ML Models

Amorphic's ML Models portal is a comprehensive tool designed to facilitate the creation and importation of machine learning models using Amazon Web Services (AWS) SageMaker. This portal provides users with a seamless interface to manage their machine learning workflows efficiently. The ML Models portal allows users to create, view, and apply machine learning models to datasets in the Amorphic portal.

ML Model Operations

Below is an in-depth look at the key features and functionalities of the ML Models portal:

• Creating ML Model: Create a new ML Model
• Viewing ML Model: View existing ML Model
• Apply ML Model: Apply an existing ML Model to a Dataset

Creating ML Model

To create ML Models:

1. Click on + New ML Model
2. Fill in the details shown in the table:

Attribute	Description
Model Name	This is the model name in the Amorphic portal.
Description	Describe the notebook purpose and important details.
Artifact Location	User has three possible venues for artifacts: Location: Use Amorphic Data Labs to create models in an S3 location. To upload a model file directly from this location, refer to the Data Labs section for the respective bucket details. Existing Resource: To import a model from the Amazon SageMaker Marketplace into the Amorphic Portal, submit a request to the administrator. The administrator will create a support ticket for the AWS Marketplace model using support@amorphicdata.com. The Amorphic team will ensure that the model is then available for selection. Upload: Selecting this option allows user to upload a SageMaker model tar file directly into the Amorphic portal. User has the option to upload any tar or tar.gz file into the portal.
Output Type	There are two options for the output which can be retrieved from the model: Dataset Data or Metadata. Select Dataset Data when the model needs to be run on a dataset file. Select Metadata when only retrieval/view of some AI/ML results are required, such as metadata on dataset files (which will be explained later).
Input Schema	This schema is used to identify the schema of the dataset on which the pre-processing type of ETL job or model will be run.
Output Schema	This schema identifies the dataset where the post-processing type of job or model output will be saved.
Algorithm Used	The platform currently supports all the major AWS Sagemaker models
Supported file formats	Select the appropriate file type for predictions. If the available options do not have the required format, select "Others". This will default to no file type required for batch predictions. Note: if a model is selected as "Others" file type, it can only be run on a "Others" file type dataset.
Preprocess Glue Job	Select the pre-processing ETL jobs created using Amorphic ETL functionality.
Postprocess Glue Job	Select the post-processing ETL jobs created using Amorphic ETL functionality.

Note

For Output Type:
Most of the time, user should use Dataset Data.
Dataset Data would require two additional inputs - Input and Output Schema.

For Schema(both Input and Output):
User can also import the schema of an Amorphic dataset using the "Import from Dataset" functionality
Both the schema should have the same following format matching the respective Datasets:

    [
        {
            "type": "Date",
            "name": "CreationDate",
            "Description": "Date type of data"
        },
        {
            "type": "String",
            "name": "Name",
            "Description": "String type of data"
        },
        {
            "type": "Double",
            "name": "Price",
            "Description": "Double type of data"
        }
    ]

Viewing ML Model

User can view the model details by clicking on the model name in the ML Models page. The model details page will allow user to perform user to perform update, share or delete operations. The below demonstration displays the same.

Apply ML Model

Once an Amorphic model object is created, user can run that model on a Dataset file in the Amorphic portal by following these steps:

1. Select a Dataset in the Amorphic portal.
2. Go to the Files tab and select the file on which user wants to run the model.
3. Click on the top right options for the file.
4. Click on Apply ML.
5. Select the ML-model from the model dropdown. All Amorphic model objects that match the corresponding input schema of the Dataset will be available for selection.
6. Select the required instance types. Note: certain AWS Marketplace subscribed models run on specific instance family types.
7. Select the Target Dataset. The Datasets matching the output schema of the Amorphic model object will be available for selection.
8. Click on “Submit”.

How ML Pipeline works in the Amorphic?

The below figure shows how a typical ML pipeline of Amorphic platform looks like. During the Amorphic model object creation process, the pre-processing and post-processing ETL job functionality provides a way to drag and drop ETL workflows for a smooth user access.