Implement hyperparam. context based normalization

Fix compute number of nodes
Add another nodes, leaves test
2025-08-17 16:36:01 +00:00 · 2021-04-15 02:13:30 +02:00 · 2021-04-13 22:31:05 +02:00 · 2021-04-09 10:56:54 +02:00 · 2021-04-08 08:27:31 +02:00 · 2021-04-07 01:02:30 +02:00
23 changed files with 2087 additions and 1840 deletions
--- a/.coveragerc
+++ b/.coveragerc
@@ -10,5 +10,4 @@ exclude_lines =
    if __name__ == .__main__.:
 ignore_errors = True
 omit =
-    stree/tests/*
    stree/__init__.py
--- a/.github/workflows/main.yml
+++ b/.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
--- a/.gitignore
+++ b/.gitignore
@@ -130,4 +130,7 @@ dmypy.json

 .idea
 .vscode
-.pre-commit-config.yaml
+.pre-commit-config.yaml
+
+**.csv
+.virtual_documents
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
-[![Codeship Status for Doctorado-ML/STree](https://app.codeship.com/projects/8b2bd350-8a1b-0138-5f2c-3ad36f3eb318/status?branch=master)](https://app.codeship.com/projects/399170)
+![CI](https://github.com/Doctorado-ML/STree/workflows/CI/badge.svg)
 [![codecov](https://codecov.io/gh/doctorado-ml/stree/branch/master/graph/badge.svg)](https://codecov.io/gh/doctorado-ml/stree)
-[![Codacy Badge](https://app.codacy.com/project/badge/Grade/35fa3dfd53a24a339344b33d9f9f2f3d)](https://www.codacy.com/gh/Doctorado-ML/STree?utm_source=github.com&amp;utm_medium=referral&amp;utm_content=Doctorado-ML/STree&amp;utm_campaign=Badge_Grade)
+[![Codacy Badge](https://app.codacy.com/project/badge/Grade/35fa3dfd53a24a339344b33d9f9f2f3d)](https://www.codacy.com/gh/Doctorado-ML/STree?utm_source=github.com&utm_medium=referral&utm_content=Doctorado-ML/STree&utm_campaign=Badge_Grade)

 # Stree

@@ -18,23 +18,43 @@ pip install git+https://github.com/doctorado-ml/stree

 ### Jupyter notebooks

-* [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/Doctorado-ML/STree/master?urlpath=lab/tree/notebooks/benchmark.ipynb) Benchmark
+- [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/Doctorado-ML/STree/master?urlpath=lab/tree/notebooks/benchmark.ipynb) Benchmark

-* [![Test](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/benchmark.ipynb) Benchmark
+- [![benchmark](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/benchmark.ipynb) Benchmark

-* [![Test2](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/features.ipynb) Test features
+- [![features](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/features.ipynb) Some features

-* [![Adaboost](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/adaboost.ipynb) Adaboost
+- [![Gridsearch](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/gridsearch.ipynb) Gridsearch

-* [![Gridsearch](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/gridsearch.ipynb) Gridsearch
+- [![Ensemble](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/ensemble.ipynb) Ensembles

-* [![Test Graphics](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/test_graphs.ipynb) Test Graphics
+## Hyperparameters

-### Command line
+|     | **Hyperparameter** | **Type/Values**                                        | **Default** | **Meaning**                                                                                                                                                                                                                                                                                                                                                                                                                                          |
+| --- | ------------------ | ------------------------------------------------------ | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| \*  | C                  | \<float\>                                              | 1.0         | Regularization parameter. The strength of the regularization is inversely proportional to C. Must be strictly positive.                                                                                                                                                                                                                                                                                                                              |
+| \*  | kernel             | {"linear", "poly", "rbf"}                              | linear      | Specifies the kernel type to be used in the algorithm. It must be one of ‘linear’, ‘poly’ or ‘rbf’.                                                                                                                                                                                                                                                                                                                                                  |
+| \*  | max_iter           | \<int\>                                                | 1e5         | Hard limit on iterations within solver, or -1 for no limit.                                                                                                                                                                                                                                                                                                                                                                                          |
+| \*  | random_state       | \<int\>                                                | None        | Controls the pseudo random number generation for shuffling the data for probability estimates. Ignored when probability is False.<br>Pass an int for reproducible output across multiple function calls                                                                                                                                                                                                                                              |
+|     | max_depth          | \<int\>                                                | None        | Specifies the maximum depth of the tree                                                                                                                                                                                                                                                                                                                                                                                                              |
+| \*  | tol                | \<float\>                                              | 1e-4        | Tolerance for stopping criterion.                                                                                                                                                                                                                                                                                                                                                                                                                    |
+| \*  | degree             | \<int\>                                                | 3           | Degree of the polynomial kernel function (‘poly’). Ignored by all other kernels.                                                                                                                                                                                                                                                                                                                                                                     |
+| \*  | gamma              | {"scale", "auto"} or \<float\>                         | scale       | Kernel coefficient for ‘rbf’ and ‘poly’.<br>if gamma='scale' (default) is passed then it uses 1 / (n_features \* X.var()) as value of gamma,<br>if ‘auto’, uses 1 / n_features.                                                                                                                                                                                                                                                                      |
+|     | split_criteria     | {"impurity", "max_samples"}                            | impurity    | Decides (just in case of a multi class classification) which column (class) use to split the dataset in a node\*\*                                                                                                                                                                                                                                                                                                                                   |
+|     | criterion          | {“gini”, “entropy”}                                    | entropy     | The function to measure the quality of a split (only used if max_features != num_features). <br>Supported criteria are “gini” for the Gini impurity and “entropy” for the information gain.                                                                                                                                                                                                                                                          |
+|     | min_samples_split  | \<int\>                                                | 0           | The minimum number of samples required to split an internal node. 0 (default) for any                                                                                                                                                                                                                                                                                                                                                                |
+|     | max_features       | \<int\>, \<float\> <br><br>or {“auto”, “sqrt”, “log2”} | None        | The number of features to consider when looking for the split:<br>If int, then consider max_features features at each split.<br>If float, then max_features is a fraction and int(max_features \* n_features) features are considered at each split.<br>If “auto”, then max_features=sqrt(n_features).<br>If “sqrt”, then max_features=sqrt(n_features).<br>If “log2”, then max_features=log2(n_features).<br>If None, then max_features=n_features. |
+|     | splitter           | {"best", "random"}                                     | random      | The strategy used to choose the feature set at each node (only used if max_features != num_features). <br>Supported strategies are “best” to choose the best feature set and “random” to choose a random combination. <br>The algorithm generates 5 candidates at most to choose from in both strategies.                                                                                                                                            |

-```bash
-python main.py
-```
+\* Hyperparameter used by the support vector classifier of every node
+
+\*\* **Splitting in a STree node**
+
+The decision function is applied to the dataset and distances from samples to hyperplanes are computed in a matrix. This matrix has as many columns as classes the samples belongs to (if more than two, i.e. multiclass classification) or 1 column if it's a binary class dataset. In binary classification only one hyperplane is computed and therefore only one column is needed to store the distances of the samples to it. If three or more classes are present in the dataset we need as many hyperplanes as classes are there, and therefore one column per hyperplane is needed.
+
+In case of multiclass classification we have to decide which column take into account to make the split, that depends on hyperparameter _split_criteria_, if "impurity" is chosen then STree computes information gain of every split candidate using each column and chooses the one that maximize the information gain, otherwise STree choses the column with more samples with a predicted class (the column with more positive numbers in it).
+
+Once we have the column to take into account for the split, the algorithm splits samples with positive distances to hyperplane from the rest.

