#!/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
import ast
import json
import warnings
import h2o
from h2o.base import Keyed
from h2o.grid import H2OGridSearch
from h2o.utils.shared_utils import quoted
from h2o.utils.typechecks import is_type
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 H2OStackedEnsembleEstimator(H2OEstimator):
"""
Stacked Ensemble
Builds a stacked ensemble (aka "super learner") machine learning method that uses two
or more H2O learning algorithms to improve predictive performance. It is a loss-based
supervised learning method that finds the optimal combination of a collection of prediction
algorithms.This method supports regression and binary classification.
:examples:
>>> import h2o
>>> h2o.init()
>>> from h2o.estimators.random_forest import H2ORandomForestEstimator
>>> from h2o.estimators.gbm import H2OGradientBoostingEstimator
>>> from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
>>> col_types = ["numeric", "numeric", "numeric", "enum",
... "enum", "numeric", "numeric", "numeric", "numeric"]
>>> data = h2o.import_file("http://h2o-public-test-data.s3.amazonaws.com/smalldata/prostate/prostate.csv", col_types=col_types)
>>> train, test = data.split_frame(ratios=[.8], seed=1)
>>> x = ["CAPSULE","GLEASON","RACE","DPROS","DCAPS","PSA","VOL"]
>>> y = "AGE"
>>> nfolds = 5
>>> gbm = H2OGradientBoostingEstimator(nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True)
>>> gbm.train(x=x, y=y, training_frame=train)
>>> rf = H2ORandomForestEstimator(nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True)
>>> rf.train(x=x, y=y, training_frame=train)
>>> stack = H2OStackedEnsembleEstimator(model_id="ensemble",
... training_frame=train,
... validation_frame=test,
... base_models=[gbm.model_id, rf.model_id])
>>> stack.train(x=x, y=y, training_frame=train, validation_frame=test)
>>> stack.model_performance()
"""
algo = "stackedensemble"
param_names = {"model_id", "training_frame", "response_column", "validation_frame", "blending_frame", "base_models",
"metalearner_algorithm", "metalearner_nfolds", "metalearner_fold_assignment",
"metalearner_fold_column", "metalearner_params", "seed", "score_training_samples",
"keep_levelone_frame", "export_checkpoints_dir"}
def __init__(self, **kwargs):
super(H2OStackedEnsembleEstimator, 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))
self._parms["_rest_version"] = 99
@property
def training_frame(self):
"""
Id of the training data frame.
Type: ``H2OFrame``.
:examples:
>>> from h2o.estimators.random_forest import H2ORandomForestEstimator
>>> from h2o.estimators.gbm import H2OGradientBoostingEstimator
>>> from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
>>> higgs = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/testng/higgs_train_5k.csv")
>>> train, valid = higgs.split_frame(ratios = [.8], seed = 1234)
>>> x = train.columns
>>> y = "response"
>>> x.remove(y)
>>> train[y] = train[y].asfactor()
>>> blend[y] = blend[y].asfactor()
>>> nfolds = 3
>>> my_gbm = H2OGradientBoostingEstimator(distribution="bernoulli",
... ntrees=1,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_gbm.train(x=x, y=y, training_frame=train)
>>> my_rf = H2ORandomForestEstimator(ntrees=50,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_rf.train(x=x, y=y, training_frame=train)
>>> stack_blend = H2OStackedEnsembleEstimator(base_models=[my_gbm, my_rf],
... seed=1,
... metalearner_fold_assignment="Random")
>>> stack_blend.train(x=x, y=y, training_frame=train, validation_frame=valid)
>>> stack_blend.model_performance(blend).auc()
"""
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 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 validation_frame(self):
"""
Id of the validation data frame.
Type: ``H2OFrame``.
