Amazon SageMaker

Usage Methodology for the algorithm: 1) The input has to be a .csv file with the content in columns titled 'customer id', ‘x co-ordinates’, ‘y co-ordinates’, ‘demand’ 2) The file should follow 'utf-8' encoding. 3) The input can have a maximum of 375 demand points. 4) The first row should contain information of depot with id as 0 and demand column as capacity of each truck.( First row should contain depot and capacity of truck information) 5) customer id: id of customer; x co-ordinates; y co-ordinates; demand: demand of each customers.

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

Customer id-|----X co-ordinates-----|----Y co-ordinates----|-----Demands--------| 0 35 35 200 1 41 49 10 2 35 17 7 3 55 45 13 ….

Output

Content type: text/csv

----cluster id----|-----------------route----------------------------------------|----route_cost---| 1 [0, 103, 161, 135, 65, 71, 136, 35, 9, 120, 164, 0] 130.62 2 [0, 175, 11, 107, 64, 49, 168, 47, 143, 19, 123, 0] 132.68 3 [0, 4, 197, 56, 186, 187, 139, 170, 67, 25, 165,.. 0] 145.59 …..

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/y29hue6q Sample Input : https://tinyurl.com/y33n8qgp Sample Output: https://tinyurl.com/yy5o8u6u

Mphasis DeepInsights
Sample Input
Sample Jupyter Notebook(Instructions)