Tutorial 7-Build,Train,Deploy Machine Learning Model AWS SageMaker- Predicting Test Data Endpoints

Please donate if you want to support the channel through GPay UPID,

Please join as a member in my channel to get additional benefits like materials in Data Science, live streaming for Members and many more

Please do subscribe my other channel too

Connect with me here:

[scientificdots]

A very nice playlist sir. It would be great to see the complete playlists where the endpoint is ready for the backend people

[chisomokezie]

Considering the changes and the encountering of the SageMaker ImportError: The following is the most updated

from sagemaker.serializers import CSVSerializer
test_data_array = test_data.drop(['y_no', 'y_yes'], axis=1).values #Load the data into an array
xgb_predictor.content_type = 'text/csv'
xgb_predictor.serializer = CSVSerializer()
predictions =
predictions_array = np.fromstring(predictions[1:], sep=', ')

[victorhenostroza]

Thanks bro, now I can go to study the entire specialization course because of this introduction. Awesome

[amventures]

Thank you Krish naik.
I once followed the same tutorial somewhere else, the author didn't mention that we should delete the instances.
I got charged 190$ that month.

[sriharisrinivasan]

Hey Krish, if I'm not wrong, in 2:51 I believe the predictions[1:] is just a reduntant statement that excludes the 0 from the 0.025... I don't think its about taking the highest values' prediction.

[dipanjanabiswas]

I was wondering you will show how to get the endpoint, where to locate them so that the backend people can use them. It would be helpful if you show that as well.

[samiullahshah]

I really appreciate it as you make many things very clear to your viewers but you missed one thing and that creating an actual endpoint means an endpoint to the model that should be integrated with any app for live inference.

[suneel]

When will you continue this series showing deep learning models?

[apnacloud]

Overall good video playlist, i have leared a lot,

Krish, if possible please add one more video about connecting Endpoint in Aws API gateway or lambda, and how we can use that model through API,

it would be happy ending

Thank you krish

[uniqueavi]

Updated:

from sagemaker.serializers import CSVSerializer

test_data_array = test_data.drop(['y_no', 'y_yes'], axis=1).values #load the data into an array
xgb_predictor.serializer = CSVSerializer() # set the serializer type
predictions = # predict!
predictions_array = np.fromstring(predictions[1:], sep=', ') # and turn the prediction into an array

[Taranggpt]

Maja hi aa gya. Hope i can clear AWS Sagemaker Interview now

[roshanpasha]

Hai Krish, i havent get the deployment part . where the model got deployed

[baouevangelia]

i am trying to connect the endpoint to API Getaway but it requires the endpoint URL. How can i find it?

[PrateekChoukikar]

Hey, How can we migrate any model from SageMaker to Vertex AI??

[mehtabmehdi]

hi, at 4:50 in this confusion matrix, 9% or 34% is not accuracy, it is showing how our machine wrongly predicted, its less value is saying that our model is working good.

[himanshukarki]

Hi Krish, isn't there further upload on Sagemaker. I am seeing only 7 videos in the playlist.

[basiletalla]

Thank you Krish, I always appreciate your work and I deligently follow all your videos but please could slow down a bit when you speak, your explanation is good but I find it hard following you. Maybe I will have to watch it again and again

[manishsharma]

Completed the playlist in one shot ! Thank you sir

[scar]

During training you do use instances. Ml. Are they deleted automatically??

[krishnabisen]

Krish you said you were going to show us how to automate it with lambda, can we expect to get a new video in the playlist anytime?