Release version 0.7.0 (rust-ml#320)

* Update CHANGELOG * (cargo-release) version 0.7.0 * (cargo-release) version 0.7.0 * (cargo-release) version 0.7.0 * (cargo-release) version 0.7.0 * (cargo-release) version 0.7.0 * (cargo-release) version 0.7.0 * (cargo-release) version 0.7.0 * (cargo-release) version 0.7.0 * (cargo-release) version 0.7.0 * (cargo-release) version 0.7.0 * (cargo-release) version 0.7.0 * (cargo-release) version 0.7.0 * (cargo-release) version 0.7.0 * (cargo-release) version 0.7.0 * (cargo-release) version 0.7.0 * (cargo-release) version 0.7.0 * (cargo-release) version 0.7.0 * (cargo-release) version 0.7.0 * Add news entry * Fix docs * Add date to changelog
gkcreate · Oct 16, 2023 · 34d1c84 · 34d1c84
1 parent f9f7dd4
commit 34d1c84
Show file tree

Hide file tree

Showing 24 changed files with 106 additions and 73 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,3 +1,18 @@
+Version 0.7.0 - 2023-10-15
+========================
+Changes
+-----------
+ * add `array_from_gz_csv` and `array_from_csv` in `linfa-datasets`
+ * make Serde support in `linfa-linear`, `linfa-logistic`, and `linfa-ftrl` optional
+ * bump `argmin` to 0.8.1
+ * add Serde support to `linfa-preprocessing` and `linfa-bayes`
+ * make licenses follow SPDX 2.1 license expression standard
+
+Removals
+-----------
+ * Removed Approximate DBSCAN from `linfa-clustering` due to performance issues. It's now an alias to regular DBSCAN.
+ * Removed `partitions` dependency, which breaks in current versions of Rust.
+
 Version 0.6.1 - 2022-12-03
 ========================
 New Algorithms

diff --git a/Cargo.toml b/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "linfa"
-version = "0.6.1"
+version = "0.7.0"
 authors = [
     "Luca Palmieri <rust@lpalmieri.com>",
     "Lorenz Schmidt <bytesnake@mailbox.org>",

diff --git a/algorithms/linfa-bayes/Cargo.toml b/algorithms/linfa-bayes/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "linfa-bayes"
-version = "0.6.1"
+version = "0.7.0"
 authors = ["VasanthakumarV <vasanth260m12@gmail.com>"]
 description = "Collection of Naive Bayes Algorithms"
 edition = "2018"
@@ -25,8 +25,8 @@ ndarray = { version = "0.15" , features = ["approx"]}
 ndarray-stats = "0.5"
 thiserror = "1.0"
 
-linfa = { version = "0.6.1", path = "../.." }
+linfa = { version = "0.7.0", path = "../.." }
 
 [dev-dependencies]
 approx = "0.4"
-linfa-datasets = { version = "0.6.1", path = "../../datasets", features = ["winequality"] }
+linfa-datasets = { version = "0.7.0", path = "../../datasets", features = ["winequality"] }
diff --git a/algorithms/linfa-clustering/Cargo.toml b/algorithms/linfa-clustering/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "linfa-clustering"
-version = "0.6.1"
+version = "0.7.0"
 edition = "2018"
 authors = [
     "Luca Palmieri <rust@lpalmieri.com>",
@@ -38,18 +38,18 @@ rand_xoshiro = "0.6"
 space = "0.12"
 thiserror = "1.0"
 #partitions = "0.2.4" This one will break in a future version of Rust and has no replacement
-linfa = { version = "0.6.1", path = "../.." }
-linfa-nn = { version = "0.6.1", path = "../linfa-nn" }
+linfa = { version = "0.7.0", path = "../.." }
+linfa-nn = { version = "0.7.0", path = "../linfa-nn" }
 noisy_float = "0.2.0"
 
