dask_from_batch_example.py

dask_from_batch_example.py

### GET DASK CLIENT ###

import os
import coiled
cluster = coiled.Cluster(os.environ.get("COILED_CLUSTER_NAME"))
cluster.adapt()
client = cluster.get_client()
print("dask client:", client)

### USER CODE FOLLOWS ###

import dask

# generate random timeseries of data
df = dask.datasets.timeseries(
    "1980", "2005", partition_freq="2w"
).persist()

# perform a groupby with an aggregation
result = df.groupby("name").aggregate({"x": "sum", "y": "max"}).compute()

print(result)