exchange codeship badge with githubs

fix github actions workflow

.coveragerc

@@ -0,0 +1,13 @@
+[run]
+branch = True
+source = stree
+
+[report]
+exclude_lines =
+    if self.debug:
+    pragma: no cover
+    raise NotImplementedError
+    if __name__ == .__main__.:
+ignore_errors = True
+omit =
+    stree/__init__.py

.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

@@ -129,4 +129,7 @@ dmypy.json
 .pyre/
 
 .idea
-.vscode
+.vscode
+.pre-commit-config.yaml
+
+**.csv

.travis.yml

@@ -1,13 +0,0 @@
-language: python
-os: linux
-dist: xenial
-install:
-  - pip install -r requirements.txt
-notifications:
-  email:
-    recipients:
-      - ricardo.montanana@alu.uclm.es
-    on_success: never # default: change
-    on_failure: always # default: always
-# command to run tests
-script: python -m unittest stree.tests

README.md

@@ -1,8 +1,10 @@
-[![Build Status](https://travis-ci.com/Doctorado-ML/STree.svg?branch=master)](https://travis-ci.com/Doctorado-ML/STree)
+![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)
 
 # Stree
 
-Oblique Tree classifier based on SVM nodes. The nodes are built and splitted with sklearn LinearSVC models.Stree is a sklearn estimator and can be integrated in pipelines, grid searches, etc.
+Oblique Tree classifier based on SVM nodes. The nodes are built and splitted with sklearn SVC models. Stree is a sklearn estimator and can be integrated in pipelines, grid searches, etc.
 
 ![Stree](https://raw.github.com/doctorado-ml/stree/master/example.png)
 
@@ -16,17 +18,17 @@ pip install git+https://github.com/doctorado-ml/stree
 
 ### Jupyter notebooks
 
-##### Slow launch but better integration
+- [![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/test.ipynb) Test notebook
+- [![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
 
-##### Fast launch but have to run first commented out cell for setup
+- [![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
 
-* [![Test](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/test.ipynb) Test notebook
+- [![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
 
-* [![Test2](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/test2.ipynb) Another Test notebook
+- [![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
 
-* [![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 notebook
+- [![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
 
 ### Command line
 

codecov.yml

@@ -0,0 +1,12 @@
+overage:
+  status:
+    project:
+      default:
+        target: 90%
+comment:
+  layout: "reach, diff, flags, files"
+  behavior: default
+  require_changes: false  
+  require_base: yes
+  require_head: yes       
+  branches: null

main.py

@@ -1,57 +1,29 @@
 import time
 from sklearn.model_selection import train_test_split
+from sklearn.datasets import load_iris
 from stree import Stree
 
-random_state=1
+random_state = 1
 
-def load_creditcard(n_examples=0):
+X, y = load_iris(return_X_y=True)
-    import pandas as pd
-    import numpy as np
-    import random
-    df = pd.read_csv('data/creditcard.csv')
-    print("Fraud: {0:.3f}% {1}".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))
-    print("Valid: {0:.3f}% {1}".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))
-    y = np.expand_dims(df.Class.values, axis=1)
-    X = df.drop(['Class', 'Time', 'Amount'], axis=1).values
-    if n_examples > 0:
-        # Take first n_examples samples
-        X = X[:n_examples, :]
-        y = y[:n_examples, :]
-    else:
-        # Take all the positive samples with a number of random negatives
-        if n_examples < 0:
-            Xt = X[(y == 1).ravel()]
-            yt = y[(y == 1).ravel()]
-            indices = random.sample(range(X.shape[0]), -1 * n_examples)
-            X = np.append(Xt, X[indices], axis=0)
-            y = np.append(yt, y[indices], axis=0)
-    print("X.shape", X.shape, " y.shape", y.shape)
-    print("Fraud: {0:.3f}% {1}".format(len(y[y == 1])*100/X.shape[0], len(y[y == 1])))
-    print("Valid: {0:.3f}% {1}".format(len(y[y == 0]) * 100 / X.shape[0], len(y[y == 0])))
-    Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state, stratify=y)
-    return Xtrain, Xtest, ytrain, ytest
 
-# data = load_creditcard(-5000) # Take all true samples + 5000 of the others
+Xtrain, Xtest, ytrain, ytest = train_test_split(
-# data = load_creditcard(5000)  # Take the first 5000 samples
+    X, y, test_size=0.2, random_state=random_state
-data = load_creditcard() # Take all the samples
+)
-
-Xtrain = data[0]
-Xtest = data[1]
-ytrain = data[2]
-ytest = data[3]
 
 now = time.time()
-clf = Stree(C=.01, random_state=random_state)
+print("Predicting with max_features=sqrt(n_features)")
+clf = Stree(C=0.01, random_state=random_state, max_features="auto")
+clf.fit(Xtrain, ytrain)
+print(f"Took {time.time() - now:.2f} seconds to train")
+print(clf)
+print(f"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}")
+print(f"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}")
+print("=" * 40)
+print("Predicting with max_features=n_features")
+clf = Stree(C=0.01, random_state=random_state)
 clf.fit(Xtrain, ytrain)
 print(f"Took {time.time() - now:.2f} seconds to train")
 print(clf)
 print(f"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}")
 print(f"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}")
-proba = clf.predict_proba(Xtest)
-print("Checking that we have correct probabilities, these are probabilities of sample belonging to class 1")
-res0 = proba[proba[:, 0] == 0]
-res1 = proba[proba[:, 0] == 1]
-print("++++++++++res0 > .8++++++++++++")
-print(res0[res0[:, 1] > .8])
-print("**********res1 < .4************")
-print(res1[res1[:, 1] < .4])

notebooks/benchmark.ipynb

@@ -0,0 +1,588 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Compare STree with different estimators"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Setup\n",
+    "Uncomment the next cell if STree is not already installed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#\n",
+    "# Google Colab setup\n",
+    "#\n",
+    "#!pip install git+https://github.com/doctorado-ml/stree"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import datetime, time\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn import tree\n",
+    "from sklearn.metrics import classification_report, confusion_matrix, f1_score\n",
+    "from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, BaggingClassifier\n",
+    "from stree import Stree"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "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"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Tests"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "2020-11-01 11:14:06\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(datetime.date.today(), time.strftime(\"%H:%M:%S\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load dataset and normalize values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load Dataset\n",
+    "df = pd.read_csv('data/creditcard.csv')\n",
+    "df.shape\n",
+    "random_state = 2020"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Fraud: 0.173% 492\nValid: 99.827% 284,315\n"
+     ]
+    }
+   ],
+   "source": [
+    "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()))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Normalize Amount\n",
+    "from sklearn.preprocessing import RobustScaler\n",
+    "values = RobustScaler().fit_transform(df.Amount.values.reshape(-1, 1))\n",
+    "df['Amount_Scaled'] = values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "X shape: (284807, 29)\ny shape: (284807,)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Remove unneeded features\n",
+    "y = df.Class.values\n",
+    "X = df.drop(['Class', 'Time', 'Amount'], axis=1).values\n",
+    "print(f\"X shape: {X.shape}\\ny shape: {y.shape}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Build the models"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Divide dataset\n",
+    "train_size = .7\n",
+    "Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=train_size, shuffle=True, random_state=random_state, stratify=y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Linear Tree\n",
+    "linear_tree = tree.DecisionTreeClassifier(random_state=random_state)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Random Forest\n",
+    "random_forest = RandomForestClassifier(random_state=random_state)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Stree\n",
+    "stree = Stree(random_state=random_state, C=.01, max_iter=1e3)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# AdaBoost\n",
+    "adaboost = AdaBoostClassifier(random_state=random_state)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Bagging\n",
+    "bagging = BaggingClassifier(random_state=random_state)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Do the test"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def try_model(name, model):\n",
+    "    print(f\"************************** {name} **********************\")\n",
+    "    now = time.time()\n",
+    "    model.fit(Xtrain, ytrain)\n",
+    "    spent = time.time() - now\n",
+    "    print(f\"Train Model {name} took: {spent:.4} seconds\")\n",
+    "    predict = model.predict(Xtrain)\n",
+    "    predictt = model.predict(Xtest)\n",
+    "    print(f\"=========== {name} - Train {Xtrain.shape[0]:,} samples =============\",)\n",
+    "    print(classification_report(ytrain, predict, digits=6))\n",
+    "    print(f\"=========== {name} - Test {Xtest.shape[0]:,} samples =============\")\n",
+    "    print(classification_report(ytest, predictt, digits=6))\n",
+    "    print(\"Confusion Matrix in Train\")\n",
+    "    print(confusion_matrix(ytrain, predict))\n",
+    "    print(\"Confusion Matrix in Test\")\n",
+    "    print(confusion_matrix(ytest, predictt))\n",
+    "    return f1_score(ytest, predictt), spent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "************************** Linear Tree **********************\n",
+      "Train Model Linear Tree took: 15.14 seconds\n",
+      "=========== Linear Tree - Train 199,364 samples =============\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0   1.000000  1.000000  1.000000    199020\n",
+      "           1   1.000000  1.000000  1.000000       344\n",
+      "\n",
+      "    accuracy                       1.000000    199364\n",
+      "   macro avg   1.000000  1.000000  1.000000    199364\n",
+      "weighted avg   1.000000  1.000000  1.000000    199364\n",
+      "\n",
+      "=========== Linear Tree - Test 85,443 samples =============\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0   0.999578  0.999613  0.999596     85295\n",
+      "           1   0.772414  0.756757  0.764505       148\n",
+      "\n",
+      "    accuracy                       0.999192     85443\n",
+      "   macro avg   0.885996  0.878185  0.882050     85443\n",
+      "weighted avg   0.999184  0.999192  0.999188     85443\n",
+      "\n",
+      "Confusion Matrix in Train\n",
+      "[[199020      0]\n",
+      " [     0    344]]\n",
+      "Confusion Matrix in Test\n",
+      "[[85262    33]\n",
+      " [   36   112]]\n",
+      "************************** Random Forest **********************\n",
+      "Train Model Random Forest took: 181.1 seconds\n",
+      "=========== Random Forest - Train 199,364 samples =============\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0   1.000000  1.000000  1.000000    199020\n",
+      "           1   1.000000  1.000000  1.000000       344\n",
+      "\n",
+      "    accuracy                       1.000000    199364\n",
+      "   macro avg   1.000000  1.000000  1.000000    199364\n",
+      "weighted avg   1.000000  1.000000  1.000000    199364\n",
+      "\n",
+      "=========== Random Forest - Test 85,443 samples =============\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0   0.999660  0.999965  0.999812     85295\n",
+      "           1   0.975410  0.804054  0.881481       148\n",
+      "\n",
+      "    accuracy                       0.999625     85443\n",
+      "   macro avg   0.987535  0.902009  0.940647     85443\n",
+      "weighted avg   0.999618  0.999625  0.999607     85443\n",
+      "\n",
+      "Confusion Matrix in Train\n",
+      "[[199020      0]\n",
+      " [     0    344]]\n",
+      "Confusion Matrix in Test\n",
+      "[[85292     3]\n",
+      " [   29   119]]\n",
+      "************************** Stree (SVM Tree) **********************\n",
+      "Train Model Stree (SVM Tree) took: 36.6 seconds\n",
+      "=========== Stree (SVM Tree) - Train 199,364 samples =============\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0   0.999623  0.999864  0.999744    199020\n",
+      "           1   0.908784  0.781977  0.840625       344\n",
+      "\n",
+      "    accuracy                       0.999488    199364\n",
+      "   macro avg   0.954204  0.890921  0.920184    199364\n",
+      "weighted avg   0.999467  0.999488  0.999469    199364\n",
+      "\n",
+      "=========== Stree (SVM Tree) - Test 85,443 samples =============\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0   0.999637  0.999918  0.999777     85295\n",
+      "           1   0.943548  0.790541  0.860294       148\n",
+      "\n",
+      "    accuracy                       0.999555     85443\n",
+      "   macro avg   0.971593  0.895229  0.930036     85443\n",
+      "weighted avg   0.999540  0.999555  0.999536     85443\n",
+      "\n",
+      "Confusion Matrix in Train\n",
+      "[[198993     27]\n",
+      " [    75    269]]\n",
+      "Confusion Matrix in Test\n",
+      "[[85288     7]\n",
+      " [   31   117]]\n",
+      "************************** AdaBoost model **********************\n",
+      "Train Model AdaBoost model took: 46.14 seconds\n",
+      "=========== AdaBoost model - Train 199,364 samples =============\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0   0.999392  0.999678  0.999535    199020\n",
+      "           1   0.777003  0.648256  0.706815       344\n",
+      "\n",
+      "    accuracy                       0.999072    199364\n",
+      "   macro avg   0.888198  0.823967  0.853175    199364\n",
+      "weighted avg   0.999008  0.999072  0.999030    199364\n",
+      "\n",
+      "=========== AdaBoost model - Test 85,443 samples =============\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0   0.999484  0.999707  0.999596     85295\n",
+      "           1   0.806202  0.702703  0.750903       148\n",
+      "\n",
+      "    accuracy                       0.999192     85443\n",
+      "   macro avg   0.902843  0.851205  0.875249     85443\n",
+      "weighted avg   0.999149  0.999192  0.999165     85443\n",
+      "\n",
+      "Confusion Matrix in Train\n",
+      "[[198956     64]\n",
+      " [   121    223]]\n",
+      "Confusion Matrix in Test\n",
+      "[[85270    25]\n",
+      " [   44   104]]\n",
+      "************************** Bagging model **********************\n",
+      "Train Model Bagging model took: 77.73 seconds\n",
+      "=========== Bagging model - Train 199,364 samples =============\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0   0.999864  1.000000  0.999932    199020\n",
+      "           1   1.000000  0.921512  0.959153       344\n",
+      "\n",
+      "    accuracy                       0.999865    199364\n",
+      "   macro avg   0.999932  0.960756  0.979542    199364\n",
+      "weighted avg   0.999865  0.999865  0.999862    199364\n",
+      "\n",
+      "=========== Bagging model - Test 85,443 samples =============\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0   0.999637  0.999953  0.999795     85295\n",
+      "           1   0.966942  0.790541  0.869888       148\n",
+      "\n",
+      "    accuracy                       0.999590     85443\n",
+      "   macro avg   0.983289  0.895247  0.934842     85443\n",
+      "weighted avg   0.999580  0.999590  0.999570     85443\n",
+      "\n",
+      "Confusion Matrix in Train\n",
+      "[[199020      0]\n",
+      " [    27    317]]\n",
+      "Confusion Matrix in Test\n",
+      "[[85291     4]\n",
+      " [   31   117]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Train & Test models\n",
+    "models = {\n",
+    "    'Linear Tree':linear_tree, 'Random Forest': random_forest, 'Stree (SVM Tree)': stree,  \n",
+    "    'AdaBoost model': adaboost, 'Bagging model': bagging\n",
+    "}\n",
+    "\n",
+    "best_f1 = 0\n",
+    "outcomes = []\n",
+    "for name, model in models.items():\n",
+    "    f1, time_spent = try_model(name, model)\n",
+    "    outcomes.append((name, f1, time_spent))\n",
+    "    if f1 > best_f1:\n",
+    "        best_model = name\n",
+    "        best_time = time_spent\n",
+    "        best_f1 = f1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "**************************************************************************************************************\n*The best f1 model is Random Forest, with a f1 score: 0.8815 in 181.07 seconds with 0.7 samples in train dataset\n**************************************************************************************************************\nModel: Linear Tree\t Time:  15.14 seconds\t f1: 0.7645\nModel: Random Forest\t Time: 181.07 seconds\t f1: 0.8815\nModel: Stree (SVM Tree)\t Time:  36.60 seconds\t f1: 0.8603\nModel: AdaBoost model\t Time:  46.14 seconds\t f1: 0.7509\nModel: Bagging model\t Time:  77.73 seconds\t f1: 0.8699\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"*\"*110)\n",
+    "print(f\"*The best f1 model is {best_model}, with a f1 score: {best_f1:.4} in {best_time:.6} seconds with {train_size:,} samples in train dataset\")\n",
+    "print(\"*\"*110)\n",
+    "for name, f1, time_spent in outcomes:\n",
+    "    print(f\"Model: {name}\\t Time: {time_spent:6.2f} seconds\\t f1: {f1:.4}\")"
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "metadata": {},
+   "source": [
+    "**************************************************************************************************************\n",
+    "*The best f1 model is Random Forest, with a f1 score: 0.8815 in 152.54 seconds with 0.7 samples in train dataset\n",
+    "**************************************************************************************************************\n",
+    "Model: Linear Tree\t Time:  13.52 seconds\t f1: 0.7645\n",
+    "Model: Random Forest\t Time: 152.54 seconds\t f1: 0.8815\n",
+    "Model: Stree (SVM Tree)\t Time:  32.55 seconds\t f1: 0.8603\n",
+    "Model: AdaBoost model\t Time:  47.34 seconds\t f1: 0.7509\n",
+    "Model: Gradient Boost.\t Time: 244.12 seconds\t f1: 0.5259"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "```\n",
+    "******************************************************************************************************************\n",
+    "*The best f1 model is Random Forest, with a f1 score: 0.8815 in 218.966 seconds with 0.7 samples in train dataset\n",
+    "******************************************************************************************************************\n",
+    "Model: Linear Tree       Time:  23.05 seconds\t f1: 0.7645\n",
+    "Model: Random Forest\t Time: 218.97 seconds\t f1: 0.8815\n",
+    "Model: Stree (SVM Tree)\t Time:  49.45 seconds\t f1: 0.8603\n",
+    "Model: AdaBoost model\t Time:  73.83 seconds\t f1: 0.7509\n",
+    "Model: Neural Network\t Time:  25.47 seconds\t f1: 0.8328\n",
+    "Model: Bagging model\t Time:  77.93 seconds\t f1: 0.8699\n",
+    "\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "{'C': 0.01,\n",
+       " 'criterion': 'entropy',\n",
+       " 'degree': 3,\n",
+       " 'gamma': 'scale',\n",
+       " 'kernel': 'linear',\n",
+       " 'max_depth': None,\n",
+       " 'max_features': None,\n",
+       " 'max_iter': 1000.0,\n",
+       " 'min_samples_split': 0,\n",
+       " 'random_state': 2020,\n",
+       " 'split_criteria': 'impurity',\n",
+       " 'splitter': 'random',\n",
+       " 'tol': 0.0001}"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 18
+    }
+   ],
+   "source": [
+    "stree.get_params()"
+   ]
+  }
+ ],
+ "metadata": {
+  "hide_input": false,
+  "kernelspec": {
+   "display_name": "Python 3.8.4 64-bit ('general': venv)",
+   "language": "python",
+   "name": "python38464bitgeneralvenv77203c0a6afd4428bd66253ef62753dc"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.4-final"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "position": {
+    "height": "392px",
+    "left": "1518px",
+    "right": "20px",
+    "top": "40px",
+    "width": "392px"
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": true
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