 [dev-dependencies]
 ndarray-npy = { version = "0.8", default-features = false }
-linfa-datasets = { version = "0.6.1", path = "../../datasets", features = ["generate"] }
+linfa-datasets = { version = "0.7.0", path = "../../datasets", features = ["generate"] }
 criterion = "0.4.0"
 serde_json = "1"
 approx = "0.4"
 lax = "0.15.0"
-linfa = { version = "0.6.0", path = "../..", features = ["benchmarks"] }
+linfa = { version = "0.7.0", path = "../..", features = ["benchmarks"] }
 
 [[bench]]
 name = "k_means"

diff --git a/algorithms/linfa-elasticnet/Cargo.toml b/algorithms/linfa-elasticnet/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "linfa-elasticnet"
-version = "0.6.1"
+version = "0.7.0"
 authors = [
     "Paul Körbitz / Google <koerbitz@google.com>",
     "Lorenz Schmidt <bytesnake@mailbox.org>"
@@ -37,9 +37,9 @@ num-traits = "0.2"
 approx = "0.4"
 thiserror = "1.0"
 
-linfa = { version = "0.6.1", path = "../.." }
+linfa = { version = "0.7.0", path = "../.." }
 
 [dev-dependencies]
-linfa-datasets = { version = "0.6.1", path = "../../datasets", features = ["diabetes", "linnerud"] }
+linfa-datasets = { version = "0.7.0", path = "../../datasets", features = ["diabetes", "linnerud"] }
 ndarray-rand = "0.14"
 rand_xoshiro = "0.6"
diff --git a/algorithms/linfa-ftrl/Cargo.toml b/algorithms/linfa-ftrl/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "linfa-ftrl"
-version = "0.6.1"
+version = "0.7.0"
 authors = ["Liudmyla Kyrashchuk <himila@tutanota.com>"]
 
 description = "A Machine Learning framework for Rust"
@@ -31,13 +31,13 @@ thiserror = "1.0"
 rand = "0.8.5"
 rand_xoshiro = "0.6.0"
 
-linfa = { version = "0.6.1", path = "../.."}
+linfa = { version = "0.7.0", path = "../.."}
 
 [dev-dependencies]
 criterion = "0.4.0"
 approx = "0.4"
-linfa-datasets = { version = "0.6.1", path = "../../datasets", features = ["winequality"] }
-linfa = { version = "0.6.1", path = "../..", features = ["benchmarks"] }
+linfa-datasets = { version = "0.7.0", path = "../../datasets", features = ["winequality"] }
+linfa = { version = "0.7.0", path = "../..", features = ["benchmarks"] }
 
 [[bench]]
 name = "ftrl"

diff --git a/algorithms/linfa-hierarchical/Cargo.toml b/algorithms/linfa-hierarchical/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "linfa-hierarchical"
-version = "0.6.1"
+version = "0.7.0"
 authors = ["Lorenz Schmidt <lorenz.schmidt@mailbox.org>"]
 edition = "2018"
 
@@ -18,10 +18,10 @@ ndarray = { version = "0.15" }
 kodama = "0.2"
 thiserror = "1.0.25"
 
-linfa = { version = "0.6.1", path = "../.." }
-linfa-kernel = { version = "0.6.1", path = "../linfa-kernel" }
+linfa = { version = "0.7.0", path = "../.." }
+linfa-kernel = { version = "0.7.0", path = "../linfa-kernel" }
 
 [dev-dependencies]
 rand = "0.8"
 ndarray-rand = "0.14"
-linfa-datasets = { version = "0.6.1", path = "../../datasets", features = ["iris"] }
+linfa-datasets = { version = "0.7.0", path = "../../datasets", features = ["iris"] }
diff --git a/algorithms/linfa-ica/Cargo.toml b/algorithms/linfa-ica/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "linfa-ica"
-version = "0.6.1"
+version = "0.7.0"
 authors = ["VasanthakumarV <vasanth260m12@gmail.com>"]
 description = "A collection of Independent Component Analysis (ICA) algorithms"
 edition = "2018"
@@ -34,13 +34,13 @@ num-traits = "0.2"
 rand_xoshiro = "0.6"
 thiserror = "1.0"
 
-linfa = { version = "0.6.1", path = "../.." }
+linfa = { version = "0.7.0", path = "../.." }
 
