IBM / nlc-icd10-classifier

A simple web app that shows how Watson's Natural Language Classifier (NLC) can classify ICD-10 code. The app is written in Python using the Flask framework and leverages the Watson Developer Cloud Python SDK
https://developer.ibm.com/patterns/classify-icd-10-data-with-watson/
Apache License 2.0
113 stars 57 forks source link

Support for service in Frankfort #38

Closed PhilippeComte closed 5 years ago

PhilippeComte commented 5 years ago

To support a NLC instance in Frankfurt with apikey:

image

and

image

Not sure it's enough, but at least my credentials are recognised . As the model is not trained yet , I still have an error :

image
stevemar commented 5 years ago

@PhilippeComte the classifier can take a few minutes to build. That error message is expected while it's building. Give it a few minute (maybe 10?) and see if it builds.

From the docs:

Check the training status periodically until you see a status of Available. With this sample data, training takes about 6 minutes:

Issue a call to the Get information about a classifier method to retrieve the status of the classifier. Replace {apikey} and {url} with the credentials that you copied in the prerequisites. Replace {classifier_id} with your information.

curl -u "apikey:{apikey}" "{url}/v1/classifiers/{classifier_id}"

There's a bunch of docs here: https://console.bluemix.net/docs/services/natural-language-classifier/getting-started.html#natural-language-classifier

PhilippeComte commented 5 years ago

Hi Thank you ! I'll be patient !

stevemar commented 5 years ago

@PhilippeComte Is this still an issue for you?

PhilippeComte commented 5 years ago

No. Thanks for your help .