Merge potential next release v0.4 (#187) Breaking Changes
* First draft of the new n-dimensional arrays + NB use case * Improves default implementation of multiple Array methods * Refactors tree methods * Adds matrix decomposition routines * Adds matrix decomposition methods to ndarray and nalgebra bindings * Refactoring + linear regression now uses array2 * Ridge & Linear regression * LBFGS optimizer & logistic regression * LBFGS optimizer & logistic regression * Changes linear methods, metrics and model selection methods to new n-dimensional arrays * Switches KNN and clustering algorithms to new n-d array layer * Refactors distance metrics * Optimizes knn and clustering methods * Refactors metrics module * Switches decomposition methods to n-dimensional arrays * Linalg refactoring - cleanup rng merge (#172) * Remove legacy DenseMatrix and BaseMatrix implementation. Port the new Number, FloatNumber and Array implementation into module structure. * Exclude AUC metrics. Needs reimplementation * Improve developers walkthrough New traits system in place at `src/numbers` and `src/linalg` Co-authored-by: Lorenzo <tunedconsulting@gmail.com> * Provide SupervisedEstimator with a constructor to avoid explicit dynamical box allocation in 'cross_validate' and 'cross_validate_predict' as required by the use of 'dyn' as per Rust 2021 * Implement getters to use as_ref() in src/neighbors * Implement getters to use as_ref() in src/naive_bayes * Implement getters to use as_ref() in src/linear * Add Clone to src/naive_bayes * Change signature for cross_validate and other model_selection functions to abide to use of dyn in Rust 2021 * Implement ndarray-bindings. Remove FloatNumber from implementations * Drop nalgebra-bindings support (as decided in conf-call to go for ndarray) * Remove benches. Benches will have their own repo at smartcore-benches * Implement SVC * Implement SVC serialization. Move search parameters in dedicated module * Implement SVR. Definitely too slow * Fix compilation issues for wasm (#202) Co-authored-by: Luis Moreno <morenol@users.noreply.github.com> * Fix tests (#203) * Port linalg/traits/stats.rs * Improve methods naming * Improve Display for DenseMatrix Co-authored-by: Montana Low <montanalow@users.noreply.github.com> Co-authored-by: VolodymyrOrlov <volodymyr.orlov@gmail.com>
This commit is contained in:
@@ -5,7 +5,7 @@
|
||||
//!
|
||||
//! ### Usage Example
|
||||
//! ```
|
||||
//! use smartcore::linalg::naive::dense_matrix::DenseMatrix;
|
||||
//! use smartcore::linalg::basic::matrix::DenseMatrix;
|
||||
//! use smartcore::preprocessing::categorical::{OneHotEncoder, OneHotEncoderParams};
|
||||
//! let data = DenseMatrix::from_2d_array(&[
|
||||
//! &[1.5, 1.0, 1.5, 3.0],
|
||||
@@ -27,10 +27,10 @@
|
||||
use std::iter;
|
||||
|
||||
use crate::error::Failed;
|
||||
use crate::linalg::Matrix;
|
||||
use crate::linalg::basic::arrays::Array2;
|
||||
|
||||
use crate::preprocessing::data_traits::{CategoricalFloat, Categorizable};
|
||||
use crate::preprocessing::series_encoder::CategoryMapper;
|
||||
use crate::preprocessing::traits::{CategoricalFloat, Categorizable};
|
||||
|
||||
/// OneHotEncoder Parameters
|
||||
#[derive(Debug, Clone)]
|
||||
@@ -106,7 +106,7 @@ impl OneHotEncoder {
|
||||
pub fn fit<T, M>(data: &M, params: OneHotEncoderParams) -> Result<OneHotEncoder, Failed>
|
||||
where
|
||||
T: Categorizable,
|
||||
M: Matrix<T>,
|
||||
M: Array2<T>,
|
||||
{
|
||||
match (params.col_idx_categorical, params.infer_categorical) {
|
||||
(None, false) => Err(Failed::fit(
|
||||
@@ -157,7 +157,7 @@ impl OneHotEncoder {
|
||||
pub fn transform<T, M>(&self, x: &M) -> Result<M, Failed>
|
||||
where
|
||||
T: Categorizable,
|
||||
M: Matrix<T>,
|
||||
M: Array2<T>,
|
||||
{
|
||||
let (nrows, p) = x.shape();
|
||||
let additional_params: Vec<usize> = self
|
||||
@@ -174,7 +174,7 @@ impl OneHotEncoder {
|
||||
|
||||
for (pidx, &old_cidx) in self.col_idx_categorical.iter().enumerate() {
|
||||
let cidx = new_col_idx[old_cidx];
|
||||
let col_iter = (0..nrows).map(|r| x.get(r, old_cidx).to_category());
|
||||
let col_iter = (0..nrows).map(|r| x.get((r, old_cidx)).to_category());
|
||||
let sencoder = &self.category_mappers[pidx];
|
||||
let oh_series = col_iter.map(|c| sencoder.get_one_hot::<T, Vec<T>>(&c));
|
||||
|
||||
@@ -188,7 +188,7 @@ impl OneHotEncoder {
|
||||
Some(v) => {
|
||||
// copy one hot vectors to their place in the data matrix;
|
||||
for (col_ofst, &val) in v.iter().enumerate() {
|
||||
res.set(row, cidx + col_ofst, val);
|
||||
res.set((row, cidx + col_ofst), val);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -209,8 +209,8 @@ impl OneHotEncoder {
|
||||
}
|
||||
|
||||
for r in 0..nrows {
|
||||
let val = x.get(r, old_p);
|
||||
res.set(r, new_p, val);
|
||||
let val = x.get((r, old_p));
|
||||
res.set((r, new_p), *val);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -221,7 +221,7 @@ impl OneHotEncoder {
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use crate::linalg::naive::dense_matrix::DenseMatrix;
|
||||
use crate::linalg::basic::matrix::DenseMatrix;
|
||||
use crate::preprocessing::series_encoder::CategoryMapper;
|
||||
|
||||
#[cfg_attr(target_arch = "wasm32", wasm_bindgen_test::wasm_bindgen_test)]
|
||||
|
||||
Reference in New Issue
Block a user