Content

Adult

Reference to code adult


The dataset is found on UCI.
Number of instances 48842, features 14. The sample of only one record is shown below. 
39, State-gov, 77516, Bachelors, 13, Never-married, Adm-clerical, Not-in-family, 
White, Male, 2174, 0, 40, United-States, <=50K
The training block is 32561 records, validation set is 16281, 14 features, accuracy is over 86%, which is the same as other people report. Training takes near $0.25$ seconds. This result can be compared to this recent preprint.