Seasoned ⭐️⭐️

While running model prediction getting ModelFailedException: EntityMatchingModel 3531921825900910 failed with error 'JobFailedException: AttributeError('TfidfVectorizer' object has no attribute 'get_feature_names')'

8 replies
190 views

I am running the notebook for my own Cognite project as per the example https://github.com/cognitedata/dshub-tutorials/blob/master/advanced/Comparing%20Entity%20Matching%20models%20with%20SDK%20demo.ipynb

I am getting below error ModelFailedException: EntityMatchingModel 3531921825900910 failed with error 'JobFailedException: AttributeError('TfidfVectorizer' object has no attribute 'get_feature_names')' at line

results = model.predict(

sources=time_series_test, targets=assets).result

R

Rahul Kumar

Cognite Academy Instructor

Hi Jaydeep,

Please can you mention the course or lesson link here.
I am waiting to hearing back from you.

Regards
Kumar

Rahul Kumar

J

jaydeepAuthor

Seasoned ⭐️⭐️

This not in any particular course. We are trying to run the entity matcher models to contextualize the assets and time series data in our project using python SDK. The below link contains the notebook for the same

https://github.com/cognitedata/dshub-tutorials/blob/master/advanced/Comparing%20Entity%20Matching%20models%20with%20SDK%20demo.ipynb

R

Rahul Kumar

Cognite Academy Instructor

Hi Jaydeep,

I am in touch with the Data engineer and he is investigating the problem.
We will get back soon.

Thank you for your patience.

Regards
Kumar

Rahul Kumar

J

jaydeepAuthor

Seasoned ⭐️⭐️

Sure , this error especially come for frequency-weighted-bigram and bigram-combo feature_type

N

Nils Barlaug

Practitioner ⭐️⭐️⭐️

Hi Jaydeep,

This seems to be a bug on our side. We will roll out a fix soon and let you know when it’s ready.

Sorry for the inconvenience!

Nils