Ошибка модели глубокого обучения при запуске H2O Automl - PullRequest
Новая
       31

Ошибка модели глубокого обучения при запуске H2O Automl

0 голосов
/ 04 февраля 2019

Я использую H20 (кластерная версия = 3.22.13) на моем локальном компьютере с использованием Python (3.6) и URL-адреса соединения - http://localhost:54321.

Код, который я использовал, можно найти ниже - 

import h2o
from h2o.automl import H2OAutoML
h2o.init()
# Load data into H2O
df = h2o.import_file('new6000-22.csv')
y='CAT'
splits = df.split_frame(ratios = [0.80], seed = 1)
train = splits[0]
test = splits[1]
aml_2 = H2OAutoML( project_name =      "powerplant_lb_frame",stopping_metric="misclassification",sort_metric="misclassification",stopping_rounds=20)
aml_2.train(y = y, training_frame = train, leaderboard_frame = test)
aml_2.leaderboard.head()

но исполнение останавливается на полпути со следующей ошибкой - 

OSError                                   Traceback (most recent call last)
<ipython-input-27-95b6caafc18d> in <module>()
     10 test = splits[1]
     11 aml_2 = H2OAutoML( project_name = "powerplant_lb_frame",stopping_metric="misclassification",sort_metric="misclassification",stopping_rounds=20)
---> 12 aml_2.train(y = y, training_frame = train, leaderboard_frame = test)
     13 aml_2.leaderboard.head()
     14 

~/.local/lib/python3.6/site-packages/h2o/automl/autoh2o.py in train(self, x, y, training_frame, fold_column, weights_column, validation_frame, leaderboard_frame)
    377 
    378         self._job = H2OJob(resp['job'], "AutoML")
--> 379         self._job.poll()
    380         self._fetch()
    381 

~/.local/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 $03017f00000132d4ffffffff$_847c859d87411cd497d6253c8eea4b17 failed with an exception: water.exceptions.H2OKeyNotFoundArgumentException: Object not found: DeepLearning_grid_1_AutoML_20190203_203216_model_3
stacktrace: 
water.exceptions.H2OKeyNotFoundArgumentException: Object not found: DeepLearning_grid_1_AutoML_20190203_203216_model_3
    at hex.ModelMetrics$MetricsComparatorForFrame.findMetricsForModel(ModelMetrics.java:215)
    at hex.ModelMetrics$MetricsComparatorForFrame.compare(ModelMetrics.java:223)
    at hex.ModelMetrics$MetricsComparatorForFrame.compare(ModelMetrics.java:183)
    at java.base/java.util.TimSort.countRunAndMakeAscending(TimSort.java:355)
    at java.base/java.util.TimSort.sort(TimSort.java:234)
    at java.base/java.util.Arrays.sort(Arrays.java:1514)
    at java.base/java.util.ArrayList.sort(ArrayList.java:1587)
    at java.base/java.util.Collections.sort(Collections.java:175)
    at hex.ModelMetrics.sortModelsByMetric(ModelMetrics.java:311)
    at ai.h2o.automl.Leaderboard$1.atomic(Leaderboard.java:272)
    at ai.h2o.automl.Leaderboard$1.atomic(Leaderboard.java:223)
    at water.TAtomic.atomic(TAtomic.java:17)
    at water.Atomic.compute2(Atomic.java:56)
    at water.Atomic.fork(Atomic.java:39)
    at water.Atomic.invoke(Atomic.java:31)
    at ai.h2o.automl.Leaderboard.addModels(Leaderboard.java:313)
    at ai.h2o.automl.Leaderboard.addModel(Leaderboard.java:360)
    at ai.h2o.automl.AutoML.addModel(AutoML.java:1473)
    at ai.h2o.automl.AutoML.pollAndUpdateProgress(AutoML.java:531)
    at ai.h2o.automl.AutoML.pollAndUpdateProgress(AutoML.java:456)
    at ai.h2o.automl.AutoML.defaultRandomForest(AutoML.java:931)
    at ai.h2o.automl.AutoML.learn(AutoML.java:1192)
    at ai.h2o.automl.AutoML.run(AutoML.java:413)
    at ai.h2o.automl.H2OJob$1.compute2(H2OJob.java:32)
    at water.H2O$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)

Может кто-нибудь помочь мне понять, что происходит?С наилучшими пожеланиями, Арджун

...