Add select KBest features #17

Add a test
Fix #27

.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]
+        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

.gitignore

@@ -133,3 +133,4 @@ dmypy.json
 .pre-commit-config.yaml
 
 **.csv
+.virtual_documents

README.md

@@ -1,6 +1,6 @@
-[![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)
+![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)
+[![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
 
@@ -18,23 +18,43 @@ 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
+- [![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
 
-* [![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
+- [![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
 
-* [![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
+- [![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
 
-* [![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
+## Hyperparameters
 
-### Command line
+|     | **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             | {"linear", "poly", "rbf"}                              | linear      | Specifies the kernel type to be used in the algorithm. It must be one of ‘linear’, ‘poly’ or ‘rbf’.                                                                                                                                                                                                                                                                                                                                                  |
+| \*  | 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’ and ‘poly’.<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\*\*                                                                                                                                                                                                                                                                                                                                   |
+|     | 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"}                                     | random      | The strategy used to choose the feature set at each node (only used if max_features != num_features). <br>Supported strategies are “best” to choose the best feature set and “random” to choose a random combination. <br>The algorithm generates 5 candidates at most to choose from in both strategies.                                                                                                                                            |
 
-```bash
+\* Hyperparameter used by the support vector classifier of every node
-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
 

main.py

@@ -8,7 +8,7 @@ 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
+    X, y, test_size=0.3, random_state=random_state
 )
 
 now = time.time()

notebooks/ensemble.ipynb

@@ -17,35 +17,43 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "#\n",
     "# Google Colab setup\n",
     "#\n",
-    "#!pip install git+https://github.com/doctorado-ml/stree"
+    "#!pip install git+https://github.com/doctorado-ml/stree\n",
+    "!pip install pandas"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "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 stree import Stree"
+    "from sklearn.exceptions import ConvergenceWarning\n",
+    "from stree import Stree\n",
+    "\n",
+    "warnings.filterwarnings(\"ignore\", category=ConvergenceWarning)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "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"
@@ -53,24 +61,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {
     "tags": []
    },
-   "outputs": [
+   "outputs": [],
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "Fraud: 0.173% 492\nValid: 99.827% 284315\nX.shape (100492, 28)  y.shape (100492,)\nFraud: 0.644% 647\nValid: 99.356% 99845\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",
@@ -121,20 +120,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {
     "tags": []
    },
-   "outputs": [
+   "outputs": [],
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "Score Train:  0.9985784146480154\nScore Test:  0.9981093273185617\nTook 73.27 seconds\n"
-    }
-   ],
    "source": [
     "now = time.time()\n",
-    "clf = Stree(max_depth=3, random_state=random_state)\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",
@@ -150,7 +143,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -161,21 +154,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "metadata": {
     "tags": []
    },
-   "outputs": [
+   "outputs": [],
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "Kernel: linear\tTime: 93.78 seconds\tScore Train: 0.9983083\tScore Test: 0.9983083\nKernel: rbf\tTime: 18.32 seconds\tScore Train: 0.9935602\tScore Test: 0.9935651\nKernel: poly\tTime: 69.68 seconds\tScore Train: 0.9973132\tScore Test: 0.9972801\n"
-    }
-   ],
    "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), algorithm=\"SAMME\", n_estimators=n_estimators, random_state=random_state)\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",
@@ -191,7 +178,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -202,21 +189,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "metadata": {
     "tags": []
    },
-   "outputs": [
+   "outputs": [],
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "Kernel: linear\tTime: 387.06 seconds\tScore Train: 0.9985784\tScore Test: 0.9981093\nKernel: rbf\tTime: 144.00 seconds\tScore Train: 0.9992750\tScore Test: 0.9983415\nKernel: poly\tTime: 101.78 seconds\tScore Train: 0.9992466\tScore Test: 0.9981757\n"
-    }
-   ],
    "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), n_estimators=n_estimators, random_state=random_state)\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",
@@ -225,6 +206,11 @@
   }
  ],
  "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
@@ -235,14 +221,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.6-final"
+   "version": "3.8.2-final"
-  },
-  "orig_nbformat": 2,
-  "kernelspec": {
-   "name": "python37664bitgeneralvenve3128601eb614c5da59c5055670b6040",
-   "display_name": "Python 3.7.6 64-bit ('general': venv)"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

