R/xgboost.R
Builds a eXtreme Gradient Boosting model using the native XGBoost backend.
h2o.xgboost(x, y, training_frame, model_id = NULL, validation_frame = NULL, nfolds = 0, keep_cross_validation_predictions = FALSE, keep_cross_validation_fold_assignment = FALSE, score_each_iteration = FALSE, fold_assignment = c("AUTO", "Random", "Modulo", "Stratified"), fold_column = NULL, ignore_const_cols = TRUE, offset_column = NULL, weights_column = NULL, stopping_rounds = 0, stopping_metric = c("AUTO", "deviance", "logloss", "MSE", "RMSE", "MAE", "RMSLE", "AUC", "lift_top_group", "misclassification", "mean_per_class_error"), stopping_tolerance = 0.001, max_runtime_secs = 0, seed = -1, distribution = c("AUTO", "bernoulli", "multinomial", "gaussian", "poisson", "gamma", "tweedie", "laplace", "quantile", "huber"), tweedie_power = 1.5, categorical_encoding = c("AUTO", "Enum", "OneHotInternal", "OneHotExplicit", "Binary", "Eigen", "LabelEncoder", "SortByResponse", "EnumLimited"), quiet_mode = TRUE, ntrees = 50, max_depth = 6, min_rows = 1, min_child_weight = 1, learn_rate = 0.3, eta = 0.3, sample_rate = 1, subsample = 1, col_sample_rate = 1, colsample_bylevel = 1, col_sample_rate_per_tree = 1, colsample_bytree = 1, max_abs_leafnode_pred = 0, max_delta_step = 0, score_tree_interval = 0, min_split_improvement = 0, gamma = 0, max_bins = 256, max_leaves = 0, min_sum_hessian_in_leaf = 100, min_data_in_leaf = 0, sample_type = c("uniform", "weighted"), normalize_type = c("tree", "forest"), rate_drop = 0, one_drop = FALSE, skip_drop = 0, tree_method = c("auto", "exact", "approx", "hist"), grow_policy = c("depthwise", "lossguide"), booster = c("gbtree", "gblinear", "dart"), reg_lambda = 0, reg_alpha = 0, dmatrix_type = c("auto", "dense", "sparse"), backend = c("auto", "gpu", "cpu"), gpu_id = 0, verbose = FALSE)
| x | (Optional) A vector containing the names or indices of the predictor variables to use in building the model. If x is missing, then all columns except y are used. |
|---|---|
| y | The name or column index of the response variable in the data. The response must be either a numeric or a categorical/factor variable. If the response is numeric, then a regression model will be trained, otherwise it will train a classification model. |
| training_frame | Id of the training data frame. |
| model_id | Destination id for this model; auto-generated if not specified. |
| validation_frame | Id of the validation data frame. |
| nfolds | Number of folds for K-fold cross-validation (0 to disable or >= 2). Defaults to 0. |
| keep_cross_validation_predictions |
|
| keep_cross_validation_fold_assignment |
|
| score_each_iteration |
|
| fold_assignment | Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified' option will stratify the folds based on the response variable, for classification problems. Must be one of: "AUTO", "Random", "Modulo", "Stratified". Defaults to AUTO. |
| fold_column | Column with cross-validation fold index assignment per observation. |
| ignore_const_cols |
|
| offset_column | Offset column. This will be added to the combination of columns before applying the link function. |
| weights_column | Column with observation weights. Giving some observation a weight of zero is equivalent to excluding it from the dataset; giving an observation a relative weight of 2 is equivalent to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row observation weights and do not increase the size of the data frame. This is typically the number of times a row is repeated, but non-integer values are supported as well. During training, rows with higher weights matter more, due to the larger loss function pre-factor. |
| stopping_rounds | Early stopping based on convergence of stopping_metric. Stop if simple moving average of length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0 to disable) Defaults to 0. |
| stopping_metric | Metric to use for early stopping (AUTO: logloss for classification, deviance for regression) Must be one of: "AUTO", "deviance", "logloss", "MSE", "RMSE", "MAE", "RMSLE", "AUC", "lift_top_group", "misclassification", "mean_per_class_error". Defaults to AUTO. |
