work/smartcore
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: consolidates API

Browse Source
This commit is contained in:
Volodymyr Orlov
2020-12-24 18:36:23 -08:00
parent a69fb3aada
commit 810a5c429b
25 changed files with 400 additions and 98 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/cluster/dbscan.rs
+45 -21
View File
@@ -15,8 +15,7 @@
//! let blobs = generator::make_blobs(100, 2, 3);
//! let x = DenseMatrix::from_vec(blobs.num_samples, blobs.num_features, &blobs.data);
//! // Fit the algorithm and predict cluster labels
//! let labels = DBSCAN::fit(&x, Distances::euclidian(),
//! DBSCANParameters::default().with_eps(3.0)).
//! let labels = DBSCAN::fit(&x, DBSCANParameters::default().with_eps(3.0)).
//! and_then(|dbscan| dbscan.predict(&x));
//!
//! println!("{:?}", labels);
@@ -33,9 +32,11 @@ use std::iter::Sum;
use serde::{Deserialize, Serialize};
use crate::algorithm::neighbour::{KNNAlgorithm, KNNAlgorithmName};
use crate::api::{Predictor, UnsupervisedEstimator};
use crate::error::Failed;
use crate::linalg::{row_iter, Matrix};
use crate::math::distance::Distance;
use crate::math::distance::euclidian::Euclidian;
use crate::math::distance::{Distance, Distances};
use crate::math::num::RealNumber;
use crate::tree::decision_tree_classifier::which_max;
@@ -50,7 +51,11 @@ pub struct DBSCAN<T: RealNumber, D: Distance<Vec<T>, T>> {
#[derive(Debug, Clone)]
/// DBSCAN clustering algorithm parameters
pub struct DBSCANParameters<T: RealNumber> {
pub struct DBSCANParameters<T: RealNumber, D: Distance<Vec<T>, T>> {
/// a function that defines a distance between each pair of point in training data.
/// This function should extend [`Distance`](../../math/distance/trait.Distance.html) trait.
/// See [`Distances`](../../math/distance/struct.Distances.html) for a list of available functions.
pub distance: D,
/// The number of samples (or total weight) in a neighborhood for a point to be considered as a core point.
pub min_samples: usize,
/// The maximum distance between two samples for one to be considered as in the neighborhood of the other.
@@ -59,7 +64,18 @@ pub struct DBSCANParameters<T: RealNumber> {
pub algorithm: KNNAlgorithmName,
}
impl<T: RealNumber> DBSCANParameters<T> {
impl<T: RealNumber, D: Distance<Vec<T>, T>> DBSCANParameters<T, D> {
/// a function that defines a distance between each pair of point in training data.
/// This function should extend [`Distance`](../../math/distance/trait.Distance.html) trait.
/// See [`Distances`](../../math/distance/struct.Distances.html) for a list of available functions.
pub fn with_distance<DD: Distance<Vec<T>, T>>(self, distance: DD) -> DBSCANParameters<T, DD> {
DBSCANParameters {
distance,
min_samples: self.min_samples,
eps: self.eps,
algorithm: self.algorithm,
}
}
/// The number of samples (or total weight) in a neighborhood for a point to be considered as a core point.
pub fn with_min_samples(mut self, min_samples: usize) -> Self {
self.min_samples = min_samples;
@@ -86,9 +102,10 @@ impl<T: RealNumber, D: Distance<Vec<T>, T>> PartialEq for DBSCAN<T, D> {
}
}
impl<T: RealNumber> Default for DBSCANParameters<T> {
impl<T: RealNumber> Default for DBSCANParameters<T, Euclidian> {
fn default() -> Self {
DBSCANParameters {
distance: Distances::euclidian(),
min_samples: 5,
eps: T::half(),
algorithm: KNNAlgorithmName::CoverTree,
@@ -96,6 +113,22 @@ impl<T: RealNumber> Default for DBSCANParameters<T> {
}
}
impl<T: RealNumber + Sum, M: Matrix<T>, D: Distance<Vec<T>, T>>
UnsupervisedEstimator<M, DBSCANParameters<T, D>> for DBSCAN<T, D>
{
fn fit(x: &M, parameters: DBSCANParameters<T, D>) -> Result<Self, Failed> {
DBSCAN::fit(x, parameters)
}
}
impl<T: RealNumber, M: Matrix<T>, D: Distance<Vec<T>, T>> Predictor<M, M::RowVector>
for DBSCAN<T, D>
{
fn predict(&self, x: &M) -> Result<M::RowVector, Failed> {
self.predict(x)
}
}
impl<T: RealNumber + Sum, D: Distance<Vec<T>, T>> DBSCAN<T, D> {
/// Fit algorithm to _NxM_ matrix where _N_ is number of samples and _M_ is number of features.