notebooks/ensemble.ipynb

@@ -1,18 +1,30 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Test Stree with AdaBoost and Bagging with different configurations"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Setup\n",
+    "Uncomment the next cell if STree is not already installed"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
-    "import time\n",
+    "#\n",
-    "from sklearn.ensemble import AdaBoostClassifier\n",
+    "# Google Colab setup\n",
-    "from sklearn.tree import DecisionTreeClassifier\n",
+    "#\n",
-    "from sklearn.svm import LinearSVC\n",
+    "#!pip install git+https://github.com/doctorado-ml/stree"
-    "from sklearn.model_selection import GridSearchCV, train_test_split\n",
-    "from sklearn.datasets import load_iris\n",
-    "from stree import Stree"
    ]
   },
   {
@@ -20,6 +32,18 @@
    "execution_count": 2,
    "metadata": {},
    "outputs": [],
+   "source": [
+    "import time\n",
+    "from sklearn.ensemble import AdaBoostClassifier, BaggingClassifier\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from stree import Stree"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "import os\n",
     "if not os.path.isfile('data/creditcard.csv'):\n",
@@ -29,13 +53,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "output_type": "stream",
      "name": "stdout",
-     "text": "Fraud: 0.244% 196\nValid: 99.755% 80234\nX.shape (1196, 28)  y.shape (1196,)\nFraud: 16.722% 200\nValid: 83.278% 996\n"
+     "text": [
+      "Fraud: 0.173% 492\n",
+      "Valid: 99.827% 284315\n",
+      "X.shape (100492, 28)  y.shape (100492,)\n",
+      "Fraud: 0.652% 655\n",
+      "Valid: 99.348% 99837\n"
+     ]
     }
    ],
    "source": [
@@ -68,9 +100,10 @@
     "    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(-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",
+    "data = load_creditcard(-100000)\n",
     "\n",
     "Xtrain = data[0]\n",
     "Xtest = data[1]\n",
@@ -79,19 +112,37 @@
    ]
   },
   {
-   "cell_type": "code",
+   "cell_type": "markdown",
-   "execution_count": 4,
    "metadata": {},
+   "source": [
+    "# Tests"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## STree alone with 100.000 samples and linear kernel"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "output_type": "stream",
      "name": "stdout",
-     "text": "Score Train:  0.986857825567503\nScore Test:  0.9805013927576601\nTook 0.12 seconds\n"
+     "text": [
+      "Score Train:  0.9985073353804162\nScore Test:  0.9983746848878864\nTook 35.80 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",
@@ -99,71 +150,94 @@
    ]
   },
   {
-   "cell_type": "code",
+   "cell_type": "markdown",
-   "execution_count": 5,
    "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "Score Train:  0.997610513739546\nScore Test:  0.9721448467966574\nTook 7.80 seconds\n"
-    }
-   ],
    "source": [
-    "now = time.time()\n",
+    "## Adaboost"
-    "clf2 = AdaBoostClassifier(Stree(max_depth=3, random_state=random_state), n_estimators=100, random_state=random_state)\n",
-    "clf2.fit(Xtrain, ytrain)\n",
-    "print(\"Score Train: \", clf2.score(Xtrain, ytrain))\n",
-    "print(\"Score Test: \", clf2.score(Xtest, ytest))\n",
-    "print(f\"Took {time.time() - now:.2f} seconds\")"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 6,
    "metadata": {},
-   "outputs": [
+   "outputs": [],
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "Score Train:  0.9796893667861409\nScore Test:  0.9554317548746518\nTook 0.48 seconds\n"
-    }
-   ],
    "source": [
-    "now = time.time()\n",
+    "n_estimators = 10\n",
-    "clf3 = AdaBoostClassifier(LinearSVC(random_state=random_state), n_estimators=100, random_state=random_state, algorithm='SAMME')\n",
+    "C = 7\n",
-    "clf3.fit(Xtrain, ytrain)\n",
+    "max_depth = 3"
-    "print(\"Score Train: \", clf3.score(Xtrain, ytrain))\n",
-    "print(\"Score Test: \", clf3.score(Xtest, ytest))\n",
-    "print(f\"Took {time.time() - now:.2f} seconds\")"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 7,
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "output_type": "stream",
      "name": "stdout",
-     "text": "Score Train:  1.0\nScore Test:  0.9721448467966574\nTook 0.86 seconds\n"
+     "text": [
+      "Kernel: linear\tTime: 49.66 seconds\tScore Train: 0.9983225\tScore Test: 0.9983083\n",
+      "Kernel: rbf\tTime: 12.73 seconds\tScore Train: 0.9934891\tScore Test: 0.9934656\n",
+      "Kernel: poly\tTime: 76.24 seconds\tScore Train: 0.9972706\tScore Test: 0.9969152\n"
+     ]
     }
    ],
    "source": [
-    "now = time.time()\n",
+    "for kernel in ['linear', 'rbf', 'poly']:\n",
-    "clf4 = AdaBoostClassifier(DecisionTreeClassifier(max_depth=1, random_state=random_state), n_estimators=100, random_state=random_state)\n",
+    "    now = time.time()\n",
-    "clf4.fit(Xtrain, ytrain)\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",
-    "print(\"Score Train: \", clf4.score(Xtrain, ytrain))\n",
+    "    clf.fit(Xtrain, ytrain)\n",
-    "print(\"Score Test: \", clf4.score(Xtest, ytest))\n",
+    "    score_train = clf.score(Xtrain, ytrain)\n",
-    "print(f\"Took {time.time() - now:.2f} seconds\")"
+    "    score_test = clf.score(Xtest, ytest)\n",
+    "    print(f\"Kernel: {kernel}\\tTime: {time.time() - now:.2f} seconds\\tScore Train: {score_train:.7f}\\tScore Test: {score_test:.7f}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Bagging"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "n_estimators = 10\n",
+    "C = 7\n",
+    "max_depth = 3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Kernel: linear\tTime: 231.51 seconds\tScore Train: 0.9984931\tScore Test: 0.9983083\n",
+      "Kernel: rbf\tTime: 114.77 seconds\tScore Train: 0.9992323\tScore Test: 0.9983083\n",
+      "Kernel: poly\tTime: 67.87 seconds\tScore Train: 0.9993319\tScore Test: 0.9985074\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, 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",
+    "    print(f\"Kernel: {kernel}\\tTime: {time.time() - now:.2f} seconds\\tScore Train: {score_train:.7f}\\tScore Test: {score_test:.7f}\")"
+   ]
   }
  ],
  "metadata": {
@@ -177,12 +251,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.6-final"
+   "version": "3.8.4-final"
   },
   "orig_nbformat": 2,
   "kernelspec": {
-   "name": "python37664bitgeneralvenvfbd0a23e74cf4e778460f5ffc6761f39",
+   "name": "python38464bitgeneralf6de308d3831407c8bd68d4a5e328a38",
-   "display_name": "Python 3.7.6 64-bit ('general': venv)"
+   "display_name": "Python 3.8.4 64-bit ('general')"
   }
  },
  "nbformat": 4,