notebooks/gridsearch.ipynb

@@ -18,64 +18,67 @@
   },
   {
    "cell_type": "code",
-      "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "#\n",
     "# Google Colab setup\n",
     "#\n",
-        "#!pip install git+https://github.com/doctorado-ml/stree"
+    "#!pip install git+https://github.com/doctorado-ml/stree\n",
+    "!pip install pandas"
    ]
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
-        "id": "zIHKVxthDZEa",
+    "colab": {},
     "colab_type": "code",
-        "colab": {}
+    "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"
-      ],
+   ]
-      "execution_count": 2,
-      "outputs": []
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
-        "id": "IEmq50QgDZEi",
+    "colab": {},
     "colab_type": "code",
-        "colab": {}
+    "id": "IEmq50QgDZEi"
    },
+   "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"
-      ],
+   ]
-      "execution_count": 3,
-      "outputs": []
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
-        "id": "z9Q-YUfBDZEq",
-        "colab_type": "code",
     "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",
-        "    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",
@@ -107,14 +110,6 @@
     "Xtest = data[1]\n",
     "ytrain = data[2]\n",
     "ytest = data[3]"
-      ],
-      "execution_count": 4,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": "Fraud: 0.173% 492\nValid: 99.827% 284315\nX.shape (1492, 28)  y.shape (1492,)\nFraud: 32.976% 492\nValid: 67.024% 1000\n"
-        }
    ]
   },
   {
@@ -126,100 +121,120 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
-        "id": "HmX3kR4PDZEw",
+    "colab": {},
     "colab_type": "code",
-        "colab": {}
+    "id": "HmX3kR4PDZEw"
    },
+   "outputs": [],
    "source": [
-        "parameters = {\n",
+    "parameters = [{\n",
-        "    'base_estimator': [Stree()],\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],\n",
+    "    'base_estimator__max_depth': [3, 5, 7],\n",
-        "    'base_estimator__C': [7, 55],\n",
+    "    'base_estimator__C': [1, 7, 55],\n",
-        "    'base_estimator__kernel': ['linear', 'poly', 'rbf']\n",
+    "    'base_estimator__kernel': ['linear']\n",
-        "}"
+    "},\n",
-      ],
+    "{\n",
-      "execution_count": 5,
+    "    'base_estimator': [Stree(random_state=random_state)],\n",
-      "outputs": []
+    "    '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": 6,
+   "execution_count": null,
    "metadata": {},
-      "outputs": [
+   "outputs": [],
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": "{'C': 1.0,\n 'criterion': 'gini',\n 'degree': 3,\n 'gamma': 'scale',\n 'kernel': 'linear',\n 'max_depth': None,\n 'max_features': None,\n 'max_iter': 1000,\n 'min_samples_split': 0,\n 'random_state': None,\n 'split_criteria': 'max_samples',\n 'splitter': 'random',\n 'tol': 0.0001}"
-          },
-          "metadata": {},
-          "execution_count": 6
-        }
-      ],
    "source": [
     "Stree().get_params()"
    ]
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
-        "id": "CrcB8o6EDZE5",
-        "colab_type": "code",
     "colab": {},
+    "colab_type": "code",
+    "id": "CrcB8o6EDZE5",
     "outputId": "7703413a-d563-4289-a13b-532f38f82762",
     "tags": []
    },
+   "outputs": [],
    "source": [
-        "random_state=2020\n",
     "clf = AdaBoostClassifier(random_state=random_state, algorithm=\"SAMME\")\n",
-        "grid = GridSearchCV(clf, parameters, verbose=10, n_jobs=-1, return_train_score=True)\n",
+    "grid = GridSearchCV(clf, parameters, verbose=5, n_jobs=-1, return_train_score=True)\n",
     "grid.fit(Xtrain, ytrain)"
-      ],
-      "execution_count": 7,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": "Fitting 5 folds for each of 96 candidates, totalling 480 fits\n[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n[Parallel(n_jobs=-1)]: Done   2 tasks      | elapsed:    2.0s\n[Parallel(n_jobs=-1)]: Done   9 tasks      | elapsed:    2.4s\n[Parallel(n_jobs=-1)]: Done  16 tasks      | elapsed:    2.7s\n[Parallel(n_jobs=-1)]: Done  25 tasks      | elapsed:    3.3s\n[Parallel(n_jobs=-1)]: Done  34 tasks      | elapsed:    4.3s\n[Parallel(n_jobs=-1)]: Done  45 tasks      | elapsed:    5.3s\n[Parallel(n_jobs=-1)]: Done  56 tasks      | elapsed:    6.6s\n[Parallel(n_jobs=-1)]: Done  69 tasks      | elapsed:    8.1s\n[Parallel(n_jobs=-1)]: Done  82 tasks      | elapsed:    9.4s\n[Parallel(n_jobs=-1)]: Done  97 tasks      | elapsed:   10.1s\n[Parallel(n_jobs=-1)]: Done 112 tasks      | elapsed:   11.1s\n[Parallel(n_jobs=-1)]: Done 129 tasks      | elapsed:   12.3s\n[Parallel(n_jobs=-1)]: Done 146 tasks      | elapsed:   13.6s\n[Parallel(n_jobs=-1)]: Done 165 tasks      | elapsed:   14.9s\n[Parallel(n_jobs=-1)]: Done 184 tasks      | elapsed:   16.2s\n[Parallel(n_jobs=-1)]: Done 205 tasks      | elapsed:   17.6s\n[Parallel(n_jobs=-1)]: Done 226 tasks      | elapsed:   19.1s\n[Parallel(n_jobs=-1)]: Done 249 tasks      | elapsed:   21.6s\n[Parallel(n_jobs=-1)]: Done 272 tasks      | elapsed:   25.9s\n[Parallel(n_jobs=-1)]: Done 297 tasks      | elapsed:   30.4s\n[Parallel(n_jobs=-1)]: Done 322 tasks      | elapsed:   36.7s\n[Parallel(n_jobs=-1)]: Done 349 tasks      | elapsed:   38.1s\n[Parallel(n_jobs=-1)]: Done 376 tasks      | elapsed:   39.6s\n[Parallel(n_jobs=-1)]: Done 405 tasks      | elapsed:   41.9s\n[Parallel(n_jobs=-1)]: Done 434 tasks      | elapsed:   44.9s\n[Parallel(n_jobs=-1)]: Done 465 tasks      | elapsed:   48.2s\n[Parallel(n_jobs=-1)]: Done 480 out of 480 | elapsed:   49.2s finished\n"
-        },
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": "GridSearchCV(estimator=AdaBoostClassifier(algorithm='SAMME', random_state=2020),\n             n_jobs=-1,\n             param_grid={'base_estimator': [Stree(C=55, max_depth=3, tol=0.01)],\n                         'base_estimator__C': [7, 55],\n                         'base_estimator__kernel': ['linear', 'poly', 'rbf'],\n                         'base_estimator__max_depth': [3, 5],\n                         'base_estimator__tol': [0.1, 0.01],\n                         'learning_rate': [0.5, 1], 'n_estimators': [10, 25]},\n             return_train_score=True, verbose=10)"
-          },
-          "metadata": {},
-          "execution_count": 7
-        }
    ]
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "metadata": {
-        "id": "ZjX88NoYDZE8",
-        "colab_type": "code",
     "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_)"
-      ],
+   ]
-      "execution_count": 8,
+  },
-      "outputs": [
   {
-          "output_type": "stream",
+   "cell_type": "markdown",
-          "name": "stdout",
+   "metadata": {},
-          "text": "Best estimator:  AdaBoostClassifier(algorithm='SAMME',\n                   base_estimator=Stree(C=55, max_depth=3, tol=0.01),\n                   learning_rate=0.5, n_estimators=25, random_state=2020)\nBest hyperparameters:  {'base_estimator': Stree(C=55, max_depth=3, tol=0.01), 'base_estimator__C': 55, 'base_estimator__kernel': 'linear', 'base_estimator__max_depth': 3, 'base_estimator__tol': 0.01, 'learning_rate': 0.5, 'n_estimators': 25}\nBest accuracy:  0.9559440559440558\n"
+   "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",
@@ -230,18 +245,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-      "version": "3.7.6-final"
+   "version": "3.8.2-final"
-    },
-    "orig_nbformat": 2,
-    "kernelspec": {
-      "name": "python37664bitgeneralvenvfbd0a23e74cf4e778460f5ffc6761f39",
-      "display_name": "Python 3.7.6 64-bit ('general': venv)"
-    },
-    "colab": {
-      "name": "gridsearch.ipynb",
-      "provenance": []
   }
  },
  "nbformat": 4,
-  "nbformat_minor": 0
+ "nbformat_minor": 4
 }

requirements.txt

@@ -1,4 +1 @@
-numpy
+scikit-learn>0.24
-scikit-learn
-pandas
-ipympl

runtime.txt

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

setup.py

@@ -1,6 +1,6 @@
 import setuptools
 
-__version__ = "0.9rc5"
+__version__ = "1.0rc1"
 __author__ = "Ricardo Montañana Gómez"
 
