Table 9 Overview of hyperparameters for classification Models.
From: Harnessing machine learning to find synergistic combinations for FDA-approved cancer drugs
Classifier | Hyperparameters | Description | Value |
|---|---|---|---|
Naive Bayes (Naive) | No hyperparameters | No hyperparameters are specified for Naive Bayes | N/A |
Random Forest (RF) | - n_estimators | Number of trees in the forest | 100 |
- max_depth | Maximum depth of the tree | None (i.e., nodes are expanded until containing less than min_samples_split samples) | |
- min_samples_split | Minimum samples required to split a node | 2 | |
- min_samples_leaf | Minimum samples required to be at a leaf node | 1 | |
K-Nearest Neighbors (KNN) | - n_neighbors | Number of neighbors to use for classification | 5 |
- weights | Weight function used in prediction | ‘uniform’ | |
- algorithm | Algorithm used to compute nearest neighbors | ‘auto’ | |
Logistic Regression (LR) | - C | Inverse of regularization strength | 1.0 |
- penalty | Type of regularization | ‘l2’ |
