Sequence Processor

Feature processor for encoding categorical sequences (e.g., medical codes) into numerical indices. Supports dynamic vocabulary construction.

Super classes

RHealth::Processor -> RHealth::FeatureProcessor -> SequenceProcessor

Public fields

code_vocab

A named integer vector representing token-to-index mappings.

.next_index

The next available index for unseen tokens.

Methods

Public methods

• SequenceProcessor$new()

• SequenceProcessor$process()

• SequenceProcessor$size()

• SequenceProcessor$print()

• SequenceProcessor$clone()

Inherited methods

• RHealth::Processor$load()
• RHealth::Processor$save()
• RHealth::FeatureProcessor$fit()

---

Method new()

Initialize with default vocabulary for and .

Usage

SequenceProcessor$new()

---

Method process()

Process a sequence of tokens into a tensor of indices.

Usage

SequenceProcessor$process(value)

Arguments

value

A character vector of tokens.

Returns

A long-type tensor of indices.

---

Method size()

Return size of vocabulary.

Usage

SequenceProcessor$size()

Returns

Integer

---

Method print()

Print summary.

Usage

SequenceProcessor$print(...)

Arguments

...

Ignored.

---

Method clone()

The objects of this class are cloneable with this method.

Usage

SequenceProcessor$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.