:examples:
>>> from h2o.estimators.random_forest import H2ORandomForestEstimator
>>> from h2o.estimators.gbm import H2OGradientBoostingEstimator
>>> from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
>>> higgs = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/testng/higgs_train_5k.csv")
>>> train, valid = higgs.split_frame(ratios = [.8], seed = 1234)
>>> x = train.columns
>>> y = "response"
>>> x.remove(y)
>>> train[y] = train[y].asfactor()
>>> blend[y] = blend[y].asfactor()
>>> nfolds = 3
>>> my_gbm = H2OGradientBoostingEstimator(distribution="bernoulli",
... ntrees=1,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_gbm.train(x=x, y=y, training_frame=train)
>>> my_rf = H2ORandomForestEstimator(ntrees=50,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_rf.train(x=x, y=y, training_frame=train)
>>> stack_blend = H2OStackedEnsembleEstimator(base_models=[my_gbm, my_rf],
... seed=1,
... metalearner_fold_assignment="Random")
>>> stack_blend.train(x=x, y=y, training_frame=train, validation_frame=valid)
>>> stack_blend.model_performance(blend).auc()
"""
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 blending_frame(self):
"""
Frame used to compute the predictions that serve as the training frame for the metalearner (triggers blending
mode if provided)
Type: ``H2OFrame``.
:examples:
>>> from h2o.estimators.random_forest import H2ORandomForestEstimator
>>> from h2o.estimators.gbm import H2OGradientBoostingEstimator
>>> from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
>>> higgs = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/testng/higgs_train_5k.csv")
>>> train, blend = higgs.split_frame(ratios = [.8], seed = 1234)
>>> x = train.columns
>>> y = "response"
>>> x.remove(y)
>>> train[y] = train[y].asfactor()
>>> blend[y] = blend[y].asfactor()
>>> nfolds = 3
>>> my_gbm = H2OGradientBoostingEstimator(distribution="bernoulli",
... ntrees=10,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_gbm.train(x=x, y=y, training_frame=train)
>>> my_rf = H2ORandomForestEstimator(ntrees=50,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_rf.train(x=x, y=y, training_frame=train)
>>> stack_blend = H2OStackedEnsembleEstimator(base_models=[my_gbm, my_rf],
... seed=1)
>>> stack_blend.train(x=x, y=y, training_frame=train, blending_frame=blend)
>>> stack_blend.model_performance(blend).auc()
"""
return self._parms.get("blending_frame")
@blending_frame.setter
def blending_frame(self, blending_frame):
self._parms["blending_frame"] = H2OFrame._validate(blending_frame, 'blending_frame')
@property
def base_models(self):
"""
List of models or grids (or their ids) to ensemble/stack together. Grids are expanded to individual models. If
not using blending frame, then models must have been cross-validated using nfolds > 1, and folds must be
identical across models.
Type: ``List[str]`` (default: ``[]``).
:examples:
>>> from h2o.estimators.random_forest import H2ORandomForestEstimator
>>> from h2o.estimators.gbm import H2OGradientBoostingEstimator
>>> from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
>>> col_types = ["numeric", "numeric", "numeric", "enum",
... "enum", "numeric", "numeric", "numeric", "numeric"]
>>> data = h2o.import_file("http://h2o-public-test-data.s3.amazonaws.com/smalldata/prostate/prostate.csv", col_types=col_types)
>>> train, test = data.split_frame(ratios=[.8], seed=1)
>>> x = ["CAPSULE","GLEASON","RACE","DPROS","DCAPS","PSA","VOL"]
>>> y = "AGE"
>>> nfolds = 5
>>> gbm = H2OGradientBoostingEstimator(nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True)
>>> gbm.train(x=x, y=y, training_frame=train)
>>> rf = H2ORandomForestEstimator(nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True)
>>> rf.train(x=x, y=y, training_frame=train)
>>> stack = H2OStackedEnsembleEstimator(model_id="ensemble",
... training_frame=train,
... validation_frame=test,
... base_models=[gbm.model_id, rf.model_id])
>>> stack.train(x=x, y=y, training_frame=train, validation_frame=test)
>>> stack.model_performance()
"""
base_models = self.actual_params.get("base_models", [])
base_models = [base_model["name"] for base_model in base_models]
if len(base_models) == 0:
base_models = self._parms.get("base_models")
return base_models
@base_models.setter
def base_models(self, base_models):
def _get_id(something):
if isinstance(something, Keyed):
return something.key
return something
if not is_type(base_models, list):
base_models = [base_models]
if is_type(base_models, [H2OEstimator, H2OGridSearch, str]):
base_models = [_get_id(b) for b in base_models]
self._parms["base_models"] = base_models
else:
assert_is_type(base_models, None)
@property
def metalearner_algorithm(self):
"""
Type of algorithm to use as the metalearner. Options include 'AUTO' (GLM with non negative weights; if
validation_frame is present, a lambda search is performed), 'deeplearning' (Deep Learning with default
parameters), 'drf' (Random Forest with default parameters), 'gbm' (GBM with default parameters), 'glm' (GLM with
default parameters), 'naivebayes' (NaiveBayes with default parameters), or 'xgboost' (if available, XGBoost with
default parameters).
