docs: update for v0.5.0 additions + 0.5.0 CHANGELOG entry (#34)

CHANGELOG.md

@@ -5,7 +5,66 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [0.4.0] - 2025-01-17
+## [0.5.0] - 2026-05-28
+
+### Added
+
+- **Hybrid crate (Rust + Python)** — `polars-statistics` now builds as both a
+  `cdylib` (Python plugin) and an `rlib` (Rust dependency). Every Polars
+  expression has a public `<name>_fit` Rust entry point in
+  `polars_statistics::expressions`. New `python` Cargo feature gates the
+  pyo3 / numpy / pymodels surface; downstream Rust crates use
+  `default-features = false`. (#13)
+- **New regression model wrappers**:
+  - `Huber` — M-estimator robust to outliers; class + `huber()` expression. (#14)
+  - `LogisticRegression` — sklearn-style API with `predict_proba`,
+    `decision_function`, `score`, `penalty="l2"`, `C` kwarg. Distinct from
+    the existing `Logistic` wrapper. (#14)
+  - `PLS` — Partial Least Squares with `transform()` for the latent space;
+    class + `pls()` expression. (#19)
+- **Penalized IRLS `lambda_` kwarg** on the GLM PyClass models — `PyLogistic`,
+  `PyPoisson`, `PyNegativeBinomial`, `PyTweedie`, `PyProbit`, `PyCloglog`
+  (the expression layer already supported it). (#15)
+- **ALM expression parity with `PyALM`** — all 25 distributions reachable
+  from `ps.alm(...)`, plus `loss`, `link`, `role_trim`, and
+  `extra_parameter` kwargs. (#16)
+- **Summary / predict completeness** — added the matching expressions for
+  families that previously only had a base fit (#18):
+  - `quantile_summary`, `quantile_predict`
+  - `isotonic_predict`
+  - `lm_dynamic_predict`
+- **Diagnostics toolkit** (#17 + #27):
+  - Multicollinearity: `vif`, `generalized_vif`, `high_vif_predictors`
+  - OLS residual battery: `standardized_residuals`,
+    `studentized_residuals`, `externally_studentized_residuals`,
+    `residual_outliers`
+  - GLM residuals (logistic + Poisson): `*_pearson_residuals`,
+    `*_deviance_residuals`, `*_working_residuals` for each family
+  - Influence / leverage: `leverage`, `cooks_distance`, `dffits`,
+    `influential_cooks`, `influential_dffits`, `high_leverage_points`
+  - Goodness of fit: `pearson_chi_squared_logistic`,
+    `pearson_chi_squared_poisson`
+- **Documentation**:
+  - Sweep of the README and mkdocs site to cover every v0.5.0 addition.
+  - New "Use from Rust" section + `examples/rust_wls.rs` walking through
+    the rlib path.
+
+### Changed
+
+- Updated `anofox-regression` dependency to v0.5.4 (introduces
+  `HuberRegressor` and the sklearn-style `LogisticRegression`)
+- Updated `anofox-statistics` dependency to v0.4.1
+- Python `__version__` caught up from 0.3.0 → 0.5.0 (was lagging two
+  minor versions behind the wheel metadata)
+
+### Backwards compatibility
+
+Additive. `PyLogistic` is unchanged — the new sklearn-style
+`LogisticRegression` is a separate class. The `alm()` expression's input
+contract grew but all existing keyword-only callers continue to work
+because the new kwargs default to `None` / `"likelihood"`.
+
+## [0.4.0] - 2026-01-17
 
 ### Added
 
@@ -197,6 +256,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   - SIMD-optimized linear algebra via faer
   - Automatic parallelization for group operations
 
+[0.5.0]: https://github.com/DataZooDE/polars-statistics/compare/v0.4.0...v0.5.0
 [0.4.0]: https://github.com/DataZooDE/polars-statistics/compare/v0.3.0...v0.4.0
 [0.3.0]: https://github.com/DataZooDE/polars-statistics/compare/v0.2.0...v0.3.0
 [0.2.0]: https://github.com/DataZooDE/polars-statistics/compare/v0.1.0...v0.2.0

docs/API_REFERENCE.md

@@ -6,7 +6,7 @@
 > **Version:** 0.4.0
 > **Last Updated:** 2026-01-17
 
-Complete API reference for polars-statistics. For quick start examples, see the [README](../README.md).
+Complete API reference for polars-statistics. For quick start examples, see the [README](https://github.com/DataZooDE/polars-statistics#readme).
 
