cancer_w: BNG Breast Cancer Wisconsin

In rebordao/modellatoR: Automatic deployment of a statistical model; from data to reporting.

Description

This dataset is intended to be used in the modellatoR demos for classification. It's a larger version of the Breast Cancer Wisconsin dataset made via a Bayesian Network trained on the original dataset and then using it to create pseudo instances.

Usage

cancer_w

Format

A data.frame with 39366 rows and 10 variables. Each row contains 9 predictors and 1 response (Class).

• Clump_Thickness: num 4.8 5.59 5.17 8.21 1 ...

• Cell_Size_Uniformity: num 1 1 1 4.56 1 ...

• Cell_Shape_Uniformity: num 1 1 1 5.43 1 ...

• Marginal_Adhesion: num 1 1 1 3.97 1 ...

• Single_Epi_Cell_Size: num 2 2 2 3 2 2 1 2 2 2 ...

• Bare_Nuclei: num 1 1 1 6.74 1 ...

• Bland_Chromatin: num 2 2 3 9.16 1 ...

• Normal_Nucleoli: num 1 1 1 10 1 ...

• Mitoses: num 1 1 1 1 1 1 1 1 1 1 ...

• Class: Factor w/ 2 levels "benign","malignant": 1 1 1 2 1 1 1 1 1 1 ...

Author(s)

This extended version was made by Geoffrey Holmes, Bernhard Pfahringer, Jan van Rijn and Joaquin Vanschoren.

The original dataset was made by Dr. WIlliam H. Wolberg and donated by Olvi Mangasarian and David W. Aha.

Source

openML - dataset 251

rebordao/modellatoR documentation built on May 27, 2019, 4:01 a.m.