install.packages(“dplyr”) install.packages(“psych”)

library(dplyr) library(psych)

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

Basic Descriptive Statistics (Mean, Median, SD, Variance)

basic_stats <- train_data %>% summarise( RoomService_Mean = mean(RoomService, na.rm = TRUE), RoomService_Median = median(RoomService, na.rm = TRUE), RoomService_SD = sd(RoomService, na.rm = TRUE), RoomService_Variance = var(RoomService, na.rm = TRUE), Spa_Mean = mean(Spa, na.rm = TRUE), Spa_Median = median(Spa, na.rm = TRUE), Spa_SD = sd(Spa, na.rm = TRUE), Spa_Variance = var(Spa, na.rm = TRUE) )

Range and IQR

range_iqr_stats <- train_data %>% summarise( RoomService_Range = max(RoomService, na.rm = TRUE) - min(RoomService, na.rm = TRUE), RoomService_IQR = IQR(RoomService, na.rm = TRUE), Spa_Range = max(Spa, na.rm = TRUE) - min(Spa, na.rm = TRUE), Spa_IQR = IQR(Spa, na.rm = TRUE) )

Skewness and Kurtosis using psych package

skew_kurt <- data.frame( RoomService_Skewness = skewness(train_data\(RoomService, na.rm = TRUE), RoomService_Kurtosis = kurtosis(train_data\)RoomService, na.rm = TRUE), Spa_Skewness = skewness(train_data\(Spa, na.rm = TRUE), Spa_Kurtosis = kurtosis(train_data\)Spa, na.rm = TRUE) )

remove.packages(“psych”) install.packages(“psych”)

The other code didn’t work, so I used below code to get the skewness

if (!requireNamespace(“e1071”, quietly = TRUE)) install.packages(“e1071”) e1071::skewness(train_data$RoomService, na.rm = TRUE)

if (!requireNamespace(“e1071”, quietly = TRUE)) install.packages(“e1071”) e1071::skewness(train_data$Spa, na.rm = TRUE)

if (!requireNamespace(“e1071”, quietly = TRUE)) { install.packages(“e1071”) } library(e1071) kurtosis_value <- kurtosis(train_data\(RoomService) + 3 kurtosis_value <- kurtosis(train_data\)Spa) + 3

Calculate frequency of each category for a qualitatiive variable

frequency_HomePlanet <- table(train_data\(HomePlanet) frequency_CryoSleep <- table(train_data\)CryoSleep)

Install corrplot

if (!requireNamespace(“corrplot”, quietly = TRUE)) { install.packages(“corrplot”) }

library(corrplot)

Subset the Dataframe

quant_vars_train_data <- train_data[, c(“Age”, “RoomService”, “FoodCourt”, “ShoppingMall”, “Spa”, “VRDeck”)]

Calculate the Correlation Matrix

cor_matrix <- cor(quant_vars_train_data, use = “complete.obs”)

Visualize the correlation matrix

corrplot(cor_matrix, method = “circle”)

Crosstab between HomePlanet and CryoSleep

crosstab_HomePlanet_CryoSleep <- table(train_data\(HomePlanet, train_data\)CryoSleep)

Crosstab between HomePlanet and Destination

crosstab_HomePlanet_Destination <- table(train_data\(HomePlanet, train_data\)Destination)

Crosstab between HomePlanet and Cabin

crosstab_HomePlanet_Cabin <- table(train_data\(HomePlanet, train_data\)Cabin)

Crosstab between HomePlanet and VIP

crosstab_HomePlanet_VIP <- table(train_data\(HomePlanet, train_data\)VIP)

Crosstab between PassengerId and Name

crosstab_PassengerId_Name <- table(train_data\(PassengerId, train_data\)Name)

Crosstab between Name and Cabin

crosstab_Name_Cabin <- table(train_data\(Name, train_data\)Cabin)