add Project

Project/Solution-Coding-02-Data Mining Process.R

@@ -0,0 +1,25 @@
+# Load data
+house.df <- read.csv("WestRoxbury.csv")
+
+# Extract the row numbers
+house.rows <- row.names(house.df)
+
+# Partition the row numbers into 10 equal subsets
+set.seed(100)
+house.rows.list <- list()
+for(i in 1:10){
+  house.rows.list[[i]] <- sample(house.rows, length(house.rows) / (10 - i + 1))
+  house.rows <- setdiff(house.rows, house.rows.list[[i]])
+}
+
+# Partition the data into 10 equal subsets
+house.df.list <- list()
+for(i in 1:10){
+  house.df.list[[i]] <- house.df[house.rows.list[[i]],]
+}
+
+# Display the number of observations in each subset
+for(i in 1:10){
+  print(paste("Number of observations in subset", i,
+              "=", dim(house.df.list[[i]])[1]))
+}