Remove all Dask-ML dependencies and references

[sarahyurick]

This is currently being tracked by #832 and #839 to replace the ParallelPostFit and Incremental classes, respectively. In addition to these, we should look into removing all Dask-ML references in our docs and pytests.

All files with dask_ml keyword in them:

• dask_sql/physical/rel/custom/create_experiment.py
• dask_sql/physical/rel/custom/create_model.py
• docs/source/machine_learning.rst
• docs/source/sql/ml.rst
• notebooks/Feature Overview.ipynb
• tests/integration/test_model.py

All files with dask-ml keyword in them:

• .github/workflows/test.yml
• .github/workflows/test-upstream.yml
• continuous_integration/environment-3.10-dev.yaml
• continuous_integration/environment-3.9-dev.yaml
• continuous_integration/environment-3.8-dev.yaml
• continuous_integration/gpuci/environment.yaml
• dask_sql/physical/rel/custom/create_experiment.py
• dask_sql/physical/rel/custom/create_model.py
• dask_sql/physical/rel/custom/predict.py
• docker/conda.txt
• docker/main.dockerfile
• docs/source/machine_learning.rst
• docs/source/sql/ml.rst
• /setup.py

All files with ml.dask.org documentation in them:

• dask_sql/physical/rel/custom/create_experiment.py
• dask_sql/physical/rel/custom/create_model.py
• dask_sql/physical/rel/custom/predict.py
• docs/source/machine_learning.rst
• docs/source/sql/ml.rst

[sarahyurick]

In addition to this checklist, we also need to decide about the model_class and experiment_class parameters.