Enum linfa_preprocessing::tf_idf_vectorization::TfIdfMethod

pub enum TfIdfMethod {
    Smooth,
    NonSmooth,
    Textbook,
}

Methods for computing the inverse document frequency of a vocabulary entry

Variants

Smooth

Computes the idf as log(1+n/1+document_frequency) + 1. The “plus ones” inside the log add an artificial document containing every vocabulary entry, preventing divisions by zero. The “plus one” after the log allows vocabulary entries that appear in every document to still be considered with a weight of one instead of being completely discarded.

NonSmooth

Computes the idf as log(n/document_frequency) +1. The “plus one” after the log allows vocabulary entries that appear in every document to still be considered with a weight of one instead of being completely discarded. If a vocabulary entry has zero document frequency this will produce a division by zero.

Textbook

Textbook definition of idf, computed as log(n/ 1 + document_frequency) which prevents divisions by zero and discards entries that appear in every document.

Implementations

impl TfIdfMethod

pub fn compute_idf(&self, n: usize, df: usize) -> f64

Trait Implementations

impl Clone for TfIdfMethod

fn clone(&self) -> TfIdfMethod

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for TfIdfMethod

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Hash for TfIdfMethod

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H) where
    H: Hasher, 

Feeds a slice of this type into the given Hasher.

impl PartialEq<TfIdfMethod> for TfIdfMethod

fn eq(&self, other: &TfIdfMethod) -> bool

This method tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

This method tests for !=.

impl Eq for TfIdfMethod

impl StructuralEq for TfIdfMethod

impl StructuralPartialEq for TfIdfMethod