{ "data_id": "42887", "name": "absenteeism-at-work", "exact_name": "absenteeism-at-work", "version": 1, "version_label": null, "description": "The database was created with records of absenteeism at work from July 2007 to July 2010 at a courier company in Brazil. The data set allows for several new combinations of attributes and attribute exclusions, or the modification of the attribute type (categorical, integer, or real) depending on the purpose of the research. The data set (Absenteeism at work - Part I) was used in academic research at the Universidade Nove de Julho - Postgraduate Program in Informatics and Knowledge Management.\n\n### Attribute Information:\n\n1. Individual identification (ID)\n2. Reason for absence (ICD).\nAbsences attested by the International Code of Diseases (ICD) stratified into 21 categories (I to XXI) as follows:\n\nI Certain infectious and parasitic diseases\nII Neoplasms\nIII Diseases of the blood and blood-forming organs and certain disorders involving the immune mechanism\nIV Endocrine, nutritional and metabolic diseases\nV Mental and behavioural disorders\nVI Diseases of the nervous system\nVII Diseases of the eye and adnexa\nVIII Diseases of the ear and mastoid process\nIX Diseases of the circulatory system\nX Diseases of the respiratory system\nXI Diseases of the digestive system\nXII Diseases of the skin and subcutaneous tissue\nXIII Diseases of the musculoskeletal system and connective tissue\nXIV Diseases of the genitourinary system\nXV Pregnancy, childbirth and the puerperium\nXVI Certain conditions originating in the perinatal period\nXVII Congenital malformations, deformations and chromosomal abnormalities\nXVIII Symptoms, signs and abnormal clinical and laboratory findings, not elsewhere classified\nXIX Injury, poisoning and certain other consequences of external causes\nXX External causes of morbidity and mortality\nXXI Factors influencing health status and contact with health services.\n\nAnd 7 categories without (CID) patient follow-up (22), medical consultation (23), blood donation (24), laboratory examination (25), unjustified absence (26), physiotherapy (27), dental consultation (28).\n\n3. Month of absence\n4. Day of the week (Monday (2), Tuesday (3), Wednesday (4), Thursday (5), Friday (6))\n5. Seasons (summer (1), autumn (2), winter (3), spring (4))\n6. Transportation expense\n7. Distance from Residence to Work (kilometers)\n8. Service time\n9. Age\n10. Work load Average\/day\n11. Hit target\n12. Disciplinary failure (yes=1, no=0)\n13. Education (high school (1), graduate (2), postgraduate (3), master and doctor (4))\n14. Son (number of children)\n15. Social drinker (yes=1, no=0)\n16. Social smoker (yes=1, no=0)\n17. Pet (number of pet)\n18. Weight\n19. Height\n20. Body mass index\n21. Absenteeism time in hours (target)", "format": "ARFF", "uploader": "Meilina Reksoprodjo", "uploader_id": 24140, "visibility": "public", "creator": "Andrea Martiniano,Ricardo Pinto Ferreira,Renato Jose Sassi", "contributor": null, "date": "2021-05-19 15:05:30", "update_comment": null, "last_update": "2021-05-19 15:05:30", "licence": "CC0", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/22045518\/Absenteeism_at_work.arff", "default_target_attribute": null, "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "absenteeism-at-work", "The database was created with records of absenteeism at work from July 2007 to July 2010 at a courier company in Brazil. The data set allows for several new combinations of attributes and attribute exclusions, or the modification of the attribute type (categorical, integer, or real) depending on the purpose of the research. The data set (Absenteeism at work - Part I) was used in academic research at the Universidade Nove de Julho - Postgraduate Program in Informatics and Knowledge Management. ## " ], "weight": 5 }, "qualities": { "NumberOfInstances": 740, "NumberOfFeatures": 21, "NumberOfClasses": null, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 14, "NumberOfSymbolicFeatures": 7, "Dimensionality": 0.02837837837837838, "PercentageOfNumericFeatures": 66.66666666666666, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 33.33333333333333, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 3, "PercentageOfBinaryFeatures": 14.285714285714285, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": null, "PercentageOfMissingValues": 0 }, "tags": [ { "uploader": "38960", "tag": "Images" }, { "uploader": "38960", "tag": "Machine Learning" } ], "features": [ { "name": "ID", "index": "0", "type": "nominal", "distinct": "36", "missing": "0", "distr": [] }, { "name": "Reason_for_absence", "index": "1", "type": "nominal", "distinct": "28", "missing": "0", "distr": [] }, { "name": "Month_of_absence", "index": "2", "type": "numeric", "distinct": "13", "missing": "0", "min": "0", "max": "12", "mean": "6", "stdev": "3" }, { "name": "Day_of_the_week", "index": "3", "type": "nominal", "distinct": "5", "missing": "0", "distr": [] }, { "name": "Seasons", "index": "4", "type": "nominal", "distinct": "4", "missing": "0", "distr": [] }, { "name": "Transportation_expense", "index": "5", "type": "numeric", "distinct": "24", "missing": "0", "min": "118", "max": "388", "mean": "221", "stdev": "67" }, { "name": "Distance_from_Residence_to_Work", "index": "6", "type": "numeric", "distinct": "25", "missing": "0", "min": "5", "max": "52", "mean": "30", "stdev": "15" }, { "name": "Service_time", "index": "7", "type": "numeric", "distinct": "18", "missing": "0", "min": "1", "max": "29", "mean": "13", "stdev": "4" }, { "name": "Age", "index": "8", "type": "numeric", "distinct": "22", "missing": "0", "min": "27", "max": "58", "mean": "36", "stdev": "6" }, { "name": "Work_load_Average\/day_", "index": "9", "type": "numeric", "distinct": "38", "missing": "0", "min": "205917", "max": "378884", "mean": "271490", "stdev": "39058" }, { "name": "Hit_target", "index": "10", "type": "numeric", "distinct": "13", "missing": "0", "min": "81", "max": "100", "mean": "95", "stdev": "4" }, { "name": "Disciplinary_failure", "index": "11", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] }, { "name": "Education", "index": "12", "type": "numeric", "distinct": "4", "missing": "0", "min": "1", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Son", "index": "13", "type": "numeric", "distinct": "5", "missing": "0", "min": "0", "max": "4", "mean": "1", "stdev": "1" }, { "name": "Social_drinker", "index": "14", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] }, { "name": "Social_smoker", "index": "15", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] }, { "name": "Pet", "index": "16", "type": "numeric", "distinct": "6", "missing": "0", "min": "0", "max": "8", "mean": "1", "stdev": "1" }, { "name": "Weight", "index": "17", "type": "numeric", "distinct": "26", "missing": "0", "min": "56", "max": "108", "mean": "79", "stdev": "13" }, { "name": "Height", "index": "18", "type": "numeric", "distinct": "14", "missing": "0", "min": "163", "max": "196", "mean": "172", "stdev": "6" }, { "name": "Body_mass_index", "index": "19", "type": "numeric", "distinct": "17", "missing": "0", "min": "19", "max": "38", "mean": "27", "stdev": "4" }, { "name": "Absenteeism_time_in_hours", "index": "20", "type": "numeric", "distinct": "19", "missing": "0", "min": "0", "max": "120", "mean": "7", "stdev": "13" } ], "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 }