Struct DBSCAN 

pub struct DBSCAN {
    pub eps: f64,
    pub min_samples: usize,
    pub metric: DistanceMetric,
    pub labels: Option<Vec<i32>>,
    pub feature_columns: Option<Vec<String>>,
}

Density-Based Spatial Clustering of Applications with Noise (DBSCAN)

Fields

eps: f64

Neighborhood radius epsilon

min_samples: usize

Minimum number of points to form a core point

metric: DistanceMetric

Distance metric

labels: Option<Vec<i32>>

Cluster assignments for each sample (-1 for noise points)

feature_columns: Option<Vec<String>>

Feature columns used for clustering

Implementations

impl DBSCAN

pub fn new(eps: f64, min_samples: usize) -> Self

Create a new DBSCAN instance

pub fn with_metric(self, metric: DistanceMetric) -> Self

Set distance metric

pub fn with_columns(self, columns: Vec<String>) -> Self

Specify feature columns to use

Trait Implementations

impl Clone for DBSCAN

fn clone(&self) -> DBSCAN

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for DBSCAN

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

Formats the value using the given formatter.

impl ModelEvaluator for DBSCAN

fn evaluate( &self, _test_data: &DataFrame, _test_target: &str, ) -> Result<ModelMetrics>

Evaluate a model using test data

fn cross_validate( &self, _data: &DataFrame, _target: &str, _folds: usize, ) -> Result<Vec<ModelMetrics>>

Cross-validate a model

impl UnsupervisedModel for DBSCAN

fn fit(&mut self, data: &DataFrame) -> Result<()>

Fit model to training data

fn transform(&self, _data: &DataFrame) -> Result<DataFrame>

Transform data using the fitted model

fn fit_transform(&mut self, data: &DataFrame) -> Result<DataFrame>

Fit and transform in one step