Dask Cheat Sheet

import dask.dataframe as dddf = dd.read_csv("data-*.csv")         # reads many files as one logical DataFrameresult = df.groupby("category")["value"].mean()computed = result.compute()             # triggers actual executiondf["ratio"] = df["a"] / df["b"]         # lazy, builds a task graphdf.to_parquet("output/", engine="pyarrow")

import daskfrom dask import delayedimport dask.array as dax = da.random.random((10000, 10000), chunks=(1000, 1000))y = (x + x.T).mean(axis=0)result = y.compute()@delayeddef process(x):    return x * 2tasks = [process(i) for i in range(10)]results = dask.compute(*tasks)

from dask.distributed import Clientclient = Client(n_workers=4, threads_per_worker=2)   # local clusterprint(client.dashboard_link)                          # web UI for the task graphfuture = client.submit(process, 10)result = future.result()client.close()