Source code for h2o.estimators.gbm

#!/usr/bin/env python
# -*- encoding: utf-8 -*-
#
# This file is auto-generated by h2o-3/h2o-bindings/bin/gen_python.py
# Copyright 2016 H2O.ai;  Apache License Version 2.0 (see LICENSE for details)
#
from __future__ import absolute_import, division, print_function, unicode_literals

from h2o.estimators.estimator_base import H2OEstimator
from h2o.exceptions import H2OValueError
from h2o.frame import H2OFrame
from h2o.utils.typechecks import assert_is_type, Enum, numeric


[docs]class H2OGradientBoostingEstimator(H2OEstimator): """ Gradient Boosting Machine Builds gradient boosted trees on a parsed data set, for regression or classification. The default distribution function will guess the model type based on the response column type. Otherwise, the response column must be an enum for "bernoulli" or "multinomial", and numeric for all other distributions. """ algo = "gbm" param_names = {"model_id", "training_frame", "validation_frame", "nfolds", "keep_cross_validation_models", "keep_cross_validation_predictions", "keep_cross_validation_fold_assignment", "score_each_iteration", "score_tree_interval", "fold_assignment", "fold_column", "response_column", "ignored_columns", "ignore_const_cols", "offset_column", "weights_column", "balance_classes", "class_sampling_factors", "max_after_balance_size", "max_confusion_matrix_size", "ntrees", "max_depth", "min_rows", "nbins", "nbins_top_level", "nbins_cats", "r2_stopping", "stopping_rounds", "stopping_metric", "stopping_tolerance", "max_runtime_secs", "seed", "build_tree_one_node", "learn_rate", "learn_rate_annealing", "distribution", "quantile_alpha", "tweedie_power", "huber_alpha", "checkpoint", "sample_rate", "sample_rate_per_class", "col_sample_rate", "col_sample_rate_change_per_level", "col_sample_rate_per_tree", "min_split_improvement", "histogram_type", "max_abs_leafnode_pred", "pred_noise_bandwidth", "categorical_encoding", "calibrate_model", "calibration_frame", "custom_metric_func", "custom_distribution_func", "export_checkpoints_dir", "monotone_constraints", "check_constant_response", "gainslift_bins", "auc_type"} def __init__(self, **kwargs): super(H2OGradientBoostingEstimator, self).__init__() self._parms = {} for pname, pvalue in kwargs.items(): if pname == 'model_id': self._id = pvalue self._parms["model_id"] = pvalue elif pname in self.param_names: # Using setattr(...) will invoke type-checking of the arguments setattr(self, pname, pvalue) else: raise H2OValueError("Unknown parameter %s = %r" % (pname, pvalue)) @property def training_frame(self): """ Id of the training data frame. Type: ``H2OFrame``. :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> train, valid = cars.split_frame(ratios=[.8], seed=1234) >>> cars_gbm = H2OGradientBoostingEstimator(seed=1234) >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cars_gbm.auc(valid=True) """ return self._parms.get("training_frame") @training_frame.setter def training_frame(self, training_frame): self._parms["training_frame"] = H2OFrame._validate(training_frame, 'training_frame') @property def validation_frame(self): """ Id of the validation data frame. Type: ``H2OFrame``. :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> train, valid = cars.split_frame(ratios=[.8], seed=1234) >>> cars_gbm = H2OGradientBoostingEstimator(seed=1234) >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cars_gbm.auc(valid=True) """ return self._parms.get("validation_frame") @validation_frame.setter def validation_frame(self, validation_frame): self._parms["validation_frame"] = H2OFrame._validate(validation_frame, 'validation_frame') @property def nfolds(self): """ Number of folds for K-fold cross-validation (0 to disable or >= 2). Type: ``int`` (default: ``0``). :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> folds = 5 >>> cars_gbm = H2OGradientBoostingEstimator(nfolds=folds, ... seed=1234 >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=cars) >>> cars_gbm.auc() """ return self._parms.get("nfolds") @nfolds.setter def nfolds(self, nfolds): assert_is_type(nfolds, None, int) self._parms["nfolds"] = nfolds @property def keep_cross_validation_models(self): """ Whether to keep the cross-validation models. Type: ``bool`` (default: ``True``). :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> folds = 5 >>> train, valid = cars.split_frame(ratios=[.8], seed=1234) >>> cars_gbm = H2OGradientBoostingEstimator(keep_cross_validation_models=True, ... nfolds=5, ... seed=1234) >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cars_gbm.auc() """ return self._parms.get("keep_cross_validation_models") @keep_cross_validation_models.setter def keep_cross_validation_models(self, keep_cross_validation_models): assert_is_type(keep_cross_validation_models, None, bool) self._parms["keep_cross_validation_models"] = keep_cross_validation_models @property def keep_cross_validation_predictions(self): """ Whether to keep the predictions of the cross-validation models. Type: ``bool`` (default: ``False``). :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> folds = 5 >>> train, valid = cars.split_frame(ratios=[.8], seed=1234) >>> cars_gbm = H2OGradientBoostingEstimator(keep_cross_validation_predictions=True, ... nfolds=5, ... seed=1234) >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cars_gbm.auc() """ return self._parms.get("keep_cross_validation_predictions") @keep_cross_validation_predictions.setter def keep_cross_validation_predictions(self, keep_cross_validation_predictions): assert_is_type(keep_cross_validation_predictions, None, bool) self._parms["keep_cross_validation_predictions"] = keep_cross_validation_predictions @property def keep_cross_validation_fold_assignment(self): """ Whether to keep the cross-validation fold assignment. Type: ``bool`` (default: ``False``). :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> folds = 5 >>> train, valid = cars.split_frame(ratios=[.8], seed=1234) >>> cars_gbm = H2OGradientBoostingEstimator(keep_cross_validation_fold_assignment=True, ... nfolds=5, ... seed=1234) >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cars_gbm.auc() """ return self._parms.get("keep_cross_validation_fold_assignment") @keep_cross_validation_fold_assignment.setter def keep_cross_validation_fold_assignment(self, keep_cross_validation_fold_assignment): assert_is_type(keep_cross_validation_fold_assignment, None, bool) self._parms["keep_cross_validation_fold_assignment"] = keep_cross_validation_fold_assignment @property def score_each_iteration(self): """ Whether to score during each iteration of model training. Type: ``bool`` (default: ``False``). :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> train, valid = cars.split_frame(ratios=[.8], ... seed=1234) >>> cars_gbm = H2OGradientBoostingEstimator(score_each_iteration=True, ... ntrees=55, ... seed=1234) >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cars_gbm.scoring_history() """ return self._parms.get("score_each_iteration") @score_each_iteration.setter def score_each_iteration(self, score_each_iteration): assert_is_type(score_each_iteration, None, bool) self._parms["score_each_iteration"] = score_each_iteration @property def score_tree_interval(self): """ Score the model after every so many trees. Disabled if set to 0. Type: ``int`` (default: ``0``). :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> train, valid = cars.split_frame(ratios=[.8], ... seed=1234) >>> cars_gbm = H2OGradientBoostingEstimator(score_tree_interval=True, ... ntrees=55, ... seed=1234) >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cars_gbm.scoring_history() """ return self._parms.get("score_tree_interval") @score_tree_interval.setter def score_tree_interval(self, score_tree_interval): assert_is_type(score_tree_interval, None, int) self._parms["score_tree_interval"] = score_tree_interval @property def fold_assignment(self): """ 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. One of: ``"auto"``, ``"random"``, ``"modulo"``, ``"stratified"`` (default: ``"auto"``). :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> assignment_type = "Random" >>> cars_gbm = H2OGradientBoostingEstimator(fold_assignment=assignment_type, ... nfolds=5, ... seed=1234) >>> cars_gbm.train(x=predictors, y=response, training_frame=cars) >>> cars_gbm.auc(xval=True) """ return self._parms.get("fold_assignment") @fold_assignment.setter def fold_assignment(self, fold_assignment): assert_is_type(fold_assignment, None, Enum("auto", "random", "modulo", "stratified")) self._parms["fold_assignment"] = fold_assignment @property def fold_column(self): """ Column with cross-validation fold index assignment per observation. Type: ``str``. :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> fold_numbers = cars.kfold_column(n_folds=5, ... seed=1234) >>> fold_numbers.set_names(["fold_numbers"]) >>> cars = cars.cbind(fold_numbers) >>> cars_gbm = H2OGradientBoostingEstimator(seed=1234) >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=cars, ... fold_column="fold_numbers") >>> cars_gbm.auc(xval=True) """ return self._parms.get("fold_column") @fold_column.setter def fold_column(self, fold_column): assert_is_type(fold_column, None, str) self._parms["fold_column"] = fold_column @property def response_column(self): """ Response variable column. Type: ``str``. """ return self._parms.get("response_column") @response_column.setter def response_column(self, response_column): assert_is_type(response_column, None, str) self._parms["response_column"] = response_column @property def ignored_columns(self): """ Names of columns to ignore for training. Type: ``List[str]``. """ return self._parms.get("ignored_columns") @ignored_columns.setter def ignored_columns(self, ignored_columns): assert_is_type(ignored_columns, None, [str]) self._parms["ignored_columns"] = ignored_columns @property def ignore_const_cols(self): """ Ignore constant columns. Type: ``bool`` (default: ``True``). :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> cars["const_1"] = 6 >>> cars["const_2"] = 7 >>> train, valid = cars.split_frame(ratios=[.8], seed=1234) >>> cars_gbm = H2OGradientBoostingEstimator(seed=1234, ... ignore_const_cols=True) >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cars_gbm.auc(valid=True) """ return self._parms.get("ignore_const_cols") @ignore_const_cols.setter def ignore_const_cols(self, ignore_const_cols): assert_is_type(ignore_const_cols, None, bool) self._parms["ignore_const_cols"] = ignore_const_cols @property def offset_column(self): """ Offset column. This will be added to the combination of columns before applying the link function. Type: ``str``. :examples: >>> boston = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/gbm_test/BostonHousing.csv") >>> predictors = boston.columns[:-1] >>> response = "medv" >>> boston['chas'] = boston['chas'].asfactor() >>> boston["offset"] = boston["medv"].log() >>> train, valid = boston.split_frame(ratios=[.8], seed=1234) >>> boston_gbm = H2OGradientBoostingEstimator(offset_column="offset", ... seed=1234) >>> boston_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> boston_gbm.mse(valid=True) """ return self._parms.get("offset_column") @offset_column.setter def offset_column(self, offset_column): assert_is_type(offset_column, None, str) self._parms["offset_column"] = offset_column @property def weights_column(self): """ 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. Type: ``str``. :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> train, valid = cars.split_frame(ratios=[.8], seed=1234) >>> cars_gbm = H2OGradientBoostingEstimator(seed=1234) >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid, ... weights_column="weight") >>> cars_gbm.auc(valid=True) """ return self._parms.get("weights_column") @weights_column.setter def weights_column(self, weights_column): assert_is_type(weights_column, None, str) self._parms["weights_column"] = weights_column @property def balance_classes(self): """ Balance training data class counts via over/under-sampling (for imbalanced data). Type: ``bool`` (default: ``False``). :examples: >>> covtype = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/covtype/covtype.20k.data") >>> covtype[54] = covtype[54].asfactor() >>> predictors = covtype.columns[0:54] >>> response = 'C55' >>> train, valid = covtype.split_frame(ratios=[.8], seed=1234) >>> cov_gbm = H2OGradientBoostingEstimator(balance_classes=True, ... seed=1234) >>> cov_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cov_gbm.logloss(valid=True) """ return self._parms.get("balance_classes") @balance_classes.setter def balance_classes(self, balance_classes): assert_is_type(balance_classes, None, bool) self._parms["balance_classes"] = balance_classes @property def class_sampling_factors(self): """ Desired over/under-sampling ratios per class (in lexicographic order). If not specified, sampling factors will be automatically computed to obtain class balance during training. Requires balance_classes. Type: ``List[float]``. :examples: >>> covtype = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/covtype/covtype.20k.data") >>> covtype[54] = covtype[54].asfactor() >>> predictors = covtype.columns[0:54] >>> response = 'C55' >>> train, valid = covtype.split_frame(ratios=[.8], seed=1234) >>> sample_factors = [1., 0.5, 1., 1., 1., 1., 1.] >>> cov_gbm = H2OGradientBoostingEstimator(balance_classes=True, ... class_sampling_factors=sample_factors, ... seed=1234) >>> cov_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cov_gbm.logloss(valid=True) """ return self._parms.get("class_sampling_factors") @class_sampling_factors.setter def class_sampling_factors(self, class_sampling_factors): assert_is_type(class_sampling_factors, None, [float]) self._parms["class_sampling_factors"] = class_sampling_factors @property def max_after_balance_size(self): """ Maximum relative size of the training data after balancing class counts (can be less than 1.0). Requires balance_classes. Type: ``float`` (default: ``5``). :examples: >>> covtype = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/covtype/covtype.20k.data") >>> covtype[54] = covtype[54].asfactor() >>> predictors = covtype.columns[0:54] >>> response = 'C55' >>> train, valid = covtype.split_frame(ratios=[.8], seed=1234) >>> max = .85 >>> cov_gbm = H2OGradientBoostingEstimator(balance_classes=True, ... max_after_balance_size=max, ... seed=1234) >>> cov_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cov_gbm.logloss(valid=True) """ return self._parms.get("max_after_balance_size") @max_after_balance_size.setter def max_after_balance_size(self, max_after_balance_size): assert_is_type(max_after_balance_size, None, float) self._parms["max_after_balance_size"] = max_after_balance_size @property def max_confusion_matrix_size(self): """ [Deprecated] Maximum size (# classes) for confusion matrices to be printed in the Logs Type: ``int`` (default: ``20``). """ return self._parms.get("max_confusion_matrix_size") @max_confusion_matrix_size.setter def max_confusion_matrix_size(self, max_confusion_matrix_size): assert_is_type(max_confusion_matrix_size, None, int) self._parms["max_confusion_matrix_size"] = max_confusion_matrix_size @property def ntrees(self): """ Number of trees. Type: ``int`` (default: ``50``). :examples: >>> titanic = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/gbm_test/titanic.csv") >>> titanic['survived'] = titanic['survived'].asfactor() >>> predictors = titanic.columns >>> del predictors[1:3] >>> response = 'survived' >>> train, valid = titanic.split_frame(ratios=[.8], seed=1234) >>> tree_num = [20, 50, 80, 110, 140, 170, 200] >>> label = ["20", "50", "80", "110", "140", "170", "200"] >>> for key, num in enumerate(tree_num): ... titanic_gbm = H2OGradientBoostingEstimator(ntrees=num, ... seed=1234) ... titanic_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) ... print(label[key], 'training score', titanic_gbm.auc(train=True)) ... print(label[key], 'validation score', titanic_gbm.auc(valid=True)) """ return self._parms.get("ntrees") @ntrees.setter def ntrees(self, ntrees): assert_is_type(ntrees, None, int) self._parms["ntrees"] = ntrees @property def max_depth(self): """ Maximum tree depth (0 for unlimited). Type: ``int`` (default: ``5``). :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> train, valid = cars.split_frame(ratios=[.8], seed=1234) >>> cars_gbm = H2OGradientBoostingEstimator(ntrees=100, ... max_depth=2, ... seed=1234) >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cars_gbm.auc(valid=True) """ return self._parms.get("max_depth") @max_depth.setter def max_depth(self, max_depth): assert_is_type(max_depth, None, int) self._parms["max_depth"] = max_depth @property def min_rows(self): """ Fewest allowed (weighted) observations in a leaf. Type: ``float`` (default: ``10``). :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> train, valid = cars.split_frame(ratios=[.8], seed=1234) >>> cars_gbm = H2OGradientBoostingEstimator(min_rows=16, ... seed=1234) >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cars_gbm.auc(valid=True) """ return self._parms.get("min_rows") @min_rows.setter def min_rows(self, min_rows): assert_is_type(min_rows, None, numeric) self._parms["min_rows"] = min_rows @property def nbins(self): """ For numerical columns (real/int), build a histogram of (at least) this many bins, then split at the best point Type: ``int`` (default: ``20``). :examples: >>> eeg = h2o.import_file("https://h2o-public-test-data.s3.amazonaws.com/smalldata/eeg/eeg_eyestate.csv") >>> eeg['eyeDetection'] = eeg['eyeDetection'].asfactor() >>> predictors = eeg.columns[:-1] >>> response = 'eyeDetection' >>> train, valid = eeg.split_frame(ratios=[.8], seed=1234) >>> bin_num = [16, 32, 64, 128, 256, 512] >>> label = ["16", "32", "64", "128", "256", "512"] >>> for key, num in enumerate(bin_num): ... eeg_gbm = H2OGradientBoostingEstimator(nbins=num, seed=1234) ... eeg_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) ... print(label[key], 'training score', eeg_gbm.auc(train=True)) ... print(label[key], 'validation score', eeg_gbm.auc(valid=True)) """ return self._parms.get("nbins") @nbins.setter def nbins(self, nbins): assert_is_type(nbins, None, int) self._parms["nbins"] = nbins @property def nbins_top_level(self): """ For numerical columns (real/int), build a histogram of (at most) this many bins at the root level, then decrease by factor of two per level Type: ``int`` (default: ``1024``). :examples: >>> eeg = h2o.import_file("https://h2o-public-test-data.s3.amazonaws.com/smalldata/eeg/eeg_eyestate.csv") >>> eeg['eyeDetection'] = eeg['eyeDetection'].asfactor() >>> predictors = eeg.columns[:-1] >>> response = 'eyeDetection' >>> train, valid = eeg.split_frame(ratios=[.8], seed=1234) >>> bin_num = [32, 64, 128, 256, 512, 1024, 2048, 4096] >>> label = ["32", "64", "128", "256", "512", "1024", "2048", "4096"] >>> for key, num in enumerate(bin_num): ... eeg_gbm = H2OGradientBoostingEstimator(nbins_top_level=num, seed=1234) ... eeg_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) ... print(label[key], 'training score', eeg_gbm.auc(train=True)) ... print(label[key], 'validation score', eeg_gbm.auc(valid=True)) """ return self._parms.get("nbins_top_level") @nbins_top_level.setter def nbins_top_level(self, nbins_top_level): assert_is_type(nbins_top_level, None, int) self._parms["nbins_top_level"] = nbins_top_level @property def nbins_cats(self): """ For categorical columns (factors), build a histogram of this many bins, then split at the best point. Higher values can lead to more overfitting. Type: ``int`` (default: ``1024``). :examples: >>> airlines= h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/airlines/allyears2k_headers.zip") >>> airlines["Year"] = airlines["Year"].asfactor() >>> airlines["Month"] = airlines["Month"].asfactor() >>> airlines["DayOfWeek"] = airlines["DayOfWeek"].asfactor() >>> airlines["Cancelled"] = airlines["Cancelled"].asfactor() >>> airlines['FlightNum'] = airlines['FlightNum'].asfactor() >>> predictors = ["Origin", "Dest", "Year", "UniqueCarrier", ... "DayOfWeek", "Month", "Distance", "FlightNum"] >>> response = "IsDepDelayed" >>> train, valid = airlines.split_frame(ratios=[.8], seed=1234) >>> bin_num = [8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096] >>> label = ["8", "16", "32", "64", "128", "256", "512", "1024", "2048", "4096"] >>> for key, num in enumerate(bin_num): ... airlines_gbm = H2OGradientBoostingEstimator(nbins_cats=num, seed=1234) ... airlines_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) ... print(label[key], 'training score', airlines_gbm.auc(train=True)) ... print(label[key], 'validation score', airlines_gbm.auc(valid=True)) """ return self._parms.get("nbins_cats") @nbins_cats.setter def nbins_cats(self, nbins_cats): assert_is_type(nbins_cats, None, int) self._parms["nbins_cats"] = nbins_cats @property def r2_stopping(self): """ r2_stopping is no longer supported and will be ignored if set - please use stopping_rounds, stopping_metric and stopping_tolerance instead. Previous version of H2O would stop making trees when the R^2 metric equals or exceeds this Type: ``float`` (default: ``1.797693135e+308``). """ return self._parms.get("r2_stopping") @r2_stopping.setter def r2_stopping(self, r2_stopping): assert_is_type(r2_stopping, None, numeric) self._parms["r2_stopping"] = r2_stopping @property def stopping_rounds(self): """ 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) Type: ``int`` (default: ``0``). :examples: >>> airlines= h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/airlines/allyears2k_headers.zip") >>> airlines["Year"] = airlines["Year"].asfactor() >>> airlines["Month"] = airlines["Month"].asfactor() >>> airlines["DayOfWeek"] = airlines["DayOfWeek"].asfactor() >>> airlines["Cancelled"] = airlines["Cancelled"].asfactor() >>> airlines['FlightNum'] = airlines['FlightNum'].asfactor() >>> predictors = ["Origin", "Dest", "Year", "UniqueCarrier", ... "DayOfWeek", "Month", "Distance", "FlightNum"] >>> response = "IsDepDelayed" >>> train, valid = airlines.split_frame(ratios=[.8], seed=1234) >>> airlines_gbm = H2OGradientBoostingEstimator(stopping_metric="auc", ... stopping_rounds=3, ... stopping_tolerance=1e-2, ... seed=1234) >>> airlines_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> airlines_gbm.auc(valid=True) """ return self._parms.get("stopping_rounds") @stopping_rounds.setter def stopping_rounds(self, stopping_rounds): assert_is_type(stopping_rounds, None, int) self._parms["stopping_rounds"] = stopping_rounds @property def stopping_metric(self): """ Metric to use for early stopping (AUTO: logloss for classification, deviance for regression and anonomaly_score for Isolation Forest). Note that custom and custom_increasing can only be used in GBM and DRF with the Python client. One of: ``"auto"``, ``"deviance"``, ``"logloss"``, ``"mse"``, ``"rmse"``, ``"mae"``, ``"rmsle"``, ``"auc"``, ``"aucpr"``, ``"lift_top_group"``, ``"misclassification"``, ``"mean_per_class_error"``, ``"custom"``, ``"custom_increasing"`` (default: ``"auto"``). :examples: >>> airlines= h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/airlines/allyears2k_headers.zip") >>> airlines["Year"] = airlines["Year"].asfactor() >>> airlines["Month"] = airlines["Month"].asfactor() >>> airlines["DayOfWeek"] = airlines["DayOfWeek"].asfactor() >>> airlines["Cancelled"] = airlines["Cancelled"].asfactor() >>> airlines['FlightNum'] = airlines['FlightNum'].asfactor() >>> predictors = ["Origin", "Dest", "Year", "UniqueCarrier", ... "DayOfWeek", "Month", "Distance", "FlightNum"] >>> response = "IsDepDelayed" >>> train, valid = airlines.split_frame(ratios=[.8], seed=1234) >>> airlines_gbm = H2OGradientBoostingEstimator(stopping_metric="auc", ... stopping_rounds=3, ... stopping_tolerance=1e-2, ... seed=1234) >>> airlines_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> airlines_gbm.auc(valid=True) """ return self._parms.get("stopping_metric") @stopping_metric.setter def stopping_metric(self, stopping_metric): assert_is_type(stopping_metric, None, Enum("auto", "deviance", "logloss", "mse", "rmse", "mae", "rmsle", "auc", "aucpr", "lift_top_group", "misclassification", "mean_per_class_error", "custom", "custom_increasing")) self._parms["stopping_metric"] = stopping_metric @property def stopping_tolerance(self): """ Relative tolerance for metric-based stopping criterion (stop if relative improvement is not at least this much) Type: ``float`` (default: ``0.001``). :examples: >>> airlines= h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/airlines/allyears2k_headers.zip") >>> airlines["Year"] = airlines["Year"].asfactor() >>> airlines["Month"] = airlines["Month"].asfactor() >>> airlines["DayOfWeek"] = airlines["DayOfWeek"].asfactor() >>> airlines["Cancelled"] = airlines["Cancelled"].asfactor() >>> airlines['FlightNum'] = airlines['FlightNum'].asfactor() >>> predictors = ["Origin", "Dest", "Year", "UniqueCarrier", ... "DayOfWeek", "Month", "Distance", "FlightNum"] >>> response = "IsDepDelayed" >>> train, valid= airlines.split_frame(ratios=[.8], seed=1234) >>> airlines_gbm = H2OGradientBoostingEstimator(stopping_metric="auc", ... stopping_rounds=3, ... stopping_tolerance=1e-2, ... seed=1234) >>> airlines_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> airlines_gbm.auc(valid=True) """ return self._parms.get("stopping_tolerance") @stopping_tolerance.setter def stopping_tolerance(self, stopping_tolerance): assert_is_type(stopping_tolerance, None, numeric) self._parms["stopping_tolerance"] = stopping_tolerance @property def max_runtime_secs(self): """ Maximum allowed runtime in seconds for model training. Use 0 to disable. Type: ``float`` (default: ``0``). :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> train, valid = cars.split_frame(ratios=[.8], seed=1234) >>> cars_gbm = H2OGradientBoostingEstimator(max_runtime_secs=10, ... ntrees=10000, ... max_depth=10, ... seed=1234) >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cars_gbm.auc(valid=True) """ return self._parms.get("max_runtime_secs") @max_runtime_secs.setter def max_runtime_secs(self, max_runtime_secs): assert_is_type(max_runtime_secs, None, numeric) self._parms["max_runtime_secs"] = max_runtime_secs @property def seed(self): """ Seed for pseudo random number generator (if applicable) Type: ``int`` (default: ``-1``). :examples: >>> airlines= h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/airlines/allyears2k_headers.zip") >>> airlines["Year"] = airlines["Year"].asfactor() >>> airlines["Month"] = airlines["Month"].asfactor() >>> airlines["DayOfWeek"] = airlines["DayOfWeek"].asfactor() >>> airlines["Cancelled"] = airlines["Cancelled"].asfactor() >>> airlines['FlightNum'] = airlines['FlightNum'].asfactor() >>> predictors = ["Origin", "Dest", "Year", "UniqueCarrier", ... "DayOfWeek", "Month", "Distance", "FlightNum"] >>> response = "IsDepDelayed" >>> train, valid = airlines.split_frame(ratios=[.8], seed=1234) >>> gbm_w_seed_1 = H2OGradientBoostingEstimator(col_sample_rate=.7, ... seed=1234) >>> gbm_w_seed_1.