<p>We are a dynamic team and our passion is to successfully implement modern solutions and technologies for companies. What are the trends that will cause future change by digitising the world of work and business? We want to play an active part when it comes to shaping the digitisation and the workplace of the future. We collaborate with various experienced and internationally acclaimed software vendors with whom as implementation partner we help you to get the most out for your business. Therefore we work with technologies in the field of Robotic Process Automation (RPA) on personal robot assistants (PRA) and Artificial Inteligence (AI).</p>

8ab03c2e-4218-40cd-a397-38cf16a5b92a.png

f4c01edf-8d77-43ab-bfd5-8f63dc70a443.jpeg

Head of Delivery Germany

Can you please help me trouble-shoot this issue?

I am trying this ML package with UiPath and after I create and run the Pipeline, I am getting the following error:

Traceback (most recent call last): File "/home/aicenter/.local/lib/python3.8/site-packages/uipath_core/trainer_run.py", line 85, in main wrapper.run() File "/microservice/training_wrapper.py", line 57, in run return self.training_plugin.model_run() File "/home/aicenter/.local/lib/python3.8/site-packages/uipath_core/training_plugin.py", line 153, in model_run raise e File "/home/aicenter/.local/lib/python3.8/site-packages/uipath_core/training_plugin.py", line 145, in model_run self.run_train_only() File "/home/aicenter/.local/lib/python3.8/site-packages/uipath_core/training_plugin.py", line 214, in run_train_only self.train_model(self.local_dataset_directory) File "/home/aicenter/.local/lib/python3.8/site-packages/uipath_core/training_plugin.py", line 118, in train_model self.model.train(directory) File "/microservice/train.py", line 78, in train self.clf.fit(X_train, y_train) File "/home/aicenter/.local/lib/python3.8/site-packages/sklearn/utils/validation.py", line 72, in inner_f return f(**kwargs) File "/home/aicenter/.local/lib/python3.8/site-packages/sklearn/model_selection/_search.py", line 736, in fit self._run_search(evaluate_candidates) File "/home/aicenter/.local/lib/python3.8/site-packages/sklearn/model_selection/_search.py", line 1188, in _run_search evaluate_candidates(ParameterGrid(self.param_grid)) File "/home/aicenter/.local/lib/python3.8/site-packages/sklearn/model_selection/_search.py", line 715, in evaluate_candidates cv.split(X, y, groups))) File "/home/aicenter/.local/lib/python3.8/site-packages/sklearn/model_selection/_split.py", line 735, in split y = check_array(y, ensure_2d=False, dtype=None) File "/home/aicenter/.local/lib/python3.8/site-packages/sklearn/utils/validation.py", line 72, in inner_f return f(**kwargs) File "/home/aicenter/.local/lib/python3.8/site-packages/sklearn/utils/validation.py", line 650, in check_array raise ValueError("Found array with %d sample(s) (shape=%s) while a" ValueError: Found array with 0 sample(s) (shape=(0,)) while a minimum of 1 is required. Traceback (most recent call last): File "/home/aicenter/.local/bin/uipath-core-training", line 8, in <module> sys.exit(main()) File "/home/aicenter/.local/lib/python3.8/site-packages/uipath_core/trainer_run.py", line 91, in main raise e File "/home/aicenter/.local/lib/python3.8/site-packages/uipath_core/trainer_run.py", line 85, in main wrapper.run() File "/microservice/training_wrapper.py", line 57, in run return self.training_plugin.model_run() File "/home/aicenter/.local/lib/python3.8/site-packages/uipath_core/training_plugin.py", line 153, in model_run raise e File "/home/aicenter/.local/lib/python3.8/site-packages/uipath_core/training_plugin.py", line 145, in model_run self.run_train_only() File "/home/aicenter/.local/lib/python3.8/site-packages/uipath_core/training_plugin.py", line 214, in run_train_only self.train_model(self.local_dataset_directory) File "/home/aicenter/.local/lib/python3.8/site-packages/uipath_core/training_plugin.py", line 118, in train_model self.model.train(directory) File "/microservice/train.py", line 78, in train self.clf.fit(X_train, y_train) File "/home/aicenter/.local/lib/python3.8/site-packages/sklearn/utils/validation.py", line 72, in inner_f return f(**kwargs) File "/home/aicenter/.local/lib/python3.8/site-packages/sklearn/model_selection/_search.py", line 736, in fit self._run_search(evaluate_candidates) File "/home/aicenter/.local/lib/python3.8/site-packages/sklearn/model_selection/_search.py", line 1188, in _run_search evaluate_candidates(ParameterGrid(self.param_grid)) File "/home/aicenter/.local/lib/python3.8/site-packages/sklearn/model_selection/_search.py", line 715, in evaluate_candidates cv.split(X, y, groups))) File "/home/aicenter/.local/lib/python3.8/site-packages/sklearn/m.... (truncated).

It seems to be a pretty good Amail classification workflow, thanks.

- In the "Classify Email" workflow, I think you doubled the Multiple Assign activity, no big deal though.

- I couldn't find where you retrain the ML Model after getting the humain input.

56e2fcf7-959f-4884-b2bc-455e02797349.zip

97293b6c-8a57-41c4-b29f-898e7e8b821a.png

The downloadable skill and ML model which was developed by Roboyo in cooperation with DatasparQ will provide a good base level of performance for emails/text in one language (English or German). 

The model needs to be trained before first use and the “buckets” the model must use to classify the given emails/texts need to be clear and supplied in the training set. After the deployment the skill can be used directly in UiPath Studio to classify any text supplied as a string - no fiddling around with JSON or REST calls needed! 

The model gives back a confidence score based on which you can decide on how to proceed with the classification. Is the confidence too low? Send it to the action center and let a human classify the correct bucket and feed the results back for retraining the model!


This model is a great starting point for using AI Center to sort and classify text directly out of the Studio and then through your robots with ease! However, we understand that real-world use cases are often more complicated. Emails come in different languages and may require mapping to hierarchical classifications. Additionally, the measure of success for a classifier will vary across different use cases.


If you have further needs for this model, please get in touch with us by opening a question on this listing page and we will get back to you!

This AI Center model will classify emails according to their contents based on buckets that are given to it by supplying appropriate training data.