notebooks/features.ipynb

@@ -0,0 +1,587 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Test sample_weight, kernels, C, sklearn estimator"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Setup\n",
+    "Uncomment the next cell if STree is not already installed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#\n",
+    "# Google Colab setup\n",
+    "#\n",
+    "#!pip install git+https://github.com/doctorado-ml/stree"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn.svm import SVC\n",
+    "from sklearn.tree import DecisionTreeClassifier\n",
+    "from sklearn.utils.estimator_checks import check_estimator\n",
+    "from sklearn.datasets import make_classification, load_iris, load_wine\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from stree import Stree\n",
+    "import time"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "tags": []
+   },
+   "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"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Fraud: 0.173% 492\nValid: 99.827% 284315\nX.shape (5492, 28)  y.shape (5492,)\nFraud: 9.141% 502\nValid: 90.859% 4990\n[0.09183143 0.09183143 0.09183143 0.09183143] [0.09041262 0.09041262 0.09041262 0.09041262]\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",
+    "    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)\n",
+    "    return Xtrain, Xtest, ytrain, ytest\n",
+    "\n",
+    "data = load_creditcard(-5000) # Take all true samples with up to 5000 of the others\n",
+    "# data = load_creditcard(5000)  # Take the first 5000 samples\n",
+    "# data = load_creditcard(-1000) # Take 1000 samples\n",
+    "\n",
+    "Xtrain = data[0]\n",
+    "Xtest = data[1]\n",
+    "ytrain = data[2]\n",
+    "ytest = data[3]\n",
+    "_, data = np.unique(ytrain, return_counts=True)\n",
+    "wtrain = (data[1] / np.sum(data),  data[0] / np.sum(data))\n",
+    "_, data = np.unique(ytest, return_counts=True)\n",
+    "wtest = (data[1] / np.sum(data),  data[0] / np.sum(data))\n",
+    "# Set weights inverse to its count class in dataset\n",
+    "weights = np.ones(Xtrain.shape[0],)\n",
+    "weights[ytrain==0] = wtrain[0]\n",
+    "weights[ytrain==1] = wtrain[1]\n",
+    "weights_test = np.ones(Xtest.shape[0],)\n",
+    "weights_test[ytest==0] = wtest[0]\n",
+    "weights_test[ytest==1] = wtest[1]\n",
+    "print(weights[:4], weights_test[:4])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Tests"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test sample_weights\n",
+    "Compute accuracy with weights in samples. The weights are set based on the inverse of the number of samples of each class"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Accuracy of Train without weights 0.9851716961498439\n",
+      "Accuracy of Train with    weights 0.986732570239334\n",
+      "Accuracy of Tests without weights 0.9866504854368932\n",
+      "Accuracy of Tests with    weights 0.9781553398058253\n"
+     ]
+    }
+   ],
+   "source": [
+    "C = 23\n",
+    "print(\"Accuracy of Train without weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain).score(Xtrain, ytrain))\n",
+    "print(\"Accuracy of Train with    weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain, sample_weight=weights).score(Xtrain, ytrain))\n",
+    "print(\"Accuracy of Tests without weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain).score(Xtest, ytest))\n",
+    "print(\"Accuracy of Tests with    weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain, sample_weight=weights).score(Xtest, ytest))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test accuracy with different kernels\n",
+    "Compute accuracy on train and test set with default hyperparmeters of every kernel"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "Time: 26.03s\tKernel: linear\tAccuracy_train: 0.9851716961498439\tAccuracy_test: 0.9866504854368932\n",
+      "Time: 0.54s\tKernel: rbf\tAccuracy_train: 0.9947970863683663\tAccuracy_test: 0.9878640776699029\n",
+      "Time: 0.43s\tKernel: poly\tAccuracy_train: 0.9960978147762747\tAccuracy_test: 0.9854368932038835\n"
+     ]
+    }
+   ],
+   "source": [
+    "random_state=1\n",
+    "for kernel in ['linear', 'rbf', 'poly']:\n",
+    "    now = time.time()\n",
+    "    clf = Stree(C=7, kernel=kernel, random_state=random_state).fit(Xtrain, ytrain)\n",
+    "    accuracy_train = clf.score(Xtrain, ytrain)\n",
+    "    accuracy_test = clf.score(Xtest, ytest)\n",
+    "    time_spent = time.time() - now\n",
+    "    print(f\"Time: {time_spent:.2f}s\\tKernel: {kernel}\\tAccuracy_train: {accuracy_train}\\tAccuracy_test: {accuracy_test}\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test diferent values of C"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "************** C=0.001 ****************************\n",
+      "Classifier's accuracy (train): 0.9828\n",
+      "Classifier's accuracy (test) : 0.9848\n",
+      "root feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.4426 counts=(array([0, 1]), array([3491,  353]))\n",
+      "root - Down, <cgaf> - Leaf class=0 belief= 0.981716 impurity=0.1317 counts=(array([0, 1]), array([3490,   65]))\n",
+      "root - Up, <cgaf> - Leaf class=1 belief= 0.996540 impurity=0.0333 counts=(array([0, 1]), array([  1, 288]))\n",
+      "\n",
+      "**************************************************\n",
+      "************** C=0.01 ****************************\n",
+      "Classifier's accuracy (train): 0.9834\n",
+      "Classifier's accuracy (test) : 0.9854\n",
+      "root feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.4426 counts=(array([0, 1]), array([3491,  353]))\n",
+      "root - Down, <cgaf> - Leaf class=0 belief= 0.982269 impurity=0.1285 counts=(array([0, 1]), array([3490,   63]))\n",
+      "root - Up, <cgaf> - Leaf class=1 belief= 0.996564 impurity=0.0331 counts=(array([0, 1]), array([  1, 290]))\n",
+      "\n",
+      "**************************************************\n",
+      "************** C=1 ****************************\n",
+      "Classifier's accuracy (train): 0.9847\n",
+      "Classifier's accuracy (test) : 0.9867\n",
+      "root feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.4426 counts=(array([0, 1]), array([3491,  353]))\n",
+      "root - Down, <cgaf> - Leaf class=0 belief= 0.983371 impurity=0.1221 counts=(array([0, 1]), array([3489,   59]))\n",
+      "root - Up feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.0584 counts=(array([0, 1]), array([  2, 294]))\n",
+      "root - Up - Down, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([2]))\n",
+      "root - Up - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([294]))\n",
+      "\n",
+      "**************************************************\n",
+      "************** C=5 ****************************\n",
+      "Classifier's accuracy (train): 0.9852\n",
+      "Classifier's accuracy (test) : 0.9867\n",
+      "root feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.4426 counts=(array([0, 1]), array([3491,  353]))\n",
+      "root - Down feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.1205 counts=(array([0, 1]), array([3488,   58]))\n",
+      "root - Down - Down, <cgaf> - Leaf class=0 belief= 0.983921 impurity=0.1188 counts=(array([0, 1]), array([3488,   57]))\n",
+      "root - Down - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([1]))\n",
+      "root - Up feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.0812 counts=(array([0, 1]), array([  3, 295]))\n",
+      "root - Up - Down, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([3]))\n",
+      "root - Up - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([295]))\n",
+      "\n",
+      "**************************************************\n",
+      "************** C=17 ****************************\n",
+      "Classifier's accuracy (train): 0.9852\n",
+      "Classifier's accuracy (test) : 0.9867\n",
+      "root feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.4426 counts=(array([0, 1]), array([3491,  353]))\n",
+      "root - Down feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.1205 counts=(array([0, 1]), array([3488,   58]))\n",
+      "root - Down - Down, <cgaf> - Leaf class=0 belief= 0.983921 impurity=0.1188 counts=(array([0, 1]), array([3488,   57]))\n",
+      "root - Down - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([1]))\n",
+      "root - Up feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.0812 counts=(array([0, 1]), array([  3, 295]))\n",
+      "root - Up - Down, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([3]))\n",
+      "root - Up - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([295]))\n",
+      "\n",
+      "**************************************************\n",
+      "64.5792 secs\n"
+     ]
+    }
+   ],
+   "source": [
+    "t = time.time()\n",
+    "for C in (.001, .01, 1, 5, 17):\n",
+    "    clf = Stree(C=C, kernel=\"linear\", random_state=random_state)\n",
+    "    clf.fit(Xtrain, ytrain)\n",
+    "    print(f\"************** C={C} ****************************\")\n",
+    "    print(f\"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}\")\n",
+    "    print(f\"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}\")\n",
+    "    print(clf)\n",
+    "    print(f\"**************************************************\")\n",
+    "print(f\"{time.time() - t:.4f} secs\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test iterator\n",
+    "Check different weays of using the iterator"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "root feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.4426 counts=(array([0, 1]), array([3491,  353]))\nroot - Down feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.1205 counts=(array([0, 1]), array([3488,   58]))\nroot - Down - Down, <cgaf> - Leaf class=0 belief= 0.983921 impurity=0.1188 counts=(array([0, 1]), array([3488,   57]))\nroot - Down - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([1]))\nroot - Up feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.0812 counts=(array([0, 1]), array([  3, 295]))\nroot - Up - Down, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([3]))\nroot - Up - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([295]))\n"
+     ]
+    }
+   ],
+   "source": [
+    "#check iterator\n",
+    "for i in list(clf):\n",
+    "    print(i)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "root feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.4426 counts=(array([0, 1]), array([3491,  353]))\nroot - Down feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.1205 counts=(array([0, 1]), array([3488,   58]))\nroot - Down - Down, <cgaf> - Leaf class=0 belief= 0.983921 impurity=0.1188 counts=(array([0, 1]), array([3488,   57]))\nroot - Down - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([1]))\nroot - Up feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.0812 counts=(array([0, 1]), array([  3, 295]))\nroot - Up - Down, <pure> - Leaf class=0 belief= 1.000000 impurity=0.0000 counts=(array([0]), array([3]))\nroot - Up - Up, <pure> - Leaf class=1 belief= 1.000000 impurity=0.0000 counts=(array([1]), array([295]))\n"
+     ]
+    }
+   ],
+   "source": [
+    "#check iterator again\n",
+    "for i in clf:\n",
+    "    print(i)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test STree is a sklearn estimator"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "1 functools.partial(<function check_no_attributes_set_in_init at 0x125acaee0>, 'Stree')\n",
+      "2 functools.partial(<function check_estimators_dtypes at 0x125ac7040>, 'Stree')\n",
+      "3 functools.partial(<function check_fit_score_takes_y at 0x125ac2ee0>, 'Stree')\n",
+      "4 functools.partial(<function check_sample_weights_pandas_series at 0x125ac0820>, 'Stree')\n",
+      "5 functools.partial(<function check_sample_weights_not_an_array at 0x125ac0940>, 'Stree')\n",
+      "6 functools.partial(<function check_sample_weights_list at 0x125ac0a60>, 'Stree')\n",
+      "7 functools.partial(<function check_sample_weights_shape at 0x125ac0b80>, 'Stree')\n",
+      "8 functools.partial(<function check_sample_weights_invariance at 0x125ac0ca0>, 'Stree')\n",
+      "9 functools.partial(<function check_estimators_fit_returns_self at 0x125aca040>, 'Stree')\n",
+      "10 functools.partial(<function check_estimators_fit_returns_self at 0x125aca040>, 'Stree', readonly_memmap=True)\n",
+      "11 functools.partial(<function check_complex_data at 0x125ac0e50>, 'Stree')\n",
+      "12 functools.partial(<function check_dtype_object at 0x125ac0dc0>, 'Stree')\n",
+      "13 functools.partial(<function check_estimators_empty_data_messages at 0x125ac7160>, 'Stree')\n",
+      "14 functools.partial(<function check_pipeline_consistency at 0x125ac2dc0>, 'Stree')\n",
+      "15 functools.partial(<function check_estimators_nan_inf at 0x125ac7280>, 'Stree')\n",
+      "16 functools.partial(<function check_estimators_overwrite_params at 0x125acadc0>, 'Stree')\n",
+      "17 functools.partial(<function check_estimator_sparse_data at 0x125ac0700>, 'Stree')\n",
+      "18 functools.partial(<function check_estimators_pickle at 0x125ac74c0>, 'Stree')\n",
+      "19 functools.partial(<function check_classifier_data_not_an_array at 0x125acd160>, 'Stree')\n",
+      "20 functools.partial(<function check_classifiers_one_label at 0x125ac7b80>, 'Stree')\n",
+      "21 functools.partial(<function check_classifiers_classes at 0x125aca5e0>, 'Stree')\n",
+      "22 functools.partial(<function check_estimators_partial_fit_n_features at 0x125ac75e0>, 'Stree')\n",
+      "23 functools.partial(<function check_classifiers_train at 0x125ac7ca0>, 'Stree')\n",
+      "24 functools.partial(<function check_classifiers_train at 0x125ac7ca0>, 'Stree', readonly_memmap=True)\n",
+      "25 functools.partial(<function check_classifiers_train at 0x125ac7ca0>, 'Stree', readonly_memmap=True, X_dtype='float32')\n",
+      "26 functools.partial(<function check_classifiers_regression_target at 0x125acdc10>, 'Stree')\n",
+      "27 functools.partial(<function check_supervised_y_no_nan at 0x125aab790>, 'Stree')\n",
+      "28 functools.partial(<function check_supervised_y_2d at 0x125aca280>, 'Stree')\n",
+      "29 functools.partial(<function check_estimators_unfitted at 0x125aca160>, 'Stree')\n",
+      "30 functools.partial(<function check_non_transformer_estimators_n_iter at 0x125acd790>, 'Stree')\n",
+      "31 functools.partial(<function check_decision_proba_consistency at 0x125acdd30>, 'Stree')\n",
+      "32 functools.partial(<function check_fit2d_predict1d at 0x125ac23a0>, 'Stree')\n",
+      "33 functools.partial(<function check_methods_subset_invariance at 0x125ac2550>, 'Stree')\n",
+      "34 functools.partial(<function check_fit2d_1sample at 0x125ac2670>, 'Stree')\n",
+      "35 functools.partial(<function check_fit2d_1feature at 0x125ac2790>, 'Stree')\n",
+      "36 functools.partial(<function check_fit1d at 0x125ac28b0>, 'Stree')\n",
+      "37 functools.partial(<function check_get_params_invariance at 0x125acd9d0>, 'Stree')\n",
+      "38 functools.partial(<function check_set_params at 0x125acdaf0>, 'Stree')\n",
+      "39 functools.partial(<function check_dict_unchanged at 0x125ac0f70>, 'Stree')\n",
+      "40 functools.partial(<function check_dont_overwrite_parameters at 0x125ac2280>, 'Stree')\n",
+      "41 functools.partial(<function check_fit_idempotent at 0x125acdee0>, 'Stree')\n",
+      "42 functools.partial(<function check_n_features_in at 0x125acdf70>, 'Stree')\n",
+      "43 functools.partial(<function check_requires_y_none at 0x125ad1040>, 'Stree')\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Make checks one by one\n",
+    "c = 0\n",
+    "checks = check_estimator(Stree(), generate_only=True)\n",
+    "for check in checks:\n",
+    "    c += 1\n",
+    "    print(c, check[1])\n",
+    "    check[1](check[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Check if the classifier is a sklearn estimator\n",
+    "check_estimator(Stree())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Compare to SVM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "== Not Weighted ===\n",
+      "SVC train score ..: 0.9825702393340271\n",
+      "STree train score : 0.9841311134235172\n",
+      "SVC test score ...: 0.9830097087378641\n",
+      "STree test score .: 0.9848300970873787\n",
+      "==== Weighted =====\n",
+      "SVC train score ..: 0.9786680541103018\n",
+      "STree train score : 0.9802289281997919\n",
+      "SVC test score ...: 0.9805825242718447\n",
+      "STree test score .: 0.9817961165048543\n",
+      "*SVC test score ..: 0.9439939825655582\n",
+      "*STree test score : 0.9476832429673473\n"
+     ]
+    }
+   ],
+   "source": [
+    "svc = SVC(C=7, kernel='rbf', gamma=.001, random_state=random_state)\n",
+    "clf = Stree(C=17, kernel='rbf', gamma=.001, random_state=random_state)\n",
+    "svc.fit(Xtrain, ytrain)\n",
+    "clf.fit(Xtrain, ytrain)\n",
+    "print(\"== Not Weighted ===\")\n",
+    "print(\"SVC train score ..:\", svc.score(Xtrain, ytrain))\n",
+    "print(\"STree train score :\", clf.score(Xtrain, ytrain))\n",
+    "print(\"SVC test score ...:\", svc.score(Xtest, ytest))\n",
+    "print(\"STree test score .:\", clf.score(Xtest, ytest))\n",
+    "svc.fit(Xtrain, ytrain, weights)\n",
+    "clf.fit(Xtrain, ytrain, weights)\n",
+    "print(\"==== Weighted =====\")\n",
+    "print(\"SVC train score ..:\", svc.score(Xtrain, ytrain))\n",
+    "print(\"STree train score :\", clf.score(Xtrain, ytrain))\n",
+    "print(\"SVC test score ...:\", svc.score(Xtest, ytest))\n",
+    "print(\"STree test score .:\", clf.score(Xtest, ytest))\n",
+    "print(\"*SVC test score ..:\", svc.score(Xtest, ytest, weights_test))\n",
+    "print(\"*STree test score :\", clf.score(Xtest, ytest, weights_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "root feaures=(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27) impurity=0.4426 counts=(array([0, 1]), array([3491,  353]))\nroot - Down, <cgaf> - Leaf class=0 belief= 0.990520 impurity=0.0773 counts=(array([0, 1]), array([3448,   33]))\nroot - Up, <cgaf> - Leaf class=1 belief= 0.881543 impurity=0.5249 counts=(array([0, 1]), array([ 43, 320]))\n\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(clf)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test max_features"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "****************************************\n",
+      "max_features None = 28\n",
+      "Train score : 0.9846514047866806\n",
+      "Test score .: 0.9866504854368932\n",
+      "Took 10.18 seconds\n",
+      "****************************************\n",
+      "max_features auto = 5\n",
+      "Train score : 0.9836108220603538\n",
+      "Test score .: 0.9842233009708737\n",
+      "Took 5.22 seconds\n",
+      "****************************************\n",
+      "max_features log2 = 4\n",
+      "Train score : 0.9791883454734651\n",
+      "Test score .: 0.9793689320388349\n",
+      "Took 2.05 seconds\n",
+      "****************************************\n",
+      "max_features 7 = 7\n",
+      "Train score : 0.9737252861602498\n",
+      "Test score .: 0.9739077669902912\n",
+      "Took 2.86 seconds\n",
+      "****************************************\n",
+      "max_features 0.5 = 14\n",
+      "Train score : 0.981789802289282\n",
+      "Test score .: 0.9824029126213593\n",
+      "Took 48.35 seconds\n",
+      "****************************************\n",
+      "max_features 0.1 = 2\n",
+      "Train score : 0.9638397502601457\n",
+      "Test score .: 0.9648058252427184\n",
+      "Took 0.35 seconds\n",
+      "****************************************\n",
+      "max_features 0.7 = 19\n",
+      "Train score : 0.9841311134235172\n",
+      "Test score .: 0.9860436893203883\n",
+      "Took 20.89 seconds\n"
+     ]
+    }
+   ],
+   "source": [
+    "for max_features in [None, \"auto\", \"log2\", 7, .5, .1, .7]:\n",
+    "    now = time.time()\n",
+    "    print(\"*\"*40)\n",
+    "    clf = Stree(random_state=random_state, max_features=max_features)\n",
+    "    clf.fit(Xtrain, ytrain)\n",
+    "    print(f\"max_features {max_features} = {clf.max_features_}\")\n",
+    "    print(\"Train score :\", clf.score(Xtrain, ytrain))\n",
+    "    print(\"Test score .:\", clf.score(Xtest, ytest))\n",
+    "    print(f\"Took {time.time() - now:.2f} seconds\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.7.6 64-bit ('general': venv)",
+   "language": "python",
+   "name": "python37664bitgeneralvenvfbd0a23e74cf4e778460f5ffc6761f39"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.4-final"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

notebooks/test2.ipynb

@@ -1,225 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#\n",
-    "# Google Colab setup\n",
-    "#\n",
-    "#!pip install git+https://github.com/doctorado-ml/stree"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "import pandas as pd\n",
-    "from sklearn.svm import LinearSVC\n",
-    "from sklearn.tree import DecisionTreeClassifier\n",
-    "from sklearn.datasets import make_classification, load_iris, load_wine\n",
-    "from sklearn.model_selection import train_test_split\n",
-    "from stree import Stree\n",
-    "import time"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "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"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "Fraud: 0.244% 196\nValid: 99.755% 80234\nX.shape (1196, 28)  y.shape (1196,)\nFraud: 16.472% 197\nValid: 83.528% 999\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",
-    "    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(-5000) # Take all true samples + 5000 of the others\n",
-    "# data = load_creditcard(5000)  # Take the first 5000 samples\n",
-    "data = load_creditcard(-1000) # Take all the samples\n",
-    "\n",
-    "Xtrain = data[0]\n",
-    "Xtest = data[1]\n",
-    "ytrain = data[2]\n",
-    "ytest = data[3]\n",
-    "# Set weights inverse to its count class in dataset\n",
-    "weights = np.ones(Xtrain.shape[0],) * 1.00244\n",
-    "weights[ytrain==1] = 1.99755 "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "Accuracy of Train without weights 0.996415770609319\nAccuracy of Train with    weights 0.994026284348865\nAccuracy of Tests without weights 0.9665738161559888\nAccuracy of Tests with    weights 0.9721448467966574\n"
-    }
-   ],
-   "source": [
-    "C = 23\n",
-    "print(\"Accuracy of Train without weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain).score(Xtrain, ytrain))\n",
-    "print(\"Accuracy of Train with    weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain, sample_weight=weights).score(Xtrain, ytrain))\n",
-    "print(\"Accuracy of Tests without weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain).score(Xtest, ytest))\n",
-    "print(\"Accuracy of Tests with    weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain, sample_weight=weights).score(Xtest, ytest))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": [
-     "outputPrepend"
-    ]
-   },
-   "outputs": [],
-   "source": [
-    "t = time.time()\n",
-    "for C in (.001, .01, 1, 5, 17):\n",
-    "    clf = Stree(C=C, random_state=random_state)\n",
-    "    clf.fit(Xtrain, ytrain)\n",
-    "    print(f\"************** C={C} ****************************\")\n",
-    "    print(f\"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}\")\n",
-    "    print(f\"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}\")\n",
-    "    print(clf)\n",
-    "    print(f\"**************************************************\")\n",
-    "print(f\"{time.time() - t:.4f} secs\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "from sklearn.preprocessing import StandardScaler\n",
-    "from sklearn.svm import LinearSVC\n",
-    "from sklearn.calibration import CalibratedClassifierCV\n",
-    "scaler = StandardScaler()\n",
-    "cclf = CalibratedClassifierCV(base_estimator=LinearSVC(), cv=5)\n",
-    "cclf.fit(Xtrain, ytrain)\n",
-    "res = cclf.predict_proba(Xtest)\n",
-    "print(res[:4, :])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#check iterator\n",
-    "for i in list(clf):\n",
-    "    print(i)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#check iterator again\n",
-    "for i in clf:\n",
-    "    print(i)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Check if the classifier is a sklearn estimator\n",
-    "from sklearn.utils.estimator_checks import check_estimator\n",
-    "check_estimator(Stree())"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Make checks one by one\n",
-    "c = 0\n",
-    "checks = check_estimator(Stree(), generate_only=True)\n",
-    "for check in checks:\n",
-    "    c += 1\n",
-    "    print(c, check[1])\n",
-    "    check[1](check[0])"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3.7.6 64-bit ('general': venv)",
-   "language": "python",
-   "name": "python37664bitgeneralvenvfbd0a23e74cf4e778460f5ffc6761f39"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.6-final"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

