model-selection

Apache Arrow has a first-class tabular file format, Feather, that the Ray Datasets IO layer should support. Combined with Ray Datasets' existing .from_arrow() and .to_arrow() APIs, this would round out our "all-Arrow" experience, which should be as nice as possible given our "distributed Arrow dataset" positioning.

Implementation Note

Currently, DaskEngine and CFEngine require a client explicitly provided to run AutoML. Perhaps, for OS user's convenience, it might be nice to make client an optional argument and instead instantiate a DaskEngine and CFEngine using threaded parallelism using max threads.

Currently:

from dask.distributed import Client, LocalCluster
from evalml.automl.engine import DaskEngine

cl = 

We should add a description to each feature defined in smartcore in the Cargo.toml file, we could use as example the Cargo.toml file of the serde project.

We should add also the documentation for the "serde" feature that currently is not present in the Cargo.toml file.

Not sure if we can u

Describe the solution you'd expect
This issue is meant to guide and support people who wants to add an external reference, these references will be shown here

You can add a blog post, a video, a kaggle notebook or an article. You can add the link of the content in the file docs/external_references.rst (followi

Is your feature request related to a problem? Please describe.
Feature is not directly related to a problem, but is rather an enhancement of existing functionality. As suggested by Julian King on the facet Slack channel, we could add Maximum Relevance Minimum Redundancy (MRMR) as a feature selection algorithm.

The algorithm is explained in the following papers:
https://arxiv.org/pdf/1