LearningNeighbors

Nearest-neighbour models. Trainers in the scikit-learn Neighbors family, behind Learning's typed contract. Each requires a clean training set (``independent_target`` and no missing values) and stamps the model with the dataset's feature/class count. ``open LearningNeighbors`` brings the core types in scope too.
Imports
open LearningCore;
Table of Contents

Functions

knn_classifier

def knn_classifier (1 ds : Dataset | independent_target ds = true && has_missing ds = false) : {m : SklearnClassifier | clf_features m = ds_features ds && clf_classes m = ds_classes ds}

knn_classifier_k

``k`` must be positive and not exceed the number of training rows.
def knn_classifier_k (k : Int | k > 0) (1 ds : Dataset | ds_rows ds ≥ k && independent_target ds = true && has_missing ds = false) : {m : SklearnClassifier | clf_features m = ds_features ds && clf_classes m = ds_classes ds}

nearest_centroid

No predict_proba; one-hot fallback.
def nearest_centroid (1 ds : Dataset | independent_target ds = true && has_missing ds = false) : {m : SklearnClassifier | clf_features m = ds_features ds && clf_classes m = ds_classes ds}

radius_neighbors_classifier

def radius_neighbors_classifier (1 ds : Dataset | independent_target ds = true && has_missing ds = false) : {m : SklearnClassifier | clf_features m = ds_features ds && clf_classes m = ds_classes ds}

knn_regressor

def knn_regressor (1 ds : Dataset | independent_target ds = true && has_missing ds = false) : {m : SklearnRegressor | reg_features m = ds_features ds}

radius_neighbors_regressor

def radius_neighbors_regressor (1 ds : Dataset | independent_target ds = true && has_missing ds = false) : {m : SklearnRegressor | reg_features m = ds_features ds}