Fix mistake in computing multiclass node belief

Set default criterion for split to entropy instead of gini
Set default max_iter to 1e5 instead of 1e3
change up-down criterion to match SVC multiclass
Fix impurity method of splitting nodes
Update jupyter Notebooks

.github/workflows/main.yml

@@ -1,47 +0,0 @@
-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]
-        python: [3.8]
-
-    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

README.md

@@ -1,6 +1,6 @@
-![CI](https://github.com/Doctorado-ML/STree/workflows/CI/badge.svg)
+[![Codeship Status for Doctorado-ML/STree](https://app.codeship.com/projects/8b2bd350-8a1b-0138-5f2c-3ad36f3eb318/status?branch=master)](https://app.codeship.com/projects/399170)
 [![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)
+[![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)
 
 # Stree
 
@@ -18,17 +18,17 @@ pip install git+https://github.com/doctorado-ml/stree
 
 ### Jupyter notebooks
 
-- [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/Doctorado-ML/STree/master?urlpath=lab/tree/notebooks/benchmark.ipynb) Benchmark
+* [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/Doctorado-ML/STree/master?urlpath=lab/tree/notebooks/benchmark.ipynb) Benchmark
 
-- [![Test](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/benchmark.ipynb) Benchmark
+* [![Test](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/benchmark.ipynb) Benchmark
 
-- [![Test2](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/features.ipynb) Test features
+* [![Test2](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/features.ipynb) Test features
 
-- [![Adaboost](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/adaboost.ipynb) Adaboost
+* [![Adaboost](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/adaboost.ipynb) Adaboost
 
-- [![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
+* [![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 Graphics](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/test_graphs.ipynb) Test Graphics
+* [![Test Graphics](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/test_graphs.ipynb) Test Graphics
 
 ### Command line
 

requirements.txt

@@ -1,4 +1,4 @@
 numpy
-scikit-learn==0.23.2
+scikit-learn
 pandas
 ipympl

setup.py

@@ -30,7 +30,7 @@ setuptools.setup(
         "Topic :: Scientific/Engineering :: Artificial Intelligence",
         "Intended Audience :: Science/Research",
     ],
-    install_requires=["scikit-learn==0.23.2", "numpy", "ipympl"],
+    install_requires=["scikit-learn>=0.23.0", "numpy", "ipympl"],
     test_suite="stree.tests",
     zip_safe=False,
 )

stree/Strees.py

@@ -10,8 +10,8 @@ import os
 import numbers
 import random
 import warnings
-from math import log, factorial
+from math import log
-from typing import Optional
+from itertools import combinations
 import numpy as np
 from sklearn.base import BaseEstimator, ClassifierMixin
 from sklearn.svm import SVC, LinearSVC
@@ -253,32 +253,19 @@ class Splitter:
                 selected = feature_set
         return selected if selected is not None else feature_set
 
-    @staticmethod
-    def _generate_spaces(features: int, max_features: int) -> list:
-        comb = set()
-        # Generate at most 5 combinations
-        if max_features == features:
-            set_length = 1
-        else:
-            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
     ) -> np.array:
-        features_sets = self._generate_spaces(dataset.shape[1], max_features)
+        features = range(dataset.shape[1])
+        features_sets = list(combinations(features, max_features))
         if len(features_sets) > 1:
             if self._splitter_type == "random":
                 index = random.randint(0, len(features_sets) - 1)
                 return features_sets[index]
             else:
+                # get only 3 sets at most
+                if len(features_sets) > 3:
+                    features_sets = random.sample(features_sets, 3)
                 return self._select_best_set(dataset, labels, features_sets)
         else:
             return features_sets[0]
@@ -297,8 +284,9 @@ class Splitter:
         :type data: np.array (m, n_classes)
         :param y: vector of labels (classes)
         :type y: np.array (m,)
-        :return: column of dataset to be taken into account to split dataset
+        :return: vector with the class assigned to each sample values
-        :rtype: int
+        (can be 0, 1, ...) -1 if none produces information gain
+        :rtype: np.array shape (m,)
         """
         max_gain = 0
         selected = -1
@@ -319,8 +307,8 @@ class Splitter:
         :type data: np.array (m, n_classes)
         :param y: vector of labels (classes)
         :type y: np.array (m,)
-        :return: column of dataset to be taken into account to split dataset
+        :return: vector with distances to hyperplane (can be positive or neg.)
-        :rtype: int
+        :rtype: np.array shape (m,)
         """
         # select the class with max number of samples
         _, samples = np.unique(y, return_counts=True)
@@ -501,7 +489,7 @@ class Stree(BaseEstimator, ClassifierMixin):
         sample_weight: np.ndarray,
         depth: int,
         title: str,
-    ) -> Optional[Snode]:
+    ) -> Snode:
         """Recursive function to split the original dataset into predictor
         nodes (leaves)
 

stree/tests/Splitter_test.py

@@ -166,14 +166,6 @@ class Splitter_test(unittest.TestCase):
         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)
@@ -184,14 +176,14 @@ class Splitter_test(unittest.TestCase):
 
     def test_splitter_parameter(self):
         expected_values = [
-            [1, 4, 9, 12],  # best   entropy max_samples
+            [0, 1, 7, 9],  # best   entropy max_samples
-            [1, 3, 6, 10],  # best   entropy impurity
+            [3, 8, 10, 11],  # best   entropy impurity
-            [6, 8, 10, 12],  # best   gini    max_samples
+            [0, 2, 8, 12],  # best   gini    max_samples
-            [7, 8, 10, 11],  # best   gini    impurity
+            [1, 2, 5, 12],  # best   gini    impurity
-            [0, 3, 8, 12],  # random entropy max_samples
+            [1, 2, 5, 10],  # random entropy max_samples
-            [0, 3, 9, 11],  # random entropy impurity
+            [4, 8, 9, 12],  # random entropy impurity
-            [0, 4, 7, 12],  # random gini    max_samples
+            [3, 9, 11, 12],  # random gini    max_samples
-            [0, 2, 5, 6],  # random gini    impurity
+            [1, 5, 6, 9],  # random gini    impurity
         ]
         X, y = load_wine(return_X_y=True)
         rn = 0

stree/tests/Stree_test.py

@@ -313,7 +313,7 @@ class Stree_test(unittest.TestCase):
         X, y = load_dataset(self._random_state)
         clf = Stree(random_state=self._random_state, max_features=2)
         clf.fit(X, y)
-        self.assertAlmostEqual(0.9246666666666666, clf.score(X, y))
+        self.assertAlmostEqual(0.944, clf.score(X, y))
 
     def test_bogus_splitter_parameter(self):
         clf = Stree(splitter="duck")