Reformat test with new black version

update installation instructions

.github/workflows/codeql-analysis.yml

@@ -2,12 +2,12 @@ name: "CodeQL"
 
 on:
   push:
-    branches: [ master ]
+    branches: [master]
   pull_request:
     # The branches below must be a subset of the branches above
-    branches: [ master ]
+    branches: [master]
   schedule:
-    - cron: '16 17 * * 3'
+    - cron: "16 17 * * 3"
 
 jobs:
   analyze:
@@ -17,40 +17,40 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        language: [ 'python' ]
+        language: ["python"]
         # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python' ]
         # Learn more:
         # https://docs.github.com/en/free-pro-team@latest/github/finding-security-vulnerabilities-and-errors-in-your-code/configuring-code-scanning#changing-the-languages-that-are-analyzed
 
     steps:
-    - name: Checkout repository
+      - name: Checkout repository
-      uses: actions/checkout@v2
+        uses: actions/checkout@v2
 
-    # Initializes the CodeQL tools for scanning.
+      # Initializes the CodeQL tools for scanning.
-    - name: Initialize CodeQL
+      - name: Initialize CodeQL
-      uses: github/codeql-action/init@v1
+        uses: github/codeql-action/init@v2
-      with:
+        with:
-        languages: ${{ matrix.language }}
+          languages: ${{ matrix.language }}
-        # If you wish to specify custom queries, you can do so here or in a config file.
+          # 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.
+          # 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.
+          # 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
+          # queries: ./path/to/local/query, your-org/your-repo/queries@main
 
-    # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
+      # 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)
+      # If this step fails, then you should remove it and run the build manually (see below)
-    - name: Autobuild
+      - name: Autobuild
-      uses: github/codeql-action/autobuild@v1
+        uses: github/codeql-action/autobuild@v2
 
-    # ℹ️ Command-line programs to run using the OS shell.
+      # ℹ️ Command-line programs to run using the OS shell.
-    # 📚 https://git.io/JvXDl
+      # 📚 https://git.io/JvXDl
 
-    # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
+      # ✏️ 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
+      #    and modify them (or add more) to build your code if your project
-    #    uses a compiled language
+      #    uses a compiled language
 
-    #- run: |
+      #- run: |
-    #   make bootstrap
+      #   make bootstrap
-    #   make release
+      #   make release
 
-    - name: Perform CodeQL Analysis
+      - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v1
+        uses: github/codeql-action/analyze@v2

.github/workflows/main.yml

@@ -12,13 +12,13 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [macos-latest, ubuntu-latest]
+        os: [macos-latest, ubuntu-latest, windows-latest]
-        python: [3.8]
+        python: [3.8, "3.10"]
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - name: Set up Python ${{ matrix.python }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python }}
       - name: Install dependencies
@@ -35,7 +35,7 @@ jobs:
           coverage run -m unittest -v stree.tests
           coverage xml
       - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v1
+        uses: codecov/codecov-action@v3
         with:
           token: ${{ secrets.CODECOV_TOKEN }}
           files: ./coverage.xml

CITATION.cff

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

Makefile

@@ -10,6 +10,9 @@ coverage:  ## Run tests with coverage
 deps:  ## Install dependencies
 	pip install -r requirements.txt
 
+devdeps:  ## Install development dependencies
+	pip install black pip-audit flake8 mypy coverage
+
 lint:  ## Lint and static-check
 	black stree
 	flake8 stree
@@ -32,6 +35,9 @@ build:  ## Build package
 doc-clean:  ## Update documentation
 	make -C docs --makefile=Makefile clean
 
+audit: ## Audit pip
+	pip-audit
+
 help: ## Show help message
 	@IFS=$$'\n' ; \
 	help_lines=(`fgrep -h "##" $(MAKEFILE_LIST) | fgrep -v fgrep | sed -e 's/\\$$//' | sed -e 's/##/:/'`); \

README.md

@@ -1,7 +1,7 @@
 ![CI](https://github.com/Doctorado-ML/STree/workflows/CI/badge.svg)
+[![CodeQL](https://github.com/Doctorado-ML/STree/actions/workflows/codeql-analysis.yml/badge.svg)](https://github.com/Doctorado-ML/STree/actions/workflows/codeql-analysis.yml)
 [![codecov](https://codecov.io/gh/doctorado-ml/stree/branch/master/graph/badge.svg)](https://codecov.io/gh/doctorado-ml/stree)
 [![Codacy Badge](https://app.codacy.com/project/badge/Grade/35fa3dfd53a24a339344b33d9f9f2f3d)](https://www.codacy.com/gh/Doctorado-ML/STree?utm_source=github.com&utm_medium=referral&utm_content=Doctorado-ML/STree&utm_campaign=Badge_Grade)
-[![Language grade: Python](https://img.shields.io/lgtm/grade/python/g/Doctorado-ML/STree.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/Doctorado-ML/STree/context:python)
 [![PyPI version](https://badge.fury.io/py/STree.svg)](https://badge.fury.io/py/STree)
 ![https://img.shields.io/badge/python-3.8%2B-blue](https://img.shields.io/badge/python-3.8%2B-brightgreen)
 [![DOI](https://zenodo.org/badge/262658230.svg)](https://zenodo.org/badge/latestdoi/262658230)
@@ -15,7 +15,7 @@ Oblique Tree classifier based on SVM nodes. The nodes are built and splitted wit
 ## Installation
 
 ```bash
-pip install git+https://github.com/doctorado-ml/stree
+pip install Stree
 ```
 
