classification_summary: Summary statistics for the classification data sets

In makeyourownmaker/pmlblite: Interface to the Penn Machine Learning Benchmarks Data Repository

Description

Summary statistics for the classification data sets

Usage

classification_summary

Format

A data frame with 15 variables:

MajorityClassSize:

Number of instances in majority class of target variable

MinorityClassSize:

Number of instances in minority class of target variable

NumberOfClasses:

Number of classes in target variable

ImbalanceMetric:

Imbalance metric, where zero means that the dataset is perfectly balanced and the higher the value, the more imbalanced the dataset

NumberOfFeatures:

Total number of features (equal to number of columns)

NumberOfBinaryFeatures:

Number of binary features

NumberOfIntegerFeatures:

Number of integer features

NumberOfFloatFeatures:

Number of float features

NumberOfInstances:

Number of data observations (equal to number of rows)

NumberOfInstancesWithMissingValues:

Number of instances with missing values (always 0)

NumberOfMissingValues:

Number of missing values (always 0)

NumberOfNumericFeatures:

Number of numeric features

NumberOfSymbolicFeatures:

Number of symbolic features

name:

Dataset name

status:

All datasets are currently categorised as 'active'

Source

https://github.com/EpistasisLab/penn-ml-benchmarks

makeyourownmaker/pmlblite documentation built on Feb. 13, 2020, 11:46 p.m.