-
Notifications
You must be signed in to change notification settings - Fork 16
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
xgboost classification specification
- Loading branch information
Showing
3 changed files
with
163 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,155 @@ | ||
| { | ||
| "id": "ml_fit_class_xgboost", | ||
| "summary": "Train an XGBoost classification model", | ||
| "description": "Executes the fit of an XGBoost classification model based on training data.", | ||
| "categories": [ | ||
| "machine learning" | ||
| ], | ||
| "experimental": true, | ||
| "parameters": [ | ||
| { | ||
| "name": "predictors", | ||
| "description": "The predictors for the XGBoost classification model as a vector data cube. Aggregated to the features (vectors) of the target input variable.", | ||
| "schema": { | ||
| "type": "object", | ||
| "subtype": "datacube", | ||
| "dimensions": [ | ||
| { | ||
| "type": "geometry" | ||
| }, | ||
| { | ||
| "type": "bands" | ||
| } | ||
| ] | ||
| } | ||
| }, | ||
| { | ||
| "name": "target", | ||
| "description": "Labeled data for XGBoost classification, aligning with predictor values based on a shared geometry dimension. This ensures a clear connection between predictor rows and labels, allowing the model to associate specific predictor values with rows during training.", | ||
| "schema": { | ||
| "type": "object", | ||
| "subtype": "datacube", | ||
| "dimensions": [ | ||
| { | ||
| "type": "geometry" | ||
| } | ||
| ] | ||
| } | ||
| }, | ||
| { | ||
| "name": "learning_rate", | ||
| "description": "Step size shrinkage used in update to prevent overfitting.", | ||
| "schema": { | ||
| "type": "number", | ||
| "minimum": 0, | ||
| "default": 0.15 | ||
| } | ||
| }, | ||
| { | ||
| "name": "max_depth", | ||
| "description": "Maximum depth of a tree.", | ||
| "schema": { | ||
| "type": "integer", | ||
| "minimum": 1, | ||
| "default": 5 | ||
| } | ||
| }, | ||
| { | ||
| "name": "min_child_weight", | ||
| "description": "Minimum sum of instance weight (hessian) needed in a child.", | ||
| "schema": { | ||
| "type": "number", | ||
| "minimum": 0, | ||
| "default": 1 | ||
| } | ||
| }, | ||
| { | ||
| "name": "subsample", | ||
| "description": "Subsample ratio of the training instance.", | ||
| "optional": true, | ||
| "default": 0.8, | ||
| "schema": { | ||
| "type": "number", | ||
| "minimum": 0, | ||
| "maximum": 1 | ||
| } | ||
| }, | ||
| { | ||
| "name": "min_split_loss", | ||
| "description": "Minimum loss reduction required to make a further partition on a leaf node of the tree.", | ||
| "optional": true, | ||
| "default": 1, | ||
| "schema": { | ||
| "type": "number", | ||
| "minimum": 0 | ||
| } | ||
| }, | ||
| { | ||
| "name": "max_delta_step", | ||
| "description": "Maximum delta step we allow each tree's weight estimation to be.", | ||
| "optional": true, | ||
| "default": 1, | ||
| "schema": { | ||
| "type": "number", | ||
| "minimum": 0 | ||
| } | ||
| }, | ||
| { | ||
| "name": "nfold", | ||
| "description": "Number of folds for cross-validation.", | ||
| "optional": true, | ||
| "default": 5, | ||
| "schema": { | ||
| "type": "integer", | ||
| "minimum": 2 | ||
| } | ||
| }, | ||
| { | ||
| "name": "nrounds", | ||
| "description": "Number of boosting rounds.", | ||
| "optional": true, | ||
| "default": 100, | ||
| "schema": { | ||
| "type": "integer", | ||
| "minimum": 1 | ||
| } | ||
| }, | ||
| { | ||
| "name": "early_stopping_rounds", | ||
| "description": "Activates early stopping. Validation metric needs to improve at least once in every early_stopping_rounds round(s) to continue training.", | ||
| "optional": true, | ||
| "default": 20, | ||
| "schema": { | ||
| "type": "integer", | ||
| "minimum": 1 | ||
| } | ||
| }, | ||
| { | ||
| "name": "seed", | ||
| "description": "A randomization seed to use for the random sampling in training. If not given or `null`, no seed is used and results may differ on subsequent use.", | ||
| "optional": true, | ||
| "default": null, | ||
| "schema": { | ||
| "type": [ | ||
| "integer", | ||
| "null" | ||
| ] | ||
| } | ||
| } | ||
| ], | ||
| "returns": { | ||
| "description": "A model object that can be saved with `save_ml_model()` and restored with `load_ml_model()`.", | ||
| "schema": { | ||
| "type": "object", | ||
| "subtype": "ml-model" | ||
| } | ||
| }, | ||
| "links": [ | ||
| { | ||
| "href": "https://dl.acm.org/doi/10.1145/2939672.2939785", | ||
| "title": "Chen and Guestrin (2016), XGBoost: A Scalable Tree Boosting System", | ||
| "type": "text/html", | ||
| "rel": "about" | ||
| } | ||
| ] | ||
| } |