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> print('auc for the 1st model built with a seed:', gbm_w_seed_1.auc(valid=True)) """ return self._parms.get("seed") @seed.setter def seed(self, seed): assert_is_type(seed, None, int) self._parms["seed"] = seed @property def build_tree_one_node(self): """ Run on one node only; no network overhead but fewer cpus used. Suitable for small datasets. Type: ``bool`` (default: ``False``). :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> train, valid = cars.split_frame(ratios=[.8], seed=1234) >>> cars_gbm = H2OGradientBoostingEstimator(build_tree_one_node=True, ... seed=1234) >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cars_gbm.auc(valid=True) """ return self._parms.get("build_tree_one_node") @build_tree_one_node.setter def build_tree_one_node(self, build_tree_one_node): assert_is_type(build_tree_one_node, None, bool) self._parms["build_tree_one_node"] = build_tree_one_node @property def learn_rate(self): """ Learning rate (from 0.0 to 1.0) Type: ``float`` (default: ``0.1``). :examples: >>> titanic = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/gbm_test/titanic.csv") >>> titanic['survived'] = titanic['survived'].asfactor() >>> predictors = titanic.columns >>> del predictors[1:3] >>> response = 'survived' >>> train, valid = titanic.split_frame(ratios=[.8], seed=1234) >>> titanic_gbm = H2OGradientBoostingEstimator(ntrees=10000, ... learn_rate=0.01, ... stopping_rounds=5, ... stopping_metric="AUC", ... stopping_tolerance=1e-4, ... seed=1234) >>> titanic_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> titanic_gbm.auc(valid=True) """ return self._parms.get("learn_rate") @learn_rate.setter def learn_rate(self, learn_rate): assert_is_type(learn_rate, None, numeric) self._parms["learn_rate"] = learn_rate @property def learn_rate_annealing(self): """ Scale the learning rate by this factor after each tree (e.g., 0.99 or 0.999) Type: ``float`` (default: ``1``). :examples: >>> titanic = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/gbm_test/titanic.csv") >>> titanic['survived'] = titanic['survived'].asfactor() >>> predictors = titanic.columns >>> del predictors[1:3] >>> response = 'survived' >>> train, valid = titanic.split_frame(ratios=[.8], seed=1234) >>> titanic_gbm = H2OGradientBoostingEstimator(ntrees=10000, ... learn_rate=0.05, ... learn_rate_annealing=.9, ... stopping_rounds=5, ... stopping_metric="AUC", ... stopping_tolerance=1e-4, ... seed=1234) >>> titanic_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> titanic_gbm.auc(valid=True) """ return self._parms.get("learn_rate_annealing") @learn_rate_annealing.setter def learn_rate_annealing(self, learn_rate_annealing): assert_is_type(learn_rate_annealing, None, numeric) self._parms["learn_rate_annealing"] = learn_rate_annealing @property def distribution(self): """ Distribution function One of: ``"auto"``, ``"bernoulli"``, ``"quasibinomial"``, ``"multinomial"``, ``"gaussian"``, ``"poisson"``, ``"gamma"``, ``"tweedie"``, ``"laplace"``, ``"quantile"``, ``"huber"``, ``"custom"`` (default: ``"auto"``). :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> response = "cylinders" >>> train, valid = cars.split_frame(ratios=[.8], seed=1234) >>> cars_gbm = H2OGradientBoostingEstimator(distribution="poisson", ... seed=1234) >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cars_gbm.mse(valid=True) """ return self._parms.get("distribution") @distribution.setter def distribution(self, distribution): assert_is_type(distribution, None, Enum("auto", "bernoulli", "quasibinomial", "multinomial", "gaussian", "poisson", "gamma", "tweedie", "laplace", "quantile", "huber", "custom")) self._parms["distribution"] = distribution @property def quantile_alpha(self): """ Desired quantile for Quantile regression, must be between 0 and 1. Type: ``float`` (default: ``0.5``). :examples: >>> boston = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/gbm_test/BostonHousing.csv") >>> predictors = boston.columns[:-1] >>> response = "medv" >>> boston['chas'] = boston['chas'].asfactor() >>> train, valid = boston.split_frame(ratios=[.8], seed=1234) >>> boston_gbm = H2OGradientBoostingEstimator(distribution="quantile", ... quantile_alpha=.8, ... seed=1234) >>> boston_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> boston_gbm.mse(valid=True) """ return self._parms.get("quantile_alpha") @quantile_alpha.setter def quantile_alpha(self, quantile_alpha): assert_is_type(quantile_alpha, None, numeric) self._parms["quantile_alpha"] = quantile_alpha @property def tweedie_power(self): """ Tweedie power for Tweedie regression, must be between 1 and 2. Type: ``float`` (default: ``1.5``). :examples: >>> insurance = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/glm_test/insurance.csv") >>> predictors = insurance.columns[0:4] >>> response = 'Claims' >>> insurance['Group'] = insurance['Group'].asfactor() >>> insurance['Age'] = insurance['Age'].asfactor() >>> train, valid = insurance.split_frame(ratios=[.8], seed=1234) >>> insurance_gbm = H2OGradientBoostingEstimator(distribution="tweedie", ... tweedie_power=1.2, ... seed=1234) >>> insurance_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> insurance_gbm.mse(valid=True) """ return self._parms.get("tweedie_power") @tweedie_power.setter def tweedie_power(self, tweedie_power): assert_is_type(tweedie_power, None, numeric) self._parms["tweedie_power"] = tweedie_power @property def huber_alpha(self): """ Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be between 0 and 1). Type: ``float`` (default: ``0.9``). :examples: >>> insurance = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/glm_test/insurance.csv") >>> predictors = insurance.columns[0:4] >>> response = 'Claims' >>> insurance['Group'] = insurance['Group'].asfactor() >>> insurance['Age'] = insurance['Age'].asfactor() >>> train, valid = insurance.split_frame(ratios=[.8], seed=1234) >>> insurance_gbm = H2OGradientBoostingEstimator(distribution="huber", ... huber_alpha=0.9, ... seed=1234) >>> insurance_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> insurance_gbm.mse(valid=True) """ return self._parms.get("huber_alpha") @huber_alpha.setter def huber_alpha(self, huber_alpha): assert_is_type(huber_alpha, None, numeric) self._parms["huber_alpha"] = huber_alpha @property def checkpoint(self): """ Model checkpoint to resume training with. Type: ``str``. :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> train, valid = cars.split_frame(ratios=[.8], seed=1234) >>> cars_gbm = H2OGradientBoostingEstimator(ntrees=1, ... seed=1234) >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> print(cars_gbm.auc(valid=True)) >>> print("Number of trees built for cars_gbm model:", cars_gbm.ntrees) >>> cars_gbm_continued = H2OGradientBoostingEstimator(checkpoint=cars_gbm.model_id, ... ntrees=50, ... seed=1234) >>> cars_gbm_continued.