# Laurice Keogh # Statistical programming script assignment 2 # May 2024 # Step 1: Load roller coaster data from CSV file # create loadDataFile function loadDataFile <- function() { # Load the csv file into a temporary data frame tempDataFrame <- read.csv("roller_coasters.csv", header=TRUE, stringsAsFactors=TRUE) # Convert specific columns to factors tempDataFrame$seating_type <- factor(tempDataFrame$seating_type) tempDataFrame$material_type <- factor(tempDataFrame$material_type) tempDataFrame$manufacturer <- factor(tempDataFrame$manufacturer) tempDataFrame$status <- factor(tempDataFrame$status) # Return coasterData to the main script return(tempDataFrame) } # Step 2: Generate data frame for highest operating roller coasters # Function to generate data frame for highest operating roller coasters by type generateHighestData <- function(coasterData) { # Create an empty data frame to store highest operating roller coasters highestData <- data.frame() # Get unique seating types unique_types <- unique(coasterData$seating_type) # Loop through each unique seating type for (type in unique_types) { # Subset data for the current seating type and the status 'status.operating' subset_data <- coasterData[coasterData$seating_type == type & coasterData$status == 'status.operating', ] # Find the roller coaster with the maximum height in the subset max_height_index <- which.max(subset_data$height) # Extract the roller coaster with the maximum height from the subset max_height_coaster <- subset_data[max_height_index, ] # Extract name, seating_type, height, park, and status columns for # highest coaster max_height_coaster <- max_height_coaster[c("name", "seating_type", "height", "park", "status")] #append the dataframe to include data from max_height_coaster highestData <- rbind(highestData, max_height_coaster) } #return the data frame return(highestData) } # Step 3: Display comparison of top 10 fastest inverted roller coasters displayComparison <- function(seating_type, coasterData) { # Subset coasterData for roller coasters of the specified seating type that # are operating subset_data <- coasterData[coasterData$seating_type == seating_type & coasterData$status == "status.operating", ] # Extract the top 10 fastest roller coasters from the subset, ordered by speed # [2] top_10_fastest <- head(subset_data[order(-subset_data$speed), ], 10) # Extract roller coaster names coaster_names <- top_10_fastest$name # Extract roller coaster speeds coaster_speeds <- top_10_fastest$speed # Create a barplot displaying the speeds of the top 10 fastest roller coasters barplot(coaster_speeds, # Set the main title of the plot [2] main = paste("Top 10 Fastest", seating_type, "Roller Coasters (Operating)"), # Set the label for the x-axis xlab = "Roller Coaster Name", # Set the label for the y-axis ylab = "Speed (mph)", # Set the color of the bars to skyblue col = "skyblue", # Set the y-axis limits dynamically based on the maximum speed, # with 20% additional space ylim = c(0, max(coaster_speeds, na.rm = TRUE) * 1.2), # Set the names for the bars to coaster_names names.arg = coaster_names, cex.names = 0.8) } # Step 4: Calculate and store the mean height, length, and correlation of length # and speed for Sit Down roller coasters correlateLengthSpeed <- function(coasterData) { # Filter coasterData for Sit Down roller coasters with [2] no NA fields sit_down_data <- coasterData[coasterData$seating_type == "Sit Down" & complete.cases(coasterData), ] # Calculate mean height mean_height <- mean(sit_down_data$height) # Calculate mean length mean_length <- mean(sit_down_data$length) # Calculate correlation coefficient between length and speed [3] correlation <- cor(sit_down_data$length, sit_down_data$speed) # Create a data frame to store the results, and [2] define the column names lengthSpeed <- data.frame(mean_height = mean_height, mean_length = mean_length, correlation = correlation) # Return the data frame return(lengthSpeed) } # Step 5: Compare wooden and steel roller coasters using t-test compareWoodenSteel <- function(coasterData) { # Filter coasterData for wooden roller coasters with [2] no NA fields wooden_data <- coasterData[coasterData$material_type == "Wooden" & complete.cases(coasterData), ] # Filter coasterData for steel roller coasters with [2] no NA fields steel_data <- coasterData[coasterData$material_type == "Steel" & complete.cases(coasterData), ] # Perform independent t-test to compare the mean speeds of wooden and steel # roller coasters t_test_result <- t.test(wooden_data$speed, steel_data$speed) # Print the t-test results print(t_test_result) # Print hypotheses and conclusions cat("Hypotheses:\n") cat("Null Hypothesis (H0): There is no significant difference in the mean speeds of wooden and steel roller coasters.\n") cat("Alternative Hypothesis (H1): There is a significant difference in the mean speeds of wooden and steel roller coasters.\n\n") cat("T-test results:\n") # Check significance level if (t_test_result$p.value < 0.05) { cat("Conclusion: We reject the null hypothesis. There is a significant difference in the mean speeds of wooden and steel roller coasters.\n") } else { cat("Conclusion: We accept the null hypothesis. There is no significant difference in the mean speeds of wooden and steel roller coasters.\n") } } ### Main Script: # Step 1: Load roller coaster data from CSV file coasterData <- loadDataFile() # Step 2: Generate data frame for highest operating roller coasters highestData <- generateHighestData(coasterData) # Step 3: Display comparison of top 10 fastest inverted roller coasters [2] displayComparison("Inverted", coasterData) # Step 4: Calculate and store the mean height, length, and correlation of length # and speed for Sit Down roller coasters lengthSpeed<-data.frame(correlateLengthSpeed(coasterData)) # Step 5: Compare wooden and steel roller coasters using t-test compareWoodenSteel(coasterData)