Unable to Train ML Package - EnglishTextClassification via Pipeline

[Amanyu_Roy]

Dear Community,

I am unable to train the ML Package - EnglishTextClassification via Pipeline.

Getting an error - Failed due to package issue.

Adding ML logs below for reference,
Traceback (most recent call last):
File “/home/aicenter/.local/lib/python3.6/site-packages/UiPath_core/trainer_run.py”, line 95, in main
wrapper.run()
File “/microservice/training_wrapper.py”, line 58, in run
return self.training_plugin.model_run()
File “/home/aicenter/.local/lib/python3.6/site-packages/UiPath_core/training_plugin.py”, line 195, in model_run
raise ex
File “/home/aicenter/.local/lib/python3.6/site-packages/UiPath_core/training_plugin.py”, line 167, in model_run
self.run_full_training()
File “/home/aicenter/.local/lib/python3.6/site-packages/UiPath_core/training_plugin.py”, line 212, in run_full_training
self.process_data()
File “/home/aicenter/.local/lib/python3.6/site-packages/UiPath_core/training_plugin.py”, line 530, in process_data
raise e
File “/home/aicenter/.local/lib/python3.6/site-packages/UiPath_core/training_plugin.py”, line 527, in process_data
self.process_data_model(self.local_dataset_directory)
File “/home/aicenter/.local/lib/python3.6/site-packages/UiPath_core/training_plugin.py”, line 152, in process_data_model
response = self.model.process_data(directory)
File “/microservice/train.py”, line 17, in process_data
self.model.process_data(directory)
File “/microservice/aiflib/model.py”, line 166, in process_data
raise UiPathUsageException(‘No valid data to run this pipeline.’)
aiflib.logger.UiPathUsageException: No valid data to run this pipeline.
Traceback (most recent call last):
File “/home/aicenter/.local/lib/python3.6/site-packages/UiPath_core/trainer_run.py”, line 101, in main
raise e
File “/home/aicenter/.local/lib/python3.6/site-packages/UiPath_core/trainer_run.py”, line 95, in main
wrapper.run()
File “/microservice/training_wrapper.py”, line 58, in run
return self.training_plugin.model_run()
File “/home/aicenter/.local/lib/python3.6/site-packages/UiPath_core/training_plugin.py”, line 195, in model_run
raise ex
File “/home/aicenter/.local/lib/python3.6/site-packages/UiPath_core/training_plugin.py”, line 167, in model_run
self.run_full_training()
File “/home/aicenter/.local/lib/python3.6/site-packages/UiPath_core/training_plugin.py”, line 212, in run_full_training
self.process_data()
File “/home/aicenter/.local/lib/python3.6/site-packages/UiPath_core/training_plugin.py”, line 530, in process_data
raise e
File “/home/aicenter/.local/lib/python3.6/site-packages/UiPath_core/training_plugin.py”, line 527, in process_data
self.process_data_model(self.local_dataset_directory)
File “/home/aicenter/.local/lib/python3.6/site-packages/UiPath_core/training_plugin.py”, line 152, in process_data_model
response = self.model.process_data(directory)
File “/microservice/train.py”, line 17, in process_data
self.model.process_data(directory)
File “/microservice/aiflib/model.py”, line 166, in process_data
raise UiPathUsageException(‘No valid data to run this pipeline.’)
aiflib.logger.UiPathUsageException: No valid data to run this pipeline.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File “/usr/local/lib/python3.6/site-packages/azure/storage/blob/_blob_client.py”, line 683, in delete_blob
self._client.blob.delete(**options)
File “/usr/local/lib/python3.6/site-packages/azure/storage/blob/_generated/operations/_blob_operations.py”, line 514, in delete
raise models.StorageErrorException(response, self._deserialize)
azure.storage.blob._generated.models._models_py3.StorageErrorException: Operation returned an invalid status ‘The specified blob does not exist.’
Content: <?xml version="1.0" encoding="utf-8"?>BlobNotFoundThe specified blob does not exist.
RequestId:9fc09980-501e-0029-711a-031b6d000000
Time:2023-10-20T05:56:18.2886086Z

During handling of the above exception, another exception occurred:

Traceback (most recent ca… (truncated).

[supermanPunch (Arpan)]

Hi @Amanyu_Roy ,

Could you let us know what is the dataset format provided ? Also if possible could you provide the dataset used if not confidential ?

[Amanyu_Roy]

Dear Arpan,

I have tried both json and csv file dataset. Please find a snippet of the dataset below,
[
{
“input”: “Extra Car Parking”,
“target”: “Rent”
},
{
“input”: “Lease Rent”,
“target”: “Rent”
},
“input”: “Housekeeping Service”,
“target”: “housekeeping charges”
},
{
“input”: “Maintenance & Repairs Service”,
“target”: “Repair & maintenance”
}
]

[sai_gupta]

@Amanyu_Roy

Check for potential issues in your data, preprocessing, or configuration, and ensure that your training pipeline is correctly set up for the English Text Classification ML package.

cheers…!

[supermanPunch (Arpan)]

@Amanyu_Roy ,

I did test it out myself, with a below dataset of Json format (created with the Help of GPT) which has around 100+ json pairs. I was able to create a Pipeline successfully.

As your Error logs does point to your dataset, could you maybe re-check on your dataset (Json format) if it is in proper format and with sufficient data ? Below is the dataset I have used :
Train Data.json (12.5 KB)

Also, For the Json format, there was no need to configure any parameters.

[Amanyu_Roy]

Dear @supermanPunch ,

Thanks for your support man. It is working now.

My previous dataset was having low no of input pairs. Maybe that was the reason.

Appreciate your efforts man.