 ## Documentation
@@ -50,7 +50,8 @@ Can be found in [stree.readthedocs.io](https://stree.readthedocs.io/en/stable/)
 |     | 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", "trandom", "mutual", "cfs", "fcbf", "iwss"} | "random"    | The strategy used to choose the feature set at each node (only used if max_features < num_features). Supported strategies are: **“best”**: sklearn SelectKBest algorithm is used in every node to choose the max_features best features. **“random”**: The algorithm generates 5 candidates and choose the best (max. info. gain) of them. **“trandom”**: The algorithm generates only one random combination. **"mutual"**: Chooses the best features w.r.t. their mutual info with the label. **"cfs"**: Apply Correlation-based Feature Selection. **"fcbf"**: Apply Fast Correlation-Based Filter. **"iwss"**: IWSS based algorithm |
+|     | splitter            | {"best", "random", "trandom", "mutual", "cfs", "fcbf", "iwss"} | "random"    | The strategy used to choose the feature set at each node (only used if max_features < num_features).
+Supported strategies are: **“best”**: sklearn SelectKBest algorithm is used in every node to choose the max_features best features. **“random”**: The algorithm generates 5 candidates and choose the best (max. info. gain) of them. **“trandom”**: The algorithm generates only one random combination. **"mutual"**: Chooses the best features w.r.t. their mutual info with the label. **"cfs"**: Apply Correlation-based Feature Selection. **"fcbf"**: Apply Fast Correlation-Based Filter. **"iwss"**: IWSS based algorithm |
 |     | normalize           | \<bool\>                                                       | False       | If standardization of features should be applied on each node with the samples that reach it                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
 | \*  | multiclass_strategy | {"ovo", "ovr"}                                                 | "ovo"       | Strategy to use with multiclass datasets, **"ovo"**: one versus one. **"ovr"**: one versus rest                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
 

docs/source/conf.py

@@ -12,19 +12,18 @@
 #
 import os
 import sys
-import stree
+from stree._version import __version__
 
 sys.path.insert(0, os.path.abspath("../../stree/"))
 
-
 # -- Project information -----------------------------------------------------
 
 project = "STree"
-copyright = "2020 - 2021, Ricardo Montañana Gómez"
+copyright = "2020 - 2022, Ricardo Montañana Gómez"
 author = "Ricardo Montañana Gómez"
 
 # The full version, including alpha/beta/rc tags
-version = stree.__version__
+version = __version__
 release = version
 
 

docs/source/hyperparameters.md

@@ -3,20 +3,20 @@
 |     | **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              | {"liblinear", "linear", "poly", "rbf", "sigmoid"}              | linear      | Specifies the kernel type to be used in the algorithm. It must be one of ‘liblinear’, ‘linear’, ‘poly’ or ‘rbf’. liblinear uses [liblinear](https://www.csie.ntu.edu.tw/~cjlin/liblinear/) library and the rest uses [libsvm](https://www.csie.ntu.edu.tw/~cjlin/libsvm/) library through scikit-learn library                                                                                                                                                                                                                                                                                                                          |
+| \*  | kernel              | {"liblinear", "linear", "poly", "rbf", "sigmoid"}              | linear      | Specifies the kernel type to be used in the algorithm. It must be one of ‘liblinear’, ‘linear’, ‘poly’ or ‘rbf’.<br>liblinear uses [liblinear](https://www.csie.ntu.edu.tw/~cjlin/liblinear/) library and the rest uses [libsvm](https://www.csie.ntu.edu.tw/~cjlin/libsvm/) library through scikit-learn library                                                                                                                                                                                                                                                                                                                          |
 | \*  | 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’, ‘poly’ and ‘sigmoid’.<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\*\*. max_samples is incompatible with 'ovo' multiclass_strategy                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+|     | 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\*\*.<br>max_samples is incompatible with 'ovo' multiclass_strategy                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
-|     | 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.                                                                                                                                                                                                                                                                                                                                                                                                                                             |
+|     | 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", "trandom", "mutual", "cfs", "fcbf", "iwss"} | "random"    | The strategy used to choose the feature set at each node (only used if max_features < num_features). Supported strategies are: **“best”**: sklearn SelectKBest algorithm is used in every node to choose the max_features best features. **“random”**: The algorithm generates 5 candidates and choose the best (max. info. gain) of them. **“trandom”**: The algorithm generates only one random combination. **"mutual"**: Chooses the best features w.r.t. their mutual info with the label. **"cfs"**: Apply Correlation-based Feature Selection. **"fcbf"**: Apply Fast Correlation-Based Filter. **"iwss"**: IWSS based algorithm |
+|     | splitter            | {"best", "random", "trandom", "mutual", "cfs", "fcbf", "iwss"} | "random"    | The strategy used to choose the feature set at each node (only used if max_features < num_features).<br>Supported strategies are:<br>**“best”**: sklearn SelectKBest algorithm is used in every node to choose the max_features best features.<br>**“random”**: The algorithm generates 5 candidates and choose the best (max. info. gain) of them.<br>**“trandom”**: The algorithm generates only one random combination.<br>**"mutual"**: Chooses the best features w.r.t. their mutual info with the label.<br>**"cfs"**: Apply Correlation-based Feature Selection.<br>**"fcbf"**: Apply Fast Correlation-Based Filter.<br>**"iwss"**: IWSS based algorithm |
 |     | normalize           | \<bool\>                                                       | False       | If standardization of features should be applied on each node with the samples that reach it                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
-| \*  | multiclass_strategy | {"ovo", "ovr"}                                                 | "ovo"       | Strategy to use with multiclass datasets, **"ovo"**: one versus one. **"ovr"**: one versus rest                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+| \*  | multiclass_strategy | {"ovo", "ovr"}                                                 | "ovo"       | Strategy to use with multiclass datasets:<br>**"ovo"**: one versus one.<br>**"ovr"**: one versus rest                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
 
