dask-ml

dask-ml copied to clipboard

What happened: Compute calls with schedule="single-threaded" while using a distributed client may lead to unexpected results. This needs to be fixed in a few places. So far:

• dask_ml.datasets.make_classification
• dask_ml.cluster.k_means

However, each of the :okwarning: options added in #929 need to be addressed.

Users currently get an unexpected UserWarning:

/datasets/vjawa/miniconda3/envs/dask-ml-dev/lib/python3.8/site-packages/dask/base.py:1282: UserWarning: Running on a single-machine scheduler when a distributed client is active might lead to unexpected results.
  warnings.warn(

Minimal Complete Verifiable Example:

from dask.distributed import Client
import dask_ml.datasets
 
client = Client()


X,y = dask_ml.datasets.make_classification_df(chunks=100)