| stopping_tolerance | Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) Defaults to 0.001. |
| max_runtime_secs | Maximum allowed runtime in seconds for model training. Use 0 to disable. Defaults to 0. |
| seed | Seed for random numbers (affects certain parts of the algo that are stochastic and those might or might not be enabled by default) Defaults to -1 (time-based random number). |
| distribution | Distribution function Must be one of: "AUTO", "bernoulli", "multinomial", "gaussian", "poisson", "gamma", "tweedie", "laplace", "quantile", "huber". Defaults to AUTO. |
| tweedie_power | Tweedie power for Tweedie regression, must be between 1 and 2. Defaults to 1.5. |
| categorical_encoding | Encoding scheme for categorical features Must be one of: "AUTO", "Enum", "OneHotInternal", "OneHotExplicit", "Binary", "Eigen", "LabelEncoder", "SortByResponse", "EnumLimited". Defaults to AUTO. |
| quiet_mode |
|
| ntrees | (same as n_estimators) Number of trees. Defaults to 50. |
| max_depth | Maximum tree depth. Defaults to 6. |
| min_rows | (same as min_child_weight) Fewest allowed (weighted) observations in a leaf. Defaults to 1. |
| min_child_weight | (same as min_rows) Fewest allowed (weighted) observations in a leaf. Defaults to 1. |
| learn_rate | (same as eta) Learning rate (from 0.0 to 1.0) Defaults to 0.3. |
| eta | (same as learn_rate) Learning rate (from 0.0 to 1.0) Defaults to 0.3. |
| sample_rate | (same as subsample) Row sample rate per tree (from 0.0 to 1.0) Defaults to 1. |
| subsample | (same as sample_rate) Row sample rate per tree (from 0.0 to 1.0) Defaults to 1. |
| col_sample_rate | (same as colsample_bylevel) Column sample rate (from 0.0 to 1.0) Defaults to 1. |
| colsample_bylevel | (same as col_sample_rate) Column sample rate (from 0.0 to 1.0) Defaults to 1. |
| col_sample_rate_per_tree | (same as colsample_bytree) Column sample rate per tree (from 0.0 to 1.0) Defaults to 1. |
| colsample_bytree | (same as col_sample_rate_per_tree) Column sample rate per tree (from 0.0 to 1.0) Defaults to 1. |
| max_abs_leafnode_pred | (same as max_delta_step) Maximum absolute value of a leaf node prediction Defaults to 0.0. |
| max_delta_step | (same as max_abs_leafnode_pred) Maximum absolute value of a leaf node prediction Defaults to 0.0. |
| score_tree_interval | Score the model after every so many trees. Disabled if set to 0. Defaults to 0. |
| min_split_improvement | (same as gamma) Minimum relative improvement in squared error reduction for a split to happen Defaults to 0.0. |
| gamma | (same as min_split_improvement) Minimum relative improvement in squared error reduction for a split to happen Defaults to 0.0. |
| max_bins | For tree_method=hist only: maximum number of bins Defaults to 256. |
| max_leaves | For tree_method=hist only: maximum number of leaves Defaults to 0. |
| min_sum_hessian_in_leaf | For tree_method=hist only: the mininum sum of hessian in a leaf to keep splitting Defaults to 100.0. |
| min_data_in_leaf | For tree_method=hist only: the mininum data in a leaf to keep splitting Defaults to 0.0. |
| sample_type | For booster=dart only: sample_type Must be one of: "uniform", "weighted". Defaults to uniform. |
| normalize_type | For booster=dart only: normalize_type Must be one of: "tree", "forest". Defaults to tree. |
| rate_drop | For booster=dart only: rate_drop (0..1) Defaults to 0.0. |
| one_drop |
|
| skip_drop | For booster=dart only: skip_drop (0..1) Defaults to 0.0. |
| tree_method | Tree method Must be one of: "auto", "exact", "approx", "hist". Defaults to auto. |
| grow_policy | Grow policy - depthwise is standard GBM, lossguide is LightGBM Must be one of: "depthwise", "lossguide". Defaults to depthwise. |
| booster | Booster type Must be one of: "gbtree", "gblinear", "dart". Defaults to gbtree. |
| reg_lambda | L2 regularization Defaults to 0.0. |
| reg_alpha | L1 regularization Defaults to 0.0. |
| dmatrix_type | Type of DMatrix. For sparse, NAs and 0 are treated equally. Must be one of: "auto", "dense", "sparse". Defaults to auto. |
| backend | Backend. By default (auto), a GPU is used if available. Must be one of: "auto", "gpu", "cpu". Defaults to auto. |
| gpu_id | Which GPU to use. Defaults to 0. |
| verbose |
|