Merge branch 'master' into UpdateDocAndVersion

* Add complete classes counts to node and tests

* Implement optimized predict and new predict_proba

* Add predict_proba test

* Add python 3.10 to CI

.coveragerc

@@ -0,0 +1,13 @@
+[run]
+branch = True
+source = stree
+
+[report]
+exclude_lines =
+    if self.debug:
+    pragma: no cover
+    raise NotImplementedError
+    if __name__ == .__main__.:
+ignore_errors = True
+omit =
+    stree/__init__.py

.github/workflows/codeql-analysis.yml

@@ -0,0 +1,56 @@
+name: "CodeQL"
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    # The branches below must be a subset of the branches above
+    branches: [ master ]
+  schedule:
+    - cron: '16 17 * * 3'
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-latest
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: [ 'python' ]
+        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python' ]
+        # Learn more:
+        # https://docs.github.com/en/free-pro-team@latest/github/finding-security-vulnerabilities-and-errors-in-your-code/configuring-code-scanning#changing-the-languages-that-are-analyzed
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v1
+      with:
+        languages: ${{ matrix.language }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+        # queries: ./path/to/local/query, your-org/your-repo/queries@main
+
+    # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
+    # If this step fails, then you should remove it and run the build manually (see below)
+    - name: Autobuild
+      uses: github/codeql-action/autobuild@v1
+
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 https://git.io/JvXDl
+
+    # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
+    #    and modify them (or add more) to build your code if your project
+    #    uses a compiled language
+
+    #- run: |
+    #   make bootstrap
+    #   make release
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v1

.github/workflows/main.yml

@@ -0,0 +1,47 @@
+name: CI
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches: [master]
+  workflow_dispatch:
+
+jobs:
+  build:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [macos-latest, ubuntu-latest, windows-latest]
+        python: [3.8, "3.10"]
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python ${{ matrix.python }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python }}
+      - name: Install dependencies
+        run: |
+          pip install -q --upgrade pip
+          pip install -q -r requirements.txt
+          pip install -q --upgrade codecov coverage black flake8 codacy-coverage
+      - name: Lint
+        run: |
+          black --check --diff stree
+          flake8 --count stree
+      - name: Tests
+        run: |
+          coverage run -m unittest -v stree.tests
+          coverage xml
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v1
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
+          files: ./coverage.xml
+      - name: Run codacy-coverage-reporter
+        if: runner.os == 'Linux'
+        uses: codacy/codacy-coverage-reporter-action@master
+        with:
+          project-token: ${{ secrets.CODACY_PROJECT_TOKEN }}
+          coverage-reports: coverage.xml

.gitignore

@@ -129,4 +129,8 @@ dmypy.json
 .pyre/
 
 .idea
-.vscode
+.vscode
+.pre-commit-config.yaml
+
+**.csv
+.virtual_documents

.travis.yml

@@ -1,13 +0,0 @@
-language: python
-os: linux
-dist: xenial
-install:
-  - pip install -r requirements.txt
-notifications:
-  email:
-    recipients:
-      - ricardo.montanana@alu.uclm.es
-    on_success: never # default: change
-    on_failure: always # default: always
-# command to run tests
-script: python -m unittest stree.tests

CITATION.cff

@@ -0,0 +1,37 @@
+cff-version: 1.2.0
+message: "If you use this software, please cite it as below."
+authors:
+  - family-names: "Montañana"
+    given-names: "Ricardo"
+    orcid: "https://orcid.org/0000-0003-3242-5452"
+  - family-names: "Gámez"
+    given-names: "José A."
+    orcid: "https://orcid.org/0000-0003-1188-1117"
+  - family-names: "Puerta"
+    given-names: "José M."
+    orcid: "https://orcid.org/0000-0002-9164-5191"
+title: "STree"
+version: 1.2.3
+doi: 10.5281/zenodo.5504083
+date-released: 2021-11-02
+url: "https://github.com/Doctorado-ML/STree"
+preferred-citation:
+  type: article
+  authors:
+    - family-names: "Montañana"
+      given-names: "Ricardo"
+      orcid: "https://orcid.org/0000-0003-3242-5452"
+    - family-names: "Gámez"
+      given-names: "José A."
+      orcid: "https://orcid.org/0000-0003-1188-1117"
+    - family-names: "Puerta"
+      given-names: "José M."
+      orcid: "https://orcid.org/0000-0002-9164-5191"
+  doi: "10.1007/978-3-030-85713-4_6"
+  journal: "Lecture Notes in Computer Science"
+  month: 9
+  start: 54
+  end: 64
+  title: "STree: A Single Multi-class Oblique Decision Tree Based on Support Vector Machines"
+  volume: 12882
+  year: 2021

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2020 Doctorado-ML
+Copyright (c) 2020-2021, Ricardo Montañana Gómez
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

Makefile

@@ -0,0 +1,56 @@
+SHELL := /bin/bash
+.DEFAULT_GOAL := help
+.PHONY: coverage deps help lint push test doc build
+
+coverage:  ## Run tests with coverage
+	coverage erase
+	coverage run -m unittest -v stree.tests
+	coverage report -m
+
+deps:  ## Install dependencies
+	pip install -r requirements.txt
+
+devdeps:  ## Install development dependencies
+	pip install black pip-audit flake8 mypy coverage
+
+lint:  ## Lint and static-check
+	black stree
+	flake8 stree
+	mypy stree
+
+push:  ## Push code with tags
+	git push && git push --tags
+
+test:  ## Run tests
+	python -m unittest -v stree.tests
+
+doc:  ## Update documentation
+	make -C docs --makefile=Makefile html
+
+build:  ## Build package
+	rm -fr dist/*
+	rm -fr build/*
+	python setup.py sdist bdist_wheel
+
+doc-clean:  ## Update documentation
+	make -C docs --makefile=Makefile clean
+
+audit: ## Audit pip
+	pip-audit
+
+help: ## Show help message
+	@IFS=$$'\n' ; \
+	help_lines=(`fgrep -h "##" $(MAKEFILE_LIST) | fgrep -v fgrep | sed -e 's/\\$$//' | sed -e 's/##/:/'`); \
+	printf "%s\n\n" "Usage: make [task]"; \
+	printf "%-20s %s\n" "task" "help" ; \
+	printf "%-20s %s\n" "------" "----" ; \
+	for help_line in $${help_lines[@]}; do \
+		IFS=$$':' ; \
+		help_split=($$help_line) ; \
+		help_command=`echo $${help_split[0]} | sed -e 's/^ *//' -e 's/ *$$//'` ; \
+		help_info=`echo $${help_split[2]} | sed -e 's/^ *//' -e 's/ *$$//'` ; \
+		printf '\033[36m'; \
+		printf "%-20s %s" $$help_command ; \
+		printf '\033[0m'; \
+		printf "%s\n" $$help_info; \
+	done

README.md

@@ -1,8 +1,14 @@
-[![Build Status](https://travis-ci.com/Doctorado-ML/STree.svg?branch=master)](https://travis-ci.com/Doctorado-ML/STree)
+![CI](https://github.com/Doctorado-ML/STree/workflows/CI/badge.svg)
+[![codecov](https://codecov.io/gh/doctorado-ml/stree/branch/master/graph/badge.svg)](https://codecov.io/gh/doctorado-ml/stree)
+[![Codacy Badge](https://app.codacy.com/project/badge/Grade/35fa3dfd53a24a339344b33d9f9f2f3d)](https://www.codacy.com/gh/Doctorado-ML/STree?utm_source=github.com&utm_medium=referral&utm_content=Doctorado-ML/STree&utm_campaign=Badge_Grade)
+[![Language grade: Python](https://img.shields.io/lgtm/grade/python/g/Doctorado-ML/STree.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/Doctorado-ML/STree/context:python)
+[![PyPI version](https://badge.fury.io/py/STree.svg)](https://badge.fury.io/py/STree)
+![https://img.shields.io/badge/python-3.8%2B-blue](https://img.shields.io/badge/python-3.8%2B-brightgreen)
+[![DOI](https://zenodo.org/badge/262658230.svg)](https://zenodo.org/badge/latestdoi/262658230)
 
-# Stree
+# STree
 
-Oblique Tree classifier based on SVM nodes
+Oblique Tree classifier based on SVM nodes. The nodes are built and splitted with sklearn SVC models. Stree is a sklearn estimator and can be integrated in pipelines, grid searches, etc.
 
 ![Stree](https://raw.github.com/doctorado-ml/stree/master/example.png)
 
@@ -12,30 +18,63 @@ Oblique Tree classifier based on SVM nodes
 pip install git+https://github.com/doctorado-ml/stree
 ```
 
+## Documentation
+
+Can be found in [stree.readthedocs.io](https://stree.readthedocs.io/en/stable/)
+
 ## Examples
 
 ### Jupyter notebooks
 
-##### Slow launch but better integration
+- [![benchmark](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/benchmark.ipynb) Benchmark
 
-* [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/Doctorado-ML/STree/master?urlpath=lab/tree/test.ipynb) Test notebook
+- [![features](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/features.ipynb) Some features
 
-##### Fast launch but have to run first commented out cell for setup
+- [![Gridsearch](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/gridsearch.ipynb) Gridsearch
 
-* [![Test](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/test.ipynb) Test notebook
+- [![Ensemble](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/ensemble.ipynb) Ensembles
 
-* [![Test2](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/test2.ipynb) Another Test notebook
+## Hyperparameters
 
-* [![Test Graphics](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/test_graphs.ipynb) Test Graphics notebook
+|     | **Hyperparameter**  | **Type/Values**                                                | **Default** | **Meaning**                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
+| --- | ------------------- | -------------------------------------------------------------- | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| \*  | C                   | \<float\>                                                      | 1.0         | Regularization parameter. The strength of the regularization is inversely proportional to C. Must be strictly positive.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+| \*  | kernel              | {"liblinear", "linear", "poly", "rbf", "sigmoid"}              | linear      | Specifies the kernel type to be used in the algorithm. It must be one of ‘liblinear’, ‘linear’, ‘poly’ or ‘rbf’. liblinear uses [liblinear](https://www.csie.ntu.edu.tw/~cjlin/liblinear/) library and the rest uses [libsvm](https://www.csie.ntu.edu.tw/~cjlin/libsvm/) library through scikit-learn library                                                                                                                                                                                                                                                                                                                          |
+| \*  | max_iter            | \<int\>                                                        | 1e5         | Hard limit on iterations within solver, or -1 for no limit.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
+| \*  | random_state        | \<int\>                                                        | None        | Controls the pseudo random number generation for shuffling the data for probability estimates. Ignored when probability is False.<br>Pass an int for reproducible output across multiple function calls                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+|     | max_depth           | \<int\>                                                        | None        | Specifies the maximum depth of the tree                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+| \*  | tol                 | \<float\>                                                      | 1e-4        | Tolerance for stopping criterion.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
+| \*  | degree              | \<int\>                                                        | 3           | Degree of the polynomial kernel function (‘poly’). Ignored by all other kernels.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| \*  | gamma               | {"scale", "auto"} or \<float\>                                 | scale       | Kernel coefficient for ‘rbf’, ‘poly’ and ‘sigmoid’.<br>if gamma='scale' (default) is passed then it uses 1 / (n_features \* X.var()) as value of gamma,<br>if ‘auto’, uses 1 / n_features.                                                                                                                                                                                                                                                                                                                                                                                                                                              |
+|     | split_criteria      | {"impurity", "max_samples"}                                    | impurity    | Decides (just in case of a multi class classification) which column (class) use to split the dataset in a node\*\*. max_samples is incompatible with 'ovo' multiclass_strategy                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+|     | criterion           | {“gini”, “entropy”}                                            | entropy     | The function to measure the quality of a split (only used if max_features != num_features). <br>Supported criteria are “gini” for the Gini impurity and “entropy” for the information gain.                                                                                                                                                                                                                                                                                                                                                                                                                                             |
+|     | min_samples_split   | \<int\>                                                        | 0           | The minimum number of samples required to split an internal node. 0 (default) for any                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
+|     | max_features        | \<int\>, \<float\> <br><br>or {“auto”, “sqrt”, “log2”}         | None        | The number of features to consider when looking for the split:<br>If int, then consider max_features features at each split.<br>If float, then max_features is a fraction and int(max_features \* n_features) features are considered at each split.<br>If “auto”, then max_features=sqrt(n_features).<br>If “sqrt”, then max_features=sqrt(n_features).<br>If “log2”, then max_features=log2(n_features).<br>If None, then max_features=n_features.                                                                                                                                                                                    |
+|     | splitter            | {"best", "random", "trandom", "mutual", "cfs", "fcbf", "iwss"} | "random"    | The strategy used to choose the feature set at each node (only used if max_features < num_features).
+Supported strategies are: **“best”**: sklearn SelectKBest algorithm is used in every node to choose the max_features best features. **“random”**: The algorithm generates 5 candidates and choose the best (max. info. gain) of them. **“trandom”**: The algorithm generates only one random combination. **"mutual"**: Chooses the best features w.r.t. their mutual info with the label. **"cfs"**: Apply Correlation-based Feature Selection. **"fcbf"**: Apply Fast Correlation-Based Filter. **"iwss"**: IWSS based algorithm |
+|     | normalize           | \<bool\>                                                       | False       | If standardization of features should be applied on each node with the samples that reach it                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
+| \*  | multiclass_strategy | {"ovo", "ovr"}                                                 | "ovo"       | Strategy to use with multiclass datasets, **"ovo"**: one versus one. **"ovr"**: one versus rest                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
 
-### Command line
+\* Hyperparameter used by the support vector classifier of every node
 
-```bash
-python main.py
-```
+\*\* **Splitting in a STree node**
+
+The decision function is applied to the dataset and distances from samples to hyperplanes are computed in a matrix. This matrix has as many columns as classes the samples belongs to (if more than two, i.e. multiclass classification) or 1 column if it's a binary class dataset. In binary classification only one hyperplane is computed and therefore only one column is needed to store the distances of the samples to it. If three or more classes are present in the dataset we need as many hyperplanes as classes are there, and therefore one column per hyperplane is needed.
+
+In case of multiclass classification we have to decide which column take into account to make the split, that depends on hyperparameter _split_criteria_, if "impurity" is chosen then STree computes information gain of every split candidate using each column and chooses the one that maximize the information gain, otherwise STree choses the column with more samples with a predicted class (the column with more positive numbers in it).
+
+Once we have the column to take into account for the split, the algorithm splits samples with positive distances to hyperplane from the rest.
 
 ## Tests
 