/// * `data` - training instances to cluster
@@ -103,8 +136,7 @@ impl<T: RealNumber + Sum, D: Distance<Vec<T>, T>> DBSCAN<T, D> {
/// * `parameters` - cluster parameters
pub fn fit<M: Matrix<T>>(
x: &M,
distance: D,
parameters: DBSCANParameters<T>,
parameters: DBSCANParameters<T, D>,
) -> Result<DBSCAN<T, D>, Failed> {
if parameters.min_samples < 1 {
return Err(Failed::fit(&"Invalid minPts".to_string()));
@@ -121,7 +153,9 @@ impl<T: RealNumber + Sum, D: Distance<Vec<T>, T>> DBSCAN<T, D> {
let n = x.shape().0;
let mut y = vec![unassigned; n];
let algo = parameters.algorithm.fit(row_iter(x).collect(), distance)?;
let algo = parameters
.algorithm
.fit(row_iter(x).collect(), parameters.distance)?;
for (i, e) in row_iter(x).enumerate() {
if y[i] == unassigned {
@@ -195,7 +229,6 @@ mod tests {
use super::*;
use crate::linalg::naive::dense_matrix::DenseMatrix;
use crate::math::distance::euclidian::Euclidian;
use crate::math::distance::Distances;
#[test]
fn fit_predict_dbscan() {
@@ -215,16 +248,7 @@ mod tests {
let expected_labels = vec![0.0, 0.0, 0.0, 0.0, 0.0, 1.0, 1.0, 1.0, 1.0, 1.0, -1.0];
let dbscan = DBSCAN::fit(
&x,
Distances::euclidian(),
DBSCANParameters {
min_samples: 5,
eps: 1.0,
algorithm: KNNAlgorithmName::CoverTree,
},
)
.unwrap();
let dbscan = DBSCAN::fit(&x, DBSCANParameters::default().with_eps(1.0)).unwrap();
let predicted_labels = dbscan.predict(&x).unwrap();
@@ -256,7 +280,7 @@ mod tests {
&[5.2, 2.7, 3.9, 1.4],
]);
let dbscan = DBSCAN::fit(&x, Distances::euclidian(), Default::default()).unwrap();
let dbscan = DBSCAN::fit(&x, Default::default()).unwrap();
let deserialized_dbscan: DBSCAN<f64, Euclidian> =
serde_json::from_str(&serde_json::to_string(&dbscan).unwrap()).unwrap();
src/cluster/kmeans.rs
+43 -22
View File
@@ -43,7 +43,7 @@
//! &[5.2, 2.7, 3.9, 1.4],
//! ]);
//!
//! let kmeans = KMeans::fit(&x, 2, Default::default()).unwrap(); // Fit to data, 2 clusters
//! let kmeans = KMeans::fit(&x, KMeansParameters::default().with_k(2)).unwrap(); // Fit to data, 2 clusters
//! let y_hat = kmeans.predict(&x).unwrap(); // use the same points for prediction
//! ```
//!
@@ -59,6 +59,7 @@ use std::iter::Sum;
use serde::{Deserialize, Serialize};
use crate::algorithm::neighbour::bbd_tree::BBDTree;
use crate::api::{Predictor, UnsupervisedEstimator};
use crate::error::Failed;
use crate::linalg::Matrix;
use crate::math::distance::euclidian::*;
@@ -101,11 +102,18 @@ impl<T: RealNumber> PartialEq for KMeans<T> {
#[derive(Debug, Clone)]
/// K-Means clustering algorithm parameters
pub struct KMeansParameters {
/// Number of clusters.
pub k: usize,
/// Maximum number of iterations of the k-means algorithm for a single run.
pub max_iter: usize,
}
impl KMeansParameters {
/// Number of clusters.
pub fn with_k(mut self, k: usize) -> Self {
self.k = k;
self
}
/// Maximum number of iterations of the k-means algorithm for a single run.
