DHSC-Capstone/ML/2-modeling.R

rm(list = ls(all.names = TRUE)) # Clear the memory of variables from previous run.
cat("\014") # Clear the console


# load packages -----------------------------------------------------------

box::use(
  magrittr[`%>%`]
  ,here[here]
  ,readr
  ,gp2 = ggplot2[ggplot, aes]
  ,rsample
)



# globals -----------------------------------------------------------------

set.seed(070823) #set seed for reproducible research


# load-data ---------------------------------------------------------------

model_data <- readr$read_rds(here("ML","data-unshared","model_data.RDS"))




# split data --------------------------------------------------------------

model_data_split <- rsample$initial_split(
  model_data
  ,prop   = 0.80
  ,strata = ft4_dia
  )

ds_train <- rsample$training(model_data_split)
ds_test  <- rsample$testing(model_data_split)

# verify distribution of data
table(ds_train$ft4_dia) %>% prop.table()
table(ds_test$ft4_dia) %>% prop.table()