cellcanvas / train-model-lightgbm / 0.0.2

Train LightGBM on Zarr Data with Cross-Validation

A solution that trains a LightGBM model using data from a Zarr zip store, filters runs with only one label, and performs 10-fold cross-validation.
Tags
imagingcryoetPythonnapari
Solution written by
Kyle Harrington
License of solution
MIT
Source Code

Arguments

--input_zarr_path
Path to the input Zarr zip store containing the features and labels. (default value: PARAMETER_VALUE)
--output_model_path
Path for the output joblib file containing the trained LightGBM model. (default value: PARAMETER_VALUE)
--n_estimators
Number of trees in the LightGBM model. (default value: 750)
--max_depth
The maximum depth of the trees. (default value: 18)
--learning_rate
The learning rate. (default value: 0.1)
--num_leaves
Maximum number of leaves. (default value: 31)
--class_weights
Class weights for the LightGBM model as a comma-separated list. (default value: )

Usage instructions

Please follow this link for details on how to install and run this solution.