Release 0.2.1

 * remove features for testing
 * fill up some missing information in Cargo.toml
 * make ready to publish to crates.io

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "linfa"
-version = "0.2.0"
+version = "0.2.1"
 authors = [
     "Luca Palmieri <[email protected]>",
     "Lorenz Schmidt <[email protected]>",
@@ -10,19 +10,21 @@ description = "A Machine Learning framework for Rust"
 edition = "2018"
 license = "MIT/Apache-2.0"
 
-repository = "https://github.com/LukeMathWalker/linfa"
+repository = "https://github.com/rust-ml/linfa"
 readme = "README.md"
 
 keywords = ["machine-learning", "linfa", "ai", "ml"]
 categories = ["algorithms", "mathematics", "science"]
 
+exclude = [".github/"]
+
 [dependencies]
-num-traits = "0.1.32"
+num-traits = "0.2"
 ndarray = { version = "0.13", default-features = false }
 
 [dev-dependencies]
 rand = "0.7"
-ndarray-rand = "0.11"
+ndarray-rand = "0.12"
 approx = "0.3"
 
 [workspace]

linfa-clustering/Cargo.toml

@@ -1,8 +1,12 @@
 [package]
 name = "linfa-clustering"
-version = "0.2.0"
+version = "0.2.1"
 edition = "2018"
-authors = ["Luca Palmieri <[email protected]>"]
+authors = [
+    "Luca Palmieri <[email protected]>",
+    "xd009642 <[email protected]>",
+    "Rémi Lafage <[email protected]>"
+]
 description = "A collection of clustering algorithms"
 license = "MIT/Apache-2.0"
 
@@ -28,7 +32,7 @@ sprs = "0.7"
 num-traits = "0.1.32"
 rand_isaac = "0.2.0"
 
-linfa = { path = ".." }
+linfa = { version = "0.2.1", path = ".." }
 
 [dev-dependencies]
 openblas-src = { version = "0.9", default-features = false, features = ["system"] }

linfa-hierarchical/Cargo.toml

@@ -1,26 +1,27 @@
 [package]
 name = "linfa-hierarchical"
-version = "0.2.0"
+version = "0.2.1"
 authors = ["Lorenz Schmidt <[email protected]>"]
 edition = "2018"
 
-description = "Support Vector Machines"
+description = "Agglomerative Hierarchical clustering"
 license = "MIT/Apache-2.0"
 
 repository = "https://github.com/rust-ml/linfa"
 readme = "README.md"
 
-keywords = ["hierachical", "agglomerative", "clustering", "cluster", "machine-learning", "linfa", "unsupervised"]
+keywords = ["hierachical", "agglomerative", "clustering", "machine-learning", "linfa"]
 categories = ["algorithms", "mathematics", "science"]
 
 [dependencies]
 ndarray = { version = "0.13", default-features = false }
 kodama = "0.2"
 
-linfa = { path = ".." }
-linfa-kernel = { path = "../linfa-kernel" }
+linfa = { version = "0.2.1", path = ".." }
+linfa-kernel = { version = "0.2.1", path = "../linfa-kernel" }
 
 [dev-dependencies]
+rand = "0.7"
 ndarray-rand = "0.11"
 csv = "1.1"
 ndarray-csv = "0.4"

linfa-ica/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "linfa-ica"
-version = "0.2.0"
+version = "0.2.1"
 authors = ["VasanthakumarV <[email protected]>"]
 description = "A collection of Independent Component Analysis (ICA) algorithms"
 edition = "2018"
@@ -17,10 +17,10 @@ ndarray = { version = "0.13", default-features = false }
 ndarray-rand = "0.11"
 ndarray-stats = "0.3"
 ndarray-linalg = "0.12"
-num-traits = "0.1.32"
+num-traits = "0.2"
 rand_isaac = "0.2.0"
 
-linfa = { path = ".." }
+linfa = { version = "0.2.1", path = ".." }
 
 [dev-dependencies]
 openblas-src = { version = "0.9", default-features = false, features = ["system"] }

linfa-kernel/Cargo.toml

@@ -1,12 +1,12 @@
 [package]
 name = "linfa-kernel"
-version = "0.2.0"
+version = "0.2.1"
 authors = ["Lorenz Schmidt <[email protected]>"]
 description = "Kernel methods for non-linear algorithms"
 edition = "2018"
 license = "MIT/Apache-2.0"
 
