h2o ensemble throws error: "Base model does not keep cross-validation predictions"
h2o ensemble throws error: "Base model does not keep cross-validation predictions"
我正在尝试根据大量 GLM、GBM 和深度学习模型在 H2O 中创建一个集成模型。
这是我目前所做的。
导入相关库：
import h2o
from h2o.estimators.glm import H2OGeneralizedLinearEstimator
from h2o.estimators.gbm import H2OGradientBoostingEstimator
from h2o.estimators.deeplearning import H2ODeepLearningEstimator
from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
from h2o.grid.grid_search import H2OGridSearch
数据可以从here下载。导入：
airlines = h2o.import_file(path = "/Users/alexwoolford/h2o/allyears2k.csv", destination_frame = "airlines.hex")
分成training/test组：
airlines_80,airlines_20 = airlines.split_frame(ratios=[.8], destination_frames=["airlines_80.hex", "airlines_20.hex"])
定义变量（预测 y 作为 x 中所有列的函数）：
x= airlines.columns
y= "ArrDelay"
x.remove(y)
设置常用属性：
folds=5
assignment_type="Modulo"
search_criteria={'strategy': 'RandomDiscrete', 'max_models': 5, 'seed': 1}
使用H2O的网格搜索创建多种模型：
# GLM
glm_params = {"alpha": [0. , 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.],
"lambda": [0, 1e-7, 1e-5, 1e-3, 1e-1]}
glm_grid = H2OGridSearch(model=H2OGeneralizedLinearEstimator(fold_assignment=assignment_type, nfolds=folds),
grid_id='glm_grid',
hyper_params=glm_params,
search_criteria=search_criteria)
glm_grid.train(x=x,
y=y,
training_frame=airlines_80,
validation_frame=airlines_20)
# GBM
gbm_params = {'learn_rate': [0.01, 0.03],
'max_depth': [3, 4, 5, 6, 9],
'sample_rate': [0.7, 0.8, 0.9, 1],
'col_sample_rate': [0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8]}
gbm_grid = H2OGridSearch(model=H2OGradientBoostingEstimator(fold_assignment=assignment_type, nfolds=folds),
grid_id='gbm_grid',
hyper_params=gbm_params,
search_criteria=search_criteria)
gbm_grid.train(x=x,
y=y,
training_frame=airlines_80,
validation_frame=airlines_20)
# Deep learning
dl_params = {'activation': ['rectifier', 'rectifier_with_dropout'],
'hidden': [[10,10], [20,15], [50,50,50]],
'l1': [0, 1e-3, 1e-5],
'l2': [0, 1e-3, 1e-5]}
dl_grid = H2OGridSearch(model=H2ODeepLearningEstimator(fold_assignment=assignment_type, nfolds=folds),
grid_id='dl_grid',
hyper_params=dl_params,
search_criteria=search_criteria)
dl_grid.train(x=x,
y=y,
training_frame=airlines_80,
validation_frame=airlines_20)
获取所有 model_id 的列表：
all_model_ids = glm_grid.model_ids + gbm_grid.model_ids + dl_grid.model_ids
我尝试创建整体的地方：
ensemble = H2OStackedEnsembleEstimator(base_models=all_model_ids)
ensemble.train(x=x, y=y, training_frame=airlines_80, validation_frame=airlines_20)
...抛出以下错误：
stackedensemble Model Build progress: | (failed)
---------------------------------------------------------------------------
OSError Traceback (most recent call last)
<ipython-input-26-bc7b6094816f> in <module>()
1 ensemble = H2OStackedEnsembleEstimator(base_models=all_model_ids)
----> 2 ensemble.train(x=x, y=y, training_frame=airlines_80, validation_frame=airlines_20)
/anaconda3/lib/python3.6/site-packages/h2o/estimators/estimator_base.py in train(self, x, y, training_frame, offset_column, fold_column, weights_column, validation_frame, max_runtime_secs, ignored_columns, model_id, verbose)
235 return
236
--> 237 model.poll(verbose_model_scoring_history=verbose)
238 model_json = h2o.api("GET /%d/Models/%s" % (rest_ver, model.dest_key))["models"][0]