 ## Tests

--- a/main.py
+++ b/main.py
@@ -1,74 +1,26 @@
 import time
 from sklearn.model_selection import train_test_split
+from sklearn.datasets import load_iris
 from stree import Stree

 random_state = 1

+X, y = load_iris(return_X_y=True)

-def load_creditcard(n_examples=0):
-    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
-# data = load_creditcard(5000)  # Take the first 5000 samples
-data = load_creditcard()  # Take all the samples
-
-Xtrain = data[0]
-Xtest = data[1]
-ytrain = data[2]
-ytest = data[3]
+Xtrain, Xtest, ytrain, ytest = train_test_split(
+    X, y, test_size=0.3, random_state=random_state
+)

 now = time.time()
+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")
--- a/notebooks/benchmark.ipynb
+++ b/notebooks/benchmark.ipynb
--- a/notebooks/ensemble.ipynb
+++ b/notebooks/ensemble.ipynb
@@ -4,7 +4,7 @@
   "cell_type": "markdown",
   "metadata": {},
   "source": [
-    "# Test AdaBoost with different configurations"
+    "# Test Stree with AdaBoost and Bagging with different configurations"
   ]
  },
  {
@@ -17,38 +17,43 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#\n",
    "# Google Colab setup\n",
    "#\n",
-    "#!pip install git+https://github.com/doctorado-ml/stree"
+    "#!pip install git+https://github.com/doctorado-ml/stree\n",
+    "!pip install pandas"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import time\n",
-    "from sklearn.ensemble import AdaBoostClassifier\n",
-    "from sklearn.tree import DecisionTreeClassifier\n",
-    "from sklearn.svm import LinearSVC, SVC\n",
-    "from sklearn.model_selection import GridSearchCV, train_test_split\n",
-    "from sklearn.datasets import load_iris\n",
-    "from stree import Stree"
+    "import os\n",
+    "import random\n",
+    "import warnings\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from sklearn.ensemble import AdaBoostClassifier, BaggingClassifier\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.exceptions import ConvergenceWarning\n",
+    "from stree import Stree\n",
+    "\n",
+    "warnings.filterwarnings(\"ignore\", category=ConvergenceWarning)"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
-    "import os\n",
    "if not os.path.isfile('data/creditcard.csv'):\n",
    "    !wget --no-check-certificate --content-disposition http://nube.jccm.es/index.php/s/Zs7SYtZQJ3RQ2H2/download\n",
    "    !tar xzf creditcard.tgz"
@@ -56,22 +61,15 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "Fraud: 0.173% 492\nValid: 99.827% 284315\nX.shape (100492, 28)  y.shape (100492,)\nFraud: 0.659% 662\nValid: 99.341% 99830\n"
-    }
-   ],
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
   "source": [
    "random_state=1\n",
    "\n",
    "def load_creditcard(n_examples=0):\n",
-    "    import pandas as pd\n",
-    "    import numpy as np\n",
-    "    import random\n",
    "    df = pd.read_csv('data/creditcard.csv')\n",
    "    print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n",
    "    print(\"Valid: {0:.3f}% {1}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))\n",
@@ -117,23 +115,19 @@
   "cell_type": "markdown",
   "metadata": {},
   "source": [
-    "## STree alone on the whole dataset and linear kernel"
+    "## STree alone with 100.000 samples and linear kernel"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "Score Train:  0.9985499829409757\nScore Test:  0.998407854584052\nTook 39.45 seconds\n"
-    }
-   ],
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
   "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",
@@ -144,12 +138,12 @@
   "cell_type": "markdown",
   "metadata": {},
   "source": [
-    "## Different kernels with different configuations"
+    "## Adaboost"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
@@ -160,19 +154,15 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "Kernel: linear\tTime: 87.00 seconds\tScore Train: 0.9982372\tScore Test: 0.9981425\nKernel: rbf\tTime: 60.60 seconds\tScore Train: 0.9934181\tScore Test: 0.9933992\nKernel: poly\tTime: 88.08 seconds\tScore Train: 0.9937450\tScore Test: 0.9938968\n"
-    }
-   ],
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
   "source": [
    "for kernel in ['linear', 'rbf', 'poly']:\n",
    "    now = time.time()\n",
-    "    clf = AdaBoostClassifier(Stree(C=7, kernel=kernel, max_depth=max_depth, random_state=random_state), n_estimators=n_estimators, random_state=random_state)\n",
+    "    clf = AdaBoostClassifier(base_estimator=Stree(C=C, kernel=kernel, max_depth=max_depth, random_state=random_state, max_iter=1e3), algorithm=\"SAMME\", n_estimators=n_estimators, random_state=random_state)\n",
    "    clf.fit(Xtrain, ytrain)\n",
    "    score_train = clf.score(Xtrain, ytrain)\n",
    "    score_test = clf.score(Xtest, ytest)\n",
@@ -183,24 +173,31 @@
   "cell_type": "markdown",
   "metadata": {},
   "source": [
-    "## Test algorithm SAMME in AdaBoost to check speed/accuracy"
+    "## Bagging"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "Kernel: linear\tTime: 58.75 seconds\tScore Train: 0.9980524\tScore Test: 0.9978771\nKernel: rbf\tTime: 12.49 seconds\tScore Train: 0.9934181\tScore Test: 0.9933992\nKernel: poly\tTime: 97.85 seconds\tScore Train: 0.9972137\tScore Test: 0.9971806\n"
-    }
-   ],
+   "outputs": [],
+   "source": [
+    "n_estimators = 10\n",
+    "C = 7\n",
+    "max_depth = 3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
   "source": [
    "for kernel in ['linear', 'rbf', 'poly']:\n",
    "    now = time.time()\n",
-    "    clf = AdaBoostClassifier(Stree(C=7, kernel=kernel, max_depth=max_depth, random_state=random_state), n_estimators=n_estimators, random_state=random_state, algorithm=\"SAMME\")\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",
@@ -209,6 +206,11 @@
  }
 ],
 "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
@@ -219,14 +221,9 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.7.6-final"
-  },
-  "orig_nbformat": 2,
-  "kernelspec": {
-   "name": "python37664bitgeneralvenvfbd0a23e74cf4e778460f5ffc6761f39",
-   "display_name": "Python 3.7.6 64-bit ('general': venv)"
+   "version": "3.8.2-final"
  }
 },
 "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }
--- a/notebooks/features.ipynb
+++ b/notebooks/features.ipynb
@@ -4,7 +4,7 @@
   "cell_type": "markdown",
   "metadata": {},
   "source": [
-    "# Test smple_weight, kernels, C, sklearn estimator"
+    "# Test sample_weight, kernels, C, sklearn estimator"
   ]
  },
  {
@@ -17,22 +17,27 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#\n",
    "# Google Colab setup\n",
    "#\n",
-    "#!pip install git+https://github.com/doctorado-ml/stree"
+    "#!pip install git+https://github.com/doctorado-ml/stree\n",
+    "!pip install pandas"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
+    "import time\n",
+    "import random\n",
+    "import warnings\n",
+    "import os\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.svm import SVC\n",
@@ -40,17 +45,20 @@
    "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 sklearn.utils.class_weight import compute_sample_weight\n",
+    "from sklearn.exceptions import ConvergenceWarning\n",
    "from stree import Stree\n",
-    "import time"
+    "warnings.filterwarnings(\"ignore\", category=ConvergenceWarning)"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
+   "execution_count": null,
+   "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"
@@ -58,22 +66,15 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "Fraud: 0.173% 492\nValid: 99.827% 284315\nX.shape (1492, 28)  y.shape (1492,)\nFraud: 33.110% 494\nValid: 66.890% 998\n"
-    }
-   ],
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
   "source": [
    "random_state=1\n",
    "\n",
    "def load_creditcard(n_examples=0):\n",
-    "    import pandas as pd\n",
-    "    import numpy as np\n",
-    "    import random\n",
    "    df = pd.read_csv('data/creditcard.csv')\n",
    "    print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n",
    "    print(\"Valid: {0:.3f}% {1}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))\n",
@@ -94,22 +95,20 @@
    "    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",
+    "    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 + 5000 of the others\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 all the 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",
-    "# Set weights inverse to its count class in dataset\n",
-    "weights = np.ones(Xtrain.shape[0],) * 1.00244\n",
-    "weights[ytrain==1] = 1.99755\n",
-    "weights_test = np.ones(Xtest.shape[0],) * 1.00244\n",
-    "weights_test[ytest==1] = 1.99755 "
+    "weights = compute_sample_weight(\"balanced\", ytrain)\n",
+    "weights_test = compute_sample_weight(\"balanced\", ytest)\n",
+    "print(weights[:4], weights_test[:4])"
   ]
  },
  {
@@ -123,21 +122,17 @@
   "cell_type": "markdown",
   "metadata": {},
   "source": [
-    "## Test smple_weights\n",