notebooks/test_graphs.ipynb

@@ -1,197 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#\n",
-    "# Google Colab setup\n",
-    "#\n",
-    "#!pip install git+https://github.com/doctorado-ml/stree"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "error",
-     "ename": "ModuleNotFoundError",
-     "evalue": "No module named 'stree'",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-12-36af63297651>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdatasets\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mmake_blobs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msvm\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mLinearSVC\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 6\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mstree\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mStree\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mStree_grapher\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
-      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'stree'"
-     ]
-    }
-   ],
-   "source": [
-    "import time\n",
-    "import random\n",
-    "import numpy as np\n",
-    "from sklearn.datasets import make_blobs\n",
-    "from sklearn.svm import LinearSVC\n",
-    "from stree import Stree, Stree_grapher"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def build_data(random_state):\n",
-    "    random.seed(random_state)\n",
-    "    X, y = make_blobs(centers=10, n_features=3, n_samples=500, random_state=random_state)\n",
-    "    def make_binary(y):\n",
-    "        for i in range(2, 10):\n",
-    "            y[y==i] = random.randint(0, 1)\n",
-    "        return y\n",
-    "    y = make_binary(y)\n",
-    "    #print(X.shape, np.unique(y), y[y==0].shape, y[y==1].shape)\n",
-    "    return X, y"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "error",
-     "ename": "NameError",
-     "evalue": "name 'Stree_grapher' is not defined",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-4-b909470cb406>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mbuild_data\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mgr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mStree_grapher\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mC\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m.01\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmax_iter\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m200\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m \u001b[0mgr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;31m#gr.save_all(save_folder='data/', save_prefix='7')\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;31mNameError\u001b[0m: name 'Stree_grapher' is not defined"
-     ]
-    }
-   ],
-   "source": [
-    "X, y = build_data(10)\n",
-    "gr = Stree_grapher(dict(C=.01, max_iter=200))\n",
-    "gr.fit(X, y)\n",
-    "#gr.save_all(save_folder='data/', save_prefix='7')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "error",
-     "ename": "NameError",
-     "evalue": "name 'gr' is not defined",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-5-efa3db892bfd>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mgr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m: name 'gr' is not defined"
-     ]
-    }
-   ],
-   "source": [
-    "print(gr)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "error",
-     "ename": "NameError",
-     "evalue": "name 'gr' is not defined",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-6-0e62f081c9aa>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mmatplotlib\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0mmatplotlib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0muse\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Agg'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0mgr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave_all\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msave_folder\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'data/'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m: name 'gr' is not defined"
-     ]
-    }
-   ],
-   "source": [
-    "import matplotlib\n",
-    "matplotlib.use('Agg')\n",
-    "gr.save_all(save_folder='data/')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "error",
-     "ename": "NameError",
-     "evalue": "name 'gr' is not defined",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-7-b0484cfe9d26>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0;31m#%matplotlib inline\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0mget_ipython\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun_line_magic\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'matplotlib'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'widget'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0mgr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_tree_gr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mplot_hyperplane\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m: name 'gr' is not defined"
-     ]
-    }
-   ],
-   "source": [
-    "#Uncomment one of the following lines to display graphics: static(inline), dynamic(widget)\n",
-    "#%matplotlib inline\n",
-    "%matplotlib widget\n",
-    "gr._tree_gr.plot_hyperplane()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "error",
-     "ename": "NameError",
-     "evalue": "name 'gr' is not defined",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-8-4277c1aacbe2>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0mget_ipython\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun_line_magic\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'matplotlib'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'inline'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0;31m#%matplotlib widget\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0mgr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mplot_all\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m: name 'gr' is not defined"
-     ]
-    }
-   ],
-   "source": [
-    "#Uncomment one of the following lines to display graphics: static(inline), dynamic(widget)\n",
-    "%matplotlib inline\n",
-    "#%matplotlib widget\n",
-    "gr.plot_all()"
-   ]
-  }
- ],
- "metadata": {
-  "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": "3.7.6-final"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

pyproject.toml

@@ -0,0 +1,16 @@
+[tool.black]
+line-length = 79
+include = '\.pyi?$'
+exclude = '''
+/(
+    \.git
+  | \.hg
+  | \.mypy_cache
+  | \.tox
+  | \.venv
+  | _build
+  | buck-out
+  | build
+  | dist
+)/
+'''

requirements.txt

@@ -1,5 +1,4 @@
 numpy
-scikit-learn
+scikit-learn==0.23.2
 pandas
-matplotlib
 ipympl

setup.py

@@ -1,41 +1,36 @@
 import setuptools
 
-__version__ = "0.9rc4"
+__version__ = "0.9rc6"
 __author__ = "Ricardo Montañana Gómez"
 
 
 def readme():
-    with open('README.md') as f:
+    with open("README.md") as f:
         return f.read()
 
 
 setuptools.setup(
-    name='STree',
+    name="STree",
     version=__version__,
-    license='MIT License',
+    license="MIT License",
-    description='Oblique decision tree with svm nodes',
+    description="Oblique decision tree with svm nodes",
     long_description=readme(),
-    long_description_content_type='text/markdown',
+    long_description_content_type="text/markdown",
     packages=setuptools.find_packages(),
-    url='https://github.com/doctorado-ml/stree',
+    url="https://github.com/doctorado-ml/stree",
     author=__author__,
-    author_email='ricardo.montanana@alu.uclm.es',
+    author_email="ricardo.montanana@alu.uclm.es",
-    keywords='scikit-learn oblique-classifier oblique-decision-tree decision-\
+    keywords="scikit-learn oblique-classifier oblique-decision-tree decision-\
-    tree svm svc',
+    tree svm svc",
     classifiers=[
-        'Development Status :: 4 - Beta',
+        "Development Status :: 4 - Beta",
-        'License :: OSI Approved :: MIT License',
+        "License :: OSI Approved :: MIT License",
-        'Programming Language :: Python :: 3.7',
+        "Programming Language :: Python :: 3.8",
-        'Natural Language :: English',
+        "Natural Language :: English",
-        'Topic :: Scientific/Engineering :: Artificial Intelligence',
+        "Topic :: Scientific/Engineering :: Artificial Intelligence",
-        'Intended Audience :: Science/Research'
+        "Intended Audience :: Science/Research",
-    ],
-    install_requires=[
-        'scikit-learn>=0.23.0',
-        'numpy',
-        'matplotlib',
-        'ipympl'
     ],
+    install_requires=["scikit-learn==0.23.2", "numpy", "ipympl"],
     test_suite="stree.tests",
-    zip_safe=False
+    zip_safe=False,
 )

stree/Strees.py

@@ -1,20 +1,30 @@
-'''
+"""
 __author__ = "Ricardo Montañana Gómez"
 __copyright__ = "Copyright 2020, Ricardo Montañana Gómez"
 __license__ = "MIT"
 __version__ = "0.9"
 Build an oblique tree classifier based on SVM Trees
-Uses LinearSVC
+"""
-'''
 
 import os
-
+import numbers
+import random
+import warnings
+from math import log, factorial
+from typing import Optional
 import numpy as np
 from sklearn.base import BaseEstimator, ClassifierMixin
-from sklearn.svm import LinearSVC
+from sklearn.svm import SVC, LinearSVC
+from sklearn.utils import check_consistent_length
 from sklearn.utils.multiclass import check_classification_targets
-from sklearn.utils.validation import check_X_y, check_array, check_is_fitted, \
+from sklearn.exceptions import ConvergenceWarning
-    _check_sample_weight
+from sklearn.utils.validation import (
+    check_X_y,
+    check_array,
+    check_is_fitted,
+    _check_sample_weight,
+)
+from sklearn.metrics._classification import _weighted_sum, _check_targets
 
 
 class Snode:
@@ -22,23 +32,49 @@ class Snode:
     dataset assigned to it
     """
 
-    def __init__(self, clf: LinearSVC, X: np.ndarray, y: np.ndarray,
+    def __init__(
-                 title: str):
+        self,
+        clf: SVC,
+        X: np.ndarray,
+        y: np.ndarray,
+        features: np.array,
+        impurity: float,
+        title: str,
+        weight: np.ndarray = None,
+    ):
         self._clf = clf
-        self._vector = None if clf is None else clf.coef_
-        self._interceptor = 0. if clf is None else clf.intercept_
         self._title = title
-        self._belief = 0.
+        self._belief = 0.0
         # Only store dataset in Testing
-        self._X = X if os.environ.get('TESTING', 'NS') != 'NS' else None
+        self._X = X if os.environ.get("TESTING", "NS") != "NS" else None
         self._y = y
         self._down = None
         self._up = None
         self._class = None
+        self._feature = None
+        self._sample_weight = (
+            weight if os.environ.get("TESTING", "NS") != "NS" else None
+        )
+        self._features = features
+        self._impurity = impurity
+        self._partition_column: int = -1
 
     @classmethod
-    def copy(cls, node: 'Snode') -> 'Snode':
+    def copy(cls, node: "Snode") -> "Snode":
-        return cls(node._clf, node._X, node._y, node._title)
+        return cls(
+            node._clf,
+            node._X,
+            node._y,
+            node._features,
+            node._impurity,
+            node._title,
+        )
+
+    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
@@ -49,10 +85,10 @@ class Snode:
     def is_leaf(self) -> bool:
         return self._up is None and self._down is None
 
-    def get_down(self) -> 'Snode':
+    def get_down(self) -> "Snode":
         return self._down
 
-    def get_up(self) -> 'Snode':
+    def get_up(self) -> "Snode":
         return self._up
 
     def make_predictor(self):
@@ -64,37 +100,38 @@ class Snode:
         classes, card = np.unique(self._y, return_counts=True)
         if len(classes) > 1:
             max_card = max(card)
-            min_card = min(card)
-            try:
-                self._belief = max_card / (max_card + min_card)
-            except ZeroDivisionError:
-                self._belief = 0.
             self._class = classes[card == max_card][0]
+            self._belief = max_card / np.sum(card)
         else:
             self._belief = 1
-            self._class = classes[0]
+            try:
+                self._class = classes[0]
+            except IndexError:
+                self._class = None
 
     def __str__(self) -> str:
+        count_values = np.unique(self._y, return_counts=True)
         if self.is_leaf():
-            count_values = np.unique(self._y, return_counts=True)
+            return (
-            result = f"{self._title} - Leaf class={self._class} belief="\
+                f"{self._title} - Leaf class={self._class} belief="
-                f"{self._belief: .6f} counts={count_values}"
+                f"{self._belief: .6f} impurity={self._impurity:.4f} "
-            return result
+                f"counts={count_values}"
+            )
         else:
-            return f"{self._title}"
+            return (
+                f"{self._title} feaures={self._features} impurity="
+                f"{self._impurity:.4f} "
+                f"counts={count_values}"
+            )
 
 
 class Siterator:
-    """Stree preorder iterator
+    """Stree preorder iterator"""
-    """
 
     def __init__(self, tree: Snode):
         self._stack = []
         self._push(tree)
 
-    def __iter__(self):
-        return self
-
     def _push(self, node: Snode):
         if node is not None:
             self._stack.append(node)
@@ -108,49 +145,220 @@ class Siterator:
         return node
 
 
-class Stree(BaseEstimator, ClassifierMixin):
+class Splitter:
-    """Estimator that is based on binary trees of svm nodes
+    def __init__(
-    can deal with sample_weights in predict, used in boosting sklearn methods
+        self,
-    inheriting from BaseEstimator implements get_params and set_params methods
+        clf: SVC = None,
-    inheriting from ClassifierMixin implement the attribute _estimator_type
+        criterion: str = None,
-    with "classifier" as value
+        splitter_type: str = None,
-    """
+        criteria: str = None,
+        min_samples_split: int = None,
+        random_state=None,
+    ):
+        self._clf = clf
+        self._random_state = random_state
+        if random_state is not None:
+            random.seed(random_state)
+        self._criterion = criterion
+        self._min_samples_split = min_samples_split
+        self._criteria = criteria
+        self._splitter_type = splitter_type
 
-    def __init__(self, C: float = 1.0, max_iter: int = 1000,
+        if clf is None:
-                 random_state: int = None, max_depth: int = None,
+            raise ValueError(f"clf has to be a sklearn estimator, got({clf})")
-                 tol: float = 1e-4, use_predictions: bool = False):
-        self.max_iter = max_iter
-        self.C = C
-        self.random_state = random_state
-        self.use_predictions = use_predictions
-        self.max_depth = max_depth
-        self.tol = tol
 
-    def _more_tags(self) -> dict:
+        if criterion not in ["gini", "entropy"]:
-        """Required by sklearn to tell that this estimator is a binary classifier
+            raise ValueError(
+                f"criterion must be gini or entropy got({criterion})"
+            )
 
