install.packages("faraway")
library("faraway")


# wbca: Wisconsin breast cancer database
# Data come from a study of breast cancer in Wisconsin. 
# There are 681 cases of potentially cancerous tumors of 
# which 238 are actually malignant. Determining whether 
# a tumor is really malignant is traditionally determined 
# by an invasive surgical procedure. The purpose of this 
# study was to determine whether a new procedure called 
# fine needle aspiration which draws only a small sample 
# of tissue could be effective in determining tumor status.
# 
# A data frame with 681 observations on the following 10 variables.
#
# Class: 0 if malignant, 1 if benign (238 0s + 443 1s)
# Adhes: marginal adhesion
# BNucl: bare nuclei
# Chrom: bland chromatin
# Epith: epithelial cell size
# Mitos: mitoses
# NNucl: normal nucleoli
# Thick: clump thickness
# UShap: cell shape uniformity
# USize: cell size uniformity
#
# Details: The predictor values are determined by a doctor observing 
#          the cells and rating them on a scale from 1 (normal) to 
#          10 (most abnormal) with respect to the particular characteristic.
data(wbca)

attach(wbca)

n = nrow(wbca)

par(mfrow=c(3,3))
plot(Adhes,Class+rnorm(n,0,0.05))
plot(BNucl,Class+rnorm(n,0,0.05))
plot(Chrom,Class+rnorm(n,0,0.05))
plot(Epith,Class+rnorm(n,0,0.05))
plot(Mitos,Class+rnorm(n,0,0.05))
plot(NNucl,Class+rnorm(n,0,0.05))
plot(Thick,Class+rnorm(n,0,0.05))
plot(UShap,Class+rnorm(n,0,0.05))
plot(USize,Class+rnorm(n,0,0.05))


# Diabetes survey on Pima Indians
# The National Institute of Diabetes and Digestive and Kidney 
# Diseases conducted a study on 768 adult female Pima Indians 
# living near Phoenix.
# 
# pregnant: Number of times pregnant
# glucose: Plasma glucose concentration at 2 hours in an oral glucose tolerance test
# diastolic: Diastolic blood pressure (mm Hg)
# triceps: Triceps skin fold thickness (mm)
# insulin: 2-Hour serum insulin (mu U/ml)
# bmi: Body mass index (weight in kg/(height in meters squared))
# diabetes: Diabetes pedigree function
# age: Age (years)
# test: test whether the patient shows signs of diabetes (coded 0 if negative, 1 if positive)
# 500 0s & 268 1s
# 
# Source: The data may be obtained from UCI Repository of 
#         machine learning databases at http://archive.ics.uci.edu/ml/

data(pima) 
attach(pima)
n = nrow(pima)

par(mfrow=c(2,4))
plot(pregnant,test+rnorm(n,0,0.05))
plot(glucose,test+rnorm(n,0,0.05))
plot(diastolic,test+rnorm(n,0,0.05))
plot(triceps,test+rnorm(n,0,0.05))
plot(insulin,test+rnorm(n,0,0.05))
plot(bmi,test+rnorm(n,0,0.05))
plot(diabetes,test+rnorm(n,0,0.05))
plot(age,test+rnorm(n,0,0.05))