", "328", "0", "0" ], [ "0", "0", "0", "4266", "0" ], [ "0", "0", "0", "0", "4044" ] ] ] }, { "name": "parents", "index": "0", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "usual", "pretentious", "great_pret" ], [ [ "1440", "2", "196", "1924", "758" ], [ "1440", "0", "132", "1484", "1264" ], [ "1440", "0", "0", "858", "2022" ] ] ] }, { "name": "has_nurs", "index": "1", "type": "nominal", "distinct": "5", "missing": "0", "distr": [ [ "proper", "less_proper", "improper", "critical", "very_crit" ], [ [ "864", "2", "130", "1344", "252" ], [ "864", "0", "132", "1344", "252" ], [ "864", "0", "66", "904", "758" ], [ "864", "0", "0", "464", "1264" ], [ "864", "0", "0", "210", "1518" ] ] ] }, { "name": "form", "index": "2", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "complete", "completed", "incomplete", "foster" ], [ [ "1080", "2", "118", "1152", "888" ], [ "1080", "0", "100", "1092", "968" ], [ "1080", "0", "70", "1038", "1052" ], [ "1080", "0", "40", "984", "1136" ] ] ] }, { "name": "children", "index": "3", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "1", "2", "3", "more" ], [ [ "1080", "2", "148", "1206", "804" ], [ "1080", "0", "100", "1092", "968" ], [ "1080", "0", "40", "984", "1136" ], [ "1080", "0", "40", "984", "1136" ] ] ] }, { "name": "housing", "index": "4", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "convenient", "less_conv", "critical" ], [ [ "1440", "2", "208", "1618", "1052" ], [ "1440", "0", "100", "1396", "1384" ], [ "1440", "0", "20", "1252", "1608" ] ] ] }, { "name": "finance", "index": "5", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "convenient", "inconv" ], [ [ "2160", "2", "218", "2244", "1856" ], [ "2160", "0", "110", "2022", "2188" ] ] ] }, { "name": "social", "index": "6", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "nonprob", "slightly_prob", "problematic" ], [ [ "1440", "1", "164", "1515", "1200" ], [ "1440", "1", "164", "1515", "1200" ], [ "1440", "0", "0", "1236", "1644" ] ] ] }, { "name": "health", "index": "7", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "recommended", "priority", "not_recom" ], [ [ "0", "2", "328", "2412", "1578" ], [ "0", "0", "0", "1854", "2466" ], [ "4320", "0", "0", "0", "0" ] ] ] } ], "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 }