Feature Engineering

“Coming up with features is difficult, time-consuming, requires expert knowledge. ‘Applied machine learning is basically feature engineering.” — Prof. Andrew Ng.

---

Overview

Joule provides a feature engineering processor that enables users to define how features are to be created ready for predictive analytics use cases.

The processor generates for each declared feature field an engineered value. Two methods are supported; raw and compute values using custom expression and plugins. On completion a feature map is generated will all the required features and placed in the StreamEvent ready for the next processor in the pipeline.

Example

feature engineering:
  name: retailProfilingFeatures
  versioned: true
  features:
    as values:
      - location_code
      - store_id

    compute:
      spend_ratio:
        scripting:
          macro:
            expression: 1 - spend/avg_spend
            language: js
            variables:
              avg_spend: 133.78
      age:
        function:
          age binning:
            source field: date_of_birth
      day:
        function:
          day-of-week transform:
            source field: date

Top level attributes

Attribute	Description	Data Type	Required
name	Name feature set which is used for a predicting model	String
features	List of supported feature functions	List
versioned	A boolean flag to apply a unique version identifier to the resulting feature map	Boolean Default: true

Features Attribute

The features attribute provide two key elements, as value and compute.

DSL Structure

features:
  as values:
    - event field1
    - event field2
    
  compute:
    output_field:
      scripting:
        ...
    other_output_field:
      function:
        plugin_name:
          ... < plugin setting > ...
          event fields:
            - f
          variables:
            varname: value

Attribute	Description	Data Type	Required
as values	List of event fields whose value will be copied in to the feature map without any changes.	List
compute	List of supported feature functions mapped to output variables to be executed using the passed event.	List

Note: Either one of the attributes must be defined

---

Supported Feature Engineering

As Value

This is most basic function whereby the StreamEvent field value is copied in to the feature map.

Example

The below example will copy the defined event field values directly in to the feature map.

features:
  as values:
    - location_code
    - store_id

Expression Based

Joule core provides the ability to deploy declariative expressions using the custom analytics processor. This has been reused within the context of feature engineering to enable users to define custom calculations within the DSL.

Example

The below example computes, per event, the spend ration based upon a Javascript expression.

features:
  compute:
    spend_ratio:
      scripting:
        macro:
          expression: 1 - spend/avg_spend
          variables:
            avg_spend: 133.78

---

Custom Plugins

Developers can extend the feature engineering capabilities by extending the AbstractFeatureEngineeringFunction interface. See CustomUserPlugin API documentation for further details.

Example

The below example computes, per event, the scale price based upon the MinMax algorithm. This example implements the AbstractFeatureEngineeringFunction class.

features:
  compute:
    scaled_price:
      function:
        minmax scaler:
          source field: price
          variables:
            min: 10.00
            max: 12.78

Supported functions

Joule provides a small set of OOTB feature engineering functions.

Scripting

Scaling

Transform

Versioning

Every feature map created is versioned using a random UUID. The version is place directly in to the resulting map and accessed using the feature_version key.