239 self._resolve_model(model.dest_key, model_json)
/anaconda3/lib/python3.6/site-packages/h2o/job.py in poll(self, verbose_model_scoring_history)
75 if (isinstance(self.job, dict)) and ("stacktrace" in list(self.job)):
76 raise EnvironmentError("Job with key {} failed with an exception: {}\nstacktrace: "
---> 77 "\n{}".format(self.job_key, self.exception, self.job["stacktrace"]))
78 else:
79 raise EnvironmentError("Job with key %s failed with an exception: %s" % (self.job_key, self.exception))
OSError: Job with key 017f00000132d4ffffffff$_a2359a38ec8d31316aee91398f0249f8 failed with an exception: water.exceptions.H2OIllegalArgumentException: Base model does not keep cross-validation predictions: 5
stacktrace:
water.exceptions.H2OIllegalArgumentException: Base model does not keep cross-validation predictions: 5
at hex.StackedEnsembleModel.checkAndInheritModelProperties(StackedEnsembleModel.java:382)
at hex.ensemble.StackedEnsemble$StackedEnsembleDriver.computeImpl(StackedEnsemble.java:234)
at hex.ModelBuilder$Driver.compute2(ModelBuilder.java:218)
at water.H2O$H2OCountedCompleter.compute(H2O.java:1395)
at jsr166y.CountedCompleter.exec(CountedCompleter.java:468)
at jsr166y.ForkJoinTask.doExec(ForkJoinTask.java:263)
at jsr166y.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:974)
at jsr166y.ForkJoinPool.runWorker(ForkJoinPool.java:1477)
at jsr166y.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:104)
你能看出我做错了什么吗？
您的每个模型中似乎都缺少参数 keep_cross_validation_predictions=True。例如，您希望为您的 GLM 执行以下操作，然后同样地为您要堆叠的其他模型执行以下操作：
glm_grid = H2OGridSearch(model=H2OGeneralizedLinearEstimator(fold_assignment=assignment_type, nfolds=folds,
keep_cross_validation_predictions=True),
grid_id='glm_grid',
hyper_params=glm_params,
search_criteria=search_criteria)
我正在尝试根据大量 GLM、GBM 和深度学习模型在 H2O 中创建一个集成模型。
这是我目前所做的。
导入相关库：
import h2o
from h2o.estimators.glm import H2OGeneralizedLinearEstimator
from h2o.estimators.gbm import H2OGradientBoostingEstimator
from h2o.estimators.deeplearning import H2ODeepLearningEstimator
from h2o.estimators.stackedensemble import H2OStackedEnsembleEstimator
from h2o.grid.grid_search import H2OGridSearch
数据可以从here下载。导入：
airlines = h2o.import_file(path = "/Users/alexwoolford/h2o/allyears2k.csv", destination_frame = "airlines.hex")
分成training/test组：
airlines_80,airlines_20 = airlines.split_frame(ratios=[.8], destination_frames=["airlines_80.hex", "airlines_20.hex"])
定义变量（预测 y 作为 x 中所有列的函数）：
x= airlines.columns
y= "ArrDelay"
x.remove(y)
设置常用属性：
folds=5
assignment_type="Modulo"
search_criteria={'strategy': 'RandomDiscrete', 'max_models': 5, 'seed': 1}
使用H2O的网格搜索创建多种模型：
# GLM
glm_params = {"alpha": [0. , 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.],
"lambda": [0, 1e-7, 1e-5, 1e-3, 1e-1]}
glm_grid = H2OGridSearch(model=H2OGeneralizedLinearEstimator(fold_assignment=assignment_type, nfolds=folds),
grid_id='glm_grid',
hyper_params=glm_params,
search_criteria=search_criteria)
glm_grid.train(x=x,
y=y,
training_frame=airlines_80,
validation_frame=airlines_20)
# GBM
gbm_params = {'learn_rate': [0.01, 0.03],
'max_depth': [3, 4, 5, 6, 9],
'sample_rate': [0.7, 0.8, 0.9, 1],
'col_sample_rate': [0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8]}
gbm_grid = H2OGridSearch(model=H2OGradientBoostingEstimator(fold_assignment=assignment_type, nfolds=folds),
grid_id='gbm_grid',
hyper_params=gbm_params,