One of: ``"auto"``, ``"deeplearning"``, ``"drf"``, ``"gbm"``, ``"glm"``, ``"naivebayes"``, ``"xgboost"``
(default: ``"auto"``).
:examples:
>>> from h2o.estimators.random_forest import H2ORandomForestEstimator
>>> from h2o.estimators.gbm import H2OGradientBoostingEstimator
>>> from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
>>> higgs = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/testng/higgs_train_5k.csv")
>>> train, blend = higgs.split_frame(ratios = [.8], seed = 1234)
>>> x = train.columns
>>> y = "response"
>>> x.remove(y)
>>> train[y] = train[y].asfactor()
>>> blend[y] = blend[y].asfactor()
>>> nfolds = 3
>>> my_gbm = H2OGradientBoostingEstimator(distribution="bernoulli",
... ntrees=1,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_gbm.train(x=x, y=y, training_frame=train)
>>> my_rf = H2ORandomForestEstimator(ntrees=50,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_rf.train(x=x, y=y, training_frame=train)
>>> stack_blend = H2OStackedEnsembleEstimator(base_models=[my_gbm, my_rf],
... seed=1,
... metalearner_algorithm="gbm")
>>> stack_blend.train(x=x, y=y, training_frame=train, blending_frame=blend)
>>> stack_blend.model_performance(blend).auc()
"""
return self._parms.get("metalearner_algorithm")
@metalearner_algorithm.setter
def metalearner_algorithm(self, metalearner_algorithm):
assert_is_type(metalearner_algorithm, None, Enum("auto", "deeplearning", "drf", "gbm", "glm", "naivebayes", "xgboost"))
self._parms["metalearner_algorithm"] = metalearner_algorithm
@property
def metalearner_nfolds(self):
"""
Number of folds for K-fold cross-validation of the metalearner algorithm (0 to disable or >= 2).
Type: ``int`` (default: ``0``).
:examples:
>>> from h2o.estimators.random_forest import H2ORandomForestEstimator
>>> from h2o.estimators.gbm import H2OGradientBoostingEstimator
>>> from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
>>> higgs = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/testng/higgs_train_5k.csv")
>>> train, blend = higgs.split_frame(ratios = [.8], seed = 1234)
>>> x = train.columns
>>> y = "response"
>>> x.remove(y)
>>> train[y] = train[y].asfactor()
>>> blend[y] = blend[y].asfactor()
>>> nfolds = 3
>>> my_gbm = H2OGradientBoostingEstimator(distribution="bernoulli",
... ntrees=1,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_gbm.train(x=x, y=y, training_frame=train)
>>> my_rf = H2ORandomForestEstimator(ntrees=50,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_rf.train(x=x, y=y, training_frame=train)
>>> stack_blend = H2OStackedEnsembleEstimator(base_models=[my_gbm, my_rf],
... seed=1,
... metalearner_nfolds=3)
>>> stack_blend.train(x=x, y=y, training_frame=train, blending_frame=blend)
>>> stack_blend.model_performance(blend).auc()
"""
return self._parms.get("metalearner_nfolds")
@metalearner_nfolds.setter
def metalearner_nfolds(self, metalearner_nfolds):
assert_is_type(metalearner_nfolds, None, int)
self._parms["metalearner_nfolds"] = metalearner_nfolds
@property
def metalearner_fold_assignment(self):
"""
Cross-validation fold assignment scheme for metalearner cross-validation. Defaults to AUTO (which is currently
set to Random). The 'Stratified' option will stratify the folds based on the response variable, for
classification problems.
One of: ``"auto"``, ``"random"``, ``"modulo"``, ``"stratified"``.