 ---
 
@@ -24,7 +24,6 @@ Complete API reference for polars-statistics. For quick start examples, see the
   - [TOST Equivalence Tests](#tost-equivalence-tests)
 - [Regression Models](#regression-models)
   - [Linear Models](#linear-models)
-  - [Robust Regression](#robust-regression)
   - [Diagnostics](#diagnostics)
   - [GLM Models](#glm-models)
   - [Augmented Linear Model (ALM)](#augmented-linear-model-alm)
@@ -1978,7 +1977,7 @@ Struct {
 
 ## See Also
 
-- [README](../README.md) - Quick start guide
+- [README](https://github.com/DataZooDE/polars-statistics#readme) - Quick start guide
 - [Polars Documentation](https://docs.pola.rs/)
 - [faer](https://github.com/sarah-ek/faer-rs) - Linear algebra backend
 

docs/api/README.md

@@ -68,5 +68,5 @@ result.with_columns(
 
 ## See Also
 
-- [README](../../README.md) - Quick start guide
+- [README](https://github.com/DataZooDE/polars-statistics#readme) - Quick start guide
 - [Polars Documentation](https://docs.pola.rs/)

docs/api/classes/glm.md

@@ -2,6 +2,8 @@
 
 Direct GLM model access outside of Polars expressions.
 