 ```bash
 python -m unittest -v stree.tests
 ```
+
+## License
+
+STree is [MIT](https://github.com/doctorado-ml/stree/blob/master/LICENSE) licensed
+
+## Reference
+
+R. Montañana, J. A. Gámez, J. M. Puerta, "STree: a single multi-class oblique decision tree based on support vector machines.", 2021 LNAI 12882, pg. 54-64

codecov.yml

@@ -0,0 +1,12 @@
+coverage:
+  status:
+    project:
+      default:
+        target: 100%
+comment:
+  layout: "reach, diff, flags, files"
+  behavior: default
+  require_changes: false
+  require_base: yes
+  require_head: yes
+  branches: null

data/.gitignore

@@ -1 +0,0 @@
-*

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = source
+BUILDDIR      = build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/requirements.txt

@@ -0,0 +1,4 @@
+sphinx
+sphinx-rtd-theme
+myst-parser
+mufs

docs/source/api/Siterator.rst

@@ -0,0 +1,9 @@
+Siterator
+=========
+
+.. automodule:: Splitter
+.. autoclass:: Siterator
+    :members:
+    :undoc-members:
+    :private-members:
+    :show-inheritance:

docs/source/api/Snode.rst

@@ -0,0 +1,9 @@
+Snode
+=====
+
+.. automodule:: Splitter
+.. autoclass:: Snode
+    :members:
+    :undoc-members:
+    :private-members:
+    :show-inheritance:

docs/source/api/Splitter.rst

@@ -0,0 +1,9 @@
+Splitter
+========
+
+.. automodule:: Splitter
+.. autoclass:: Splitter
+    :members:
+    :undoc-members:
+    :private-members:
+    :show-inheritance:

docs/source/api/Stree.rst

@@ -0,0 +1,9 @@
+Stree
+=====
+
+.. automodule:: stree
+.. autoclass:: Stree
+    :members:
+    :undoc-members:
+    :private-members:
+    :show-inheritance:

docs/source/api/index.rst

@@ -0,0 +1,11 @@
+API index
+=========
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Contents:
+
+   Stree
+   Siterator
+   Snode
+   Splitter

docs/source/conf.py

@@ -0,0 +1,56 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# This file only contains a selection of the most common options. For a full
+# list see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Path setup --------------------------------------------------------------
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+import os
+import sys
+from stree._version import __version__
+
+sys.path.insert(0, os.path.abspath("../../stree/"))
+
+# -- Project information -----------------------------------------------------
+
+project = "STree"
+copyright = "2020 - 2022, Ricardo Montañana Gómez"
+author = "Ricardo Montañana Gómez"
+
+# The full version, including alpha/beta/rc tags
+version = __version__
+release = version
+
+
+# -- General configuration ---------------------------------------------------
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = ["myst_parser", "sphinx.ext.autodoc", "sphinx.ext.viewcode"]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ["_templates"]
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path.
+exclude_patterns = []
+
+
+# -- Options for HTML output -------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = "sphinx_rtd_theme"
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = []

docs/source/example.md

@@ -0,0 +1,42 @@
+# Examples
+
+## Notebooks
+
+- [![benchmark](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/benchmark.ipynb) Benchmark
+
+- [![features](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/features.ipynb) Some features
+
+- [![Gridsearch](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/gridsearch.ipynb) Gridsearch
+
+- [![Ensemble](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/ensemble.ipynb) Ensembles
+
+## Sample Code
+
+```python
+import time
+from sklearn.model_selection import train_test_split
+from sklearn.datasets import load_iris
+from stree import Stree
+
+random_state = 1
+X, y = load_iris(return_X_y=True)
+Xtrain, Xtest, ytrain, ytest = train_test_split(
+    X, y, test_size=0.2, random_state=random_state
+)
+now = time.time()
+print("Predicting with max_features=sqrt(n_features)")
+clf = Stree(random_state=random_state, max_features="auto")
+clf.fit(Xtrain, ytrain)
+print(f"Took {time.time() - now:.2f} seconds to train")
+print(clf)
+print(f"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}")
+print(f"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}")
+print("=" * 40)
+print("Predicting with max_features=n_features")
+clf = Stree(random_state=random_state)
+clf.fit(Xtrain, ytrain)
+print(f"Took {time.time() - now:.2f} seconds to train")
+print(clf)
+print(f"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}")
+print(f"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}")
+```

docs/source/hyperparameters.md

@@ -0,0 +1,29 @@
+# Hyperparameters
+
+|     | **Hyperparameter**  | **Type/Values**                                                | **Default** | **Meaning**                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
+| --- | ------------------- | -------------------------------------------------------------- | ----------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| \*  | C                   | \<float\>                                                      | 1.0         | Regularization parameter. The strength of the regularization is inversely proportional to C. Must be strictly positive.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+| \*  | kernel              | {"liblinear", "linear", "poly", "rbf", "sigmoid"}              | linear      | Specifies the kernel type to be used in the algorithm. It must be one of ‘liblinear’, ‘linear’, ‘poly’ or ‘rbf’.<br>liblinear uses [liblinear](https://www.csie.ntu.edu.tw/~cjlin/liblinear/) library and the rest uses [libsvm](https://www.csie.ntu.edu.tw/~cjlin/libsvm/) library through scikit-learn library                                                                                                                                                                                                                                                                                                                          |
+| \*  | max_iter            | \<int\>                                                        | 1e5         | Hard limit on iterations within solver, or -1 for no limit.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
+| \*  | random_state        | \<int\>                                                        | None        | Controls the pseudo random number generation for shuffling the data for probability estimates. Ignored when probability is False.<br>Pass an int for reproducible output across multiple function calls                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+|     | max_depth           | \<int\>                                                        | None        | Specifies the maximum depth of the tree                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+| \*  | tol                 | \<float\>                                                      | 1e-4        | Tolerance for stopping criterion.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
+| \*  | degree              | \<int\>                                                        | 3           | Degree of the polynomial kernel function (‘poly’). Ignored by all other kernels.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| \*  | gamma               | {"scale", "auto"} or \<float\>                                 | scale       | Kernel coefficient for ‘rbf’, ‘poly’ and ‘sigmoid’.<br>if gamma='scale' (default) is passed then it uses 1 / (n_features \* X.var()) as value of gamma,<br>if ‘auto’, uses 1 / n_features.                                                                                                                                                                                                                                                                                                                                                                                                                                              |
+|     | split_criteria      | {"impurity", "max_samples"}                                    | impurity    | Decides (just in case of a multi class classification) which column (class) use to split the dataset in a node\*\*.<br>max_samples is incompatible with 'ovo' multiclass_strategy                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+|     | criterion           | {“gini”, “entropy”}                                            | entropy     | The function to measure the quality of a split (only used if max_features != num_features).<br>Supported criteria are “gini” for the Gini impurity and “entropy” for the information gain.                                                                                                                                                                                                                                                                                                                                                                                                                                             |
+|     | min_samples_split   | \<int\>                                                        | 0           | The minimum number of samples required to split an internal node. 0 (default) for any                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
+|     | max_features        | \<int\>, \<float\> <br><br>or {“auto”, “sqrt”, “log2”}         | None        | The number of features to consider when looking for the split:<br>If int, then consider max_features features at each split.<br>If float, then max_features is a fraction and int(max_features \* n_features) features are considered at each split.<br>If “auto”, then max_features=sqrt(n_features).<br>If “sqrt”, then max_features=sqrt(n_features).<br>If “log2”, then max_features=log2(n_features).<br>If None, then max_features=n_features.                                                                                                                                                                                    |
+|     | splitter            | {"best", "random", "trandom", "mutual", "cfs", "fcbf", "iwss"} | "random"    | The strategy used to choose the feature set at each node (only used if max_features < num_features).<br>Supported strategies are:<br>**“best”**: sklearn SelectKBest algorithm is used in every node to choose the max_features best features.<br>**“random”**: The algorithm generates 5 candidates and choose the best (max. info. gain) of them.<br>**“trandom”**: The algorithm generates only one random combination.<br>**"mutual"**: Chooses the best features w.r.t. their mutual info with the label.<br>**"cfs"**: Apply Correlation-based Feature Selection.<br>**"fcbf"**: Apply Fast Correlation-Based Filter.<br>**"iwss"**: IWSS based algorithm |
+|     | normalize           | \<bool\>                                                       | False       | If standardization of features should be applied on each node with the samples that reach it                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
+| \*  | multiclass_strategy | {"ovo", "ovr"}                                                 | "ovo"       | Strategy to use with multiclass datasets:<br>**"ovo"**: one versus one.<br>**"ovr"**: one versus rest                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+
+\* Hyperparameter used by the support vector classifier of every node
+
+\*\* **Splitting in a STree node**
+
+The decision function is applied to the dataset and distances from samples to hyperplanes are computed in a matrix. This matrix has as many columns as classes the samples belongs to (if more than two, i.e. multiclass classification) or 1 column if it's a binary class dataset. In binary classification only one hyperplane is computed and therefore only one column is needed to store the distances of the samples to it. If three or more classes are present in the dataset we need as many hyperplanes as classes are there, and therefore one column per hyperplane is needed.
+
+In case of multiclass classification we have to decide which column take into account to make the split, that depends on hyperparameter _split_criteria_, if "impurity" is chosen then STree computes information gain of every split candidate using each column and chooses the one that maximize the information gain, otherwise STree choses the column with more samples with a predicted class (the column with more positive numbers in it).
+
+Once we have the column to take into account for the split, the algorithm splits samples with positive distances to hyperplane from the rest.

docs/source/index.rst

@@ -0,0 +1,15 @@
+Welcome to STree's documentation!
+=================================
+
+.. toctree::
+   :caption: Contents:
+   :titlesonly:
+
+
+   stree
+   install
+   hyperparameters
+   example
+   api/index
+
+* :ref:`genindex`

docs/source/install.rst

@@ -0,0 +1,16 @@
+Install
+=======
+
+The main stable release
+
+``pip install stree``
+
+or the last development branch
+
+``pip install git+https://github.com/doctorado-ml/stree``
+
+Tests
+*****
+
+
+``python -m unittest -v stree.tests``

docs/source/stree.md

@@ -0,0 +1,17 @@
+# STree
+
+![CI](https://github.com/Doctorado-ML/STree/workflows/CI/badge.svg)
+[![codecov](https://codecov.io/gh/doctorado-ml/stree/branch/master/graph/badge.svg)](https://codecov.io/gh/doctorado-ml/stree)
+[![Codacy Badge](https://app.codacy.com/project/badge/Grade/35fa3dfd53a24a339344b33d9f9f2f3d)](https://www.codacy.com/gh/Doctorado-ML/STree?utm_source=github.com&utm_medium=referral&utm_content=Doctorado-ML/STree&utm_campaign=Badge_Grade)
+[![Language grade: Python](https://img.shields.io/lgtm/grade/python/g/Doctorado-ML/STree.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/Doctorado-ML/STree/context:python)
+[![PyPI version](https://badge.fury.io/py/STree.svg)](https://badge.fury.io/py/STree)
+![https://img.shields.io/badge/python-3.8%2B-blue](https://img.shields.io/badge/python-3.8%2B-brightgreen)
+[![DOI](https://zenodo.org/badge/262658230.svg)](https://zenodo.org/badge/latestdoi/262658230)
+
+Oblique Tree classifier based on SVM nodes. The nodes are built and splitted with sklearn SVC models. Stree is a sklearn estimator and can be integrated in pipelines, grid searches, etc.
+
+![Stree](./example.png)
+
+## License
+
+STree is [MIT](https://github.com/doctorado-ml/stree/blob/master/LICENSE) licensed

main.py

@@ -1,57 +0,0 @@
-import time
-from sklearn.model_selection import train_test_split
-from stree import Stree
-
-random_state=1
-
-def load_creditcard(n_examples=0):
-    import pandas as pd
-    import numpy as np
-    import random
-    df = pd.read_csv('data/creditcard.csv')
-    print("Fraud: {0:.3f}% {1}".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))
-    print("Valid: {0:.3f}% {1}".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))
-    y = np.expand_dims(df.Class.values, axis=1)
-    X = df.drop(['Class', 'Time', 'Amount'], axis=1).values
-    if n_examples > 0:
-        # Take first n_examples samples
-        X = X[:n_examples, :]
-        y = y[:n_examples, :]
-    else:
-        # Take all the positive samples with a number of random negatives
-        if n_examples < 0:
-            Xt = X[(y == 1).ravel()]
-            yt = y[(y == 1).ravel()]
-            indices = random.sample(range(X.shape[0]), -1 * n_examples)
-            X = np.append(Xt, X[indices], axis=0)
-            y = np.append(yt, y[indices], axis=0)
-    print("X.shape", X.shape, " y.shape", y.shape)
-    print("Fraud: {0:.3f}% {1}".format(len(y[y == 1])*100/X.shape[0], len(y[y == 1])))
-    print("Valid: {0:.3f}% {1}".format(len(y[y == 0]) * 100 / X.shape[0], len(y[y == 0])))
-    Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state, stratify=y)
-    return Xtrain, Xtest, ytrain, ytest
-
-# data = load_creditcard(-5000) # Take all true samples + 5000 of the others
-# data = load_creditcard(5000)  # Take the first 5000 samples
-data = load_creditcard() # Take all the samples
-
-Xtrain = data[0]
-Xtest = data[1]
-ytrain = data[2]
-ytest = data[3]
-
-now = time.time()
-clf = Stree(C=.01, random_state=random_state)
-clf.fit(Xtrain, ytrain)
-print(f"Took {time.time() - now:.2f} seconds to train")
-print(clf)
-print(f"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}")
-print(f"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}")
-proba = clf.predict_proba(Xtest)
-print("Checking that we have correct probabilities, these are probabilities of sample belonging to class 1")
-res0 = proba[proba[:, 0] == 0]
-res1 = proba[proba[:, 0] == 1]
-print("++++++++++res0 > .8++++++++++++")
-print(res0[res0[:, 1] > .8])
-print("**********res1 < .4************")
-print(res1[res1[:, 1] < .4])

notebooks/benchmark.ipynb

@@ -0,0 +1,371 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Compare STree with different estimators"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Setup\n",
+    "Uncomment the next cell if STree is not already installed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#\n",
+    "# Google Colab setup\n",
+    "#\n",
+    "#!pip install git+https://github.com/doctorado-ml/stree\n",
+    "!pip install pandas"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import datetime, time\n",
+    "import os\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.metrics import classification_report, confusion_matrix, f1_score\n",
+    "from sklearn.tree import DecisionTreeClassifier\n",
+    "from sklearn.naive_bayes import GaussianNB\n",
+    "from sklearn.neural_network import MLPClassifier\n",
+    "from sklearn.svm import LinearSVC\n",
+    "from stree import Stree"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if not os.path.isfile('data/creditcard.csv'):\n",
+    "    !wget --no-check-certificate --content-disposition http://nube.jccm.es/index.php/s/Zs7SYtZQJ3RQ2H2/download\n",
+    "    !tar xzf creditcard.tgz"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Tests"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "print(datetime.date.today(), time.strftime(\"%H:%M:%S\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load dataset and normalize values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load Dataset\n",
+    "df = pd.read_csv('data/creditcard.csv')\n",
+    "df.shape\n",
+    "random_state = 2020"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n",
+    "print(\"Valid: {0:.3f}% {1:,}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Normalize Amount\n",
+    "from sklearn.preprocessing import RobustScaler\n",
+    "values = RobustScaler().fit_transform(df.Amount.values.reshape(-1, 1))\n",
+    "df['Amount_Scaled'] = values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# Remove unneeded features\n",
+    "y = df.Class.values\n",
+    "X = df.drop(['Class', 'Time', 'Amount'], axis=1).values\n",
+    "print(f\"X shape: {X.shape}\\ny shape: {y.shape}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Build the models"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Divide dataset\n",
+    "train_size = .7\n",
+    "Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=train_size, shuffle=True, random_state=random_state, stratify=y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Linear Tree\n",
+    "linear_tree = DecisionTreeClassifier(random_state=random_state)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Naive Bayes\n",
+    "naive_bayes = GaussianNB()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Stree\n",
+    "stree = Stree(random_state=random_state, C=.01, max_iter=1e3, kernel=\"liblinear\", multiclass_strategy=\"ovr\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Neural Network\n",
+    "mlp = MLPClassifier(random_state=random_state, alpha=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# SVC (linear)\n",
+    "svc = LinearSVC(random_state=random_state, C=.01, max_iter=1e3)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Do the test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def try_model(name, model):\n",
+    "    print(f\"************************** {name} **********************\")\n",
+    "    now = time.time()\n",
+    "    model.fit(Xtrain, ytrain)\n",
+    "    spent = time.time() - now\n",
+    "    print(f\"Train Model {name} took: {spent:.4} seconds\")\n",
+    "    predict = model.predict(Xtrain)\n",
+    "    predictt = model.predict(Xtest)\n",
+    "    print(f\"=========== {name} - Train {Xtrain.shape[0]:,} samples =============\",)\n",
+    "    print(classification_report(ytrain, predict, digits=6))\n",
+    "    print(f\"=========== {name} - Test {Xtest.shape[0]:,} samples =============\")\n",
+    "    print(classification_report(ytest, predictt, digits=6))\n",
+    "    print(\"Confusion Matrix in Train\")\n",
+    "    print(confusion_matrix(ytrain, predict))\n",
+    "    print(\"Confusion Matrix in Test\")\n",
+    "    print(confusion_matrix(ytest, predictt))\n",
+    "    return f1_score(ytest, predictt), spent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# Train & Test models\n",
+    "models = {\n",
+    "    'Linear Tree':linear_tree, 'Naive Bayes': naive_bayes, 'Stree    ': stree,  \n",
+    "    'Neural Network': mlp, 'SVC (linear)': svc\n",
+    "}\n",
+    "\n",
+    "best_f1 = 0\n",
+    "outcomes = []\n",
+    "for name, model in models.items():\n",
+    "    f1, time_spent = try_model(name, model)\n",
+    "    outcomes.append((name, f1, time_spent))\n",
+    "    if f1 > best_f1:\n",
+    "        best_model = name\n",
+    "        best_time = time_spent\n",
+    "        best_f1 = f1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "print(\"*\"*110)\n",
+    "print(f\"*The best f1 model is {best_model}, with a f1 score: {best_f1:.4} in {best_time:.6} seconds with {train_size:,} samples in train dataset\")\n",
+    "print(\"*\"*110)\n",
+    "for name, f1, time_spent in outcomes:\n",
+    "    print(f\"Model: {name}\\t Time: {time_spent:6.2f} seconds\\t f1: {f1:.4}\")"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "**************************************************************************************************************\n",
+    "*The best f1 model is Stree (SVM Tree), with a f1 score: 0.8603 in 28.4743 seconds with 0.7 samples in train dataset\n",
+    "**************************************************************************************************************\n",
+    "Model: Linear Tree\t Time:  10.25 seconds\t f1: 0.7645\n",
+    "Model: Naive Bayes\t Time:   0.10 seconds\t f1: 0.1154\n",
+    "Model: Stree (SVM Tree)\t Time:  28.47 seconds\t f1: 0.8603\n",
+    "Model: Neural Network\t Time:   9.76 seconds\t f1: 0.7381\n",
+    "Model: SVC (linear)\t Time:   8.21 seconds\t f1: 0.739"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "stree.get_params()"
+   ]
+  }
+ ],
+ "metadata": {
+  "hide_input": false,
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.2-final"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "position": {
+    "height": "392px",
+    "left": "1518px",
+    "right": "20px",
+    "top": "40px",
+    "width": "392px"
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": true
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

notebooks/ensemble.ipynb

@@ -0,0 +1,229 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Test Stree with AdaBoost and Bagging with different configurations"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Setup\n",
+    "Uncomment the next cell if STree is not already installed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#\n",
+    "# Google Colab setup\n",
+    "#\n",
+    "#!pip install git+https://github.com/doctorado-ml/stree\n",
+    "!pip install pandas"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import time\n",
+    "import os\n",
+    "import random\n",
+    "import warnings\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from sklearn.ensemble import AdaBoostClassifier, BaggingClassifier\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.exceptions import ConvergenceWarning\n",
+    "from stree import Stree\n",
+    "\n",
+    "warnings.filterwarnings(\"ignore\", category=ConvergenceWarning)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "if not os.path.isfile('data/creditcard.csv'):\n",
+    "    !wget --no-check-certificate --content-disposition http://nube.jccm.es/index.php/s/Zs7SYtZQJ3RQ2H2/download\n",
+    "    !tar xzf creditcard.tgz"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "random_state=1\n",
+    "\n",
+    "def load_creditcard(n_examples=0):\n",
+    "    df = pd.read_csv('data/creditcard.csv')\n",
+    "    print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n",
+    "    print(\"Valid: {0:.3f}% {1}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))\n",
+    "    y = df.Class\n",
+    "    X = df.drop(['Class', 'Time', 'Amount'], axis=1).values\n",
+    "    if n_examples > 0:\n",
+    "        # Take first n_examples samples\n",
+    "        X = X[:n_examples, :]\n",
+    "        y = y[:n_examples, :]\n",
+    "    else:\n",
+    "        # Take all the positive samples with a number of random negatives\n",
+    "        if n_examples < 0:\n",
+    "            Xt = X[(y == 1).ravel()]\n",
+    "            yt = y[(y == 1).ravel()]\n",
+    "            indices = random.sample(range(X.shape[0]), -1 * n_examples)\n",
+    "            X = np.append(Xt, X[indices], axis=0)\n",
+    "            y = np.append(yt, y[indices], axis=0)\n",
+    "    print(\"X.shape\", X.shape, \" y.shape\", y.shape)\n",
+    "    print(\"Fraud: {0:.3f}% {1}\".format(len(y[y == 1])*100/X.shape[0], len(y[y == 1])))\n",