+    "## 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": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "Accuracy of Train without weights 0.9789272030651341\nAccuracy of Train with    weights 0.9952107279693486\nAccuracy of Tests without weights 0.9598214285714286\nAccuracy of Tests with    weights 0.9508928571428571\n"
-    }
-   ],
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
   "source": [
    "C = 23\n",
    "print(\"Accuracy of Train without weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain).score(Xtrain, ytrain))\n",
@@ -156,15 +151,11 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "Time: 0.27s\tKernel: linear\tAccuracy_train: 0.9683908045977011\tAccuracy_test: 0.953125\nTime: 0.09s\tKernel: rbf\tAccuracy_train: 0.9875478927203065\tAccuracy_test: 0.9598214285714286\nTime: 0.06s\tKernel: poly\tAccuracy_train: 0.9885057471264368\tAccuracy_test: 0.9464285714285714\n"
-    }
-   ],
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
   "source": [
    "random_state=1\n",
    "for kernel in ['linear', 'rbf', 'poly']:\n",
@@ -185,19 +176,11 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
   "metadata": {
-    "tags": [
-     "outputPrepend"
-    ]
+    "tags": []
   },
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "************** C=0.001 ****************************\nClassifier's accuracy (train): 0.9531\nClassifier's accuracy (test) : 0.9621\nroot\nroot - Down, <cgaf> - Leaf class=1 belief= 0.983713 counts=(array([0, 1]), array([  5, 302]))\nroot - Up, <cgaf> - Leaf class=0 belief= 0.940299 counts=(array([0, 1]), array([693,  44]))\n\n**************************************************\n************** C=0.01 ****************************\nClassifier's accuracy (train): 0.9569\nClassifier's accuracy (test) : 0.9621\nroot\nroot - Down, <cgaf> - Leaf class=1 belief= 0.990228 counts=(array([0, 1]), array([  3, 304]))\nroot - Up, <cgaf> - Leaf class=0 belief= 0.943012 counts=(array([0, 1]), array([695,  42]))\n\n**************************************************\n************** C=1 ****************************\nClassifier's accuracy (train): 0.9655\nClassifier's accuracy (test) : 0.9643\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([310]))\nroot - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([5]))\nroot - Up, <cgaf> - Leaf class=0 belief= 0.950617 counts=(array([0, 1]), array([693,  36]))\n\n**************************************************\n************** C=5 ****************************\nClassifier's accuracy (train): 0.9684\nClassifier's accuracy (test) : 0.9598\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([311]))\nroot - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([8]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up\nroot - Up - Up - Down, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down\nroot - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief= 0.954039 counts=(array([0, 1]), array([685,  33]))\n\n**************************************************\n************** C=17 ****************************\nClassifier's accuracy (train): 0.9751\nClassifier's accuracy (test) : 0.9464\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([304]))\nroot - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([8]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([4]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([3]))\nroot - Up - Up\nroot - Up - Up - Down\nroot - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([4]))\nroot - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down\nroot - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([3]))\nroot - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([3]))\nroot - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([3]))\nroot - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([2]))\nroot - Up - Up - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief= 0.963225 counts=(array([0, 1]), array([681,  26]))\n\n**************************************************\n0.6869 secs\n"
-    }
-   ],
+   "outputs": [],
   "source": [
    "t = time.time()\n",
    "for C in (.001, .01, 1, 5, 17):\n",
@@ -216,20 +199,16 @@
   "metadata": {},
   "source": [
    "## Test iterator\n",
-    "Check different weays of using the iterator"
+    "Check different ways of using the iterator"
   ]
  },
  {
   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "root\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([304]))\nroot - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([8]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([4]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([3]))\nroot - Up - Up\nroot - Up - Up - Down\nroot - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([4]))\nroot - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down\nroot - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([3]))\nroot - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([3]))\nroot - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([3]))\nroot - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([2]))\nroot - Up - Up - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief= 0.963225 counts=(array([0, 1]), array([681,  26]))\n"
-    }
-   ],
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
   "source": [
    "#check iterator\n",
    "for i in list(clf):\n",
@@ -238,15 +217,11 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "root\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([304]))\nroot - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([8]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([4]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([3]))\nroot - Up - Up\nroot - Up - Up - Down\nroot - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([4]))\nroot - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down\nroot - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([3]))\nroot - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([3]))\nroot - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([3]))\nroot - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Down, <pure> - Leaf class=1 belief= 1.000000 counts=(array([1]), array([2]))\nroot - Up - Up - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief= 0.963225 counts=(array([0, 1]), array([681,  26]))\n"
-    }
-   ],
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
   "source": [
    "#check iterator again\n",
    "for i in clf:\n",
@@ -262,15 +237,11 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "1 functools.partial(<function check_no_attributes_set_in_init at 0x1254f13b0>, 'Stree')\n2 functools.partial(<function check_estimators_dtypes at 0x1254e84d0>, 'Stree')\n3 functools.partial(<function check_fit_score_takes_y at 0x1254e83b0>, 'Stree')\n4 functools.partial(<function check_sample_weights_pandas_series at 0x1254e0cb0>, 'Stree')\n5 functools.partial(<function check_sample_weights_not_an_array at 0x1254e0dd0>, 'Stree')\n6 functools.partial(<function check_sample_weights_list at 0x1254e0ef0>, 'Stree')\n7 functools.partial(<function check_sample_weights_shape at 0x1254e2050>, 'Stree')\n8 functools.partial(<function check_sample_weights_invariance at 0x1254e2170>, 'Stree')\n9 functools.partial(<function check_estimators_fit_returns_self at 0x1254eb4d0>, 'Stree')\n10 functools.partial(<function check_estimators_fit_returns_self at 0x1254eb4d0>, 'Stree', readonly_memmap=True)\n11 functools.partial(<function check_complex_data at 0x1254e2320>, 'Stree')\n12 functools.partial(<function check_dtype_object at 0x1254e2290>, 'Stree')\n13 functools.partial(<function check_estimators_empty_data_messages at 0x1254e85f0>, 'Stree')\n14 functools.partial(<function check_pipeline_consistency at 0x1254e8290>, 'Stree')\n15 functools.partial(<function check_estimators_nan_inf at 0x1254e8710>, 'Stree')\n16 functools.partial(<function check_estimators_overwrite_params at 0x1254f1290>, 'Stree')\n17 functools.partial(<function check_estimator_sparse_data at 0x1254e0b90>, 'Stree')\n18 functools.partial(<function check_estimators_pickle at 0x1254e8950>, 'Stree')\n19 functools.partial(<function check_classifier_data_not_an_array at 0x1254f15f0>, 'Stree')\n20 functools.partial(<function check_classifiers_one_label at 0x1254eb050>, 'Stree')\n21 functools.partial(<function check_classifiers_classes at 0x1254eba70>, 'Stree')\n22 functools.partial(<function check_estimators_partial_fit_n_features at 0x1254e8a70>, 'Stree')\n23 functools.partial(<function check_classifiers_train at 0x1254eb170>, 'Stree')\n24 functools.partial(<function check_classifiers_train at 0x1254eb170>, 'Stree', readonly_memmap=True)\n25 functools.partial(<function check_classifiers_train at 0x1254eb170>, 'Stree', readonly_memmap=True, X_dtype='float32')\n26 functools.partial(<function check_classifiers_regression_target at 0x1254f40e0>, 'Stree')\n27 functools.partial(<function check_supervised_y_no_nan at 0x1254da9e0>, 'Stree')\n28 functools.partial(<function check_supervised_y_2d at 0x1254eb710>, 'Stree')\n29 functools.partial(<function check_estimators_unfitted at 0x1254eb5f0>, 'Stree')\n30 functools.partial(<function check_non_transformer_estimators_n_iter at 0x1254f1c20>, 'Stree')\n31 functools.partial(<function check_decision_proba_consistency at 0x1254f4200>, 'Stree')\n32 functools.partial(<function check_fit2d_predict1d at 0x1254e2830>, 'Stree')\n33 functools.partial(<function check_methods_subset_invariance at 0x1254e29e0>, 'Stree')\n34 functools.partial(<function check_fit2d_1sample at 0x1254e2b00>, 'Stree')\n35 functools.partial(<function check_fit2d_1feature at 0x1254e2c20>, 'Stree')\n36 functools.partial(<function check_fit1d at 0x1254e2d40>, 'Stree')\n37 functools.partial(<function check_get_params_invariance at 0x1254f1e60>, 'Stree')\n38 functools.partial(<function check_set_params at 0x1254f1f80>, 'Stree')\n39 functools.partial(<function check_dict_unchanged at 0x1254e2440>, 'Stree')\n40 functools.partial(<function check_dont_overwrite_parameters at 0x1254e2710>, 'Stree')\n41 functools.partial(<function check_fit_idempotent at 0x1254f43b0>, 'Stree')\n42 functools.partial(<function check_n_features_in at 0x1254f4440>, 'Stree')\n43 functools.partial(<function check_requires_y_none at 0x1254f44d0>, 'Stree')\n"
