Sign in
Sign in
or
Create a new account
Categories
Your Saved List Partners Sell in AWS Marketplace Amazon Web Services Home Help
Amazon SageMaker ×

Amazon SageMaker is a fully-managed platform that enables developers and data scientists to quickly and easily build, train, and deploy machine learning models at any scale. With Amazon SageMaker, all the barriers and complexity that typically slow down developers who want to use machine learning are removed. The service includes models that can be used together or independently to build, train, and deploy your machine learning models.

Explainable AI : Tree Based Explainer

By: Mphasis Latest Version: 2.4

An explainable AI solution based on tree based models providing global as well as local explanations

Product Overview

The solution helps users interpret complex black-box machine learning models by bringing out the important features which the model uses for predictions. It also identifies the features and their effect on the predictions, for each of the predictions. The solution supports 40+ tree based classifiers and regressors such as Random Forest, Decision Trees, XgBoost, CatBoost etc.

Key Data

Version
By Mphasis
Categories
Type Algorithm
Fulfillment Methods Amazon SageMaker

Usage Information

Fulfillment Methods

Amazon SageMaker

Supported Algorithms

Click here to get the list of supported algorithms

Input

  • Supported content-types for testing: application/zip
Input Schema: (For Training)

The Training requires three files to be present in S3 bukcet:

  • matrix.csv - This file contains the sparse matrix used to train tree based model by the user
  • model - Tree based model trained by user
  • featureimportance.png - A blank file which will be replaced by an image with global explanations
  • feature_names.csv - This file contains the list of features in the column 'features' Sample zipped files
Input Schema: (For Testing)

The Testing require three files to be ziped in input.zip file:

  • matrix.csv - Same as mentioned for training
  • feature_names.csv - Same as mentioned for training
  • x_explain.csv - Initial record before preprocessing and creating the matrix for training

Output

Content type: application/json. The json will contain two fields:

  • 'image-uri' - This field value is a image uri which user can copy-paste in broser url field to see the results for the model explainations
  • 'factors' - Contains the factors effecting the prediction/classification by the model

Notebook

Sample jupyter notebook

Additional Resources

End User License Agreement

By subscribing to this product you agree to terms and conditions outlined in the product End User License Agreement (EULA)

Support Information

Explainable AI : Tree Based Explainer

For any assistance reach out to us at:

https://www2.mphasis.com/AWS-Marketplace-Support-LP.html

AWS Infrastructure

AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services. Learn more

Refund Policy

Currently we do not support refunds, but you can cancel your subscription to the service at any time.

Customer Reviews