-        :return: the tag required
+        if criteria not in [
-        :rtype: dict
+            "max_samples",
+            "impurity",
+        ]:
+            raise ValueError(
+                f"criteria has to be max_samples or impurity; got ({criteria})"
+            )
+
+        if splitter_type not in ["random", "best"]:
+            raise ValueError(
+                f"splitter must be either random or best, got({splitter_type})"
+            )
+        self.criterion_function = getattr(self, f"_{self._criterion}")
+        self.decision_criteria = getattr(self, f"_{self._criteria}")
+
+    def partition_impurity(self, y: np.array) -> np.array:
+        return self.criterion_function(y)
+
+    @staticmethod
+    def _gini(y: np.array) -> float:
+        _, count = np.unique(y, return_counts=True)
+        return 1 - np.sum(np.square(count / np.sum(count)))
+
+    @staticmethod
+    def _entropy(y: np.array) -> float:
+        n_labels = len(y)
+        if n_labels <= 1:
+            return 0
+        counts = np.bincount(y)
+        proportions = counts / n_labels
+        n_classes = np.count_nonzero(proportions)
+        if n_classes <= 1:
+            return 0
+        entropy = 0.0
+        # Compute standard entropy.
+        for prop in proportions:
+            if prop != 0.0:
+                entropy -= prop * log(prop, n_classes)
+        return entropy
+
+    def information_gain(
+        self, labels: np.array, labels_up: np.array, labels_dn: np.array
+    ) -> float:
+        imp_prev = self.criterion_function(labels)
+        card_up = card_dn = imp_up = imp_dn = 0
+        if labels_up is not None:
+            card_up = labels_up.shape[0]
+            imp_up = self.criterion_function(labels_up)
+        if labels_dn is not None:
+            card_dn = labels_dn.shape[0] if labels_dn is not None else 0
+            imp_dn = self.criterion_function(labels_dn)
+        samples = card_up + card_dn
+        if samples == 0:
+            return 0.0
+        else:
+            result = (
+                imp_prev
+                - (card_up / samples) * imp_up
+                - (card_dn / samples) * imp_dn
+            )
+            return result
+
+    def _select_best_set(
+        self, dataset: np.array, labels: np.array, features_sets: list
+    ) -> list:
+        max_gain = 0
+        selected = None
+        warnings.filterwarnings("ignore", category=ConvergenceWarning)
+        for feature_set in features_sets:
+            self._clf.fit(dataset[:, feature_set], labels)
+            node = Snode(
+                self._clf, dataset, labels, feature_set, 0.0, "subset"
+            )
+            self.partition(dataset, node, train=True)
+            y1, y2 = self.part(labels)
+            gain = self.information_gain(labels, y1, y2)
+            if gain > max_gain:
+                max_gain = gain
+                selected = feature_set
+        return selected if selected is not None else feature_set
+
+    @staticmethod
+    def _generate_spaces(features: int, max_features: int) -> list:
+        comb = set()
+        # Generate at most 5 combinations
+        if max_features == features:
+            set_length = 1
+        else:
+            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:
+        features_sets = self._generate_spaces(dataset.shape[1], max_features)
+        if len(features_sets) > 1:
+            if self._splitter_type == "random":
+                index = random.randint(0, len(features_sets) - 1)
+                return features_sets[index]
+            else:
+                return self._select_best_set(dataset, labels, features_sets)
+        else:
+            return features_sets[0]
+
+    def get_subspace(
+        self, dataset: np.array, labels: np.array, max_features: int
+    ) -> tuple:
+        """Return the best/random subspace to make a split"""
+        indices = self._get_subspaces_set(dataset, labels, max_features)
+        return dataset[:, indices], indices
+
+    def _impurity(self, data: np.array, y: np.array) -> np.array:
+        """return column of dataset to be taken into account to split dataset
+
+        :param data: distances to hyper plane of every class
+        :type data: np.array (m, n_classes)
+        :param y: vector of labels (classes)
+        :type y: np.array (m,)
+        :return: column of dataset to be taken into account to split dataset
+        :rtype: int
         """
-        return {'binary_only': True, 'requires_y': True}
+        max_gain = 0
+        selected = -1
+        for col in range(data.shape[1]):
+            tup = y[data[:, col] > 0]
+            tdn = y[data[:, col] <= 0]
+            info_gain = self.information_gain(y, tup, tdn)
+            if info_gain > max_gain:
+                selected = col
+                max_gain = info_gain
+        return selected
 
-    def _linear_function(self, data: np.array, node: Snode) -> np.array:
+    @staticmethod
-        """Compute the distance of set of samples to a hyperplane, in
+    def _max_samples(data: np.array, y: np.array) -> np.array:
-        multiclass classification it should compute the distance to a
+        """return column of dataset to be taken into account to split dataset
-        hyperplane of each class
 
-        :param data: dataset of samples
+        :param data: distances to hyper plane of every class
-        :type data: np.array
+        :type data: np.array (m, n_classes)
-        :param node: the node that contains the hyperplance coefficients
+        :param y: vector of labels (classes)
-        :type node: Snode
+        :type y: np.array (m,)
-        :return: array of distances of each sample to the hyperplane
+        :return: column of dataset to be taken into account to split dataset
-        :rtype: np.array
+        :rtype: int
         """
-        coef = node._vector[0, :].reshape(-1, data.shape[1])
+        # select the class with max number of samples
-        return data.dot(coef.T) + node._interceptor[0]
+        _, samples = np.unique(y, return_counts=True)
+        return np.argmax(samples)
 
-    def _split_array(self, origin: np.array, down: np.array) -> list:
+    def partition(self, samples: np.array, node: Snode, train: bool):
-        """Split an array in two based on indices passed as down and its complement
+        """Set the criteria to split arrays. Compute the indices of the samples
+        that should go to one side of the tree (down)
+
+        """
+        # 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:
+            # 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
+            # Convert data to a (m, 1) array selecting values for samples
+            if train:
+                # in train time we have to compute the column to take into
+                # account to split the dataset
+                col = self.decision_criteria(data, node._y)
+                node.set_partition_column(col)
+            else:
+                # in predcit time just use the column computed in train time
+                # is taking the classifier of class <col>
+                col = node.get_partition_column()
+                if col == -1:
+                    # No partition is producing information gain
+                    data = np.ones(data.shape)
+            data = data[:, col]
+        self._up = data > 0
+
+    def part(self, origin: np.array) -> list:
+        """Split an array in two based on indices (down) and its complement
+        partition has to be called first to establish down indices
 
         :param origin: dataset to split
         :type origin: np.array
@@ -159,88 +367,141 @@ class Stree(BaseEstimator, ClassifierMixin):
         :return: list with two splits of the array
         :rtype: list
         """
-        up = ~down
+        down = ~self._up
-        return origin[up[:, 0]] if any(up) else None, \
+        return [
-            origin[down[:, 0]] if any(down) else None
+            origin[self._up] if any(self._up) else None,
+            origin[down] if any(down) else None,
+        ]
 
-    def _distances(self, node: Snode, data: np.ndarray) -> np.array:
+    @staticmethod
+    def _distances(node: Snode, data: np.ndarray) -> np.array:
         """Compute distances of the samples to the hyperplane of the node
 
         :param node: node containing the svm classifier
         :type node: Snode
         :param data: samples to find out distance to hyperplane
         :type data: np.ndarray
-        :return: array of shape (m, 1) with the distances of every sample to
+        :return: array of shape (m, nc) with the distances of every sample to
-        the hyperplane of the node
+        the hyperplane of every class. nc = # of classes
         :rtype: np.array
         """
-        if self.use_predictions:
+        return node._clf.decision_function(data[:, node._features])
-            res = np.expand_dims(node._clf.decision_function(data), 1)
-        else:
-            """doesn't work with multiclass as each sample has to do inner
-            product with its own coefficients computes positition of every
-            sample is w.r.t. the hyperplane
-            """
-            res = self._linear_function(data, node)
-        return res
 
-    def _split_criteria(self, data: np.array) -> np.array:
-        """Set the criteria to split arrays
 
-        :param data: [description]
+class Stree(BaseEstimator, ClassifierMixin):
-        :type data: np.array
+    """Estimator that is based on binary trees of svm nodes
-        :return: [description]
+    can deal with sample_weights in predict, used in boosting sklearn methods
-        :rtype: np.array
+    inheriting from BaseEstimator implements get_params and set_params methods
+    inheriting from ClassifierMixin implement the attribute _estimator_type
+    with "classifier" as value
+    """
+
+    def __init__(
+        self,
+        C: float = 1.0,
+        kernel: str = "linear",
+        max_iter: int = 1e5,
+        random_state: int = None,
+        max_depth: int = None,
+        tol: float = 1e-4,
+        degree: int = 3,
+        gamma="scale",
+        split_criteria: str = "impurity",
+        criterion: str = "entropy",
+        min_samples_split: int = 0,
+        max_features=None,
+        splitter: str = "random",
+    ):
+        self.max_iter = max_iter
+        self.C = C
+        self.kernel = kernel
+        self.random_state = random_state
+        self.max_depth = max_depth
+        self.tol = tol
+        self.gamma = gamma
+        self.degree = degree
+        self.min_samples_split = min_samples_split
+        self.split_criteria = split_criteria
+        self.max_features = max_features
+        self.criterion = criterion
+        self.splitter = splitter
+
+    def _more_tags(self) -> dict:
+        """Required by sklearn to supply features of the classifier
+
+        :return: the tag required
+        :rtype: dict
         """
-        return data > 0
+        return {"requires_y": True}
 
-    def fit(self, X: np.ndarray, y: np.ndarray,
+    def fit(
-            sample_weight: np.array = None) -> 'Stree':
+        self, X: np.ndarray, y: np.ndarray, sample_weight: np.array = None
+    ) -> "Stree":
         """Build the tree based on the dataset of samples and its labels
 
+        :param X: dataset of samples to make predictions
+        :type X: np.array
+        :param y: samples labels
+        :type y: np.array
+        :param sample_weight: weights of the samples. Rescale C per sample.
+        Hi' weights force the classifier to put more emphasis on these points
+        :type sample_weight: np.array optional
         :raises ValueError: if parameters C or max_depth are out of bounds
         :return: itself to be able to chain actions: fit().predict() ...
         :rtype: Stree
         """
         # Check parameters are Ok.
-        if type(y).__name__ == 'np.ndarray':
-            y = y.ravel()
         if self.C < 0:
             raise ValueError(
-                f"Penalty term must be positive... got (C={self.C:f})")
+                f"Penalty term must be positive... got (C={self.C:f})"
-        self.__max_depth = np.iinfo(
+            )
-            np.int32).max if self.max_depth is None else self.max_depth
+        self.__max_depth = (
+            np.iinfo(np.int32).max
+            if self.max_depth is None
+            else self.max_depth
+        )
         if self.__max_depth < 1:
             raise ValueError(
                 f"Maximum depth has to be greater than 1... got (max_depth=\
-                    {self.max_depth})")
+                    {self.max_depth})"
+            )
+
         check_classification_targets(y)
         X, y = check_X_y(X, y)
-        sample_weight = _check_sample_weight(sample_weight, X)
+        sample_weight = _check_sample_weight(
+            sample_weight, X, dtype=np.float64
+        )
         check_classification_targets(y)
         # Initialize computed parameters
+        self.splitter_ = Splitter(
+            clf=self._build_clf(),
+            criterion=self.criterion,
+            splitter_type=self.splitter,
+            criteria=self.split_criteria,
+            random_state=self.random_state,
+            min_samples_split=self.min_samples_split,
+        )
+        if self.random_state is not None:
+            random.seed(self.random_state)
         self.classes_, y = np.unique(y, return_inverse=True)
+        self.n_classes_ = self.classes_.shape[0]
         self.n_iter_ = self.max_iter
         self.depth_ = 0
+        self.n_features_ = X.shape[1]
         self.n_features_in_ = X.shape[1]
-        self.tree_ = self.train(X, y, sample_weight, 1, 'root')
+        self.max_features_ = self._initialize_max_features()
+        self.tree_ = self.train(X, y, sample_weight, 1, "root")
         self._build_predictor()
         return self
 
-    def _build_predictor(self):
+    def train(
-        """Process the leaves to make them predictors
+        self,
-        """
+        X: np.ndarray,
-        def run_tree(node: Snode):
+        y: np.ndarray,
-            if node.is_leaf():
+        sample_weight: np.ndarray,
-                node.make_predictor()
+        depth: int,
-                return
+        title: str,
-            run_tree(node.get_down())
+    ) -> Optional[Snode]:
-            run_tree(node.get_up())
-
-        run_tree(self.tree_)
-
-    def train(self, X: np.ndarray, y: np.ndarray, sample_weight: np.ndarray,
-              depth: int, title: str) -> Snode:
         """Recursive function to split the original dataset into predictor
         nodes (leaves)
 
@@ -248,7 +509,8 @@ class Stree(BaseEstimator, ClassifierMixin):
         :type X: np.ndarray
         :param y: samples labels
         :type y: np.ndarray
-        :param sample_weight: weight of samples (used in boosting)
+        :param sample_weight: weight of samples. Rescale C per sample.
+        Hi weights force the classifier to put more emphasis on these points.
         :type sample_weight: np.ndarray
         :param depth: actual depth in the tree
         :type depth: int
@@ -261,25 +523,83 @@ class Stree(BaseEstimator, ClassifierMixin):
             return None
         if np.unique(y).shape[0] == 1:
             # only 1 class => pure dataset
-            return Snode(None, X, y, title + ', <pure>')
+            return Snode(
+                clf=None,
+                X=X,
+                y=y,
+                features=X.shape[1],
+                impurity=0.0,
+                title=title + ", <pure>",
+                weight=sample_weight,
+            )
         # Train the model
-        clf = LinearSVC(max_iter=self.max_iter, random_state=self.random_state,
+        clf = self._build_clf()
-                        C=self.C)  # , sample_weight=sample_weight)
+        Xs, features = self.splitter_.get_subspace(X, y, self.max_features_)
-        clf.fit(X, y, sample_weight=sample_weight)
+        # solve WARNING: class label 0 specified in weight is not found
-        tree = Snode(clf, X, y, title)
+        # in bagging
+        if any(sample_weight == 0):
+            indices = sample_weight == 0
+            y_next = y[~indices]
+            # touch weights if removing any class
+            if np.unique(y_next).shape[0] != self.n_classes_:
+                sample_weight += 1e-5
+        clf.fit(Xs, y, sample_weight=sample_weight)
+        impurity = self.splitter_.partition_impurity(y)
+        node = Snode(clf, X, y, features, impurity, title, sample_weight)
         self.depth_ = max(depth, self.depth_)
-        down = self._split_criteria(self._distances(tree, X))
+        self.splitter_.partition(X, node, True)
-        X_U, X_D = self._split_array(X, down)
+        X_U, X_D = self.splitter_.part(X)
-        y_u, y_d = self._split_array(y, down)
+        y_u, y_d = self.splitter_.part(y)
-        sw_u, sw_d = self._split_array(sample_weight, down)
+        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(clf, X, y, title + ', <cgaf>')
+            return Snode(
-        tree.set_up(self.train(X_U, y_u, sw_u, depth + 1, title + ' - Up'))
+                clf,
-        tree.set_down(self.train(X_D, y_d, sw_d, depth + 1, title + ' - Down'))
+                X,
-        return tree
+                y,
+                features=X.shape[1],
+                impurity=impurity,
+                title=title + ", <cgaf>",
+                weight=sample_weight,
+            )
+        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 _reorder_results(self, y: np.array, indices: np.array) -> np.array:
+    def _build_predictor(self):
+        """Process the leaves to make them predictors"""
+
+        def run_tree(node: Snode):
+            if node.is_leaf():
+                node.make_predictor()
+                return
+            run_tree(node.get_down())
+            run_tree(node.get_up())
+
+        run_tree(self.tree_)
+
+    def _build_clf(self):
+        """Build the correct classifier for the node"""
+        return (
+            LinearSVC(
+                max_iter=self.max_iter,
+                random_state=self.random_state,
+                C=self.C,
+                tol=self.tol,
+            )
+            if self.kernel == "linear"
+            else SVC(
+                kernel=self.kernel,
+                max_iter=self.max_iter,
+                tol=self.tol,
+                C=self.C,
+                gamma=self.gamma,
+                degree=self.degree,
+            )
+        )
+
+    @staticmethod
+    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
@@ -289,12 +609,8 @@ class Stree(BaseEstimator, ClassifierMixin):
         :return: array y ordered
         :rtype: np.array
         """
-        if y.ndim > 1 and y.shape[1] > 1:
+        # return array of same type given in y
-            # if predict_proba return np.array of floats
+        y_ordered = y.copy()
-            y_ordered = np.zeros(y.shape, dtype=float)
-        else:
-            # return array of same type given in y
-            y_ordered = y.copy()
         indices = indices.astype(int)
         for i, index in enumerate(indices):
             y_ordered[index] = y[i]
@@ -308,108 +624,70 @@ class Stree(BaseEstimator, ClassifierMixin):
         :return: array of labels
         :rtype: np.array
         """
-        def predict_class(xp: np.array, indices: np.array,
+
-                          node: Snode) -> np.array:
+        def predict_class(
+            xp: np.array, indices: np.array, node: Snode
+        ) -> np.array:
             if xp is None:
                 return [], []
             if node.is_leaf():
                 # set a class for every sample in dataset
                 prediction = np.full((xp.shape[0], 1), node._class)
                 return prediction, indices
-            down = self._split_criteria(self._distances(node, xp))
+            self.splitter_.partition(xp, node, train=False)
-            X_U, X_D = self._split_array(xp, down)
+            x_u, x_d = self.splitter_.part(xp)
-            i_u, i_d = self._split_array(indices, down)
+            i_u, i_d = self.splitter_.part(indices)
-            prx_u, prin_u = predict_class(X_U, i_u, node.get_up())
+            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())
+            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
-        check_is_fitted(self, ['tree_'])
+        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]})"
+            )
         # setup prediction & make it happen
         indices = np.arange(X.shape[0])
-        result = self._reorder_results(
+        result = (
-            *predict_class(X, indices, self.tree_)).astype(int).ravel()
+            self._reorder_results(*predict_class(X, indices, self.tree_))
+            .astype(int)
+            .ravel()
+        )
         return self.classes_[result]
 