+    "    print(\"Valid: {0:.3f}% {1}\".format(len(y[y == 0]) * 100 / X.shape[0], len(y[y == 0])))\n",
+    "    Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state, stratify=y)\n",
+    "    return Xtrain, Xtest, ytrain, ytest\n",
+    "\n",
+    "# data = load_creditcard(-1000) # Take all true samples + 1000 of the others\n",
+    "# data = load_creditcard(5000)  # Take the first 5000 samples\n",
+    "# data = load_creditcard(0) # Take all the samples\n",
+    "data = load_creditcard(-100000)\n",
+    "\n",
+    "Xtrain = data[0]\n",
+    "Xtest = data[1]\n",
+    "ytrain = data[2]\n",
+    "ytest = data[3]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Tests"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## STree alone with 100.000 samples and linear kernel"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "now = time.time()\n",
+    "clf = Stree(max_depth=3, random_state=random_state, max_iter=1e3)\n",
+    "clf.fit(Xtrain, ytrain)\n",
+    "print(\"Score Train: \", clf.score(Xtrain, ytrain))\n",
+    "print(\"Score Test: \", clf.score(Xtest, ytest))\n",
+    "print(f\"Took {time.time() - now:.2f} seconds\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Adaboost"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "n_estimators = 10\n",
+    "C = 7\n",
+    "max_depth = 3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "for kernel in ['linear', 'rbf', 'poly']:\n",
+    "    now = time.time()\n",
+    "    clf = AdaBoostClassifier(base_estimator=Stree(C=C, kernel=kernel, max_depth=max_depth, random_state=random_state, max_iter=1e3), algorithm=\"SAMME\", n_estimators=n_estimators, random_state=random_state)\n",
+    "    clf.fit(Xtrain, ytrain)\n",
+    "    score_train = clf.score(Xtrain, ytrain)\n",
+    "    score_test = clf.score(Xtest, ytest)\n",
+    "    print(f\"Kernel: {kernel}\\tTime: {time.time() - now:.2f} seconds\\tScore Train: {score_train:.7f}\\tScore Test: {score_test:.7f}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Bagging"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "n_estimators = 10\n",
+    "C = 7\n",
+    "max_depth = 3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "for kernel in ['linear', 'rbf', 'poly']:\n",
+    "    now = time.time()\n",
+    "    clf = BaggingClassifier(base_estimator=Stree(C=C, kernel=kernel, max_depth=max_depth, random_state=random_state, max_iter=1e3), n_estimators=n_estimators, random_state=random_state)\n",
+    "    clf.fit(Xtrain, ytrain)\n",
+    "    score_train = clf.score(Xtrain, ytrain)\n",
+    "    score_test = clf.score(Xtest, ytest)\n",
+    "    print(f\"Kernel: {kernel}\\tTime: {time.time() - now:.2f} seconds\\tScore Train: {score_train:.7f}\\tScore Test: {score_test:.7f}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.2-final"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

notebooks/features.ipynb

@@ -0,0 +1,359 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Test sample_weight, kernels, C, sklearn estimator"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Setup\n",
+    "Uncomment the next cell if STree is not already installed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#\n",
+    "# Google Colab setup\n",
+    "#\n",
+    "#!pip install git+https://github.com/doctorado-ml/stree\n",
+    "!pip install pandas"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import time\n",
+    "import random\n",
+    "import warnings\n",
+    "import os\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn.svm import SVC\n",
+    "from sklearn.tree import DecisionTreeClassifier\n",
+    "from sklearn.utils.estimator_checks import check_estimator\n",
+    "from sklearn.datasets import make_classification, load_iris, load_wine\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.utils.class_weight import compute_sample_weight\n",
+    "from sklearn.exceptions import ConvergenceWarning\n",
+    "from stree import Stree\n",
+    "warnings.filterwarnings(\"ignore\", category=ConvergenceWarning)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "if not os.path.isfile('data/creditcard.csv'):\n",
+    "    !wget --no-check-certificate --content-disposition http://nube.jccm.es/index.php/s/Zs7SYtZQJ3RQ2H2/download\n",
+    "    !tar xzf creditcard.tgz"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "random_state=1\n",
+    "\n",
+    "def load_creditcard(n_examples=0):\n",
+    "    df = pd.read_csv('data/creditcard.csv')\n",
+    "    print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n",
+    "    print(\"Valid: {0:.3f}% {1}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))\n",
+    "    y = df.Class\n",
+    "    X = df.drop(['Class', 'Time', 'Amount'], axis=1).values\n",
+    "    if n_examples > 0:\n",
+    "        # Take first n_examples samples\n",
+    "        X = X[:n_examples, :]\n",
+    "        y = y[:n_examples, :]\n",
+    "    else:\n",
+    "        # Take all the positive samples with a number of random negatives\n",
+    "        if n_examples < 0:\n",
+    "            Xt = X[(y == 1).ravel()]\n",
+    "            yt = y[(y == 1).ravel()]\n",
+    "            indices = random.sample(range(X.shape[0]), -1 * n_examples)\n",
+    "            X = np.append(Xt, X[indices], axis=0)\n",
+    "            y = np.append(yt, y[indices], axis=0)\n",
+    "    print(\"X.shape\", X.shape, \" y.shape\", y.shape)\n",
+    "    print(\"Fraud: {0:.3f}% {1}\".format(len(y[y == 1])*100/X.shape[0], len(y[y == 1])))\n",
+    "    print(\"Valid: {0:.3f}% {1}\".format(len(y[y == 0]) * 100 / X.shape[0], len(y[y == 0])))\n",
+    "    Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state)\n",
+    "    return Xtrain, Xtest, ytrain, ytest\n",
+    "\n",
+    "data = load_creditcard(-5000) # Take all true samples with up to 5000 of the others\n",
+    "# data = load_creditcard(5000)  # Take the first 5000 samples\n",
+    "# data = load_creditcard(-1000) # Take 1000 samples\n",
+    "\n",
+    "Xtrain = data[0]\n",
+    "Xtest = data[1]\n",
+    "ytrain = data[2]\n",
+    "ytest = data[3]\n",
+    "weights = compute_sample_weight(\"balanced\", ytrain)\n",
+    "weights_test = compute_sample_weight(\"balanced\", ytest)\n",
+    "print(weights[:4], weights_test[:4])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Tests"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test sample_weights\n",
+    "Compute accuracy with weights in samples. The weights are set based on the inverse of the number of samples of each class"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "C = 23\n",
+    "print(\"Accuracy of Train without weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain).score(Xtrain, ytrain))\n",
+    "print(\"Accuracy of Train with    weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain, sample_weight=weights).score(Xtrain, ytrain))\n",
+    "print(\"Accuracy of Tests without weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain).score(Xtest, ytest))\n",
+    "print(\"Accuracy of Tests with    weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain, sample_weight=weights).score(Xtest, ytest))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test accuracy with different kernels\n",
+    "Compute accuracy on train and test set with default hyperparmeters of every kernel"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "random_state=1\n",
+    "for kernel in ['linear', 'rbf', 'poly']:\n",
+    "    now = time.time()\n",
+    "    clf = Stree(C=7, kernel=kernel, random_state=random_state).fit(Xtrain, ytrain)\n",
+    "    accuracy_train = clf.score(Xtrain, ytrain)\n",
+    "    accuracy_test = clf.score(Xtest, ytest)\n",
+    "    time_spent = time.time() - now\n",
+    "    print(f\"Time: {time_spent:.2f}s\\tKernel: {kernel}\\tAccuracy_train: {accuracy_train}\\tAccuracy_test: {accuracy_test}\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test diferent values of C"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "t = time.time()\n",
+    "for C in (.001, .01, 1, 5, 17):\n",
+    "    clf = Stree(C=C, kernel=\"linear\", random_state=random_state)\n",
+    "    clf.fit(Xtrain, ytrain)\n",
+    "    print(f\"************** C={C} ****************************\")\n",
+    "    print(f\"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}\")\n",
+    "    print(f\"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}\")\n",
+    "    print(clf)\n",
+    "    print(f\"**************************************************\")\n",
+    "print(f\"{time.time() - t:.4f} secs\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test iterator\n",
+    "Check different ways of using the iterator"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "#check iterator\n",
+    "for i in list(clf):\n",
+    "    print(i)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "#check iterator again\n",
+    "for i in clf:\n",
+    "    print(i)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test STree is a sklearn estimator"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# Make checks one by one\n",
+    "c = 0\n",
+    "checks = check_estimator(Stree(), generate_only=True)\n",
+    "for check in checks:\n",
+    "    c += 1\n",
+    "    print(c, check[1])\n",
+    "    check[1](check[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Check if the classifier is a sklearn estimator\n",
+    "check_estimator(Stree())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Compare to SVM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "svc = SVC(C=7, kernel='rbf', gamma=.001, random_state=random_state)\n",
+    "clf = Stree(C=17, kernel='rbf', gamma=.001, random_state=random_state)\n",
+    "svc.fit(Xtrain, ytrain)\n",
+    "clf.fit(Xtrain, ytrain)\n",
+    "print(\"== Not Weighted ===\")\n",
+    "print(\"SVC train score ..:\", svc.score(Xtrain, ytrain))\n",
+    "print(\"STree train score :\", clf.score(Xtrain, ytrain))\n",
+    "print(\"SVC test score ...:\", svc.score(Xtest, ytest))\n",
+    "print(\"STree test score .:\", clf.score(Xtest, ytest))\n",
+    "svc.fit(Xtrain, ytrain, weights)\n",
+    "clf.fit(Xtrain, ytrain, weights)\n",
+    "print(\"==== Weighted =====\")\n",
+    "print(\"SVC train score ..:\", svc.score(Xtrain, ytrain))\n",
+    "print(\"STree train score :\", clf.score(Xtrain, ytrain))\n",
+    "print(\"SVC test score ...:\", svc.score(Xtest, ytest))\n",
+    "print(\"STree test score .:\", clf.score(Xtest, ytest))\n",
+    "print(\"*SVC test score ..:\", svc.score(Xtest, ytest, weights_test))\n",
+    "print(\"*STree test score :\", clf.score(Xtest, ytest, weights_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "print(clf)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test max_features"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "for max_features in [None, \"auto\", \"log2\", 7, .5, .1, .7]:\n",
+    "    now = time.time()\n",
+    "    print(\"*\"*40)\n",
+    "    clf = Stree(random_state=random_state, max_features=max_features)\n",
+    "    clf.fit(Xtrain, ytrain)\n",
+    "    print(f\"max_features {max_features} = {clf.max_features_}\")\n",
+    "    print(\"Train score :\", clf.score(Xtrain, ytrain))\n",
+    "    print(\"Test score .:\", clf.score(Xtest, ytest))\n",
+    "    print(f\"Took {time.time() - now:.2f} seconds\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.2-final"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

notebooks/gridsearch.ipynb

@@ -0,0 +1,253 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Test Gridsearch\n",
+    "with different kernels and different configurations"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Setup\n",
+    "Uncomment the next cell if STree is not already installed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#\n",
+    "# Google Colab setup\n",
+    "#\n",
+    "#!pip install git+https://github.com/doctorado-ml/stree\n",
+    "!pip install pandas"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "zIHKVxthDZEa"
+   },
+   "outputs": [],
+   "source": [
+    "import random\n",
+    "import os\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from sklearn.ensemble import AdaBoostClassifier\n",
+    "from sklearn.svm import LinearSVC\n",
+    "from sklearn.model_selection import GridSearchCV, train_test_split\n",
+    "from stree import Stree"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "IEmq50QgDZEi"
+   },
+   "outputs": [],
+   "source": [
+    "if not os.path.isfile('data/creditcard.csv'):\n",
+    "    !wget --no-check-certificate --content-disposition http://nube.jccm.es/index.php/s/Zs7SYtZQJ3RQ2H2/download\n",
+    "    !tar xzf creditcard.tgz"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "z9Q-YUfBDZEq",
+    "outputId": "afc822fb-f16a-4302-8a67-2b9e2880159b",
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "random_state=1\n",
+    "\n",
+    "def load_creditcard(n_examples=0):\n",
+    "    df = pd.read_csv('data/creditcard.csv')\n",
+    "    print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n",
+    "    print(\"Valid: {0:.3f}% {1}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))\n",
+    "    y = df.Class\n",
+    "    X = df.drop(['Class', 'Time', 'Amount'], axis=1).values\n",
+    "    if n_examples > 0:\n",
+    "        # Take first n_examples samples\n",
+    "        X = X[:n_examples, :]\n",
+    "        y = y[:n_examples, :]\n",
+    "    else:\n",
+    "        # Take all the positive samples with a number of random negatives\n",
+    "        if n_examples < 0:\n",
+    "            Xt = X[(y == 1).ravel()]\n",
+    "            yt = y[(y == 1).ravel()]\n",
+    "            indices = random.sample(range(X.shape[0]), -1 * n_examples)\n",
+    "            X = np.append(Xt, X[indices], axis=0)\n",
+    "            y = np.append(yt, y[indices], axis=0)\n",
+    "    print(\"X.shape\", X.shape, \" y.shape\", y.shape)\n",
+    "    print(\"Fraud: {0:.3f}% {1}\".format(len(y[y == 1])*100/X.shape[0], len(y[y == 1])))\n",
+    "    print(\"Valid: {0:.3f}% {1}\".format(len(y[y == 0]) * 100 / X.shape[0], len(y[y == 0])))\n",
+    "    Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state, stratify=y)\n",
+    "    return Xtrain, Xtest, ytrain, ytest\n",
+    "\n",
+    "data = load_creditcard(-1000) # Take all true samples + 1000 of the others\n",
+    "# data = load_creditcard(5000)  # Take the first 5000 samples\n",
+    "# data = load_creditcard(0) # Take all the samples\n",
+    "\n",
+    "Xtrain = data[0]\n",
+    "Xtest = data[1]\n",
+    "ytrain = data[2]\n",
+    "ytest = data[3]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Tests"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "HmX3kR4PDZEw"
+   },
+   "outputs": [],
+   "source": [
+    "parameters = [{\n",
+    "    'base_estimator': [Stree(random_state=random_state)],\n",
+    "    'n_estimators': [10, 25],\n",
+    "    'learning_rate': [.5, 1],\n",
+    "    'base_estimator__split_criteria': ['max_samples', 'impurity'],\n",
+    "    'base_estimator__tol': [.1,  1e-02],\n",
+    "    'base_estimator__max_depth': [3, 5, 7],\n",
+    "    'base_estimator__C': [1, 7, 55],\n",
+    "    'base_estimator__kernel': ['linear']\n",
+    "},\n",
+    "{\n",
+    "    'base_estimator': [Stree(random_state=random_state)],\n",
+    "    'n_estimators': [10, 25],\n",
+    "    'learning_rate': [.5, 1],\n",
+    "    'base_estimator__split_criteria': ['max_samples', 'impurity'],\n",
+    "    'base_estimator__tol': [.1,  1e-02],\n",
+    "    'base_estimator__max_depth': [3, 5, 7],\n",
+    "    'base_estimator__C': [1, 7, 55],\n",
+    "    'base_estimator__degree': [3, 5, 7],\n",
+    "    'base_estimator__kernel': ['poly']\n",
+    "},\n",
+    "{\n",
+    "    'base_estimator': [Stree(random_state=random_state)],\n",
+    "    'n_estimators': [10, 25],\n",
+    "    'learning_rate': [.5, 1],\n",
+    "    'base_estimator__split_criteria': ['max_samples', 'impurity'],\n",
+    "    'base_estimator__tol': [.1,  1e-02],\n",
+    "    'base_estimator__max_depth': [3, 5, 7],\n",
+    "    'base_estimator__C': [1, 7, 55],\n",
+    "    'base_estimator__gamma': [.1, 1, 10],\n",
+    "    'base_estimator__kernel': ['rbf']\n",
+    "}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Stree().get_params()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "CrcB8o6EDZE5",
+    "outputId": "7703413a-d563-4289-a13b-532f38f82762",
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "clf = AdaBoostClassifier(random_state=random_state, algorithm=\"SAMME\")\n",
+    "grid = GridSearchCV(clf, parameters, verbose=5, n_jobs=-1, return_train_score=True)\n",
+    "grid.fit(Xtrain, ytrain)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "ZjX88NoYDZE8",
+    "outputId": "285163c8-fa33-4915-8ae7-61c4f7844344",
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "print(\"Best estimator: \", grid.best_estimator_)\n",
+    "print(\"Best hyperparameters: \", grid.best_params_)\n",
+    "print(\"Best accuracy: \", grid.best_score_)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Best estimator:  AdaBoostClassifier(algorithm='SAMME',\n",
+    "                   base_estimator=Stree(C=55, max_depth=7, random_state=1,\n",
+    "                                        split_criteria='max_samples', tol=0.1),\n",
+    "                   learning_rate=0.5, n_estimators=25, random_state=1)\n",
+    "Best hyperparameters:  {'base_estimator': Stree(C=55, max_depth=7, random_state=1, split_criteria='max_samples', tol=0.1), 'base_estimator__C': 55, 'base_estimator__kernel': 'linear', 'base_estimator__max_depth': 7, 'base_estimator__split_criteria': 'max_samples', 'base_estimator__tol': 0.1, 'learning_rate': 0.5, 'n_estimators': 25}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Best accuracy:  0.9511777695988222"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "name": "gridsearch.ipynb",
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.2-final"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

pyproject.toml

@@ -0,0 +1,16 @@
+[tool.black]
+line-length = 79
+include = '\.pyi?$'
+exclude = '''
+/(
+    \.git
+  | \.hg
+  | \.mypy_cache
+  | \.tox
+  | \.venv
+  | _build
+  | buck-out
+  | build
+  | dist
+)/
+'''

requirements.txt

@@ -1,5 +1,2 @@
-numpy
-scikit-learn
-pandas
-matplotlib
-ipympl
+scikit-learn>0.24
+mufs

runtime.txt

@@ -0,0 +1 @@
+python-3.8

setup.py

@@ -1,39 +1,56 @@
 import setuptools
+import os
 
-__version__ = "0.9rc2"
-__author__ = "Ricardo Montañana Gómez"
 
 def readme():
-    with open('README.md') as f:
+    with open("README.md") as f:
         return f.read()
 
 
+def get_data(field, file_name="__init__.py"):
+    item = ""
+    with open(os.path.join("stree", file_name)) as f:
+        for line in f.readlines():
+            if line.startswith(f"__{field}__"):
+                delim = '"' if '"' in line else "'"
+                item = line.split(delim)[1]
+                break
+        else:
+            raise RuntimeError(f"Unable to find {field} string.")
+    return item
+
+
+def get_requirements():
+    with open("requirements.txt") as f:
+        return f.read().splitlines()
+
+
 setuptools.setup(
-    name='STree',
-    version=__version__,
-    license='MIT License',
-    description='Oblique decision tree with svm nodes',
+    name="STree",
+    version=get_data("version", "_version.py"),
+    license=get_data("license"),
+    description="Oblique decision tree with svm nodes",
     long_description=readme(),
-    long_description_content_type='text/markdown',
+    long_description_content_type="text/markdown",
     packages=setuptools.find_packages(),
-    url='https://github.com/doctorado-ml/stree',
-    author=__author__,
-    author_email='ricardo.montanana@alu.uclm.es',
-    keywords='scikit-learn oblique-classifier oblique-decision-tree decision-tree svm svc',
+    url="https://github.com/Doctorado-ML/STree#stree",
+    project_urls={
+        "Code": "https://github.com/Doctorado-ML/STree",
+        "Documentation": "https://stree.readthedocs.io/en/latest/index.html",
+    },
+    author=get_data("author"),
+    author_email=get_data("author_email"),
+    keywords="scikit-learn oblique-classifier oblique-decision-tree decision-\
+    tree svm svc",
     classifiers=[
-        'Development Status :: 4 - Beta',
-        'License :: OSI Approved :: MIT License',
-        'Programming Language :: Python :: 3.7',
-        'Natural Language :: English',
-        'Topic :: Scientific/Engineering :: Artificial Intelligence',
-        'Intended Audience :: Science/Research'
-    ],
-    install_requires=[
-        'scikit-learn>=0.23.0',
-        'numpy',
-        'matplotlib',
-        'ipympl'
+        "Development Status :: 5 - Production/Stable",
+        "License :: OSI Approved :: " + get_data("license"),
+        "Programming Language :: Python :: 3.8",
+        "Natural Language :: English",
+        "Topic :: Scientific/Engineering :: Artificial Intelligence",
+        "Intended Audience :: Science/Research",
     ],
+    install_requires=get_requirements(),
     test_suite="stree.tests",
-    zip_safe=False
+    zip_safe=False,
 )

stree/.readthedocs.yaml

@@ -0,0 +1,10 @@
+version: 2
+
+sphinx:
+  configuration: docs/source/conf.py
+
+python:
+  version: 3.8
+  install:
+    - requirements: requirements.txt
+    - requirements: docs/requirements.txt

stree/Splitter.py

@@ -0,0 +1,809 @@
+"""
+Oblique decision tree classifier based on SVM nodes
+Splitter class
+"""
+
+import os
+import warnings
+import random
+from math import log, factorial
+import numpy as np
+from sklearn.feature_selection import SelectKBest, mutual_info_classif
+from sklearn.preprocessing import StandardScaler
+from sklearn.svm import SVC
+from sklearn.exceptions import ConvergenceWarning
+from mufs import MUFS
+
+
+class Snode:
+    """
+    Nodes of the tree that keeps the svm classifier and if testing the
+    dataset assigned to it
+
+    Parameters
+    ----------
+    clf : SVC
+        Classifier used
+    X : np.ndarray
+        input dataset in train time (only in testing)
+    y : np.ndarray
+        input labes in train time
+    features : np.array
+        features used to compute hyperplane
+    impurity : float
+        impurity of the node
+    title : str
+        label describing the route to the node
+    weight : np.ndarray, optional
+        weights applied to input dataset in train time, by default None
+    scaler : StandardScaler, optional
+        scaler used if any, by default None
+    """
+
+    def __init__(
+        self,
+        clf: SVC,
+        X: np.ndarray,
+        y: np.ndarray,
+        features: np.array,
+        impurity: float,
+        title: str,
+        weight: np.ndarray = None,
+        scaler: StandardScaler = None,
+    ):
+        self._clf = clf
+        self._title = title
+        self._belief = 0.0
+        # Only store dataset in Testing
+        self._X = X if os.environ.get("TESTING", "NS") != "NS" else None
+        self._y = y
+        self._down = None
+        self._up = None
+        self._class = None
+        self._feature = None
+        self._sample_weight = (
+            weight if os.environ.get("TESTING", "NS") != "NS" else None
+        )
+        self._features = features
+        self._impurity = impurity
+        self._partition_column: int = -1
+        self._scaler = scaler
+        self._proba = None
+
+    @classmethod
+    def copy(cls, node: "Snode") -> "Snode":
+        return cls(
+            node._clf,
+            node._X,
+            node._y,
+            node._features,
+            node._impurity,
+            node._title,
+            node._sample_weight,
+            node._scaler,
+        )
+
+    def set_partition_column(self, col: int):
+        self._partition_column = col
+
+    def get_partition_column(self) -> int:
+        return self._partition_column
+
+    def set_down(self, son):
+        self._down = son
+
+    def set_title(self, title):
+        self._title = title
+
+    def set_classifier(self, clf):
+        self._clf = clf
+
+    def set_features(self, features):
+        self._features = features
+
+    def set_impurity(self, impurity):
+        self._impurity = impurity
+
+    def get_title(self) -> str:
+        return self._title
+
+    def get_classifier(self) -> SVC:
+        return self._clf
+
+    def get_impurity(self) -> float:
+        return self._impurity
+
+    def get_features(self) -> np.array:
+        return self._features
+
+    def set_up(self, son):
+        self._up = son
+
+    def is_leaf(self) -> bool:
+        return self._up is None and self._down is None
+
+    def get_down(self) -> "Snode":
+        return self._down
+
+    def get_up(self) -> "Snode":
+        return self._up
+
+    def make_predictor(self, num_classes: int) -> None:
+        """Compute the class of the predictor and its belief based on the
+        subdataset of the node only if it is a leaf
+        """
+        if not self.is_leaf():
+            return
+        classes, card = np.unique(self._y, return_counts=True)
+        self._proba = np.zeros((num_classes,), dtype=np.int64)
+        for c, n in zip(classes, card):
+            self._proba[c] = n
+        try:
+            max_card = max(card)
+            self._class = classes[card == max_card][0]
+            self._belief = max_card / np.sum(card)
+        except ValueError:
+            self._class = None
+
+    def graph(self):
+        """
+        Return a string representing the node in graphviz format
+        """
+        output = ""
+        count_values = np.unique(self._y, return_counts=True)
+        if self.is_leaf():
+            output += (