 \* Hyperparameter used by the support vector classifier of every node
 

notebooks/benchmark.ipynb

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

notebooks/gridsearch.ipynb

@@ -1,253 +1,253 @@
 {
- "cells": [
+  "cells": [
-  {
+    {
-   "cell_type": "markdown",
+      "cell_type": "markdown",
-   "metadata": {},
+      "metadata": {},
-   "source": [
+      "source": [
-    "# Test Gridsearch\n",
+        "# Test Gridsearch\n",
-    "with different kernels and different configurations"
+        "with different kernels and different configurations"
-   ]
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Setup\n",
+        "Uncomment the next cell if STree is not already installed"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "#\n",
+        "# Google Colab setup\n",
+        "#\n",
+        "#!pip install git+https://github.com/doctorado-ml/stree\n",
+        "!pip install pandas"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {},
+        "colab_type": "code",
+        "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"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {},
+        "colab_type": "code",
+        "id": "IEmq50QgDZEi"
+      },
+      "outputs": [],
+      "source": [
+        "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"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "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",
+        "    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",
+        "    y = df.Class\n",
+        "    X = df.drop(['Class', 'Time', 'Amount'], axis=1).values\n",
+        "    if n_examples > 0:\n",
+        "        # Take first n_examples samples\n",
+        "        X = X[:n_examples, :]\n",
+        "        y = y[:n_examples, :]\n",
+        "    else:\n",
+        "        # Take all the positive samples with a number of random negatives\n",
+        "        if n_examples < 0:\n",
+        "            Xt = X[(y == 1).ravel()]\n",
+        "            yt = y[(y == 1).ravel()]\n",
+        "            indices = random.sample(range(X.shape[0]), -1 * n_examples)\n",
+        "            X = np.append(Xt, X[indices], axis=0)\n",
+        "            y = np.append(yt, y[indices], axis=0)\n",
+        "    print(\"X.shape\", X.shape, \" y.shape\", y.shape)\n",
+        "    print(\"Fraud: {0:.3f}% {1}\".format(len(y[y == 1])*100/X.shape[0], len(y[y == 1])))\n",
+        "    print(\"Valid: {0:.3f}% {1}\".format(len(y[y == 0]) * 100 / X.shape[0], len(y[y == 0])))\n",
+        "    Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state, stratify=y)\n",
+        "    return Xtrain, Xtest, ytrain, ytest\n",
+        "\n",
+        "data = load_creditcard(-1000) # Take all true samples + 1000 of the others\n",
+        "# data = load_creditcard(5000)  # Take the first 5000 samples\n",
+        "# data = load_creditcard(0) # Take all the samples\n",
+        "\n",
+        "Xtrain = data[0]\n",
+        "Xtest = data[1]\n",
+        "ytrain = data[2]\n",
+        "ytest = data[3]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "# Tests"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {},
+        "colab_type": "code",
+        "id": "HmX3kR4PDZEw"
+      },
+      "outputs": [],
+      "source": [
+        "parameters = [{\n",
+        "    'base_estimator': [Stree(random_state=random_state)],\n",
+        "    'n_estimators': [10, 25],\n",
+        "    'learning_rate': [.5, 1],\n",
+        "    'estimator__split_criteria': ['max_samples', 'impurity'],\n",
+        "    'estimator__tol': [.1,  1e-02],\n",
+        "    'estimator__max_depth': [3, 5, 7],\n",
+        "    'estimator__C': [1, 7, 55],\n",
+        "    'estimator__kernel': ['linear']\n",
+        "},\n",
+        "{\n",
+        "    'base_estimator': [Stree(random_state=random_state)],\n",
+        "    'n_estimators': [10, 25],\n",
+        "    'learning_rate': [.5, 1],\n",
+        "    'estimator__split_criteria': ['max_samples', 'impurity'],\n",
+        "    'estimator__tol': [.1,  1e-02],\n",
+        "    'estimator__max_depth': [3, 5, 7],\n",
+        "    'estimator__C': [1, 7, 55],\n",
+        "    'estimator__degree': [3, 5, 7],\n",
+        "    'estimator__kernel': ['poly']\n",
+        "},\n",
+        "{\n",
+        "    'base_estimator': [Stree(random_state=random_state)],\n",
+        "    'n_estimators': [10, 25],\n",
+        "    'learning_rate': [.5, 1],\n",
+        "    'estimator__split_criteria': ['max_samples', 'impurity'],\n",
+        "    'estimator__tol': [.1,  1e-02],\n",
+        "    'estimator__max_depth': [3, 5, 7],\n",
+        "    'estimator__C': [1, 7, 55],\n",
+        "    'estimator__gamma': [.1, 1, 10],\n",
+        "    'estimator__kernel': ['rbf']\n",
+        "}]"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "Stree().get_params()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {},
+        "colab_type": "code",
+        "id": "CrcB8o6EDZE5",
+        "outputId": "7703413a-d563-4289-a13b-532f38f82762",
+        "tags": []
+      },
+      "outputs": [],
+      "source": [
+        "clf = AdaBoostClassifier(random_state=random_state, algorithm=\"SAMME\")\n",
+        "grid = GridSearchCV(clf, parameters, verbose=5, n_jobs=-1, return_train_score=True)\n",
+        "grid.fit(Xtrain, ytrain)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "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_)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "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), 'estimator__C': 55, 'estimator__kernel': 'linear', 'estimator__max_depth': 7, 'estimator__split_criteria': 'max_samples', 'estimator__tol': 0.1, 'learning_rate': 0.5, 'n_estimators': 25}"
+      ]
+    },
+    {
+      "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",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.8.2-final"
+    }
   },
-  {
+  "nbformat": 4,
-   "cell_type": "markdown",
+  "nbformat_minor": 4
-   "metadata": {},
+}
-   "source": [
-    "# Setup\n",
-    "Uncomment the next cell if STree is not already installed"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#\n",
-    "# Google Colab setup\n",
-    "#\n",
-    "#!pip install git+https://github.com/doctorado-ml/stree\n",
-    "!pip install pandas"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "colab": {},
-    "colab_type": "code",
-    "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"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "colab": {},
-    "colab_type": "code",
-    "id": "IEmq50QgDZEi"
-   },
-   "outputs": [],
-   "source": [
-    "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"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "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",
-    "    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",
-    "    y = df.Class\n",
-    "    X = df.drop(['Class', 'Time', 'Amount'], axis=1).values\n",
-    "    if n_examples > 0:\n",
-    "        # Take first n_examples samples\n",
-    "        X = X[:n_examples, :]\n",
-    "        y = y[:n_examples, :]\n",
-    "    else:\n",
-    "        # Take all the positive samples with a number of random negatives\n",
-    "        if n_examples < 0:\n",
-    "            Xt = X[(y == 1).ravel()]\n",
-    "            yt = y[(y == 1).ravel()]\n",
-    "            indices = random.sample(range(X.shape[0]), -1 * n_examples)\n",
-    "            X = np.append(Xt, X[indices], axis=0)\n",
-    "            y = np.append(yt, y[indices], axis=0)\n",
-    "    print(\"X.shape\", X.shape, \" y.shape\", y.shape)\n",
-    "    print(\"Fraud: {0:.3f}% {1}\".format(len(y[y == 1])*100/X.shape[0], len(y[y == 1])))\n",
-    "    print(\"Valid: {0:.3f}% {1}\".format(len(y[y == 0]) * 100 / X.shape[0], len(y[y == 0])))\n",
-    "    Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state, stratify=y)\n",
-    "    return Xtrain, Xtest, ytrain, ytest\n",
-    "\n",
-    "data = load_creditcard(-1000) # Take all true samples + 1000 of the others\n",
-    "# data = load_creditcard(5000)  # Take the first 5000 samples\n",
-    "# data = load_creditcard(0) # Take all the samples\n",
-    "\n",
-    "Xtrain = data[0]\n",
-    "Xtest = data[1]\n",
-    "ytrain = data[2]\n",
-    "ytest = data[3]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Tests"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "colab": {},
-    "colab_type": "code",
-    "id": "HmX3kR4PDZEw"
-   },
-   "outputs": [],
-   "source": [
-    "parameters = [{\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__kernel': ['linear']\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__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": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "Stree().get_params()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "colab": {},
-    "colab_type": "code",
-    "id": "CrcB8o6EDZE5",
-    "outputId": "7703413a-d563-4289-a13b-532f38f82762",
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "clf = AdaBoostClassifier(random_state=random_state, algorithm=\"SAMME\")\n",
-    "grid = GridSearchCV(clf, parameters, verbose=5, n_jobs=-1, return_train_score=True)\n",
-    "grid.fit(Xtrain, ytrain)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "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_)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "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",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.8.2-final"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

