Data engineering and BI courses are free!
This is a simple way to extract the meta-features from a dataset, where all meta-features from each group is extracted.
metafeatures(...)# S3 method for default
metafeatures(x, y, groups = "default", summary = c("mean", "sd"), ...)
# S3 method for formula
metafeatures(formula, data, groups = "default", summary = c("mean", "sd"), ...)
Optional arguments to the summary methods.
A data.frame contained only the input attributes.
A factor response vector with one label for each row/component of x.
A list of meta-features groups, "default" for traditional
groups of meta-features or "all" to include all them. The details
section describes the valid values for this parameter.
A list of summarization functions or empty for all values. See
post.processing method to more information. (Default:
c("mean", "sd"))
A formula to define the class column.
A data.frame dataset contained the input attributes and class The details section describes the valid values for this group.
A numeric vector named by the meta-features from the specified groups.
The following groups are allowed for this method:
Include all information theoretical meta-features. See infotheo for more details.
Include all general (simple) meta-features. See general for more details.
Include all landmarking meta-features. See landmarking for more details.
Include all model based meta-features. See model.based for more details.
Include all statistical meta-features. See statistical for more details.
Include all clustering meta-features. See clustering for more details.
Include all complexity meta-features. See complexity for more details.
Include all concept variation meta-features. See concept for more details.
Include all itemset meta-features. See itemset for more details.
# NOT RUN {
## Extract all meta-features
metafeatures(Species ~ ., iris)
## Extract some groups of meta-features
metafeatures(iris[1:4], iris[5], c("general", "statistical", "infotheo"))
## Use another summary methods
metafeatures(Species ~ ., iris, summary=c("min", "median", "max"))
# }
Run the code above in your browser using DataLab