 
@@ -25,12 +25,12 @@ setuptools.setup(
     classifiers=[
         "Development Status :: 4 - Beta",
         "License :: OSI Approved :: MIT License",
-        "Programming Language :: Python :: 3.7",
+        "Programming Language :: Python :: 3.8",
         "Natural Language :: English",
         "Topic :: Scientific/Engineering :: Artificial Intelligence",
         "Intended Audience :: Science/Research",
     ],
-    install_requires=["scikit-learn>=0.23.0", "numpy", "ipympl"],
+    install_requires=["scikit-learn", "numpy", "ipympl"],
     test_suite="stree.tests",
     zip_safe=False,
 )

stree/Strees.py

@@ -3,18 +3,20 @@ __author__ = "Ricardo Montañana Gómez"
 __copyright__ = "Copyright 2020, Ricardo Montañana Gómez"
 __license__ = "MIT"
 __version__ = "0.9"
-Build an oblique tree classifier based on SVM Trees
+Build an oblique tree classifier based on SVM nodes
 """
 
 import os
 import numbers
 import random
 import warnings
-from math import log
+from math import log, factorial
-from itertools import combinations
+from typing import Optional
 import numpy as np
 from sklearn.base import BaseEstimator, ClassifierMixin
 from sklearn.svm import SVC, LinearSVC
+from sklearn.feature_selection import SelectKBest
+from sklearn.preprocessing import StandardScaler
 from sklearn.utils import check_consistent_length
 from sklearn.utils.multiclass import check_classification_targets
 from sklearn.exceptions import ConvergenceWarning
@@ -41,6 +43,7 @@ class Snode:
         impurity: float,
         title: str,
         weight: np.ndarray = None,
+        scaler: StandardScaler = None,
     ):
         self._clf = clf
         self._title = title
@@ -57,6 +60,8 @@ class Snode:
         )
         self._features = features
         self._impurity = impurity
+        self._partition_column: int = -1
+        self._scaler = scaler
 
     @classmethod
     def copy(cls, node: "Snode") -> "Snode":
@@ -67,11 +72,43 @@ class Snode:
             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
 
@@ -93,9 +130,8 @@ class Snode:
         classes, card = np.unique(self._y, return_counts=True)
         if len(classes) > 1:
             max_card = max(card)
-            min_card = min(card)
             self._class = classes[card == max_card][0]
-            self._belief = max_card / (max_card + min_card)
+            self._belief = max_card / np.sum(card)
         else:
             self._belief = 1
             try:
@@ -104,24 +140,23 @@ class Snode:
                 self._class = None
 
     def __str__(self) -> str:
-        if self.is_leaf():
         count_values = np.unique(self._y, return_counts=True)
-            result = (
+        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 result
         else:
             return (
                 f"{self._title} feaures={self._features} impurity="
-                f"{self._impurity:.4f}"
+                f"{self._impurity:.4f} "
+                f"counts={count_values}"
             )
 
 
 class Siterator:
-    """Stree preorder iterator
+    """Stree preorder iterator"""
-    """
 
     def __init__(self, tree: Snode):
         self._stack = []
@@ -145,10 +180,11 @@ class Splitter:
         self,
         clf: SVC = None,
         criterion: str = None,
-        splitter_type: 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
@@ -157,7 +193,8 @@ class Splitter:
         self._criterion = criterion
         self._min_samples_split = min_samples_split
         self._criteria = criteria
-        self._splitter_type = splitter_type
+        self._feature_select = feature_select
+        self._normalize = normalize
 
         if clf is None:
             raise ValueError(f"clf has to be a sklearn estimator, got({clf})")
@@ -167,20 +204,23 @@ class Splitter:
                 f"criterion must be gini or entropy got({criterion})"
             )
 
-        if criteria not in ["min_distance", "max_samples", "max_distance"]:
+        if criteria not in [
+            "max_samples",
+            "impurity",
+        ]:
             raise ValueError(
-                "split_criteria has to be min_distance "
+                f"criteria has to be max_samples or impurity; got ({criteria})"
-                f"max_distance or max_samples got ({criteria})"
             )
 
-        if splitter_type not in ["random", "best"]:
+        if feature_select not in ["random", "best"]:
             raise ValueError(
-                f"splitter must be either random or best got({splitter_type})"
+                "splitter must be either random or best, got "
+                f"({feature_select})"
             )
         self.criterion_function = getattr(self, f"_{self._criterion}")
         self.decision_criteria = getattr(self, f"_{self._criteria}")
 
-    def impurity(self, y: np.array) -> np.array:
+    def partition_impurity(self, y: np.array) -> np.array:
         return self.criterion_function(y)
 
     @staticmethod
@@ -190,6 +230,18 @@ class Splitter:
 
     @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
@@ -208,6 +260,22 @@ class Splitter:
     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:
@@ -238,7 +306,7 @@ class Splitter:
             node = Snode(
                 self._clf, dataset, labels, feature_set, 0.0, "subset"
             )
-            self.partition(dataset, node)
+            self.partition(dataset, node, train=True)
             y1, y2 = self.part(labels)
             gain = self.information_gain(labels, y1, y2)
             if gain > max_gain:
@@ -246,124 +314,210 @@ 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:
+        """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
-    ) -> np.array:
+    ) -> tuple:
-        features = range(dataset.shape[1])
+        """Compute the indices of the features selected by splitter depending
-        features_sets = list(combinations(features, max_features))
+        on the self._feature_select hyper parameter
-        if len(features_sets) > 1:
+
-            if self._splitter_type == "random":
+        Parameters
-                index = random.randint(0, len(features_sets) - 1)
+        ----------
-                return features_sets[index]
+        dataset : np.array
-            else:
+            array of samples
-                # get only 3 sets at most
+        labels : np.array
-                if len(features_sets) > 3:
+            labels of the dataset
-                    features_sets = random.sample(features_sets, 3)
+        max_features : int
+            number of features of the subspace
+            (<= number of features in dataset)
+
+        Returns
+        -------
+        tuple
+            indices of the features selected
+        """
+        if dataset.shape[1] == max_features:
+            # No feature reduction applies
+            return tuple(range(dataset.shape[1]))
+        if self._feature_select == "random":
+            features_sets = self._generate_spaces(
+                dataset.shape[1], max_features
+            )
             return self._select_best_set(dataset, labels, features_sets)
-        else:
+        # Take KBest features
-            return features_sets[0]
+        return (
+            SelectKBest(k=max_features)
+            .fit(dataset, labels)
+            .get_support(indices=True)
+        )
 
     def get_subspace(
         self, dataset: np.array, labels: np.array, max_features: int
-    ) -> list:
+    ) -> tuple:
-        """Return the best subspace to make a split
+        """Re3turn a subspace of the selected dataset of max_features length.
+        Depending on hyperparmeter
+
+        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
 
-    @staticmethod
+    def _impurity(self, data: np.array, y: np.array) -> np.array:
-    def _min_distance(data: np.array, _) -> np.array:
+        """return column of dataset to be taken into account to split dataset
-        """Assign class to min distances
 
