tpot
tpot copied to clipboard
EpistasisLab
A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.
When training TPOT using Dask, you can navigate to the WebUI on port 8786, and see an output like this:  ...which lets you monitor the scheduled tasks. Which is...
`Windows 10, Python 3.10.5, scikit-learn==1.1.1, TPOT==0.11.7, dask==2022.7.0, dask-glm==0.2.0, dask-ml==2022.5.27` Just trying to run a regression training session with a BIG (out of memory) `parquet` dataset that I created in another...
Hello, whilst inspecting the nn part, noticed the following discrepancy, perhaps worth noting: https://github.com/EpistasisLab/tpot/blob/c3a155b5a76f7ac0911482d0478d4ca6c2fcb3bd/tpot/builtins/nn.py#L218 The suggested solution is aligned variable/activation naming (e.g. self.tanhAct)
I am currently working with TPOT and had to implement functions for getting feature_importances_ and coefs_ from the pipelines, as well as functions for calculating the permutation importance, LIME and...
Hello, I want to use TPOT for feature engineering. Therefore, I chose a fixed model for TPOT like a linear regression model and the default configuration. Having some features {x1,x2,…},...
I am working on a multioutput regression problem, that is the target values have more than 1-dim. A number of regressors from scikit-learn can only be used for multi output...
When using the TPOTRegressor object, with the method "fit" such that the during the constraction of the object we provide a "sklearn.model_selection.StratifiedKFold" object to the "cv" argument an error occurs...
Replaced `sklearn`'s `SCORERS` attribute with a locally generated one.
Usage of of `SCORERS` in [`tpot.metrics`](https://github.com/EpistasisLab/tpot/blob/435dc100ee9ee40b9e5a44f70e62ed1a659c86cd/tpot/metrics.py#L27) causes sklearn to raise: ```sh FutureWarning: sklearn.metrics.SCORERS is deprecated and will be removed in v1.3. Please use sklearn.metrics.get_scorer_names to get a list of available...
It would be nice to be able to export the pipeline as a json file and use them later on, example if you have to create pipelines for subsets of...
Metadata
Owner
Metadata
A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.