Check out DiagrammeR
(or mermaid) if you need clean easy flow diagrams. I find they’re not to hard to make and even easier to forget that you’ve made them.
DiagrammeR::grViz("digraph {
graph [layout = dot]
# define the global styles of the nodes. We can override these in box if we wish
node [shape = circle, style = filled, fillcolor = LightSteelBlue]
data1 [label = 'Input', shape = folder, fillcolor = Beige]
glmnet [label = 'Lasso
Regression', shape = box, fillcolor = Linen]
mnnet [label = 'Mulitnomial
Neural
Network', shape = box, fillcolor = Linen]
nnet [label = 'Neural
Network', shape = box, fillcolor = Linen]
knn [label = 'k-Nearest
Neighbor', shape = box, fillcolor = Linen]
ranger [label = 'Random
Forest', shape = box, fillcolor = Linen]
svml [label = 'SVM
Linear', shape = box, fillcolor = Linen]
svmr [label = 'SVM
Radial', shape = box, fillcolor = Linen]
data2 [label = '5-fold CV
Accuracy', shape = folder, fillcolor = Beige]
# edge definitions with the node IDs
data1 -> {glmnet mnnet nnet knn ranger svml svmr} -> data2
{alpha lambda} -> glmnet
decay -> mnnet
{size decay} -> nnet
k -> knn
{mtry splitrule minNodeSize} -> ranger
cost -> svml
sigma -> svmr
}")