Plan to version 1.0.0

1. close issues that are irrelevant or too far-fetched
2. aggregate issues into macro-issues with sub-issues
3. prioritise and order for potential implementation

https://github.com/smartcorelib/smartcore/issues?page=1

Here is a comprehensive plan to organise the 52 open issues in smartcorelib/smartcore.

Issues to Close

These issues are either too vague, exploratory dead-ends, near-duplicates, or out of scope for a focused ML library:

Macro-Issues with Sub-Issues

Group actionable issues into 7 macro-themes:

🧱 1. Core API & Type System Cleanup

Foundation work that unblocks everything else.

• (Review usages for numbers traits #219 ) — Consolidate FloatNumber / RealNumber traits
• (Trait bounds of RandomForest::fit conflict with those of predict and other metrics #322 ) — Fix trait bound conflicts in RandomForest::fit vs metrics
• (Use Default::default instead of new in traits #230 ) — Replace new() with Default::default() in traits
• (Defaults only exist for Euclidean impls #174 ) — Defaults only exist for Euclidean distance impls
• (Serde JSON defaults don't match Default::default() #175 ) — Serde JSON defaults don't match Default::default()
• (Add getters to the structs in order to check internal state #73 ) — Add getters to structs to expose internal state

⚡ 2. Performance & Memory

Optimisation work for real-world scale.

• (tech-debt: replace unsafe raw-pointer iterator_mut in DenseMatrix (basic/matrix.rs) with safe split_at_mut approach #368 ) — Remove unsafe from iterator_mut (safe split_at_mut)
• (Consider implementing memory pooling system #317 ) — Memory pooling for tree construction
• (SIMD and Optimath #292 ) — SIMD / Optimath investigation
• (Look into slipstream and ILP #284 ) — Investigate slipstream and ILP
• (Compare performance of argsort and algorithm::sort::quick_sort #213 ) — Compare argsort vs quick_sort performance
• (Performance #261 ) — General performance gap vs scikit-learn
• (Consider the possibility to use [T] instead of Vec<T> in trait Array #199 ) — Use [T] slices instead of Vec in Array trait

🌲 3. Tree Models & Ensembles

High-demand improvements to the most-used model family.

• (Feature request: sample weights support in RandomForest (and other tree-based models) #356 ) — Sample weights in RandomForest
• (Variable Importance in Random Forest Analysis #124 ) — Variable importance in RandomForest
• (feature request: extra-trees classifier and regressor #183 ) — Extra-Trees classifier/regressor
• (Implement LEURN #254 ) — LEURN (neural net for tabular data, tree-based)

📐 4. Linear Models & Solvers

Completing the linear algebra and regression stack.

• (Add new solver that supports L1 penalty to Logistic Regression #70 ) — L1 solver (SAGA/LIBLINEAR) for Logistic Regression
• (Add L1 and Elastic Net regularization terms to the Logistic Regression #63 ) — L1 / ElasticNet regularisation in Logistic Regression
• (Request to add further summary stats, like Python OLS to regression #106 ) — F-stat, adjusted R2, t-stat for regression
• (Add Linear Discriminant Analysis (LDA) support #136 ) — Linear Discriminant Analysis (LDA)
• (Support for rust_decimal #49 ) — rust_decimal support (non-float arithmetic)

🔧 5. Data I/O & Interoperability

Making smartcore work in real pipelines.

• (Implement a convenience method DenseMatrix::from_ndarray2 (in case the ndarray feature is on) #326 ) — DenseMatrix::from_ndarray2 convenience method
• (Array conventions: support CSR #156 ) — CSR (Compressed Sparse Row) array support
• (Allow read/write of parquet files #249 ) — Parquet / Arrow file format support
• (Support streaming/incremental fitting #279 ) — Streaming / incremental fitting
• (Implement SGDClassifier #62 ) — SGDClassifier (incremental learning)

🖥️ 6. DX, Display & Documentation

Developer experience and discoverability.

• (Define default formatter for linalg::basic::arrays::{Array, Array2} #197 ) — Display impl for Array/Array2
• (Improve Display for naive_bayes #225 ) — Improve Display for NaiveBayes
• (No implementation of Display for Dataset #77 ) — Display for Dataset
• (Document features in Cargo.toml #68 ) — Document Cargo features
• (Have a guide for Wasm compilation #259 ) — WASM compilation guide
• (Consider applying derive_builder #189 ) — derive_builder for model parameters
• (Show clear input-shape validation errors instead of index out of bounds panics (was: index out of bounds using logistic_regression) #256 ) — Index out of bounds bug in logistic regression (large input)

🧩 7. New Algorithms

Expanding coverage for ML practitioners.

• (Make SVC multiclass #224 ) — Multiclass SVC (OvR/OvO)
• (Embed HDBSCAN #291 ) — HDBSCAN clustering
• (OPTICS algorithm #52 ) — OPTICS clustering
• (Implement Recursive Feature Elimination (RFE) algorithm #61 ) — Recursive Feature Elimination (RFE)
• (Implement OrdinalEncoder #59 ) — OrdinalEncoder / preprocessing
• (Add feature extractions tools #170 ) — Feature extraction (CountVectorizer, HashVectorizer)
• (Survival analysis #248 ) — Survival analysis
• (Feature request: time series functionality #91 ) — Time series functionality
• (Investigate possible usages of const contexts #226 ) — const context investigation

Priority Order for Implementation

The single highest-impact starting point is #322 + #219 (trait bound and number trait cleanup), since they directly break user workflows and their resolution would unblock correct cross-validation for tree models. Immediately after, the #256 logistic regression panic should be treated as a bug fix given its user impact.