#!/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 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"]
>>> dat = h2o.import_file("http://h2o-public-test-data.s3.amazonaws.com/smalldata/prostate/prostate.csv", destination_frame="prostate_hex", col_types= col_types)
>>> train, test = dat.split_frame(ratios=[.8], seed=1)
>>> x = ["CAPSULE","GLEASON","RACE","DPROS","DCAPS","PSA","VOL"]
>>> y = "AGE"
>>> my_gbm = H2OGradientBoostingEstimator()
>>> my_gbm.train(x=x, y=y, training_frame=train)
>>> my_rf = H2ORandomForestEstimator()
>>> my_rf.train(x=x, y=y, training_frame=train)
>>> stack = H2OStackedEnsembleEstimator(model_id="my_ensemble_guassian", training_frame=train, validation_frame=test, base_models=[my_gbm.model_id, my_rf.model_id], selection_strategy="choose_all")
>>> stack.train(x=x, y=y, training_frame=train, validation_frame=test)
>>> stack.model_performance()
"""
algo = "stackedensemble"
def __init__(self, **kwargs):
super(H2OStackedEnsembleEstimator, self).__init__()
self._parms = {}
names_list = {"model_id", "training_frame", "validation_frame", "base_models", "selection_strategy"}
if "Lambda" in kwargs: kwargs["lambda_"] = kwargs.pop("Lambda")
for pname, pvalue in kwargs.items():
if pname == 'model_id':
self._id = pvalue
self._parms["model_id"] = pvalue
elif pname in names_list:
# 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 (Not required, to allow initial validation of model parameters).
Type: ``str``.
"""
return self._parms.get("training_frame")
@training_frame.setter
def training_frame(self, training_frame):
assert_is_type(training_frame, None, H2OFrame)
self._parms["training_frame"] = training_frame
@property
def validation_frame(self):
"""
Id of the validation data frame.
Type: ``str``.
"""
return self._parms.get("validation_frame")
@validation_frame.setter
def validation_frame(self, validation_frame):
assert_is_type(validation_frame, None, H2OFrame)
self._parms["validation_frame"] = validation_frame
@property
def base_models(self):
"""
List of model ids which we can stack together. Which ones are chosen depends on the selection_strategy
(currently, all models will be used since selection_strategy can only be set to choose_all). Models must have
been cross-validated using nfolds > 1, fold_assignment equal to Modulo, and keep_cross_validation_folds must be
set to True.
Type: ``List[str]`` (default: ``[]``).
"""
return self._parms.get("base_models")
@base_models.setter
def base_models(self, base_models):
assert_is_type(base_models, None, [str])
self._parms["base_models"] = base_models
@property
def selection_strategy(self):
"""
Strategy for choosing which models to stack.
One of: ``"choose_all"``.
"""
return self._parms.get("selection_strategy")
@selection_strategy.setter
def selection_strategy(self, selection_strategy):
assert_is_type(selection_strategy, None, Enum("choose_all"))
self._parms["selection_strategy"] = selection_strategy