Summarizes a data.frame, somewhat differently than the normal summary function of R. The function is mainly useful as a basic EDA tool on data.frames before they are converted to tasks, but can be used on tasks as well.

Columns can be of type numeric, integer, logical, factor, or character. Characters and logicals will be treated as factors.

summarizeColumns(obj)

## Arguments

obj (data.frame | Task) Input data.

## Value

(data.frame). With columns:

name

Name of column.

type

Data type of column.

na

Number of NAs in column.

disp

Measure of dispersion, for numerics and integers sd is used, for categorical columns the qualitative variation.

mean

Mean value of column, NA for categorical columns.

median

Median value of column, NA for categorical columns.

MAD of column, NA for categorical columns.

min

Minimal value of column, for categorical columns the size of the smallest category.

max

Maximal value of column, for categorical columns the size of the largest category.

nlevs

For categorical columns, the number of factor levels, NA else.

Other eda_and_preprocess: capLargeValues, createDummyFeatures, dropFeatures, mergeSmallFactorLevels, normalizeFeatures, removeConstantFeatures
summarizeColumns(iris)#>           name    type na     mean      disp median     mad  min  max nlevs
#> 5      Species  factor  0       NA 0.6666667     NA      NA 50.0 50.0     3