[R] Data Preprocessing.ipynb

Kernel: R

Data Preprocessing

Import the dataset

dataset = read.csv('Data.csv')

dataset # Unlike python indexing starts with 1 in R

Taking care of missing data

dataset$Age = ifelse(is.na(dataset$Age), 
                     ave(dataset$Age, FUN = function(x) mean(x, na.rm = TRUE)), 
                         dataset$Age)
dataset$Salary = ifelse(is.na(dataset$Salary), 
                        ave(dataset$Salary, FUN = function(x) mean(x, na.rm = TRUE)), 
                            dataset$Salary)

dataset

Encoding categorical data

dataset$Country = factor(dataset$Country, 
                         levels = c('France', 'Spain', 'Germany'),
                         labels = c(1, 2, 3))

dataset

dataset$Purchased = factor(dataset$Purchased, 
                         levels = c('No', 'Yes'),
                         labels = c(0, 1))

dataset

Splitting the dataset into the Training set and Test set

# install.packages('caTools')

library(caTools)

set.seed(42)
split = sample.split(dataset$Purchased, SplitRatio = 0.8)

split # TRUE = Training set, FALSE = Test set

training_set = subset(dataset, split == TRUE)
test_set = subset(dataset, split == FALSE)

training_set

dim(training_set)[1]

test_set

dim(test_set)[1]

Feature Scaling

training_set = scale(training_set)
test_set = scale(test_set)

Error in colMeans(x, na.rm = TRUE): 'x' must be numeric
Traceback:
1. scale(training_set)
2. scale.default(training_set)
3. colMeans(x, na.rm = TRUE)

training_set[, 2:3] = scale(training_set[, 2:3])
test_set[, 2:3] = scale(test_set[, 2:3])

training_set

test_set