-    }
-   ],
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
   "source": [
    "# Make checks one by one\n",
    "c = 0\n",
@@ -283,7 +254,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
@@ -300,15 +271,11 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "== Not Weighted ===\nSVC train score ..: 0.9521072796934866\nSTree train score : 0.9578544061302682\nSVC test score ...: 0.9553571428571429\nSTree test score .: 0.9575892857142857\n==== Weighted =====\nSVC train score ..: 0.9616858237547893\nSTree train score : 0.9616858237547893\nSVC test score ...: 0.9642857142857143\nSTree test score .: 0.9598214285714286\n*SVC test score ..: 0.951413553411694\n*STree test score : 0.9480517444389333\n"
-    }
-   ],
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
   "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",
@@ -332,25 +299,47 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "root\nroot - Down\nroot - Down - Down, <cgaf> - Leaf class=1 belief= 0.969325 counts=(array([0, 1]), array([ 10, 316]))\nroot - Down - Up, <pure> - Leaf class=0 belief= 1.000000 counts=(array([0]), array([1]))\nroot - Up, <cgaf> - Leaf class=0 belief= 0.958159 counts=(array([0, 1]), array([687,  30]))\n\n"
-    }
-   ],
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
   "source": [
    "print(clf)"
   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test max_features"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "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)",
+   "display_name": "Python 3",
   "language": "python",
-   "name": "python37664bitgeneralvenvfbd0a23e74cf4e778460f5ffc6761f39"
+   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
@@ -362,9 +351,9 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.7.6-final"
+   "version": "3.8.2-final"
  }
 },
 "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }
--- a/notebooks/gridsearch.ipynb
+++ b/notebooks/gridsearch.ipynb
@@ -1,244 +1,253 @@
 {
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Test Gridsearch\n",
-        "with different kernels and different configurations"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Setup\n",
-        "Uncomment the next cell if STree is not already installed"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 1,
-      "metadata": {},
-      "outputs": [],
-      "source": [
-        "#\n",
-        "# Google Colab setup\n",
-        "#\n",
-        "#!pip install git+https://github.com/doctorado-ml/stree"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "zIHKVxthDZEa",
-        "colab_type": "code",
-        "colab": {}
-      },
-      "source": [
-        "from sklearn.ensemble import AdaBoostClassifier\n",
-        "from sklearn.svm import LinearSVC\n",
-        "from sklearn.model_selection import GridSearchCV, train_test_split\n",
-        "from stree import Stree"
-      ],
-      "execution_count": 2,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "IEmq50QgDZEi",
-        "colab_type": "code",
-        "colab": {}
-      },
-      "source": [
-        "import os\n",
-        "if not os.path.isfile('data/creditcard.csv'):\n",
-        "    !wget --no-check-certificate --content-disposition http://nube.jccm.es/index.php/s/Zs7SYtZQJ3RQ2H2/download\n",
-        "    !tar xzf creditcard.tgz"
-      ],
-      "execution_count": 3,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "z9Q-YUfBDZEq",
-        "colab_type": "code",
-        "colab": {},
-        "outputId": "afc822fb-f16a-4302-8a67-2b9e2880159b"
-      },
-      "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(-1000) # Take all true samples + 1000 of the others\n",
-        "# data = load_creditcard(5000)  # Take the first 5000 samples\n",
-        "# data = load_creditcard(0) # Take all the samples\n",
-        "\n",
-        "Xtrain = data[0]\n",
-        "Xtest = data[1]\n",
-        "ytrain = data[2]\n",
-        "ytest = data[3]"
-      ],
-      "execution_count": 4,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": "Fraud: 0.173% 492\nValid: 99.827% 284315\nX.shape (1492, 28)  y.shape (1492,)\nFraud: 33.244% 496\nValid: 66.756% 996\n"
-        }
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {},
-      "source": [
-        "# Tests"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "HmX3kR4PDZEw",
-        "colab_type": "code",
-        "colab": {}
-      },
-      "source": [
-        "parameters = {\n",
-        "    'base_estimator': [Stree()],\n",
-        "    'n_estimators': [10, 25],\n",
-        "    'learning_rate': [.5, 1],\n",
-        "    'base_estimator__tol': [.1,  1e-02],\n",
-        "    'base_estimator__max_depth': [3, 5],\n",
-        "    'base_estimator__C': [1, 3],\n",
-        "    'base_estimator__kernel': ['linear', 'poly', 'rbf']\n",
-        "}"
-      ],
-      "execution_count": 9,
-      "outputs": []
-    },
-    {
-      "cell_type": "code",
-      "execution_count": 14,
-      "metadata": {},
-      "outputs": [
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": "{'C': 1.0,\n 'degree': 3,\n 'gamma': 'scale',\n 'kernel': 'linear',\n 'max_depth': None,\n 'max_iter': 1000,\n 'min_samples_split': 0,\n 'random_state': None,\n 'tol': 0.0001}"
-          },
-          "metadata": {},
-          "execution_count": 14
-        }
-      ],
-      "source": [
-        "Stree().get_params()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "CrcB8o6EDZE5",
-        "colab_type": "code",
-        "colab": {},
-        "outputId": "7703413a-d563-4289-a13b-532f38f82762"
-      },
-      "source": [
-        "random_state=2020\n",
-        "clf = AdaBoostClassifier(random_state=random_state)\n",
-        "grid = GridSearchCV(clf, parameters, verbose=10, n_jobs=-1, return_train_score=True)\n",
-        "grid.fit(Xtrain, ytrain)"
-      ],
-      "execution_count": 11,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": "Fitting 5 folds for each of 96 candidates, totalling 480 fits\n[Parallel(n_jobs=-1)]: Using backend LokyBackend with 8 concurrent workers.\n[Parallel(n_jobs=-1)]: Done   2 tasks      | elapsed:    3.6s\n[Parallel(n_jobs=-1)]: Done   9 tasks      | elapsed:    4.2s\n[Parallel(n_jobs=-1)]: Done  16 tasks      | elapsed:    4.8s\n[Parallel(n_jobs=-1)]: Done  25 tasks      | elapsed:    5.3s\n[Parallel(n_jobs=-1)]: Done  34 tasks      | elapsed:    6.2s\n[Parallel(n_jobs=-1)]: Done  45 tasks      | elapsed:    7.2s\n[Parallel(n_jobs=-1)]: Done  56 tasks      | elapsed:    8.9s\n[Parallel(n_jobs=-1)]: Done  69 tasks      | elapsed:   10.7s\n[Parallel(n_jobs=-1)]: Done  82 tasks      | elapsed:   12.7s\n[Parallel(n_jobs=-1)]: Done  97 tasks      | elapsed:   16.7s\n[Parallel(n_jobs=-1)]: Done 112 tasks      | elapsed:   19.4s\n[Parallel(n_jobs=-1)]: Done 129 tasks      | elapsed:   24.4s\n[Parallel(n_jobs=-1)]: Done 146 tasks      | elapsed:   29.3s\n[Parallel(n_jobs=-1)]: Done 165 tasks      | elapsed:   32.7s\n[Parallel(n_jobs=-1)]: Done 184 tasks      | elapsed:   36.4s\n[Parallel(n_jobs=-1)]: Done 205 tasks      | elapsed:   39.7s\n[Parallel(n_jobs=-1)]: Done 226 tasks      | elapsed:   43.7s\n[Parallel(n_jobs=-1)]: Done 249 tasks      | elapsed:   46.6s\n[Parallel(n_jobs=-1)]: Done 272 tasks      | elapsed:   48.8s\n[Parallel(n_jobs=-1)]: Done 297 tasks      | elapsed:   52.0s\n[Parallel(n_jobs=-1)]: Done 322 tasks      | elapsed:   55.9s\n[Parallel(n_jobs=-1)]: Done 349 tasks      | elapsed:  1.0min\n[Parallel(n_jobs=-1)]: Done 376 tasks      | elapsed:  1.2min\n[Parallel(n_jobs=-1)]: Done 405 tasks      | elapsed:  1.3min\n[Parallel(n_jobs=-1)]: Done 434 tasks      | elapsed:  1.3min\n[Parallel(n_jobs=-1)]: Done 465 tasks      | elapsed:  1.4min\n[Parallel(n_jobs=-1)]: Done 480 out of 480 | elapsed:  1.5min finished\n"
-        },
-        {
-          "output_type": "execute_result",
-          "data": {