setup.py

@@ -1,4 +1,5 @@
 import setuptools
+import os
 
 
 def readme():
@@ -6,9 +7,9 @@ def readme():
         return f.read()
 
 
-def get_data(field):
+def get_data(field, file_name="__init__.py"):
     item = ""
-    with open("stree/__init__.py") as f:
+    with open(os.path.join("stree", file_name)) as f:
         for line in f.readlines():
             if line.startswith(f"__{field}__"):
                 delim = '"' if '"' in line else "'"
@@ -19,9 +20,14 @@ def get_data(field):
     return item
 
 
+def get_requirements():
+    with open("requirements.txt") as f:
+        return f.read().splitlines()
+
+
 setuptools.setup(
     name="STree",
-    version=get_data("version"),
+    version=get_data("version", "_version.py"),
     license=get_data("license"),
     description="Oblique decision tree with svm nodes",
     long_description=readme(),
@@ -44,7 +50,7 @@ setuptools.setup(
         "Topic :: Scientific/Engineering :: Artificial Intelligence",
         "Intended Audience :: Science/Research",
     ],
-    install_requires=["scikit-learn", "mufs"],
+    install_requires=get_requirements(),
     test_suite="stree.tests",
     zip_safe=False,
 )

stree/Splitter.py

@@ -68,6 +68,7 @@ class Snode:
         self._impurity = impurity
         self._partition_column: int = -1
         self._scaler = scaler
+        self._proba = None
 
     @classmethod
     def copy(cls, node: "Snode") -> "Snode":
@@ -127,23 +128,44 @@ class Snode:
     def get_up(self) -> "Snode":
         return self._up
 