-    def predict_proba(self, X: np.array) -> np.array:
+    def score(
-        """Computes an approximation of the probability of samples belonging to
+        self, X: np.array, y: np.array, sample_weight: np.array = None
-        class 0 and 1
+    ) -> float:
-        :param X: dataset
-        :type X: np.array
-        :return: array array of shape (m, num_classes), probability of being
-        each class
-        :rtype: np.array
-        """
-        def predict_class(xp: np.array, indices: np.array, dist: np.array,
-                          node: Snode) -> np.array:
-            """Run the tree to compute predictions
-
-            :param xp: subdataset of samples
-            :type xp: np.array
-            :param indices: indices of subdataset samples to rebuild original
-            order
-            :type indices: np.array
-            :param dist: distances of every sample to the hyperplane or the
-            father node
-            :type dist: np.array
-            :param node: node of the leaf with the class
-            :type node: Snode
-            :return: array of labels and distances, array of indices
-            :rtype: np.array
-            """
-            if xp is None:
-                return [], []
-            if node.is_leaf():
-                # set a class for every sample in dataset
-                prediction = np.full((xp.shape[0], 1), node._class)
-                prediction_proba = dist
-                return np.append(prediction, prediction_proba, axis=1), indices
-            distances = self._distances(node, xp)
-            down = self._split_criteria(distances)
-            X_U, X_D = self._split_array(xp, down)
-            i_u, i_d = self._split_array(indices, down)
-            di_u, di_d = self._split_array(distances, down)
-            prx_u, prin_u = predict_class(X_U, i_u, di_u, node.get_up())
-            prx_d, prin_d = predict_class(X_D, i_d, di_d, node.get_down())
-            return np.append(prx_u, prx_d), np.append(prin_u, prin_d)
-
-        # sklearn check
-        check_is_fitted(self, ['tree_'])
-        # Input validation
-        X = check_array(X)
-        # setup prediction & make it happen
-        indices = np.arange(X.shape[0])
-        empty_dist = np.empty((X.shape[0], 1), dtype=float)
-        result, indices = predict_class(X, indices, empty_dist, self.tree_)
-        result = result.reshape(X.shape[0], 2)
-        # Turn distances to hyperplane into probabilities based on fitting
-        # distances of samples to its hyperplane that classified them, to the
-        # sigmoid function
-        # Probability of being 1
-        result[:, 1] = 1 / (1 + np.exp(-result[:, 1]))
-        # Probability of being 0
-        result[:, 0] = 1 - result[:, 1]
-        return self._reorder_results(result, indices)
-
-    def score(self, X: np.array, y: np.array) -> float:
         """Compute accuracy of the prediction
 
         :param X: dataset of samples to make predictions
         :type X: np.array
-        :param y: samples labels
+        :param y_true: samples labels
-        :type y: np.array
+        :type y_true: np.array
+        :param sample_weight: weights of the samples. Rescale C per sample.
+        Hi' weights force the classifier to put more emphasis on these points
+        :type sample_weight: np.array optional
         :return: accuracy of the prediction
         :rtype: float
         """
         # sklearn check
         check_is_fitted(self)
-        yp = self.predict(X).reshape(y.shape)
+        check_classification_targets(y)
-        return np.mean(yp == y)
+        X, y = check_X_y(X, y)
+        y_pred = self.predict(X).reshape(y.shape)
+        # Compute accuracy for each possible representation
+        _, y_true, y_pred = _check_targets(y, y_pred)
+        check_consistent_length(y_true, y_pred, sample_weight)
+        score = y_true == y_pred
+        return _weighted_sum(score, sample_weight, normalize=True)
 
     def __iter__(self) -> Siterator:
-        """Create an iterator to be able to visit the nodes of the tree in preorder,
+        """Create an iterator to be able to visit the nodes of the tree in
-        can make a list with all the nodes in preorder
+        preorder, can make a list with all the nodes in preorder
 
         :return: an iterator, can for i in... and list(...)
         :rtype: Siterator
@@ -426,7 +704,38 @@ class Stree(BaseEstimator, ClassifierMixin):
         :return: description of nodes in the tree in preorder
         :rtype: str
         """
-        output = ''
+        output = ""
         for i in self:
-            output += str(i) + '\n'
+            output += str(i) + "\n"
         return output
+
+    def _initialize_max_features(self) -> int:
+        if isinstance(self.max_features, str):
+            if self.max_features == "auto":
+                max_features = max(1, int(np.sqrt(self.n_features_)))
+            elif self.max_features == "sqrt":
+                max_features = max(1, int(np.sqrt(self.n_features_)))
+            elif self.max_features == "log2":
+                max_features = max(1, int(np.log2(self.n_features_)))
+            else:
+                raise ValueError(
+                    "Invalid value for max_features. "
+                    "Allowed string values are 'auto', "
+                    "'sqrt' or 'log2'."
+                )
+        elif self.max_features is None:
+            max_features = self.n_features_
+        elif isinstance(self.max_features, numbers.Integral):
+            max_features = self.max_features
+        else:  # float
+            if self.max_features > 0.0:
+                max_features = max(
+                    1, int(self.max_features * self.n_features_)
+                )
+            else:
+                raise ValueError(
+                    "Invalid value for max_features."
+                    "Allowed float must be in range (0, 1] "
+                    f"got ({self.max_features})"
+                )
+        return max_features

stree/Strees_grapher.py

@@ -1,189 +0,0 @@
-'''
-__author__ = "Ricardo Montañana Gómez"
-__copyright__ = "Copyright 2020, Ricardo Montañana Gómez"
-__license__ = "MIT"
-__version__ = "0.9"
-Plot 3D views of nodes in Stree
-'''
-
-import os
-
-import matplotlib.pyplot as plt
-import numpy as np
-from sklearn.decomposition import PCA
-from mpl_toolkits.mplot3d import Axes3D
-
-from .Strees import Stree, Snode, Siterator
-
-
-class Snode_graph(Snode):
-
-    def __init__(self, node: Stree):
-        self._plot_size = (8, 8)
-        self._xlimits = (None, None)
-        self._ylimits = (None, None)
-        self._zlimits = (None, None)
-        n = Snode.copy(node)
-        super().__init__(n._clf, n._X, n._y, n._title)
-
-    def set_plot_size(self, size: tuple):
-        self._plot_size = size
-
-    def _is_pure(self) -> bool:
-        """is considered pure a leaf node with one label
-        """
-        if self.is_leaf():
-            return self._belief == 1.
-        return False
-
-    def set_axis_limits(self, limits: tuple):
-        self._xlimits = limits[0]
-        self._ylimits = limits[1]
-        self._zlimits = limits[2]
-
-    def _set_graphics_axis(self, ax: Axes3D):
-        ax.set_xlim(self._xlimits)
-        ax.set_ylim(self._ylimits)
-        ax.set_zlim(self._zlimits)
-
-    def save_hyperplane(self, save_folder: str = './', save_prefix: str = '',
-                        save_seq: int = 1):
-        _, fig = self.plot_hyperplane()
-        name = f"{save_folder}{save_prefix}STnode{save_seq}.png"
-        fig.savefig(name, bbox_inches='tight')
-        plt.close(fig)
-
-    def _get_cmap(self):
-        cmap = 'jet'
-        if self._is_pure() and self._class == 1:
-            cmap = 'jet_r'
-        return cmap
-
-    def _graph_title(self):
-        n_class, card = np.unique(self._y, return_counts=True)
-        return f"{self._title} {n_class} {card}"
-
-    def plot_hyperplane(self, plot_distribution: bool = True):
-        fig = plt.figure(figsize=self._plot_size)
-        ax = fig.add_subplot(1, 1, 1, projection='3d')
-        if not self._is_pure():
-            # Can't plot hyperplane of leaves with one label because it hasn't
-            # classiffier
-            # get the splitting hyperplane
-            def hyperplane(x, y): return (-self._interceptor
-                                          - self._vector[0][0] * x
-                                          - self._vector[0][1] * y) \
-                / self._vector[0][2]
-
-            tmpx = np.linspace(self._X[:, 0].min(), self._X[:, 0].max())
-            tmpy = np.linspace(self._X[:, 1].min(), self._X[:, 1].max())
-            xx, yy = np.meshgrid(tmpx, tmpy)
-            ax.plot_surface(xx, yy, hyperplane(xx, yy), alpha=.5,
-                            antialiased=True, rstride=1, cstride=1,
-                            cmap='seismic')
-            self._set_graphics_axis(ax)
-        if plot_distribution:
-            self.plot_distribution(ax)
-        else:
-            plt.title(self._graph_title())
-            plt.show()
-        return ax, fig
-
-    def plot_distribution(self, ax: Axes3D = None):
-        if ax is None:
-            fig = plt.figure(figsize=self._plot_size)
-            ax = fig.add_subplot(1, 1, 1, projection='3d')
-        plt.title(self._graph_title())
-        cmap = self._get_cmap()
-        ax.scatter(self._X[:, 0], self._X[:, 1],
-                   self._X[:, 2], c=self._y, cmap=cmap)
-        ax.set_xlabel('X0')
-        ax.set_ylabel('X1')
-        ax.set_zlabel('X2')
-        plt.show()
-
-
-class Stree_grapher(Stree):
-    """Build 3d graphs of any dataset, if it's more than 3 features PCA shall
-    make its magic
-    """
-
-    def __init__(self, params: dict):
-        self._plot_size = (8, 8)
-        self._tree_gr = None
-        # make Snode store X's
-        os.environ['TESTING'] = '1'
-        self._fitted = False
-        self._pca = None
-        super().__init__(**params)
-
-    def __del__(self):
-        try:
-            os.environ.pop('TESTING')
-        except KeyError:
-            pass
-        plt.close('all')
-
-    def _copy_tree(self, node: Snode) -> Snode_graph:
-        mirror = Snode_graph(node)
-        # clone node
-        mirror._class = node._class
-        mirror._belief = node._belief
-        if node.get_down() is not None:
-            mirror.set_down(self._copy_tree(node.get_down()))
-        if node.get_up() is not None:
-            mirror.set_up(self._copy_tree(node.get_up()))
-        return mirror
-
-    def fit(self, X: np.array, y: np.array) -> Stree:
-        """Fit the Stree and copy the tree in a Snode_graph tree
-
-        :param X: Dataset
-        :type X: np.array
-        :param y: Labels
-        :type y: np.array
-        :return: Stree model
-        :rtype: Stree
-        """
-        if X.shape[1] != 3:
-            self._pca = PCA(n_components=3)
-            X = self._pca.fit_transform(X)
-        res = super().fit(X, y)
-        self._tree_gr = self._copy_tree(self.tree_)
-        self._fitted = True
-        return res
-
-    def score(self, X: np.array, y: np.array) -> float:
-        self._check_fitted()
-        if X.shape[1] != 3:
-            X = self._pca.transform(X)
-        return super().score(X, y)
-
-    def _check_fitted(self):
-        if not self._fitted:
-            raise Exception('Have to fit the grapher first!')
-
-    def save_all(self, save_folder: str = './', save_prefix: str = ''):
-        """Save all the node plots in png format, each with a sequence number
-
-        :param save_folder: folder where the plots are saved, defaults to './'
-        :type save_folder: str, optional
-        """
-        self._check_fitted()
-        if not os.path.isdir(save_folder):
-            os.mkdir(save_folder)
-        seq = 1
-        for node in self:
-            node.save_hyperplane(save_folder=save_folder,
-                                 save_prefix=save_prefix, save_seq=seq)
-            seq += 1
-
-    def plot_all(self):
-        """Plots all the nodes
-        """
-        self._check_fitted()
-        for node in self:
-            node.plot_hyperplane()
-
-    def __iter__(self):
-        return Siterator(self._tree_gr)

stree/__init__.py

@@ -1,2 +1,3 @@
-from .Strees import Stree, Snode, Siterator
+from .Strees import Stree, Snode, Siterator, Splitter
-from .Strees_grapher import Stree_grapher, Snode_graph
+
+__all__ = ["Stree", "Snode", "Siterator", "Splitter"]

stree/tests/Snode_test.py

@@ -0,0 +1,96 @@
+import os
+import unittest
+
+import numpy as np
+
+from stree import Stree, Snode
+from .utils import load_dataset
+
+
+class Snode_test(unittest.TestCase):
+    def __init__(self, *args, **kwargs):
+        self._random_state = 1
+        self._clf = Stree(random_state=self._random_state)
+        self._clf.fit(*load_dataset(self._random_state))
+        super().__init__(*args, **kwargs)
+
+    @classmethod
+    def setUp(cls):
+        os.environ["TESTING"] = "1"
+
+    def test_attributes_in_leaves(self):
+        """Check if the attributes in leaves have correct values so they form a
+        predictor
+        """
+
+        def check_leave(node: Snode):
+            if not node.is_leaf():
+                check_leave(node.get_down())
+                check_leave(node.get_up())
+                return
+            # Check Belief in leave
+            classes, card = np.unique(node._y, return_counts=True)
+            max_card = max(card)
+            min_card = min(card)
+            if len(classes) > 1:
+                belief = max_card / (max_card + min_card)
+            else:
+                belief = 1
+            self.assertEqual(belief, node._belief)
+            # 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"""
+
+        def run_tree(node: Snode):
+            if node._belief < 1:
+                # only exclude pure leaves
+                self.assertIsNotNone(node._clf)
+                self.assertIsNotNone(node._clf.coef_)
+            if node.is_leaf():
+                return
+            run_tree(node.get_up())
+            run_tree(node.get_down())
+
+        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_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]
+        test = Snode(Stree(), px, py, [], 0.0, "test")
+        computed = Snode.copy(test)
+        self.assertListEqual(computed._X, px)
+        self.assertListEqual(computed._y, py)
+        self.assertEqual("test", computed._title)
+        self.assertIsInstance(computed._clf, Stree)
+        self.assertEqual(test._partition_column, computed._partition_column)

