Amazon SageMaker

Usage Methodology for the algorithm: 1) The input must be 'csv' file. 2) The csv file should contain column named "text". 3) The file should follow 'utf-8' encoding.

General instructions for consuming the service on Sagemaker: 1) Access to AWS SageMaker and the model package 2) An S3 bucket to specify input/output 3) Role for AWS SageMaker to access input/output from S3

Input

Supported content types: text/csv |-----------------------------------------------text-----------------------------------------------| we have been reaserching neighborhoods and so far New York seems to be the best.. New York is really nice if you can afford it new york is a bad place , dallas is ok but a bit out of the way i have never had a problem in New York even waiting for a night bus at 2am in morning

Output

Content type: text/csv --------------text----------------------------------------------|----entity----|---sentiment--- we have been reaserching neighborhoods and .. new york Positive New York is really nice if you can afford it. new york Positive new york is a bad place , dallas is ok but a bit out of the.. new york Negative new york is a bad place , dallas is ok but a bit out of the.. dallas Positive ....

Invoking endpoint

AWS CLI Command

You can invoke endpoint using AWS CLI:

aws sagemaker-runtime invoke-endpoint --endpoint-name $model_name --body fileb://$file_name --content-type 'text/csv' --region us-east-2 output.csv

Substitute the following parameters:

• "endpoint-name" - name of the inference endpoint where the model is deployed
• input.csv - input file to do the inference on
• text/csv - Type of input data
• output.csv - filename where the inference results are written to

Resources

Sample Notebook : https://tinyurl.com/y3qufjul Sample Input : https://tinyurl.com/y3d8n6rx Sample Output: https://tinyurl.com/y2qedbrj

Mphasis HyperGraf
Sample input
Sample jupyter notebook