-    def make_predictor(self):
+    def make_predictor(self, num_classes: int) -> None:
         """Compute the class of the predictor and its belief based on the
         subdataset of the node only if it is a leaf
         """
         if not self.is_leaf():
             return
         classes, card = np.unique(self._y, return_counts=True)
-        if len(classes) > 1:
+        self._proba = np.zeros((num_classes,), dtype=np.int64)
+        for c, n in zip(classes, card):
+            self._proba[c] = n
+        try:
             max_card = max(card)
             self._class = classes[card == max_card][0]
             self._belief = max_card / np.sum(card)
+        except ValueError:
+            self._class = None
+
+    def graph(self):
+        """
+        Return a string representing the node in graphviz format
+        """
+        output = ""
+        count_values = np.unique(self._y, return_counts=True)
+        if self.is_leaf():
+            output += (
+                f'N{id(self)} [shape=box style=filled label="'
+                f"class={self._class} impurity={self._impurity:.3f} "
+                f'counts={self._proba}"];\n'
+            )
         else:
-            self._belief = 1
+            output += (
-            try:
+                f'N{id(self)} [label="#features={len(self._features)} '
-                self._class = classes[0]
+                f"classes={count_values[0]} samples={count_values[1]} "
-            except IndexError:
+                f'({sum(count_values[1])})" fontcolor=black];\n'
-                self._class = None
+            )
+            output += f"N{id(self)} -> N{id(self.get_up())} [color=black];\n"
+            output += f"N{id(self)} -> N{id(self.get_down())} [color=black];\n"
+        return output
 
     def __str__(self) -> str:
         count_values = np.unique(self._y, return_counts=True)
@@ -245,7 +267,6 @@ class Splitter:
         random_state=None,
         normalize=False,
     ):
-
         self._clf = clf
         self._random_state = random_state
         if random_state is not None:
@@ -367,9 +388,8 @@ class Splitter:
             .get_support(indices=True)
         )
 
-    @staticmethod
     def _fs_mutual(
-        dataset: np.array, labels: np.array, max_features: int
+        self, dataset: np.array, labels: np.array, max_features: int
     ) -> tuple:
         """Return the best features with mutual information with labels
 
@@ -389,7 +409,9 @@ class Splitter:
             indices of the features selected
         """
         # return best features with mutual info with the label
-        feature_list = mutual_info_classif(dataset, labels)
+        feature_list = mutual_info_classif(
+            dataset, labels, random_state=self._random_state
+        )
         return tuple(
             sorted(
                 range(len(feature_list)), key=lambda sub: feature_list[sub]

stree/Strees.py

@@ -17,6 +17,7 @@ from sklearn.utils.validation import (
     _check_sample_weight,
 )
 from .Splitter import Splitter, Snode, Siterator
+from ._version import __version__
 
 
 class Stree(BaseEstimator, ClassifierMixin):
@@ -138,7 +139,7 @@ class Stree(BaseEstimator, ClassifierMixin):
         self,
         C: float = 1.0,
         kernel: str = "linear",
-        max_iter: int = 1e5,
+        max_iter: int = int(1e5),
         random_state: int = None,
         max_depth: int = None,
         tol: float = 1e-4,
@@ -152,7 +153,6 @@ class Stree(BaseEstimator, ClassifierMixin):
         multiclass_strategy: str = "ovo",
         normalize: bool = False,
     ):
-
         self.max_iter = max_iter
         self.C = C
         self.kernel = kernel
@@ -169,6 +169,11 @@ class Stree(BaseEstimator, ClassifierMixin):
         self.normalize = normalize
         self.multiclass_strategy = multiclass_strategy
 
+    @staticmethod
+    def version() -> str:
+        """Return the version of the package."""
+        return __version__
+
     def _more_tags(self) -> dict:
         """Required by sklearn to supply features of the classifier
         make mandatory the labels array
@@ -308,7 +313,7 @@ class Stree(BaseEstimator, ClassifierMixin):
         if np.unique(y).shape[0] == 1:
             # only 1 class => pure dataset
             node.set_title(title + ", <pure>")
-            node.make_predictor()
+            node.make_predictor(self.n_classes_)
             return node
         # Train the model
         clf = self._build_clf()
@@ -327,7 +332,7 @@ class Stree(BaseEstimator, ClassifierMixin):
         if X_U is None or X_D is None:
             # didn't part anything
             node.set_title(title + ", <cgaf>")
-            node.make_predictor()
+            node.make_predictor(self.n_classes_)
             return node
         node.set_up(
             self._train(X_U, y_u, sw_u, depth + 1, title + f" - Up({depth+1})")
@@ -361,28 +366,100 @@ class Stree(BaseEstimator, ClassifierMixin):
             )
         )
 
-    @staticmethod
+    def __predict_class(self, X: np.array) -> np.array:
-    def _reorder_results(y: np.array, indices: np.array) -> np.array:
+        """Compute the predicted class for the samples in X. Returns the number
-        """Reorder an array based on the array of indices passed
+        of samples of each class in the corresponding leaf node.
 
         Parameters
         ----------
-        y : np.array
+        X : np.array
-            data untidy
+            Array of samples
-        indices : np.array
-            indices used to set order
 