 [dev-dependencies]
 ndarray-npy = { version = "0.8", default-features = false }
 paste = "1.0"
 criterion = "0.4.0"
-linfa = { version = "0.6.0", path = "../..", features = ["benchmarks"] }
+linfa = { version = "0.7.0", path = "../..", features = ["benchmarks"] }
 
 [[bench]]
 name = "fast_ica"

diff --git a/algorithms/linfa-kernel/Cargo.toml b/algorithms/linfa-kernel/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "linfa-kernel"
-version = "0.6.1"
+version = "0.7.0"
 authors = ["Lorenz Schmidt <bytesnake@mailbox.org>"]
 description = "Kernel methods for non-linear algorithms"
 edition = "2018"
@@ -28,5 +28,5 @@ ndarray = "0.15"
 num-traits = "0.2"
 sprs = { version="0.11", default-features = false }
 
-linfa = { version = "0.6.1", path = "../.." }
-linfa-nn = { version = "0.6.1", path = "../linfa-nn" }
+linfa = { version = "0.7.0", path = "../.." }
+linfa-nn = { version = "0.7.0", path = "../linfa-nn" }
diff --git a/algorithms/linfa-linear/Cargo.toml b/algorithms/linfa-linear/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "linfa-linear"
-version = "0.6.1"
+version = "0.7.0"
 authors = [
     "Paul Körbitz / Google <koerbitz@google.com>",
     "VasanthakumarV <vasanth260m12@gmail.com>"
@@ -36,14 +36,14 @@ argmin = { version = "0.8.1", default-features = false }
 argmin-math = { version = "0.3", features = ["ndarray_v0_15-nolinalg"] }
 thiserror = "1.0"
 
-linfa = { version = "0.6.1", path = "../.." }
+linfa = { version = "0.7.0", path = "../.." }
 
 [dev-dependencies]
-linfa-datasets = { version = "0.6.1", path = "../../datasets", features = ["diabetes"] }
+linfa-datasets = { version = "0.7.0", path = "../../datasets", features = ["diabetes"] }
 approx = "0.4"
 criterion = "0.4.0" 
 statrs = "0.16.0"
-linfa = { version = "0.6.0", path = "../..", features = ["benchmarks"] }
+linfa = { version = "0.7.0", path = "../..", features = ["benchmarks"] }
 
 [[bench]]
 name = "ols_bench"

diff --git a/algorithms/linfa-logistic/Cargo.toml b/algorithms/linfa-logistic/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "linfa-logistic"
-version = "0.6.1"
+version = "0.7.0"
 authors = ["Paul Körbitz / Google <koerbitz@google.com>"]
 
 description = "A Machine Learning framework for Rust"
@@ -30,9 +30,9 @@ argmin-math = { version = "0.3", features = ["ndarray_v0_15-nolinalg"] }
 thiserror = "1.0"
 
 
-linfa = { version = "0.6.1", path = "../.." }
+linfa = { version = "0.7.0", path = "../.." }
 
 [dev-dependencies]
 approx = "0.4"
-linfa-datasets = { version = "0.6.1", path = "../../datasets", features = ["winequality"] }
+linfa-datasets = { version = "0.7.0", path = "../../datasets", features = ["winequality"] }
 rmp-serde = "1"
diff --git a/algorithms/linfa-nn/Cargo.toml b/algorithms/linfa-nn/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "linfa-nn"
-version = "0.6.1"
+version = "0.7.0"
 authors = ["YuhanLiin <yuhanliin+github@protonmail.com>"]
 edition = "2018"
 description = "A collection of nearest neighbour algorithms"
@@ -33,14 +33,14 @@ thiserror = "1.0"
 
 kdtree = "0.6.0"
 
-linfa = { version = "0.6.1", path = "../.." }
+linfa = { version = "0.7.0", path = "../.." }
 
 [dev-dependencies]
 approx = "0.4"
 criterion = "0.4.0"
 rand_xoshiro = "0.6"
 ndarray-rand = "0.14"
-linfa = { version = "0.6.0", path = "../..", features = ["benchmarks"] }
+linfa = { version = "0.7.0", path = "../..", features = ["benchmarks"] }
 
