ML - MLModelBuilder

ML.MLModelBuilder

A builder to define (and optionally train) a machine learning model.

Example

  // use a DictType stream
  const training_stream = Stream(
      "My Stream",
      DictType(
          StringType,
          StructType({
              x: FloatType,
              y: FloatType,
          })
      )
  );

  // create a gradient boosted tree
  const ml_model = new MLModelBuilder("ML Training")
      .feature("x", FloatType)
      .output(FloatType)
      .model({ type: "boosted_trees", noise: "none" })
      .trainFromStream({
          output_name: "y",
          input: training_stream,
      });

Type parameters

Name	Type
`Name`	extends `string`
`Features`	extends `Record` =

ML

constructor

• new MLModelBuilder(name, module?):

MLModelBuilder

Construct a new ML model with a given name

Type parameters

Name	Type
`Name`	extends `string`
`Features`	extends `Record` =

Parameters

Name	Type
`name`	`Name`
`module?`	`ModulePath` \| `ModuleBuilder`

Returns

MLModelBuilder

Example

  // use a DictType stream
  const training_stream = Stream(
      "My Stream",
      DictType(
          StringType,
          StructType({
              x: FloatType,
              y: FloatType,
          })
      )
  );

  // create a gradient boosted tree
  const ml_model = new MLModelBuilder("ML Training")
      .feature("x", FloatType)
      .output(FloatType)
      .model({ type: "boosted_trees", noise: "none" })
      .trainFromStream({
          output_name: "y",
          input: training_stream,
      });

feature

▸ feature(name, type):

MLModelBuilder<Name, Features & { [K in string]: T }>

Define an input feature for the model.

Type parameters

Name	Type
`FeatureName`	extends `string`
`T`	extends `EastType`

Parameters

Name	Type	Description
`name`	`FeatureName`	the name of the feature
`type`	`T`	the EastType of the feature

Returns

MLModelBuilder<Name, Features & { [K in string]: T }>

Example

  // create a gradient boosted tree
  const ml_model = new MLModelBuilder("ML Training")
      .feature("x", FloatType)
      .output(FloatType)

output

▸ output(type): T extends

FloatType ? FloatMLBuilder<Name, Features, { noise: "gaussian" ; type: "gaussian_process" }> : StringMLBuilder<Name, Features, { noise: "weighted" ; type: "boosted_trees_string" }>

Define the EastType the model will predict.

Type parameters

Name	Type
`T`	extends `FloatType` \| `StringType`

Parameters

Name	Type	Description
`type`	`T`	the EastType of the output

Returns

T extends

Example

  // create a gradient boosted tree
  const ml_model = new MLModelBuilder("ML Training")
      .output(FloatType)