         Returns
         -------
         np.array
-            array y ordered
+            Array of shape (n_samples, n_classes) with the number of samples
+            of each class in the corresponding leaf node
         """
-        # return array of same type given in y
+
-        y_ordered = y.copy()
+        def compute_prediction(xp, indices, node):
-        indices = indices.astype(int)
+            if xp is None:
-        for i, index in enumerate(indices):
+                return
-            y_ordered[index] = y[i]
+            if node.is_leaf():
-        return y_ordered
+                # set a class for indices
+                result[indices] = node._proba
+                return
+            self.splitter_.partition(xp, node, train=False)
+            x_u, x_d = self.splitter_.part(xp)
+            i_u, i_d = self.splitter_.part(indices)
+            compute_prediction(x_u, i_u, node.get_up())
+            compute_prediction(x_d, i_d, node.get_down())
+
+        # setup prediction & make it happen
+        result = np.zeros((X.shape[0], self.n_classes_))
+        indices = np.arange(X.shape[0])
+        compute_prediction(X, indices, self.tree_)
+        return result
+
+    def check_predict(self, X) -> np.array:
+        """Checks predict and predict_proba preconditions. If input X is not an
+        np.array convert it to one.
+
+        Parameters
+        ----------
+        X : np.ndarray
+            Array of samples
+
+        Returns
+        -------
+        np.array
+            Array of samples
+
+        Raises
+        ------
+        ValueError
+            If number of features of X is different of the number of features
+            in training data
+        """
+        check_is_fitted(self, ["tree_"])
+        # Input validation
+        X = check_array(X)
+        if X.shape[1] != self.n_features_:
+            raise ValueError(
+                f"Expected {self.n_features_} features but got "
+                f"({X.shape[1]})"
+            )
+        return X
+
+    def predict_proba(self, X: np.array) -> np.array:
+        """Predict class probabilities of the input samples X.
+
+        The predicted class probability is the fraction of samples of the same
+        class in a leaf.
+
+        Parameters
+        ----------
+        X : dataset of samples.
+
+        Returns
+        -------
+        proba : array of shape (n_samples, n_classes)
+            The class probabilities of the input samples.
+
+        Raises
+        ------
+        ValueError
+            if dataset with inconsistent number of features
+        NotFittedError
+            if model is not fitted
+        """
+
+        X = self.check_predict(X)
+        # return # of samples of each class in leaf node
+        values = self.__predict_class(X)
+        normalizer = values.sum(axis=1)[:, np.newaxis]
+        normalizer[normalizer == 0.0] = 1.0
+        return values / normalizer
 
     def predict(self, X: np.array) -> np.array:
         """Predict labels for each sample in dataset passed
@@ -404,40 +481,45 @@ class Stree(BaseEstimator, ClassifierMixin):
         NotFittedError
             if model is not fitted
         """
+        X = self.check_predict(X)
+        return self.classes_[np.argmax(self.__predict_class(X), axis=1)]
 
-        def predict_class(
+    def get_nodes(self) -> int:
-            xp: np.array, indices: np.array, node: Snode
+        """Return the number of nodes in the tree
-        ) -> np.array:
+
-            if xp is None:
+        Returns
-                return [], []
+        -------
+        int
+            number of nodes
+        """
+        nodes = 0
+        for _ in self:
+            nodes += 1
+        return nodes
+
+    def get_leaves(self) -> int:
+        """Return the number of leaves in the tree
+
+        Returns
+        -------
+        int
+            number of leaves
+        """
+        leaves = 0
+        for node in self:
             if node.is_leaf():
-                # set a class for every sample in dataset
+                leaves += 1
-                prediction = np.full((xp.shape[0], 1), node._class)
+        return leaves
-                return prediction, indices
-            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())
-            prx_d, prin_d = predict_class(x_d, i_d, node.get_down())
-            return np.append(prx_u, prx_d), np.append(prin_u, prin_d)
 
-        # sklearn check
+    def get_depth(self) -> int:
-        check_is_fitted(self, ["tree_"])
+        """Return the depth of the tree
-        # Input validation
+
-        X = check_array(X)
+        Returns
-        if X.shape[1] != self.n_features_:
+        -------
-            raise ValueError(
+        int
-                f"Expected {self.n_features_} features but got "
+            depth of the tree
-                f"({X.shape[1]})"
+        """
-            )
+        return self.depth_
-        # setup prediction & make it happen
-        indices = np.arange(X.shape[0])
-        result = (
-            self._reorder_results(*predict_class(X, indices, self.tree_))
-            .astype(int)
-            .ravel()
-        )
-        return self.classes_[result]
 
     def nodes_leaves(self) -> tuple:
         """Compute the number of nodes and leaves in the built tree
@@ -470,6 +552,23 @@ class Stree(BaseEstimator, ClassifierMixin):
             tree = None
         return Siterator(tree)
 
+    def graph(self, title="") -> str:
+        """Graphviz code representing the tree
+
+        Returns
+        -------
+        str
+            graphviz code
+        """
+        output = (
+            "digraph STree {\nlabel=<STree "
+            f"{title}>\nfontsize=30\nfontcolor=blue\nlabelloc=t\n"
+        )
+        for node in self:
+            output += node.graph()
+        output += "}\n"
+        return output
+
     def __str__(self) -> str:
         """String representation of the tree
 

stree/__init__.py

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

stree/_version.py

@@ -0,0 +1 @@
+__version__ = "1.3.2"

stree/tests/Snode_test.py

@@ -67,10 +67,28 @@ class Snode_test(unittest.TestCase):
 
     def test_make_predictor_on_leaf(self):
         test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
-        test.make_predictor()
+        test.make_predictor(2)
         self.assertEqual(1, test._class)
         self.assertEqual(0.75, test._belief)
         self.assertEqual(-1, test._partition_column)
+        self.assertListEqual([1, 3], test._proba.tolist())
+
+    def test_make_predictor_on_not_leaf(self):
+        test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
+        test.set_up(Snode(None, [1], [1], [], 0.0, "another_test"))
+        test.make_predictor(2)
+        self.assertIsNone(test._class)
+        self.assertEqual(0, test._belief)
+        self.assertEqual(-1, test._partition_column)
+        self.assertEqual(-1, test.get_up()._partition_column)
+        self.assertIsNone(test._proba)
+
+    def test_make_predictor_on_leaf_bogus_data(self):
+        test = Snode(None, [1, 2, 3, 4], [], [], 0.0, "test")
+        test.make_predictor(2)
+        self.assertIsNone(test._class)
+        self.assertEqual(-1, test._partition_column)
+        self.assertListEqual([0, 0], test._proba.tolist())
 
     def test_set_title(self):
         test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
@@ -97,21 +115,6 @@ class Snode_test(unittest.TestCase):
         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")
-        test.set_up(Snode(None, [1], [1], [], 0.0, "another_test"))
-        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]
         py = [1]

stree/tests/Stree_test.py

@@ -10,6 +10,7 @@ from sklearn.svm import LinearSVC
 from stree import Stree
 from stree.Splitter import Snode
 from .utils import load_dataset
+from .._version import __version__
 
 
 class Stree_test(unittest.TestCase):
@@ -114,6 +115,38 @@ class Stree_test(unittest.TestCase):
             yp = clf.fit(X, y).predict(X[:num, :])
             self.assertListEqual(y[:num].tolist(), yp.tolist())
 