 [[bench]]
 name = "nn"

diff --git a/algorithms/linfa-pls/Cargo.toml b/algorithms/linfa-pls/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "linfa-pls"
-version = "0.6.1"
+version = "0.7.0"
 edition = "2018"
 authors = ["relf <remi.lafage@onera.fr>"]
 description = "Partial Least Squares family methods"
@@ -33,11 +33,11 @@ ndarray-rand = "0.14"
 num-traits = "0.2"
 paste = "1.0"
 thiserror = "1.0"
-linfa = { version = "0.6.1", path = "../.." }
+linfa = { version = "0.7.0", path = "../.." }
 
 [dev-dependencies]
-linfa = { version = "0.6.1", path = "../..", features = ["benchmarks"] }
-linfa-datasets = { version = "0.6.1", path = "../../datasets", features = ["linnerud"] }
+linfa = { version = "0.7.0", path = "../..", features = ["benchmarks"] }
+linfa-datasets = { version = "0.7.0", path = "../../datasets", features = ["linnerud"] }
 approx = "0.4"
 rand_xoshiro = "0.6"
 criterion = "0.4.0"

diff --git a/algorithms/linfa-preprocessing/Cargo.toml b/algorithms/linfa-preprocessing/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "linfa-preprocessing"
-version = "0.6.1"
+version = "0.7.0"
 authors = ["Sauro98 <ivadonadi98@gmail.com>"]
 
 description = "A Machine Learning framework for Rust"
@@ -18,7 +18,7 @@ blas = ["ndarray-linalg", "linfa/ndarray-linalg"]
 serde = ["serde_crate", "ndarray/serde", "serde_regex"]
 
 [dependencies]
-linfa = { version = "0.6.1", path = "../.." }
+linfa = { version = "0.7.0", path = "../.." }
 ndarray = { version = "0.15", features = ["approx"] }
 ndarray-linalg = { version = "0.15", optional = true }
 linfa-linalg = { version = "0.1", default-features = false }
@@ -41,8 +41,8 @@ default-features = false
 features = ["std", "derive"]
 
 [dev-dependencies]
-linfa-datasets = { version = "0.6.1", path = "../../datasets", features = ["diabetes", "winequality"] }
-linfa-bayes = { version = "0.6.1", path = "../linfa-bayes" }
+linfa-datasets = { version = "0.7.0", path = "../../datasets", features = ["diabetes", "winequality"] }
+linfa-bayes = { version = "0.7.0", path = "../linfa-bayes" }
 iai = "0.1" 
 curl = "0.4.35"
 flate2 = "1.0.20"

diff --git a/algorithms/linfa-preprocessing/src/linear_scaling.rs b/algorithms/linfa-preprocessing/src/linear_scaling.rs
@@ -19,7 +19,7 @@ use serde_crate::{Deserialize, Serialize};
     serde(crate = "serde_crate")
 )]
 #[derive(Clone, Debug, PartialEq, Eq)]
-/// Possible scaling methods for [LinearScaler](LinearScaler)
+/// Possible scaling methods for [LinearScaler]
 ///
 /// * Standard (with mean, with std): subtracts the mean to each feature and scales it by the inverse of its standard deviation
 /// * MinMax (min, max): scales each feature to fit in the range `min..=max`, default values are
@@ -271,7 +271,7 @@ impl<F: Float> LinearScaler<F> {
         &self.scales
     }
 
-    /// Returns the method used for fitting. Useful for printing, since [ScalingMethod](ScalingMethod) implements `Display`
+    /// Returns the method used for fitting. Useful for printing, since [ScalingMethod] implements `Display`
     pub fn method(&self) -> &ScalingMethod<F> {
         &self.method
     }

diff --git a/algorithms/linfa-preprocessing/src/tf_idf_vectorization.rs b/algorithms/linfa-preprocessing/src/tf_idf_vectorization.rs
@@ -40,12 +40,12 @@ impl TfIdfMethod {
     }
 }
 
