Skip to main content

No project description provided

Project description

  • parallel evaluation with joblib (n_jobs)

  • implement genetic algorithm to find pipelines

  • copy parameters from tpot

  • add rules to prevent stupid things (PolynomialFeatures with many columns)

  • distribute genetic algorithms with dask

  • test joblib distributed backend with dask (nothing to do, just test)

  • fine-grained distribution with dask computation graph:

    • trivial for prediction

    • for fit, each step returns a cross-validated estimate and a fitted model. The fitted model is not used before the final step.

  • it is possible to implement cross-validation with a factor 2 improvement when the cross-val and the training folds match

  • handle timeouts: https://github.com/dask/distributed/issues/391, https://github.com/dask/dask/issues/1183

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pamalia-0.0.1.tar.gz (5.2 kB view hashes)

Uploaded Source

Built Distribution

pamalia-0.0.1-py3-none-any.whl (5.4 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page