Amazon SageMaker

Input:

Following are the mandatory inputs for predictions made by the algorithm:

input_text : This is the path of the '.txt' file stored in S3. Ensure that the file is 'utf-8' encoded. Please follow the below instructions as well: 1) Within the content of the file, the address length must be between 5-9 words, without any special characters 2) The address must contain country name 3) In this version we extract USA and Canada address with following formats/patterns: - 1031 E 226th St Wakefield, USA - 331 E 132nd St Mott Haven, USA - 015 Matthews Ave Williamsbridge, USA - 3034 Hone Ave Baychester, USA 4) The Address extraction is purely pattern based recognition algorithm.

Supported content types for input: 'text/plain' Sample Input:

RKH Specialty Page 3 of 4 UMR: B0180 ME1706357 Fiscal and Regulatory Section TAX PAYABLE BY INSURER(S): None applicable. COUNTRY OF ORIGIN: United States of America. OVERSEAS BROKER: 331 E 132nd St Mott Haven, USA

Output:

Supported content types: 'text/csv' Sample Output:

Addresses
0, 331 E 132nd St Mott Haven, USA

Invoking endpoint:

If you are using real time inferencing, please create the endpoint first and then use the following command to invoke it:

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

Substitute the following parameters:

"endpoint-name" - name of the inference endpoint where the model is deployed "input.txt"- input text file to do the inference on "text/plain" - MIME type of the given input file (above) "output.csv" - filename where the inference results are written to

Resources:

Link to Instructions Notebook: https://tinyurl.com/tqtxju9

Link to Sample Input Txt Files : https://tinyurl.com/u8fahm8

Link to Sample Output csv files https://tinyurl.com/vene8nt

Mphasis DeepInsights
Sample Python Notebook
Sample Input File