Predicting: Predicting Class

In fuseMLR: Fusing Machine Learning in R

Predicting Class

Description

This class is designed for predictions.

The Predicting is structured as followed:

• PredictLayer: Exists for each modality.

  • PredictData: Related class for modality-specific predictions.

• PredictMetaLayer: Related class for meta predictions.

  • PredictData: Specific to the meta layer, it is set up internally after cross-validation.

Use the function train for training and predict for predicting.

TODO: Do not export me.

Super class

fuseMLR::HashTable -> Predicting

Methods

Public methods

• Predicting$new()

• Predicting$print()

• Predicting$createMetaTestData()

• Predicting$getIndIDs()

• Predicting$getPredictMetaLayer()

• Predicting$getIndCol()

Inherited methods

• fuseMLR::HashTable$add2HashTable()
• fuseMLR::HashTable$checkClassExist()
• fuseMLR::HashTable$getFromHashTable()
• fuseMLR::HashTable$getHashTable()
• fuseMLR::HashTable$getId()
• fuseMLR::HashTable$getKeyClass()
• fuseMLR::HashTable$removeFromHashTable()

---

Method new()

constructor

Usage

Predicting$new(id, ind_col)

Arguments

id

character
Predicting id.

ind_col

character Name of column of individuals IDS

---

Method print()

Printer

Usage

Predicting$print(...)

Arguments

...

any

---

Method createMetaTestData()

Creates a new modality-specific predictions dataset based on layer predictions.

Usage

Predicting$createMetaTestData(meta_layer_id)

Arguments

meta_layer_id

(character(1))
ID of the meta layer where the testing meta data will be stored.

Returns

A TestData is returned.

---

Method getIndIDs()

Gather individual IDs from all layer.

Usage

Predicting$getIndIDs()

Returns

A data.frame containing individuals IDs.

---

Method getPredictMetaLayer()

Getter of the meta layer.

Usage

Predicting$getPredictMetaLayer()

Returns

Object from class PredictMetaLayer

---

Method getIndCol()

Getter of the individual column name.

Usage

Predicting$getIndCol()

See Also

TrainLayer

fuseMLR documentation built on April 3, 2025, 8:49 p.m.