search_criteria=search_criteria)
gbm_grid.train(x=x,
y=y,
training_frame=airlines_80,
validation_frame=airlines_20)
# Deep learning
dl_params = {'activation': ['rectifier', 'rectifier_with_dropout'],
'hidden': [[10,10], [20,15], [50,50,50]],
'l1': [0, 1e-3, 1e-5],
'l2': [0, 1e-3, 1e-5]}
dl_grid = H2OGridSearch(model=H2ODeepLearningEstimator(fold_assignment=assignment_type, nfolds=folds),
grid_id='dl_grid',
hyper_params=dl_params,
search_criteria=search_criteria)
dl_grid.train(x=x,
y=y,
training_frame=airlines_80,
validation_frame=airlines_20)
获取所有 model_id 的列表：
all_model_ids = glm_grid.model_ids + gbm_grid.model_ids + dl_grid.model_ids
我尝试创建整体的地方：
ensemble = H2OStackedEnsembleEstimator(base_models=all_model_ids)
ensemble.train(x=x, y=y, training_frame=airlines_80, validation_frame=airlines_20)
...抛出以下错误：
stackedensemble Model Build progress: | (failed)
---------------------------------------------------------------------------
OSError Traceback (most recent call last)
<ipython-input-26-bc7b6094816f> in <module>()
1 ensemble = H2OStackedEnsembleEstimator(base_models=all_model_ids)
----> 2 ensemble.train(x=x, y=y, training_frame=airlines_80, validation_frame=airlines_20)
/anaconda3/lib/python3.6/site-packages/h2o/estimators/estimator_base.py in train(self, x, y, training_frame, offset_column, fold_column, weights_column, validation_frame, max_runtime_secs, ignored_columns, model_id, verbose)
235 return
236
--> 237 model.poll(verbose_model_scoring_history=verbose)
238 model_json = h2o.api("GET /%d/Models/%s" % (rest_ver, model.dest_key))["models"][0]
239 self._resolve_model(model.dest_key, model_json)
/anaconda3/lib/python3.6/site-packages/h2o/job.py in poll(self, verbose_model_scoring_history)
75 if (isinstance(self.job, dict)) and ("stacktrace" in list(self.job)):
76 raise EnvironmentError("Job with key {} failed with an exception: {}\nstacktrace: "
---> 77 "\n{}".format(self.job_key, self.exception, self.job["stacktrace"]))
78 else:
79 raise EnvironmentError("Job with key %s failed with an exception: %s" % (self.job_key, self.exception))
OSError: Job with key 017f00000132d4ffffffff$_a2359a38ec8d31316aee91398f0249f8 failed with an exception: water.exceptions.H2OIllegalArgumentException: Base model does not keep cross-validation predictions: 5
stacktrace:
water.exceptions.H2OIllegalArgumentException: Base model does not keep cross-validation predictions: 5
at hex.StackedEnsembleModel.checkAndInheritModelProperties(StackedEnsembleModel.java:382)
at hex.ensemble.StackedEnsemble$StackedEnsembleDriver.computeImpl(StackedEnsemble.java:234)
at hex.ModelBuilder$Driver.compute2(ModelBuilder.java:218)
at water.H2O$H2OCountedCompleter.compute(H2O.java:1395)
at jsr166y.CountedCompleter.exec(CountedCompleter.java:468)
at jsr166y.ForkJoinTask.doExec(ForkJoinTask.java:263)
at jsr166y.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:974)
at jsr166y.ForkJoinPool.runWorker(ForkJoinPool.java:1477)
at jsr166y.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:104)
你能看出我做错了什么吗？
您的每个模型中似乎都缺少参数 keep_cross_validation_predictions=True。例如，您希望为您的 GLM 执行以下操作，然后同样地为您要堆叠的其他模型执行以下操作：
glm_grid = H2OGridSearch(model=H2OGeneralizedLinearEstimator(fold_assignment=assignment_type, nfolds=folds,
keep_cross_validation_predictions=True),
grid_id='glm_grid',
hyper_params=glm_params,
search_criteria=search_criteria)