hyperparameter-optimization

Search before asking

• I had searched in the issues and found no similar feature requirement.

Description

the ci/travis folder is confusing. The ci/README.md also mentions Travis, could be interpreted in all sorts of ways. maybe time to change that to something more agnostic? After all, we're not using Travis anymore.

Use case

https://github.com/microsoft/nni/blob/8d5f643c64580bb26a7b10a3c4c9accf617f65b1/nni/compression/pytorch/speedup/jit_translate.py#L382

While trying to speedup my single shot detector, the following error comes up. Any way to fix this,

/usr/local/lib/python3.8/dist-packages/nni/compression/pytorch/speedup/jit_translate.py in forward(self, *args)
    363 
    364         def forward(self, *

The colormaps of plot_contour and plot_paralell_coordinate are reversed depending on its optimisation direction and target argument. It would be great to explain this rule in their documentation.

See optuna/optuna#3424 for the concrete rule.

Originally posted by @nzw0301 in optuna/optuna#3424 (comment)

We currently fit and predict upon loading autosklearn.experimental.askl2 for the first time. In environments with a non-persistent filesystem (autosklearn is installed into a new filesystem each time), this can add quite a bit of time delay as experienced in #1362

It seems more applicable to export the

Related: awslabs/autogluon#1479

Add a scikit-learn compatible API wrapper of TabularPredictor:

• TabularClassifier
• TabularRegressor

Required functionality (may need more than listed):

• init API
• fit API
• predict API
• works in sklearn pipelines

Use case

Polyaxon tracking can be used to automatically log all information generated by Ludwig.

We should probably think about adding support for Polyaxon's tracking module in Ludwig contrib.

When using r2 as eval metric for regression task (with 'Explain' mode) the metric values reported in Leaderboard (at README.md file) are multiplied by -1.
For instance, the metric value for some model shown in the Leaderboard is -0.41, while when clicking the model name leads to the detailed results page - and there the value of r2 is 0.41.
I've noticed that when one of R2 metric values in the L

I published a new v0.1.12 release of HCrystalBall, that updated some package dependencies and fixed some bugs in cross validation.

Should the original pin for 0.1.10 be updated? Unfortunately won't have time soon to submit a PR for this.

If enter_data() is called with the same train_path twice in a row and the data itself hasn't changed, a new Dataset does not need to be created.

We should add a column which stores some kind of hash of the actual data. When a Dataset would be created, if the metadata and data hash are exactly the same as an existing Dataset, nothing should be added to the ModelHub database and the existing

Describe the bug
Code could be more conform to pep8 and so forth.

To Reproduce
https://app.codacy.com/gh/Neuraxio/Neuraxle/issues?&filters=W3siaWQiOiJMYW5ndWFnZSIsInZhbHVlcyI6W119LHsiaWQiOiJDYXRlZ29yeSIsInZhbHVlcyI6WyJDb2RlU3R5bGUiXX0seyJpZCI6IkxldmVsIiwidmFsdWVzIjpbXX0seyJpZCI6IlBhdHRlcm4iLCJ2YWx1ZXMiOltdfSx7ImlkIjoiQXV0aG9yIiwidmFsdWVzIjpbXX1d

Expected behavior
Less code st