DataYatriSpark, seen under the hood
Simulate

Simulation/Spark

Educational simulation
Spark

Narrow vs wide transforms

filter stays put. groupBy shuffles. Neither runs until an action.

Watch the canvas:narrow (no shuffle)wide (shuffle)Live simulation
filter / mapnarrowgroupBy(region)wide · Exchangeshow()actionfilter never asks another worker for rows.
Narrow stays put. Wide moves keys. Neither runs until an action.