Indexing

As explained in Deep Learning with R, Third Edition

Indexing is the mapping of text tokens to integer positions in a vocabulary.

vocabulary <- c("the", "quick", "brown", "fox", "jumped", "over", "dog", ".")
words <- split_words("The quick brown fox jumped over the lazy dog.")
indices <- match(words, vocabulary, nomatch = 0L)
indices

[1] 0 2 3 4 5 6 1 0 7 8

How Deep Learning with R, Third Edition covers it

How deep it goes

Defines indexing and demonstrates vocabulary matching, without detailing model internals.

Examples

Uses a sentence, a word vocabulary, and R matching to show tokens mapped to integer positions.

What it assumes

Assumes text has been split into tokens and a vocabulary is available for lookup.

What you can do after

Apply R's match() to map split tokens to vocabulary indices, with unmatched tokens returning 0 in the example.

How it connects

Connects indexing to tokenization, standardization, splitting, and character, word, and subword tokenization.

liveBookmanning.com

Read Deep Learning with R, Third Edition on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Get Programming: Learn to code with Python
• 

  liveBookmanning.com
  Grokking Data StructuresAn array index is the position used to identify an element within an array.
• 

  liveBookmanning.com
  Modern C, Third EditionArray indexing is the C operation of selecting an array element with an index expression, such as A[i].
• 

  liveBookmanning.com
  Learn Rust in a Month of LunchesIndexing selects elements in an ordered collection by their numeric positions.
• 

  liveBookmanning.com
  Pro Angular 16An array index is a numeric position used to access an element in an array.
• 

  liveBookmanning.com
  Generative AI in ActionData indexing is the organization of stored data into searchable structures that support efficient information retrieval.
• 

  liveBookmanning.com
  Modern CAn index is an integer position used to identify an item in an array.
• 

  liveBookmanning.com
  Build AI-Enhanced Web AppsDocument indexing is the organization of document content into searchable structures for efficient information retrieval.
• 

  liveBookmanning.com
  Deep Learning with PyTorch, Second EditionSelecting tensor elements or slices by using tensor values as indices or masks.
• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionIndexing is the construction of auxiliary structures that organize document content for efficient retrieval.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionThe stage of text preprocessing that maps tokens to integer indices for numeric model input.
• 

  liveBookmanning.com
  Grokking SimplicityA numeric position identifying an element within an indexed array.
• 

  liveBookmanning.com
  Python Workout, Second EditionAn index is a numeric position identifying an element within an ordered sequence.
• 

  liveBookmanning.com
  The Well-Grounded Rubyist, Fourth EditionAn index is a numeric or key-based identifier for an element in a collection, including an ordinal position in an ordered collection.

Compare how 15 books explain indexing →

Related concepts

• arrayused by · An array is an indexed, ordered collection of elements arranged in one or more dimensions, with elements accessed by position.
• partial indexincludes · A partial index is a database index containing entries only for records that satisfy a specified predicate.
• covering indexincludes · A covering index is an index containing all columns needed to evaluate and return a query, avoiding access to the base table.
• tuplepart of · A tuple is a finite, ordered collection of elements treated as a single composite value or record.

This explainer was generated by Manning's knowledge graph from the text of Deep Learning with R, Third Edition. The section links point to the parts of the book it draws on.