Analytics Extension

FlexRule.Extensions.Analytics

This extension enables Predictive Analytics capability to FlexRule platform. The extensions adds both expression commands Toolbox commands.

train

Trains and builds a predictive model using data.

 train (list, algorithm, class, options)

• algorithm:
  • PMML v4.3 (Read Details)
    • Regression Model
    • Generalized Regression Model
    • Naive Bayes Model
    • Classification and Regression Tree Model
    • Support Vector Machine Model
    • Random Forest (Mining Model)
    • Neural Networks Model
    • Clustering Model
    • Gradient Boosting Machine Model (Mining Model)
    • Association Rules Model
    • K-Nearest Neighbors Model
  • c45: Decision Tree
  • nb: Naive Bayes
• class: attributes name that is the class name (i.e. attribute or field of data that going ot be the result of prediction)
• options: Algorithm options if it is available
• Return: analytic’s trainedModel

predict

Uses a trained model to predict result for a data record.

 predict (trainedModel, data, options)

• trainedModel: the train function result.
• data: Situan that requires the prediction. (i.e. a JSON with fields of value)
• options: Algorithm options if it is available

extractRules

Extracts rules for Decision Tree.

 extractRules (trainedModel, type)

• type: if, elseIf
• Retrun: list of rules that are bases of the trained model

Examples

The following examples are available by default when you open FlexRule Designer.

• PMML Import and use Regression on IRIS Dataset
• Golf Weather Forecast
• Medical Diagnosis