Skip to content

Instantly share code, notes, and snippets.

What would you like to do?
OLAP operations in base R
## credits
# Setup the dimension tables
state_table <- data.frame(key=c("CA", "NY", "WA", "ON", "QU"),
name=c("California", "new York", "Washington", "Ontario", "Quebec"),
country=c("USA", "USA", "USA", "Canada", "Canada"))
month_table <- data.frame(key=1:12,
desc=c("Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"),
prod_table <- data.frame(key=c("Printer", "Tablet", "Laptop"), price=c(225, 570, 1120))
# Function to generate the Sales table
gen_sales <- function(no_of_recs) {
# Generate transaction data randomly
loc <- sample(state_table$key, no_of_recs, replace=T, prob=c(2,2,1,1,1))
time_month <- sample(month_table$key, no_of_recs, replace=T)
time_year <- sample(c(2012, 2013), no_of_recs, replace=T)
prod <- sample(prod_table$key, no_of_recs, replace=T, prob=c(1, 3, 2))
unit <- sample(c(1,2), no_of_recs, replace=T, prob=c(10, 3))
amount <- unit*prod_table[prod,]$price
sales <- data.frame(month=time_month, year=time_year, loc=loc, prod=prod, unit=unit, amount=amount)
# Sort the records by time order
sales <- sales[order(sales$year, sales$month),]
row.names(sales) <- NULL
} # Now create the sales fact table
sales_fact <- gen_sales(500) # Look at a few records
# Build up a cube
revenue_cube <- tapply(sales_fact$amount, sales_fact[,c("prod", "month", "year", "loc")], FUN=function(x){return(sum(x))})
# Showing the cells of the cube
# Slice
# cube data in Jan, 2012
revenue_cube[, "1", "2012",]
# cube data in Jan, 2012
revenue_cube["Tablet", "1", "2012",]
# Dice
revenue_cube[c("Tablet","Laptop"), c("1","2","3"), , c("CA","NY")]
# Rollup
apply(revenue_cube, c("year", "prod"), FUN=function(x) {return(sum(x, na.rm=TRUE))})
# Drilldown
apply(revenue_cube, c("year", "month", "prod"), FUN=function(x) {return(sum(x, na.rm=TRUE))})
# Pivot
apply(revenue_cube, c("year", "month"), FUN=function(x) {return(sum(x, na.rm=TRUE))})
apply(revenue_cube, c("prod", "loc"), FUN=function(x) {return(sum(x, na.rm=TRUE))})
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment