Struct LocalOutlierFactor 

pub struct LocalOutlierFactor { /* private fields */ }

Local Outlier Factor (LOF) for density-based anomaly detection.

LOF detects anomalies based on local density deviation. Unlike global methods, it finds outliers in regions with varying density by comparing each point’s density to its neighbors’ densities.

Algorithm

1. For each point, find k-nearest neighbors
2. Compute reachability distance for each neighbor
3. Compute local reachability density (LRD) for each point
4. Compute LOF score: ratio of neighbors’ LRD to point’s LRD

LOF Score Interpretation

• LOF ≈ 1: Similar density to neighbors (normal point)
• LOF >> 1: Lower density than neighbors (outlier)
• LOF < 1: Higher density than neighbors (core point)

Examples

use aprender::prelude::*;

let data = Matrix::from_vec(
    6,
    2,
    vec![
        2.0, 2.0, 2.1, 2.0, 1.9, 2.1, 2.0, 1.9,  // Normal cluster
        10.0, 10.0, -10.0, -10.0,                 // Outliers
    ],
)
.expect("Valid matrix dimensions and data length");

let mut lof = LocalOutlierFactor::new()
    .with_n_neighbors(3)
    .with_contamination(0.3);
lof.fit(&data).expect("Fit succeeds with valid data");

// Predict returns 1 for normal, -1 for anomaly
let predictions = lof.predict(&data);

// score_samples returns LOF scores (higher = more anomalous)
let scores = lof.score_samples(&data);

Performance

• Time complexity: O(n² log k) for k-NN search
• Space complexity: O(n²) for distance matrix

Implementations

impl LocalOutlierFactor

pub fn new() -> Self

Create a new Local Outlier Factor with default parameters.

Default: 20 neighbors, 0.1 contamination

pub fn with_n_neighbors(self, n_neighbors: usize) -> Self

Set the number of neighbors.

pub fn with_contamination(self, contamination: f32) -> Self

Set the expected proportion of anomalies (0 to 0.5).

pub fn is_fitted(&self) -> bool

Check if model has been fitted.

pub fn fit(&mut self, x: &Matrix<f32>) -> Result<()>

Fit the Local Outlier Factor on training data.

pub fn score_samples(&self, x: &Matrix<f32>) -> Vec<f32>

Compute LOF scores for samples.

Returns a vector of LOF scores where higher scores indicate anomalies.

pub fn predict(&self, x: &Matrix<f32>) -> Vec<i32>

Predict anomaly labels for samples.

Returns 1 for normal points and -1 for anomalies.

pub fn negative_outlier_factor(&self) -> &[f32]

Get the negative outlier factor for training samples.

Returns negative of LOF scores (sklearn compatibility).

Trait Implementations

impl Clone for LocalOutlierFactor

fn clone(&self) -> LocalOutlierFactor

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LocalOutlierFactor

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

Formats the value using the given formatter.

impl Default for LocalOutlierFactor

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for LocalOutlierFactor

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for LocalOutlierFactor

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.