+    def test_multiple_predict_proba(self):
+        expected = {
+            "liblinear": {
+                0: [0.02401129943502825, 0.9759887005649718],
+                17: [0.9282970550576184, 0.07170294494238157],
+            },
+            "linear": {
+                0: [0.029329608938547486, 0.9706703910614525],
+                17: [0.9298469387755102, 0.07015306122448979],
+            },
+            "rbf": {
+                0: [0.023448275862068966, 0.976551724137931],
+                17: [0.9458064516129032, 0.05419354838709677],
+            },
+            "poly": {
+                0: [0.01601164483260553, 0.9839883551673945],
+                17: [0.9089790897908979, 0.0910209102091021],
+            },
+        }
+        indices = [0, 17]
+        X, y = load_dataset(self._random_state)
+        for kernel in ["liblinear", "linear", "rbf", "poly"]:
+            clf = Stree(
+                kernel=kernel,
+                multiclass_strategy="ovr" if kernel == "liblinear" else "ovo",
+                random_state=self._random_state,
+            )
+            yp = clf.fit(X, y).predict_proba(X)
+            for index in indices:
+                for exp, comp in zip(expected[kernel][index], yp[index]):
+                    self.assertAlmostEqual(exp, comp)
+
     def test_single_vs_multiple_prediction(self):
         """Check if predicting sample by sample gives the same result as
         predicting all samples at once
@@ -206,6 +239,7 @@ class Stree_test(unittest.TestCase):
             )
             tcl.fit(*load_dataset(self._random_state))
             self.assertEqual(depth, tcl.depth_)
+            self.assertEqual(depth, tcl.get_depth())
 
     def test_unfitted_tree_is_iterable(self):
         tcl = Stree()
@@ -273,10 +307,10 @@ class Stree_test(unittest.TestCase):
             for criteria in ["max_samples", "impurity"]:
                 for kernel in self._kernels:
                     clf = Stree(
-                        max_iter=1e4,
+                        max_iter=int(1e4),
-                        multiclass_strategy="ovr"
+                        multiclass_strategy=(
-                        if kernel == "liblinear"
+                            "ovr" if kernel == "liblinear" else "ovo"
-                        else "ovo",
+                        ),
                         kernel=kernel,
                         random_state=self._random_state,
                     )
@@ -357,6 +391,7 @@ class Stree_test(unittest.TestCase):
 
     # Tests of score
     def test_score_binary(self):
+        """Check score for binary classification."""
         X, y = load_dataset(self._random_state)
         accuracies = [
             0.9506666666666667,
@@ -379,6 +414,7 @@ class Stree_test(unittest.TestCase):
             self.assertAlmostEqual(accuracy_expected, accuracy_score)
 
     def test_score_max_features(self):
+        """Check score using max_features."""
         X, y = load_dataset(self._random_state)
         clf = Stree(
             kernel="liblinear",
@@ -390,6 +426,7 @@ class Stree_test(unittest.TestCase):
         self.assertAlmostEqual(0.9453333333333334, clf.score(X, y))
 
     def test_bogus_splitter_parameter(self):
+        """Check that bogus splitter parameter raises exception."""
         clf = Stree(splitter="duck")
         with self.assertRaises(ValueError):
             clf.fit(*load_dataset())
@@ -445,6 +482,7 @@ class Stree_test(unittest.TestCase):
         self.assertListEqual([47], resdn[1].tolist())
 
     def test_score_multiclass_rbf(self):
+        """Test score for multiclass classification with rbf kernel."""
         X, y = load_dataset(
             random_state=self._random_state,
             n_classes=3,
@@ -462,6 +500,7 @@ class Stree_test(unittest.TestCase):
         self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
 
     def test_score_multiclass_poly(self):
+        """Test score for multiclass classification with poly kernel."""
         X, y = load_dataset(
             random_state=self._random_state,
             n_classes=3,
@@ -483,6 +522,7 @@ class Stree_test(unittest.TestCase):
         self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
 
     def test_score_multiclass_liblinear(self):
+        """Test score for multiclass classification with liblinear kernel."""
         X, y = load_dataset(
             random_state=self._random_state,
             n_classes=3,
@@ -508,6 +548,7 @@ class Stree_test(unittest.TestCase):
         self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
 
     def test_score_multiclass_sigmoid(self):
+        """Test score for multiclass classification with sigmoid kernel."""
         X, y = load_dataset(
             random_state=self._random_state,
             n_classes=3,
@@ -528,6 +569,7 @@ class Stree_test(unittest.TestCase):
         self.assertEqual(0.9662921348314607, clf2.fit(X, y).score(X, y))
 
     def test_score_multiclass_linear(self):
+        """Test score for multiclass classification with linear kernel."""
         warnings.filterwarnings("ignore", category=ConvergenceWarning)
         warnings.filterwarnings("ignore", category=RuntimeWarning)
         X, y = load_dataset(
@@ -555,11 +597,13 @@ class Stree_test(unittest.TestCase):
         self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
 
