Merge branch 'master' into UpdateDocAndVersion

.github/workflows/codeql-analysis.yml

@@ -2,12 +2,12 @@ name: "CodeQL"
 
 on:
   push:
-    branches: [master]
+    branches: [ master ]
   pull_request:
     # The branches below must be a subset of the branches above
-    branches: [master]
+    branches: [ master ]
   schedule:
-    - cron: "16 17 * * 3"
+    - cron: '16 17 * * 3'
 
 jobs:
   analyze:
@@ -17,7 +17,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        language: ["python"]
+        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
@@ -28,7 +28,7 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-        uses: github/codeql-action/init@v2
+      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.
@@ -39,7 +39,7 @@ jobs:
     # 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@v2
+      uses: github/codeql-action/autobuild@v1
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 https://git.io/JvXDl
@@ -53,4 +53,4 @@ jobs:
     #   make release
 
     - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@v2
+      uses: github/codeql-action/analyze@v1

.github/workflows/main.yml

@@ -16,9 +16,9 @@ jobs:
         python: [3.8, "3.10"]
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v2
       - name: Set up Python ${{ matrix.python }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v2
         with:
           python-version: ${{ matrix.python }}
       - name: Install dependencies
@@ -35,7 +35,7 @@ jobs:
           coverage run -m unittest -v stree.tests
           coverage xml
       - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v3
+        uses: codecov/codecov-action@v1
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           files: ./coverage.xml

README.md

@@ -1,7 +1,7 @@
 ![CI](https://github.com/Doctorado-ML/STree/workflows/CI/badge.svg)
-[![CodeQL](https://github.com/Doctorado-ML/STree/actions/workflows/codeql-analysis.yml/badge.svg)](https://github.com/Doctorado-ML/STree/actions/workflows/codeql-analysis.yml)
 [![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)
@@ -15,7 +15,7 @@ Oblique Tree classifier based on SVM nodes. The nodes are built and splitted wit
 ## Installation
 
 ```bash
-pip install Stree
+pip install git+https://github.com/doctorado-ml/stree
 ```
 
 ## Documentation

notebooks/benchmark.ipynb

@@ -178,7 +178,7 @@
    "outputs": [],
    "source": [
     "# Stree\n",
-    "stree = Stree(random_state=random_state, C=.01, max_iter=1000, kernel=\"liblinear\", multiclass_strategy=\"ovr\")"
+    "stree = Stree(random_state=random_state, C=.01, max_iter=1e3, kernel=\"liblinear\", multiclass_strategy=\"ovr\")"
    ]
   },
   {
@@ -198,7 +198,7 @@
    "outputs": [],
    "source": [
     "# SVC (linear)\n",
-    "svc = LinearSVC(random_state=random_state, C=.01, max_iter=1000)"
+    "svc = LinearSVC(random_state=random_state, C=.01, max_iter=1e3)"
    ]
   },
   {

notebooks/gridsearch.ipynb

@@ -133,33 +133,33 @@
     "    'base_estimator': [Stree(random_state=random_state)],\n",
     "    'n_estimators': [10, 25],\n",
     "    'learning_rate': [.5, 1],\n",
-        "    'estimator__split_criteria': ['max_samples', 'impurity'],\n",
-        "    'estimator__tol': [.1,  1e-02],\n",
-        "    'estimator__max_depth': [3, 5, 7],\n",
-        "    'estimator__C': [1, 7, 55],\n",
-        "    'estimator__kernel': ['linear']\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",
-        "    'estimator__split_criteria': ['max_samples', 'impurity'],\n",
-        "    'estimator__tol': [.1,  1e-02],\n",
-        "    'estimator__max_depth': [3, 5, 7],\n",
-        "    'estimator__C': [1, 7, 55],\n",
-        "    'estimator__degree': [3, 5, 7],\n",
-        "    'estimator__kernel': ['poly']\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",
-        "    'estimator__split_criteria': ['max_samples', 'impurity'],\n",
-        "    'estimator__tol': [.1,  1e-02],\n",
-        "    'estimator__max_depth': [3, 5, 7],\n",
-        "    'estimator__C': [1, 7, 55],\n",
-        "    'estimator__gamma': [.1, 1, 10],\n",
-        "    'estimator__kernel': ['rbf']\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",
     "}]"
    ]
   },
@@ -214,7 +214,7 @@
     "                   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), 'estimator__C': 55, 'estimator__kernel': 'linear', 'estimator__max_depth': 7, 'estimator__split_criteria': 'max_samples', 'estimator__tol': 0.1, 'learning_rate': 0.5, 'n_estimators': 25}"
+    "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}"
    ]
   },
   {

