Merge branch 'rust-ml:master' into master

Author: montanalow

.github/workflows/checking.yml

@@ -10,7 +10,7 @@ jobs:
       fail-fast: false
       matrix:
         toolchain:
-          - 1.67.0
+          - 1.70.0
           - stable
           - nightly
         os:

.github/workflows/codequality.yml

@@ -10,7 +10,7 @@ jobs:
     strategy:
       matrix:
         toolchain:
-          - 1.67.0
+          - 1.70.0
           - stable
 
     steps:

.github/workflows/testing.yml

@@ -10,7 +10,7 @@ jobs:
       fail-fast: false
       matrix:
         toolchain:
-          - 1.67.0
+          - 1.70.0
           - stable
         os:
           - ubuntu-latest
@@ -35,7 +35,7 @@ jobs:
       fail-fast: false
       matrix:
         toolchain:
-          - 1.67.0
+          - 1.70.0
           - stable
         os:
           - ubuntu-latest

.gitignore

@@ -36,3 +36,6 @@ poetry.lock
 # Generated artifacts of website (with Zola)
 docs/website/public/*
 docs/website/static/rustdocs/
+
+# Downloaded data for the linfa-preprocessing benches
+20news/

Cargo.toml

@@ -5,7 +5,7 @@ authors = [
     "Luca Palmieri <rust@lpalmieri.com>",
     "Lorenz Schmidt <bytesnake@mailbox.org>",
     "Paul Körbitz <koerbitz@google.com>",
-    "Yuhan Lin <yuhanliin@protonmail.com>"
+    "Yuhan Lin <yuhanliin@protonmail.com>",
 ]
 description = "A Machine Learning framework for Rust"
 edition = "2018"
@@ -41,12 +41,12 @@ rand = { version = "0.8", features = ["small_rng"] }
 approx = "0.4"
 
 ndarray = { version = "0.15", features = ["approx"] }
-ndarray-linalg = { version = "0.15", optional = true }
+ndarray-linalg = { version = "0.16", optional = true }
 sprs = { version = "0.11", default-features = false }
 
 thiserror = "1.0"
 
-criterion = { version = "0.4.0", optional = true}
+criterion = { version = "0.4.0", optional = true }
 
 [dependencies.serde_crate]
 package = "serde"
@@ -57,17 +57,22 @@ features = ["std", "derive"]
 
 [dev-dependencies]
 ndarray-rand = "0.14"
-linfa-datasets = { path = "datasets", features = ["winequality", "iris", "diabetes", "generate"] }
+linfa-datasets = { path = "datasets", features = [
+    "winequality",
+    "iris",
+    "diabetes",
+    "generate",
+] }
 statrs = "0.16.0"
 
 [target.'cfg(not(windows))'.dependencies]
-pprof = { version = "0.11.0", features = ["flamegraph", "criterion"], optional = true}
+pprof = { version = "0.11.0", features = [
+    "flamegraph",
+    "criterion",
+], optional = true }
 
 [workspace]
-members = [
-    "algorithms/*",
-    "datasets",
-]
+members = ["algorithms/*", "datasets"]
 
 [profile.release]
 opt-level = 3

…thms/linfa-bayes/examples/winequality.rs …infa-bayes/examples/winequality_bayes.rsalgorithms/linfa-bayes/examples/winequality.rs renamed to algorithms/linfa-bayes/examples/winequality_bayes.rs algorithms/linfa-bayes/examples/winequality.rs renamed to algorithms/linfa-bayes/examples/winequality_bayes.rs

@@ -84,7 +84,7 @@ where
             let nclass = xclass.nrows();
 
             // We compute the update of the gaussian mean and variance
-            let mut class_info = model
+            let class_info = model
                 .class_info
                 .entry(class)
                 .or_insert_with(GaussianClassInfo::default);

algorithms/linfa-bayes/src/gaussian_nb.rs

@@ -71,7 +71,7 @@ where
             let nclass = xclass.nrows();
 
