Scoring doenst work with image classification model

suzannechang

Hi all,

I have created a image classification model.

The training works and the model is quite ok.

Except the scoring doenst work, i get and python exit error -1

Can anyone help me out?

suzannechang

The Python process failed (exit code: 1). More info might be available in the logs.

Type: com.dataiku.dip.exceptions.ProcessDiedException

Clément_Stenac

Hi, this is only the error message. In order to understand what happened, we would need the complete log content.

suzannechang

pandas._libs.hashtable.PyObjectHashTable.get_item (pandas/_libs/hashtable.c:20477)
[08:47:01] [INFO] [dku.utils] - KeyError: u'appliance'
[08:47:02] [INFO] [dku.flow.activity] - Run thread failed for activity evaluate_on_test_NP
com.dataiku.dip.exceptions.ProcessDiedException: The Python process failed (exit code: 1). More info might be available in the logs.
at com.dataiku.dip.dataflow.exec.AbstractCodeBasedActivityRunner.throwSubprocessError(AbstractCodeBasedActivityRunner.java:395)
at com.dataiku.dip.dataflow.exec.AbstractCodeBasedActivityRunner.handleExecutionResult(AbstractCodeBasedActivityRunner.java:370)
at com.dataiku.dip.dataflow.exec.AbstractCodeBasedActivityRunner.execute(AbstractCodeBasedActivityRunner.java:311)
at com.dataiku.dip.dataflow.exec.AbstractCodeBasedActivityRunner.execute(AbstractCodeBasedActivityRunner.java:277)
at com.dataiku.dip.dataflow.exec.AbstractPythonRecipeRunner.executeModule(AbstractPythonRecipeRunner.java:41)
at com.dataiku.dip.analysis.ml.prediction.flow.EvaluationRecipeRunner.runPython(EvaluationRecipeRunner.java:276)
at com.dataiku.dip.analysis.ml.prediction.flow.EvaluationRecipeRunner.run(EvaluationRecipeRunner.java:199)
at com.dataiku.dip.dataflow.jobrunner.ActivityRunner$FlowRunnableThread.run(ActivityRunner.java:358)
[08:47:02] [INFO] [dku.flow.activity] running evaluate_on_test_NP - activity is finished
[08:47:02] [ERROR] [dku.flow.activity] running evaluate_on_test_NP - Activity failed
com.dataiku.dip.exceptions.ProcessDiedException: The Python process failed (exit code: 1). More info might be available in the logs.
at com.dataiku.dip.dataflow.exec.AbstractCodeBasedActivityRunner.throwSubprocessError(AbstractCodeBasedActivityRunner.java:395)
at com.dataiku.dip.dataflow.exec.AbstractCodeBasedActivityRunner.handleExecutionResult(AbstractCodeBasedActivityRunner.java:370)
at com.dataiku.dip.dataflow.exec.AbstractCodeBasedActivityRunner.execute(AbstractCodeBasedActivityRunner.java:311)
at com.dataiku.dip.dataflow.exec.AbstractCodeBasedActivityRunner.execute(AbstractCodeBasedActivityRunner.java:277)
at com.dataiku.dip.dataflow.exec.AbstractPythonRecipeRunner.executeModule(AbstractPythonRecipeRunner.java:41)
at com.dataiku.dip.analysis.ml.prediction.flow.EvaluationRecipeRunner.runPython(EvaluationRecipeRunner.java:276)
at com.dataiku.dip.analysis.ml.prediction.flow.EvaluationRecipeRunner.run(EvaluationRecipeRunner.java:199)
at com.dataiku.dip.dataflow.jobrunner.ActivityRunner$FlowRunnableThread.run(ActivityRunner.java:358)
[08:47:02] [INFO] [dku.flow.activity] running evaluate_on_test_NP - Executing default post-activity lifecycle hook
[08:47:02] [INFO] [dku.flow.activity] running evaluate_on_test_NP - Removing samples for NOGEENX.rwsr
[08:47:02] [INFO] [dku.flow.activity] running evaluate_on_test_NP - Removing samples for NOGEENX.tezfsadsa
[08:47:02] [INFO] [dku.flow.activity] running evaluate_on_test_NP - Done post-activity tasks

Alex_Combessie

In the log sample you posted, there is a "KeyError: u'appliance'" at the beginning. Is this a column used for training in the training dataset? If so, it should also be present in the dataset to be scored.