:examples:
>>> from h2o.estimators.random_forest import H2ORandomForestEstimator
>>> from h2o.estimators.gbm import H2OGradientBoostingEstimator
>>> from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
>>> higgs = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/testng/higgs_train_5k.csv")
>>> train, blend = higgs.split_frame(ratios = [.8], seed = 1234)
>>> x = train.columns
>>> y = "response"
>>> x.remove(y)
>>> train[y] = train[y].asfactor()
>>> blend[y] = blend[y].asfactor()
>>> nfolds = 3
>>> my_gbm = H2OGradientBoostingEstimator(distribution="bernoulli",
... ntrees=1,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_gbm.train(x=x, y=y, training_frame=train)
>>> my_rf = H2ORandomForestEstimator(ntrees=50,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_rf.train(x=x, y=y, training_frame=train)
>>> stack_blend = H2OStackedEnsembleEstimator(base_models=[my_gbm, my_rf],
... seed=1,
... metalearner_fold_assignment="Random")
>>> stack_blend.train(x=x, y=y, training_frame=train, blending_frame=blend)
>>> stack_blend.model_performance(blend).auc()
"""
return self._parms.get("metalearner_fold_assignment")
@metalearner_fold_assignment.setter
def metalearner_fold_assignment(self, metalearner_fold_assignment):
assert_is_type(metalearner_fold_assignment, None, Enum("auto", "random", "modulo", "stratified"))
self._parms["metalearner_fold_assignment"] = metalearner_fold_assignment
@property
def metalearner_fold_column(self):
"""
Column with cross-validation fold index assignment per observation for cross-validation of the metalearner.
Type: ``str``.
:examples:
>>> from h2o.estimators.random_forest import H2ORandomForestEstimator
>>> from h2o.estimators.gbm import H2OGradientBoostingEstimator
>>> from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
>>> train = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/testng/higgs_train_5k.csv")
>>> test = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/testng/higgs_test_5k.csv")
>>> fold_column = "fold_id"
>>> train[fold_column] = train.kfold_column(n_folds=3, seed=1)
>>> x = train.columns
>>> y = "response"
>>> x.remove(y)
>>> x.remove(fold_column)
>>> train[y] = train[y].asfactor()
>>> test[y] = test[y].asfactor()
>>> nfolds = 3
>>> my_gbm = H2OGradientBoostingEstimator(distribution="bernoulli",
... ntrees=10,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_gbm.train(x=x, y=y, training_frame=train)
>>> my_rf = H2ORandomForestEstimator(ntrees=50,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_rf.train(x=x, y=y, training_frame=train)
>>> stack = H2OStackedEnsembleEstimator(base_models=[my_gbm, my_rf],
... metalearner_fold_column=fold_column,
... metalearner_params=dict(keep_cross_validation_models=True))
>>> stack.train(x=x, y=y, training_frame=train)
>>> stack.model_performance().auc()
"""
return self._parms.get("metalearner_fold_column")
@metalearner_fold_column.setter
def metalearner_fold_column(self, metalearner_fold_column):
assert_is_type(metalearner_fold_column, None, str)
self._parms["metalearner_fold_column"] = metalearner_fold_column
@property
def metalearner_params(self):
"""
Parameters for metalearner algorithm
Type: ``dict``.