             // We compute the feature log probabilities and feature counts on the slice corresponding to the current class
-            let mut class_info = model
+            let class_info = model
                 .class_info
                 .entry(class)
                 .or_insert_with(MultinomialClassInfo::default);

algorithms/linfa-bayes/src/multinomial_nb.rs

@@ -5,15 +5,21 @@ edition = "2018"
 authors = [
     "Luca Palmieri <rust@lpalmieri.com>",
     "xd009642 <danielmckenna93@gmail.com>",
-    "Rémi Lafage <remi.lafage@onera.fr>"
+    "Rémi Lafage <remi.lafage@onera.fr>",
 ]
 description = "A collection of clustering algorithms"
 license = "MIT OR Apache-2.0"
 
 repository = "https://github.com/rust-ml/linfa/"
 readme = "README.md"
 
-keywords = ["clustering", "machine-learning", "linfa", "k-means", "unsupervised"]
+keywords = [
+    "clustering",
+    "machine-learning",
+    "linfa",
+    "k-means",
+    "unsupervised",
+]
 categories = ["algorithms", "mathematics", "science"]
 
 [features]
@@ -28,9 +34,9 @@ default-features = false
 features = ["std", "derive"]
 
 [dependencies]
-ndarray = { version = "0.15", features = ["rayon", "approx"]}
+ndarray = { version = "0.15", features = ["rayon", "approx"] }
 linfa-linalg = { version = "0.1", default-features = false }
-ndarray-linalg = { version = "0.15", optional = true }
+ndarray-linalg = { version = "0.16", optional = true }
 ndarray-rand = "0.14"
 ndarray-stats = "0.5"
 num-traits = "0.2"
@@ -44,7 +50,9 @@ noisy_float = "0.2.0"
 
 [dev-dependencies]
 ndarray-npy = { version = "0.8", default-features = false }
-linfa-datasets = { version = "0.7.0", path = "../../datasets", features = ["generate"] }
+linfa-datasets = { version = "0.7.0", path = "../../datasets", features = [
+    "generate",
+] }
 criterion = "0.4.0"
 serde_json = "1"
 approx = "0.4"

algorithms/linfa-clustering/Cargo.toml

@@ -4,8 +4,15 @@ use linfa::Float;
 use linfa_nn::distance::{Distance, L2Dist};
 use ndarray::{Array1, ArrayView1, ArrayView2, ArrayViewMut1};
 use partitions::PartitionVec;
+#[cfg(feature = "serde")]
+use serde_crate::{Deserialize, Serialize};
 
 #[derive(Clone, Debug, PartialEq, Eq)]
+#[cfg_attr(
+    feature = "serde",
+    derive(Serialize, Deserialize),
+    serde(crate = "serde_crate")
+)]
 /// A point in a D dimensional euclidean space that memorizes its
 /// status: 'core' or 'non core'
 pub struct StatusPoint {
@@ -16,10 +23,7 @@ pub struct StatusPoint {
 
 impl StatusPoint {
     pub fn new(point_index: usize) -> StatusPoint {
-        StatusPoint {
-            point_index,
-            is_core: false,
-        }
+        StatusPoint { point_index, is_core: false }
     }
 
     pub fn is_core(&self) -> bool {
@@ -32,6 +36,11 @@ impl StatusPoint {
 }
 
 #[derive(Clone, Debug, PartialEq)]
+#[cfg_attr(
+    feature = "serde",
+    derive(Serialize, Deserialize),
+    serde(crate = "serde_crate")
+)]
 /// Informations regarding the cell used in various stages of the approximate DBSCAN
 /// algorithm if it is a core cell
 pub struct CoreCellInfo<F: Float> {
@@ -42,6 +51,11 @@ pub struct CoreCellInfo<F: Float> {
 }
 
 #[derive(Clone, Debug, PartialEq)]
+#[cfg_attr(
+    feature = "serde",
+    derive(Serialize, Deserialize),
+    serde(crate = "serde_crate")
+)]
 /// A cell from a grid that partitions the D dimensional euclidean space.
 pub struct Cell<F: Float> {
     /// The index of the intervals of the D dimensional axes where this cell lies