-            "text/plain": "GridSearchCV(estimator=AdaBoostClassifier(random_state=2020), n_jobs=-1,\n             param_grid={'base_estimator': [Stree(C=1, max_depth=3, tol=0.1)],\n                         'base_estimator__C': [1, 3],\n                         'base_estimator__kernel': ['linear', 'poly', 'rbf'],\n                         'base_estimator__max_depth': [3, 5],\n                         'base_estimator__tol': [0.1, 0.01],\n                         'learning_rate': [0.5, 1], 'n_estimators': [10, 25]},\n             return_train_score=True, verbose=10)"
-          },
-          "metadata": {},
-          "execution_count": 11
-        }
-      ]
-    },
-    {
-      "cell_type": "code",
-      "metadata": {
-        "id": "ZjX88NoYDZE8",
-        "colab_type": "code",
-        "colab": {},
-        "outputId": "285163c8-fa33-4915-8ae7-61c4f7844344"
-      },
-      "source": [
-        "print(\"Best estimator: \", grid.best_estimator_)\n",
-        "print(\"Best hyperparameters: \", grid.best_params_)\n",
-        "print(\"Best accuracy: \", grid.best_score_)"
-      ],
-      "execution_count": 16,
-      "outputs": [
-        {
-          "output_type": "stream",
-          "name": "stdout",
-          "text": "Best estimator:  AdaBoostClassifier(base_estimator=Stree(C=1, max_depth=3, tol=0.1),\n                   learning_rate=0.5, n_estimators=10, random_state=2020)\nBest hyperparameters:  {'base_estimator': Stree(C=1, max_depth=3, tol=0.1), 'base_estimator__C': 1, 'base_estimator__kernel': 'linear', 'base_estimator__max_depth': 3, 'base_estimator__tol': 0.1, 'learning_rate': 0.5, 'n_estimators': 10}\nBest accuracy:  0.9492316893632683\n"
-        }
-      ]
-    }
-  ],
-  "metadata": {
-    "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"
-    },
-    "orig_nbformat": 2,
-    "kernelspec": {
-      "name": "python37664bitgeneralvenvfbd0a23e74cf4e778460f5ffc6761f39",
-      "display_name": "Python 3.7.6 64-bit ('general': venv)"
-    },
-    "colab": {
-      "name": "gridsearch.ipynb",
-      "provenance": []
-    }
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Test Gridsearch\n",
+    "with different kernels and different configurations"
+   ]
  },
-  "nbformat": 4,
-  "nbformat_minor": 0
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Setup\n",
+    "Uncomment the next cell if STree is not already installed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#\n",
+    "# Google Colab setup\n",
+    "#\n",
+    "#!pip install git+https://github.com/doctorado-ml/stree\n",
+    "!pip install pandas"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "zIHKVxthDZEa"
+   },
+   "outputs": [],
+   "source": [
+    "import random\n",
+    "import os\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from sklearn.ensemble import AdaBoostClassifier\n",
+    "from sklearn.svm import LinearSVC\n",
+    "from sklearn.model_selection import GridSearchCV, train_test_split\n",
+    "from stree import Stree"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "IEmq50QgDZEi"
+   },
+   "outputs": [],
+   "source": [
+    "if not os.path.isfile('data/creditcard.csv'):\n",
+    "    !wget --no-check-certificate --content-disposition http://nube.jccm.es/index.php/s/Zs7SYtZQJ3RQ2H2/download\n",
+    "    !tar xzf creditcard.tgz"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "z9Q-YUfBDZEq",
+    "outputId": "afc822fb-f16a-4302-8a67-2b9e2880159b",
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "random_state=1\n",
+    "\n",
+    "def load_creditcard(n_examples=0):\n",
+    "    df = pd.read_csv('data/creditcard.csv')\n",
+    "    print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n",
+    "    print(\"Valid: {0:.3f}% {1}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))\n",
+    "    y = df.Class\n",
+    "    X = df.drop(['Class', 'Time', 'Amount'], axis=1).values\n",
+    "    if n_examples > 0:\n",
+    "        # Take first n_examples samples\n",
+    "        X = X[:n_examples, :]\n",
+    "        y = y[:n_examples, :]\n",
+    "    else:\n",
+    "        # Take all the positive samples with a number of random negatives\n",
+    "        if n_examples < 0:\n",
+    "            Xt = X[(y == 1).ravel()]\n",
+    "            yt = y[(y == 1).ravel()]\n",
+    "            indices = random.sample(range(X.shape[0]), -1 * n_examples)\n",
+    "            X = np.append(Xt, X[indices], axis=0)\n",
+    "            y = np.append(yt, y[indices], axis=0)\n",
+    "    print(\"X.shape\", X.shape, \" y.shape\", y.shape)\n",
+    "    print(\"Fraud: {0:.3f}% {1}\".format(len(y[y == 1])*100/X.shape[0], len(y[y == 1])))\n",
+    "    print(\"Valid: {0:.3f}% {1}\".format(len(y[y == 0]) * 100 / X.shape[0], len(y[y == 0])))\n",
+    "    Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state, stratify=y)\n",
+    "    return Xtrain, Xtest, ytrain, ytest\n",
+    "\n",
+    "data = load_creditcard(-1000) # Take all true samples + 1000 of the others\n",
+    "# data = load_creditcard(5000)  # Take the first 5000 samples\n",
+    "# data = load_creditcard(0) # Take all the samples\n",
+    "\n",
+    "Xtrain = data[0]\n",
+    "Xtest = data[1]\n",
+    "ytrain = data[2]\n",
+    "ytest = data[3]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Tests"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "HmX3kR4PDZEw"
+   },
+   "outputs": [],
+   "source": [
+    "parameters = [{\n",
+    "    'base_estimator': [Stree(random_state=random_state)],\n",
+    "    'n_estimators': [10, 25],\n",
+    "    'learning_rate': [.5, 1],\n",
+    "    'base_estimator__split_criteria': ['max_samples', 'impurity'],\n",
+    "    'base_estimator__tol': [.1,  1e-02],\n",
+    "    'base_estimator__max_depth': [3, 5, 7],\n",
+    "    'base_estimator__C': [1, 7, 55],\n",
+    "    'base_estimator__kernel': ['linear']\n",
+    "},\n",
+    "{\n",
+    "    'base_estimator': [Stree(random_state=random_state)],\n",
+    "    'n_estimators': [10, 25],\n",
+    "    'learning_rate': [.5, 1],\n",
+    "    'base_estimator__split_criteria': ['max_samples', 'impurity'],\n",
+    "    'base_estimator__tol': [.1,  1e-02],\n",
+    "    'base_estimator__max_depth': [3, 5, 7],\n",
+    "    'base_estimator__C': [1, 7, 55],\n",
+    "    'base_estimator__degree': [3, 5, 7],\n",
+    "    'base_estimator__kernel': ['poly']\n",
+    "},\n",
+    "{\n",
+    "    'base_estimator': [Stree(random_state=random_state)],\n",
+    "    'n_estimators': [10, 25],\n",
+    "    'learning_rate': [.5, 1],\n",
+    "    'base_estimator__split_criteria': ['max_samples', 'impurity'],\n",
+    "    'base_estimator__tol': [.1,  1e-02],\n",
+    "    'base_estimator__max_depth': [3, 5, 7],\n",
+    "    'base_estimator__C': [1, 7, 55],\n",
+    "    'base_estimator__gamma': [.1, 1, 10],\n",
+    "    'base_estimator__kernel': ['rbf']\n",
+    "}]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Stree().get_params()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "CrcB8o6EDZE5",
+    "outputId": "7703413a-d563-4289-a13b-532f38f82762",
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "clf = AdaBoostClassifier(random_state=random_state, algorithm=\"SAMME\")\n",
+    "grid = GridSearchCV(clf, parameters, verbose=5, n_jobs=-1, return_train_score=True)\n",
+    "grid.fit(Xtrain, ytrain)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {},
+    "colab_type": "code",
+    "id": "ZjX88NoYDZE8",
+    "outputId": "285163c8-fa33-4915-8ae7-61c4f7844344",
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "print(\"Best estimator: \", grid.best_estimator_)\n",
+    "print(\"Best hyperparameters: \", grid.best_params_)\n",
+    "print(\"Best accuracy: \", grid.best_score_)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Best estimator:  AdaBoostClassifier(algorithm='SAMME',\n",
+    "                   base_estimator=Stree(C=55, max_depth=7, random_state=1,\n",
+    "                                        split_criteria='max_samples', tol=0.1),\n",
+    "                   learning_rate=0.5, n_estimators=25, random_state=1)\n",
+    "Best hyperparameters:  {'base_estimator': Stree(C=55, max_depth=7, random_state=1, split_criteria='max_samples', tol=0.1), 'base_estimator__C': 55, 'base_estimator__kernel': 'linear', 'base_estimator__max_depth': 7, 'base_estimator__split_criteria': 'max_samples', 'base_estimator__tol': 0.1, 'learning_rate': 0.5, 'n_estimators': 25}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Best accuracy:  0.9511777695988222"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "name": "gridsearch.ipynb",
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.2-final"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
 }
--- a/notebooks/test_graphs.ipynb
+++ b/notebooks/test_graphs.ipynb
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,5 +1 @@
-numpy
-scikit-learn
-pandas
-matplotlib
-ipympl
+scikit-learn>0.24
--- a/runtime.txt
+++ b/runtime.txt
@@ -0,0 +1 @@
+python-3.8
--- a/setup.py
+++ b/setup.py
@@ -1,6 +1,6 @@
 import setuptools