-repository = "https://github.com/rust-ml/linfa/"
+repository = "https://github.com/rust-ml/linfa"
 readme = "README.md"
 
 keywords = ["kernel", "machine-learning", "linfa"]
@@ -18,4 +18,4 @@ sprs = { version = "0.9", default-features = false }
 hnsw = "0.6"
 space = "0.10"
 
-linfa = { path = ".." }
+linfa = { version = "0.2.1", path = ".." }

linfa-linear/Cargo.toml

@@ -1,9 +1,20 @@
 [package]
 name = "linfa-linear"
-version = "0.2.0"
-authors = ["Paul Körbitz / Google <[email protected]>"]
+version = "0.2.1"
+authors = [
+    "Paul Körbitz / Google <[email protected]>",
+    "VasanthakumarV <[email protected]>"
+]
+
+description = "A Machine Learning framework for Rust"
 edition = "2018"
-workspace = ".."
+license = "MIT/Apache-2.0"
+
+repository = "https://github.com/rust-ml/linfa"
+readme = "README.md"
+
+keywords = ["machine-learning", "linfa", "ai", "ml", "linear"]
+categories = ["algorithms", "mathematics", "science"]
 
 [dependencies]
 ndarray = {version = "0.13", features = ["blas", "approx"]}

linfa-logistic/Cargo.toml

@@ -1,9 +1,17 @@
 [package]
 name = "linfa-logistic"
-version = "0.2.0"
+version = "0.2.1"
 authors = ["Paul Körbitz / Google <[email protected]>"]
+
+description = "A Machine Learning framework for Rust"
 edition = "2018"
-workspace = ".."
+license = "MIT/Apache-2.0"
+
+repository = "https://github.com/rust-ml/linfa"
+readme = "README.md"
+
+keywords = ["machine-learning", "linfa", "ai", "ml", "linear"]
+categories = ["algorithms", "mathematics", "science"]
 
 [dependencies]
 ndarray = {version = "0.13", features = ["blas", "approx"]}

linfa-reduction/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "linfa-reduction"
-version = "0.2.0"
+version = "0.2.1"
 authors = ["Lorenz Schmidt <[email protected]>"]
 description = "A collection of dimensionality reduction techniques"
 edition = "2018"
@@ -9,27 +9,20 @@ license = "MIT/Apache-2.0"
 repository = "https://github.com/rust-ml/linfa"
 readme = "README.md"
 
-keywords = ["dimensionality reduction", "machine-learning", "linfa", "spectral", "unsupervised"]
+keywords = ["reduction", "machine-learning", "linfa", "spectral", "unsupervised"]
 categories = ["algorithms", "mathematics", "science"]
 
-[features]
-default = []
-tests-openblas-system = ["openblas-src/system"]
-tests-openblas-build = ["openblas-src/cblas", "openblas-src/lapacke"]
-
 [dependencies]
 ndarray = "0.13"
 ndarray-rand = "0.11"
 ndarray-stats = "0.3"
 ndarray-linalg = "0.12"
-num-traits = "0.1.32"
+num-traits = "0.2"
 
-linfa = { path = ".." }
-linfa-kernel = { path = "../linfa-kernel" }
+linfa = { version = "0.2.1", path = ".." }
+linfa-kernel = { version = "0.2.1", path = "../linfa-kernel" }
 
 [dev-dependencies]
-openblas-src = { version = "0.9", default-features=false }
+openblas-src = { version = "0.9", default-features=false, features = ["system"] }
 rand_isaac = "0.2.0"
 ndarray-npy = { version = "0.5", default-features = false }
-criterion = "0.3"
-approx = "0.3"

linfa-svm/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "linfa-svm"
-version = "0.2.0"
+version = "0.2.1"
 edition = "2018"
 authors = ["Lorenz Schmidt <[email protected]>"]
 description = "Support Vector Machines"
@@ -9,16 +9,16 @@ license = "MIT/Apache-2.0"
 repository = "https://github.com/rust-ml/linfa"
 readme = "README.md"
 