stree/tests/Splitter_test.py

@@ -0,0 +1,224 @@
+import os
+import unittest
+import random
+
+import numpy as np
+from sklearn.svm import SVC
+from sklearn.datasets import load_wine, load_iris
+from stree import Splitter
+
+
+class Splitter_test(unittest.TestCase):
+    def __init__(self, *args, **kwargs):
+        self._random_state = 1
+        super().__init__(*args, **kwargs)
+
+    @staticmethod
+    def build(
+        clf=SVC,
+        min_samples_split=0,
+        splitter_type="random",
+        criterion="gini",
+        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,
+            criterion=criterion,
+            criteria=criteria,
+            random_state=random_state,
+        )
+
+    @classmethod
+    def setUp(cls):
+        os.environ["TESTING"] = "1"
+
+    def test_init(self):
+        with self.assertRaises(ValueError):
+            self.build(criterion="duck")
+        with self.assertRaises(ValueError):
+            self.build(splitter_type="duck")
+        with self.assertRaises(ValueError):
+            self.build(criteria="duck")
+        with self.assertRaises(ValueError):
+            _ = Splitter(clf=None)
+        for splitter_type in ["best", "random"]:
+            for criterion in ["gini", "entropy"]:
+                for criteria in ["max_samples", "impurity"]:
+                    tcl = self.build(
+                        splitter_type=splitter_type,
+                        criterion=criterion,
+                        criteria=criteria,
+                    )
+                    self.assertEqual(splitter_type, tcl._splitter_type)
+                    self.assertEqual(criterion, tcl._criterion)
+                    self.assertEqual(criteria, tcl._criteria)
+
+    def test_gini(self):
+        expected_values = [
+            ([0, 1, 1, 1, 1, 1, 0, 0, 0, 1], 0.48),
+            ([0, 1, 1, 2, 2, 3, 4, 5, 3, 2, 1, 1], 0.7777777777777778),
+            ([0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 2, 2, 2], 0.520408163265306),
+            ([0, 0, 1, 1, 1, 1, 0, 0], 0.5),
+            ([0, 0, 1, 1, 2, 2, 3, 3], 0.75),
+            ([0, 0, 1, 1, 1, 1, 1, 1], 0.375),
+            ([0], 0),
+            ([1, 1, 1, 1], 0),
+        ]
+        for labels, expected in expected_values:
+            self.assertAlmostEqual(expected, Splitter._gini(labels))
+            tcl = self.build(criterion="gini")
+            self.assertAlmostEqual(expected, tcl.criterion_function(labels))
+
+    def test_entropy(self):
+        expected_values = [
+            ([0, 1, 1, 1, 1, 1, 0, 0, 0, 1], 0.9709505944546686),
+            ([0, 1, 1, 2, 2, 3, 4, 5, 3, 2, 1, 1], 0.9111886696810589),
+            ([0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 2, 2, 2], 0.8120406807940999),
+            ([0, 0, 1, 1, 1, 1, 0, 0], 1),
+            ([0, 0, 1, 1, 2, 2, 3, 3], 1),
+            ([0, 0, 1, 1, 1, 1, 1, 1], 0.8112781244591328),
+            ([1], 0),
+            ([0, 0, 0, 0], 0),
+        ]
+        for labels, expected in expected_values:
+            self.assertAlmostEqual(expected, Splitter._entropy(labels))
+            tcl = self.build(criterion="entropy")
+            self.assertAlmostEqual(expected, tcl.criterion_function(labels))
+
+    def test_information_gain(self):
+        expected_values = [
+            (
+                [0, 1, 1, 1, 1, 1],
+                [0, 0, 0, 1],
+                0.16333333333333333,
+                0.25642589168200297,
+            ),
+            (
+                [0, 1, 1, 2, 2, 3, 4, 5, 3, 2, 1, 1],
+                [5, 3, 2, 1, 1],
+                0.007381776239907684,
+                -0.03328610916207225,
+            ),
+            ([], [], 0.0, 0.0),
+            ([1], [], 0.0, 0.0),
+            ([], [1], 0.0, 0.0),
+            ([0, 0, 0, 0], [0, 0], 0.0, 0.0),
+            ([], [1, 1, 1, 2], 0.0, 0.0),
+            (None, [1, 2, 3], 0.0, 0.0),
+            ([1, 2, 3], None, 0.0, 0.0),
+        ]
+        for yu, yd, expected_gini, expected_entropy in expected_values:
+            yu = np.array(yu, dtype=np.int32) if yu is not None else None
+            yd = np.array(yd, dtype=np.int32) if yd is not None else None
+            if yu is not None and yd is not None:
+                complete = np.append(yu, yd)
+            elif yd is not None:
+                complete = yd
+            else:
+                complete = yu
+            tcl = self.build(criterion="gini")
+            computed = tcl.information_gain(complete, yu, yd)
+            self.assertAlmostEqual(expected_gini, computed)
+            tcl = self.build(criterion="entropy")
+            computed = tcl.information_gain(complete, yu, yd)
+            self.assertAlmostEqual(expected_entropy, computed)
+
+    def test_max_samples(self):
+        tcl = self.build(criteria="max_samples")
+        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 = data[:, 0]
+        y = [1, 2, 1, 0, 0, 0]
+        computed = tcl._max_samples(data, y)
+        self.assertEqual(0, computed)
+        computed_data = data[:, computed]
+        self.assertEqual((6,), computed_data.shape)
+        self.assertListEqual(expected.tolist(), computed_data.tolist())
+
+    def test_impurity(self):
+        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 = data[:, 2]
+        y = np.array([1, 2, 1, 0, 0, 0])
+        computed = tcl._impurity(data, y)
+        self.assertEqual(2, computed)
+        computed_data = data[:, computed]
+        self.assertEqual((6,), computed_data.shape)
+        self.assertListEqual(expected.tolist(), computed_data.tolist())
+
+    def test_generate_subspaces(self):
+        features = 250
+        for max_features in range(2, features):
+            num = len(Splitter._generate_spaces(features, max_features))
+            self.assertEqual(5, num)
+        self.assertEqual(3, len(Splitter._generate_spaces(3, 2)))
+        self.assertEqual(4, len(Splitter._generate_spaces(4, 3)))
+
+    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)
+        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 = [
+            [1, 4, 9, 12],  # best   entropy max_samples
+            [1, 3, 6, 10],  # best   entropy impurity
+            [6, 8, 10, 12],  # best   gini    max_samples
+            [7, 8, 10, 11],  # best   gini    impurity
+            [0, 3, 8, 12],  # random entropy max_samples
+            [0, 3, 9, 11],  # random entropy impurity
+            [0, 4, 7, 12],  # random gini    max_samples
+            [0, 2, 5, 6],  # random gini    impurity
+        ]
+        X, y = load_wine(return_X_y=True)
+        rn = 0
+        for splitter_type in ["best", "random"]:
+            for criterion in ["entropy", "gini"]:
+                for criteria in [
+                    "max_samples",
+                    "impurity",
+                ]:
+                    tcl = self.build(
+                        splitter_type=splitter_type,
+                        criterion=criterion,
+                        criteria=criteria,
+                    )
+                    expected = expected_values.pop(0)
+                    random.seed(rn)
+                    rn += 1
+                    dataset, computed = tcl.get_subspace(X, y, max_features=4)
+                    # print(
+                    #     "{},  # {:7s}{:8s}{:15s}".format(
+                    #         list(computed),
+                    #         splitter_type,
+                    #         criterion,
+                    #         criteria,
+                    #     )
+                    # )
+                    self.assertListEqual(expected, list(computed))
+                    self.assertListEqual(
+                        X[:, computed].tolist(), dataset.tolist()
+                    )

stree/tests/Stree_test.py

@@ -0,0 +1,444 @@
+import os
+import unittest
+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
+
+
+class Stree_test(unittest.TestCase):
+    def __init__(self, *args, **kwargs):
+        self._random_state = 1
+        self._kernels = ["linear", "rbf", "poly"]
+        super().__init__(*args, **kwargs)
+
+    @classmethod
+    def setUp(cls):
+        os.environ["TESTING"] = "1"
+
+    def _check_tree(self, node: Snode):
+        """Check recursively that the nodes that are not leaves have the
+        correct number of labels and its sons have the right number of elements
+        in their dataset
+
+        Arguments:
+            node {Snode} -- node to check
+        """
+        if node.is_leaf():
+            return
+        y_prediction = node._clf.predict(node._X)
+        y_down = node.get_down()._y
+        y_up = node.get_up()._y
+        # Is a correct partition in terms of cadinality?
+        # i.e. The partition algorithm didn't forget any sample
+        self.assertEqual(node._y.shape[0], y_down.shape[0] + y_up.shape[0])
+        unique_y, count_y = np.unique(node._y, return_counts=True)
+        _, count_d = np.unique(y_down, return_counts=True)
+        _, count_u = np.unique(y_up, return_counts=True)
+        #
+        for i in unique_y:
+            number_up = count_u[i]
+            try:
+                number_down = count_d[i]
+            except IndexError:
+                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[1], y_up.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"""
+        warnings.filterwarnings("ignore")
+        for kernel in self._kernels:
+            clf = Stree(kernel=kernel, random_state=self._random_state)
+            clf.fit(*load_dataset(self._random_state))
+            self._check_tree(clf.tree_)
+
+    def test_single_prediction(self):
+        X, y = load_dataset(self._random_state)
+        for kernel in self._kernels:
+            clf = Stree(kernel=kernel, random_state=self._random_state)
+            yp = clf.fit(X, y).predict((X[0, :].reshape(-1, X.shape[1])))
+            self.assertEqual(yp[0], y[0])
+
+    def test_multiple_prediction(self):
+        # First 27 elements the predictions are the same as the truth
+        num = 27
+        X, y = load_dataset(self._random_state)
+        for kernel in self._kernels:
+            clf = Stree(kernel=kernel, random_state=self._random_state)
+            yp = clf.fit(X, y).predict(X[:num, :])
+            self.assertListEqual(y[:num].tolist(), yp.tolist())
+
+    def test_single_vs_multiple_prediction(self):
+        """Check if predicting sample by sample gives the same result as
+        predicting all samples at once
+        """
+        X, y = load_dataset(self._random_state)
+        for kernel in self._kernels:
+            clf = Stree(kernel=kernel, random_state=self._random_state)
+            clf.fit(X, y)
+            # Compute prediction line by line
+            yp_line = np.array([], dtype=int)
+            for xp in X:
+                yp_line = np.append(
+                    yp_line, clf.predict(xp.reshape(-1, X.shape[1]))
+                )
+            # Compute prediction at once
+            yp_once = clf.predict(X)
+            self.assertListEqual(yp_line.tolist(), yp_once.tolist())
+
+    def test_iterator_and_str(self):
+        """Check preorder iterator"""
+        expected = [
+            "root feaures=(0, 1, 2) impurity=1.0000 counts=(array([0, 1]), arr"
+            "ay([750, 750]))",
+            "root - Down, <cgaf> - Leaf class=0 belief= 0.928297 impurity=0.37"
+            "22 counts=(array([0, 1]), array([725,  56]))",
+            "root - Up feaures=(0, 1, 2) impurity=0.2178 counts=(array([0, 1])"
+            ", array([ 25, 694]))",
+            "root - Up - Down feaures=(0, 1, 2) impurity=0.8454 counts=(array("
+            "[0, 1]), array([8, 3]))",
+            "root - Up - Down - Down, <pure> - Leaf class=0 belief= 1.000000 i"
+            "mpurity=0.0000 counts=(array([0]), array([7]))",
+            "root - Up - Down - Up, <cgaf> - Leaf class=1 belief= 0.750000 imp"
+            "urity=0.8113 counts=(array([0, 1]), array([1, 3]))",
+            "root - Up - Up, <cgaf> - Leaf class=1 belief= 0.975989 impurity=0"
+            ".1634 counts=(array([0, 1]), array([ 17, 691]))",
+        ]
+        computed = []
+        expected_string = ""
+        clf = Stree(kernel="linear", random_state=self._random_state)
+        clf.fit(*load_dataset(self._random_state))
+        for node in clf:
+            computed.append(str(node))
+            expected_string += str(node) + "\n"
+        self.assertListEqual(expected, computed)
+        self.assertEqual(expected_string, str(clf))
+
+    @staticmethod
+    def test_is_a_sklearn_classifier():
+        warnings.filterwarnings("ignore", category=ConvergenceWarning)
+        warnings.filterwarnings("ignore", category=RuntimeWarning)
+        from sklearn.utils.estimator_checks import check_estimator
+
+        check_estimator(Stree())
+
+    def test_exception_if_C_is_negative(self):
+        tclf = Stree(C=-1)
+        with self.assertRaises(ValueError):
+            tclf.fit(*load_dataset(self._random_state))
+
+    def test_exception_if_bogus_split_criteria(self):
+        tclf = Stree(split_criteria="duck")
+        with self.assertRaises(ValueError):
+            tclf.fit(*load_dataset(self._random_state))
+
+    def test_check_max_depth_is_positive_or_None(self):
+        tcl = Stree()
+        self.assertIsNone(tcl.max_depth)
+        tcl = Stree(max_depth=1)
+        self.assertGreaterEqual(1, tcl.max_depth)
+        with self.assertRaises(ValueError):
+            tcl = Stree(max_depth=-1)
+            tcl.fit(*load_dataset(self._random_state))
+
+    def test_check_max_depth(self):
+        depths = (3, 4)
+        for depth in depths:
+            tcl = Stree(random_state=self._random_state, max_depth=depth)
+            tcl.fit(*load_dataset(self._random_state))
+            self.assertEqual(depth, tcl.depth_)
+
+    def test_unfitted_tree_is_iterable(self):
+        tcl = Stree()
+        self.assertEqual(0, len(list(tcl)))
+
+    def test_min_samples_split(self):
+        dataset = [[1], [2], [3]], [1, 1, 0]
+        tcl_split = Stree(min_samples_split=3).fit(*dataset)
+        self.assertIsNotNone(tcl_split.tree_.get_down())
+        self.assertIsNotNone(tcl_split.tree_.get_up())
+        tcl_nosplit = Stree(min_samples_split=4).fit(*dataset)
+        self.assertIsNone(tcl_nosplit.tree_.get_down())
+        self.assertIsNone(tcl_nosplit.tree_.get_up())
+
+    def test_simple_muticlass_dataset(self):
+        for kernel in self._kernels:
+            clf = Stree(
+                kernel=kernel,
+                split_criteria="max_samples",
+                random_state=self._random_state,
+            )
+            px = [[1, 2], [5, 6], [9, 10]]
+            py = [0, 1, 2]
+            clf.fit(px, py)
+            self.assertEqual(1.0, clf.score(px, py))
+            self.assertListEqual(py, clf.predict(px).tolist())
+            self.assertListEqual(py, clf.classes_.tolist())
+
+    def test_muticlass_dataset(self):
+        datasets = {
+            "Synt": load_dataset(random_state=self._random_state, n_classes=3),
+            "Iris": load_wine(return_X_y=True),
+        }
+        outcomes = {
+            "Synt": {
+                "max_samples linear": 0.9606666666666667,
+                "max_samples rbf": 0.7133333333333334,
+                "max_samples poly": 0.49066666666666664,
+                "impurity linear": 0.9606666666666667,
+                "impurity rbf": 0.7133333333333334,
+                "impurity poly": 0.49066666666666664,
+            },
+            "Iris": {
+                "max_samples linear": 1.0,
+                "max_samples rbf": 0.6910112359550562,
+                "max_samples poly": 0.6966292134831461,
+                "impurity linear": 1,
+                "impurity rbf": 0.6910112359550562,
+                "impurity poly": 0.6966292134831461,
+            },
+        }
+
+        for name, dataset in datasets.items():
+            px, py = dataset
+            for criteria in ["max_samples", "impurity"]:
+                for kernel in self._kernels:
+                    clf = Stree(
+                        C=55,
+                        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):
+        n_features = 16
+        expected_values = [
+            ("auto", 4),
+            ("log2", 4),
+            ("sqrt", 4),
+            (0.5, 8),
+            (3, 3),
+            (None, 16),
+        ]
+        clf = Stree()
+        clf.n_features_ = n_features
+        for max_features, expected in expected_values:
+            clf.set_params(**dict(max_features=max_features))
+            computed = clf._initialize_max_features()
+            self.assertEqual(expected, computed)
+        # Check bogus max_features
+        values = ["duck", -0.1, 0.0]
+        for max_features in values:
+            clf.set_params(**dict(max_features=max_features))
+            with self.assertRaises(ValueError):
+                _ = clf._initialize_max_features()
+
+    def test_get_subspaces(self):
+        dataset = np.random.random((10, 16))
+        y = np.random.randint(0, 2, 10)
+        expected_values = [
+            ("auto", 4),
+            ("log2", 4),
+            ("sqrt", 4),
+            (0.5, 8),
+            (3, 3),
+            (None, 16),
+        ]
+        clf = Stree()
+        for max_features, expected in expected_values:
+            clf.set_params(**dict(max_features=max_features))
+            clf.fit(dataset, y)
+            computed, indices = clf.splitter_.get_subspace(
+                dataset, y, clf.max_features_
+            )
+            self.assertListEqual(
+                dataset[:, indices].tolist(), computed.tolist()
+            )
+            self.assertEqual(expected, len(indices))
+
+    def test_bogus_criterion(self):
+        clf = Stree(criterion="duck")
+        with self.assertRaises(ValueError):
+            clf.fit(*load_dataset())
+
+    def test_predict_feature_dimensions(self):
+        X = np.random.rand(10, 5)
+        y = np.random.randint(0, 2, 10)
+        clf = Stree()
+        clf.fit(X, y)
+        with self.assertRaises(ValueError):
+            clf.predict(X[:, :3])
+
+    # Tests of score
+
+    def test_score_binary(self):
+        X, y = load_dataset(self._random_state)
+        accuracies = [
+            0.9506666666666667,
+            0.9606666666666667,
+            0.9433333333333334,
+        ]
+        for kernel, accuracy_expected in zip(self._kernels, accuracies):
+            clf = Stree(
+                random_state=self._random_state,
+                kernel=kernel,
+            )
+            clf.fit(X, y)
+            accuracy_score = clf.score(X, y)
+            yp = clf.predict(X)
+            accuracy_computed = np.mean(yp == y)
+            self.assertEqual(accuracy_score, accuracy_computed)
+            self.assertAlmostEqual(accuracy_expected, accuracy_score)
+
+    def test_score_max_features(self):
+        X, y = load_dataset(self._random_state)
+        clf = Stree(random_state=self._random_state, max_features=2)
+        clf.fit(X, y)
+        self.assertAlmostEqual(0.9246666666666666, clf.score(X, y))
+
+    def test_bogus_splitter_parameter(self):
+        clf = Stree(splitter="duck")
+        with self.assertRaises(ValueError):
+            clf.fit(*load_dataset())
+
+    def test_weights_removing_class(self):
+        # This patch solves an stderr message from sklearn svm lib
+        # "WARNING: class label x specified in weight is not found"
+        X = np.array(
+            [
+                [0.1, 0.1],
+                [0.1, 0.2],
+                [0.2, 0.1],
+                [5, 6],
+                [8, 9],
+                [6, 7],
+                [0.2, 0.2],
+            ]
+        )
+        y = np.array([0, 0, 0, 1, 1, 1, 0])
+        epsilon = 1e-5
+        weights = [1, 1, 1, 0, 0, 0, 1]
+        weights = np.array(weights, dtype="float64")
+        weights_epsilon = [x + epsilon for x in weights]
+        weights_no_zero = np.array([1, 1, 1, 0, 0, 2, 1])
+        original = weights_no_zero.copy()
+        clf = Stree()
+        clf.fit(X, y)
+        node = clf.train(
+            X,
+            y,
+            weights,
+            1,
+            "test",
+        )
+        # if a class is lost with zero weights the patch adds epsilon
+        self.assertListEqual(weights.tolist(), weights_epsilon)
+        self.assertListEqual(node._sample_weight.tolist(), weights_epsilon)
+        # zero weights are ok when they don't erase a class
+        _ = clf.train(X, y, weights_no_zero, 1, "test")
+        self.assertListEqual(weights_no_zero.tolist(), original.tolist())
+
+    def test_multiclass_classifier_integrity(self):
+        """Checks if the multiclass operation is done right"""
+        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)
+        self.assertEqual(0.824, clf.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))
+
+    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
+        )
+        self.assertEqual(0.786, clf.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))
+
+    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))
+        X, y = load_wine(return_X_y=True)
+        self.assertEqual(0.9550561797752809, clf.fit(X, y).score(X, y))

