Struct abd_clam::VecDataset

pub struct VecDataset<I: Instance, U: Number, M: Instance> { /* private fields */ }

A Dataset of a Vec of instances.

This may be used for any data that can fit in memory. It is not recommended for large datasets.

Type Parameters

• T: The type of the instances in the Dataset.
• U: The type of the distance values between instances.
• M: The type of the metadata associated with each instance.

Implementations

impl<I: Instance, U: Number> VecDataset<I, U, usize>

pub fn new( name: String, data: Vec<I>, metric: fn(_: &I, _: &I) -> U, is_expensive: bool, ) -> Self

Creates a new dataset.

Arguments

• name: The name of the dataset.
• data: The vector of instances.
• metric: The metric for computing distances between instances.
• is_expensive: Whether the metric is expensive to compute.

impl<I: Instance, U: Number, M: Instance> VecDataset<I, U, M>

pub fn assign_metadata<Mn: Instance>( self, metadata: Vec<Mn>, ) -> Result<VecDataset<I, U, Mn>, String>

Assigns metadata to the dataset.

Arguments

• metadata: The metadata to assign to the dataset.

Returns

The dataset with the metadata assigned.

Errors

• If the metadata is not the same length as the dataset.

pub fn data(&self) -> &[I]

A reference to the underlying data.

pub fn data_owned(self) -> Vec<I>

Moves the underlying data out of the dataset.

pub fn metadata(&self) -> &[M]

A reference to the underlying metadata.

pub fn metadata_owned(self) -> Vec<M>

Moves the underlying metadata out of the dataset.

pub fn metadata_of(&self, index: usize) -> &M

A reference to the metadata of a specific instance.

Trait Implementations

impl<I: Clone + Instance, U: Clone + Number, M: Clone + Instance> Clone for VecDataset<I, U, M>

fn clone(&self) -> VecDataset<I, U, M>

Returns a copy of the value.

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

Performs copy-assignment from source.

impl<I: Instance, U: Number, M: Instance> Dataset<I, U> for VecDataset<I, U, M>

fn type_name() -> String

Returns the name of the type of the dataset.

fn name(&self) -> &str

Returns the name of the dataset. This is used to identify the dataset in various places.

fn cardinality(&self) -> usize

Returns the number of instances in the dataset.

fn is_metric_expensive(&self) -> bool

Whether or not the metric is expensive to calculate.

fn metric(&self) -> fn(_: &I, _: &I) -> U

Returns the metric used to calculate distances between instances.

fn set_permuted_indices(&mut self, indices: Option<&[usize]>)

Sets the permutation of indices that was used to reorder the dataset.

fn swap(&mut self, left: usize, right: usize) -> Result<(), String>

Swaps the location of two instances in the dataset.

fn permuted_indices(&self) -> Option<&[usize]>

Returns the permutation of indices that was used to reorder the dataset.

fn permute_instances(&mut self, permutation: &[usize]) -> Result<(), String>

Reorders the internal order of instances by a given permutation of indices.

fn make_shards(self, max_cardinality: usize) -> Vec<Self>

Makes a vector of sharded datasets from the given dataset.

fn save(&self, path: &Path) -> Result<(), String>

Saves the dataset to a file.

fn load( path: &Path, metric: fn(_: &I, _: &I) -> U, is_expensive: bool, ) -> Result<Self, String>

Loads a dataset from a file.

fn original_index(&self, index: usize) -> usize

Get the index before the dataset was reordered. If the dataset was not reordered, this is the identity function.

fn one_to_one(&self, left: usize, right: usize) -> U

Calculates the distance between two indexed instances in the dataset.

fn are_instances_equal(&self, left: usize, right: usize) -> bool

Returns whether or not two indexed instances in the dataset are equal.

fn one_to_many(&self, left: usize, right: &[usize]) -> Vec<U>

Returns a vector of distances.

fn many_to_many(&self, left: &[usize], right: &[usize]) -> Vec<Vec<U>>

Returns a vector of vectors of distances.

fn pairs(&self, index_pairs: &[(usize, usize)]) -> Vec<U>

Returns a vector of distances between the given pairs of indexed instances.

fn pairwise(&self, indices: &[usize]) -> Vec<Vec<U>>

Returns a vector of distances between all pairs of indexed instances.

fn query_to_one(&self, query: &I, index: usize) -> U

Calculates the distance between a query and an indexed instance in the dataset.

fn query_to_many(&self, query: &I, indices: &[usize]) -> Vec<U>

Returns a vector of distances between a query and all indexed instances.

fn choose_unique( &self, n: usize, indices: &[usize], seed: Option<u64>, ) -> Vec<usize>

Chooses a subset of indices that are unique with respect to the metric.

fn median(&self, indices: &[usize]) -> Option<usize>

Calculates the geometric median of a set of indexed instances. Returns a value from the set of indices that is the index of the median in the dataset.

fn linear_knn(&self, query: &I, k: usize) -> Vec<(usize, U)>

Runs linear KNN search on the dataset.

fn par_linear_knn(&self, query: &I, k: usize) -> Vec<(usize, U)>

Runs parallelized linear KNN search on the dataset.

fn linear_rnn(&self, query: &I, radius: U) -> Vec<(usize, U)>

Runs linear RNN search on the dataset.

fn par_linear_rnn(&self, query: &I, radius: U) -> Vec<(usize, U)>

Runs parallelized linear RNN search on the dataset.

impl<I: Debug + Instance, U: Debug + Number, M: Debug + Instance> Debug for VecDataset<I, U, M>

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

Formats the value using the given formatter.

impl<I: Instance, U: Number, M: Instance> Index<usize> for VecDataset<I, U, M>

type Output = I

The returned type after indexing.

fn index(&self, index: usize) -> &Self::Output

Performs the indexing (container[index]) operation.