:examples:
>>> from h2o.estimators.random_forest import H2ORandomForestEstimator
>>> from h2o.estimators.gbm import H2OGradientBoostingEstimator
>>> from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
>>> higgs = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/testng/higgs_train_5k.csv")
>>> train, blend = higgs.split_frame(ratios = [.8], seed = 1234)
>>> x = train.columns
>>> y = "response"
>>> x.remove(y)
>>> train[y] = train[y].asfactor()
>>> blend[y] = blend[y].asfactor()
>>> nfolds = 3
>>> gbm_params = {"ntrees" : 100, "max_depth" : 6}
>>> my_gbm = H2OGradientBoostingEstimator(distribution="bernoulli",
... ntrees=1,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_gbm.train(x=x, y=y, training_frame=train)
>>> my_rf = H2ORandomForestEstimator(ntrees=50,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_rf.train(x=x, y=y, training_frame=train)
>>> stack_blend = H2OStackedEnsembleEstimator(base_models=[my_gbm, my_rf],
... metalearner_algorithm="gbm",
... metalearner_params=gbm_params)
>>> stack_blend.train(x=x, y=y, training_frame=train, blending_frame=blend)
>>> stack_blend.model_performance(blend).auc()
"""
if self._parms.get("metalearner_params") != None:
metalearner_params_dict = ast.literal_eval(self._parms.get("metalearner_params"))
for k in metalearner_params_dict:
if len(metalearner_params_dict[k]) == 1: #single parameter
metalearner_params_dict[k] = metalearner_params_dict[k][0]
return metalearner_params_dict
else:
return self._parms.get("metalearner_params")
@metalearner_params.setter
def metalearner_params(self, metalearner_params):
assert_is_type(metalearner_params, None, dict)
if metalearner_params is not None and metalearner_params != "":
for k in metalearner_params:
if ("[" and "]") not in str(metalearner_params[k]):
metalearner_params[k] = [metalearner_params[k]]
self._parms["metalearner_params"] = str(json.dumps(metalearner_params))
else:
self._parms["metalearner_params"] = None
@property
def seed(self):
"""
Seed for random numbers; passed through to the metalearner algorithm. Defaults to -1 (time-based random number)
Type: ``int`` (default: ``-1``).
:examples:
>>> from h2o.estimators.random_forest import H2ORandomForestEstimator
>>> from h2o.estimators.gbm import H2OGradientBoostingEstimator
>>> from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
>>> higgs = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/testng/higgs_train_5k.csv")
>>> train, blend = higgs.split_frame(ratios = [.8], seed = 1234)
>>> x = train.columns
>>> y = "response"
>>> x.remove(y)
>>> train[y] = train[y].asfactor()
>>> blend[y] = blend[y].asfactor()
>>> nfolds = 3
>>> my_gbm = H2OGradientBoostingEstimator(distribution="bernoulli",
... ntrees=1,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_gbm.train(x=x, y=y, training_frame=train)
>>> my_rf = H2ORandomForestEstimator(ntrees=50,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_rf.train(x=x, y=y, training_frame=train)
>>> stack_blend = H2OStackedEnsembleEstimator(base_models=[my_gbm, my_rf],
... seed=1,
... metalearner_fold_assignment="Random")
>>> stack_blend.train(x=x, y=y, training_frame=train, blending_frame=blend)
>>> stack_blend.model_performance(blend).auc()
"""
return self._parms.get("seed")
@seed.setter
def seed(self, seed):
assert_is_type(seed, None, int)
self._parms["seed"] = seed
@property
def score_training_samples(self):
"""
Specify the number of training set samples for scoring. The value must be >= 0. To use all training samples,
enter 0.
Type: ``int`` (default: ``10000``).
"""
return self._parms.get("score_training_samples")
@score_training_samples.setter
def score_training_samples(self, score_training_samples):
assert_is_type(score_training_samples, None, int)
self._parms["score_training_samples"] = score_training_samples
@property
def keep_levelone_frame(self):
"""
Keep level one frame used for metalearner training.
Type: ``bool`` (default: ``False``).
:examples:
>>> from h2o.estimators.random_forest import H2ORandomForestEstimator
>>> from h2o.estimators.gbm import H2OGradientBoostingEstimator
>>> from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
>>> higgs = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/testng/higgs_train_5k.csv")
>>> train, blend = higgs.split_frame(ratios = [.8], seed = 1234)
>>> x = train.columns
>>> y = "response"
>>> x.remove(y)
>>> train[y] = train[y].asfactor()
>>> blend[y] = blend[y].asfactor()
>>> nfolds = 3
>>> my_gbm = H2OGradientBoostingEstimator(distribution="bernoulli",
... ntrees=1,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_gbm.train(x=x, y=y, training_frame=train)
>>> my_rf = H2ORandomForestEstimator(ntrees=50,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_rf.train(x=x, y=y, training_frame=train)
>>> stack_blend = H2OStackedEnsembleEstimator(base_models=[my_gbm, my_rf],
... seed=1,
... keep_levelone_frame=True)
>>> stack_blend.train(x=x, y=y, training_frame=train, blending_frame=blend)
>>> stack_blend.model_performance(blend).auc()
"""
return self._parms.get("keep_levelone_frame")
@keep_levelone_frame.setter
def keep_levelone_frame(self, keep_levelone_frame):
assert_is_type(keep_levelone_frame, None, bool)
self._parms["keep_levelone_frame"] = keep_levelone_frame
@property
def export_checkpoints_dir(self):
"""
Automatically export generated models to this directory.
