Blocks

Dask collections are broken up into blocks (these can also be called chunks or partitions).

import dask.array as da

arr = da.random.random(size=(1_000, 1_000), chunks=(250, 500))
arr

Array Chunk Bytes 7.63 MiB 0.95 MiB Shape (1000, 1000) (250, 500) Count 8 Tasks 8 Chunks Type float64 numpy.ndarray

arr.blocks[0, 1]

Array Chunk Bytes 0.95 MiB 0.95 MiB Shape (250, 500) (250, 500) Count 9 Tasks 1 Chunks Type float64 numpy.ndarray

When you call a function, Dask applies that function to each block.

arr.sum().visualize()