Dask array implements the NumPy API. It is composed of many small NumPy arrays
from dask_kubernetes import KubeCluster
cluster = KubeCluster(n_workers=10)
cluster
from dask.distributed import Client
client = Client(cluster)
client
import dask.array as da
x = da.random.random((20000, 20000), chunks=(2000, 2000)).persist()
x
x[0, :5].compute()
x.sum().compute()
y = x + x.T - x.mean(axis=0)
y = y.persist()
y
y[:5, :5].compute()