I just did an update to the notebook for this video and included a few more tips that can help with this. The evaluation contains a metrics field which has a filed named 'confidenceMetrics' which is a list of metrics at different threshold levels ranging from low to high in increments of 0.005. Take a look and let me know if this helps!
![End-To-End: Interactive Code (Python) - AutoML in Vertex AI for ML Operations [notebook 02b]](http://i.ytimg.com/vi/GOxHYfCLc6U/mqdefault.jpg)
![End-To-End: Interactive Code (Python) - AutoML in Vertex AI for ML Operations [notebook 02b]](/img/tr.png)
![End-To-End: ML with SQL in BigQuery (BQML) [notebook 03a]](http://i.ytimg.com/vi/IcVyP_ZAXmY/mqdefault.jpg)
![End-to-End: Pipeline Orchestration (KFP) - BigQuery (BQML) Model For Endpoint Update [notebook 03C]](http://i.ytimg.com/vi/kzDd94KucBQ/mqdefault.jpg)
THANK YOU! 100 WORTH WATCHING
Thank you for great videos!
Great video Mike!
Can I retrieve the evaluation of API with different thresholds? I see by default the threshold is 0.5... If yes, how?
I just did an update to the notebook for this video and included a few more tips that can help with this. The evaluation contains a metrics field which has a filed named 'confidenceMetrics' which is a list of metrics at different threshold levels ranging from low to high in increments of 0.005. Take a look and let me know if this helps!