Sold by: Mphasis
Deployed on AWS
The solution performs automated feature engineering steps like feature selection and can remove rare levels from features.
Overview
The solution will provide machine learning related feature engineering as output for the user provided data. The feature engineering operations to execute on the data can be specified by user in a separate config file. This will simplify the task of feature engineering for a data scientist where in the user will only have to specify select few parameter to generate the output feature engineered data instead of writing the complete code for the feature engineering pipeline.
Highlights
- This solution will transform the user input data by running machine learning related feature engineering operations as specified by the user. It can process tabular data which can have categorical and numerical values. The solution provides the most common feature engineering techniques including but not limited to check for inter-feature interaction, apply polynomial and trigonometric functions and can also remove rare levels.
- This solution saves a significant amount of time spent over developing and running different feature engineering operations on the data. This improves data scientists/engineers productivity and allows them to focus on more value added parts in the data science experiments.
- PACE - ML is Mphasis Framework and Methodology for end-to-end machine learning development and deployment. PACE-ML enables organizations to improve the quality & reliability of the machine learning solutions in production and helps automate, scale, and monitor them. Need customized Machine Learning and Deep Learning solutions? Get in touch!
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m5.large Inference (Batch) Recommended | Model inference on the ml.m5.large instance type, batch mode | $20.00 |
ml.m5.xlarge Inference (Real-Time) Recommended | Model inference on the ml.m5.xlarge instance type, real-time mode | $10.00 |
ml.m4.4xlarge Inference (Batch) | Model inference on the ml.m4.4xlarge instance type, batch mode | $20.00 |
ml.m5.4xlarge Inference (Batch) | Model inference on the ml.m5.4xlarge instance type, batch mode | $20.00 |
ml.m4.16xlarge Inference (Batch) | Model inference on the ml.m4.16xlarge instance type, batch mode | $20.00 |
ml.m5.2xlarge Inference (Batch) | Model inference on the ml.m5.2xlarge instance type, batch mode | $20.00 |
ml.p3.16xlarge Inference (Batch) | Model inference on the ml.p3.16xlarge instance type, batch mode | $20.00 |
ml.m4.2xlarge Inference (Batch) | Model inference on the ml.m4.2xlarge instance type, batch mode | $20.00 |
ml.c5.2xlarge Inference (Batch) | Model inference on the ml.c5.2xlarge instance type, batch mode | $20.00 |
ml.p3.2xlarge Inference (Batch) | Model inference on the ml.p3.2xlarge instance type, batch mode | $20.00 |
Vendor refund policy
Currently we do not support refunds, but you can cancel your subscription to the service at any time.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
It is the 2.1 version of the algorithm
Additional details
Inputs
- Summary
This solution takes a zip file as an input. This zip file should contain exactly two files as mentioned below
- Data.csv – This will be the data on which feature engineering is to be done
- Config.json – This file should contain parameters specific to feature engineering tasks to be executed on the supplied data
- Input MIME type
- text/csv, application/zip, text/plain
https://github.com/Mphasis-ML-Marketplace/Automated-Feature-Engineering/blob/main/Input/data.zip
https://github.com/Mphasis-ML-Marketplace/Automated-Feature-Engineering/blob/main/Input/data.zip
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
Feature_interactions_to_apply | It is defined in config.json file.
Specifies the manner in which features should be combined if feature interactions are the be applied. Can take more than one value from: add, subtract, divide, multiply. If more than one value is required please pass them in list format
| Type: Categorical
Allowed values: ‘add’, ‘subtract’, ‘divide’, ‘multiply’ | Yes |
Trget_variable | It is defined in config.json file.
Specifies the target variable from the provided input data. | Type: FreeText
Allowed values: It is given by user (column name) | Yes |
Feature_interactions_top_features_to_keep | It is defined in config.json file.
Specifies the percentage of top features to keep after applying arithmetic feature interactions to them. Should be as low as possible for better results. | Type: Continuous
Minimum: 0
Maximum: 1 | Yes |
Apply_polynomial_and_trigonometry_functions | It is defined in config.json file.
Specifies whether polynomial and trigonometric functions are to be applied on the base provided features to generate new features. Value: True/False | Type: Categorical
Allowed values: True, False | Yes |
Max_polynomial | It is defined in config.json file.
Specifies the degree of polynomial function to apply if apply_polynomial_and_trigonometry_functions is True
| Type: Integer
Minimum: 1 | Yes |
Trigonometry_functions | It is defined in config.json file.
Specifies the trigonometric functions to apply if apply_polynomial_and_trigonometric_functions is True. Can take more than one values from: sin, cos, tan. Pass values in the form of a list | Type: Categorical
Allowed values: ‘sin’, ‘cos’, ‘tan’ | Yes |
Top_poly_trig_features_to_keep | It is defined in config.json.
Specifies the percentage of top features to keep after applying polynomial and trigonometric feature interactions to them. Should be as low as possible for better results. | Type: Continuous
Minimum: 0
Maximum: 1 | Yes |
Club_rare_levels | It is defined in config.json.
Specifies whether all the rare categorical levels from the base input features should be clubbed into one.
Values: True/False
| Type: Categorical
Allowed values: True, False | Yes |
Rare_level_threshold | It is defined in config.json file.
Specifies the percentage of features to consider as rare levels. Should be as low as possible for better results. | Type: Continuous
Minimum: 0
Maximum: 1 | Yes |
Apply_feature_interactions | It is defined in config.json.
Specifies whether feature interaction should be applied to the input features provided. Value: True/False | Type: Categorical
Allowed values: True, False | Yes |
Resources
Vendor resources
Support
Vendor support
For any assistance, please reach out at:
AWS infrastructure support
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.
Similar products
Harness is an AI-powered software delivery platform that helps DevSecOps and engineering teams accelerate, secure, and optimize software delivery across cloud and hybrid environments. It automates every stage of the SDLC - from testing and deployments to security, cost management, and continuous verification - with AI-driven features like advanced deployment strategies, automated rollbacks, and real-time analytics. With modular products spanning the SDLC, Harness enables faster innovation, reduced risk, and optimized cloud spend, making it easier for enterprises to deliver software efficiently at scale.
Automated Feature Extraction (AFE) extracts and selects an optimal set of predictive features from transactional datasets without human effort. AFE is part of Autonon AutoML solution created by Organon Analytics.
dotData Cloud delivers a fully-managed cloud service encompassing all dotData products, along with comprehensive support, infrastructure, and management. The service includes dotData Enterprise for machine learning, dotData Insight for advanced analytics, dotData Feature Factory for automated feature engineering, and dotData Ops for seamless MLOps deployment.
Build, secure and run better websites, domains and applications on AWS with Plesk. Includes all your server management and security tools plus WordPress management (staging/cloning). Simplifying the lives of Web Professionals and providing the scalability, security, and performance that your web hosting customers need.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.