-/// Simlar to [`CountVectorizer`](CountVectorizer) but instead of
+/// Simlar to [`CountVectorizer`] but instead of
 /// just counting the term frequency of each vocabulary entry in each given document,
 /// it computes the term frequecy times the inverse document frequency, thus giving more importance
 /// to entries that appear many times but only on some documents. The weight function can be adjusted
 /// by setting the appropriate [method](TfIdfMethod). This struct provides the same string  
-/// processing customizations described in [`CountVectorizer`](CountVectorizer).
+/// processing customizations described in [`CountVectorizer`].
 #[cfg_attr(
     feature = "serde",
     derive(Serialize, Deserialize),
@@ -123,7 +123,7 @@ impl TfIdfVectorizer {
     }
 
     /// Learns a vocabulary from the texts in `x`, according to the specified attributes and maps each
-    /// vocabulary entry to an integer value, producing a [FittedTfIdfVectorizer](FittedTfIdfVectorizer).
+    /// vocabulary entry to an integer value, producing a [FittedTfIdfVectorizer].
     ///
     /// Returns an error if:
     /// * one of the `n_gram` boundaries is set to zero or the minimum value is greater than the maximum value
@@ -140,8 +140,8 @@ impl TfIdfVectorizer {
         })
     }
 
-    /// Produces a [FittedTfIdfVectorizer](FittedTfIdfVectorizer) with the input vocabulary.
-    /// All struct attributes are ignored in the fitting but will be used by the [FittedTfIdfVectorizer](FittedTfIdfVectorizer)
+    /// Produces a [FittedTfIdfVectorizer] with the input vocabulary.
+    /// All struct attributes are ignored in the fitting but will be used by the [FittedTfIdfVectorizer]
     /// to transform any text to be examined. As such this will return an error in the same cases as the `fit` method.
     pub fn fit_vocabulary<T: ToString>(&self, words: &[T]) -> Result<FittedTfIdfVectorizer> {
         let fitted_vectorizer = self.count_vectorizer.fit_vocabulary(words)?;

diff --git a/algorithms/linfa-preprocessing/src/whitening.rs b/algorithms/linfa-preprocessing/src/whitening.rs
@@ -39,7 +39,7 @@ pub enum WhiteningMethod {
 }
 
 /// Struct that can be fitted to the input data to obtain the related whitening matrix.
-/// Fitting returns a [FittedWhitener](FittedWhitener) struct that can be used to
+/// Fitting returns a [FittedWhitener] struct that can be used to
 /// apply the whitening transformation to the input data.
 #[cfg_attr(
     feature = "serde",
@@ -157,7 +157,7 @@ impl<F: Float, D: Data<Elem = F>, T: AsTargets> Fit<ArrayBase<D, Ix2>, T, Prepro
 
 /// Struct that can be used to whiten data. Data will be scaled according to the whitening matrix learned
 /// during fitting.
-/// Obtained by fitting a [Whitener](Whitener).
+/// Obtained by fitting a [Whitener].
 ///
 /// Transforming the data used during fitting will yield a scaled data matrix with
 /// unit diagonal covariance matrix.

diff --git a/algorithms/linfa-reduction/Cargo.toml b/algorithms/linfa-reduction/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "linfa-reduction"
-version = "0.6.1"
+version = "0.7.0"
 authors = ["Lorenz Schmidt <bytesnake@mailbox.org>"]
 description = "A collection of dimensionality reduction techniques"
 edition = "2018"
@@ -33,10 +33,10 @@ num-traits = "0.2"
 thiserror = "1.0"
 rand = { version = "0.8", features = ["small_rng"] }
 
-linfa = { version = "0.6.1", path = "../.." }
-linfa-kernel = { version = "0.6.1", path = "../linfa-kernel" }
+linfa = { version = "0.7.0", path = "../.." }
+linfa-kernel = { version = "0.7.0", path = "../linfa-kernel" }
 
 [dev-dependencies]
 ndarray-npy = { version = "0.8", default-features = false }
-linfa-datasets = { version = "0.6.1", path = "../../datasets", features = ["iris", "generate"] }
+linfa-datasets = { version = "0.7.0", path = "../../datasets", features = ["iris", "generate"] }
 approx = { version = "0.4" }