Skip to main content

Table 1 Summary of data sets used in our experiments

From: Differentially private distributed logistic regression using private and public data

Data set

Data set description

# of

attributes

# of

samples

Class distribution (negative/positive)

1

German breast cancer

9

686

43.6% / 56.4%

2

Hospital discharge

17

8,668

4.4% / 95.6%

3

SEER breast Cancer

37

55,000

21.0% / 79.0%