hyperparameter-optimization

Search before asking

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

Description

We have introduced detached flag to indicate the lifetime of the actor in Python as following.

counter = Counter.options(name="CounterActor", lifetime="detached").remote()

But we have not introduced it for J

From issue #1302, it appears autosklearn is a bit unstable when run many times in the same script, i.e. in a for loop.

for i in range(400):
    automodel = AutoSklearn(full_resources)
    automodel.fit(x, y)

We currently have no test for this and it would be good to see if we can reproduce the same connection refused error.

Motivation

Since lightgbm v3.3.0, train/cv's arguments have been deprecated as described in optuna/optuna#3013. It would be great to replace such deprecated arguments with recommended way by lightgbm.

Description

Replace the deprecated arguments with callback-ish way. The ta

When running TabularPredictor.fit(), I encounter a BrokenPipeError for some reason.
What is causing this?
Could it be due to OOM error?

Fitting model: XGBoost ...
-34.1179 = Validation root_mean_squared_error score
10.58s = Training runtime
0.03s = Validation runtime
Fitting model: NeuralNetMXNet ...
-34.2849 = Validation root_mean_squared_error score
43.63s =

Details in discussion mljar/mljar-supervised#421

Here's the code:

settings = {
    "time_budget": 360,  
    "metric": 'ap',   
    "task": 'classification', 
    "log_file_name": f'{output_dir}/flaml1.log',  
    "seed": 7654321,    
    "log_training_metric": True,
    "groups": group_id,
    "estimator_list": ['catboost']  
}

automl.fit(X_train=X_train, y_train=y_train, **settings)

Here's the output:

I think it would be useful to have a grid search optimizer in this package. But its implementation would probably be quite different from other ones (sklearn, ...).

The requirements are:

• The grid search has to stop after n_iter instead of searching the entire search space
• The positions should not be precalculated at the beginning of the optimization (i have concerns about memory load).

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