+                f'N{id(self)} [shape=box style=filled label="'
+                f"class={self._class} impurity={self._impurity:.3f} "
+                f'counts={self._proba}"];\n'
+            )
+        else:
+            output += (
+                f'N{id(self)} [label="#features={len(self._features)} '
+                f"classes={count_values[0]} samples={count_values[1]} "
+                f'({sum(count_values[1])})" fontcolor=black];\n'
+            )
+            output += f"N{id(self)} -> N{id(self.get_up())} [color=black];\n"
+            output += f"N{id(self)} -> N{id(self.get_down())} [color=black];\n"
+        return output
+
+    def __str__(self) -> str:
+        count_values = np.unique(self._y, return_counts=True)
+        if self.is_leaf():
+            return (
+                f"{self._title} - Leaf class={self._class} belief="
+                f"{self._belief: .6f} impurity={self._impurity:.4f} "
+                f"counts={count_values}"
+            )
+        return (
+            f"{self._title} feaures={self._features} impurity="
+            f"{self._impurity:.4f} "
+            f"counts={count_values}"
+        )
+
+
+class Siterator:
+    """Stree preorder iterator"""
+
+    def __init__(self, tree: Snode):
+        self._stack = []
+        self._push(tree)
+
+    def __iter__(self):
+        # To complete the iterator interface
+        return self
+
+    def _push(self, node: Snode):
+        if node is not None:
+            self._stack.append(node)
+
+    def __next__(self) -> Snode:
+        if len(self._stack) == 0:
+            raise StopIteration()
+        node = self._stack.pop()
+        self._push(node.get_up())
+        self._push(node.get_down())
+        return node
+
+
+class Splitter:
+    """
+    Splits a dataset in two based on different criteria
+
+    Parameters
+    ----------
+    clf : SVC, optional
+        classifier, by default None
+    criterion : str, optional
+        The function to measure the quality of a split (only used if
+        max_features != num_features). Supported criteria are “gini” for the
+        Gini impurity and “entropy” for the information gain., by default
+        "entropy", by default None
+    feature_select : str, optional
+        The strategy used to choose the feature set at each node (only used if
+        max_features < num_features). Supported strategies are: “best”: sklearn
+        SelectKBest algorithm is used in every node to choose the max_features
+        best features. “random”: The algorithm generates 5 candidates and
+        choose the best (max. info. gain) of them. “trandom”: The algorithm
+        generates only one random combination. "mutual": Chooses the best
+        features w.r.t. their mutual info with the label. "cfs": Apply
+        Correlation-based Feature Selection. "fcbf": Apply Fast Correlation-
+        Based, by default None
+    criteria : str, optional
+        ecides (just in case of a multi class classification) which column
+        (class) use to split the dataset in a node. max_samples is
+        incompatible with 'ovo' multiclass_strategy, by default None
+    min_samples_split : int, optional
+        The minimum number of samples required to split an internal node. 0
+        (default) for any, by default None
+    random_state : optional
+        Controls the pseudo random number generation for shuffling the data for
+        probability estimates. Ignored when probability is False.Pass an int
+        for reproducible output across multiple function calls, by
+        default None
+    normalize : bool, optional
+        If standardization of features should be applied on each node with the
+        samples that reach it , by default False
+
+    Raises
+    ------
+    ValueError
+        clf has to be a sklearn estimator
+    ValueError
+        criterion must be gini or entropy
+    ValueError
+        criteria has to be max_samples or impurity
+    ValueError
+        splitter must be in {random, best, mutual, cfs, fcbf}
+    """
+
+    def __init__(
+        self,
+        clf: SVC = None,
+        criterion: str = None,
+        feature_select: str = None,
+        criteria: str = None,
+        min_samples_split: int = None,
+        random_state=None,
+        normalize=False,
+    ):
+
+        self._clf = clf
+        self._random_state = random_state
+        if random_state is not None:
+            random.seed(random_state)
+        self._criterion = criterion
+        self._min_samples_split = min_samples_split
+        self._criteria = criteria
+        self._feature_select = feature_select
+        self._normalize = normalize
+
+        if clf is None:
+            raise ValueError(f"clf has to be a sklearn estimator, got({clf})")
+
+        if criterion not in ["gini", "entropy"]:
+            raise ValueError(
+                f"criterion must be gini or entropy got({criterion})"
+            )
+
+        if criteria not in [
+            "max_samples",
+            "impurity",
+        ]:
+            raise ValueError(
+                f"criteria has to be max_samples or impurity; got ({criteria})"
+            )
+
+        if feature_select not in [
+            "random",
+            "trandom",
+            "best",
+            "mutual",
+            "cfs",
+            "fcbf",
+            "iwss",
+        ]:
+            raise ValueError(
+                "splitter must be in {random, trandom, best, mutual, cfs, "
+                "fcbf, iwss} "
+                f"got ({feature_select})"
+            )
+        self.criterion_function = getattr(self, f"_{self._criterion}")
+        self.decision_criteria = getattr(self, f"_{self._criteria}")
+        self.fs_function = getattr(self, f"_fs_{self._feature_select}")
+
+    def _fs_random(
+        self, dataset: np.array, labels: np.array, max_features: int
+    ) -> tuple:
+        """Return the best of five random feature set combinations
+
+        Parameters
+        ----------
+        dataset : np.array
+            array of samples
+        labels : np.array
+            labels of the dataset
+        max_features : int
+            number of features of the subspace
+            (< number of features in dataset)
+
+        Returns
+        -------
+        tuple
+            indices of the features selected
+        """
+        # Random feature reduction
+        n_features = dataset.shape[1]
+        features_sets = self._generate_spaces(n_features, max_features)
+        return self._select_best_set(dataset, labels, features_sets)
+
+    @staticmethod
+    def _fs_trandom(
+        dataset: np.array, labels: np.array, max_features: int
+    ) -> tuple:
+        """Return the a random feature set combination
+
+        Parameters
+        ----------
+        dataset : np.array
+            array of samples
+        labels : np.array
+            labels of the dataset
+        max_features : int
+            number of features of the subspace
+            (< number of features in dataset)
+
+        Returns
+        -------
+        tuple
+            indices of the features selected
+        """
+        # Random feature reduction
+        n_features = dataset.shape[1]
+        return tuple(sorted(random.sample(range(n_features), max_features)))
+
+    @staticmethod
+    def _fs_best(
+        dataset: np.array, labels: np.array, max_features: int
+    ) -> tuple:
+        """Return the variabes with higher f-score
+
+        Parameters
+        ----------
+        dataset : np.array
+            array of samples
+        labels : np.array
+            labels of the dataset
+        max_features : int
+            number of features of the subspace
+            (< number of features in dataset)
+
+        Returns
+        -------
+        tuple
+            indices of the features selected
+        """
+        return (
+            SelectKBest(k=max_features)
+            .fit(dataset, labels)
+            .get_support(indices=True)
+        )
+
+    def _fs_mutual(
+        self, dataset: np.array, labels: np.array, max_features: int
+    ) -> tuple:
+        """Return the best features with mutual information with labels
+
+        Parameters
+        ----------
+        dataset : np.array
+            array of samples
+        labels : np.array
+            labels of the dataset
+        max_features : int
+            number of features of the subspace
+            (< number of features in dataset)
+
+        Returns
+        -------
+        tuple
+            indices of the features selected
+        """
+        # return best features with mutual info with the label
+        feature_list = mutual_info_classif(
+            dataset, labels, random_state=self._random_state
+        )
+        return tuple(
+            sorted(
+                range(len(feature_list)), key=lambda sub: feature_list[sub]
+            )[-max_features:]
+        )
+
+    @staticmethod
+    def _fs_cfs(
+        dataset: np.array, labels: np.array, max_features: int
+    ) -> tuple:
+        """Correlattion-based feature selection with max_features limit
+
+        Parameters
+        ----------
+        dataset : np.array
+            array of samples
+        labels : np.array
+            labels of the dataset
+        max_features : int
+            number of features of the subspace
+            (< number of features in dataset)
+
+        Returns
+        -------
+        tuple
+            indices of the features selected
+        """
+        mufs = MUFS(max_features=max_features, discrete=False)
+        return mufs.cfs(dataset, labels).get_results()
+
+    @staticmethod
+    def _fs_fcbf(
+        dataset: np.array, labels: np.array, max_features: int
+    ) -> tuple:
+        """Fast Correlation-based Filter algorithm with max_features limit
+
+        Parameters
+        ----------
+        dataset : np.array
+            array of samples
+        labels : np.array
+            labels of the dataset
+        max_features : int
+            number of features of the subspace
+            (< number of features in dataset)
+
+        Returns
+        -------
+        tuple
+            indices of the features selected
+        """
+        mufs = MUFS(max_features=max_features, discrete=False)
+        return mufs.fcbf(dataset, labels, 5e-4).get_results()
+
+    @staticmethod
+    def _fs_iwss(
+        dataset: np.array, labels: np.array, max_features: int
+    ) -> tuple:
+        """Correlattion-based feature selection based on iwss with max_features
+        limit
+
+        Parameters
+        ----------
+        dataset : np.array
+            array of samples
+        labels : np.array
+            labels of the dataset
+        max_features : int
+            number of features of the subspace
+            (< number of features in dataset)
+
+        Returns
+        -------
+        tuple
+            indices of the features selected
+        """
+        mufs = MUFS(max_features=max_features, discrete=False)
+        return mufs.iwss(dataset, labels, 0.25).get_results()
+
+    def partition_impurity(self, y: np.array) -> np.array:
+        return self.criterion_function(y)
+
+    @staticmethod
+    def _gini(y: np.array) -> float:
+        _, count = np.unique(y, return_counts=True)
+        return 1 - np.sum(np.square(count / np.sum(count)))
+
+    @staticmethod
+    def _entropy(y: np.array) -> float:
+        """Compute entropy of a labels set
+
+        Parameters
+        ----------
+        y : np.array
+            set of labels
+
+        Returns
+        -------
+        float
+            entropy
+        """
+        n_labels = len(y)
+        if n_labels <= 1:
+            return 0
+        counts = np.bincount(y)
+        proportions = counts / n_labels
+        n_classes = np.count_nonzero(proportions)
+        if n_classes <= 1:
+            return 0
+        entropy = 0.0
+        # Compute standard entropy.
+        for prop in proportions:
+            if prop != 0.0:
+                entropy -= prop * log(prop, n_classes)
+        return entropy
+
+    def information_gain(
+        self, labels: np.array, labels_up: np.array, labels_dn: np.array
+    ) -> float:
+        """Compute information gain of a split candidate
+
+        Parameters
+        ----------
+        labels : np.array
+            labels of the dataset
+        labels_up : np.array
+            labels of one side
+        labels_dn : np.array
+            labels on the other side
+
+        Returns
+        -------
+        float
+            information gain
+        """
+        imp_prev = self.criterion_function(labels)
+        card_up = card_dn = imp_up = imp_dn = 0
+        if labels_up is not None:
+            card_up = labels_up.shape[0]
+            imp_up = self.criterion_function(labels_up)
+        if labels_dn is not None:
+            card_dn = labels_dn.shape[0] if labels_dn is not None else 0
+            imp_dn = self.criterion_function(labels_dn)
+        samples = card_up + card_dn
+        if samples == 0:
+            return 0.0
+        else:
+            result = (
+                imp_prev
+                - (card_up / samples) * imp_up
+                - (card_dn / samples) * imp_dn
+            )
+            return result
+
+    def _select_best_set(
+        self, dataset: np.array, labels: np.array, features_sets: list
+    ) -> list:
+        """Return the best set of features among feature_sets, the criterion is
+        the information gain
+
+        Parameters
+        ----------
+        dataset : np.array
+            array of samples (# samples, # features)
+        labels : np.array
+            array of labels
+        features_sets : list
+            list of features sets to check
+
+        Returns
+        -------
+        list
+            best feature set
+        """
+        max_gain = 0
+        selected = None
+        warnings.filterwarnings("ignore", category=ConvergenceWarning)
+        for feature_set in features_sets:
+            self._clf.fit(dataset[:, feature_set], labels)
+            node = Snode(
+                self._clf, dataset, labels, feature_set, 0.0, "subset"
+            )
+            self.partition(dataset, node, train=True)
+            y1, y2 = self.part(labels)
+            gain = self.information_gain(labels, y1, y2)
+            if gain > max_gain:
+                max_gain = gain
+                selected = feature_set
+        return selected if selected is not None else feature_set
+
+    @staticmethod
+    def _generate_spaces(features: int, max_features: int) -> list:
+        """Generate at most 5 feature random combinations
+
+        Parameters
+        ----------
+        features : int
+            number of features in each combination
+        max_features : int
+            number of features in dataset
+
+        Returns
+        -------
+        list
+            list with up to 5 combination of features randomly selected
+        """
+        comb = set()
+        # Generate at most 5 combinations
+        number = factorial(features) / (
+            factorial(max_features) * factorial(features - max_features)
+        )
+        set_length = min(5, number)
+        while len(comb) < set_length:
+            comb.add(
+                tuple(sorted(random.sample(range(features), max_features)))
+            )
+        return list(comb)
+
+    def _get_subspaces_set(
+        self, dataset: np.array, labels: np.array, max_features: int
+    ) -> tuple:
+        """Compute the indices of the features selected by splitter depending
+        on the self._feature_select hyper parameter
+
+        Parameters
+        ----------
+        dataset : np.array
+            array of samples
+        labels : np.array
+            labels of the dataset
+        max_features : int
+            number of features of the subspace
+            (<= number of features in dataset)
+
+        Returns
+        -------
+        tuple
+            indices of the features selected
+        """
+        # No feature reduction
+        n_features = dataset.shape[1]
+        if n_features == max_features:
+            return tuple(range(n_features))
+        # select features as selected in constructor
+        return self.fs_function(dataset, labels, max_features)
+
+    def get_subspace(
+        self, dataset: np.array, labels: np.array, max_features: int
+    ) -> tuple:
+        """Re3turn a subspace of the selected dataset of max_features length.
+        Depending on hyperparameter
+
+        Parameters
+        ----------
+        dataset : np.array
+            array of samples (# samples, # features)
+        labels : np.array
+            labels of the dataset
+        max_features : int
+            number of features to form the subspace
+
+        Returns
+        -------
+        tuple
+            tuple with the dataset with only the features selected  and the
+            indices of the features selected
+        """
+        indices = self._get_subspaces_set(dataset, labels, max_features)
+        return dataset[:, indices], indices
+
+    def _impurity(self, data: np.array, y: np.array) -> np.array:
+        """return column of dataset to be taken into account to split dataset
+
+        Parameters
+        ----------
+        data : np.array
+            distances to hyper plane of every class
+        y : np.array
+            vector of labels (classes)
+
+        Returns
+        -------
+        np.array
+            column of dataset to be taken into account to split dataset
+        """
+        max_gain = 0
+        selected = -1
+        for col in range(data.shape[1]):
+            tup = y[data[:, col] > 0]
+            tdn = y[data[:, col] <= 0]
+            info_gain = self.information_gain(y, tup, tdn)
+            if info_gain > max_gain:
+                selected = col
+                max_gain = info_gain
+        return selected
+
+    @staticmethod
+    def _max_samples(data: np.array, y: np.array) -> np.array:
+        """return column of dataset to be taken into account to split dataset
+
+        Parameters
+        ----------
+        data : np.array
+            distances to hyper plane of every class
+        y : np.array
+            column of dataset to be taken into account to split dataset
+
+        Returns
+        -------
+        np.array
+            column of dataset to be taken into account to split dataset
+        """
+        # select the class with max number of samples
+        _, samples = np.unique(y, return_counts=True)
+        return np.argmax(samples)
+
+    def partition(self, samples: np.array, node: Snode, train: bool):
+        """Set the criteria to split arrays. Compute the indices of the samples
+        that should go to one side of the tree (up)
+
+        Parameters
+        ----------
+        samples : np.array
+            array of samples (# samples, # features)
+        node : Snode
+            Node of the tree where partition is going to be made
+        train : bool
+            Train time - True / Test time - False
+        """
+        # data contains the distances of every sample to every class hyperplane
+        # array of (m, nc) nc = # classes
+        data = self._distances(node, samples)
+        if data.shape[0] < self._min_samples_split:
+            # there aren't enough samples to split
+            self._up = np.ones((data.shape[0]), dtype=bool)
+            return
+        if data.ndim > 1:
+            # split criteria for multiclass
+            # Convert data to a (m, 1) array selecting values for samples
+            if train:
+                # in train time we have to compute the column to take into
+                # account to split the dataset
+                col = self.decision_criteria(data, node._y)
+                node.set_partition_column(col)
+            else:
+                # in predcit time just use the column computed in train time
+                # is taking the classifier of class <col>
+                col = node.get_partition_column()
+            if col == -1:
+                # No partition is producing information gain
+                data = np.ones(data.shape)
+            data = data[:, col]
+        self._up = data > 0
+
+    def part(self, origin: np.array) -> list:
+        """Split an array in two based on indices (self._up) and its complement
+        partition has to be called first to establish up indices
+
+        Parameters
+        ----------
+        origin : np.array
+            dataset to split
+
+        Returns
+        -------
+        list
+            list with two splits of the array
+        """
+        down = ~self._up
+        return [
+            origin[self._up] if any(self._up) else None,
+            origin[down] if any(down) else None,
+        ]
+
+    def _distances(self, node: Snode, data: np.ndarray) -> np.array:
+        """Compute distances of the samples to the hyperplane of the node
+
+        Parameters
+        ----------
+        node : Snode
+            node containing the svm classifier
+        data : np.ndarray
+            samples to compute distance to hyperplane
+
+        Returns
+        -------
+        np.array
+            array of shape (m, nc) with the distances of every sample to
+            the hyperplane of every class. nc = # of classes
+        """
+        X_transformed = data[:, node._features]
+        if self._normalize:
+            X_transformed = node._scaler.transform(X_transformed)
+        return node._clf.decision_function(X_transformed)

stree/Strees.py

@@ -1,311 +1,584 @@
-'''
-__author__ = "Ricardo Montañana Gómez"
-__copyright__ = "Copyright 2020, Ricardo Montañana Gómez"
-__license__ = "MIT"
-__version__ = "0.9"
-Build an oblique tree classifier based on SVM Trees
-Uses LinearSVC
-'''
-
-import typing
-import os
+"""
+Oblique decision tree classifier based on SVM nodes
+"""
 
+import numbers
+import random
+from typing import Optional
 import numpy as np
 from sklearn.base import BaseEstimator, ClassifierMixin
-from sklearn.svm import LinearSVC
-from sklearn.utils.validation import check_X_y, check_array, check_is_fitted
+from sklearn.svm import SVC, LinearSVC
+from sklearn.preprocessing import StandardScaler
+from sklearn.utils.multiclass import check_classification_targets
+from sklearn.utils.validation import (
+    check_X_y,
+    check_array,
+    check_is_fitted,
+    _check_sample_weight,
+)
+from .Splitter import Splitter, Snode, Siterator
+from ._version import __version__
 
-class Snode:
-    def __init__(self, clf: LinearSVC, X: np.ndarray, y: np.ndarray, title: str):
-        self._clf = clf
-        self._vector = None if clf is None else clf.coef_
-        self._interceptor = 0. if clf is None else clf.intercept_
-        self._title = title
-        self._belief = 0.  # belief of the prediction in a leaf node based on samples
-        # Only store dataset in Testing 
-        self._X = X if os.environ.get('TESTING', 'NS') != 'NS' else None
-        self._y = y
-        self._down = None
-        self._up = None
-        self._class = None
-
-    @classmethod
-    def copy(cls, node: 'Snode') -> 'Snode':
-        return cls(node._clf, node._X, node._y, node._title)
-
-    def set_down(self, son):
-        self._down = son
-
-    def set_up(self, son):
-        self._up = son
-
-    def is_leaf(self) -> bool:
-        return self._up is None and self._down is None
-
-    def get_down(self) -> 'Snode':
-        return self._down
-
-    def get_up(self) -> 'Snode':
-        return self._up
-
-    def make_predictor(self):
-        """Compute the class of the predictor and its belief based on the subdataset of the node
-        only if it is a leaf
-        """
-        if not self.is_leaf():
-            return
-        classes, card = np.unique(self._y, return_counts=True)
-        if len(classes) > 1:
-            max_card = max(card)
-            min_card = min(card)
-            try:
-                self._belief = max_card / (max_card + min_card)
-            except:
-                self._belief = 0.
-            self._class = classes[card == max_card][0]
-        else:
-            self._belief = 1
-            self._class = classes[0]
-
-    def __str__(self) -> str:
-        if self.is_leaf():
-            return f"{self._title} - Leaf class={self._class} belief={self._belief:.6f} counts={np.unique(self._y, return_counts=True)}"
-        else:
-            return f"{self._title}"
-
-
-class Siterator:
-    """Stree preorder iterator
-    """
-
-    def __init__(self, tree: Snode):
-        self._stack = []
-        self._push(tree)
-
-    def __iter__(self):
-        return self
-
-    def _push(self, node: Snode):
-        if node is not None:
-            self._stack.append(node)
-
-    def __next__(self) -> Snode:
-        if len(self._stack) == 0:
-            raise StopIteration()
-        node = self._stack.pop()
-        self._push(node.get_up())
-        self._push(node.get_down())
-        return node
 
 class Stree(BaseEstimator, ClassifierMixin):
     """
+    Estimator that is based on binary trees of svm nodes
+    can deal with sample_weights in predict, used in boosting sklearn methods
+    inheriting from BaseEstimator implements get_params and set_params methods
+    inheriting from ClassifierMixin implement the attribute _estimator_type
+    with "classifier" as value
+
+    Parameters
+    ----------
+    C : float, optional
+        Regularization parameter. The strength of the regularization is
+        inversely proportional to C. Must be strictly positive., by default 1.0