     def test_zero_all_sample_weights(self):
+        """Test exception raises when all sample weights are zero."""
         X, y = load_dataset(self._random_state)
         with self.assertRaises(ValueError):
             Stree().fit(X, y, np.zeros(len(y)))
 
     def test_mask_samples_weighted_zero(self):
+        """Check that the weighted zero samples are masked."""
         X = np.array(
             [
                 [1, 1],
@@ -587,6 +631,7 @@ class Stree_test(unittest.TestCase):
         self.assertEqual(model2.score(X, y, w), 1)
 
     def test_depth(self):
+        """Check depth of the tree."""
         X, y = load_dataset(
             random_state=self._random_state,
             n_classes=3,
@@ -596,12 +641,15 @@ class Stree_test(unittest.TestCase):
         clf = Stree(random_state=self._random_state)
         clf.fit(X, y)
         self.assertEqual(6, clf.depth_)
+        self.assertEqual(6, clf.get_depth())
         X, y = load_wine(return_X_y=True)
         clf = Stree(random_state=self._random_state)
         clf.fit(X, y)
         self.assertEqual(4, clf.depth_)
+        self.assertEqual(4, clf.get_depth())
 
     def test_nodes_leaves(self):
+        """Check number of nodes and leaves."""
         X, y = load_dataset(
             random_state=self._random_state,
             n_classes=3,
@@ -612,15 +660,20 @@ class Stree_test(unittest.TestCase):
         clf.fit(X, y)
         nodes, leaves = clf.nodes_leaves()
         self.assertEqual(31, nodes)
+        self.assertEqual(31, clf.get_nodes())
         self.assertEqual(16, leaves)
+        self.assertEqual(16, clf.get_leaves())
         X, y = load_wine(return_X_y=True)
         clf = Stree(random_state=self._random_state)
         clf.fit(X, y)
         nodes, leaves = clf.nodes_leaves()
         self.assertEqual(11, nodes)
+        self.assertEqual(11, clf.get_nodes())
         self.assertEqual(6, leaves)
+        self.assertEqual(6, clf.get_leaves())
 
     def test_nodes_leaves_artificial(self):
+        """Check leaves of artificial dataset."""
         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")
@@ -636,15 +689,19 @@ class Stree_test(unittest.TestCase):
         clf.tree_ = n1
         nodes, leaves = clf.nodes_leaves()
         self.assertEqual(6, nodes)
+        self.assertEqual(6, clf.get_nodes())
         self.assertEqual(2, leaves)
+        self.assertEqual(2, clf.get_leaves())
 
     def test_bogus_multiclass_strategy(self):
+        """Check invalid multiclass strategy."""
         clf = Stree(multiclass_strategy="other")
         X, y = load_wine(return_X_y=True)
         with self.assertRaises(ValueError):
             clf.fit(X, y)
 
     def test_multiclass_strategy(self):
+        """Check multiclass strategy."""
         X, y = load_wine(return_X_y=True)
         clf_o = Stree(multiclass_strategy="ovo")
         clf_r = Stree(multiclass_strategy="ovr")
@@ -654,6 +711,7 @@ class Stree_test(unittest.TestCase):
         self.assertEqual(0.9269662921348315, score_r)
 
     def test_incompatible_hyperparameters(self):
+        """Check incompatible hyperparameters."""
         X, y = load_wine(return_X_y=True)
         clf = Stree(kernel="liblinear", multiclass_strategy="ovo")
         with self.assertRaises(ValueError):
@@ -661,3 +719,50 @@ class Stree_test(unittest.TestCase):
         clf = Stree(multiclass_strategy="ovo", split_criteria="max_samples")
         with self.assertRaises(ValueError):
             clf.fit(X, y)
+
+    def test_version(self):
+        """Check STree version."""
+        clf = Stree()
+        self.assertEqual(__version__, clf.version())
+
+    def test_graph(self):
+        """Check graphviz representation of the tree."""
+        X, y = load_wine(return_X_y=True)
+        clf = Stree(random_state=self._random_state)
+
+        expected_head = (
+            "digraph STree {\nlabel=<STree >\nfontsize=30\n"
+            "fontcolor=blue\nlabelloc=t\n"
+        )
+        expected_tail = (
+            ' [shape=box style=filled label="class=1 impurity=0.000 '
+            'counts=[0 1 0]"];\n}\n'
+        )
+        self.assertEqual(clf.graph(), expected_head + "}\n")
+        clf.fit(X, y)
+        computed = clf.graph()
+        computed_head = computed[: len(expected_head)]
+        num = -len(expected_tail)
+        computed_tail = computed[num:]
+        self.assertEqual(computed_head, expected_head)
+        self.assertEqual(computed_tail, expected_tail)
+
+    def test_graph_title(self):
+        X, y = load_wine(return_X_y=True)
+        clf = Stree(random_state=self._random_state)
+        expected_head = (
+            "digraph STree {\nlabel=<STree Sample title>\nfontsize=30\n"
+            "fontcolor=blue\nlabelloc=t\n"
+        )
+        expected_tail = (
+            ' [shape=box style=filled label="class=1 impurity=0.000 '
+            'counts=[0 1 0]"];\n}\n'
+        )
+        self.assertEqual(clf.graph("Sample title"), expected_head + "}\n")
+        clf.fit(X, y)
+        computed = clf.graph("Sample title")
+        computed_head = computed[: len(expected_head)]
+        num = -len(expected_tail)
+        computed_tail = computed[num:]
+        self.assertEqual(computed_head, expected_head)
+        self.assertEqual(computed_tail, expected_tail)