stree/tests/Strees_test.py

@@ -1,357 +0,0 @@
-import os
-import unittest
-
-import numpy as np
-from sklearn.datasets import make_classification
-
-from stree import Stree, Snode
-
-
-class Stree_test(unittest.TestCase):
-
-    def __init__(self, *args, **kwargs):
-        os.environ['TESTING'] = '1'
-        self._random_state = 1
-        self._clf = Stree(random_state=self._random_state,
-                          use_predictions=False)
-        self._clf.fit(*self._get_Xy())
-        super().__init__(*args, **kwargs)
-
-    @classmethod
-    def tearDownClass(cls):
-        try:
-            os.environ.pop('TESTING')
-        except KeyError:
-            pass
-
-    def _get_Xy(self):
-        X, y = make_classification(n_samples=1500, n_features=3,
-                                   n_informative=3, n_redundant=0,
-                                   n_repeated=0, n_classes=2,
-                                   n_clusters_per_class=2, class_sep=1.5,
-                                   flip_y=0, weights=[0.5, 0.5],
-                                   random_state=self._random_state)
-        return X, y
-
-    def _check_tree(self, node: Snode):
-        """Check recursively that the nodes that are not leaves have the
-        correct number of labels and its sons have the right number of elements
-        in their dataset
-
-        Arguments:
-            node {Snode} -- node to check
-        """
-        if node.is_leaf():
-            return
-        y_prediction = node._clf.predict(node._X)
-        y_down = node.get_down()._y
-        y_up = node.get_up()._y
-        # Is a correct partition in terms of cadinality?
-        # i.e. The partition algorithm didn't forget any sample
-        self.assertEqual(node._y.shape[0], y_down.shape[0] + y_up.shape[0])
-        unique_y, count_y = np.unique(node._y, return_counts=True)
-        _, count_d = np.unique(y_down, return_counts=True)
-        _, count_u = np.unique(y_up, return_counts=True)
-        #
-        for i in unique_y:
-            try:
-                number_down = count_d[i]
-            except IndexError:
-                number_down = 0
-            try:
-                number_up = count_u[i]
-            except IndexError:
-                number_up = 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_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
-        """
-        self._check_tree(self._clf.tree_)
-
-    def _get_file_data(self, file_name: str) -> tuple:
-        """Return X, y from data, y is the last column in array
-
-        Arguments:
-            file_name {str} -- the file name
-
-        Returns:
-            tuple -- tuple with samples, categories
-        """
-        data = np.genfromtxt(file_name, delimiter=',')
-        data = np.array(data)
-        column_y = data.shape[1] - 1
-        fy = data[:, column_y]
-        fx = np.delete(data, column_y, axis=1)
-        return fx, fy
-
-    def _find_out(self, px: np.array, x_original: np.array,
-                  y_original) -> list:
-        """Find the original values of y for a given array of samples
-
-        Arguments:
-            px {np.array} -- array of samples to search for
-            x_original {np.array} -- original dataset
-            y_original {[type]} -- original classes
-
-        Returns:
-            np.array -- classes of the given samples
-        """
-        res = []
-        for needle in px:
-            for row in range(x_original.shape[0]):
-                if all(x_original[row, :] == needle):
-                    res.append(y_original[row])
-        return res
-
-    def test_single_prediction(self):
-        X, y = self._get_Xy()
-        yp = self._clf.predict((X[0, :].reshape(-1, X.shape[1])))
-        self.assertEqual(yp[0], y[0])
-
-    def test_multiple_prediction(self):
-        # First 27 elements the predictions are the same as the truth
-        num = 27
-        X, y = self._get_Xy()
-        yp = self._clf.predict(X[:num, :])
-        self.assertListEqual(y[:num].tolist(), yp.tolist())
-
-    def test_score(self):
-        X, y = self._get_Xy()
-        accuracy_score = self._clf.score(X, y)
-        yp = self._clf.predict(X)
-        accuracy_computed = np.mean(yp == y)
-        self.assertEqual(accuracy_score, accuracy_computed)
-        self.assertGreater(accuracy_score, 0.9)
-
-    def test_single_predict_proba(self):
-        """Check that element 28 has a prediction different that the current
-        label
-        """
-        # Element 28 has a different prediction than the truth
-        decimals = 5
-        prob = 0.29026400766
-        X, y = self._get_Xy()
-        yp = self._clf.predict_proba(X[28, :].reshape(-1, X.shape[1]))
-        self.assertEqual(np.round(1 - prob, decimals),
-                         np.round(yp[0:, 0], decimals))
-        self.assertEqual(1, y[28])
-
-        self.assertAlmostEqual(
-            round(prob, decimals),
-            round(yp[0, 1], decimals),
-            decimals
-        )
-
-    def test_multiple_predict_proba(self):
-        # First 27 elements the predictions are the same as the truth
-        num = 27
-        decimals = 5
-        X, y = self._get_Xy()
-        yp = self._clf.predict_proba(X[:num, :])
-        self.assertListEqual(
-            y[:num].tolist(), np.argmax(yp[:num], axis=1).tolist())
-        expected_proba = [0.88395641, 0.36746962, 0.84158767, 0.34106833,
-                          0.14269291, 0.85193236,
-                          0.29876058, 0.7282164, 0.85958616, 0.89517877,
-                          0.99745224, 0.18860349,
-                          0.30756427, 0.8318412, 0.18981198, 0.15564624,
-                          0.25740655, 0.22923355,
-                          0.87365959, 0.49928689, 0.95574351, 0.28761257,
-                          0.28906333, 0.32643692,
-                          0.29788483, 0.01657364, 0.81149083]
-        expected = np.round(expected_proba, decimals=decimals).tolist()
-        computed = np.round(yp[:, 1], decimals=decimals).tolist()
-        for i in range(len(expected)):
-            self.assertAlmostEqual(expected[i], computed[i], decimals)
-
-    def build_models(self):
-        """Build and train two models, model_clf will use the sklearn
-        classifier to compute predictions and split data. model_computed will
-        use vector of coefficients to compute both predictions and splitted
-        data
-        """
-        model_clf = Stree(random_state=self._random_state,
-                          use_predictions=True)
-        model_computed = Stree(random_state=self._random_state,
-                               use_predictions=False)
-        X, y = self._get_Xy()
-        model_clf.fit(X, y)
-        model_computed.fit(X, y)
-        return model_clf, model_computed, X, y
-
-    def test_use_model_predict(self):
-        """Check that we get the same results wether we use the estimator in
-        nodes to compute labels or we use the hyperplane and the position of
-        samples wrt to it
-        """
-        use_clf, use_math, X, _ = self.build_models()
-        self.assertListEqual(
-            use_clf.predict(X).tolist(),
-            use_math.predict(X).tolist()
-        )
-
-    def test_use_model_score(self):
-        use_clf, use_math, X, y = self.build_models()
-        b = use_math.score(X, y)
-        self.assertEqual(
-            use_clf.score(X, y),
-            b
-        )
-        self.assertGreater(b, .95)
-
-    def test_use_model_predict_proba(self):
-        use_clf, use_math, X, _ = self.build_models()
-        self.assertListEqual(
-            use_clf.predict_proba(X).tolist(),
-            use_math.predict_proba(X).tolist()
-        )
-
-    def test_single_vs_multiple_prediction(self):
-        """Check if predicting sample by sample gives the same result as
-        predicting all samples at once
-        """
-        X, _ = self._get_Xy()
-        # Compute prediction line by line
-        yp_line = np.array([], dtype=int)
-        for xp in X:
-            yp_line = np.append(yp_line, self._clf.predict(
-                xp.reshape(-1, X.shape[1])))
-        # Compute prediction at once
-        yp_once = self._clf.predict(X)
-        #
-        self.assertListEqual(yp_line.tolist(), yp_once.tolist())
-
-    def test_iterator(self):
-        """Check preorder iterator
-        """
-        expected = [
-            'root',
-            'root - Down',
-            'root - Down - Down, <cgaf> - Leaf class=1 belief= 0.975989 counts'
-            '=(array([0, 1]), array([ 17, 691]))',
-            'root - Down - Up',
-            'root - Down - Up - Down, <cgaf> - Leaf class=1 belief= 0.750000 '
-            'counts=(array([0, 1]), array([1, 3]))',
-            'root - Down - Up - Up, <pure> - Leaf class=0 belief= 1.000000 '
-            'counts=(array([0]), array([7]))',
-            'root - Up, <cgaf> - Leaf class=0 belief= 0.928297 counts=(array('
-            '[0, 1]), array([725,  56]))',
-        ]
-        computed = []
-        for node in self._clf:
-            computed.append(str(node))
-        self.assertListEqual(expected, computed)
-
-    def test_is_a_sklearn_classifier(self):
-        import warnings
-        from sklearn.exceptions import ConvergenceWarning
-        warnings.filterwarnings('ignore', category=ConvergenceWarning)
-        warnings.filterwarnings('ignore', category=RuntimeWarning)
-        from sklearn.utils.estimator_checks import check_estimator
-        check_estimator(Stree())
-
-    def test_exception_if_C_is_negative(self):
-        tclf = Stree(C=-1)
-        with self.assertRaises(ValueError):
-            tclf.fit(*self._get_Xy())
-
-    def test_check_max_depth_is_positive_or_None(self):
-        tcl = Stree()
-        self.assertIsNone(tcl.max_depth)
-        tcl = Stree(max_depth=1)
-        self.assertGreaterEqual(1, tcl.max_depth)
-        with self.assertRaises(ValueError):
-            tcl = Stree(max_depth=-1)
-            tcl.fit(*self._get_Xy())
-
-    def test_check_max_depth(self):
-        depth = 3
-        tcl = Stree(random_state=self._random_state, max_depth=depth)
-        tcl.fit(*self._get_Xy())
-        self.assertEqual(depth, tcl.depth_)
-
-    def test_unfitted_tree_is_iterable(self):
-        tcl = Stree()
-        self.assertEqual(0, len(list(tcl)))
-
-
-class Snode_test(unittest.TestCase):
-
-    def __init__(self, *args, **kwargs):
-        os.environ['TESTING'] = '1'
-        self._random_state = 1
-        self._clf = Stree(random_state=self._random_state,
-                          use_predictions=True)
-        self._clf.fit(*self._get_Xy())
-        super().__init__(*args, **kwargs)
-
-    @classmethod
-    def tearDownClass(cls):
-        """[summary]
-        """
-        try:
-            os.environ.pop('TESTING')
-        except KeyError:
-            pass
-
-    def _get_Xy(self):
-        X, y = make_classification(n_samples=1500, n_features=3,
-                                   n_informative=3, n_redundant=0, n_classes=2,
-                                   n_repeated=0, n_clusters_per_class=2,
-                                   class_sep=1.5, flip_y=0, weights=[0.5, 0.5],
-                                   random_state=self._random_state)
-        return X, y
-
-    def test_attributes_in_leaves(self):
-        """Check if the attributes in leaves have correct values so they form a
-        predictor
-        """
-
-        def check_leave(node: Snode):
-            if not node.is_leaf():
-                check_leave(node.get_down())
-                check_leave(node.get_up())
-                return
-            # Check Belief in leave
-            classes, card = np.unique(node._y, return_counts=True)
-            max_card = max(card)
-            min_card = min(card)
-            if len(classes) > 1:
-                try:
-                    belief = max_card / (max_card + min_card)
-                except ZeroDivisionError:
-                    belief = 0.
-            else:
-                belief = 1
-            self.assertEqual(belief, node._belief)
-            # Check Class
-            class_computed = classes[card == max_card]
-            self.assertEqual(class_computed, node._class)
-
-        check_leave(self._clf.tree_)
-
-    def test_nodes_coefs(self):
-        """Check if the nodes of the tree have the right attributes filled
-        """
-
-        def run_tree(node: Snode):
-            if node._belief < 1:
-                # only exclude pure leaves
-                self.assertIsNotNone(node._clf)
-                self.assertIsNotNone(node._clf.coef_)
-                self.assertIsNotNone(node._vector)
-                self.assertIsNotNone(node._interceptor)
-            if node.is_leaf():
-                return
-            run_tree(node.get_down())
-            run_tree(node.get_up())
-
-        run_tree(self._clf.tree_)

stree/tests/__init__.py

@@ -1 +1,5 @@
-from .Strees_test import Stree_test, Snode_test
+from .Stree_test import Stree_test
+from .Snode_test import Snode_test
+from .Splitter_test import Splitter_test
+
+__all__ = ["Stree_test", "Snode_test", "Splitter_test"]

stree/tests/utils.py

@@ -0,0 +1,17 @@
+from sklearn.datasets import make_classification
+
+
+def load_dataset(random_state=0, n_classes=2, n_features=3, n_samples=1500):
+    X, y = make_classification(
+        n_samples=n_samples,
+        n_features=n_features,
+        n_informative=3,
+        n_redundant=0,
+        n_repeated=0,
+        n_classes=n_classes,
+        n_clusters_per_class=2,
+        class_sep=1.5,
+        flip_y=0,
+        random_state=random_state,
+    )
+    return X, y