-__version__ = "0.9rc4"
+__version__ = "1.0rc1"
 __author__ = "Ricardo Montañana Gómez"


@@ -25,12 +25,12 @@ setuptools.setup(
    classifiers=[
        "Development Status :: 4 - Beta",
        "License :: OSI Approved :: MIT License",
-        "Programming Language :: Python :: 3.7",
+        "Programming Language :: Python :: 3.8",
        "Natural Language :: English",
        "Topic :: Scientific/Engineering :: Artificial Intelligence",
        "Intended Audience :: Science/Research",
    ],
-    install_requires=["scikit-learn>=0.23.0", "numpy", "matplotlib", "ipympl"],
+    install_requires=["scikit-learn", "numpy", "ipympl"],
    test_suite="stree.tests",
    zip_safe=False,
 )
--- a/stree/Strees.py
+++ b/stree/Strees.py
@@ -3,16 +3,22 @@ __author__ = "Ricardo Montañana Gómez"
 __copyright__ = "Copyright 2020, Ricardo Montañana Gómez"
 __license__ = "MIT"
 __version__ = "0.9"
-Build an oblique tree classifier based on SVM Trees
+Build an oblique tree classifier based on SVM nodes
 """

 import os
-
+import numbers
+import random
+import warnings
+from math import log, factorial
+from typing import Optional
 import numpy as np
 from sklearn.base import BaseEstimator, ClassifierMixin
 from sklearn.svm import SVC, LinearSVC
+from sklearn.preprocessing import StandardScaler
 from sklearn.utils import check_consistent_length
 from sklearn.utils.multiclass import check_classification_targets
+from sklearn.exceptions import ConvergenceWarning
 from sklearn.utils.validation import (
    check_X_y,
    check_array,
@@ -27,7 +33,17 @@ class Snode:
    dataset assigned to it
    """

-    def __init__(self, clf: SVC, X: np.ndarray, y: np.ndarray, title: str):
+    def __init__(
+        self,
+        clf: SVC,
+        X: np.ndarray,
+        y: np.ndarray,
+        features: np.array,
+        impurity: float,
+        title: str,
+        weight: np.ndarray = None,
+        scaler: StandardScaler = None,
+    ):
        self._clf = clf
        self._title = title
        self._belief = 0.0
@@ -37,14 +53,61 @@ class Snode:
        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
+        self._scaler = scaler

    @classmethod
    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,
+            node._sample_weight,
+            node._scaler,
+        )
+
+    def set_partition_column(self, col: int):
+        self._partition_column = col
+
+    def get_partition_column(self) -> int:
+        return self._partition_column

    def set_down(self, son):
        self._down = son

+    def set_title(self, title):
+        self._title = title
+
+    def set_classifier(self, clf):
+        self._clf = clf
+
+    def set_features(self, features):
+        self._features = features
+
+    def set_impurity(self, impurity):
+        self._impurity = impurity
+
+    def get_title(self) -> str:
+        return self._title
+
+    def get_classifier(self) -> SVC:
+        return self._clf
+
+    def get_impurity(self) -> float:
+        return self._impurity
+
+    def get_features(self) -> np.array:
+        return self._features
+
    def set_up(self, son):
        self._up = son

@@ -66,9 +129,8 @@ class Snode:
        classes, card = np.unique(self._y, return_counts=True)
        if len(classes) > 1:
            max_card = max(card)
-            min_card = min(card)
            self._class = classes[card == max_card][0]
-            self._belief = max_card / (max_card + min_card)
+            self._belief = max_card / np.sum(card)
        else:
            self._belief = 1
            try:
@@ -77,28 +139,28 @@ class Snode:
                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)
-            result = (
+            return (
                f"{self._title} - Leaf class={self._class} belief="
-                f"{self._belief: .6f} counts={count_values}"
+                f"{self._belief: .6f} impurity={self._impurity:.4f} "
+                f"counts={count_values}"
            )
-            return result
        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)
@@ -112,6 +174,347 @@ class Siterator:
        return node


+class Splitter:
+    def __init__(
+        self,
+        clf: SVC = None,
+        criterion: str = None,
+        splitter_type: str = None,
+        criteria: str = None,
+        min_samples_split: int = None,
+        random_state=None,
+        normalize=False,
+    ):
+        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
+        self._normalize = normalize
+
+        if clf is None:
+            raise ValueError(f"clf has to be a sklearn estimator, got({clf})")
+
+        if criterion not in ["gini", "entropy"]:
+            raise ValueError(
+                f"criterion must be gini or entropy got({criterion})"
+            )
+
+        if criteria not in [
+            "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:
+        """Compute entropy of a labels set
+
+        Parameters
+        ----------
+        y : np.array
+            set of labels
+
+        Returns
+        -------
+        float
+            entropy
+        """
+        n_labels = len(y)
+        if n_labels <= 1:
+            return 0
+        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:
+        """Compute information gain of a split candidate
+
+        Parameters
+        ----------
+        labels : np.array
+            labels of the dataset
+        labels_up : np.array
+            labels of one side
+        labels_dn : np.array
+            labels on the other side
+
+        Returns
+        -------
+        float
+            information gain
+        """
+        imp_prev = self.criterion_function(labels)
+        card_up = card_dn = imp_up = imp_dn = 0
+        if labels_up is not None:
+            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:
+        """Generate at most 5 feature random combinations
+
+        Parameters
+        ----------
+        features : int
+            number of features in each combination
+        max_features : int
+            number of features in dataset
+
+        Returns
+        -------
+        list
+            list with up to 5 combination of features randomly selected
+        """
+        comb = set()
+        # Generate at most 5 combinations
+        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:
+        """Compute the indices of the features selected by splitter depending
+        on the self._splitter_type hyper parameter
+
+        Parameters
+        ----------
+        dataset : np.array
+            array of samples
+        labels : np.array
+            labels of the dataset
+        max_features : int
+            number of features of the subspace
+            (<= number of features in dataset)
+
+        Returns
+        -------
+        np.array
+            indices of the features selected
+        """
+        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 a subspace of the selected dataset of max_features length.
+        Depending on hyperparmeter
+
+        Parameters
+        ----------
+        dataset : np.array
+            array of samples (# samples, # features)
+        labels : np.array
+            labels of the dataset
+        max_features : int
+            number of features to form the subspace
+
+        Returns
+        -------
+        tuple
+            tuple with the dataset with only the features selected  and the
+            indices of the features selected
+        """
+        indices = self._get_subspaces_set(dataset, labels, max_features)
+        return dataset[:, indices], indices
+
+    def _impurity(self, data: np.array, y: np.array) -> np.array:
+        """return column of dataset to be taken into account to split dataset
+
+        Parameters
+        ----------
+        data : np.array
+            distances to hyper plane of every class
+        y : np.array
+            vector of labels (classes)
+
+        Returns
+        -------
+        np.array
+            column of dataset to be taken into account to split dataset
+        """
+        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
+
+    @staticmethod
+    def _max_samples(data: np.array, y: np.array) -> np.array:
+        """return column of dataset to be taken into account to split dataset
+
+        Parameters
+        ----------
+        data : np.array
+            distances to hyper plane of every class
+        y : np.array
+            column of dataset to be taken into account to split dataset
+
+        Returns
+        -------
+        np.array
+            column of dataset to be taken into account to split dataset
+        """
+        # select the class with max number of samples
+        _, samples = np.unique(y, return_counts=True)
+        return np.argmax(samples)
+
+    def partition(self, samples: np.array, node: Snode, train: bool):
+        """Set the criteria to split arrays. Compute the indices of the samples
+        that should go to one side of the tree (up)
+        """
+        # data contains the distances of every sample to every class hyperplane
+        # array of (m, nc) nc = # classes
+        data = self._distances(node, samples)
+        if data.shape[0] < self._min_samples_split:
+            # 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 (self._up) and its complement
+        partition has to be called first to establish up indices
+
+        Parameters
+        ----------
+        origin : np.array
+            dataset to split
+
+        Returns
+        -------
+        list
+            list with two splits of the array
+        """
+        down = ~self._up
+        return [
+            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:
+        """Compute distances of the samples to the hyperplane of the node
+
+        Parameters
+        ----------
+        node : Snode
+            node containing the svm classifier
+        data : np.ndarray
+            samples to compute distance to hyperplane
+
+        Returns
+        -------
+        np.array
+            array of shape (m, nc) with the distances of every sample to
+            the hyperplane of every class. nc = # of classes
+        """
+        X_transformed = data[:, node._features]
+        if self._normalize:
+            X_transformed = node._scaler.transform(X_transformed)
+        return node._clf.decision_function(X_transformed)
+
+
 class Stree(BaseEstimator, ClassifierMixin):
    """Estimator that is based on binary trees of svm nodes
    can deal with sample_weights in predict, used in boosting sklearn methods
@@ -124,14 +527,18 @@ class Stree(BaseEstimator, ClassifierMixin):
        self,
        C: float = 1.0,
        kernel: str = "linear",
-        max_iter: int = 1000,
+        max_iter: int = 1e5,
        random_state: int = None,
        max_depth: int = None,
        tol: float = 1e-4,
        degree: int = 3,
        gamma="scale",
-        split_criteria="max_samples",
+        split_criteria: str = "impurity",
+        criterion: str = "entropy",
        min_samples_split: int = 0,
+        max_features=None,
+        splitter: str = "random",
+        normalize: bool = False,
    ):
        self.max_iter = max_iter
        self.C = C
@@ -143,90 +550,38 @@ class Stree(BaseEstimator, ClassifierMixin):
        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
+        self.normalize = normalize