-        return a vector of classes so partition can separate class 0 from
+        Parameters
-        the rest of classes, ie. class 0 goes to one splitted node and the
+        ----------
-        rest of classes go to the other
+        data : np.array
-        :param data: distances to hyper plane of every class
+            distances to hyper plane of every class
-        :type data: np.array (m, n_classes)
+        y : np.array
-        :param _: enable call compat with other measures
+            vector of labels (classes)
-        :type _: None
+
-        :return: vector with the class assigned to each sample
+        Returns
-        :rtype: np.array shape (m,)
+        -------
+        np.array
+            column of dataset to be taken into account to split dataset
         """
-        return np.argmin(data, axis=1)
+        max_gain = 0
-
+        selected = -1
-    @staticmethod
+        for col in range(data.shape[1]):
-    def _max_distance(data: np.array, _) -> np.array:
+            tup = y[data[:, col] > 0]
-        """Assign class to max distances
+            tdn = y[data[:, col] <= 0]
-
+            info_gain = self.information_gain(y, tup, tdn)
-        return a vector of classes so partition can separate class 0 from
+            if info_gain > max_gain:
-        the rest of classes, ie. class 0 goes to one splitted node and the
+                selected = col
-        rest of classes go to the other
+                max_gain = info_gain
-        :param data: distances to hyper plane of every class
+        return selected
-        :type data: np.array (m, n_classes)
-        :param _: enable call compat with other measures
-        :type _: None
-        :return: vector with the class assigned to each sample values
-        (can be 0, 1, ...)
-        :rtype: np.array shape (m,)
-        """
-        return np.argmax(data, axis=1)
 
     @staticmethod
     def _max_samples(data: np.array, y: np.array) -> np.array:
-        """return distances of the class with more samples
+        """return column of dataset to be taken into account to split dataset
 
-        :param data: distances to hyper plane of every class
+        Parameters
-        :type data: np.array (m, n_classes)
+        ----------
-        :param y: vector of labels (classes)
+        data : np.array
-        :type y: np.array (m,)
+            distances to hyper plane of every class
-        :return: vector with distances to hyperplane (can be positive or neg.)
+        y : np.array
-        :rtype: np.array shape (m,)
+            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)
-        selected = np.argmax(samples)
+        return np.argmax(samples)
-        return data[:, selected]
 
-    def partition(self, samples: np.array, node: Snode):
+    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 (down)
+        that should go to one side of the tree (up)
-
         """
+        # 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:
-            self._down = np.ones((data.shape[0]), dtype=bool)
+            # 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
-            data = self.decision_criteria(data, node._y)
+            # Convert data to a (m, 1) array selecting values for samples
-        self._down = data > 0
+            if train:
-
+                # in train time we have to compute the column to take into
-    @staticmethod
+                # account to split the dataset
-    def _distances(node: Snode, data: np.ndarray) -> np.array:
+                col = self.decision_criteria(data, node._y)
-        """Compute distances of the samples to the hyperplane of the node
+                node.set_partition_column(col)
-
+            else:
-        :param node: node containing the svm classifier
+                # in predcit time just use the column computed in train time
-        :type node: Snode
+                # is taking the classifier of class <col>
-        :param data: samples to find out distance to hyperplane
+                col = node.get_partition_column()
-        :type data: np.ndarray
+            if col == -1:
-        :return: array of shape (m, 1) with the distances of every sample to
+                # No partition is producing information gain
-        the hyperplane of the node
+                data = np.ones(data.shape)
-        :rtype: np.array
+            data = data[:, col]
-        """
+        self._up = data > 0
-        return node._clf.decision_function(data[:, node._features])
 
     def part(self, origin: np.array) -> list:
-        """Split an array in two based on indices (down) and its complement
+        """Split an array in two based on indices (self._up) and its complement
+        partition has to be called first to establish up indices
 
-        :param origin: dataset to split
+        Parameters
-        :type origin: np.array
+        ----------
-        :param down: indices to use to split array
+        origin : np.array
-        :type down: np.array
+            dataset to split
-        :return: list with two splits of the array
+
-        :rtype: list
+        Returns
+        -------
+        list
+            list with two splits of the array
         """
-        up = ~self._down
+        down = ~self._up
         return [
-            origin[up] if any(up) else None,
+            origin[self._up] if any(self._up) else None,
-            origin[self._down] if any(self._down) 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)
+
 
 class Stree(BaseEstimator, ClassifierMixin):
     """Estimator that is based on binary trees of svm nodes
@@ -377,17 +531,18 @@ class Stree(BaseEstimator, ClassifierMixin):
         self,
         C: float = 1.0,
         kernel: str = "linear",
-        max_iter: int = 1000,
+        max_iter: int = 1e5,
         random_state: int = None,
         max_depth: int = None,
         tol: float = 1e-4,
         degree: int = 3,
         gamma="scale",
-        split_criteria: str = "max_samples",
+        split_criteria: str = "impurity",
-        criterion: str = "gini",
+        criterion: str = "entropy",
         min_samples_split: int = 0,
         max_features=None,
         splitter: str = "random",
+        normalize: bool = False,
     ):
         self.max_iter = max_iter
         self.C = C
@@ -402,9 +557,11 @@ class Stree(BaseEstimator, ClassifierMixin):
         self.max_features = max_features
         self.criterion = criterion
         self.splitter = splitter
+        self.normalize = normalize
 
     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
@@ -416,16 +573,19 @@ class Stree(BaseEstimator, ClassifierMixin):
     ) -> "Stree":
         """Build the tree based on the dataset of samples and its labels
 
-        :param X: dataset of samples to make predictions
+        Returns
-        :type X: np.array
+        -------
-        :param y: samples labels
+        Stree
-        :type y: np.array
+            itself to be able to chain actions: fit().predict() ...
-        :param sample_weight: weights of the samples. Rescale C per sample.
+
-        Hi' weights force the classifier to put more emphasis on these points
+        Raises
-        :type sample_weight: np.array optional
+        ------
-        :raises ValueError: if parameters C or max_depth are out of bounds
+        ValueError
-        :return: itself to be able to chain actions: fit().predict() ...
+            if C < 0
-        :rtype: Stree
+        ValueError
+            if max_depth < 1
+        ValueError
+            if all samples have 0 or negative weights
         """
         # Check parameters are Ok.
         if self.C < 0:
@@ -448,15 +608,20 @@ class Stree(BaseEstimator, ClassifierMixin):
         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,
-            splitter_type=self.splitter,
+            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)
@@ -469,6 +634,8 @@ class Stree(BaseEstimator, ClassifierMixin):
         self.max_features_ = self._initialize_max_features()
         self.tree_ = self.train(X, y, sample_weight, 1, "root")
         self._build_predictor()
+        self.X_ = X
+        self.y_ = y
         return self
 
     def train(
@@ -478,74 +645,73 @@ class Stree(BaseEstimator, ClassifierMixin):
         sample_weight: np.ndarray,
         depth: int,
         title: str,
-    ) -> Snode:
+    ) -> Optional[Snode]:
         """Recursive function to split the original dataset into predictor
         nodes (leaves)
 
