Assignment 6: Generate and Apply Transformations and Scaling

#Load train.csv data file

file_path <- “C:\Users\fardm\OneDrive\Desktop\PhD\train.csv” train_data <- read.csv(“C:\Users\fardm\OneDrive\Desktop\PhD\train.csv”)

Set the seed for reproducibility

set.seed(123)

Number of rows in the dataset

n <- nrow(train_data)

Calculate the size of the training set (80% of the dataset)

train_size <- floor(0.8 * n)

Randomly sample indices for the training set

train_indices <- sample(1:n, train_size)

Split the dataset

Training set

train_set <- train_data[train_indices, ]

Test set (excluding the training set indices)

test_set <- train_data[train_indices, ]

Summary statistics for each quantitative variable

summary(train_set\(Age) summary(train_set\)RoomService) summary(train_set\(FoodCourt) summary(train_set\)ShoppingMall) summary(train_set\(Spa) summary(train_set\)VRDeck)

Histogram for Age

hist(train_set\(Age, main = "Distribution of Age", xlab = "Age") # Histogram for RoomService hist(train_set\)RoomService, main = “Distribution of Room Service”, xlab = “Room Service”) # Histogram for FoodCourt hist(train_set\(FoodCourt, main = "Distribution of Food Court", xlab = "Food Court") # Histogram for ShoppingMall hist(train_set\)ShoppingMall, main = “Distribution of Shopping Mall”, xlab = “Shopping Mall”) # Histogram for Spa hist(train_set\(Spa, main = "Distribution of Spa", xlab = "Spa") # Histogram for VRDeck hist(train_set\)VRDeck, main = “Distribution of VR Deck”, xlab = “VR Deck”)

library(ggplot2)

Plot for Age

ggplot(train_set, aes(x = Age)) + geom_histogram(binwidth = 1, fill = “blue”, color = “black”) + ggtitle(“Distribution of Age”) + xlab(“Age”) + ylab(“Frequency”)

Plot for RoomService

ggplot(train_set, aes(x = RoomService)) + geom_histogram(binwidth = 1, fill = “blue”, color = “black”) + ggtitle(“Distribution of RoomService”) + xlab(“RoomService”) + ylab(“Frequency”)

Check for zeros and add a constant if needed

train_set\(Age <- ifelse(train_set\)Age == 0, 1, train_set$Age)

Check for zeros and add a constant if needed

train_set\(RoomService <- ifelse(train_set\)RoomService == 0, 1, train_set$RoomService)

Check for zeros and add a constant if needed

train_set\(FoodCourt <- ifelse(train_set\)FoodCourt == 0, 1, train_set$FoodCourt)

Check for zeros and add a constant if needed

train_set\(ShoppingMall <- ifelse(train_set\)ShoppingMall == 0, 1, train_set$ShoppingMall)

Check for zeros and add a constant if needed

train_set\(Spa <- ifelse(train_set\)Spa == 0, 1, train_set$Spa)

Check for zeros and add a constant if needed

train_set\(VRDeck <- ifelse(train_set\)VRDeck == 0, 1, train_set$VRDeck)

Apply log transformation

train_set\(log_Age <- log(train_set\)Age)

Apply log transformation

train_set\(log_RoomService <- log(train_set\)RoomService)

Apply log transformation

train_set\(log_Spa <- log(train_set\)Spa)

Apply log transformation

train_set\(log_FoodCourt <- log(train_set\)FoodCourt)

Apply log transformation

train_set\(log_ShoppingMall <- log(train_set\)ShoppingMall)

Apply log transformation

train_set\(log_VRDeck <- log(train_set\)VRDeck)

Check for zeros and add a constant if needed

test_set\(Age <- ifelse(test_set\)Age == 0, 1, test_set$Age)

Check for zeros and add a constant if needed

test_set\(RoomService <- ifelse(test_set\)RoomService == 0, 1, test_set$RoomService)

Check for zeros and add a constant if needed

test_set\(FoodCourt <- ifelse(test_set\)FoodCourt == 0, 1, test_set$FoodCourt)

Check for zeros and add a constant if needed

test_set\(ShoppingMall <- ifelse(test_set\)ShoppingMall == 0, 1, test_set$ShoppingMall)

Check for zeros and add a constant if needed

test_set\(Spa <- ifelse(test_set\)Spa == 0, 1, test_set$Spa)

Check for zeros and add a constant if needed

test_set\(VRDeck <- ifelse(test_set\)VRDeck == 0, 1, test_set$VRDeck)

Apply log transformation

test_set\(log_Age <- log(test_set\)Age)

Apply log transformation

test_set\(log_RoomService <- log(test_set\)RoomService)

Apply log transformation

test_set\(log_Spa <- log(test_set\)Spa)

Apply log transformation

test_set\(log_FoodCourt <- log(test_set\)FoodCourt)

Apply log transformation

test_set\(log_ShoppingMall <- log(test_set\)ShoppingMall)

Apply log transformation

test_set\(log_VRDeck <- log(test_set\)VRDeck)

Define a function for min-max scaling

Assuming ‘train_set’ is your training data frame and it’s already loaded

Min-max scaling function

min_max_scaling <- function(x) { return ((x - min(x)) / (max(x) - min(x))) }

Apply min-max scaling to each column

train_set\(scaled_Age <- min_max_scaling(train_set\)Age) train_set\(scaled_RoomService <- min_max_scaling(train_set\)RoomService) train_set\(scaled_FoodCourt <- min_max_scaling(train_set\)FoodCourt) train_set\(scaled_ShoppingMall <- min_max_scaling(train_set\)ShoppingMall) train_set\(scaled_Spa <- min_max_scaling(train_set\)Spa) train_set\(scaled_VRDeck <- min_max_scaling(train_set\)VRDeck)

Check the first few rows to confirm scaling

head(train_set[, c(“scaled_Age”, “scaled_RoomService”, “scaled_FoodCourt”, “scaled_ShoppingMall”, “scaled_Spa”, “scaled_VRDeck”)])

Apply min-max scaling to each column

test_set\(scaled_Age <- min_max_scaling(test_set\)Age) test_set\(scaled_RoomService <- min_max_scaling(test_set\)RoomService) test_set\(scaled_FoodCourt <- min_max_scaling(test_set\)FoodCourt) test_set\(scaled_ShoppingMall <- min_max_scaling(test_set\)ShoppingMall) test_set\(scaled_Spa <- min_max_scaling(test_set\)Spa) test_set\(scaled_VRDeck <- min_max_scaling(test_set\)VRDeck)

Check the first few rows to confirm scaling

head(train_set[, c(“scaled_Age”, “scaled_RoomService”, “scaled_FoodCourt”, “scaled_ShoppingMall”, “scaled_Spa”, “scaled_VRDeck”)])