R Notebook

dataset=read.csv("karpur.csv")
head(dataset)

dataset=dataset[order(dataset$k.core,decreasing = TRUE),]
k=dataset$k.core

sample=c(1:length(k))

k_percent=(sample*100)/length(k)

xlab="Portion of Total Samples Having Larger or Equal k "
ylab="permeability(md)"
plot(k_percent,k,log = 'y',xlab = xlab,ylab = ylab,pch=10,cex=0.5,col='#001c49')

log_k=log(k)
model=lm(log_k~k_percent)
plot(k_percent,log_k,xlab = xlab,ylab = ylab,pch=10,cex=0.5,col='#001c49')
abline(model,col='red',lwd=2)

summary(model)

new_data=data.frame(k_percent=c(50,84.1))
predicted_values=predict(model,new_data)
heterogeneity_index=(predicted_values[1]-predicted_values[2])/predicted_values[1]
heterogeneity_index