+    kernel : str, optional
+        Specifies the kernel type to be used in the algorithm. It must be one
+        of ‘liblinear’, ‘linear’, ‘poly’ or ‘rbf’. liblinear uses
+        [liblinear](https://www.csie.ntu.edu.tw/~cjlin/liblinear/) library and
+        the rest uses [libsvm](https://www.csie.ntu.edu.tw/~cjlin/libsvm/)
+        library through scikit-learn library, by default "linear"
+    max_iter : int, optional
+        Hard limit on iterations within solver, or -1 for no limit., by default
+        1e5
+    random_state : int, optional
+        Controls the pseudo random number generation for shuffling the data for
+        probability estimates. Ignored when probability is False.Pass an int
+        for reproducible output across multiple function calls, by
+        default None
+    max_depth : int, optional
+        Specifies the maximum depth of the tree, by default None
+    tol : float, optional
+        Tolerance for stopping, by default 1e-4
+    degree : int, optional
+        Degree of the polynomial kernel function (‘poly’). Ignored by all other
+        kernels., by default 3
+    gamma : str, optional
+        Kernel coefficient for ‘rbf’, ‘poly’ and ‘sigmoid’.if gamma='scale'
+        (default) is passed then it uses 1 / (n_features * X.var()) as value
+        of gamma,if ‘auto’, uses 1 / n_features., by default "scale"
+    split_criteria : str, optional
+        Decides (just in case of a multi class classification) which column
+        (class) use to split the dataset in a node. max_samples is
+        incompatible with 'ovo' multiclass_strategy, by default "impurity"
+    criterion : str, optional
+        The function to measure the quality of a split (only used if
+        max_features != num_features). Supported criteria are “gini” for the
+        Gini impurity and “entropy” for the information gain., by default
+        "entropy"
+    min_samples_split : int, optional
+        The minimum number of samples required to split an internal node. 0
+        (default) for any, by default 0
+    max_features : optional
+        The number of features to consider when looking for the split: If int,
+        then consider max_features features at each split. If float, then
+        max_features is a fraction and int(max_features * n_features) features
+        are considered at each split. If “auto”, then max_features=
+        sqrt(n_features). If “sqrt”, then max_features=sqrt(n_features). If
+        “log2”, then max_features=log2(n_features). If None, then max_features=
+        n_features., by default None
+    splitter : str, optional
+        The strategy used to choose the feature set at each node (only used if
+        max_features < num_features). Supported strategies are: “best”: sklearn
+        SelectKBest algorithm is used in every node to choose the max_features
+        best features. “random”: The algorithm generates 5 candidates and
+        choose the best (max. info. gain) of them. “trandom”: The algorithm
+        generates only one random combination. "mutual": Chooses the best
+        features w.r.t. their mutual info with the label. "cfs": Apply
+        Correlation-based Feature Selection. "fcbf": Apply Fast Correlation-
+        Based , by default "random"
+    multiclass_strategy : str, optional
+        Strategy to use with multiclass datasets, "ovo": one versus one. "ovr":
+        one versus rest, by default "ovo"
+    normalize : bool, optional
+        If standardization of features should be applied on each node with the
+        samples that reach it , by default False
+
+    Attributes
+    ----------
+    classes_ : ndarray of shape (n_classes,)
+        The classes labels.
+
+    n_classes_ : int
+        The number of classes
+
+    n_iter_ : int
+        Max number of iterations in classifier
+
+    depth_ : int
+        Max depht of the tree
+
+    n_features_ : int
+        The number of features when ``fit`` is performed.
+
+    n_features_in_ : int
+        Number of features seen during :term:`fit`.
+
+    max_features_ : int
+        Number of features to use in hyperplane computation
+
+    tree_ : Node
+        root of the tree
+
+    X_ : ndarray
+        points to the input dataset
+
+    y_ : ndarray
+        points to the input labels
+
+    References
+    ----------
+    R. Montañana, J. A. Gámez, J. M. Puerta, "STree: a single multi-class
+    oblique decision tree based on support vector machines.", 2021 LNAI 12882
+
+
     """
 
-    def __init__(self, C: float = 1.0, max_iter: int = 1000, random_state: int = 0, use_predictions: bool = False):
-        self._max_iter = max_iter
-        self._C = C
-        self._random_state = random_state
-        self._tree = None
-        self.__folder = 'data/'
-        self.__use_predictions = use_predictions
-        self.__trained = False
-        self.__proba = False
+    def __init__(
+        self,
+        C: float = 1.0,
+        kernel: str = "linear",
+        max_iter: int = 1e5,
+        random_state: int = None,
+        max_depth: int = None,
+        tol: float = 1e-4,
+        degree: int = 3,
+        gamma="scale",
+        split_criteria: str = "impurity",
+        criterion: str = "entropy",
+        min_samples_split: int = 0,
+        max_features=None,
+        splitter: str = "random",
+        multiclass_strategy: str = "ovo",
+        normalize: bool = False,
+    ):
 
-    def get_params(self, deep=True):
-        """Get dict with hyperparameters and its values to accomplish sklearn rules
+        self.max_iter = max_iter
+        self.C = C
+        self.kernel = kernel
+        self.random_state = random_state
+        self.max_depth = max_depth
+        self.tol = tol
+        self.gamma = gamma
+        self.degree = degree
+        self.min_samples_split = min_samples_split
+        self.split_criteria = split_criteria
+        self.max_features = max_features
+        self.criterion = criterion
+        self.splitter = splitter
+        self.normalize = normalize
+        self.multiclass_strategy = multiclass_strategy
+
+    @staticmethod
+    def version() -> str:
+        """Return the version of the package."""
+        return __version__
+
+    def _more_tags(self) -> dict:
+        """Required by sklearn to supply features of the classifier
+        make mandatory the labels array
+
+        :return: the tag required
+        :rtype: dict
         """
-        return {"C": self._C, "random_state": self._random_state, 'max_iter': self._max_iter}
+        return {"requires_y": True}
 
-    def set_params(self, **parameters):
-        """Set hyperparmeters as specified by sklearn, needed in Gridsearchs
+    def fit(
+        self, X: np.ndarray, y: np.ndarray, sample_weight: np.array = None
+    ) -> "Stree":
+        """Build the tree based on the dataset of samples and its labels
+
+        Returns
+        -------
+        Stree
+            itself to be able to chain actions: fit().predict() ...
+
+        Raises
+        ------
+        ValueError
+            if C < 0
+        ValueError
+            if max_depth < 1
+        ValueError
+            if all samples have 0 or negative weights
         """
-        for parameter, value in parameters.items():
-            setattr(self, parameter, value)
-        return self
-
-    def _linear_function(self, data: np.array, node: Snode) -> np.array:
-        coef = node._vector[0, :].reshape(-1, data.shape[1])
-        return data.dot(coef.T) + node._interceptor[0]
-
-    def _split_data(self, node: Snode, data: np.ndarray, indices: np.ndarray) -> list:
-        if self.__use_predictions:
-            yp = node._clf.predict(data)
-            down = (yp == 1).reshape(-1, 1)
-            res = np.expand_dims(node._clf.decision_function(data), 1)
-        else:
-            # doesn't work with multiclass as each sample has to do inner product with its own coeficients
-            # computes positition of every sample is w.r.t. the hyperplane
-            res = self._linear_function(data, node)
-            down = res > 0
-        up = ~down
-        data_down = data[down[:, 0]] if any(down) else None
-        indices_down = indices[down[:, 0]] if any(down) else None
-        res_down = res[down[:, 0]] if any(down) else None
-        data_up = data[up[:, 0]] if any(up) else None
-        indices_up = indices[up[:, 0]] if any(up) else None
-        res_up = res[up[:, 0]] if any(up) else None
-        return [data_up, indices_up, data_down, indices_down, res_up, res_down]
-
-    def fit(self, X: np.ndarray, y: np.ndarray, title: str = 'root') -> 'Stree':
-        X, y = check_X_y(X, y.ravel())
+        # Check parameters are Ok.
+        if self.C < 0:
+            raise ValueError(
+                f"Penalty term must be positive... got (C={self.C:f})"
+            )
+        self.__max_depth = (
+            np.iinfo(np.int32).max
+            if self.max_depth is None
+            else self.max_depth
+        )
+        if self.__max_depth < 1:
+            raise ValueError(
+                f"Maximum depth has to be greater than 1... got (max_depth=\
+                    {self.max_depth})"
+            )
+        if self.multiclass_strategy not in ["ovr", "ovo"]:
+            raise ValueError(
+                "mutliclass_strategy has to be either ovr or ovo"
+                f" but got {self.multiclass_strategy}"
+            )
+        if self.multiclass_strategy == "ovo":
+            if self.kernel == "liblinear":
+                raise ValueError(
+                    "The kernel liblinear is incompatible with ovo "
+                    "multiclass_strategy"
+                )
+            if self.split_criteria == "max_samples":
+                raise ValueError(
+                    "The multiclass_strategy 'ovo' is incompatible with "
+                    "split_criteria 'max_samples'"
+                )
+        kernels = ["liblinear", "linear", "rbf", "poly", "sigmoid"]
+        if self.kernel not in kernels:
+            raise ValueError(f"Kernel {self.kernel} not in {kernels}")
+        check_classification_targets(y)
+        X, y = check_X_y(X, y)
+        sample_weight = _check_sample_weight(
+            sample_weight, X, dtype=np.float64
+        )
+        if not any(sample_weight):
+            raise ValueError(
+                "Invalid input - all samples have zero or negative weights."
+            )
+        check_classification_targets(y)
+        # Initialize computed parameters
+        self.splitter_ = Splitter(
+            clf=self._build_clf(),
+            criterion=self.criterion,
+            feature_select=self.splitter,
+            criteria=self.split_criteria,
+            random_state=self.random_state,
+            min_samples_split=self.min_samples_split,
+            normalize=self.normalize,
+        )
+        if self.random_state is not None:
+            random.seed(self.random_state)
+        self.classes_, y = np.unique(y, return_inverse=True)
+        self.n_classes_ = self.classes_.shape[0]
+        self.n_iter_ = self.max_iter
+        self.depth_ = 0
+        self.n_features_ = X.shape[1]
         self.n_features_in_ = X.shape[1]
-        self._tree = self.train(X, y.ravel(), title)
-        self._build_predictor()
-        self.__trained = True
+        self.max_features_ = self._initialize_max_features()
+        self.tree_ = self._train(X, y, sample_weight, 1, "root")
+        self.X_ = X
+        self.y_ = y
         return self
 
-    def _build_predictor(self):
-        """Process the leaves to make them predictors
+    def _train(
+        self,
+        X: np.ndarray,
+        y: np.ndarray,
+        sample_weight: np.ndarray,
+        depth: int,
+        title: str,
+    ) -> Optional[Snode]:
+        """Recursive function to split the original dataset into predictor
+        nodes (leaves)
+
+        Parameters
+        ----------
+        X : np.ndarray
+            samples dataset
+        y : np.ndarray
+            samples labels
+        sample_weight : np.ndarray
+            weight of samples. Rescale C per sample.
+        depth : int
+            actual depth in the tree
+        title : str
+            description of the node
+
+        Returns
+        -------
+        Optional[Snode]
+            binary tree
         """
-
-        def run_tree(node: Snode):
-            if node.is_leaf():
-                node.make_predictor()
-                return
-            run_tree(node.get_down())
-            run_tree(node.get_up())
-
-        run_tree(self._tree)
-
-    def train(self, X: np.ndarray, y: np.ndarray, title: str = 'root') -> Snode:
+        if depth > self.__max_depth:
+            return None
+        # Mask samples with 0 weight
+        if any(sample_weight == 0):
+            indices_zero = sample_weight == 0
+            X = X[~indices_zero, :]
+            y = y[~indices_zero]
+            sample_weight = sample_weight[~indices_zero]
+        self.depth_ = max(depth, self.depth_)
+        scaler = StandardScaler()
+        node = Snode(None, X, y, X.shape[1], 0.0, title, sample_weight, scaler)
         if np.unique(y).shape[0] == 1:
             # only 1 class => pure dataset
-            return Snode(None, X, y, title + ', <pure>')
+            node.set_title(title + ", <pure>")
+            node.make_predictor(self.n_classes_)
+            return node
         # Train the model
-        clf = LinearSVC(max_iter=self._max_iter, C=self._C,
-                        random_state=self._random_state)
-        clf.fit(X, y)
-        tree = Snode(clf, X, y, title)
-        X_U, y_u, X_D, y_d, _, _ = self._split_data(tree, X, y)
+        clf = self._build_clf()
+        Xs, features = self.splitter_.get_subspace(X, y, self.max_features_)
+        if self.normalize:
+            scaler.fit(Xs)
+            Xs = scaler.transform(Xs)
+        clf.fit(Xs, y, sample_weight=sample_weight)
+        node.set_impurity(self.splitter_.partition_impurity(y))
+        node.set_classifier(clf)
+        node.set_features(features)
+        self.splitter_.partition(X, node, True)
+        X_U, X_D = self.splitter_.part(X)
+        y_u, y_d = self.splitter_.part(y)
+        sw_u, sw_d = self.splitter_.part(sample_weight)
         if X_U is None or X_D is None:
             # didn't part anything
-            return Snode(clf, X, y, title + ', <cgaf>')
-        tree.set_up(self.train(X_U, y_u, title + ' - Up'))
-        tree.set_down(self.train(X_D, y_d, title + ' - Down'))
-        return tree
+            node.set_title(title + ", <cgaf>")
+            node.make_predictor(self.n_classes_)
+            return node
+        node.set_up(
+            self._train(X_U, y_u, sw_u, depth + 1, title + f" - Up({depth+1})")
+        )
+        node.set_down(
+            self._train(
+                X_D, y_d, sw_d, depth + 1, title + f" - Down({depth+1})"
+            )
+        )
+        return node
 
-    def _reorder_results(self, y: np.array, indices: np.array) -> np.array:
-        y_ordered = np.zeros(y.shape, dtype=int if y.ndim == 1 else float)
-        indices = indices.astype(int)
-        for i, index in enumerate(indices):
-            y_ordered[index] = y[i]
-        return y_ordered
+    def _build_clf(self):
+        """Build the right classifier for the node"""
+        return (
+            LinearSVC(
+                max_iter=self.max_iter,
+                random_state=self.random_state,
+                C=self.C,
+                tol=self.tol,
+            )
+            if self.kernel == "liblinear"
+            else SVC(
+                kernel=self.kernel,
+                max_iter=self.max_iter,
+                tol=self.tol,
+                C=self.C,
+                gamma=self.gamma,
+                degree=self.degree,
+                random_state=self.random_state,
+                decision_function_shape=self.multiclass_strategy,
+            )
+        )
 
-    def predict(self, X: np.array) -> np.array:
-        def predict_class(xp: np.array, indices: np.array, node: Snode) -> np.array:
+    def __predict_class(self, X: np.array) -> np.array:
+        """Compute the predicted class for the samples in X. Returns the number
+        of samples of each class in the corresponding leaf node.
+
+        Parameters
+        ----------
+        X : np.array
+            Array of samples
+
+        Returns
+        -------
+        np.array
+            Array of shape (n_samples, n_classes) with the number of samples
+            of each class in the corresponding leaf node
+        """
+
+        def compute_prediction(xp, indices, node):
             if xp is None:
-                return [], []
+                return
             if node.is_leaf():
-                # set a class for every sample in dataset
-                prediction = np.full((xp.shape[0], 1), node._class)
-                return prediction, indices
-            u, i_u, d, i_d, _, _ = self._split_data(node, xp, indices)
-            k, l = predict_class(d, i_d, node.get_down())
-            m, n = predict_class(u, i_u, node.get_up())
-            return np.append(k, m), np.append(l, n)
+                # set a class for indices
+                result[indices] = node._proba
+                return
+            self.splitter_.partition(xp, node, train=False)
+            x_u, x_d = self.splitter_.part(xp)
+            i_u, i_d = self.splitter_.part(indices)
+            compute_prediction(x_u, i_u, node.get_up())
+            compute_prediction(x_d, i_d, node.get_down())
 
-        # sklearn check
-        check_is_fitted(self)
+        # setup prediction & make it happen
+        result = np.zeros((X.shape[0], self.n_classes_))
+        indices = np.arange(X.shape[0])
+        compute_prediction(X, indices, self.tree_)
+        return result
+
+    def check_predict(self, X) -> np.array:
+        """Checks predict and predict_proba preconditions. If input X is not an
+        np.array convert it to one.
+
+        Parameters
+        ----------
+        X : np.ndarray
+            Array of samples
+
+        Returns
+        -------
+        np.array
+            Array of samples
+
+        Raises
+        ------
+        ValueError
+            If number of features of X is different of the number of features
+            in training data
+        """
+        check_is_fitted(self, ["tree_"])
         # Input validation
         X = check_array(X)
-        # setup prediction & make it happen
-        indices = np.arange(X.shape[0])
-        return self._reorder_results(*predict_class(X, indices, self._tree))
+        if X.shape[1] != self.n_features_:
+            raise ValueError(
+                f"Expected {self.n_features_} features but got "
+                f"({X.shape[1]})"
+            )
+        return X
 
     def predict_proba(self, X: np.array) -> np.array:
-        """Computes an approximation of the probability of samples belonging to class 1 
-        (nothing more, nothing less)
+        """Predict class probabilities of the input samples X.
 
-        :param X: dataset
-        :type X: np.array
+        The predicted class probability is the fraction of samples of the same
+        class in a leaf.
+
+        Parameters
+        ----------
+        X : dataset of samples.
+
+        Returns
+        -------
+        proba : array of shape (n_samples, n_classes)
+            The class probabilities of the input samples.
+
+        Raises
+        ------
+        ValueError
+            if dataset with inconsistent number of features
+        NotFittedError
+            if model is not fitted
         """
 
-        def predict_class(xp: np.array, indices: np.array, dist: np.array, node: Snode) -> np.array:
-            """Run the tree to compute predictions
+        X = self.check_predict(X)
+        # return # of samples of each class in leaf node
+        values = self.__predict_class(X)
+        normalizer = values.sum(axis=1)[:, np.newaxis]
+        normalizer[normalizer == 0.0] = 1.0
+        return values / normalizer
 
-            :param xp: subdataset of samples
-            :type xp: np.array
-            :param indices: indices of subdataset samples to rebuild original order
-            :type indices: np.array
-            :param dist: distances of every sample to the hyperplane or the father node
-            :type dist: np.array
-            :param node: node of the leaf with the class
-            :type node: Snode
-            :return: array of labels and distances, array of indices
-            :rtype: np.array
-            """
-            if xp is None:
-                return [], []
+    def predict(self, X: np.array) -> np.array:
+        """Predict labels for each sample in dataset passed
+
+        Parameters
+        ----------
+        X : np.array
+            dataset of samples
+
+        Returns
+        -------
+        np.array
+            array of labels
+
+        Raises
+        ------
+        ValueError
+            if dataset with inconsistent number of features
+        NotFittedError
+            if model is not fitted
+        """
+        X = self.check_predict(X)
+        return self.classes_[np.argmax(self.__predict_class(X), axis=1)]
+
+    def nodes_leaves(self) -> tuple:
+        """Compute the number of nodes and leaves in the built tree
+
+        Returns
+        -------
+        [tuple]
+            tuple with the number of nodes and the number of leaves
+        """
+        nodes = 0
+        leaves = 0
+        for node in self:
+            nodes += 1
             if node.is_leaf():
-                # set a class for every sample in dataset
-                prediction = np.full((xp.shape[0], 1), node._class)
-                prediction_proba = dist
-                return np.append(prediction, prediction_proba, axis=1), indices
-            u, i_u, d, i_d, r_u, r_d = self._split_data(node, xp, indices)
-            k, l = predict_class(d, i_d, r_d, node.get_down())
-            m, n = predict_class(u, i_u, r_u, node.get_up())
-            return np.append(k, m), np.append(l, n)
+                leaves += 1
+        return nodes, leaves
 
-        # sklearn check
-        check_is_fitted(self)
-        # Input validation
-        X = check_array(X)
-        # setup prediction & make it happen
-        indices = np.arange(X.shape[0])
-        result, indices = predict_class(X, indices, [], self._tree)
-        result = result.reshape(X.shape[0], 2)
-        # Turn distances to hyperplane into probabilities based on fitting distances
-        # of samples to its hyperplane that classified them, to the sigmoid function
-        result[:, 1] = 1 / (1 + np.exp(-result[:, 1]))
-        return self._reorder_results(result, indices)
+    def __iter__(self) -> Siterator:
+        """Create an iterator to be able to visit the nodes of the tree in
+        preorder, can make a list with all the nodes in preorder
 
-    def score(self, X: np.array, y: np.array) -> float:
-        """Return accuracy
+        Returns
+        -------
+        Siterator
+            an iterator, can for i in... and list(...)
         """
-        if not self.__trained:
-            self.fit(X, y)
-        yp = self.predict(X).reshape(y.shape)
-        right = (yp == y).astype(int)
-        return np.sum(right) / len(y)
+        try:
+            tree = self.tree_
+        except AttributeError:
+            tree = None
+        return Siterator(tree)
 
-    def __iter__(self):
-        return Siterator(self._tree)
+    def graph(self, title="") -> str:
+        """Graphviz code representing the tree
 
-    def __str__(self) -> str:
-        output = ''
-        for i in self:
-            output += str(i) + '\n'
+        Returns
+        -------
+        str
+            graphviz code
+        """
+        output = (
+            "digraph STree {\nlabel=<STree "
+            f"{title}>\nfontsize=30\nfontcolor=blue\nlabelloc=t\n"
+        )
+        for node in self:
+            output += node.graph()
+        output += "}\n"
         return output
 
-    def _save_datasets(self, tree: Snode, catalog: typing.TextIO, number: int):
-        """Save the dataset of the node in a csv file
+    def __str__(self) -> str:
+        """String representation of the tree
 
-        :param tree: node with data to save
-        :type tree: Snode
-        :param catalog: catalog file handler
-        :type catalog: typing.TextIO
-        :param number: sequential number for the generated file name
-        :type number: int
+        Returns
+        -------
+        str
+            description of nodes in the tree in preorder
         """
-        data = np.append(tree._X, tree._y.reshape(-1, 1), axis=1)
-        name = f"{self.__folder}dataset{number}.csv"
-        np.savetxt(name, data, delimiter=",")
-        catalog.write(f"{name}, - {str(tree)}")
-        if tree.is_leaf():
-            return
-        self._save_datasets(tree.get_down(), catalog, number + 1)
-        self._save_datasets(tree.get_up(), catalog, number + 2)
-
-    def get_catalog_name(self):
-        return self.__folder + "catalog.txt"
-
-    def save_sub_datasets(self):
-        """Save the every dataset stored in the tree to check with manual classifier
-        """
-        if not os.path.isdir(self.__folder):
-            os.mkdir(self.__folder)
-        with open(self.get_catalog_name(), 'w', encoding='utf-8') as catalog:
-            self._save_datasets(self._tree, catalog, 1)
-
-
+        output = ""
+        for i in self:
+            output += str(i) + "\n"
+        return output
 
+    def _initialize_max_features(self) -> int:
+        if isinstance(self.max_features, str):
+            if self.max_features == "auto":
+                max_features = max(1, int(np.sqrt(self.n_features_)))
+            elif self.max_features == "sqrt":
+                max_features = max(1, int(np.sqrt(self.n_features_)))
+            elif self.max_features == "log2":
+                max_features = max(1, int(np.log2(self.n_features_)))
+            else:
+                raise ValueError(
+                    "Invalid value for max_features. "
+                    "Allowed string values are 'auto', "
+                    "'sqrt' or 'log2'."
+                )
+        elif self.max_features is None:
+            max_features = self.n_features_
+        elif isinstance(self.max_features, numbers.Integral):
+            if self.max_features > self.n_features_:
+                raise ValueError(
+                    "Invalid value for max_features. "
+                    "It can not be greater than number of features "
+                    f"({self.n_features_})"
+                )
+            max_features = self.max_features
+        else:  # float
+            if self.max_features > 0.0:
+                max_features = max(
+                    1, int(self.max_features * self.n_features_)
+                )
+            else:
+                raise ValueError(
+                    "Invalid value for max_features."
+                    "Allowed float must be in range (0, 1] "
+                    f"got ({self.max_features})"
+                )
+        return max_features

stree/Strees_grapher.py

@@ -1,184 +0,0 @@
-'''
-__author__ = "Ricardo Montañana Gómez"
-__copyright__ = "Copyright 2020, Ricardo Montañana Gómez"
-__license__ = "MIT"
-__version__ = "0.9"
-Plot 3D views of nodes in Stree
-'''
-
-import os
-
-import matplotlib.pyplot as plt
-import numpy as np
-from sklearn.decomposition import PCA
-from mpl_toolkits.mplot3d import Axes3D
-
-from .Strees import Stree, Snode, Siterator
-
-class Snode_graph(Snode):
-
-    def __init__(self, node: Stree):
-        self._plot_size = (8, 8)
-        self._xlimits = (None, None)
-        self._ylimits = (None, None)
-        self._zlimits = (None, None)
-        n = Snode.copy(node)
-        super().__init__(n._clf, n._X, n._y, n._title)
-
-    def set_plot_size(self, size: tuple):
-        self._plot_size = size
-
-    def _is_pure(self) -> bool:
-        """is considered pure a leaf node with one label
-        """
-        if self.is_leaf():
-            return self._belief == 1.
-        return False
-
-    def set_axis_limits(self, limits: tuple):
-        self._xlimits = limits[0]
-        self._ylimits = limits[1]
-        self._zlimits = limits[2]
-
-    def _set_graphics_axis(self, ax: Axes3D):
-        ax.set_xlim(self._xlimits)
-        ax.set_ylim(self._ylimits)
-        ax.set_zlim(self._zlimits)
-
-    def save_hyperplane(self, save_folder: str = './', save_prefix: str = '', save_seq: int = 1):
-        _, fig = self.plot_hyperplane()
-        name = f"{save_folder}{save_prefix}STnode{save_seq}.png"
-        fig.savefig(name, bbox_inches='tight')
-        plt.close(fig)
-
-    def _get_cmap(self):
-        cmap = 'jet'
-        if self._is_pure():
-            if self._class == 1:
-                cmap = 'jet_r'
-        return cmap
-
-    def _graph_title(self):
-        n_class, card = np.unique(self._y, return_counts=True)
-        return f"{self._title} {n_class} {card}"
-
-    def plot_hyperplane(self, plot_distribution: bool = True):
-        fig = plt.figure(figsize=self._plot_size)
-        ax = fig.add_subplot(1, 1, 1, projection='3d')
-        if not self._is_pure():
-            # Can't plot hyperplane of leaves with one label because it hasn't classiffier
-            # get the splitting hyperplane
-            def hyperplane(x, y): return (-self._interceptor - self._vector[0][0] * x
-                                          - self._vector[0][1] * y) / self._vector[0][2]
-
-            tmpx = np.linspace(self._X[:, 0].min(), self._X[:, 0].max())
-            tmpy = np.linspace(self._X[:, 1].min(), self._X[:, 1].max())
-            xx, yy = np.meshgrid(tmpx, tmpy)
-            ax.plot_surface(xx, yy, hyperplane(xx, yy), alpha=.5, antialiased=True,
-                            rstride=1, cstride=1, cmap='seismic')
-            self._set_graphics_axis(ax)
-        if plot_distribution:
-            self.plot_distribution(ax)
-        else:
-            plt.title(self._graph_title())
-            plt.show()
-        return ax, fig
-
-    def plot_distribution(self, ax: Axes3D = None):
-        if ax is None:
-            fig = plt.figure(figsize=self._plot_size)
-            ax = fig.add_subplot(1, 1, 1, projection='3d')
-        plt.title(self._graph_title())
-        cmap = self._get_cmap()
-        ax.scatter(self._X[:, 0], self._X[:, 1],
-                   self._X[:, 2], c=self._y, cmap=cmap)
-        ax.set_xlabel('X0')
-        ax.set_ylabel('X1')
-        ax.set_zlabel('X2')
-        plt.show()
-
-class Stree_grapher(Stree):
-    """Build 3d graphs of any dataset, if it's more than 3 features PCA shall
-    make its magic
-    """
-
-    def __init__(self, params: dict):
-        self._plot_size = (8, 8)
-        self._tree_gr = None
-        # make Snode store X's
-        os.environ['TESTING'] = '1'
-        self._fitted = False
-        self._pca = None
-        super().__init__(**params)
-
-    def __del__(self):
-        try:
-            os.environ.pop('TESTING')
-        except:
-            pass
-        plt.close('all')
-
-    def _copy_tree(self, node: Snode) -> Snode_graph:
-        mirror = Snode_graph(node)
-        # clone node
-        mirror._class = node._class
-        mirror._belief = node._belief
-        if node.get_down() is not None:
-            mirror.set_down(self._copy_tree(node.get_down()))
-        if node.get_up() is not None:
-            mirror.set_up(self._copy_tree(node.get_up()))
-        return mirror
-
-    def fit(self, X: np.array, y: np.array) -> Stree:
-        """Fit the Stree and copy the tree in a Snode_graph tree
-
-        :param X: Dataset
-        :type X: np.array
-        :param y: Labels
-        :type y: np.array
-        :return: Stree model
-        :rtype: Stree
-        """
-        if X.shape[1] != 3:
-            self._pca = PCA(n_components=3)
-            X = self._pca.fit_transform(X)
-        res = super().fit(X, y)
-        self._tree_gr = self._copy_tree(self._tree)
-        self._fitted = True
-        return res
-
-    def score(self, X: np.array, y: np.array) -> float:
-        self._check_fitted()
-        if X.shape[1] != 3:
-            X = self._pca.transform(X)
-        return super().score(X, y)
-
-    def _check_fitted(self):
-        if not self._fitted:
-            raise Exception('Have to fit the grapher first!')
-
-    def save_all(self, save_folder: str = './', save_prefix: str = ''):
-        """Save all the node plots in png format, each with a sequence number
-
-        :param save_folder: folder where the plots are saved, defaults to './'
-        :type save_folder: str, optional
-        """
-        self._check_fitted()
-        if not os.path.isdir(save_folder):
-            os.mkdir(save_folder)
-        seq = 1
-        for node in self:
-            node.save_hyperplane(save_folder=save_folder,
-                                 save_prefix=save_prefix, save_seq=seq)
-            seq += 1
-
-    def plot_all(self):
-        """Plots all the nodes
-        """
-        self._check_fitted()
-        for node in self:
-            node.plot_hyperplane()
-
-    def __iter__(self):
-        return Siterator(self._tree_gr)
-

stree/__init__.py

@@ -1,2 +1,8 @@
-from .Strees import Stree, Snode, Siterator
-from .Strees_grapher import Stree_grapher, Snode_graph
+from .Strees import Stree, Siterator
+
+__author__ = "Ricardo Montañana Gómez"
+__copyright__ = "Copyright 2020-2021, Ricardo Montañana Gómez"
+__license__ = "MIT License"
+__author_email__ = "ricardo.montanana@alu.uclm.es"
+
+__all__ = ["Stree", "Siterator"]

stree/_version.py

@@ -0,0 +1 @@
+__version__ = "1.3.0"

stree/tests/Snode_test.py

@@ -0,0 +1,129 @@
+import os
+import unittest
+import numpy as np
+from stree import Stree
+from stree.Splitter import Snode
+from .utils import load_dataset
+
+
+class Snode_test(unittest.TestCase):
+    def __init__(self, *args, **kwargs):
+        self._random_state = 1
+        self._clf = Stree(
+            random_state=self._random_state,
+            kernel="liblinear",
+            multiclass_strategy="ovr",
+        )
+        self._clf.fit(*load_dataset(self._random_state))
+        super().__init__(*args, **kwargs)
+
+    @classmethod
+    def setUp(cls):
+        os.environ["TESTING"] = "1"
+
+    def test_attributes_in_leaves(self):
+        """Check if the attributes in leaves have correct values so they form a
+        predictor
+        """
+
+        def check_leave(node: Snode):
+            if not node.is_leaf():
+                check_leave(node.get_down())
+                check_leave(node.get_up())
+                return
+            # Check Belief in leave
+            classes, card = np.unique(node._y, return_counts=True)
+            max_card = max(card)
+            min_card = min(card)
+            if len(classes) > 1:
+                belief = max_card / (max_card + min_card)
+            else:
+                belief = 1
+            self.assertEqual(belief, node._belief)
+            # Check Class
+            class_computed = classes[card == max_card]
+            self.assertEqual(class_computed, node._class)
+            # Check Partition column
+            self.assertEqual(node._partition_column, -1)
+
+        check_leave(self._clf.tree_)
+
+    def test_nodes_coefs(self):
+        """Check if the nodes of the tree have the right attributes filled"""
+
+        def run_tree(node: Snode):
+            if node._belief < 1:
+                # only exclude pure leaves
+                self.assertIsNotNone(node._clf)
+                self.assertIsNotNone(node._clf.coef_)
+            if node.is_leaf():
+                return
+            run_tree(node.get_up())
+            run_tree(node.get_down())
+
+        model = Stree(self._random_state)
+        model.fit(*load_dataset(self._random_state, 3, 4))
+        run_tree(model.tree_)
+
+    def test_make_predictor_on_leaf(self):
+        test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
+        test.make_predictor(2)
+        self.assertEqual(1, test._class)
+        self.assertEqual(0.75, test._belief)
+        self.assertEqual(-1, test._partition_column)
+        self.assertListEqual([1, 3], test._proba.tolist())
+
+    def test_make_predictor_on_not_leaf(self):
+        test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
+        test.set_up(Snode(None, [1], [1], [], 0.0, "another_test"))
+        test.make_predictor(2)
+        self.assertIsNone(test._class)
+        self.assertEqual(0, test._belief)
+        self.assertEqual(-1, test._partition_column)
+        self.assertEqual(-1, test.get_up()._partition_column)
+        self.assertIsNone(test._proba)
+
+    def test_make_predictor_on_leaf_bogus_data(self):
+        test = Snode(None, [1, 2, 3, 4], [], [], 0.0, "test")
+        test.make_predictor(2)
+        self.assertIsNone(test._class)
+        self.assertEqual(-1, test._partition_column)
+        self.assertListEqual([0, 0], test._proba.tolist())
+
+    def test_set_title(self):
+        test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
+        self.assertEqual("test", test.get_title())
+        test.set_title("another")
+        self.assertEqual("another", test.get_title())
+
+    def test_set_classifier(self):
+        test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
+        clf = Stree()
+        self.assertIsNone(test.get_classifier())
+        test.set_classifier(clf)
+        self.assertEqual(clf, test.get_classifier())
+
+    def test_set_impurity(self):
+        test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
+        self.assertEqual(0.0, test.get_impurity())
+        test.set_impurity(54.7)
+        self.assertEqual(54.7, test.get_impurity())
+
+    def test_set_features(self):
+        test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [0, 1], 0.0, "test")
+        self.assertListEqual([0, 1], test.get_features())
+        test.set_features([1, 2])
+        self.assertListEqual([1, 2], test.get_features())
+
+    def test_copy_node(self):
+        px = [1, 2, 3, 4]
+        py = [1]
+        test = Snode(Stree(), px, py, [], 0.0, "test")
+        computed = Snode.copy(test)
+        self.assertListEqual(computed._X, px)
+        self.assertListEqual(computed._y, py)
+        self.assertEqual("test", computed._title)
+        self.assertIsInstance(computed._clf, Stree)
+        self.assertEqual(test._partition_column, computed._partition_column)
+        self.assertEqual(test._sample_weight, computed._sample_weight)
+        self.assertEqual(test._scaler, computed._scaler)

stree/tests/Splitter_test.py

@@ -0,0 +1,312 @@
+import os
+import unittest
+import random
+
+import numpy as np
+from sklearn.svm import SVC
+from sklearn.datasets import load_wine, load_iris
+from stree.Splitter import Splitter
+from .utils import load_dataset, load_disc_dataset
+
+
+class Splitter_test(unittest.TestCase):
+    def __init__(self, *args, **kwargs):
+        self._random_state = 1
+        super().__init__(*args, **kwargs)
+
+    @staticmethod
+    def build(
+        clf=SVC,
+        min_samples_split=0,
+        feature_select="random",
+        criterion="gini",
+        criteria="max_samples",
+        random_state=None,
+    ):
+        return Splitter(
+            clf=clf(random_state=random_state, kernel="rbf"),
+            min_samples_split=min_samples_split,
+            feature_select=feature_select,
+            criterion=criterion,
+            criteria=criteria,
+            random_state=random_state,
+        )
+
+    @classmethod
+    def setUp(cls):
+        os.environ["TESTING"] = "1"
+
+    def test_init(self):
+        with self.assertRaises(ValueError):
+            self.build(criterion="duck")
+        with self.assertRaises(ValueError):
+            self.build(feature_select="duck")
+        with self.assertRaises(ValueError):
+            self.build(criteria="duck")
+        with self.assertRaises(ValueError):
+            _ = Splitter(clf=None)
+        for feature_select in ["best", "random"]:
+            for criterion in ["gini", "entropy"]:
+                for criteria in ["max_samples", "impurity"]:
+                    tcl = self.build(
+                        feature_select=feature_select,
+                        criterion=criterion,
+                        criteria=criteria,
+                    )
+                    self.assertEqual(feature_select, tcl._feature_select)
+                    self.assertEqual(criterion, tcl._criterion)
+                    self.assertEqual(criteria, tcl._criteria)
+
+    def test_gini(self):
+        expected_values = [
+            ([0, 1, 1, 1, 1, 1, 0, 0, 0, 1], 0.48),
+            ([0, 1, 1, 2, 2, 3, 4, 5, 3, 2, 1, 1], 0.7777777777777778),
+            ([0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 2, 2, 2], 0.520408163265306),
+            ([0, 0, 1, 1, 1, 1, 0, 0], 0.5),
+            ([0, 0, 1, 1, 2, 2, 3, 3], 0.75),
+            ([0, 0, 1, 1, 1, 1, 1, 1], 0.375),
+            ([0], 0),
+            ([1, 1, 1, 1], 0),
+        ]
+        for labels, expected in expected_values:
+            self.assertAlmostEqual(expected, Splitter._gini(labels))
+            tcl = self.build(criterion="gini")
+            self.assertAlmostEqual(expected, tcl.criterion_function(labels))
+
+    def test_entropy(self):
+        expected_values = [
+            ([0, 1, 1, 1, 1, 1, 0, 0, 0, 1], 0.9709505944546686),
+            ([0, 1, 1, 2, 2, 3, 4, 5, 3, 2, 1, 1], 0.9111886696810589),
+            ([0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 2, 2, 2], 0.8120406807940999),
+            ([0, 0, 1, 1, 1, 1, 0, 0], 1),
+            ([0, 0, 1, 1, 2, 2, 3, 3], 1),
+            ([0, 0, 1, 1, 1, 1, 1, 1], 0.8112781244591328),
+            ([1], 0),
+            ([0, 0, 0, 0], 0),
+        ]
+        for labels, expected in expected_values:
+            self.assertAlmostEqual(expected, Splitter._entropy(labels))
+            tcl = self.build(criterion="entropy")
+            self.assertAlmostEqual(expected, tcl.criterion_function(labels))
+
+    def test_information_gain(self):
+        expected_values = [
+            (
+                [0, 1, 1, 1, 1, 1],
+                [0, 0, 0, 1],
+                0.16333333333333333,
+                0.25642589168200297,
+            ),
+            (
+                [0, 1, 1, 2, 2, 3, 4, 5, 3, 2, 1, 1],
+                [5, 3, 2, 1, 1],
+                0.007381776239907684,
+                -0.03328610916207225,
+            ),
+            ([], [], 0.0, 0.0),
+            ([1], [], 0.0, 0.0),
+            ([], [1], 0.0, 0.0),
+            ([0, 0, 0, 0], [0, 0], 0.0, 0.0),
+            ([], [1, 1, 1, 2], 0.0, 0.0),
+            (None, [1, 2, 3], 0.0, 0.0),
+            ([1, 2, 3], None, 0.0, 0.0),
+        ]
+        for yu, yd, expected_gini, expected_entropy in expected_values:
+            yu = np.array(yu, dtype=np.int32) if yu is not None else None
+            yd = np.array(yd, dtype=np.int32) if yd is not None else None
+            if yu is not None and yd is not None:
+                complete = np.append(yu, yd)
+            elif yd is not None:
+                complete = yd
+            else:
+                complete = yu
+            tcl = self.build(criterion="gini")
+            computed = tcl.information_gain(complete, yu, yd)
+            self.assertAlmostEqual(expected_gini, computed)
+            tcl = self.build(criterion="entropy")
+            computed = tcl.information_gain(complete, yu, yd)
+            self.assertAlmostEqual(expected_entropy, computed)
+
+    def test_max_samples(self):
+        tcl = self.build(criteria="max_samples")
+        data = np.array(
+            [
+                [-0.1, 0.2, -0.3],
+                [0.7, 0.01, -0.1],
+                [0.7, -0.9, 0.5],
+                [0.1, 0.2, 0.3],
+                [-0.1, 0.2, 0.3],
+                [-0.1, 0.2, 0.3],
+            ]
+        )
+        expected = data[:, 0]
+        y = [1, 2, 1, 0, 0, 0]
+        computed = tcl._max_samples(data, y)
+        self.assertEqual(0, computed)
+        computed_data = data[:, computed]
+        self.assertEqual((6,), computed_data.shape)
+        self.assertListEqual(expected.tolist(), computed_data.tolist())
+
+    def test_impurity(self):
+        tcl = self.build(criteria="impurity")
+        data = np.array(
+            [
+                [-0.1, 0.2, -0.3],
+                [0.7, 0.01, -0.1],
+                [0.7, -0.9, 0.5],
+                [0.1, 0.2, 0.3],
+                [-0.1, 0.2, 0.3],
+                [-0.1, 0.2, 0.3],
+            ]
+        )
+        expected = data[:, 2]
+        y = np.array([1, 2, 1, 0, 0, 0])
+        computed = tcl._impurity(data, y)
+        self.assertEqual(2, computed)
+        computed_data = data[:, computed]
+        self.assertEqual((6,), computed_data.shape)
+        self.assertListEqual(expected.tolist(), computed_data.tolist())
+
+    def test_generate_subspaces(self):
+        features = 250
+        for max_features in range(2, features):
+            num = len(Splitter._generate_spaces(features, max_features))
+            self.assertEqual(5, num)
+        self.assertEqual(3, len(Splitter._generate_spaces(3, 2)))
+        self.assertEqual(4, len(Splitter._generate_spaces(4, 3)))
+
+    def test_best_splitter_few_sets(self):
+        X, y = load_iris(return_X_y=True)
+        X = np.delete(X, 3, 1)
+        tcl = self.build(
+            feature_select="best", random_state=self._random_state
+        )
+        dataset, computed = tcl.get_subspace(X, y, max_features=2)
+        self.assertListEqual([0, 2], list(computed))
+        self.assertListEqual(X[:, computed].tolist(), dataset.tolist())
+
+    def test_splitter_parameter(self):
+        expected_values = [
+            [0, 6, 11, 12],  # best   entropy max_samples
+            [0, 6, 11, 12],  # best   entropy impurity
+            [0, 6, 11, 12],  # best   gini    max_samples
+            [0, 6, 11, 12],  # best   gini    impurity
+            [0, 3, 8, 12],  # random entropy max_samples
+            [0, 3, 7, 12],  # random entropy impurity
+            [1, 7, 9, 12],  # random gini    max_samples
+            [1, 5, 8, 12],  # random gini    impurity
+            [6, 9, 11, 12],  # mutual entropy max_samples
+            [6, 9, 11, 12],  # mutual entropy impurity
+            [6, 9, 11, 12],  # mutual gini    max_samples
+            [6, 9, 11, 12],  # mutual gini    impurity
+        ]
+        X, y = load_wine(return_X_y=True)
+        rn = 0
+        for feature_select in ["best", "random", "mutual"]:
+            for criterion in ["entropy", "gini"]:
+                for criteria in [
+                    "max_samples",
+                    "impurity",
+                ]:
+                    tcl = self.build(
+                        feature_select=feature_select,
+                        criterion=criterion,
+                        criteria=criteria,
+                    )
+                    expected = expected_values.pop(0)
+                    random.seed(rn)
+                    rn += 1
+                    dataset, computed = tcl.get_subspace(X, y, max_features=4)
+                    # print(
+                    #     "{},  # {:7s}{:8s}{:15s}".format(
+                    #         list(computed),
+                    #         feature_select,
+                    #         criterion,
+                    #         criteria,
+                    #     )
+                    # )
+                    self.assertListEqual(expected, sorted(list(computed)))
+                    self.assertListEqual(
+                        X[:, computed].tolist(), dataset.tolist()
+                    )
+
+    def test_get_best_subspaces(self):
+        results = [
+            (4, [3, 4, 11, 13]),
+            (7, [1, 3, 4, 5, 11, 13, 16]),
+            (9, [1, 3, 4, 5, 7, 10, 11, 13, 16]),
+        ]
+        X, y = load_dataset(n_features=20)
+        for k, expected in results:
+            tcl = self.build(
+                feature_select="best",
+            )
+            Xs, computed = tcl.get_subspace(X, y, k)
+            self.assertListEqual(expected, list(computed))
+            self.assertListEqual(X[:, expected].tolist(), Xs.tolist())
+
+    def test_get_best_subspaces_discrete(self):
+        results = [
+            (4, [0, 3, 16, 18]),
+            (7, [0, 3, 13, 14, 16, 18, 19]),
+            (9, [0, 3, 7, 13, 14, 15, 16, 18, 19]),
+        ]
+        X, y = load_disc_dataset(n_features=20)
+        for k, expected in results:
+            tcl = self.build(
+                feature_select="best",
+            )
+            Xs, computed = tcl.get_subspace(X, y, k)
+            self.assertListEqual(expected, list(computed))
+            self.assertListEqual(X[:, expected].tolist(), Xs.tolist())
+
+    def test_get_cfs_subspaces(self):
+        results = [
+            (4, [1, 5, 9, 12]),
+            (6, [1, 5, 9, 12, 4, 2]),
+            (7, [1, 5, 9, 12, 4, 2, 3]),
+        ]
+        X, y = load_dataset(n_features=20, n_informative=7)
+        for k, expected in results:
+            tcl = self.build(feature_select="cfs")
+            Xs, computed = tcl.get_subspace(X, y, k)
+            self.assertListEqual(expected, list(computed))
+            self.assertListEqual(X[:, expected].tolist(), Xs.tolist())
+
+    def test_get_fcbf_subspaces(self):
+        results = [
+            (4, [1, 5, 9, 12]),
+            (6, [1, 5, 9, 12, 4, 2]),
+            (7, [1, 5, 9, 12, 4, 2, 16]),
+        ]
+        for rs, expected in results:
+            X, y = load_dataset(n_features=20, n_informative=7)
+            tcl = self.build(feature_select="fcbf", random_state=rs)
+            Xs, computed = tcl.get_subspace(X, y, rs)
+            self.assertListEqual(expected, list(computed))
+            self.assertListEqual(X[:, expected].tolist(), Xs.tolist())
+
+    def test_get_iwss_subspaces(self):
+        results = [
+            (4, [1, 5, 9, 12]),
+            (6, [1, 5, 9, 12, 4, 15]),
+        ]
+        for rs, expected in results:
+            X, y = load_dataset(n_features=20, n_informative=7)
+            tcl = self.build(feature_select="iwss", random_state=rs)
+            Xs, computed = tcl.get_subspace(X, y, rs)
+            self.assertListEqual(expected, list(computed))
+            self.assertListEqual(X[:, expected].tolist(), Xs.tolist())
+
+    def test_get_trandom_subspaces(self):
+        results = [
+            (4, [3, 7, 9, 12]),
+            (6, [0, 1, 2, 8, 15, 18]),
+            (7, [1, 2, 4, 8, 10, 12, 13]),
+        ]
+        for rs, expected in results:
+            X, y = load_dataset(n_features=20, n_informative=7)
+            tcl = self.build(feature_select="trandom", random_state=rs)
+            Xs, computed = tcl.get_subspace(X, y, rs)
+            self.assertListEqual(expected, list(computed))
+            self.assertListEqual(X[:, expected].tolist(), Xs.tolist())

stree/tests/Stree_test.py

@@ -0,0 +1,759 @@
+import os
+import unittest
+import warnings
+
+import numpy as np
+from sklearn.datasets import load_iris, load_wine