-        :param X: samples dataset
+        Parameters
-        :type X: np.ndarray
+        ----------
-        :param y: samples labels
+        X : np.ndarray
-        :type y: np.ndarray
+            samples dataset
-        :param sample_weight: weight of samples. Rescale C per sample.
+        y : np.ndarray
-        Hi weights force the classifier to put more emphasis on these points.
+            samples labels
-        :type sample_weight: np.ndarray
+        sample_weight : np.ndarray
-        :param depth: actual depth in the tree
+            weight of samples. Rescale C per sample.
-        :type depth: int
+        depth : int
-        :param title: description of the node
+            actual depth in the tree
-        :type title: str
+        title : str
-        :return: binary tree
+            description of the node
-        :rtype: Snode
+
+        Returns
+        -------
+        Optional[Snode]
+            binary tree
         """
         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(
+            node.set_title(title + ", <pure>")
-                clf=None,
+            return node
-                X=X,
-                y=y,
-                features=X.shape[1],
-                impurity=0.0,
-                title=title + ", <pure>",
-                weight=sample_weight,
-            )
         # 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
+        if self.normalize:
-        # in bagging
+            scaler.fit(Xs)
-        if any(sample_weight == 0):
+            Xs = scaler.transform(Xs)
-            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_.impurity(y)
+        node.set_impurity(self.splitter_.partition_impurity(y))
-        node = Snode(clf, X, y, features, impurity, title, sample_weight)
+        node.set_classifier(clf)
-        self.depth_ = max(depth, self.depth_)
+        node.set_features(features)
-        self.splitter_.partition(X, node)
+        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(
+            node.set_title(title + ", <cgaf>")
-                clf,
+            return node
-                X,
+        node.set_up(
-                y,
+            self.train(X_U, y_u, sw_u, depth + 1, title + f" - Up({depth+1})")
-                features=X.shape[1],
+        )
-                impurity=impurity,
+        node.set_down(
-                title=title + ", <cgaf>",
+            self.train(
-                weight=sample_weight,
+                X_D, y_d, sw_d, depth + 1, title + f" - Down({depth+1})"
+            )
         )
-        node.set_up(self.train(X_U, y_u, sw_u, depth + 1, title + " - Up"))
-        node.set_down(self.train(X_D, y_d, sw_d, depth + 1, title + " - Down"))
         return node
 
     def _build_predictor(self):
-        """Process the leaves to make them predictors
+        """Process the leaves to make them predictors"""
-        """
 
         def run_tree(node: Snode):
             if node.is_leaf():
@@ -557,8 +723,7 @@ class Stree(BaseEstimator, ClassifierMixin):
         run_tree(self.tree_)
 
     def _build_clf(self):
-        """ Build the correct classifier for the node
+        """Build the correct classifier for the node"""
-        """
         return (
             LinearSVC(
                 max_iter=self.max_iter,
@@ -581,12 +746,17 @@ class Stree(BaseEstimator, ClassifierMixin):
     def _reorder_results(y: np.array, indices: np.array) -> np.array:
         """Reorder an array based on the array of indices passed
 
-        :param y: data untidy
+        Parameters
-        :type y: np.array
+        ----------
-        :param indices: indices used to set order
+        y : np.array
-        :type indices: np.array
+            data untidy
-        :return: array y ordered
+        indices : np.array
-        :rtype: np.array
+            indices used to set order
+
+        Returns
+        -------
+        np.array
+            array y ordered
         """
         # return array of same type given in y
         y_ordered = y.copy()
@@ -598,10 +768,22 @@ class Stree(BaseEstimator, ClassifierMixin):
     def predict(self, X: np.array) -> np.array:
         """Predict labels for each sample in dataset passed
 
-        :param X: dataset of samples
+        Parameters
-        :type X: np.array
+        ----------
-        :return: array of labels
+        X : np.array
-        :rtype: 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
         """
 
         def predict_class(
@@ -613,7 +795,7 @@ class Stree(BaseEstimator, ClassifierMixin):
                 # set a class for every sample in dataset
                 prediction = np.full((xp.shape[0], 1), node._class)
                 return prediction, indices
-            self.splitter_.partition(xp, node)
+            self.splitter_.partition(xp, node, train=False)
             x_u, x_d = self.splitter_.part(xp)
             i_u, i_d = self.splitter_.part(indices)
             prx_u, prin_u = predict_class(x_u, i_u, node.get_up())
@@ -643,15 +825,19 @@ class Stree(BaseEstimator, ClassifierMixin):
     ) -> float:
         """Compute accuracy of the prediction
 
-        :param X: dataset of samples to make predictions
+        Parameters
-        :type X: np.array
+        ----------
-        :param y_true: samples labels
+        X : np.array
-        :type y_true: np.array
+            dataset of samples to make predictions
-        :param sample_weight: weights of the samples. Rescale C per sample.
+        y : np.array
-        Hi' weights force the classifier to put more emphasis on these points
+            samples labels
-        :type sample_weight: np.array optional
+        sample_weight : np.array, optional
-        :return: accuracy of the prediction
+            weights of the samples. Rescale C per sample, by default None
-        :rtype: float
+
+        Returns
+        -------
+        float
+            accuracy of the prediction
         """
         # sklearn check
         check_is_fitted(self)
@@ -664,12 +850,30 @@ class Stree(BaseEstimator, ClassifierMixin):
         score = y_true == y_pred
         return _weighted_sum(score, sample_weight, normalize=True)
 
+    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():
+                leaves += 1
+        return nodes, leaves
+
     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
 
-        :return: an iterator, can for i in... and list(...)
+        Returns
-        :rtype: Siterator
+        -------
+        Siterator
+            an iterator, can for i in... and list(...)
         """
         try:
             tree = self.tree_
@@ -680,8 +884,10 @@ class Stree(BaseEstimator, ClassifierMixin):
     def __str__(self) -> str:
         """String representation of the tree
 
-        :return: description of nodes in the tree in preorder
+        Returns
-        :rtype: str
+        -------
+        str
+            description of nodes in the tree in preorder
         """
         output = ""
         for i in self:

stree/tests/Snode_test.py

@@ -1,8 +1,6 @@
 import os
 import unittest
-
 import numpy as np
-
 from stree import Stree, Snode
 from .utils import load_dataset
 
