background image

Characteristics

β–  Consists of .csv files:

– πΎπ·π·π‘‡π‘Ÿπ‘Žπ‘–𝑛 + with 125,973 data entries 
– πΎπ·π·π‘‡π‘’𝑠𝑑 + with 22,544 data entries 

β†’ 17.9% π‘Ÿπ‘Žπ‘‘𝑒

β–  Difficulty levels: 21

– 49.66% of training set and 47.44% of test set are 21/21 level

β–  43 columns: 1-41 β†’ features, 42 β†’ label, 43 β†’ difficulty level

β–  Subsets: KDDTest-21, KDDTraini+_20Percent

– Their records are all included in the bigger datasets

10