    def _more_tags(self) -> dict:
        """Required by sklearn to supply features of the classifier
+        make mandatory the labels array

        :return: the tag required
        :rtype: dict
        """
        return {"requires_y": True}

-    def _split_array(self, origin: np.array, down: np.array) -> list:
-        """Split an array in two based on indices (down) and its complement
-
-        :param origin: dataset to split
-        :type origin: np.array
-        :param down: indices to use to split array
-        :type down: np.array
-        :return: list with two splits of the array
-        :rtype: list
-        """
-        up = ~down
-        return (
-            origin[up] if any(up) else None,
-            origin[down] if any(down) else None,
-        )
-
-    def _distances(self, node: Snode, data: np.ndarray) -> np.array:
-        """Compute distances of the samples to the hyperplane of the node
-
-        :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
-        the hyperplane of the node
-        :rtype: np.array
-        """
-        return node._clf.decision_function(data)
-
-    def _min_distance(self, data: np.array, _) -> np.array:
-        # chooses the lowest distance of every sample
-        indices = np.argmin(np.abs(data), axis=1)
-        return np.take(data, indices)
-
-    def _max_samples(self, data: np.array, y: np.array) -> np.array:
-        # select the class with max number of samples
-        _, samples = np.unique(y, return_counts=True)
-        selected = np.argmax(samples)
-        return data[:, selected]
-
-    def _split_criteria(self, data: np.array, node: Snode) -> np.array:
-        """Set the criteria to split arrays
-
-        :param data: distances of samples to hyperplanes shape (m, nclasses)
-        if nclasses > 2 else (m,)
-        :type data: np.array
-        :param node: node containing the svm classifier
-        :type node: Snode
-        :return: array of booleans of samples under or above zero
-        :rtype: np.array
-        """
-
-        if data.shape[0] < self.min_samples_split:
-            return np.ones((data.shape[0]), dtype=bool)
-        if data.ndim > 1:
-            # split criteria for multiclass
-            data = getattr(self, f"_{self.split_criteria}")(data, node._y)
-        res = data > 0
-        return res
-
    def fit(
        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
+        Returns
+        -------
+        Stree
+            itself to be able to chain actions: fit().predict() ...
+
+        Raises
+        ------
+        ValueError
+            if C < 0
+        ValueError
+            if max_depth < 1
+        ValueError
+            if all samples have 0 or negative weights
        """
        # Check parameters are Ok.
        if self.C < 0:
@@ -243,24 +598,40 @@ class Stree(BaseEstimator, ClassifierMixin):
                f"Maximum depth has to be greater than 1... got (max_depth=\
                    {self.max_depth})"
            )
-        if self.split_criteria not in ["min_distance", "max_samples"]:
-            raise ValueError(
-                f"split_criteria has to be min_distance or \
-                max_samples got ({self.split_criteria})"
-            )

        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
+        )
+        if not any(sample_weight):
+            raise ValueError(
+                "Invalid input - all samples have zero or negative weights."
+            )
        check_classification_targets(y)
        # Initialize computed parameters
+        self.splitter_ = Splitter(
+            clf=self._build_clf(),
+            criterion=self.criterion,
+            splitter_type=self.splitter,
+            criteria=self.split_criteria,
+            random_state=self.random_state,
+            min_samples_split=self.min_samples_split,
+            normalize=self.normalize,
+        )
+        if self.random_state is not None:
+            random.seed(self.random_state)
        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.max_features_ = self._initialize_max_features()
        self.tree_ = self.train(X, y, sample_weight, 1, "root")
        self._build_predictor()
+        self.X_ = X
+        self.y_ = y
        return self

    def train(
@@ -270,48 +641,73 @@ class Stree(BaseEstimator, ClassifierMixin):
        sample_weight: np.ndarray,
        depth: int,
        title: str,
-    ) -> Snode:
+    ) -> Optional[Snode]:
        """Recursive function to split the original dataset into predictor
        nodes (leaves)

-        :param X: samples dataset
-        :type X: np.ndarray
-        :param y: samples labels
-        :type y: np.ndarray
-        :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
-        :param title: description of the node
-        :type title: str
-        :return: binary tree
-        :rtype: Snode
+        Parameters
+        ----------
+        X : np.ndarray
+            samples dataset
+        y : np.ndarray
+            samples labels
+        sample_weight : np.ndarray
+            weight of samples. Rescale C per sample.
+        depth : int
+            actual depth in the tree
+        title : str
+            description of the node
+
+        Returns
+        -------
+        Optional[Snode]
+            binary tree
        """
        if depth > self.__max_depth:
            return None
+        # Mask samples with 0 weight
+        if any(sample_weight == 0):
+            indices_zero = sample_weight == 0
+            X = X[~indices_zero, :]
+            y = y[~indices_zero]
+            sample_weight = sample_weight[~indices_zero]
+        self.depth_ = max(depth, self.depth_)
+        scaler = StandardScaler()
+        node = Snode(None, X, y, X.shape[1], 0.0, title, sample_weight, scaler)
        if np.unique(y).shape[0] == 1:
            # only 1 class => pure dataset
-            return Snode(None, X, y, title + ", <pure>")
+            node.set_title(title + ", <pure>")
+            return node
        # Train the model
        clf = self._build_clf()
-        clf.fit(X, y, sample_weight=sample_weight)
-        node = Snode(clf, X, y, title)
-        self.depth_ = max(depth, self.depth_)
-        down = self._split_criteria(self._distances(node, X), node)
-        X_U, X_D = self._split_array(X, down)
-        y_u, y_d = self._split_array(y, down)
-        sw_u, sw_d = self._split_array(sample_weight, down)
+        Xs, features = self.splitter_.get_subspace(X, y, self.max_features_)
+        if self.normalize:
+            scaler.fit(Xs)
+            Xs = scaler.transform(Xs)
+        clf.fit(Xs, y, sample_weight=sample_weight)
+        node.set_impurity(self.splitter_.partition_impurity(y))
+        node.set_classifier(clf)
+        node.set_features(features)
+        self.splitter_.partition(X, node, True)
+        X_U, X_D = self.splitter_.part(X)
+        y_u, y_d = self.splitter_.part(y)
+        sw_u, sw_d = self.splitter_.part(sample_weight)
        if X_U is None or X_D is None:
            # didn't part anything
-            return Snode(clf, X, y, title + ", <cgaf>")
-        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"))
+            node.set_title(title + ", <cgaf>")
+            return node
+        node.set_up(
+            self.train(X_U, y_u, sw_u, depth + 1, title + f" - Up({depth+1})")
+        )
+        node.set_down(
+            self.train(
+                X_D, y_d, sw_d, depth + 1, title + f" - Down({depth+1})"
+            )
+        )
        return node

    def _build_predictor(self):
-        """Process the leaves to make them predictors
-        """
+        """Process the leaves to make them predictors"""

        def run_tree(node: Snode):
            if node.is_leaf():
@@ -323,8 +719,7 @@ class Stree(BaseEstimator, ClassifierMixin):
        run_tree(self.tree_)

    def _build_clf(self):
-        """ Build the correct classifier for the node
-        """
+        """Build the correct classifier for the node"""
        return (
            LinearSVC(
                max_iter=self.max_iter,
@@ -343,15 +738,21 @@ class Stree(BaseEstimator, ClassifierMixin):
            )
        )

