Census-Income (KDD) data set

1: Description.

The Census data set was extracted in 1994 from census data of the United States. It contains continuous and nominal attributes, describing some social information
(age, race, sex, marital status, ...) about the citizens registered. The task is to predict whether the citizen’s income exceeds fifty thousand dollars a year.

This data set is an extended version of the Adult data set. It has four times its number of instances, and three times its number of attributes.

2: Type.			Classification	
3: Origin.			Real World
4: Instances.		142521 (299284)
5: Features.		41
6: Classes.			3	
7: Missing values.	Yes

8: Header.

@relation census
@attribute Atr-0 integer[0,90]
@attribute Atr-1 {Self-employed-not_incorporated,Not_in_universe,Private,Local_government,Federal_government,Self-employed-incorporated,State_government,Never_worked,Without_pay}
@attribute Atr-2 integer[0,51]
@attribute Atr-3 integer[0,46]
@attribute Atr-4 {Some_college_but_no_degree,10th_grade,Children,Bachelors_degree(BA_AB_BS),High_school_graduate,Masters_degree(MA_MS_MEng_MEd_MSW_MBA),Less_than_1st_grade,Associates_degree-academic_program,7th_and_8th_grade,12th_grade_no_diploma,Associates_degree-occup_/vocational,Prof_school_degree_(MD_DDS_DVM_LLB_JD),5th_or_6th_grade,11th_grade,Doctorate_degree(PhD_EdD),9th_grade,1st_2nd_3rd_or_4th_grade}
@attribute Atr-5 integer[0,9999]
@attribute Atr-6 {Not_in_universe,High_school,College_or_university}
@attribute Atr-7 {Divorced,Never_married,Married-civilian_spouse_present,Widowed,Separated,Married-spouse_absent,Married-A_F_spouse_present}
@attribute Atr-8 {Construction,Not_in_universe_or_children,Entertainment,Finance_insurance_and_real_estate,Education,Business_and_repair_services,Manufacturing-nondurable_goods,Personal_services_except_private_HH,Manufacturing-durable_goods,Other_professional_services,Mining,Transportation,Wholesale_trade,Public_administration,Retail_trade,Social_services,Private_household_services,Utilities_and_sanitary_services,Communications,Hospital_services,Medical_except_hospital,Agriculture,Forestry_and_fisheries,Armed_Forces}
@attribute Atr-9 {Precision_production_craft_&_repair,Not_in_universe,Professional_specialty,Executive_admin_and_managerial,Handlers_equip_cleaners_etc,Adm_support_including_clerical,Machine_operators_assmblrs_&_inspctrs,Other_service,Sales,Private_household_services,Technicians_and_related_support,Transportation_and_material_moving,Farming_forestry_and_fishing,Protective_services,Armed_Forces}
@attribute Atr-10 {White,Asian_or_Pacific_Islander,Amer_Indian_Aleut_or_Eskimo,Black,Other}
@attribute Atr-11 {All_other,Do_not_know,Central_or_South_American,Mexican_(Mexicano),Mexican-American,Other_Spanish,Puerto_Rican,Cuban,Chicano,NA}
@attribute Atr-12 {Male,Female}
@attribute Atr-13 {Not_in_universe,No,Yes}
@attribute Atr-14 {Not_in_universe,Job_loser_-_on_layoff,Other_job_loser,New_entrant,Re-entrant,Job_leaver}
@attribute Atr-15 {Children_or_Armed_Forces,Not_in_labor_force,Full-time_schedules,Unemployed_full-time,Unemployed_part-_time,PT_for_non-econ_reasons_usually_FT,PT_for_econ_reasons_usually_PT,PT_for_econ_reasons_usually_FT}
@attribute Atr-16 integer[0,99999]
@attribute Atr-17 integer[0,4608]
@attribute Atr-18 integer[0,99999]
@attribute Atr-19 {Head_of_household,Nonfiler,Joint_both_under_65,Single,Joint_both_65+,Joint_one_under_65_&_one_65+}
@attribute Atr-20 {South,Not_in_universe,Northeast,Midwest,West,Abroad}
@attribute Atr-21 {Arkansas,Not_in_universe,Utah,Michigan,Minnesota,Alaska,Kansas,Indiana,Massachusetts,New_Mexico,Nevada,Tennessee,Colorado,Abroad,Kentucky,California,Arizona,North_Carolina,Connecticut,Florida,Vermont,Maryland,Oklahoma,Oregon,Ohio,South_Carolina,Texas,Montana,Wyoming,Georgia,Pennsylvania,Iowa,New_Hampshire,Missouri,Alabama,North_Dakota,New_Jersey,Louisiana,West_Virginia,Delaware,Illinois,Maine,Wisconsin,New_York,Idaho,District_of_Columbia,South_Dakota,Nebraska,Virginia,Mississippi}
