Outils pour utilisateurs

Outils du site


nsi:datasets:income

Dataset : Revenus

Présentation

Données issues d'un recensement américain de 1994.

On donne des informations détaillées pour chaque individu. On peut essayer de prédire si le revenu annuel de l'individu est supérieur à 50K$.

Colonnes

  • age en années
  • workclass parmi Private, Self-emp-not-inc, Self-emp-inc, Federal-gov, Local-gov, State-gov, Without-pay, Never-worked.
  • fnlwgt : final weigth. Il s'agit d'un indice attribué par les services de recensement américains. L'idée est que deux personnes ayant à peu près le même indice sont susceptibles d'avoir des conditions sociales équivalentes.
  • education, le niveau d'étude. Parmi : Bachelors, Some-college, 11th, HS-grad, Prof-school, Assoc-acdm, Assoc-voc, 9th, 7th-8th, 12th, Masters, 1st-4th, 10th, Doctorate, 5th-6th, Preschool.
  • education-num : nombre d'années d'études
  • marital-status : statut matrimonial. Parmi : Married-civ-spouse, Divorced, Never-married, Separated, Widowed, Married-spouse-absent, Married-AF-spouse.
  • occupation : emploi. Parmi : Tech-support, Craft-repair, Other-service, Sales, Exec-managerial, Prof-specialty, Handlers-cleaners, Machine-op-inspct, Adm-clerical, Farming-fishing, Transport-moving, Priv-house-serv, Protective-serv, Armed-Forces.
  • relationship L'individu est-il un mari, un parent… Parmi : Wife, Own-child, Husband, Not-in-family, Other-relative, Unmarried.
  • race : un peu surprenant en France, mais c'est une étude statistique américaine. Parmi : White, Asian-Pac-Islander, Amer-Indian-Eskimo, Other, Black.
  • sex : genre. Female ou Male.
  • capital-gain
  • capital-loss
  • hours-per-week : nombre d'heures travaillées
  • native-country : pays d'origine.
  • state réponse à la question. <=50K ou >50K

Tables

Entraînement

32561 individus – income.train.csv

ageworkclassfnlwgteducationeducation-nummarital-statusoccupationrelationshipracesexcapital-gaincapital-losshours-per-weeknative-countrystate
39State-gov77516Bachelors13Never-marriedAdm-clericalNot-in-familyWhiteMale2174040United-States<=50K
50Self-emp-not-inc83311Bachelors13Married-civ-spouseExec-managerialHusbandWhiteMale0013United-States<=50K
38Private215646HS-grad9DivorcedHandlers-cleanersNot-in-familyWhiteMale0040United-States<=50K
53Private23472111th7Married-civ-spouseHandlers-cleanersHusbandBlackMale0040United-States<=50K
28Private338409Bachelors13Married-civ-spouseProf-specialtyWifeBlackFemale0040Cuba<=50K
37Private284582Masters14Married-civ-spouseExec-managerialWifeWhiteFemale0040United-States<=50K
49Private1601879th5Married-spouse-absentOther-serviceNot-in-familyBlackFemale0016Jamaica<=50K
52Self-emp-not-inc209642HS-grad9Married-civ-spouseExec-managerialHusbandWhiteMale0045United-States>50K
31Private45781Masters14Never-marriedProf-specialtyNot-in-familyWhiteFemale14084050United-States>50K
42Private159449Bachelors13Married-civ-spouseExec-managerialHusbandWhiteMale5178040United-States>50K

Test

16281 individus – income.test.csv

ageworkclassfnlwgteducationeducation-nummarital-statusoccupationrelationshipracesexcapital-gaincapital-losshours-per-weeknative-countrystate
25Private22680211th7Never-marriedMachine-op-inspctOwn-childBlackMale0040United-States<=50K
38Private89814HS-grad9Married-civ-spouseFarming-fishingHusbandWhiteMale0050United-States<=50K
28Local-gov336951Assoc-acdm12Married-civ-spouseProtective-servHusbandWhiteMale0040United-States>50K
44Private160323Some-college10Married-civ-spouseMachine-op-inspctHusbandBlackMale7688040United-States>50K
18?103497Some-college10Never-married?Own-childWhiteFemale0030United-States<=50K
34Private19869310th6Never-marriedOther-serviceNot-in-familyWhiteMale0030United-States<=50K
29?227026HS-grad9Never-married?UnmarriedBlackMale0040United-States<=50K
63Self-emp-not-inc104626Prof-school15Married-civ-spouseProf-specialtyHusbandWhiteMale3103032United-States>50K
24Private369667Some-college10Never-marriedOther-serviceUnmarriedWhiteFemale0040United-States<=50K
55Private1049967th-8th4Married-civ-spouseCraft-repairHusbandWhiteMale0010United-States<=50K
nsi/datasets/income.txt · Dernière modification : de goupillwiki