numeric and factor basic script

R - Basic Description.R

#1 Numeric Variable
numeric_stats <- function (x, na.omit =FALSE){
  if(na.omit)
    x <-x[!is.na(x)]
  m <- mean(x)
  a <- median(x)
  s <- sd(x)
  min <- min(x)
  max <- max(x)
  return(c(min = min, mean = m, avg = a, max = max, sd = s))
}

t(sapply(mtcars, numeric_stats))


#2 Numberical Variable Group by target
aggregate(mtcars, by = list(am=mtcars$am), median)
library(doBy)
t(summaryBy(mpg+hp+wt~am, data = mtcars, FUN = numeric_stats))

#3 Categorical Variable
table(iris$Species)
prop.table(table(iris$Species))*100

prop.table(xtabs(~ factor(am) + factor(cyl) , data =mtcars),1)
prop.table(xtabs(~ factor(am) + factor(cyl), data =mtcars),2)
chisq.test(xtabs(~ factor(am) + factor(cyl), data =mtcars))
fisher.test(xtabs(~ factor(am) + factor(cyl), data =mtcars))
library(vcd)
assocstats(xtabs(~ factor(am) + factor(cyl), data =mtcars))

#4 Correlation
cor(mtcars)
cor(mtcars, method = "spearman")

#5 T
t.test(cyl ~ factor(am), data= mtcars)#anova

library(psych)
principal(iris[,1:4],nfactors =2)