This recipe uses the cor (), cov (), rcorr() packages in R to establish relationships between the features. It then outputs a correlation matrix.
What is a Feature variable ?
A feature variable refers to the fields in a dataset used for analytics or machine learning. Feature selection, also known as variable selection is the process of selecting a subset of relevant features (variables) from the dataset for in model construction.
What is R ?
R is a programming language used for statistics and data science computing. R has very powerful libraries (almost 12,000) for performing data analytics including regression, classification, visualisation etc.
# -------------------------------------------------
# How to find correlations among feature variables in R
# -------------------------------------------------
# load library and data
library(mlbench)
library(Hmisc)
data(mtcars)
dim(mtcars)
par(mfrow=c(1,1))
# Correlations/covariances among numeric variables
# Use listwise deletion of missing data.
cor(mtcars, use="complete.obs", method="kendall")
cov(mtcars, use="complete.obs")
# Correlations with significance levels
rcorr(as.matrix(mtcars), type="pearson")
# Correlation matrix from mtcars
# with mpg, cyl, and disp as rows
# and hp, drat, and wt as columns
x <- mtcars[1:3]
y <- mtcars[4:6]
cor(x, y)