basic.R

# Load R packages for use
library("dplyr")
library("recipes")
library("rsample")
library("broom")
library("jsonlite")
library("sessioninfo")

# Sample data
sm_iris = initial_split(iris)
train   = training(sm_iris)
test    = testing(iris)

# Assign our volumes to our output params
ntrain = nrow(train)
ntest  = nrow(test)

# Feature engineering
transform = recipe(train, ~.)
transform %>% 
  step_rm("Species") %>% 
  step_scale(all_numeric()) ->
  transform
transform = prep(transform)

# Prepare our data for modelling
train_clean = bake(transform, train)
test_clean = bake(transform, test)

# Build model
km = kmeans(train_clean, centers = 3)

# Predict on test data
test_scored = kmeans(test_clean, centers = km$centers)

# Generate output
OutputDataSet = cbind(test_clean, test_scored$cluster)

# Prepare quality measures
keymetric = "tot.withinss"
keymetricval = test_scored$tot.withinss
metric = toJSON(glance(test_scored))

# Info
inf = toJSON(package_info())

# Convert models for output
femodel = paste0(serialize(transform, NULL), collapse = "")
mlmodel = paste0(serialize(km, NULL), collapse = "")