@@ -40,12 +38,13 @@ class Snode_test(unittest.TestCase):
             # 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
+        """Check if the nodes of the tree have the right attributes filled"""
-        """
 
         def run_tree(node: Snode):
             if node._belief < 1:
@@ -54,16 +53,44 @@ class Snode_test(unittest.TestCase):
                 self.assertIsNotNone(node._clf.coef_)
             if node.is_leaf():
                 return
-            run_tree(node.get_down())
             run_tree(node.get_up())
+            run_tree(node.get_down())
 
-        run_tree(self._clf.tree_)
+        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()
         self.assertEqual(1, test._class)
         self.assertEqual(0.75, test._belief)
+        self.assertEqual(-1, test._partition_column)
+
+    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_make_predictor_on_not_leaf(self):
         test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
@@ -71,11 +98,14 @@ class Snode_test(unittest.TestCase):
         test.make_predictor()
         self.assertIsNone(test._class)
         self.assertEqual(0, test._belief)
+        self.assertEqual(-1, test._partition_column)
+        self.assertEqual(-1, test.get_up()._partition_column)
 
     def test_make_predictor_on_leaf_bogus_data(self):
         test = Snode(None, [1, 2, 3, 4], [], [], 0.0, "test")
         test.make_predictor()
         self.assertIsNone(test._class)
+        self.assertEqual(-1, test._partition_column)
 
     def test_copy_node(self):
         px = [1, 2, 3, 4]
@@ -86,3 +116,6 @@ class Snode_test(unittest.TestCase):
         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

@@ -6,6 +6,7 @@ import numpy as np
 from sklearn.svm import SVC
 from sklearn.datasets import load_wine, load_iris
 from stree import Splitter
+from .utils import load_dataset
 
 
 class Splitter_test(unittest.TestCase):
@@ -17,15 +18,15 @@ class Splitter_test(unittest.TestCase):
     def build(
         clf=SVC,
         min_samples_split=0,
-        splitter_type="random",
+        feature_select="random",
         criterion="gini",
-        criteria="min_distance",
+        criteria="max_samples",
         random_state=None,
     ):
         return Splitter(
             clf=clf(random_state=random_state, kernel="rbf"),
             min_samples_split=min_samples_split,
-            splitter_type=splitter_type,
+            feature_select=feature_select,
             criterion=criterion,
             criteria=criteria,
             random_state=random_state,
@@ -39,24 +40,20 @@ class Splitter_test(unittest.TestCase):
         with self.assertRaises(ValueError):
             self.build(criterion="duck")
         with self.assertRaises(ValueError):
-            self.build(splitter_type="duck")
+            self.build(feature_select="duck")
         with self.assertRaises(ValueError):
             self.build(criteria="duck")
         with self.assertRaises(ValueError):
             _ = Splitter(clf=None)
-        for splitter_type in ["best", "random"]:
+        for feature_select in ["best", "random"]:
             for criterion in ["gini", "entropy"]:
-                for criteria in [
+                for criteria in ["max_samples", "impurity"]:
-                    "min_distance",
-                    "max_samples",
-                    "max_distance",
-                ]:
                     tcl = self.build(
-                        splitter_type=splitter_type,
+                        feature_select=feature_select,
                         criterion=criterion,
                         criteria=criteria,
                     )
-                    self.assertEqual(splitter_type, tcl._splitter_type)
+                    self.assertEqual(feature_select, tcl._feature_select)
                     self.assertEqual(criterion, tcl._criterion)
                     self.assertEqual(criteria, tcl._criteria)
 
@@ -138,78 +135,77 @@ class Splitter_test(unittest.TestCase):
                 [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 = np.array([0.2, 0.01, -0.9, 0.2])
+        expected = data[:, 0]
-        y = [1, 2, 1, 0]
+        y = [1, 2, 1, 0, 0, 0]
         computed = tcl._max_samples(data, y)
-        self.assertEqual((4,), computed.shape)
+        self.assertEqual(0, computed)
-        self.assertListEqual(expected.tolist(), computed.tolist())
+        computed_data = data[:, computed]
+        self.assertEqual((6,), computed_data.shape)
+        self.assertListEqual(expected.tolist(), computed_data.tolist())
 
-    def test_min_distance(self):
+    def test_impurity(self):
-        tcl = self.build()
+        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 = np.array([2, 2, 1, 0])
+        expected = data[:, 2]
-        computed = tcl._min_distance(data, None)
+        y = np.array([1, 2, 1, 0, 0, 0])
-        self.assertEqual((4,), computed.shape)
+        computed = tcl._impurity(data, y)
-        self.assertListEqual(expected.tolist(), computed.tolist())
+        self.assertEqual(2, computed)
+        computed_data = data[:, computed]
+        self.assertEqual((6,), computed_data.shape)
+        self.assertListEqual(expected.tolist(), computed_data.tolist())
 
-    def test_max_distance(self):
+    def test_generate_subspaces(self):
-        tcl = self.build(criteria="max_distance")
+        features = 250
-        data = np.array(
+        for max_features in range(2, features):
-            [
+            num = len(Splitter._generate_spaces(features, max_features))
-                [-0.1, 0.2, -0.3],
+            self.assertEqual(5, num)
-                [0.7, 0.01, -0.1],
+        self.assertEqual(3, len(Splitter._generate_spaces(3, 2)))
-                [0.7, -0.9, 0.5],
+        self.assertEqual(4, len(Splitter._generate_spaces(4, 3)))
-                [0.1, 0.2, 0.3],
-            ]
-        )
-        expected = np.array([1, 0, 0, 2])
-        computed = tcl._max_distance(data, None)
-        self.assertEqual((4,), computed.shape)
-        self.assertListEqual(expected.tolist(), computed.tolist())
 
     def test_best_splitter_few_sets(self):
         X, y = load_iris(return_X_y=True)
         X = np.delete(X, 3, 1)
-        tcl = self.build(splitter_type="best", random_state=self._random_state)
+        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 = [
-            [2, 3, 5, 7],  # best   entropy min_distance
+            [0, 6, 11, 12],  # best   entropy max_samples
-            [0, 2, 4, 5],  # best   entropy max_samples
+            [0, 6, 11, 12],  # best   entropy impurity
-            [0, 2, 8, 12],  # best   entropy max_distance
+            [0, 6, 11, 12],  # best   gini    max_samples
-            [1, 2, 5, 12],  # best   gini    min_distance
+            [0, 6, 11, 12],  # best   gini    impurity
-            [0, 3, 4, 10],  # best   gini    max_samples
+            [0, 3, 8, 12],  # random entropy max_samples
-            [1, 2, 9, 12],  # best   gini    max_distance
+            [0, 3, 7, 12],  # random entropy impurity
-            [3, 9, 11, 12],  # random entropy min_distance
+            [1, 7, 9, 12],  # random gini    max_samples
-            [1, 5, 6, 9],  # random entropy max_samples
+            [1, 5, 8, 12],  # random gini    impurity
-            [1, 2, 4, 8],  # random entropy max_distance
-            [2, 6, 7, 12],  # random gini    min_distance
-            [3, 9, 10, 11],  # random gini    max_samples
-            [2, 5, 8, 12],  # random gini    max_distance
         ]
         X, y = load_wine(return_X_y=True)
         rn = 0
-        for splitter_type in ["best", "random"]:
+        for feature_select in ["best", "random"]:
             for criterion in ["entropy", "gini"]:
                 for criteria in [
-                    "min_distance",
                     "max_samples",
-                    "max_distance",
+                    "impurity",
                 ]:
                     tcl = self.build(
-                        splitter_type=splitter_type,
+                        feature_select=feature_select,
                         criterion=criterion,
                         criteria=criteria,
                     )
@@ -219,7 +215,9 @@ class Splitter_test(unittest.TestCase):
                     dataset, computed = tcl.get_subspace(X, y, max_features=4)
                     # print(
                     #     "{},  # {:7s}{:8s}{:15s}".format(
-                    #         list(computed), splitter_type, criterion,
+                    #         list(computed),
+                    #         feature_select,
+                    #         criterion,
                     #         criteria,
                     #     )
                     # )
@@ -227,3 +225,18 @@ class Splitter_test(unittest.TestCase):
                     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())

