Skip to main content

Table 1 Overview of datasets. Number of features after removing samples with missing values

From: Compensation of feature selection biases accompanied with improved predictive performance for binary classification by using a novel ensemble feature selection approach

Dataset No. of Samples No. of Features Categorical Numeric
MI-Mortality 406 14 7 7
Fibrosis 101 26 7 19
FLIP 103 13 6 7
SPECTF 267 44 44 0
Sonar 208 60 0 60
WBC 569 30 0 30