+from sklearn.exceptions import ConvergenceWarning
+from sklearn.svm import LinearSVC
+
+from stree import Stree
+from stree.Splitter import Snode
+from .utils import load_dataset
+from .._version import __version__
+
+
+class Stree_test(unittest.TestCase):
+    def __init__(self, *args, **kwargs):
+        self._random_state = 1
+        self._kernels = ["liblinear", "linear", "rbf", "poly", "sigmoid"]
+        super().__init__(*args, **kwargs)
+
+    @classmethod
+    def setUp(cls):
+        os.environ["TESTING"] = "1"
+
+    def test_valid_kernels(self):
+        X, y = load_dataset()
+        for kernel in self._kernels:
+            clf = Stree(kernel=kernel, multiclass_strategy="ovr")
+            clf.fit(X, y)
+            self.assertIsNotNone(clf.tree_)
+
+    def test_bogus_kernel(self):
+        kernel = "other"
+        X, y = load_dataset()
+        clf = Stree(kernel=kernel)
+        with self.assertRaises(ValueError):
+            clf.fit(X, y)
+
+    def _check_tree(self, node: Snode):
+        """Check recursively that the nodes that are not leaves have the
+        correct number of labels and its sons have the right number of elements
+        in their dataset
+
+        Parameters
+        ----------
+        node : Snode
+            node to check
+        """
+        if node.is_leaf():
+            return
+        y_prediction = node._clf.predict(node._X)
+        y_down = node.get_down()._y
+        y_up = node.get_up()._y
+        # Is a correct partition in terms of cadinality?
+        # i.e. The partition algorithm didn't forget any sample
+        self.assertEqual(node._y.shape[0], y_down.shape[0] + y_up.shape[0])
+        unique_y, count_y = np.unique(node._y, return_counts=True)
+        labels_d, count_d = np.unique(y_down, return_counts=True)
+        labels_u, count_u = np.unique(y_up, return_counts=True)
+        dict_d = {label: count_d[i] for i, label in enumerate(labels_d)}
+        dict_u = {label: count_u[i] for i, label in enumerate(labels_u)}
+        #
+        for i in unique_y:
+            try:
+                number_up = dict_u[i]
+            except KeyError:
+                number_up = 0
+            try:
+                number_down = dict_d[i]
+            except KeyError:
+                number_down = 0
+            self.assertEqual(count_y[i], number_down + number_up)
+        # Is the partition made the same as the prediction?
+        # as the node is not a leaf...
+        _, count_yp = np.unique(y_prediction, return_counts=True)
+        self.assertEqual(count_yp[1], y_up.shape[0])
+        self.assertEqual(count_yp[0], y_down.shape[0])
+        self._check_tree(node.get_down())
+        self._check_tree(node.get_up())
+
+    def test_build_tree(self):
+        """Check if the tree is built the same way as predictions of models"""
+        warnings.filterwarnings("ignore")
+        for kernel in self._kernels:
+            clf = Stree(
+                kernel="sigmoid",
+                multiclass_strategy="ovr" if kernel == "liblinear" else "ovo",
+                random_state=self._random_state,
+            )
+            clf.fit(*load_dataset(self._random_state))
+            self._check_tree(clf.tree_)
+
+    def test_single_prediction(self):
+        X, y = load_dataset(self._random_state)
+        for kernel in self._kernels:
+            clf = Stree(
+                kernel=kernel,
+                multiclass_strategy="ovr" if kernel == "liblinear" else "ovo",
+                random_state=self._random_state,
+            )
+            yp = clf.fit(X, y).predict((X[0, :].reshape(-1, X.shape[1])))
+            self.assertEqual(yp[0], y[0])
+
+    def test_multiple_prediction(self):
+        # First 27 elements the predictions are the same as the truth
+        num = 27
+        X, y = load_dataset(self._random_state)
+        for kernel in ["liblinear", "linear", "rbf", "poly"]:
+            clf = Stree(
+                kernel=kernel,
+                multiclass_strategy="ovr" if kernel == "liblinear" else "ovo",
+                random_state=self._random_state,
+            )
+            yp = clf.fit(X, y).predict(X[:num, :])
+            self.assertListEqual(y[:num].tolist(), yp.tolist())
+
+    def test_multiple_predict_proba(self):
+        expected = {
+            "liblinear": {
+                0: [0.02401129943502825, 0.9759887005649718],
+                17: [0.9282970550576184, 0.07170294494238157],
+            },
+            "linear": {
+                0: [0.029329608938547486, 0.9706703910614525],
+                17: [0.9298469387755102, 0.07015306122448979],
+            },
+            "rbf": {
+                0: [0.023448275862068966, 0.976551724137931],
+                17: [0.9458064516129032, 0.05419354838709677],
+            },
+            "poly": {
+                0: [0.01601164483260553, 0.9839883551673945],
+                17: [0.9089790897908979, 0.0910209102091021],
+            },
+        }
+        indices = [0, 17]
+        X, y = load_dataset(self._random_state)
+        for kernel in ["liblinear", "linear", "rbf", "poly"]:
+            clf = Stree(
+                kernel=kernel,
+                multiclass_strategy="ovr" if kernel == "liblinear" else "ovo",
+                random_state=self._random_state,
+            )
+            yp = clf.fit(X, y).predict_proba(X)
+            for index in indices:
+                for exp, comp in zip(expected[kernel][index], yp[index]):
+                    self.assertAlmostEqual(exp, comp)
+
+    def test_single_vs_multiple_prediction(self):
+        """Check if predicting sample by sample gives the same result as
+        predicting all samples at once
+        """
+        X, y = load_dataset(self._random_state)
+        for kernel in self._kernels:
+            clf = Stree(
+                kernel=kernel,
+                multiclass_strategy="ovr" if kernel == "liblinear" else "ovo",
+                random_state=self._random_state,
+            )
+            clf.fit(X, y)
+            # Compute prediction line by line
+            yp_line = np.array([], dtype=int)
+            for xp in X:
+                yp_line = np.append(
+                    yp_line, clf.predict(xp.reshape(-1, X.shape[1]))
+                )
+            # Compute prediction at once
+            yp_once = clf.predict(X)
+            self.assertListEqual(yp_line.tolist(), yp_once.tolist())
+
+    def test_iterator_and_str(self):
+        """Check preorder iterator"""
+        expected = [
+            "root feaures=(0, 1, 2) impurity=1.0000 counts=(array([0, 1]), "
+            "array([750, 750]))",
+            "root - Down(2), <cgaf> - Leaf class=0 belief= 0.928297 impurity="
+            "0.3722 counts=(array([0, 1]), array([725,  56]))",
+            "root - Up(2) feaures=(0, 1, 2) impurity=0.2178 counts=(array([0, "
+            "1]), array([ 25, 694]))",
+            "root - Up(2) - Down(3) feaures=(0, 1, 2) impurity=0.8454 counts="
+            "(array([0, 1]), array([8, 3]))",
+            "root - Up(2) - Down(3) - Down(4), <pure> - Leaf class=0 belief= "
+            "1.000000 impurity=0.0000 counts=(array([0]), array([7]))",
+            "root - Up(2) - Down(3) - Up(4), <cgaf> - Leaf class=1 belief= "
+            "0.750000 impurity=0.8113 counts=(array([0, 1]), array([1, 3]))",
+            "root - Up(2) - Up(3), <cgaf> - Leaf class=1 belief= 0.975989 "
+            "impurity=0.1634 counts=(array([0, 1]), array([ 17, 691]))",
+        ]
+        computed = []
+        expected_string = ""
+        clf = Stree(
+            kernel="liblinear",
+            multiclass_strategy="ovr",
+            random_state=self._random_state,
+        )
+        clf.fit(*load_dataset(self._random_state))
+        for node in iter(clf):
+            computed.append(str(node))
+            expected_string += str(node) + "\n"
+        self.assertListEqual(expected, computed)
+        self.assertEqual(expected_string, str(clf))
+
+    @staticmethod
+    def test_is_a_sklearn_classifier():
+        warnings.filterwarnings("ignore", category=ConvergenceWarning)
+        warnings.filterwarnings("ignore", category=RuntimeWarning)
+        from sklearn.utils.estimator_checks import check_estimator
+
+        check_estimator(Stree())
+
+    def test_exception_if_C_is_negative(self):
+        tclf = Stree(C=-1)
+        with self.assertRaises(ValueError):
+            tclf.fit(*load_dataset(self._random_state))
+
+    def test_exception_if_bogus_split_criteria(self):
+        tclf = Stree(split_criteria="duck")
+        with self.assertRaises(ValueError):
+            tclf.fit(*load_dataset(self._random_state))
+
+    def test_check_max_depth_is_positive_or_None(self):
+        tcl = Stree()
+        self.assertIsNone(tcl.max_depth)
+        tcl = Stree(max_depth=1)
+        self.assertGreaterEqual(1, tcl.max_depth)
+        with self.assertRaises(ValueError):
+            tcl = Stree(max_depth=-1)
+            tcl.fit(*load_dataset(self._random_state))
+
+    def test_check_max_depth(self):
+        depths = (3, 4)
+        for depth in depths:
+            tcl = Stree(
+                kernel="liblinear",
+                multiclass_strategy="ovr",
+                random_state=self._random_state,
+                max_depth=depth,
+            )
+            tcl.fit(*load_dataset(self._random_state))
+            self.assertEqual(depth, tcl.depth_)
+
+    def test_unfitted_tree_is_iterable(self):
+        tcl = Stree()
+        self.assertEqual(0, len(list(tcl)))
+
+    def test_min_samples_split(self):
+        dataset = [[1], [2], [3]], [1, 1, 0]
+        tcl_split = Stree(min_samples_split=3).fit(*dataset)
+        self.assertIsNotNone(tcl_split.tree_.get_down())
+        self.assertIsNotNone(tcl_split.tree_.get_up())
+        tcl_nosplit = Stree(min_samples_split=4).fit(*dataset)
+        self.assertIsNone(tcl_nosplit.tree_.get_down())
+        self.assertIsNone(tcl_nosplit.tree_.get_up())
+
+    def test_simple_muticlass_dataset(self):
+        for kernel in self._kernels:
+            clf = Stree(
+                kernel=kernel,
+                multiclass_strategy="ovr" if kernel == "liblinear" else "ovo",
+                random_state=self._random_state,
+            )
+            px = [[1, 2], [5, 6], [9, 10]]
+            py = [0, 1, 2]
+            clf.fit(px, py)
+            self.assertEqual(1.0, clf.score(px, py))
+            self.assertListEqual(py, clf.predict(px).tolist())
+            self.assertListEqual(py, clf.classes_.tolist())
+
+    def test_muticlass_dataset(self):
+        warnings.filterwarnings("ignore", category=ConvergenceWarning)
+        warnings.filterwarnings("ignore", category=RuntimeWarning)
+        datasets = {
+            "Synt": load_dataset(random_state=self._random_state, n_classes=3),
+            "Iris": load_wine(return_X_y=True),
+        }
+        outcomes = {
+            "Synt": {
+                "max_samples liblinear": 0.9493333333333334,
+                "max_samples linear": 0.9426666666666667,
+                "max_samples rbf": 0.9606666666666667,
+                "max_samples poly": 0.9373333333333334,
+                "max_samples sigmoid": 0.824,
+                "impurity liblinear": 0.9493333333333334,
+                "impurity linear": 0.9426666666666667,
+                "impurity rbf": 0.9606666666666667,
+                "impurity poly": 0.9373333333333334,
+                "impurity sigmoid": 0.824,
+            },
+            "Iris": {
+                "max_samples liblinear": 0.9550561797752809,
+                "max_samples linear": 1.0,
+                "max_samples rbf": 0.6685393258426966,
+                "max_samples poly": 0.6853932584269663,
+                "max_samples sigmoid": 0.6404494382022472,
+                "impurity liblinear": 0.9550561797752809,
+                "impurity linear": 1.0,
+                "impurity rbf": 0.6685393258426966,
+                "impurity poly": 0.6853932584269663,
+                "impurity sigmoid": 0.6404494382022472,
+            },
+        }
+
+        for name, dataset in datasets.items():
+            px, py = dataset
+            for criteria in ["max_samples", "impurity"]:
+                for kernel in self._kernels:
+                    clf = Stree(
+                        max_iter=1e4,
+                        multiclass_strategy="ovr"
+                        if kernel == "liblinear"
+                        else "ovo",
+                        kernel=kernel,
+                        random_state=self._random_state,
+                    )
+                    clf.fit(px, py)
+                    outcome = outcomes[name][f"{criteria} {kernel}"]
+                    # print(f'"{criteria} {kernel}": {clf.score(px, py)},')
+                    self.assertAlmostEqual(
+                        outcome,
+                        clf.score(px, py),
+                        5,
+                        f"{name} - {criteria} - {kernel}",
+                    )
+
+    def test_max_features(self):
+        n_features = 16
+        expected_values = [
+            ("auto", 4),
+            ("log2", 4),
+            ("sqrt", 4),
+            (0.5, 8),
+            (3, 3),
+            (None, 16),
+        ]
+        clf = Stree()
+        clf.n_features_ = n_features
+        for max_features, expected in expected_values:
+            clf.set_params(**dict(max_features=max_features))
+            computed = clf._initialize_max_features()
+            self.assertEqual(expected, computed)
+        # Check bogus max_features
+        values = ["duck", -0.1, 0.0]
+        for max_features in values:
+            clf.set_params(**dict(max_features=max_features))
+            with self.assertRaises(ValueError):
+                _ = clf._initialize_max_features()
+
+    def test_wrong_max_features(self):
+        X, y = load_dataset(n_features=15)
+        clf = Stree(max_features=16)
+        with self.assertRaises(ValueError):
+            clf.fit(X, y)
+
+    def test_get_subspaces(self):
+        dataset = np.random.random((10, 16))
+        y = np.random.randint(0, 2, 10)
+        expected_values = [
+            ("auto", 4),
+            ("log2", 4),
+            ("sqrt", 4),
+            (0.5, 8),
+            (3, 3),
+            (None, 16),
+        ]
+        clf = Stree()
+        for max_features, expected in expected_values:
+            clf.set_params(**dict(max_features=max_features))
+            clf.fit(dataset, y)
+            computed, indices = clf.splitter_.get_subspace(
+                dataset, y, clf.max_features_
+            )
+            self.assertListEqual(
+                dataset[:, indices].tolist(), computed.tolist()
+            )
+            self.assertEqual(expected, len(indices))
+
+    def test_bogus_criterion(self):
+        clf = Stree(criterion="duck")
+        with self.assertRaises(ValueError):
+            clf.fit(*load_dataset())
+
+    def test_predict_feature_dimensions(self):
+        X = np.random.rand(10, 5)
+        y = np.random.randint(0, 2, 10)
+        clf = Stree()
+        clf.fit(X, y)
+        with self.assertRaises(ValueError):
+            clf.predict(X[:, :3])
+
+    # Tests of score
+    def test_score_binary(self):
+        """Check score for binary classification."""
+        X, y = load_dataset(self._random_state)
+        accuracies = [
+            0.9506666666666667,
+            0.9493333333333334,
+            0.9606666666666667,
+            0.9433333333333334,
+            0.9153333333333333,
+        ]
+        for kernel, accuracy_expected in zip(self._kernels, accuracies):
+            clf = Stree(
+                random_state=self._random_state,
+                multiclass_strategy="ovr" if kernel == "liblinear" else "ovo",
+                kernel=kernel,
+            )
+            clf.fit(X, y)
+            accuracy_score = clf.score(X, y)
+            yp = clf.predict(X)
+            accuracy_computed = np.mean(yp == y)
+            self.assertEqual(accuracy_score, accuracy_computed)
+            self.assertAlmostEqual(accuracy_expected, accuracy_score)
+
+    def test_score_max_features(self):
+        """Check score using max_features."""
+        X, y = load_dataset(self._random_state)
+        clf = Stree(
+            kernel="liblinear",
+            multiclass_strategy="ovr",
+            random_state=self._random_state,
+            max_features=2,
+        )
+        clf.fit(X, y)
+        self.assertAlmostEqual(0.9453333333333334, clf.score(X, y))
+
+    def test_bogus_splitter_parameter(self):
+        """Check that bogus splitter parameter raises exception."""
+        clf = Stree(splitter="duck")
+        with self.assertRaises(ValueError):
+            clf.fit(*load_dataset())
+
+    def test_multiclass_classifier_integrity(self):
+        """Checks if the multiclass operation is done right"""
+        X, y = load_iris(return_X_y=True)
+        clf = Stree(
+            kernel="liblinear", multiclass_strategy="ovr", random_state=0
+        )
+        clf.fit(X, y)
+        score = clf.score(X, y)
+        # Check accuracy of the whole model
+        self.assertAlmostEquals(0.98, score, 5)
+        svm = LinearSVC(random_state=0)
+        svm.fit(X, y)
+        self.assertAlmostEquals(0.9666666666666667, svm.score(X, y), 5)
+        data = svm.decision_function(X)
+        expected = [
+            0.4444444444444444,
+            0.35777777777777775,
+            0.4569777777777778,
+        ]
+        ty = data.copy()
+        ty[data <= 0] = 0
+        ty[data > 0] = 1
+        ty = ty.astype(int)
+        for i in range(3):
+            self.assertAlmostEquals(
+                expected[i],
+                clf.splitter_._gini(ty[:, i]),
+            )
+        # 1st Branch
+        # up has to have 50 samples of class 0
+        # down should have 100 [50, 50]
+        up = data[:, 2] > 0
+        resup = np.unique(y[up], return_counts=True)
+        resdn = np.unique(y[~up], return_counts=True)
+        self.assertListEqual([1, 2], resup[0].tolist())
+        self.assertListEqual([3, 50], resup[1].tolist())
+        self.assertListEqual([0, 1], resdn[0].tolist())
+        self.assertListEqual([50, 47], resdn[1].tolist())
+        # 2nd Branch
+        # up  should have 53 samples of classes [1, 2] [3, 50]
+        # down shoud have 47 samples of class 1
+        node_up = clf.tree_.get_down().get_up()
+        node_dn = clf.tree_.get_down().get_down()
+        resup = np.unique(node_up._y, return_counts=True)
+        resdn = np.unique(node_dn._y, return_counts=True)
+        self.assertListEqual([1, 2], resup[0].tolist())
+        self.assertListEqual([3, 50], resup[1].tolist())
+        self.assertListEqual([1], resdn[0].tolist())
+        self.assertListEqual([47], resdn[1].tolist())
+
+    def test_score_multiclass_rbf(self):
+        """Test score for multiclass classification with rbf kernel."""
+        X, y = load_dataset(
+            random_state=self._random_state,
+            n_classes=3,
+            n_features=5,
+            n_samples=500,
+        )
+        clf = Stree(kernel="rbf", random_state=self._random_state)
+        clf2 = Stree(
+            kernel="rbf", random_state=self._random_state, normalize=True
+        )
+        self.assertEqual(0.966, clf.fit(X, y).score(X, y))
+        self.assertEqual(0.964, clf2.fit(X, y).score(X, y))
+        X, y = load_wine(return_X_y=True)
+        self.assertEqual(0.6685393258426966, clf.fit(X, y).score(X, y))
+        self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
+
+    def test_score_multiclass_poly(self):
+        """Test score for multiclass classification with poly kernel."""
+        X, y = load_dataset(
+            random_state=self._random_state,
+            n_classes=3,
+            n_features=5,
+            n_samples=500,
+        )
+        clf = Stree(
+            kernel="poly", random_state=self._random_state, C=10, degree=5
+        )
+        clf2 = Stree(
+            kernel="poly",
+            random_state=self._random_state,
+            normalize=True,
+        )
+        self.assertEqual(0.946, clf.fit(X, y).score(X, y))
+        self.assertEqual(0.972, clf2.fit(X, y).score(X, y))
+        X, y = load_wine(return_X_y=True)
+        self.assertEqual(0.7808988764044944, clf.fit(X, y).score(X, y))
+        self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
+
+    def test_score_multiclass_liblinear(self):
+        """Test score for multiclass classification with liblinear kernel."""
+        X, y = load_dataset(
+            random_state=self._random_state,
+            n_classes=3,
+            n_features=5,
+            n_samples=500,
+        )
+        clf = Stree(
+            kernel="liblinear",
+            multiclass_strategy="ovr",
+            random_state=self._random_state,
+            C=10,
+        )
+        clf2 = Stree(
+            kernel="liblinear",
+            multiclass_strategy="ovr",
+            random_state=self._random_state,
+            normalize=True,
+        )
+        self.assertEqual(0.968, clf.fit(X, y).score(X, y))
+        self.assertEqual(0.97, clf2.fit(X, y).score(X, y))
+        X, y = load_wine(return_X_y=True)
+        self.assertEqual(1.0, clf.fit(X, y).score(X, y))
+        self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
+
+    def test_score_multiclass_sigmoid(self):
+        """Test score for multiclass classification with sigmoid kernel."""
+        X, y = load_dataset(
+            random_state=self._random_state,
+            n_classes=3,
+            n_features=5,
+            n_samples=500,
+        )
+        clf = Stree(kernel="sigmoid", random_state=self._random_state, C=10)
+        clf2 = Stree(
+            kernel="sigmoid",
+            random_state=self._random_state,
+            normalize=True,
+            C=10,
+        )
+        self.assertEqual(0.796, clf.fit(X, y).score(X, y))
+        self.assertEqual(0.952, clf2.fit(X, y).score(X, y))
+        X, y = load_wine(return_X_y=True)
+        self.assertEqual(0.6910112359550562, clf.fit(X, y).score(X, y))
+        self.assertEqual(0.9662921348314607, clf2.fit(X, y).score(X, y))
+
+    def test_score_multiclass_linear(self):
+        """Test score for multiclass classification with linear kernel."""
+        warnings.filterwarnings("ignore", category=ConvergenceWarning)
+        warnings.filterwarnings("ignore", category=RuntimeWarning)
+        X, y = load_dataset(
+            random_state=self._random_state,
+            n_classes=3,
+            n_features=5,
+            n_samples=1500,
+        )
+        clf = Stree(
+            kernel="liblinear",
+            multiclass_strategy="ovr",
+            random_state=self._random_state,
+        )
+        self.assertEqual(0.9533333333333334, clf.fit(X, y).score(X, y))
+        # Check with context based standardization
+        clf2 = Stree(
+            kernel="liblinear",
+            multiclass_strategy="ovr",
+            random_state=self._random_state,
+            normalize=True,
+        )
+        self.assertEqual(0.9526666666666667, clf2.fit(X, y).score(X, y))
+        X, y = load_wine(return_X_y=True)
+        self.assertEqual(0.9831460674157303, clf.fit(X, y).score(X, y))
+        self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
+
+    def test_zero_all_sample_weights(self):
+        """Test exception raises when all sample weights are zero."""
+        X, y = load_dataset(self._random_state)
+        with self.assertRaises(ValueError):
+            Stree().fit(X, y, np.zeros(len(y)))
+
+    def test_mask_samples_weighted_zero(self):
+        """Check that the weighted zero samples are masked."""
+        X = np.array(
+            [
+                [1, 1],
+                [1, 1],
+                [1, 1],
+                [2, 2],
+                [2, 2],
+                [2, 2],
+                [3, 3],
+                [3, 3],
+                [3, 3],
+            ]
+        )
+        y = np.array([1, 1, 1, 2, 2, 2, 5, 5, 5])
+        yw = np.array([1, 1, 1, 1, 1, 1, 5, 5, 5])
+        w = [1, 1, 1, 0, 0, 0, 1, 1, 1]
+        model1 = Stree().fit(X, y)
+        model2 = Stree().fit(X, y, w)
+        predict1 = model1.predict(X)
+        predict2 = model2.predict(X)
+        self.assertListEqual(y.tolist(), predict1.tolist())
+        self.assertListEqual(yw.tolist(), predict2.tolist())
+        self.assertEqual(model1.score(X, y), 1)
+        self.assertAlmostEqual(model2.score(X, y), 0.66666667)
+        self.assertEqual(model2.score(X, y, w), 1)
+
+    def test_depth(self):
+        """Check depth of the tree."""
+        X, y = load_dataset(
+            random_state=self._random_state,
+            n_classes=3,
+            n_features=5,
+            n_samples=1500,
+        )
+        clf = Stree(random_state=self._random_state)
+        clf.fit(X, y)
+        self.assertEqual(6, clf.depth_)
+        X, y = load_wine(return_X_y=True)
+        clf = Stree(random_state=self._random_state)
+        clf.fit(X, y)
+        self.assertEqual(4, clf.depth_)
+
+    def test_nodes_leaves(self):
+        """Check number of nodes and leaves."""
+        X, y = load_dataset(
+            random_state=self._random_state,
+            n_classes=3,
+            n_features=5,
+            n_samples=1500,
+        )
+        clf = Stree(random_state=self._random_state)
+        clf.fit(X, y)
+        nodes, leaves = clf.nodes_leaves()
+        self.assertEqual(31, nodes)
+        self.assertEqual(16, leaves)
+        X, y = load_wine(return_X_y=True)
