"All trials either failed or did not return results to hyperopt." AutoML is not working on a fairly simple classification problem.

[colinsorensen]

First the exploratory notebook fails, though when I run it manually it works just fine.

After that, the AutoML notebook eventually fails without completing any trials.

I get this: Tried to attach usage logger `pyspark.databricks.pandas.usage_logger`, but an exception was raised: <property object at 0x7f2a7f543540> is not a callable object

/databricks/python_shell/dbruntime/PythonPackageImportsInstrumentation/__init__.py:16 .... AutoML run with experiment id: 1897258622316955 failed with ExecutionResultError('All trials either failed or did not return results to hyperopt.')

Tried Googling this error...found nothing.

[Anonymous]

@Colin Sorensen​ :

The error message "All trials either failed or did not return results to hyperopt" in AutoML indicates that the algorithm tried to find the best hyperparameters for the model, but it could not find any. This could be due to a variety of reasons such as lack of data, poor feature selection, or inadequate tuning of the hyperparameters.

Regarding the error "Tried to attach usage logger pyspark.databricks.pandas.usage_logger , but an exception was raised: <property object at 0x7f2a7f543540> is not a callable object", it appears to be related to the usage logger feature of PySpark. You can try disabling the usage logger by setting the configuration property "spark.databricks.pandas.usageLoggerAutoStart" to "false" before running your code.

Here is an example of how to set the configuration property in a Databricks notebook:

spark.conf.set("spark.databricks.pandas.usageLoggerAutoStart", "false")

If the issue persists, it might be helpful to check the AutoML logs for more details on why the trials failed or didn't return any results. You can find the logs in the "Logs" tab of the AutoML run.

[Anonymous]

Hi @Colin Sorensen​ 

Thank you for posting your question in our community! We are happy to assist you.

To help us provide you with the most accurate information, could you please take a moment to review the responses and select the one that best answers your question?

This will also help other community members who may have similar questions in the future. Thank you for your participation and let us know if you need any further assistance! 

[colinsorensen]

Ultimately this problem magically resolved itself. I think I updated the cluster or something.