stree/tests/Stree_test.py

@@ -5,6 +5,7 @@ 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, Snode
 from .utils import load_dataset
@@ -25,8 +26,10 @@ class Stree_test(unittest.TestCase):
         correct number of labels and its sons have the right number of elements
         in their dataset
 
-        Arguments:
+        Parameters
-            node {Snode} -- node to check
+        ----------
+        node : Snode
+            node to check
         """
         if node.is_leaf():
             return
@@ -41,23 +44,22 @@ class Stree_test(unittest.TestCase):
         _, count_u = np.unique(y_up, return_counts=True)
         #
         for i in unique_y:
-            number_down = count_d[i]
-            try:
             number_up = count_u[i]
+            try:
+                number_down = count_d[i]
             except IndexError:
-                number_up = 0
+                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[0], y_up.shape[0])
+        self.assertEqual(count_yp[1], y_up.shape[0])
-        self.assertEqual(count_yp[1], y_down.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
+        """Check if the tree is built the same way as predictions of models"""
-        """
         warnings.filterwarnings("ignore")
         for kernel in self._kernels:
             clf = Stree(kernel=kernel, random_state=self._random_state)
@@ -99,20 +101,22 @@ class Stree_test(unittest.TestCase):
             self.assertListEqual(yp_line.tolist(), yp_once.tolist())
 
     def test_iterator_and_str(self):
-        """Check preorder iterator
+        """Check preorder iterator"""
-        """
         expected = [
-            "root feaures=(0, 1, 2) impurity=0.5000",
+            "root feaures=(0, 1, 2) impurity=1.0000 counts=(array([0, 1]), "
-            "root - Down feaures=(0, 1, 2) impurity=0.0671",
+            "array([750, 750]))",
-            "root - Down - Down, <cgaf> - Leaf class=1 belief= 0.975989 "
+            "root - Down(2), <cgaf> - Leaf class=0 belief= 0.928297 impurity="
-            "impurity=0.0469 counts=(array([0, 1]), array([ 17, 691]))",
+            "0.3722 counts=(array([0, 1]), array([725,  56]))",
-            "root - Down - Up feaures=(0, 1, 2) impurity=0.3967",
+            "root - Up(2) feaures=(0, 1, 2) impurity=0.2178 counts=(array([0, "
-            "root - Down - Up - Down, <cgaf> - Leaf class=1 belief= 0.750000 "
+            "1]), array([ 25, 694]))",
-            "impurity=0.3750 counts=(array([0, 1]), array([1, 3]))",
+            "root - Up(2) - Down(3) feaures=(0, 1, 2) impurity=0.8454 counts="
-            "root - Down - Up - Up, <pure> - Leaf class=0 belief= 1.000000 "
+            "(array([0, 1]), array([8, 3]))",
-            "impurity=0.0000 counts=(array([0]), array([7]))",
+            "root - Up(2) - Down(3) - Down(4), <pure> - Leaf class=0 belief= "
-            "root - Up, <cgaf> - Leaf class=0 belief= 0.928297 impurity=0.1331"
+            "1.000000 impurity=0.0000 counts=(array([0]), array([7]))",
-            " counts=(array([0, 1]), array([725,  56]))",
+            "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 = ""
@@ -188,44 +192,43 @@ class Stree_test(unittest.TestCase):
     def test_muticlass_dataset(self):
         datasets = {
             "Synt": load_dataset(random_state=self._random_state, n_classes=3),
-            "Iris": load_iris(return_X_y=True),
+            "Iris": load_wine(return_X_y=True),
         }
         outcomes = {
             "Synt": {
-                "max_samples linear": 0.9533333333333334,
+                "max_samples linear": 0.9606666666666667,
-                "max_samples rbf": 0.836,
+                "max_samples rbf": 0.7133333333333334,
-                "max_samples poly": 0.9473333333333334,
+                "max_samples poly": 0.618,
-                "min_distance linear": 0.9533333333333334,
+                "impurity linear": 0.9606666666666667,
-                "min_distance rbf": 0.836,
+                "impurity rbf": 0.7133333333333334,
-                "min_distance poly": 0.9473333333333334,
+                "impurity poly": 0.618,
-                "max_distance linear": 0.9533333333333334,
-                "max_distance rbf": 0.836,
-                "max_distance poly": 0.9473333333333334,
             },
             "Iris": {
-                "max_samples linear": 0.98,
+                "max_samples linear": 1.0,
-                "max_samples rbf": 1.0,
+                "max_samples rbf": 0.6910112359550562,
-                "max_samples poly": 1.0,
+                "max_samples poly": 0.6966292134831461,
-                "min_distance linear": 0.98,
+                "impurity linear": 1,
-                "min_distance rbf": 1.0,
+                "impurity rbf": 0.6910112359550562,
-                "min_distance poly": 1.0,
+                "impurity poly": 0.6966292134831461,
-                "max_distance linear": 0.98,
-                "max_distance rbf": 1.0,
-                "max_distance poly": 1.0,
             },
         }
+
         for name, dataset in datasets.items():
             px, py = dataset
-            for criteria in ["max_samples", "min_distance", "max_distance"]:
+            for criteria in ["max_samples", "impurity"]:
                 for kernel in self._kernels:
                     clf = Stree(
-                        C=1e4,
+                        C=55,
-                        max_iter=1e4,
+                        max_iter=1e5,
                         kernel=kernel,
                         random_state=self._random_state,
                     )
                     clf.fit(px, py)
                     outcome = outcomes[name][f"{criteria} {kernel}"]
+                    # print(
+                    #     f"{name} {criteria} {kernel} {outcome} {clf.score(px"
+                    #     ", py)}"
+                    # )
                     self.assertAlmostEqual(outcome, clf.score(px, py))
 
