first commit

assignment1.R

@@ -0,0 +1,53 @@
+# Load the dataset
+cat("Task 1: Load Dataset\n")
+data <- read.csv('WestRoxbury.csv', header = TRUE) # Enable Heading
+
+# Task 2: Extract the row numbers of the dataset
+row_numbers <- row.names(data)
+cat("Task 2: Row numbers extracted.\n\n")
+
+# Task 3: Partition row numbers into subsets
+set.seed(123)  # For reproducibility
+row_numbers_shuffled <- sample(row_numbers)  # Shuffle row numbers
+
+# Number of subsets (10 subsets)
+num_subsets <- 10
+
+# Calculate the subset size and the remainder
+subset_size <- floor(length(row_numbers_shuffled) / num_subsets)
+cat("Subset size default is: ", subset_size, "\n")
+remainder <- length(row_numbers_shuffled) %% num_subsets
+cat("Remainder is: ", remainder, "\n")
+
+# Create a list of partitioned row numbers
+# the subnet stop at near ending for remainder rows, reserve final subset for adding remainder
+partitioned_row_numbers <- list()
+start_index <- 1
+for (i in 1:(num_subsets - 1)) {  # For the first (num_subsets - 1) subsets. Reserve final subset.
+  end_index <- start_index + subset_size - 1
+  partitioned_row_numbers[[i]] <- row_numbers_shuffled[start_index:end_index] # load row to subset
+  start_index <- end_index + 1 # bump up index for next subset in loop.
+}
+# end_index will be recorded for final run on new subset
+# Add the remainder rows to the last subset (subset num_subsets) 
+partitioned_row_numbers[[num_subsets]] <- row_numbers_shuffled[start_index:(start_index + subset_size + remainder - 1)]
+
+cat("Task 3: Row numbers partitioned into 10 subsets with the remainder in subset 10.\n")
+
+# Task 4: Partition the dataset into 10 subsets using the partitioned row numbers
+partitioned_data <- list()
+for (i in 1:num_subsets) {
+  # Check if partitioned_row_numbers[[i]] exists and is not empty
+  if (length(partitioned_row_numbers[[i]]) > 0) {
+    partitioned_data[[i]] <- data[partitioned_row_numbers[[i]], ]
+  }
+}
+
+cat("Task 4: Dataset partitioned into 10 subsets.\n\n")
+
+# Task 5: Display the number of observations in each subset
+for (i in 1:num_subsets) {
+  cat("Number of observations in subset", i, "=", nrow(partitioned_data[[i]]), "\n")
+}
+
+