Currently, when ROC values are calculated, they are based on thresholding values that have already been transformed to values of 0 or 1. Because all of the values are already 0 or 1, every threshold shows the same true positive and false positive rate. To resolve this issue, the ROC curve calculations have been updated to apply thresholds to the original values that have not yet been transformed to 0 or 1.

TA-1104

In both Windows and Linux environments, where the Regional setting is not U.S., and a model is generated with a Boolean goal, ROC curve and confusion matrix results appear incorrect. To resolve this issue in the short term, ThingWorx Analytics Server will be set to a U.S. locale during installation. With this solution, only U.S. data formats will be supported, but it avoids the need for all users to set their server to U.S. locales.

The long term goal for a future release is to support additional locales.

TA-1146

During installation on a non-English operating system, the output of certain commands is not externalized. When the non-English operating system translates the command output, an error is generated and causes the system to think a previous version is installed. This issue has been resolved.

TA-1233

When attempting to delete the Analytics Builder extension from the ThingWorx Foundation, in preparation to install a newer version, the removal fails because the AnalyticsServerFiltersInstance is still in use by another entity. Due to this conflicting dependency, the Analytics Builder extension cannot be completely removed and the upgrade is blocked. Two fixes have been implemented to resolve this issue:

TA-1282

When retrieving important fields from a scoring job run on a model generated by the Training microserver with a Boolean opType goal, an error occurs. The calculation expects the goal value from the scoring job to be a number and fails when it finds a True/False string. To resolve this issue, an update has been made to allow important fields to be calculated when scoring a Boolean goal PMML model generated by the Training microserver. For third-party PMML models, this solution may not be applicable.

TA-1339

When ThingWorx server is installed on the local server, and localhost is entered for connection purposes during the ThingWorx Analytics Docker installation, the connection validates successfully but the ThingWorx Analytics Server Things are not created in ThingWorx. The Edge Microserver in the Docker container cannot accept localhost as the connection to ThingWorx. The following possible work arounds are available to resolve this issue:

TA-536

When running a request for Signals, and specifying maxAtATime = 2, Mutual Information (MI), in relation to the goal, is not returned for all field combinations as expected. Instead, individual (one-at-a-time) MI scores are returned for all fields and then are filtered down to the top 25% most relevant fields. Two-at-a-time signals are calculated only for those fields. There is currently no way to modify this filtering behavior.

TA-729

When a dataset filter is deleted, all models, signals, profiles, and scoring jobs created using that filter should also be deleted. Currently, these items are not all being removed. New jobs cannot be initiated using the deleted filter, but if a user tries to retrain a model that was based on a deleted filter, the job will run against the entire dataset.

TA-502

When a time series model is built using the default lookback window size of 0, the lookback size is not retained when the time series model is retrained. This issue can manifest itself in two scenarios:

As a work around, rerun the training as a new model, using the same configuration as the original training job.

TA-472

While creating an analysis model for ThingPredictor, if you specify a network location in the Model File URL field, ThingPredictor cannot download the file and deploy the model.

AM-807

When deployer agent deploys an agent on a machine, the corresponding job status is shown to be in the INPROCESS state. However, the deployment is completed.

AM-819

Analysis agents must be restarted after a ThingWorx server restart. Without restart of the agent, any new simulation jobs will fail to execute.

—