pub fn with_max_iter(mut self, max_iter: usize) -> Self {
self.max_iter = max_iter;
@@ -115,24 +123,37 @@ impl KMeansParameters {
impl Default for KMeansParameters {
fn default() -> Self {
KMeansParameters { max_iter: 100 }
KMeansParameters {
k: 2,
max_iter: 100,
}
}
}
impl<T: RealNumber + Sum, M: Matrix<T>> UnsupervisedEstimator<M, KMeansParameters> for KMeans<T> {
fn fit(x: &M, parameters: KMeansParameters) -> Result<Self, Failed> {
KMeans::fit(x, parameters)
}
}
impl<T: RealNumber, M: Matrix<T>> Predictor<M, M::RowVector> for KMeans<T> {
fn predict(&self, x: &M) -> Result<M::RowVector, Failed> {
self.predict(x)
}
}
impl<T: RealNumber + Sum> KMeans<T> {
/// Fit algorithm to _NxM_ matrix where _N_ is number of samples and _M_ is number of features.
/// * `data` - training instances to cluster
/// * `k` - number of clusters
/// * `data` - training instances to cluster
/// * `parameters` - cluster parameters
pub fn fit<M: Matrix<T>>(
data: &M,
k: usize,
parameters: KMeansParameters,
) -> Result<KMeans<T>, Failed> {
pub fn fit<M: Matrix<T>>(data: &M, parameters: KMeansParameters) -> Result<KMeans<T>, Failed> {
let bbd = BBDTree::new(data);
if k < 2 {
return Err(Failed::fit(&format!("invalid number of clusters: {}", k)));
if parameters.k < 2 {
return Err(Failed::fit(&format!(
"invalid number of clusters: {}",
parameters.k
)));
}
if parameters.max_iter == 0 {
@@ -145,9 +166,9 @@ impl<T: RealNumber + Sum> KMeans<T> {
let (n, d) = data.shape();
let mut distortion = T::max_value();
let mut y = KMeans::kmeans_plus_plus(data, k);
let mut size = vec![0; k];
let mut centroids = vec![vec![T::zero(); d]; k];
let mut y = KMeans::kmeans_plus_plus(data, parameters.k);
let mut size = vec![0; parameters.k];
let mut centroids = vec![vec![T::zero(); d]; parameters.k];
for i in 0..n {
size[y[i]] += 1;
@@ -159,16 +180,16 @@ impl<T: RealNumber + Sum> KMeans<T> {
}
}
for i in 0..k {
for i in 0..parameters.k {
for j in 0..d {
centroids[i][j] /= T::from(size[i]).unwrap();
}
}
let mut sums = vec![vec![T::zero(); d]; k];
let mut sums = vec![vec![T::zero(); d]; parameters.k];
for _ in 1..=parameters.max_iter {
let dist = bbd.clustering(&centroids, &mut sums, &mut size, &mut y);
for i in 0..k {
for i in 0..parameters.k {
if size[i] > 0 {
for j in 0..d {
centroids[i][j] = T::from(sums[i][j]).unwrap() / T::from(size[i]).unwrap();
@@ -184,7 +205,7 @@ impl<T: RealNumber + Sum> KMeans<T> {
}
Ok(KMeans {
k,
k: parameters.k,
y,
size,
distortion,
@@ -280,10 +301,10 @@ mod tests {
fn invalid_k() {
let x = DenseMatrix::from_2d_array(&[&[1., 2., 3.], &[4., 5., 6.]]);
assert!(KMeans::fit(&x, 0, Default::default()).is_err());
assert!(KMeans::fit(&x, KMeansParameters::default().with_k(0)).is_err());
assert_eq!(
"Fit failed: invalid number of clusters: 1",
KMeans::fit(&x, 1, Default::default())
KMeans::fit(&x, KMeansParameters::default().with_k(1))
.unwrap_err()
.to_string()
);
@@ -314,7 +335,7 @@ mod tests {
&[5.2, 2.7, 3.9, 1.4],
]);
let kmeans = KMeans::fit(&x, 2, Default::default()).unwrap();
let kmeans = KMeans::fit(&x, Default::default()).unwrap();
let y = kmeans.predict(&x).unwrap();
@@ -348,7 +369,7 @@ mod tests {
&[5.2, 2.7, 3.9, 1.4],
]);
let kmeans = KMeans::fit(&x, 2, Default::default()).unwrap();
let kmeans = KMeans::fit(&x, Default::default()).unwrap();
let deserialized_kmeans: KMeans<f64> =
serde_json::from_str(&serde_json::to_string(&kmeans).unwrap()).unwrap();