It's running so slow! | Understanding the inputs | The input data | The methods we support | Before running ML | The simplest way to run_ml() | Customizing parameters | Changing kfold, cv_times, and training_frac | Custom training indices | Changing the performance metric | Using groups | Controlling how groups are assigned to partitions | More arguments | Case weights | Finding feature importance | Tuning hyperparameters (using the hyperparameter argument) | Other models | Random forest | Decision tree | SVM | Other data | Multiclass data | Continuous data | References

Summary | Statement of need | mikropml package | Preprocessing data | Running ML | Ideal workflow for running mikropml with many different train/test splits | Tuning & visualization | Dependencies | Acknowledgments | Funding | Author contributions | Conflicts of interest | References

Background | Starting Up | Read count files | Read distance matrix file | Clustering the data | Selecting different clustering methods | Output data from clustering