scikit-lego
scikit-lego copied to clipboard
koaning
Extra blocks for scikit-learn pipelines.
When using `predict_proba(newdata)` with a `BayesianGMMClassifier` model, I get 2 col vectors one filled with 1 and the other filled with 0. However, when using `predict_proba(train_X)` where "train_X" is the...
I am unable to find any API doc of RepeatingBasisFunction (Specially the input parameters), and any background information about how Repeating Basis function works.
In the notebook there is a line that says: "Let's consider the number 0.2346 in the lower left corner. " There is no such number.
With 3.10 inbound, it'd be good to check. https://twitter.com/hugovk/status/1443212543590387713
Feels like a good thing to add.
is it possible to use custom optimizer for QuantileRegression optimizer but not current the SLSQP algorithm for example to use available in scipy ? https://docs.scipy.org/doc/scipy/reference/generated/scipy.optimize.minimize.html#scipy.optimize.minimize since SLSQP is slow and...
I am using the ZeroInflatedRegressor for the prediction of some materials' prices. For some materials I am getting this error: ``` Traceback (most recent call last): File "/home/bugra/project-mats/mat_analyser.py", line 61,...
Hi again! When using the `DecayEstimator` inside the `ZeroInflatedRegressor` an error occurred, because DecayEstimator is neither a regressor nor a classifier. ```python from sklego.meta import DecayEstimator from sklearn.base import is_regressor,...
Hi! First of all thanks for your package, it's awesome! (Same as calmcode and other resources you built). I'm trying to perform a LeaveOneOutEncoder transformation for each group of my...
Heya! How about some meta model for time series? It can consist of two models, such as in the ZeroInflatedRegressor: One model to capture trend (and optionally seasonality) of the...