+All GLM classes (`Logistic`, `Poisson`, `NegativeBinomial`, `Tweedie`, `Probit`, `Cloglog`) accept a `lambda_=0.0` kwarg for L2 (ridge) penalty applied inside the IRLS update. The sklearn-style [`LogisticRegression`](#logisticregression) class exposes the same penalty via `C = 1 / lambda_` and an explicit `penalty` choice.
+
 ## Common Interface
 
 ```python
@@ -44,6 +46,39 @@ probabilities = model.predict_proba(X_new)  # Probability estimates
 
 ---
 
+## LogisticRegression
+
+Sklearn-style logistic regression. Distinct from [`Logistic`](#logistic): uses inverse-strength regularization `C = 1 / lambda_` and an explicit `penalty` choice.
+
+```python
+from polars_statistics import LogisticRegression
+
+model = LogisticRegression(
+    penalty: str = "l2",                # "l2" or "none"
+    C: float = 1.0,                     # Inverse of regularization strength
+    threshold: float = 0.5,
+    with_intercept: bool = True,
+    max_iter: int = 100,
+    tol: float = 1e-8,
+    compute_inference: bool = True,
+    confidence_level: float = 0.95,
+)
+model.fit(X, y)                         # y: binary (0/1)
+
+# Methods
+classes      = model.predict(X_new)             # 0/1 predictions
+probs        = model.predict_proba(X_new)       # Probability estimates
+scores       = model.decision_function(X_new)   # Linear scores (log-odds)
+accuracy     = model.score(X_new, y_new)        # Mean accuracy
+
+# Properties
+model.coefficients    # np.ndarray
+model.intercept       # float or None
+model.n_iter          # int — IRLS iterations until convergence
+```
+
+---
+
 ## Poisson
 
 Poisson regression for count data.
@@ -135,6 +170,7 @@ model.fit(X, y)  # y: binary (0/1)
 | Class | Parameters |
 |-------|------------|
 | `Logistic` | `lambda_`, `with_intercept` |
+| `LogisticRegression` | `penalty`, `C`, `threshold`, `with_intercept`, `max_iter`, `tol`, `compute_inference`, `confidence_level` |
 | `Poisson` | `lambda_`, `with_intercept` |
 | `NegativeBinomial` | `theta`, `estimate_theta`, `lambda_`, `with_intercept` |
 | `Tweedie` | `var_power`, `lambda_`, `with_intercept` |

docs/api/classes/linear.md

@@ -129,6 +129,67 @@ model.fit(X, y)
 
 ---
 
+## Huber
+
+Huber M-estimator (robust regression).
+
+```python
+from polars_statistics import Huber
+
+model = Huber(
+    epsilon: float = 1.35,
+    alpha: float = 0.0001,
+    with_intercept: bool = True,
+    max_iter: int = 100,
+    tol: float = 1e-5,
+)
+model.fit(X, y)
+
+# Properties
+model.coefficients      # np.ndarray
+model.intercept         # float or None
+model.scale             # float — robust scale estimate
+model.epsilon           # float
+model.outliers          # np.ndarray[bool] — down-weighted observations
+model.n_outliers        # int
+model.r_squared         # float
+model.mse               # float
+model.rmse              # float
+model.n_observations    # int
+```
+
+---
+
+## PLS
+
+Partial Least Squares regression.
+
+```python
+from polars_statistics import PLS
+
+model = PLS(
+    n_components: int = 2,
+    with_intercept: bool = True,
+    tol: float = 1e-6,
+    scale: bool = True,
+)
+model.fit(X, y)
+
+# Methods
+predictions = model.predict(X_new)
+latent      = model.transform(X_new)   # Project into latent space
+
+# Properties
+model.coefficients              # np.ndarray
+model.intercept                 # float or None
+model.n_components              # int
+model.explained_variance_ratio  # np.ndarray (one entry per component)
+model.r_squared                 # float
+model.n_observations            # int
+```
+
+---
+
 ## Quantile
 
 Quantile regression.
@@ -179,6 +240,8 @@ model.fitted_values    # np.ndarray
 | `WLS` | `with_intercept`, `compute_inference` |
 | `RLS` | `forgetting_factor`, `with_intercept` |
 | `BLS` | `lower_bound`, `upper_bound`, `with_intercept` |
+| `Huber` | `epsilon`, `alpha`, `with_intercept`, `max_iter`, `tol` |
+| `PLS` | `n_components`, `with_intercept`, `tol`, `scale` |
 | `Quantile` | `tau`, `with_intercept` |
 | `Isotonic` | `increasing` |
 

docs/api/outputs.md

@@ -88,6 +88,141 @@ Struct {
 
 ---
 
+## VIF Output
+
+Returned by `vif`.
+
+```
+Struct {
+    terms: List[String],          # "x1", "x2", ...
+    vif: List[Float64],
+    n_observations: UInt32,
+}
+```
+
+---
+
+## VIF Mask Output
+
+Returned by `high_vif_predictors`.
+
+```
+Struct {
+    is_high: List[Boolean],       # one per input feature column
+    n_high: UInt32,
+    n_features: UInt32,
+}
+```
+
+---
+
+## GVIF Output
+
+Returned by `generalized_vif`.
+
+```
+Struct {
+    gvif: List[Float64],          # one value per group
+    n_groups: UInt32,
+}
+```
+
+---
+
+## Leverage Output
+
+Returned by `leverage`.
+
+```
+Struct {
+    leverage: List[Float64],      # one h_ii per input row
+    n_observations: UInt32,
+}
+```
+
+---
+
+## Cook's Distance Output
+
+Returned by `cooks_distance`.
+
+```
+Struct {
+    cooks_d: List[Float64],       # one D_i per input row
+    n_observations: UInt32,
+}
+```
+
+---
+
+## DFFITS Output
+
+Returned by `dffits`.
+
+```
+Struct {
+    dffits: List[Float64],        # one value per input row
+    n_observations: UInt32,
+}
+```
+
+---
+
+## Influence Mask Output
+
+Returned by `influential_cooks`, `influential_dffits`, `high_leverage_points`.
+
+```
+Struct {
+    is_influential: List[Boolean],
+    n_influential: UInt32,
+    n_observations: UInt32,
+}
+```
+
+---
+
+## Residual Diagnostics Output
+
+Returned by `standardized_residuals`, `studentized_residuals`, `externally_studentized_residuals`, and all GLM residual functions (`logistic_*_residuals`, `poisson_*_residuals`).
+
+```
+Struct {
+    residuals: List[Float64],     # one residual per input row
+    n_observations: UInt32,
+}
+```
+
+---
+
+## Outlier Mask Output
+
+Returned by `residual_outliers`.
+
+```
+Struct {
+    is_outlier: List[Boolean],
+    n_outliers: UInt32,
+    n_observations: UInt32,
+}
+```
+
+---
+
+## Chi-Squared Output
+
+Returned by `pearson_chi_squared_logistic` and `pearson_chi_squared_poisson`.
+
+```
+Struct {
+    chi_squared: Float64,
+    df_resid: UInt32,
+    n_observations: UInt32,
+}
+```
+
+---
+
 ## GLM Output
 
 Returned by `logistic`, `poisson`, `negative_binomial`, `tweedie`, `probit`, `cloglog`.