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cars_gbm_continued.auc(valid=True) >>> print("Number of trees built for cars_gbm model:",cars_gbm_continued.ntrees) """ return self._parms.get("checkpoint") @checkpoint.setter def checkpoint(self, checkpoint): assert_is_type(checkpoint, None, str, H2OEstimator) self._parms["checkpoint"] = checkpoint @property def sample_rate(self): """ Row sample rate per tree (from 0.0 to 1.0) Type: ``float`` (default: ``1``). :examples: >>> airlines= h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/airlines/allyears2k_headers.zip") >>> airlines["Month"] = airlines["Month"].asfactor() >>> airlines["Year"]= airlines["Year"].asfactor() >>> airlines["DayOfWeek"] = airlines["DayOfWeek"].asfactor() >>> airlines["Cancelled"] = airlines["Cancelled"].asfactor() >>> airlines['FlightNum'] = airlines['FlightNum'].asfactor() >>> predictors = ["Origin", "Dest", "Year", "UniqueCarrier", ... "DayOfWeek", "Month", "Distance", "FlightNum"] >>> response = "IsDepDelayed" >>> train, valid = airlines.split_frame(ratios=[.8], seed=1234) >>> airlines_gbm = H2OGradientBoostingEstimator(sample_rate=.7, ... seed=1234) >>> airlines_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> airlines_gbm.auc(valid=True) """ return self._parms.get("sample_rate") @sample_rate.setter def sample_rate(self, sample_rate): assert_is_type(sample_rate, None, numeric) self._parms["sample_rate"] = sample_rate @property def sample_rate_per_class(self): """ A list of row sample rates per class (relative fraction for each class, from 0.0 to 1.0), for each tree Type: ``List[float]``. :examples: >>> covtype = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/covtype/covtype.20k.data") >>> covtype[54] = covtype[54].asfactor() >>> predictors = covtype.columns[0:54] >>> response = 'C55' >>> train, valid = covtype.split_frame(ratios=[.8], seed=1234) >>> rate_per_class_list = [1, .4, 1, 1, 1, 1, 1] >>> cov_gbm = H2OGradientBoostingEstimator(sample_rate_per_class=rate_per_class_list, ... seed=1234) >>> cov_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cov_gbm.logloss(valid=True) """ return self._parms.get("sample_rate_per_class") @sample_rate_per_class.setter def sample_rate_per_class(self, sample_rate_per_class): assert_is_type(sample_rate_per_class, None, [numeric]) self._parms["sample_rate_per_class"] = sample_rate_per_class @property def col_sample_rate(self): """ Column sample rate (from 0.0 to 1.0) Type: ``float`` (default: ``1``). :examples: >>> airlines= h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/airlines/allyears2k_headers.zip") >>> airlines["Year"] = airlines["Year"].asfactor() >>> airlines["Month"] = airlines["Month"].asfactor() >>> airlines["DayOfWeek"] = airlines["DayOfWeek"].asfactor() >>> airlines["Cancelled"] = airlines["Cancelled"].asfactor() >>> airlines['FlightNum'] = airlines['FlightNum'].asfactor() >>> predictors = ["Origin", "Dest", "Year", "UniqueCarrier", ... "DayOfWeek", "Month", "Distance", "FlightNum"] >>> response = "IsDepDelayed" >>> train, valid = airlines.split_frame(ratios=[.8], seed=1234) >>> airlines_gbm = H2OGradientBoostingEstimator(col_sample_rate=.7, ... seed=1234) >>> airlines_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> airlines_gbm.auc(valid=True) """ return self._parms.get("col_sample_rate") @col_sample_rate.setter def col_sample_rate(self, col_sample_rate): assert_is_type(col_sample_rate, None, numeric) self._parms["col_sample_rate"] = col_sample_rate @property def col_sample_rate_change_per_level(self): """ Relative change of the column sampling rate for every level (must be > 0.0 and <= 2.0) Type: ``float`` (default: ``1``). :examples: >>> airlines= h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/airlines/allyears2k_headers.zip") >>> airlines["Year"] = airlines["Year"].asfactor() >>> airlines["Month"] = airlines["Month"].asfactor() >>> airlines["DayOfWeek"] = airlines["DayOfWeek"].asfactor() >>> airlines["Cancelled"] = airlines["Cancelled"].asfactor() >>> airlines['FlightNum'] = airlines['FlightNum'].asfactor() >>> predictors = ["Origin", "Dest", "Year", "UniqueCarrier", ... "DayOfWeek", "Month", "Distance", "FlightNum"] >>> response = "IsDepDelayed" >>> train, valid = airlines.split_frame(ratios=[.8], seed=1234) >>> airlines_gbm = H2OGradientBoostingEstimator(col_sample_rate_change_per_level=.9, ... seed=1234) >>> airlines_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> airlines_gbm.auc(valid=True) """ return self._parms.get("col_sample_rate_change_per_level") @col_sample_rate_change_per_level.setter def col_sample_rate_change_per_level(self, col_sample_rate_change_per_level): assert_is_type(col_sample_rate_change_per_level, None, numeric) self._parms["col_sample_rate_change_per_level"] = col_sample_rate_change_per_level @property def col_sample_rate_per_tree(self): """ Column sample rate per tree (from 0.0 to 1.0) Type: ``float`` (default: ``1``). :examples: >>> airlines= h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/airlines/allyears2k_headers.zip") >>> airlines["Year"] = airlines["Year"].asfactor() >>> airlines["Month"] = airlines["Month"].asfactor() >>> airlines["DayOfWeek"] = airlines["DayOfWeek"].asfactor() >>> airlines["Cancelled"] = airlines["Cancelled"].asfactor() >>> airlines['FlightNum'] = airlines['FlightNum'].asfactor() >>> predictors = ["Origin", "Dest", "Year", "UniqueCarrier", ... "DayOfWeek", "Month", "Distance", "FlightNum"] >>> response = "IsDepDelayed" >>> train, valid = airlines.split_frame(ratios=[.8], seed=1234) >>> airlines_gbm = H2OGradientBoostingEstimator(col_sample_rate_per_tree=.7, ... seed=1234) >>> airlines_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> airlines_gbm.auc(valid=True) """ return self._parms.get("col_sample_rate_per_tree") @col_sample_rate_per_tree.setter def col_sample_rate_per_tree(self, col_sample_rate_per_tree): assert_is_type(col_sample_rate_per_tree, None, numeric) self._parms["col_sample_rate_per_tree"] = col_sample_rate_per_tree @property def min_split_improvement(self): """ Minimum relative improvement in squared error reduction for a split to happen Type: ``float`` (default: ``1e-05``). :examples: >>> cars = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/junit/cars_20mpg.csv") >>> cars["economy_20mpg"] = cars["economy_20mpg"].asfactor() >>> predictors = ["displacement","power","weight","acceleration","year"] >>> response = "economy_20mpg" >>> train, valid = cars.split_frame(ratios=[.8], seed=1234) >>> cars_gbm = H2OGradientBoostingEstimator(min_split_improvement=1e-3, ... seed=1234) >>> cars_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cars_gbm.auc(valid=True) """ return self._parms.get("min_split_improvement") @min_split_improvement.setter def min_split_improvement(self, min_split_improvement): assert_is_type(min_split_improvement, None, numeric) self._parms["min_split_improvement"] = min_split_improvement @property def histogram_type(self): """ What type of histogram to use for finding optimal split points One of: ``"auto"``, ``"uniform_adaptive"``, ``"random"``, ``"quantiles_global"``, ``"round_robin"`` (default: ``"auto"``). :examples: >>> airlines= h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/airlines/allyears2k_headers.zip") >>> airlines["Year"] = airlines["Year"].asfactor() >>> airlines["Month"] = airlines["Month"].asfactor() >>> airlines["DayOfWeek"] = airlines["DayOfWeek"].asfactor() >>> airlines["Cancelled"] = airlines["Cancelled"].asfactor() >>> airlines['FlightNum'] = airlines['FlightNum'].asfactor() >>> predictors = ["Origin", "Dest", "Year", "UniqueCarrier", ... "DayOfWeek", "Month", "Distance", "FlightNum"] >>> response = "IsDepDelayed" >>> train, valid = airlines.split_frame(ratios=[.8], seed=1234) >>> airlines_gbm = H2OGradientBoostingEstimator(histogram_type="UniformAdaptive", ... seed=1234) >>> airlines_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> airlines_gbm.auc(valid=True) """ return self._parms.get("histogram_type") @histogram_type.setter def histogram_type(self, histogram_type): assert_is_type(histogram_type, None, Enum("auto", "uniform_adaptive", "random", "quantiles_global", "round_robin")) self._parms["histogram_type"] = histogram_type @property def max_abs_leafnode_pred(self): """ Maximum absolute value of a leaf node prediction Type: ``float`` (default: ``1.797693135e+308``). :examples: >>> covtype = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/covtype/covtype.20k.data") >>> covtype[54] = covtype[54].asfactor() >>> predictors = covtype.columns[0:54] >>> response = 'C55' >>> train, valid = covtype.split_frame(ratios=[.8], seed=1234) >>> cov_gbm = H2OGradientBoostingEstimator(max_abs_leafnode_pred=2, ... seed=1234) >>> cov_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> cov_gbm.logloss(valid=True) """ return self._parms.get("max_abs_leafnode_pred") @max_abs_leafnode_pred.setter def max_abs_leafnode_pred(self, max_abs_leafnode_pred): assert_is_type(max_abs_leafnode_pred, None, numeric) self._parms["max_abs_leafnode_pred"] = max_abs_leafnode_pred @property def pred_noise_bandwidth(self): """ Bandwidth (sigma) of Gaussian multiplicative noise ~N(1,sigma) for tree node predictions Type: ``float`` (default: ``0``). :examples: >>> titanic = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/gbm_test/titanic.csv") >>> titanic['survived'] = titanic['survived'].asfactor() >>> predictors = titanic.columns >>> del predictors[1:3] >>> response = 'survived' >>> train, valid = titanic.split_frame(ratios=[.8], seed=1234) >>> titanic_gbm = H2OGradientBoostingEstimator(pred_noise_bandwidth=0.1, ... seed=1234) >>> titanic_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> titanic_gbm.auc(valid = True) """ return self._parms.get("pred_noise_bandwidth") @pred_noise_bandwidth.setter def pred_noise_bandwidth(self, pred_noise_bandwidth): assert_is_type(pred_noise_bandwidth, None, numeric) self._parms["pred_noise_bandwidth"] = pred_noise_bandwidth @property def categorical_encoding(self): """ Encoding scheme for categorical features One of: ``"auto"``, ``"enum"``, ``"one_hot_internal"``, ``"one_hot_explicit"``, ``"binary"``, ``"eigen"``, ``"label_encoder"``, ``"sort_by_response"``, ``"enum_limited"`` (default: ``"auto"``). :examples: >>> airlines= h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/airlines/allyears2k_headers.zip") >>> airlines["Year"] = airlines["Year"].asfactor() >>> airlines["Month"] = airlines["Month"].asfactor() >>> airlines["DayOfWeek"] = airlines["DayOfWeek"].asfactor() >>> airlines["Cancelled"] = airlines["Cancelled"].asfactor() >>> airlines['FlightNum'] = airlines['FlightNum'].asfactor() >>> predictors = ["Origin", "Dest", "Year", "UniqueCarrier", ... "DayOfWeek", "Month", "Distance", "FlightNum"] >>> response = "IsDepDelayed" >>> train, valid = airlines.split_frame(ratios=[.8], seed=1234) >>> airlines_gbm = H2OGradientBoostingEstimator(categorical_encoding="labelencoder", ... seed=1234) >>> airlines_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> airlines_gbm.auc(valid=True) """ return self._parms.get("categorical_encoding") @categorical_encoding.setter def categorical_encoding(self, categorical_encoding): assert_is_type(categorical_encoding, None, Enum("auto", "enum", "one_hot_internal", "one_hot_explicit", "binary", "eigen", "label_encoder", "sort_by_response", "enum_limited")) self._parms["categorical_encoding"] = categorical_encoding @property def calibrate_model(self): """ Use Platt Scaling to calculate calibrated class probabilities. Calibration can provide more accurate estimates of class probabilities. Type: ``bool`` (default: ``False``). :examples: >>> ecology = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/gbm_test/ecology_model.csv") >>> ecology['Angaus'] = ecology['Angaus'].asfactor() >>> response = 'Angaus' >>> train, calib = ecology.split_frame(seed = 12354) >>> predictors = ecology.columns[3:13] >>> w = h2o.create_frame(binary_fraction=1, ... binary_ones_fraction=0.5, ... missing_fraction=0, ... rows=744, cols=1) >>> w.set_names(["weight"]) >>> train = train.cbind(w) >>> ecology_gbm = H2OGradientBoostingEstimator(ntrees=10, ... max_depth=5, ... min_rows=10, ... learn_rate=0.1, ... distribution="multinomial", ... weights_column="weight", ... calibrate_model=True, ... calibration_frame=calib) >>> ecology_gbm.train(x=predictors, ... y="Angaus", ... training_frame=train) >>> ecology_gbm.auc() """ return self._parms.get("calibrate_model") @calibrate_model.setter def calibrate_model(self, calibrate_model): assert_is_type(calibrate_model, None, bool) self._parms["calibrate_model"] = calibrate_model @property def calibration_frame(self): """ Calibration frame for Platt Scaling Type: ``H2OFrame``. :examples: >>> ecology = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/gbm_test/ecology_model.csv") >>> ecology['Angaus'] = ecology['Angaus'].asfactor() >>> response = 'Angaus' >>> predictors = ecology.columns[3:13] >>> train, calib = ecology.split_frame(seed=12354) >>> w = h2o.create_frame(binary_fraction=1, ... binary_ones_fraction=0.5, ... missing_fraction=0, ... rows=744,cols=1) >>> w.set_names(["weight"]) >>> train = train.cbind(w) >>> ecology_gbm = H2OGradientBoostingEstimator(ntrees=10, ... max_depth=5, ... min_rows=10, ... learn_rate=0.1, ... distribution="multinomial", ... calibrate_model=True, ... calibration_frame=calib) >>> ecology_gbm.train(x=predictors, ... y="Angaus", ... training_frame=train, ... weights_column="weight") >>> ecology_gbm.auc() """ return self._parms.get("calibration_frame") @calibration_frame.setter def calibration_frame(self, calibration_frame): self._parms["calibration_frame"] = H2OFrame._validate(calibration_frame, 'calibration_frame') @property def custom_metric_func(self): """ Reference to custom evaluation function, format: `language:keyName=funcName` Type: ``str``. """ return self._parms.get("custom_metric_func") @custom_metric_func.setter def custom_metric_func(self, custom_metric_func): assert_is_type(custom_metric_func, None, str) self._parms["custom_metric_func"] = custom_metric_func @property def custom_distribution_func(self): """ Reference to custom distribution, format: `language:keyName=funcName` Type: ``str``. :examples: >>> airlines= h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/airlines/allyears2k_headers.zip") >>> airlines["Year"] = airlines["Year"].asfactor() >>> airlines["Month"] = airlines["Month"].asfactor() >>> airlines["DayOfWeek"] = airlines["DayOfWeek"].asfactor() >>> airlines["Cancelled"] = airlines["Cancelled"].asfactor() >>> airlines['FlightNum'] = airlines['FlightNum'].asfactor() >>> predictors = ["Origin", "Dest", "Year", "UniqueCarrier", ... "DayOfWeek", "Month", "Distance", "FlightNum"] >>> response = "IsDepDelayed" >>> train, valid = airlines.split_frame(ratios=[.8], seed=1234) >>> airlines_gbm = H2OGradientBoostingEstimator(ntrees=3, ... max_depth=5, ... distribution="bernoulli", ... seed=1234) >>> airlines_gbm.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame valid) >>> from h2o.utils.distributions import CustomDistributionBernoulli >>> custom_distribution_bernoulli = h2o.upload_custom_distribution(CustomDistributionBernoulli, ... func_name="custom_bernoulli", ... func_file="custom_bernoulli.py") >>> airlines_gbm_custom = H2OGradientBoostingEstimator(ntrees=3, ... max_depth=5, ... distribution="custom", ... custom_distribution_func=custom_distribution_bernoulli, ... seed=1235) >>> airlines_gbm_custom.train(x=predictors, ... y=response, ... training_frame=train, ... validation_frame=valid) >>> airlines_gbm.auc() """ return self._parms.get("custom_distribution_func") @custom_distribution_func.setter def custom_distribution_func(self, custom_distribution_func): assert_is_type(custom_distribution_func, None, str) self._parms["custom_distribution_func"] = custom_distribution_func @property def export_checkpoints_dir(self): """ Automatically export generated models to this directory. Type: ``str``. :examples: >>> airlines = h2o.import_file("http://s3.amazonaws.com/h2o-public-test-data/smalldata/airlines/allyears2k_headers.zip", destination_frame="air.hex") >>> predictors = ["DayofMonth", "DayOfWeek"] >>> response = "IsDepDelayed" >>> hyper_parameters = {'ntrees': [5,10]} >>> search_crit = {'strategy': "RandomDiscrete", ... 'max_models': 5, ... 'seed': 1234, ... 'stopping_rounds': 3, ... 'stopping_metric': "AUTO", ... 'stopping_tolerance': 1e-2} >>> checkpoints_dir = tempfile.mkdtemp() >>> air_grid = H2OGridSearch(H2OGradientBoostingEstimator, ... hyper_params=hyper_parameters, ... search_criteria=search_crit) >>> air_grid.train(x=predictors, ... y=response, ... training_frame=airlines, ... distribution="bernoulli", ... learn_rate=0.1, ... max_depth=3, ... export_checkpoints_dir=checkpoints_dir) >>> len(listdir(checkpoints_dir)) """ return self._parms.get("export_checkpoints_dir") @export_checkpoints_dir.setter def export_checkpoints_dir(self, export_checkpoints_dir): assert_is_type(export_checkpoints_dir, None, str) self._parms["export_checkpoints_dir"] = export_checkpoints_dir @property def monotone_constraints(self): """ A mapping representing monotonic constraints. Use +1 to enforce an increasing constraint and -1 to specify a decreasing constraint. Type: ``dict``. :examples: >>> prostate_hex = h2o.import_file("http://s3.amazonaws.com/h2o-public-test-data/smalldata/prostate/prostate.csv.zip") >>> prostate_hex["CAPSULE"] = prostate_hex["CAPSULE"].asfactor() >>> response = "CAPSULE" >>> seed = 42 >>> monotone_constraints = {"AGE":1} >>> gbm_model = H2OGradientBoostingEstimator(seed=seed, ... monotone_constraints=monotone_constraints) >>> gbm_model.train(y=response, ... ignored_columns=["ID"], ... training_frame=prostate_hex) >>> gbm_model.scoring_history() """ return self._parms.get("monotone_constraints") @monotone_constraints.setter def monotone_constraints(self, monotone_constraints): assert_is_type(monotone_constraints, None, dict) self._parms["monotone_constraints"] = monotone_constraints @property def check_constant_response(self): """ Check if response column is constant. If enabled, then an exception is thrown if the response column is a constant value.If disabled, then model will train regardless of the response column being a constant value or not. Type: ``bool`` (default: ``True``). :examples: >>> train = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/iris/iris_train.csv") >>> train["constantCol"] = 1 >>> my_gbm = H2OGradientBoostingEstimator(check_constant_response=False) >>> my_gbm.train(x=list(range(1,5)), ... y="constantCol", ... training_frame=train) """ return self._parms.get("check_constant_response") @check_constant_response.setter def check_constant_response(self, check_constant_response): assert_is_type(check_constant_response, None, bool) self._parms["check_constant_response"] = check_constant_response @property def gainslift_bins(self): """ Gains/Lift table number of bins. 0 means disabled.. Default value -1 means automatic binning. Type: ``int`` (default: ``-1``). :examples: >>> airlines= h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/testng/airlines_train.csv") >>> model = H2OGradientBoostingEstimator(ntrees=1, gainslift_bins=20) >>> model.train(x=["Origin", "Distance"], ... y="IsDepDelayed", ... training_frame=airlines) >>> model.gains_lift() """ return self._parms.get("gainslift_bins") @gainslift_bins.setter def gainslift_bins(self, gainslift_bins): assert_is_type(gainslift_bins, None, int) self._parms["gainslift_bins"] = gainslift_bins @property def auc_type(self): """ Set default multinomial AUC type. One of: ``"auto"``, ``"none"``, ``"macro_ovr"``, ``"weighted_ovr"``, ``"macro_ovo"``, ``"weighted_ovo"`` (default: ``"auto"``). """ return self._parms.get("auc_type") @auc_type.setter def auc_type(self, auc_type): assert_is_type(auc_type, None, Enum("auto", "none", "macro_ovr", "weighted_ovr", "macro_ovo", "weighted_ovo")) self._parms["auc_type"] = auc_type