* Fix cubic spline when x isn't sorted

* Format

…lixir-nx#222)

* Add other non-encoding preprocessing utilities as separate modules

* Delete test/scholar/preprocessing/normalizer_test.exs

* Delete lib/scholar/preprocessing/normalizer.ex

* Format

* Remove redundant module attribute

* Introduce encoders in separate modules

* Update preprocessing.ex

* Add module docs

* Add Normalizer

* Change preprocessing.ex

* Update moduledoc

* Add draft of NNDescent

* Working version

* Apply improvements

* Format

* Add documentation, unify variables, etc

* Format

* Remove redundant comma

* Remove unused comment

* Apply suggestions from feedback

* Pass key as an argument

* Update paper in documentation

* Add quering

* Improve doctest

* Make num_neighbors more functional

* Add Trimap

* Update lib/scholar/manifold/trimap.ex

Co-authored-by: José Valim <[email protected]>

* Add docs and tests

* Apply improvements

* Resolve after merge

* increase temporarily size of stack

---------

Co-authored-by: José Valim <[email protected]>

* Add priority queue

* Apply changes to NNDescent

* Apply Suggestions form code review

* Format

* Remove redundant space

* Raise when tree_init and non-euclidean metric

* Update lib/scholar/neighbors/nn_descent.ex

Co-authored-by: Krsto Proroković <[email protected]>

* Update lib/scholar/neighbors/nn_descent.ex

Co-authored-by: José Valim <[email protected]>

* Decrease tolerance

* Ensure that all initial nearest neighbors are initialized and fix tests according to the implemented changes

---------

Co-authored-by: Krsto Proroković <[email protected]>
Co-authored-by: José Valim <[email protected]>

* update multinomial naive bayes

* remove Nx.Type.merge/2

---------

Co-authored-by: Krsto Proroković <[email protected]>

* Added ndcg metric

* Update lib/scholar/metrics/ranking.ex

Co-authored-by: José Valim <[email protected]>

* Update lib/scholar/metrics/ranking.ex

Co-authored-by: José Valim <[email protected]>

* Update lib/scholar/metrics/ranking.ex

Co-authored-by: Krsto Proroković <[email protected]>

* Update lib/scholar/metrics/ranking.ex

Co-authored-by: Mateusz Sluszniak <[email protected]>

* Update lib/scholar/metrics/ranking.ex

---------

Co-authored-by: José Valim <[email protected]>
Co-authored-by: Krsto Proroković <[email protected]>
Co-authored-by: Mateusz Sluszniak <[email protected]>

* add BruteKNN

* update docs and tests

* mix format

* move get_batches inside BruteKNN

* raise error when k > n

---------

Co-authored-by: Krsto Proroković <[email protected]>

* Add livebook

* Update notebooks/nearest_neighbors.livemd

Co-authored-by: José Valim <[email protected]>

* Update notebooks/nearest_neighbors.livemd

Co-authored-by: José Valim <[email protected]>

* Update notebooks/nearest_neighbors.livemd

Co-authored-by: José Valim <[email protected]>

* Apply suggestions from code review

Co-authored-by: Krsto Proroković <[email protected]>

* Apply changes from code review

---------

Co-authored-by: José Valim <[email protected]>
Co-authored-by: Krsto Proroković <[email protected]>

* Output distances in kdtree

* Add checks on data in predict

* Major update, submitting a PR

* Update doc

* Update doc

* Add distance to KDTree.predict/2

* Update doc

* Update doc

* Add metric to RandomProjectionForest and LargeVis, more unit-tests, etc

* Add predict_proba/2

* Rename predict_proba to predict_probability, fix a bug inside of it

* Remove Nx.Type.merge in predict_probability

Co-authored-by: José Valim <[email protected]>

---------

Co-authored-by: Krsto Proroković <[email protected]>
Co-authored-by: José Valim <[email protected]>

Closes elixir-nx#265.

* Add k-NN regressor.

* Remove k_nearest_neighbors

* Resolve conflicts.

* y must be of rank 2

---------

Co-authored-by: Krsto Proroković <[email protected]>

…lixir-nx#267)

…elixir-nx#270)

Just a minor fix in the changelog.

* Added d2_absolute_error_score and d2_pinball_score

* Updateted multioutput desc

* run mix format

* run mix format

* Update lib/scholar/metrics/regression.ex

Co-authored-by: Mateusz Sluszniak <[email protected]>

* Removed repeating code

---------

Co-authored-by: Mateusz Sluszniak <[email protected]>

* Make nn algorithm configurable

* Update lib/scholar/manifold/trimap.ex

Co-authored-by: José Valim <[email protected]>

* Make tests passing

* Add :auto option for knn_algo auto detection

---------

Co-authored-by: José Valim <[email protected]>

* Add manifold learning algorithm notebook and corrections to trimap

* Persistent outputs

* Remove tests with unsupported metrics

* Apply suggestions from code review

Co-authored-by: Krsto Proroković <[email protected]>

* Apply suggestions from code review

* Format

* Change tests to well define states

* Update notebooks/manifold_learning.livemd

---------

Co-authored-by: Krsto Proroković <[email protected]>

Changed Trimap to t-SNE next to the plot of t-SNE embeddings.

* Add partial_fit/2 and incremental_fit/2 to Scholar.Decomposition.PCA

* Update fit_transform/2 docstring.

* mix.lock

* Fix incremental_fit/2 docstring

---------

Co-authored-by: Krsto Proroković <[email protected]>

* user dot/4 on set_intercept

* use dot/4 on linear regression predict

* add column target tests

* better name for test

* working on svm

* svm supports multioutput

* check col and regular models are the same. invalid y raises

* move y shape validation to linear_helper function

* add linear helper function for shape validation

* formatter

* clean up test

* modify validate_y_shape for isotonic regression

* add y shape validation and test to isotonic regression

* formatter

* decouple validation from flattening helper to handle multioutput options

* flatten linear input. no longer matches sklearn

* add prediction test

* linear regression always returns {n_samples} vector

* formatter

* bayesian ridge fixed

* remove wip tags

* removing wip tags

* refactor test data

* wrote polynomial regression test

* wrote tests for logistic and ridge regression

* logistic and ridge test pass

* Update lib/scholar/linear/linear_helpers.ex

Co-authored-by: José Valim <[email protected]>

* Update lib/scholar/linear/linear_helpers.ex

Co-authored-by: José Valim <[email protected]>

* fixed valid_colum_vector? name

* fixed error messages

* updated docs

* proper formatting of predict docs

* ran formatter

---------

Co-authored-by: José Valim <[email protected]>

…gression (elixir-nx#293)

* Update

* mix format

* Remove Scholar.Preprocessing import from Scholar.Metrics.Classification

* mix format

* emove commented out code from NaiveBayes.Complement

* update docstrings

---------

Co-authored-by: Krsto Proroković <[email protected]>

Co-authored-by: Krsto Proroković <[email protected]>

…or (elixir-nx#296)