In memory, DOS and Modin really are to make stuff faster than Pandas. Once we include IO, all those tools first needed to go via Pandas. And yeah, what this sort of shows is that we have Pandas, which is a single threaded data frame engine. And then we have tools that parallelize Pandas. So, if we have a filter or an element-wise multiplication, parallelization is easy. You just split it up in chunks and do your parallelization. And then those tools will win.