Type: ``str``.
:examples:
>>> from h2o.estimators.random_forest import H2ORandomForestEstimator
>>> from h2o.estimators.gbm import H2OGradientBoostingEstimator
>>> from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
>>> import tempfile
>>> from os import listdir
>>> higgs = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/testng/higgs_train_5k.csv")
>>> train, blend = higgs.split_frame(ratios = [.8], seed = 1234)
>>> x = train.columns
>>> y = "response"
>>> x.remove(y)
>>> train[y] = train[y].asfactor()
>>> blend[y] = blend[y].asfactor()
>>> nfolds = 3
>>> checkpoints_dir = tempfile.mkdtemp()
>>> my_gbm = H2OGradientBoostingEstimator(distribution="bernoulli",
... ntrees=10,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_gbm.train(x=x, y=y, training_frame=train)
>>> my_rf = H2ORandomForestEstimator(ntrees=50,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_rf.train(x=x, y=y, training_frame=train)
>>> stack_blend = H2OStackedEnsembleEstimator(base_models=[my_gbm, my_rf],
... seed=1,
... export_checkpoints_dir=checkpoints_dir)
>>> stack_blend.train(x=x, y=y, training_frame=train, blending_frame=blend)
>>> 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
[docs] def levelone_frame_id(self):
"""Fetch the levelone_frame_id for an H2OStackedEnsembleEstimator.
:examples:
>>> from h2o.estimators.random_forest import H2ORandomForestEstimator
>>> from h2o.estimators.gbm import H2OGradientBoostingEstimator
>>> from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
>>> higgs = h2o.import_file("https://s3.amazonaws.com/h2o-public-test-data/smalldata/testng/higgs_train_5k.csv")
>>> train, blend = higgs.split_frame(ratios = [.8], seed = 1234)
>>> x = train.columns
>>> y = "response"
>>> x.remove(y)
>>> train[y] = train[y].asfactor()
>>> blend[y] = blend[y].asfactor()
>>> nfolds = 3
>>> my_gbm = H2OGradientBoostingEstimator(distribution="bernoulli",
... ntrees=10,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_gbm.train(x=x, y=y, training_frame=train)
>>> my_rf = H2ORandomForestEstimator(ntrees=50,
... nfolds=nfolds,
... fold_assignment="Modulo",
... keep_cross_validation_predictions=True,
... seed=1)
>>> my_rf.train(x=x, y=y, training_frame=train)
>>> stack_blend = H2OStackedEnsembleEstimator(base_models=[my_gbm, my_rf],
... seed=1,
... keep_levelone_frame=True)
>>> stack_blend.train(x=x, y=y, training_frame=train, blending_frame=blend)
>>> stack_blend.levelone_frame_id()
"""
model = self._model_json["output"]
if "levelone_frame_id" in model and model["levelone_frame_id"] is not None:
return model["levelone_frame_id"]
print("No levelone_frame_id for this model")
def stacking_strategy(self):
model = self._model_json["output"]
if "stacking_strategy" in model and model["stacking_strategy"] is not None:
return model["stacking_strategy"]
print("No stacking strategy for this model")
# Override train method to support blending
[docs] def train(self, x=None, y=None, training_frame=None, blending_frame=None, verbose=False, **kwargs):
has_training_frame = training_frame is not None or self.training_frame is not None
blending_frame = H2OFrame._validate(blending_frame, 'blending_frame', required=not has_training_frame)
if not has_training_frame:
training_frame = blending_frame # used to bypass default checks in super class and backend and to guarantee default metrics
sup = super(self.__class__, self)
def extend_parms(parms):
if blending_frame is not None:
parms['blending_frame'] = blending_frame
if self.metalearner_fold_column is not None:
parms['ignored_columns'].remove(quoted(self.metalearner_fold_column))
parms = sup._make_parms(x, y, training_frame, extend_parms_fn=extend_parms, **kwargs)
sup._train(parms, verbose=verbose)