Create codeql-analysis.yml

* Add Hyperparameters description to README
Comment get_subspace method
Add environment info for binder (runtime.txt)

* Complete source comments
Change docstring type to numpy
update hyperameters table and explanation

* Fix problem with zero weighted samples
Solve WARNING: class label x specified in weight is not found
with a different approach

* Allow update of scikitlearn to latest version

.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

requirements.txt

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

setup.py

@@ -1,6 +1,6 @@
 import setuptools
 
-__version__ = "0.9rc6"
+__version__ = "1.0rc1"
 __author__ = "Ricardo Montañana Gómez"
 
 
@@ -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", "numpy", "ipympl"],
     test_suite="stree.tests",
     zip_safe=False,
 )

stree/Strees.py

@@ -629,6 +629,12 @@ class Stree(BaseEstimator, ClassifierMixin):
         """
         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]
         if np.unique(y).shape[0] == 1:
             # only 1 class => pure dataset
             return Snode(
@@ -643,14 +649,6 @@ class Stree(BaseEstimator, ClassifierMixin):
         # Train the model
         clf = self._build_clf()
         Xs, features = self.splitter_.get_subspace(X, y, self.max_features_)
-        # solve WARNING: class label 0 specified in weight is not found
-        # in bagging
-        if any(sample_weight == 0):
-            indices = sample_weight == 0
-            y_next = y[~indices]
-            # touch weights if removing any class
-            if np.unique(y_next).shape[0] != self.n_classes_:
-                sample_weight += 1e-5
         clf.fit(Xs, y, sample_weight=sample_weight)
         impurity = self.splitter_.partition_impurity(y)
         node = Snode(clf, X, y, features, impurity, title, sample_weight)

stree/tests/Stree_test.py

@@ -413,39 +413,29 @@ class Stree_test(unittest.TestCase):
         with self.assertRaises(ValueError):
             Stree().fit(X, y, np.zeros(len(y)))
 
-    def test_weights_removing_class(self):
+    def test_mask_samples_weighted_zero(self):
-        # This patch solves an stderr message from sklearn svm lib
-        # "WARNING: class label x specified in weight is not found"
         X = np.array(
             [
-                [0.1, 0.1],
+                [1, 1],
-                [0.1, 0.2],
+                [1, 1],
-                [0.2, 0.1],
+                [1, 1],
-                [5, 6],
+                [2, 2],
-                [8, 9],
+                [2, 2],
-                [6, 7],
+                [2, 2],
-                [0.2, 0.2],
+                [3, 3],
+                [3, 3],
+                [3, 3],
             ]
         )
-        y = np.array([0, 0, 0, 1, 1, 1, 0])
+        y = np.array([1, 1, 1, 2, 2, 2, 5, 5, 5])
-        epsilon = 1e-5
+        yw = np.array([1, 1, 1, 5, 5, 5, 5, 5, 5])
-        weights = [1, 1, 1, 0, 0, 0, 1]
+        w = [1, 1, 1, 0, 0, 0, 1, 1, 1]
-        weights = np.array(weights, dtype="float64")
+        model1 = Stree().fit(X, y)
-        weights_epsilon = [x + epsilon for x in weights]
+        model2 = Stree().fit(X, y, w)
-        weights_no_zero = np.array([1, 1, 1, 0, 0, 2, 1])
+        predict1 = model1.predict(X)
-        original = weights_no_zero.copy()
+        predict2 = model2.predict(X)
-        clf = Stree()
+        self.assertListEqual(y.tolist(), predict1.tolist())
-        clf.fit(X, y)
+        self.assertListEqual(yw.tolist(), predict2.tolist())
-        node = clf.train(
+        self.assertEqual(model1.score(X, y), 1)
-            X,
+        self.assertAlmostEqual(model2.score(X, y), 0.66666667)
-            y,
+        self.assertEqual(model2.score(X, y, w), 1)
-            weights,
-            1,
-            "test",
-        )
-        # if a class is lost with zero weights the patch adds epsilon
-        self.assertListEqual(weights.tolist(), weights_epsilon)
-        self.assertListEqual(node._sample_weight.tolist(), weights_epsilon)
-        # zero weights are ok when they don't erase a class
-        _ = clf.train(X, y, weights_no_zero, 1, "test")
-        self.assertListEqual(weights_no_zero.tolist(), original.tolist())