     def test_max_features(self):
@@ -297,7 +300,10 @@ class Stree_test(unittest.TestCase):
             0.9433333333333334,
         ]
         for kernel, accuracy_expected in zip(self._kernels, accuracies):
-            clf = Stree(random_state=self._random_state, kernel=kernel,)
+            clf = Stree(
+                random_state=self._random_state,
+                kernel=kernel,
+            )
             clf.fit(X, y)
             accuracy_score = clf.score(X, y)
             yp = clf.predict(X)
@@ -309,108 +315,197 @@ 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(0.9426666666666667, clf.score(X, y))
+        self.assertAlmostEqual(0.9453333333333334, clf.score(X, y))
-
-    def test_score_multi_class(self):
-        warnings.filterwarnings("ignore")
-        accuracies = [
-            0.8258427,  # Wine    linear min_distance
-            0.6741573,  # Wine    linear max_distance
-            0.8314607,  # Wine    linear max_samples
-            0.6629213,  # Wine    rbf   min_distance
-            1.0000000,  # Wine    rbf   max_distance
-            0.4044944,  # Wine    rbf   max_samples
-            0.9157303,  # Wine    poly  min_distance
-            1.0000000,  # Wine    poly  max_distance
-            0.7640449,  # Wine    poly  max_samples
-            0.9933333,  # Iris    linear min_distance
-            0.9666667,  # Iris    linear max_distance
-            0.9666667,  # Iris    linear max_samples
-            0.9800000,  # Iris    rbf   min_distance
-            0.9800000,  # Iris    rbf   max_distance
-            0.9800000,  # Iris    rbf   max_samples
-            1.0000000,  # Iris    poly  min_distance
-            1.0000000,  # Iris    poly  max_distance
-            1.0000000,  # Iris    poly  max_samples
-            0.8993333,  # Synthetic linear min_distance
-            0.6533333,  # Synthetic linear max_distance
-            0.9313333,  # Synthetic linear max_samples
-            0.8320000,  # Synthetic rbf   min_distance
-            0.6660000,  # Synthetic rbf   max_distance
-            0.8320000,  # Synthetic rbf   max_samples
-            0.6066667,  # Synthetic poly  min_distance
-            0.6840000,  # Synthetic poly  max_distance
-            0.6340000,  # Synthetic poly  max_samples
-        ]
-        datasets = [
-            ("Wine", load_wine(return_X_y=True)),
-            ("Iris", load_iris(return_X_y=True)),
-            (
-                "Synthetic",
-                load_dataset(self._random_state, n_classes=3, n_features=5),
-            ),
-        ]
-        for dataset_name, dataset in datasets:
-            X, y = dataset
-            for kernel in self._kernels:
-                for criteria in [
-                    "min_distance",
-                    "max_distance",
-                    "max_samples",
-                ]:
-                    clf = Stree(
-                        C=17,
-                        random_state=self._random_state,
-                        kernel=kernel,
-                        split_criteria=criteria,
-                        degree=5,
-                        gamma="auto",
-                    )
-                    clf.fit(X, y)
-                    accuracy_score = clf.score(X, y)
-                    yp = clf.predict(X)
-                    accuracy_computed = np.mean(yp == y)
-                    # print(
-                    #     "{:.7f},  # {:7} {:5} {}".format(
-                    #         accuracy_score, dataset_name, kernel, criteria
-                    #     )
-                    # )
-                    accuracy_expected = accuracies.pop(0)
-                    self.assertEqual(accuracy_score, accuracy_computed)
-                    self.assertAlmostEqual(accuracy_expected, accuracy_score)
 
     def test_bogus_splitter_parameter(self):
         clf = Stree(splitter="duck")
         with self.assertRaises(ValueError):
             clf.fit(*load_dataset())
 
-    def test_weights_removing_class(self):
+    def test_multiclass_classifier_integrity(self):
-        # This patch solves an stderr message from sklearn svm lib
+        """Checks if the multiclass operation is done right"""
-        # "WARNING: class label x specified in weight is not found"
+        X, y = load_iris(return_X_y=True)
+        clf = Stree(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):
+        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(0.768, clf.fit(X, y).score(X, y))
+        self.assertEqual(0.814, clf2.fit(X, y).score(X, y))
+        X, y = load_wine(return_X_y=True)
+        self.assertEqual(0.6741573033707865, clf.fit(X, y).score(X, y))
+        self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
+
+    def test_score_multiclass_poly(self):
+        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(0.786, clf.fit(X, y).score(X, y))
+        self.assertEqual(0.818, clf2.fit(X, y).score(X, y))
+        X, y = load_wine(return_X_y=True)
+        self.assertEqual(0.702247191011236, clf.fit(X, y).score(X, y))
+        self.assertEqual(0.6067415730337079, clf2.fit(X, y).score(X, y))
+
+    def test_score_multiclass_linear(self):
+        X, y = load_dataset(
+            random_state=self._random_state,
+            n_classes=3,
+            n_features=5,
+            n_samples=1500,
+        )
+        clf = Stree(kernel="linear", random_state=self._random_state)
+        self.assertEqual(0.9533333333333334, clf.fit(X, y).score(X, y))
+        # Check with context based standardization
+        clf2 = Stree(
+            kernel="linear", 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):
+        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):
         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())
+        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):
+        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)
-        node = clf.train(X, y, weights, 1, "test",)
+        self.assertEqual(6, clf.depth_)
-        # if a class is lost with zero weights the patch adds epsilon
+        X, y = load_wine(return_X_y=True)
-        self.assertListEqual(weights.tolist(), weights_epsilon)
+        clf = Stree(random_state=self._random_state)
-        self.assertListEqual(node._sample_weight.tolist(), weights_epsilon)
+        clf.fit(X, y)
-        # zero weights are ok when they don't erase a class
+        self.assertEqual(4, clf.depth_)
-        _ = clf.train(X, y, weights_no_zero, 1, "test")
+
-        self.assertListEqual(weights_no_zero.tolist(), original.tolist())
+    def test_nodes_leaves(self):
+        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(25, nodes)
+        self.assertEquals(13, 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(9, nodes)
+        self.assertEquals(5, leaves)
+
+    def test_nodes_leaves_artificial(self):
+        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)

stree/tests/utils.py

@@ -1,9 +1,9 @@
 from sklearn.datasets import make_classification
 
 
-def load_dataset(random_state=0, n_classes=2, n_features=3):
+def load_dataset(random_state=0, n_classes=2, n_features=3, n_samples=1500):
     X, y = make_classification(
-        n_samples=1500,
+        n_samples=n_samples,
         n_features=n_features,
         n_informative=3,
         n_redundant=0,