lightautoml.tasks.losses
Wrappers of loss and metric functions for different machine learning algorithms.
Base Classes
Wrapper for metric. |
|
Loss function with target transformation. |
Wrappers for LightGBM
Classes
Wrapper of metric function for LightGBM. |
|
Loss used for LightGBM. |
Functions
Softmax columnwise. |
|
Custom loss for optimizing f1. |
Wrappers for CatBoost
Classes
Loss used for CatBoost. |
|
Metric wrapper class for CatBoost. |
|
Regression metric wrapper for CatBoost. |
|
Classification metric wrapper for CatBoost. |
|
Multiclassification metric wrapper for CatBoost. |
Functions
CatBoost loss name wrapper, if it has keyword args. |
Wrappers for Sklearn
Classes
Loss used for scikit-learn. |
Wrappers for Torch
Classes
Customize PyTorch-based loss. |
|
Loss used for PyTorch. |
Functions
Computes Root Mean Squared Logarithmic Error. |
|
Computes Mean Quantile Error. |
|
Computes Mean Fair Error. |
|
Computes Mean Huber Error. |
|
Computes F1 macro. |
|
Computes Mean Absolute Percentage Error. |