@attribute Atr-22 {Householder,Child_18+_never_marr_Not_in_a_subfamily,Child_<18_never_marr_not_in_subfamily,Spouse_of_householder,Secondary_individual,Other_Rel_18+_never_marr_not_in_subfamily,Nonfamily_householder,Grandchild_<18_never_marr_not_in_subfamily,Grandchild_<18_never_marr_child_of_subfamily_RP,Child_18+_ever_marr_Not_in_a_subfamily,Child_18+_never_marr_RP_of_subfamily,Child_18+_spouse_of_subfamily_RP,Other_Rel_<18_never_marr_child_of_subfamily_RP,Child_under_18_of_RP_of_unrel_subfamily,Grandchild_18+_never_marr_not_in_subfamily,Child_18+_ever_marr_RP_of_subfamily,Other_Rel_18+_ever_marr_RP_of_subfamily,Other_Rel_18+_ever_marr_not_in_subfamily,RP_of_unrelated_subfamily,Other_Rel_18+_spouse_of_subfamily_RP,Other_Rel_<18_never_marr_not_in_subfamily,Other_Rel_<18_spouse_of_subfamily_RP,In_group_quarters,Grandchild_18+_spouse_of_subfamily_RP,Other_Rel_18+_never_marr_RP_of_subfamily,Child_<18_never_marr_RP_of_subfamily,Child_<18_ever_marr_not_in_subfamily,Other_Rel_<18_ever_marr_RP_of_subfamily,Grandchild_18+_ever_marr_not_in_subfamily,Child_<18_spouse_of_subfamily_RP,Spouse_of_RP_of_unrelated_subfamily,Other_Rel_<18_never_married_RP_of_subfamily,Grandchild_18+_never_marr_RP_of_subfamily,Grandchild_18+_ever_marr_RP_of_subfamily,Child_<18_ever_marr_RP_of_subfamily,Other_Rel_<18_ever_marr_not_in_subfamily,Grandchild_<18_never_marr_RP_of_subfamily,Grandchild_<18_ever_marr_not_in_subfamily}
@attribute Atr-23 {Householder,Child_18_or_older,Child_under_18_never_married,Spouse_of_householder,Nonrelative_of_householder,Other_relative_of_householder,Group_Quarters-_Secondary_individual,Child_under_18_ever_married}
@attribute Atr-24 real[37.87,18656.3]
@attribute Atr-25 {MSA_to_MSA,Nonmover,NonMSA_to_nonMSA,Not_in_universe,Not_identifiable,Abroad_to_MSA,MSA_to_nonMSA,Abroad_to_nonMSA,NonMSA_to_MSA}
@attribute Atr-26 {Same_county,Nonmover,Different_region,Different_county_same_state,Not_in_universe,Different_division_same_region,Abroad,Different_state_same_division}
@attribute Atr-27 {Same_county,Nonmover,Different_state_in_South,Different_county_same_state,Not_in_universe,Different_state_in_Northeast,Abroad,Different_state_in_Midwest,Different_state_in_West}
@attribute Atr-28 {No,Not_in_universe_under_1_year_old,Yes}
@attribute Atr-29 {Yes,Not_in_universe,No}
@attribute Atr-30 integer[0,6]
@attribute Atr-31 {Not_in_universe,Both_parents_present,Mother_only_present,Neither_parent_present,Father_only_present}
@attribute Atr-32 {United-States,Vietnam,Philippines,Columbia,Germany,Mexico,Japan,Peru,Dominican-Republic,South_Korea,Cuba,El-Salvador,Canada,Scotland,Outlying-U_S_(Guam_USVI_etc),Italy,Guatemala,Ecuador,Puerto-Rico,Cambodia,China,Poland,Nicaragua,Taiwan,England,Ireland,Hungary,Yugoslavia,Trinadad&Tobago,Jamaica,Honduras,Portugal,Iran,France,India,Hong_Kong,Haiti,Greece,Holand-Netherlands,Thailand,Laos,Panama}
@attribute Atr-33 {United-States,Vietnam,Columbia,Mexico,El-Salvador,Peru,Puerto-Rico,Cuba,Philippines,Dominican-Republic,Germany,England,Guatemala,Scotland,Portugal,Italy,Ecuador,Yugoslavia,China,Poland,Hungary,Nicaragua,Taiwan,Ireland,Canada,South_Korea,Trinadad&Tobago,Jamaica,Honduras,Iran,France,Cambodia,India,Hong_Kong,Haiti,Japan,Greece,Holand-Netherlands,Thailand,Panama,Laos,Outlying-U_S_(Guam_USVI_etc)}
@attribute Atr-34 {United-States,Vietnam,Columbia,Mexico,Peru,Cuba,Philippines,Dominican-Republic,El-Salvador,Canada,Scotland,Portugal,Guatemala,Ecuador,Germany,Outlying-U_S_(Guam_USVI_etc),Puerto-Rico,Italy,China,Poland,Nicaragua,Taiwan,England,Ireland,South_Korea,Trinadad&Tobago,Jamaica,Honduras,Iran,Hungary,France,Cambodia,India,Hong_Kong,Japan,Haiti,Holand-Netherlands,Greece,Thailand,Panama,Yugoslavia,Laos}
@attribute Atr-35 {Native-_Born_in_the_United_States,Foreign_born-_Not_a_citizen_of_U_S,Foreign_born-_U_S_citizen_by_naturalization,Native-_Born_abroad_of_American_Parent(s),Native-_Born_in_Puerto_Rico_or_U_S_Outlying}
@attribute Atr-36 integer[0,2]
@attribute Atr-37 {Not_in_universe,No,Yes}
@attribute Atr-38 integer[0,2]
@attribute Atr-39 integer[0,52]
@attribute Atr-40 integer[94,95]
@attribute Class {-_50000.,50000+.}
@inputs Atr-0, Atr-1, Atr-2, Atr-3, Atr-4, Atr-5, Atr-6, Atr-7, Atr-8, Atr-9, Atr-10, Atr-11, Atr-12, Atr-13, Atr-14, Atr-15, Atr-16, Atr-17, Atr-18, Atr-19, Atr-20, Atr-21, Atr-22, Atr-23, Atr-24, Atr-25, Atr-26, Atr-27, Atr-28, Atr-29, Atr-30, Atr-31, Atr-32, Atr-33, Atr-34, Atr-35, Atr-36, Atr-37, Atr-38, Atr-39, Atr-40
@outputs Class