Struct Idf

pub struct Idf<T> { /* private fields */ }

Weighter of inverse document frequency.

Implementations

impl<T> Idf<T>

where T: Hash + Eq + Copy + Default,

pub fn new() -> Self

Creates an instance.

Examples found in repository

examples/find_cosine.rs (line 17)

fn main() {
    let documents = vec![
        "Welcome to Jimbocho, the town of books and curry!",
        "Welcome to Jimbocho, the city of books and curry!",
        "We welcome you to Jimbocho, the town of books and curry.",
        "Welcome to the town of books and curry, Jimbocho!",
    ];

    // Creates a searcher for word unigrams (with random seed value 42).
    let searcher = CosineSearcher::new(1, Some(' '), Some(42)).unwrap();
    // Creates a term frequency (TF) weighter.
    let tf = Tf::new();
    // Creates a inverse document frequency (IDF) weighter.
    let idf = Idf::new()
        .build(documents.iter().clone(), searcher.config())
        .unwrap();
    // Builds the database of binary sketches converted from input documents,
    let searcher = searcher
        // with the TF weighter and
        .tf(Some(tf))
        // the IDF weighter,
        .idf(Some(idf))
        // where binary sketches are in the Hamming space of 10*64 dimensions.
        .build_sketches_in_parallel(documents.iter(), 10)
        .unwrap();

    // Searches all similar pairs within radius 0.25.
    let results = searcher.search_similar_pairs(0.25);
    // A result consists of the left-side id, the right-side id, and their distance.
    assert_eq!(results, vec![(0, 1, 0.1671875), (0, 3, 0.246875)]);
}

pub const fn smooth(self, yes: bool) -> Self

Enables smoothing.

pub fn add(&mut self, terms: &[T])

Trains the frequency of terms for a document.

pub const fn num_docs(&self) -> usize

Gets the number of input documents.

pub fn idf(&self, term: T) -> f64

Computes the IDF of an input term.

impl Idf<u64>

pub fn build<I, D>(self, documents: I, config: &FeatureConfig) -> Result<Self>

where I: IntoIterator<Item = D>, D: AsRef<str>,

Trains the term frequency of input documents.

Arguments

• documents - List of documents.
• config - Configuration of feature extraction. Use the same configuration as that in search.

Examples found in repository

examples/find_cosine.rs (line 18)

fn main() {
    let documents = vec![
        "Welcome to Jimbocho, the town of books and curry!",
        "Welcome to Jimbocho, the city of books and curry!",
        "We welcome you to Jimbocho, the town of books and curry.",
        "Welcome to the town of books and curry, Jimbocho!",
    ];

    // Creates a searcher for word unigrams (with random seed value 42).
    let searcher = CosineSearcher::new(1, Some(' '), Some(42)).unwrap();
    // Creates a term frequency (TF) weighter.
    let tf = Tf::new();
    // Creates a inverse document frequency (IDF) weighter.
    let idf = Idf::new()
        .build(documents.iter().clone(), searcher.config())
        .unwrap();
    // Builds the database of binary sketches converted from input documents,
    let searcher = searcher
        // with the TF weighter and
        .tf(Some(tf))
        // the IDF weighter,
        .idf(Some(idf))
        // where binary sketches are in the Hamming space of 10*64 dimensions.
        .build_sketches_in_parallel(documents.iter(), 10)
        .unwrap();

    // Searches all similar pairs within radius 0.25.
    let results = searcher.search_similar_pairs(0.25);
    // A result consists of the left-side id, the right-side id, and their distance.
    assert_eq!(results, vec![(0, 1, 0.1671875), (0, 3, 0.246875)]);
}

Trait Implementations

impl<T: Default> Default for Idf<T>

fn default() -> Idf<T>

Returns the “default value” for a type.