generate_data.r

# specify size 
n <- 1e7

# generate data.table with random data
data_dt <- data.table(id=stri_rand_strings(n, 3, pattern = "[A-Z]"),
                      product=stri_rand_strings(n, 3, pattern = "[A-Z]"),
                      date=sample(seq(as.Date('2019/01/01'), as.Date('2019/04/01'), by="day"), n, replace=TRUE),
                      amount=sample(1:10000,n,replace=TRUE),
                      price=rnorm(n, mean = 100, sd = 20))

data_dt_lazy <- lazy_dt(data_dt)

# convert to data.frame
data_df <- as.data.frame(data_dt)