Graphviz (#52)

* Add graphviz representation of the tree

* Complete graphviz test
Add comments to some tests

* Add optional title to tree graph

* Add fontcolor keyword to nodes of the tree

* Add color keyword to arrows of graph

* Update version file to 1.2.4

.github/workflows/main.yml

@@ -12,7 +12,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [macos-latest, ubuntu-latest]
+        os: [macos-latest, ubuntu-latest, windows-latest]
         python: [3.8]
 
     steps:

CITATION.cff

@@ -11,7 +11,7 @@ authors:
     given-names: "José M."
     orcid: "https://orcid.org/0000-0002-9164-5191"
 title: "STree"
-version: 1.0.2
+version: 1.2.3
 doi: 10.5281/zenodo.5504083
 date-released: 2021-11-02
 url: "https://github.com/Doctorado-ML/STree"

Makefile

@@ -10,6 +10,9 @@ coverage:  ## Run tests with coverage
 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
@@ -32,6 +35,9 @@ build:  ## Build package
 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/##/:/'`); \

setup.py

@@ -1,4 +1,5 @@
 import setuptools
+import os
 
 
 def readme():
@@ -8,7 +9,8 @@ def readme():
 
 def get_data(field):
     item = ""
-    with open("stree/__init__.py") as f:
+    file_name = "_version.py" if field == "version" else "__init__.py"
+    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 "'"

stree/Splitter.py

@@ -145,6 +145,28 @@ class Snode:
             except IndexError:
                 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'classes={count_values[0]} samples={count_values[1]}"];\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():
@@ -367,9 +389,8 @@ class Splitter:
             .get_support(indices=True)
         )
 
-    @staticmethod
     def _fs_mutual(
-        dataset: np.array, labels: np.array, max_features: int
+        self, dataset: np.array, labels: np.array, max_features: int
     ) -> tuple:
         """Return the best features with mutual information with labels
 
@@ -389,7 +410,9 @@ class Splitter:
             indices of the features selected
         """
         # return best features with mutual info with the label
-        feature_list = mutual_info_classif(dataset, labels)
+        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]

stree/Strees.py

@@ -17,6 +17,7 @@ from sklearn.utils.validation import (
     _check_sample_weight,
 )
 from .Splitter import Splitter, Snode, Siterator
+from ._version import __version__
 
 
 class Stree(BaseEstimator, ClassifierMixin):
@@ -169,6 +170,11 @@ class Stree(BaseEstimator, ClassifierMixin):
         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
@@ -470,6 +476,23 @@ class Stree(BaseEstimator, ClassifierMixin):
             tree = None
         return Siterator(tree)
 
+    def graph(self, title="") -> str:
+        """Graphviz code representing the tree
+
+        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 __str__(self) -> str:
         """String representation of the tree
 

stree/__init__.py

@@ -1,7 +1,5 @@
 from .Strees import Stree, Siterator
 
-__version__ = "1.2.2"
-
 __author__ = "Ricardo Montañana Gómez"
 __copyright__ = "Copyright 2020-2021, Ricardo Montañana Gómez"
 __license__ = "MIT License"

stree/_version.py

@@ -0,0 +1 @@
+__version__ = "1.2.4"

stree/tests/Stree_test.py

@@ -10,6 +10,7 @@ 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):
@@ -357,6 +358,7 @@ class Stree_test(unittest.TestCase):
 
     # Tests of score
     def test_score_binary(self):
+        """Check score for binary classification."""
         X, y = load_dataset(self._random_state)
         accuracies = [
             0.9506666666666667,
@@ -379,6 +381,7 @@ class Stree_test(unittest.TestCase):
             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",
@@ -390,6 +393,7 @@ class Stree_test(unittest.TestCase):
         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())
@@ -445,6 +449,7 @@ class Stree_test(unittest.TestCase):
         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,
@@ -462,6 +467,7 @@ class Stree_test(unittest.TestCase):
         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,
@@ -483,6 +489,7 @@ class Stree_test(unittest.TestCase):
         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,
@@ -508,6 +515,7 @@ class Stree_test(unittest.TestCase):
         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,
@@ -528,6 +536,7 @@ class Stree_test(unittest.TestCase):
         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(
@@ -555,11 +564,13 @@ class Stree_test(unittest.TestCase):
         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],
@@ -587,6 +598,7 @@ class Stree_test(unittest.TestCase):
         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,
@@ -602,6 +614,7 @@ class Stree_test(unittest.TestCase):
         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,
@@ -621,6 +634,7 @@ class Stree_test(unittest.TestCase):
         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")
@@ -639,12 +653,14 @@ class Stree_test(unittest.TestCase):
         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")
@@ -654,6 +670,7 @@ class Stree_test(unittest.TestCase):
         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):
@@ -661,3 +678,50 @@ class Stree_test(unittest.TestCase):
         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 '
+            'classes=[1] samples=[1]"];\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 '
+            'classes=[1] samples=[1]"];\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)