Data Partitioning for machine learning

head(iris)

##   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1          5.1         3.5          1.4         0.2  setosa
## 2          4.9         3.0          1.4         0.2  setosa
## 3          4.7         3.2          1.3         0.2  setosa
## 4          4.6         3.1          1.5         0.2  setosa
## 5          5.0         3.6          1.4         0.2  setosa
## 6          5.4         3.9          1.7         0.4  setosa

library(caret)

## Warning: package 'caret' was built under R version 3.5.2

## Loading required package: lattice

## Loading required package: ggplot2

set.seed(123)
v.index <- createDataPartition(iris$Species, p = 0.8, list = FALSE)
validation <- iris[-v.index,]
training <- iris[v.index,]

dim(validation)

## [1] 30  5

dim(training)

## [1] 120   5

head(validation)

##    Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 5           5.0         3.6          1.4         0.2  setosa
## 6           5.4         3.9          1.7         0.4  setosa
## 10          4.9         3.1          1.5         0.1  setosa
## 12          4.8         3.4          1.6         0.2  setosa
## 16          5.7         4.4          1.5         0.4  setosa
## 17          5.4         3.9          1.3         0.4  setosa

head(training)

##   Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1          5.1         3.5          1.4         0.2  setosa
## 2          4.9         3.0          1.4         0.2  setosa
## 3          4.7         3.2          1.3         0.2  setosa
## 4          4.6         3.1          1.5         0.2  setosa
## 7          4.6         3.4          1.4         0.3  setosa
## 8          5.0         3.4          1.5         0.2  setosa