I am trying to set up a basic text classification bot in Ai Centre to get familiar with the workflow. I don’t have any training data on hand so I created a small test case. In the Pipeline it says No data is found and throws this error:
Train only of ClassificationTest 2.0 launched - Run 84e5cb1a-06e8-43c9-9531-5d2d3b7eb70d
Train only of ClassificationTest 2.0 scheduled - Run 84e5cb1a-06e8-43c9-9531-5d2d3b7eb70d
Train only of ClassificationTest 2.0 started - Run 84e5cb1a-06e8-43c9-9531-5d2d3b7eb70d
Train only of ClassificationTest 2.0 failed - Run 84e5cb1a-06e8-43c9-9531-5d2d3b7eb70dError Details : Pipeline failed due to ML Package Issue
The training set has a single csv file. When I download the file in the Dataset I get the file I uploaded:
input,target
this is a test,test
and this is a test,test
this is also a test,test
this is not a test,notest
this certainly is not a test,notest
a test? No this can never be a test,notest
My ML Package is the standard EnglishTextClassification Package:
Arguments for ClassificationTest V 2.0
Input Type:JSON
Input description:
Text to be classified as String: ‘I loved this movie.’
Output description:
JSON with pedicted class name, associated confidence on that class prediction (between 0-1). For example: {“prediction”: “Positive”, “confidence”: 0.9422031841278076}
Recommend GPU: No
Enable Training: Yes
Status: Undeployed
Package Version: 2.0
Why is the error thrown?