stree/Splitter.py

@@ -267,6 +267,7 @@ class Splitter:
         random_state=None,
         normalize=False,
     ):
+
         self._clf = clf
         self._random_state = random_state
         if random_state is not None:

stree/Strees.py

@@ -139,7 +139,7 @@ class Stree(BaseEstimator, ClassifierMixin):
         self,
         C: float = 1.0,
         kernel: str = "linear",
-        max_iter: int = int(1e5),
+        max_iter: int = 1e5,
         random_state: int = None,
         max_depth: int = None,
         tol: float = 1e-4,
@@ -153,6 +153,7 @@ class Stree(BaseEstimator, ClassifierMixin):
         multiclass_strategy: str = "ovo",
         normalize: bool = False,
     ):
+
         self.max_iter = max_iter
         self.C = C
         self.kernel = kernel
@@ -484,43 +485,6 @@ class Stree(BaseEstimator, ClassifierMixin):
         X = self.check_predict(X)
         return self.classes_[np.argmax(self.__predict_class(X), axis=1)]
 
-    def get_nodes(self) -> int:
-        """Return the number of nodes in the tree
-
-        Returns
-        -------
-        int
-            number of nodes
-        """
-        nodes = 0
-        for _ in self:
-            nodes += 1
-        return nodes
-
-    def get_leaves(self) -> int:
-        """Return the number of leaves in the tree
-
-        Returns
-        -------
-        int
-            number of leaves
-        """
-        leaves = 0
-        for node in self:
-            if node.is_leaf():
-                leaves += 1
-        return leaves
-
-    def get_depth(self) -> int:
-        """Return the depth of the tree
-
-        Returns
-        -------
-        int
-            depth of the tree
-        """
-        return self.depth_
-
     def nodes_leaves(self) -> tuple:
         """Compute the number of nodes and leaves in the built tree
 

stree/_version.py

@@ -1 +1 @@
-__version__ = "1.3.2"
+__version__ = "1.3.0"

stree/tests/Stree_test.py

@@ -239,7 +239,6 @@ class Stree_test(unittest.TestCase):
             )
             tcl.fit(*load_dataset(self._random_state))
             self.assertEqual(depth, tcl.depth_)
-            self.assertEqual(depth, tcl.get_depth())
 
     def test_unfitted_tree_is_iterable(self):
         tcl = Stree()
@@ -307,10 +306,10 @@ class Stree_test(unittest.TestCase):
             for criteria in ["max_samples", "impurity"]:
                 for kernel in self._kernels:
                     clf = Stree(
-                        max_iter=int(1e4),
-                        multiclass_strategy=(
-                            "ovr" if kernel == "liblinear" else "ovo"
-                        ),
+                        max_iter=1e4,
+                        multiclass_strategy="ovr"
+                        if kernel == "liblinear"
+                        else "ovo",
                         kernel=kernel,
                         random_state=self._random_state,
                     )
@@ -641,12 +640,10 @@ class Stree_test(unittest.TestCase):
         clf = Stree(random_state=self._random_state)
         clf.fit(X, y)
         self.assertEqual(6, clf.depth_)
-        self.assertEqual(6, clf.get_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_)
-        self.assertEqual(4, clf.get_depth())
 
     def test_nodes_leaves(self):
         """Check number of nodes and leaves."""
@@ -660,17 +657,13 @@ class Stree_test(unittest.TestCase):
         clf.fit(X, y)
         nodes, leaves = clf.nodes_leaves()
         self.assertEqual(31, nodes)
-        self.assertEqual(31, clf.get_nodes())
         self.assertEqual(16, leaves)
-        self.assertEqual(16, clf.get_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(11, clf.get_nodes())
         self.assertEqual(6, leaves)
-        self.assertEqual(6, clf.get_leaves())
 
     def test_nodes_leaves_artificial(self):
         """Check leaves of artificial dataset."""
@@ -689,9 +682,7 @@ class Stree_test(unittest.TestCase):
         clf.tree_ = n1
         nodes, leaves = clf.nodes_leaves()
         self.assertEqual(6, nodes)
-        self.assertEqual(6, clf.get_nodes())
         self.assertEqual(2, leaves)
-        self.assertEqual(2, clf.get_leaves())
 
     def test_bogus_multiclass_strategy(self):
         """Check invalid multiclass strategy."""