+        clf = Stree(random_state=self._random_state)
+        clf.fit(X, y)
+        nodes, leaves = clf.nodes_leaves()
+        self.assertEqual(11, nodes)
+        self.assertEqual(6, leaves)
+
+    def test_nodes_leaves_artificial(self):
+        """Check leaves of artificial dataset."""
+        n1 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test1")
+        n2 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test2")
+        n3 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test3")
+        n4 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test4")
+        n5 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test5")
+        n6 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test6")
+        n1.set_up(n2)
+        n2.set_up(n3)
+        n2.set_down(n4)
+        n3.set_up(n5)
+        n4.set_down(n6)
+        clf = Stree(random_state=self._random_state)
+        clf.tree_ = n1
+        nodes, leaves = clf.nodes_leaves()
+        self.assertEqual(6, nodes)
+        self.assertEqual(2, leaves)
+
+    def test_bogus_multiclass_strategy(self):
+        """Check invalid multiclass strategy."""
+        clf = Stree(multiclass_strategy="other")
+        X, y = load_wine(return_X_y=True)
+        with self.assertRaises(ValueError):
+            clf.fit(X, y)
+
+    def test_multiclass_strategy(self):
+        """Check multiclass strategy."""
+        X, y = load_wine(return_X_y=True)
+        clf_o = Stree(multiclass_strategy="ovo")
+        clf_r = Stree(multiclass_strategy="ovr")
+        score_o = clf_o.fit(X, y).score(X, y)
+        score_r = clf_r.fit(X, y).score(X, y)
+        self.assertEqual(1.0, score_o)
+        self.assertEqual(0.9269662921348315, score_r)
+
+    def test_incompatible_hyperparameters(self):
+        """Check incompatible hyperparameters."""
+        X, y = load_wine(return_X_y=True)
+        clf = Stree(kernel="liblinear", multiclass_strategy="ovo")
+        with self.assertRaises(ValueError):
+            clf.fit(X, y)
+        clf = Stree(multiclass_strategy="ovo", split_criteria="max_samples")
+        with self.assertRaises(ValueError):
+            clf.fit(X, y)
+
+    def test_version(self):
+        """Check STree version."""
+        clf = Stree()
+        self.assertEqual(__version__, clf.version())
+
+    def test_graph(self):
+        """Check graphviz representation of the tree."""
+        X, y = load_wine(return_X_y=True)
+        clf = Stree(random_state=self._random_state)
+
+        expected_head = (
+            "digraph STree {\nlabel=<STree >\nfontsize=30\n"
+            "fontcolor=blue\nlabelloc=t\n"
+        )
+        expected_tail = (
+            ' [shape=box style=filled label="class=1 impurity=0.000 '
+            'counts=[0 1 0]"];\n}\n'
+        )
+        self.assertEqual(clf.graph(), expected_head + "}\n")
+        clf.fit(X, y)
+        computed = clf.graph()
+        computed_head = computed[: len(expected_head)]
+        num = -len(expected_tail)
+        computed_tail = computed[num:]
+        self.assertEqual(computed_head, expected_head)
+        self.assertEqual(computed_tail, expected_tail)
+
+    def test_graph_title(self):
+        X, y = load_wine(return_X_y=True)
+        clf = Stree(random_state=self._random_state)
+        expected_head = (
+            "digraph STree {\nlabel=<STree Sample title>\nfontsize=30\n"
+            "fontcolor=blue\nlabelloc=t\n"
+        )
+        expected_tail = (
+            ' [shape=box style=filled label="class=1 impurity=0.000 '
+            'counts=[0 1 0]"];\n}\n'
+        )
+        self.assertEqual(clf.graph("Sample title"), expected_head + "}\n")
+        clf.fit(X, y)
+        computed = clf.graph("Sample title")
+        computed_head = computed[: len(expected_head)]
+        num = -len(expected_tail)
+        computed_tail = computed[num:]
+        self.assertEqual(computed_head, expected_head)
+        self.assertEqual(computed_tail, expected_tail)

stree/tests/Strees_test.py

@@ -1,313 +0,0 @@
-import csv
-import os
-import unittest
-
-import numpy as np
-from sklearn.datasets import make_classification
-
-from stree import Stree, Snode
-
-
-class Stree_test(unittest.TestCase):
-
-    def __init__(self, *args, **kwargs):
-        os.environ['TESTING'] = '1'
-        self._random_state = 1
-        self._clf = Stree(random_state=self._random_state,
-                          use_predictions=False)
-        self._clf.fit(*self._get_Xy())
-        super().__init__(*args, **kwargs)
-
-    @classmethod
-    def tearDownClass(cls):
-        try:
-            os.environ.pop('TESTING')
-        except:
-            pass
-
-    def _get_Xy(self):
-        X, y = make_classification(n_samples=1500, n_features=3, n_informative=3,
-                                   n_redundant=0, n_repeated=0, n_classes=2, n_clusters_per_class=2,
-                                   class_sep=1.5, flip_y=0, weights=[0.5, 0.5], random_state=self._random_state)
-        return X, y
-
-    def _check_tree(self, node: Snode):
-        """Check recursively that the nodes that are not leaves have the correct 
-        number of labels and its sons have the right number of elements in their dataset
-
-        Arguments:
-            node {Snode} -- node to check
-        """
-        if node.is_leaf():
-            return
-        y_prediction = node._clf.predict(node._X)
-        y_down = node.get_down()._y
-        y_up = node.get_up()._y
-        # Is a correct partition in terms of cadinality?
-        # i.e. The partition algorithm didn't forget any sample
-        self.assertEqual(node._y.shape[0], y_down.shape[0] + y_up.shape[0])
-        unique_y, count_y = np.unique(node._y, return_counts=True)
-        _, count_d = np.unique(y_down, return_counts=True)
-        _, count_u = np.unique(y_up, return_counts=True)
-        #
-        for i in unique_y:
-            try:
-                number_down = count_d[i]
-            except:
-                number_down = 0
-            try:
-                number_up = count_u[i]
-            except:
-                number_up = 0
-            self.assertEqual(count_y[i], number_down + number_up)
-        # Is the partition made the same as the prediction?
-        # as the node is not a leaf...
-        _, count_yp = np.unique(y_prediction, return_counts=True)
-        self.assertEqual(count_yp[0], y_up.shape[0])
-        self.assertEqual(count_yp[1], y_down.shape[0])
-        self._check_tree(node.get_down())
-        self._check_tree(node.get_up())
-
-    def test_build_tree(self):
-        """Check if the tree is built the same way as predictions of models
-        """
-        self._check_tree(self._clf._tree)
-
-    def _get_file_data(self, file_name: str) -> tuple:
-        """Return X, y from data, y is the last column in array
-
-        Arguments:
-            file_name {str} -- the file name
-
-        Returns:
-            tuple -- tuple with samples, categories
-        """
-        data = np.genfromtxt(file_name, delimiter=',')
-        data = np.array(data)
-        column_y = data.shape[1] - 1
-        fy = data[:, column_y]
-        fx = np.delete(data, column_y, axis=1)
-        return fx, fy
-
-    def _find_out(self, px: np.array, x_original: np.array, y_original) -> list:
-        """Find the original values of y for a given array of samples
-
-        Arguments:
-            px {np.array} -- array of samples to search for
-            x_original {np.array} -- original dataset
-            y_original {[type]} -- original classes
-
-        Returns:
-            np.array -- classes of the given samples
-        """
-        res = []
-        for needle in px:
-            for row in range(x_original.shape[0]):
-                if all(x_original[row, :] == needle):
-                    res.append(y_original[row])
-        return res
-
-    def test_subdatasets(self):
-        """Check if the subdatasets files have the same labels as the original dataset
-        """
-        self._clf.save_sub_datasets()
-        with open(self._clf.get_catalog_name()) as cat_file:
-            catalog = csv.reader(cat_file, delimiter=',')
-            for row in catalog:
-                X, y = self._get_Xy()
-                x_file, y_file = self._get_file_data(row[0])
-                y_original = np.array(self._find_out(x_file, X, y), dtype=int)
-                self.assertTrue(np.array_equal(y_file, y_original))
-
-    def test_single_prediction(self):
-        X, y = self._get_Xy()
-        yp = self._clf.predict((X[0, :].reshape(-1, X.shape[1])))
-        self.assertEqual(yp[0], y[0])
-
-    def test_multiple_prediction(self):
-        # First 27 elements the predictions are the same as the truth
-        num = 27
-        X, y = self._get_Xy()
-        yp = self._clf.predict(X[:num, :])
-        self.assertListEqual(y[:num].tolist(), yp.tolist())
-
-    def test_score(self):
-        X, y = self._get_Xy()
-        accuracy_score = self._clf.score(X, y)
-        yp = self._clf.predict(X)
-        right = (yp == y).astype(int)
-        accuracy_computed = sum(right) / len(y)
-        self.assertEqual(accuracy_score, accuracy_computed)
-        self.assertGreater(accuracy_score, 0.8)
-
-    def test_single_predict_proba(self):
-        """Check that element 28 has a prediction different that the current label
-        """
-        # Element 28 has a different prediction than the truth
-        decimals = 5
-        X, y = self._get_Xy()
-        yp = self._clf.predict_proba(X[28, :].reshape(-1, X.shape[1]))
-        self.assertEqual(0, yp[0:, 0])
-        self.assertEqual(1, y[28])
-        self.assertAlmostEqual(
-            round(0.29026400766, decimals),
-            round(yp[0, 1], decimals),
-            decimals
-        )
-
-    def test_multiple_predict_proba(self):
-        # First 27 elements the predictions are the same as the truth
-        num = 27
-        decimals = 5
-        X, y = self._get_Xy()
-        yp = self._clf.predict_proba(X[:num, :])
-        self.assertListEqual(y[:num].tolist(), yp[:, 0].tolist())
-        expected_proba = [0.88395641, 0.36746962, 0.84158767, 0.34106833, 0.14269291, 0.85193236,
-                          0.29876058, 0.7282164, 0.85958616, 0.89517877, 0.99745224, 0.18860349,
-                          0.30756427, 0.8318412, 0.18981198, 0.15564624, 0.25740655, 0.22923355,
-                          0.87365959, 0.49928689, 0.95574351, 0.28761257, 0.28906333, 0.32643692,
-                          0.29788483, 0.01657364, 0.81149083]
-        expected = np.round(expected_proba, decimals=decimals).tolist()
-        computed = np.round(yp[:, 1], decimals=decimals).tolist()
-        for i in range(len(expected)):
-            self.assertAlmostEqual(expected[i], computed[i], decimals)
-
-    def build_models(self):
-        """Build and train two models, model_clf will use the sklearn classifier to
-        compute predictions and split data. model_computed will use vector of
-        coefficients to compute both predictions and splitted data
-        """
-        model_clf = Stree(random_state=self._random_state,
-                          use_predictions=True)
-        model_computed = Stree(random_state=self._random_state,
-                               use_predictions=False)
-        X, y = self._get_Xy()
-        model_clf.fit(X, y)
-        model_computed.fit(X, y)
-        return model_clf, model_computed, X, y
-
-    def test_use_model_predict(self):
-        """Check that we get the same results wether we use the estimator in nodes
-        to compute labels or we use the hyperplane and the position of samples wrt to it
-        """
-        use_clf, use_math, X, _ = self.build_models()
-        self.assertListEqual(
-            use_clf.predict(X).tolist(),
-            use_math.predict(X).tolist()
-        )
-
-    def test_use_model_score(self):
-        use_clf, use_math, X, y = self.build_models()
-        b = use_math.score(X, y)
-        self.assertEqual(
-            use_clf.score(X, y),
-            b
-        )
-        self.assertGreater(b, .95)
-
-    def test_use_model_predict_proba(self):
-        use_clf, use_math, X, _ = self.build_models()
-        self.assertListEqual(
-            use_clf.predict_proba(X).tolist(),
-            use_math.predict_proba(X).tolist()
-        )
-
-    def test_single_vs_multiple_prediction(self):
-        """Check if predicting sample by sample gives the same result as predicting
-        all samples at once
-        """
-        X, _ = self._get_Xy()
-        # Compute prediction line by line
-        yp_line = np.array([], dtype=int)
-        for xp in X:
-            yp_line = np.append(yp_line, self._clf.predict(xp.reshape(-1, X.shape[1])))
-        # Compute prediction at once
-        yp_once = self._clf.predict(X)
-        #
-        self.assertListEqual(yp_line.tolist(), yp_once.tolist())
-
-    def test_iterator(self):
-        """Check preorder iterator
-        """
-        expected = [
-            'root',
-            'root - Down',
-            'root - Down - Down, <cgaf> - Leaf class=1 belief=0.975989 counts=(array([0, 1]), array([ 17, 691]))',
-            'root - Down - Up',
-            'root - Down - Up - Down, <cgaf> - Leaf class=1 belief=0.750000 counts=(array([0, 1]), array([1, 3]))',
-            'root - Down - Up - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([7]))',
-            'root - Up, <cgaf> - Leaf class=0 belief=0.928297 counts=(array([0, 1]), array([725,  56]))',
-        ]
-        computed = []
-        for node in self._clf:
-            computed.append(str(node))
-        self.assertListEqual(expected, computed)
-
-class Snode_test(unittest.TestCase):
-
-    def __init__(self, *args, **kwargs):
-        os.environ['TESTING'] = '1'
-        self._random_state = 1
-        self._clf = Stree(random_state=self._random_state,
-                          use_predictions=True)
-        self._clf.fit(*self._get_Xy())
-        super().__init__(*args, **kwargs)
-
-    @classmethod
-    def tearDownClass(cls):
-        try:
-            os.environ.pop('TESTING')
-        except:
-            pass
-
-    def _get_Xy(self):
-        X, y = make_classification(n_samples=1500, n_features=3, n_informative=3,
-                                   n_redundant=0, n_repeated=0, n_classes=2, n_clusters_per_class=2,
-                                   class_sep=1.5, flip_y=0, weights=[0.5, 0.5], random_state=self._random_state)
-        return X, y
-
-    def test_attributes_in_leaves(self):
-        """Check if the attributes in leaves have correct values so they form a predictor
-        """
-
-        def check_leave(node: Snode):
-            if not node.is_leaf():
-                check_leave(node.get_down())
-                check_leave(node.get_up())
-                return
-            # Check Belief in leave
-            classes, card = np.unique(node._y, return_counts=True)
-            max_card = max(card)
-            min_card = min(card)
-            if len(classes) > 1:
-                try:
-                    belief = max_card / (max_card + min_card)
-                except:
-                    belief = 0.
-            else:
-                belief = 1
-            self.assertEqual(belief, node._belief)
-            # Check Class
-            class_computed = classes[card == max_card]
-            self.assertEqual(class_computed, node._class)
-
-        check_leave(self._clf._tree)
-
-    def test_nodes_coefs(self):
-        """Check if the nodes of the tree have the right attributes filled
-        """
-
-        def run_tree(node: Snode):
-            if node._belief < 1:
-                # only exclude pure leaves
-                self.assertIsNotNone(node._clf)
-                self.assertIsNotNone(node._clf.coef_)
-                self.assertIsNotNone(node._vector)
-                self.assertIsNotNone(node._interceptor)
-            if node.is_leaf():
-                return
-            run_tree(node.get_down())
-            run_tree(node.get_up())
-
-        run_tree(self._clf._tree)
-

stree/tests/__init__.py

@@ -1 +1,5 @@
-from .Strees_test import Stree_test, Snode_test
+from .Stree_test import Stree_test
+from .Snode_test import Snode_test
+from .Splitter_test import Splitter_test
+
+__all__ = ["Stree_test", "Snode_test", "Splitter_test"]

stree/tests/utils.py

@@ -0,0 +1,29 @@
+from sklearn.datasets import make_classification
+import numpy as np
+
+
+def load_dataset(
+    random_state=0, n_classes=2, n_features=3, n_samples=1500, n_informative=3
+):
+    X, y = make_classification(
+        n_samples=n_samples,
+        n_features=n_features,
+        n_informative=n_informative,
+        n_redundant=0,
+        n_repeated=0,
+        n_classes=n_classes,
+        n_clusters_per_class=2,
+        class_sep=1.5,
+        flip_y=0,
+        random_state=random_state,
+    )
+    return X, y
+
+
+def load_disc_dataset(
+    random_state=0, n_classes=2, n_features=3, n_samples=1500
+):
+    np.random.seed(random_state)
+    X = np.random.randint(1, 17, size=(n_samples, n_features)).astype(float)
+    y = np.random.randint(low=0, high=n_classes, size=(n_samples), dtype=int)
+    return X, y

test2.ipynb

@@ -1,191 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#\n",
-    "# Google Colab setup\n",
-    "#\n",
-    "#!pip install git+https://github.com/doctorado-ml/stree"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "import pandas as pd\n",
-    "from sklearn.svm import LinearSVC\n",
-    "from sklearn.tree import DecisionTreeClassifier\n",
-    "from sklearn.datasets import make_classification, load_iris, load_wine\n",
-    "from sklearn.model_selection import train_test_split\n",
-    "from stree import Stree\n",
-    "import time"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "if not os.path.isfile('data/creditcard.csv'):\n",
-    "    !wget --no-check-certificate --content-disposition http://nube.jccm.es/index.php/s/Zs7SYtZQJ3RQ2H2/download\n",
-    "    !tar xzf creditcard.tgz"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "Fraud: 0.173% 492\nValid: 99.827% 284315\nX.shape (1492, 28)  y.shape (1492,)\nFraud: 33.110% 494\nValid: 66.890% 998\n"
-    }
-   ],
-   "source": [
-    "random_state=1\n",
-    "\n",
-    "def load_creditcard(n_examples=0):\n",
-    "    import pandas as pd\n",
-    "    import numpy as np\n",
-    "    import random\n",
-    "    df = pd.read_csv('data/creditcard.csv')\n",
-    "    print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n",
-    "    print(\"Valid: {0:.3f}% {1}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))\n",
-    "    y = df.Class\n",
-    "    X = df.drop(['Class', 'Time', 'Amount'], axis=1).values\n",
-    "    if n_examples > 0:\n",
-    "        # Take first n_examples samples\n",
-    "        X = X[:n_examples, :]\n",
-    "        y = y[:n_examples, :]\n",
-    "    else:\n",
-    "        # Take all the positive samples with a number of random negatives\n",
-    "        if n_examples < 0:\n",
-    "            Xt = X[(y == 1).ravel()]\n",
-    "            yt = y[(y == 1).ravel()]\n",
-    "            indices = random.sample(range(X.shape[0]), -1 * n_examples)\n",
-    "            X = np.append(Xt, X[indices], axis=0)\n",
-    "            y = np.append(yt, y[indices], axis=0)\n",
-    "    print(\"X.shape\", X.shape, \" y.shape\", y.shape)\n",
-    "    print(\"Fraud: {0:.3f}% {1}\".format(len(y[y == 1])*100/X.shape[0], len(y[y == 1])))\n",
-    "    print(\"Valid: {0:.3f}% {1}\".format(len(y[y == 0]) * 100 / X.shape[0], len(y[y == 0])))\n",
-    "    Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state, stratify=y)\n",
-    "    return Xtrain, Xtest, ytrain, ytest\n",
-    "\n",
-    "# data = load_creditcard(-5000) # Take all true samples + 5000 of the others\n",
-    "# data = load_creditcard(5000)  # Take the first 5000 samples\n",
-    "data = load_creditcard(-1000) # Take all the samples\n",
-    "\n",
-    "Xtrain = data[0]\n",
-    "Xtest = data[1]\n",
-    "ytrain = data[2]\n",
-    "ytest = data[3]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "************** C=0.001 ****************************\nClassifier's accuracy (train): 0.9521\nClassifier's accuracy (test) : 0.9598\nroot\nroot - Down, <cgaf> - Leaf class=1 belief=0.980519 counts=(array([0, 1]), array([  6, 302]))\nroot - Up, <cgaf> - Leaf class=0 belief=0.940217 counts=(array([0, 1]), array([692,  44]))\n\n**************************************************\n************** C=0.01 ****************************\nClassifier's accuracy (train): 0.9521\nClassifier's accuracy (test) : 0.9643\nroot\nroot - Down\nroot - Down - Down, <cgaf> - Leaf class=1 belief=0.986842 counts=(array([0, 1]), array([  4, 300]))\nroot - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([1]))\nroot - Up, <cgaf> - Leaf class=0 belief=0.937754 counts=(array([0, 1]), array([693,  46]))\n\n**************************************************\n************** C=1 ****************************\nClassifier's accuracy (train): 0.9636\nClassifier's accuracy (test) : 0.9688\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([308]))\nroot - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([8]))\nroot - Up, <cgaf> - Leaf class=0 belief=0.947802 counts=(array([0, 1]), array([690,  38]))\n\n**************************************************\n************** C=5 ****************************\nClassifier's accuracy (train): 0.9665\nClassifier's accuracy (test) : 0.9621\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([308]))\nroot - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([11]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([1]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([1]))\nroot - Up - Up\nroot - Up - Up - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief=0.951456 counts=(array([0, 1]), array([686,  35]))\n\n**************************************************\n************** C=17 ****************************\nClassifier's accuracy (train): 0.9741\nClassifier's accuracy (test) : 0.9576\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([306]))\nroot - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([10]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([3]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([2]))\nroot - Up - Up\nroot - Up - Up - Down\nroot - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([3]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down\nroot - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([7]))\nroot - Up - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([4]))\nroot - Up - Up - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief=0.961538 counts=(array([0, 1]), array([675,  27]))\n\n**************************************************\n0.7816 secs\n"
-    }
-   ],
-   "source": [
-    "t = time.time()\n",
-    "for C in (.001, .01, 1, 5, 17):\n",
-    "    clf = Stree(C=C, random_state=random_state)\n",
-    "    clf.fit(Xtrain, ytrain)\n",
-    "    print(f\"************** C={C} ****************************\")\n",
-    "    print(f\"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}\")\n",
-    "    print(f\"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}\")\n",
-    "    print(clf)\n",
-    "    print(f\"**************************************************\")\n",
-    "print(f\"{time.time() - t:.4f} secs\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "from sklearn.preprocessing import StandardScaler\n",
-    "from sklearn.svm import LinearSVC\n",
-    "from sklearn.calibration import CalibratedClassifierCV\n",
-    "scaler = StandardScaler()\n",
-    "cclf = CalibratedClassifierCV(base_estimator=LinearSVC(), cv=5)\n",
-    "cclf.fit(Xtrain, ytrain)\n",
-    "res = cclf.predict_proba(Xtest)\n",
-    "#an array containing probabilities of belonging to the 1st class"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "root\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([306]))\nroot - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([10]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([3]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([2]))\nroot - Up - Up\nroot - Up - Up - Down\nroot - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([3]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down\nroot - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([7]))\nroot - Up - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([4]))\nroot - Up - Up - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief=0.961538 counts=(array([0, 1]), array([675,  27]))\n"
-    }
-   ],
-   "source": [
-    "#check iterator\n",
-    "for i in list(clf):\n",
-    "    print(i)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "root\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([306]))\nroot - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([10]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([3]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([2]))\nroot - Up - Up\nroot - Up - Up - Down\nroot - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([3]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down\nroot - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([7]))\nroot - Up - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([4]))\nroot - Up - Up - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief=0.961538 counts=(array([0, 1]), array([675,  27]))\n"
-    }
-   ],
-   "source": [
-    "#check iterator again\n",
-    "for i in clf:\n",
-    "    print(i)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.6-final"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}