Tim Jurka timjurka

timjurka / cancer.R

Created October 1, 2012 03:43

How to classify breast cancer as benign or malignant using RTextTools.

	# FILE: Classifying Breast Cancer as Benign or Malignant
	# AUTHOR: Timothy P. Jurka

	library(RTextTools);

	# GET THE BREAST CANCER DATA FROM http://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.names
	data <- read.csv("http://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data",header=FALSE)
	data <- data[-1]

	# ADD TEXTUAL DESCRIPTORS FOR EACH MASS CHARACTERISTIC FOR THE DOCUMENT-TERM MATRIX

timjurka / cancer_classification.R

Created October 17, 2012 20:28

Classifying Breast Cancer as Benign or Malignant Using RTextTools

	library(RTextTools) # LOAD THE RTextTools PACKAGE
	set.seed(95616) # SET THE SEED FOR REPLICABILITY

	url <- "http://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data"
	data <- read.csv(url,header=FALSE) # GET THE BREAST CANCER DATA

	data <- data[-1] # STRIP PATIENT IDs
	diagnosis <- data[,10] # GET THE DEPENDENT VARIABLE: THE DIAGNOSIS
	characteristics <- data[,1:9] # GET THE CHARACTERISTICS OF THE MASS

timjurka / cancer_classification.R

Created October 17, 2012 20:29

Classifying Breast Cancer as Benign or Malignant Using RTextTools

	library(RTextTools) # LOAD THE RTextTools PACKAGE
	set.seed(95616) # SET THE SEED FOR REPLICABILITY

	url <- "http://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data"
	data <- read.csv(url,header=FALSE) # GET THE BREAST CANCER DATA

	data <- data[-1] # STRIP PATIENT IDs
	diagnosis <- data[,10] # GET THE DEPENDENT VARIABLE: THE DIAGNOSIS
	characteristics <- data[,1:9] # GET THE CHARACTERISTICS OF THE MASS