-keywords = ["svm", "support vector machine", "machine-learning", "linfa", "supervised"]
+keywords = ["svm", "machine-learning", "linfa", "supervised"]
 categories = ["algorithms", "mathematics", "science"]
 
 [dependencies]
 ndarray = { version = "0.13", default-features=false, features=["blas"] }
 ndarray-rand = "0.11"
 num-traits = "0.1.32"
 
-linfa = { path = ".." }
-linfa-kernel = { path = "../linfa-kernel" }
+linfa = { version = "0.2.1", path = ".." }
+linfa-kernel = { version = "0.2.1", path = "../linfa-kernel" }
 
 [dev-dependencies]
 openblas-src = { version = "0.9", default-features = false, features = ["system"] }

linfa-trees/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "linfa-trees"
-version = "0.2.0"
+version = "0.2.1"
 edition = "2018"
 authors = ["Moss Ebeling <[email protected]>"]
 description = "A collection of tree-based algorithms"
@@ -22,7 +22,7 @@ ndarray-npy = { version = "0.5", default-features = false }
 criterion = "0.3"
 serde_json = "1"
 approx = "0.3"
-linfa-clustering = { path = "../linfa-clustering" }
+#linfa-clustering = { version = "0.2.1", path = "../linfa-clustering" }
 
 [[bench]]
 name = "decision_tree"

linfa-trees/examples/decision_tree.rs

@@ -1,10 +1,53 @@
-use linfa_clustering::generate_blobs;
 use linfa_trees::{DecisionTree, DecisionTreeParams, SplitQuality};
-use ndarray::{array, Array, ArrayBase, Data, Ix1};
+use ndarray::{array, Array, ArrayBase, Data, Ix1, Ix2, Array2, s};
+use ndarray_rand::rand::Rng;
 use ndarray_rand::rand::SeedableRng;
+use ndarray_rand::rand_distr::StandardNormal;
+use ndarray_rand::RandomExt;
 use rand_isaac::Isaac64Rng;
 use std::iter::FromIterator;
 
+/// Given an input matrix `blob_centroids`, with shape `(n_blobs, n_features)`,
+/// generate `blob_size` data points (a "blob") around each of the blob centroids.
+///
+/// More specifically, each blob is formed by `blob_size` points sampled from a normal
+/// distribution centered in the blob centroid with unit variance.
+///
+/// `generate_blobs` can be used to quickly assemble a synthetic dataset to test or
+/// benchmark various clustering algorithms on a best-case scenario input.
+pub fn generate_blobs(
+    blob_size: usize,
+    blob_centroids: &ArrayBase<impl Data<Elem = f64>, Ix2>,
+    rng: &mut impl Rng,
+) -> Array2<f64> {
+    let (n_centroids, n_features) = blob_centroids.dim();
+    let mut blobs: Array2<f64> = Array2::zeros((n_centroids * blob_size, n_features));
+
+    for (blob_index, blob_centroid) in blob_centroids.genrows().into_iter().enumerate() {
+        let blob = generate_blob(blob_size, &blob_centroid, rng);
+
+        let indexes = s![blob_index * blob_size..(blob_index + 1) * blob_size, ..];
+        blobs.slice_mut(indexes).assign(&blob);
+    }
+    blobs
+}
+
+/// Generate `blob_size` data points (a "blob") around `blob_centroid`.
+///
+/// More specifically, the blob is formed by `blob_size` points sampled from a normal
+/// distribution centered in `blob_centroid` with unit variance.
+///
+/// `generate_blob` can be used to quickly assemble a synthetic stereotypical cluster.
+pub fn generate_blob(
+    blob_size: usize,
+    blob_centroid: &ArrayBase<impl Data<Elem = f64>, Ix1>,
+    rng: &mut impl Rng,
+) -> Array2<f64> {
+    let shape = (blob_size, blob_centroid.len());
+    let origin_blob: Array2<f64> = Array::random_using(shape, StandardNormal, rng);
+    origin_blob + blob_centroid
+}
+
 fn accuracy(
     labels: &ArrayBase<impl Data<Elem = u64>, Ix1>,
     pred: &ArrayBase<impl Data<Elem = u64>, Ix1>,