-    def _reorder_results(self, y: np.array, indices: np.array) -> np.array:
+    @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
-        :type y: np.array
-        :param indices: indices used to set order
-        :type indices: np.array
-        :return: array y ordered
-        :rtype: np.array
+        Parameters
+        ----------
+        y : np.array
+            data untidy
+        indices : np.array
+            indices used to set order
+
+        Returns
+        -------
+        np.array
+            array y ordered
        """
        # return array of same type given in y
        y_ordered = y.copy()
@@ -363,10 +764,22 @@ class Stree(BaseEstimator, ClassifierMixin):
    def predict(self, X: np.array) -> np.array:
        """Predict labels for each sample in dataset passed

-        :param X: dataset of samples
-        :type X: np.array
-        :return: array of labels
-        :rtype: np.array
+        Parameters
+        ----------
+        X : np.array
+            dataset of samples
+
+        Returns
+        -------
+        np.array
+            array of labels
+
+        Raises
+        ------
+        ValueError
+            if dataset with inconsistent number of features
+        NotFittedError
+            if model is not fitted
        """

        def predict_class(
@@ -378,9 +791,9 @@ class Stree(BaseEstimator, ClassifierMixin):
                # 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), node)
-            x_u, x_d = self._split_array(xp, down)
-            i_u, i_d = self._split_array(indices, down)
+            self.splitter_.partition(xp, node, train=False)
+            x_u, x_d = self.splitter_.part(xp)
+            i_u, i_d = self.splitter_.part(indices)
            prx_u, prin_u = predict_class(x_u, i_u, node.get_up())
            prx_d, prin_d = predict_class(x_d, i_d, node.get_down())
            return np.append(prx_u, prx_d), np.append(prin_u, prin_d)
@@ -389,6 +802,11 @@ class Stree(BaseEstimator, ClassifierMixin):
        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 = (
@@ -403,15 +821,19 @@ class Stree(BaseEstimator, ClassifierMixin):
    ) -> float:
        """Compute accuracy of the prediction

-        :param X: dataset of samples to make predictions
-        :type X: np.array
-        :param y_true: samples labels
-        :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
+        Parameters
+        ----------
+        X : np.array
+            dataset of samples to make predictions
+        y : np.array
+            samples labels
+        sample_weight : np.array, optional
+            weights of the samples. Rescale C per sample, by default None
+
+        Returns
+        -------
+        float
+            accuracy of the prediction
        """
        # sklearn check
        check_is_fitted(self)
@@ -419,17 +841,35 @@ class Stree(BaseEstimator, ClassifierMixin):
        X, y = check_X_y(X, y)
        y_pred = self.predict(X).reshape(y.shape)
        # Compute accuracy for each possible representation
-        y_type, y_true, y_pred = _check_targets(y, y_pred)
+        _, 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 nodes_leaves(self) -> tuple:
+        """Compute the number of nodes and leaves in the built tree
+
+        Returns
+        -------
+        [tuple]
+            tuple with the number of nodes and the number of leaves
+        """
+        nodes = 0
+        leaves = 0
+        for node in self:
+            nodes += 1
+            if node.is_leaf():
+                leaves += 1
+        return nodes, leaves
+
    def __iter__(self) -> Siterator:
        """Create an iterator to be able to visit the nodes of the tree in
        preorder, can make a list with all the nodes in preorder

-        :return: an iterator, can for i in... and list(...)
-        :rtype: Siterator
+        Returns
+        -------
+        Siterator
+            an iterator, can for i in... and list(...)
        """
        try:
            tree = self.tree_
@@ -440,10 +880,43 @@ class Stree(BaseEstimator, ClassifierMixin):
    def __str__(self) -> str:
        """String representation of the tree

-        :return: description of nodes in the tree in preorder
-        :rtype: str
+        Returns
+        -------
+        str
+            description of nodes in the tree in preorder
        """
        output = ""
        for i in self:
            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
--- a/stree/Strees_grapher.py
+++ b/stree/Strees_grapher.py
@@ -1,205 +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 get_plot_size(self) -> tuple:
-        return self._plot_size
-
-    def _is_pure(self) -> bool:
-        """is considered pure a leaf node with one label
-        """
-        if self.is_leaf():
-            return self._belief == 1.0
-        return False
-
-    def set_axis_limits(self, limits: tuple):
-        self._xlimits, self._ylimits, self._zlimits = limits
-
-    def get_axis_limits(self) -> tuple:
-        return self._xlimits, self._ylimits, self._zlimits
-
-    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 = os.path.join(save_folder, f"{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._clf.intercept_
-                    - self._clf.coef_[0][0] * x
-                    - self._clf.coef_[0][1] * y
-                ) / self._clf.coef_[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=0.5,
-                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
-
-    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, sample_weight: np.array = None
-    ) -> "Stree_grapher":
-        """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)
-        super().fit(X, y, sample_weight=sample_weight)
-        self._tree_gr = self._copy_tree(self.tree_)
-        self._fitted = True
-        return self
-
-    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)
--- a/stree/init.py
+++ b/stree/init.py
@@ -1,4 +1,3 @@
-from .Strees import Stree, Snode, Siterator
-from .Strees_grapher import Stree_grapher, Snode_graph
+from .Strees import Stree, Snode, Siterator, Splitter

-__all__ = ["Stree", "Snode", "Siterator", "Stree_grapher", "Snode_graph"]
+__all__ = ["Stree", "Snode", "Siterator", "Splitter"]
--- a/stree/tests/Snode_test.py
+++ b/stree/tests/Snode_test.py
@@ -0,0 +1,121 @@
+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_set_title(self):
+        test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
+        self.assertEqual("test", test.get_title())
+        test.set_title("another")
+        self.assertEqual("another", test.get_title())
+
+    def test_set_classifier(self):
+        test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
+        clf = Stree()
+        self.assertIsNone(test.get_classifier())
+        test.set_classifier(clf)
+        self.assertEqual(clf, test.get_classifier())
+
+    def test_set_impurity(self):
+        test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
+        self.assertEqual(0.0, test.get_impurity())
+        test.set_impurity(54.7)
+        self.assertEqual(54.7, test.get_impurity())
+
+    def test_set_features(self):
+        test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [0, 1], 0.0, "test")
+        self.assertListEqual([0, 1], test.get_features())
+        test.set_features([1, 2])
+        self.assertListEqual([1, 2], test.get_features())
+
+    def test_make_predictor_on_not_leaf(self):
+        test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test")
+        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)
+        self.assertEqual(test._sample_weight, computed._sample_weight)
+        self.assertEqual(test._scaler, computed._scaler)
--- a/stree/tests/Splitter_test.py
+++ b/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()
+                    )
--- a/stree/tests/Stree_test.py
+++ b/stree/tests/Stree_test.py
@@ -0,0 +1,511 @@
+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
+
+        Parameters
+        ----------
+        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]), "
+            "array([750, 750]))",
+            "root - Down(2), <cgaf> - Leaf class=0 belief= 0.928297 impurity="
+            "0.3722 counts=(array([0, 1]), array([725,  56]))",
+            "root - Up(2) feaures=(0, 1, 2) impurity=0.2178 counts=(array([0, "
+            "1]), array([ 25, 694]))",
+            "root - Up(2) - Down(3) feaures=(0, 1, 2) impurity=0.8454 counts="
+            "(array([0, 1]), array([8, 3]))",
+            "root - Up(2) - Down(3) - Down(4), <pure> - Leaf class=0 belief= "
+            "1.000000 impurity=0.0000 counts=(array([0]), array([7]))",
+            "root - Up(2) - Down(3) - Up(4), <cgaf> - Leaf class=1 belief= "
+            "0.750000 impurity=0.8113 counts=(array([0, 1]), array([1, 3]))",
+            "root - Up(2) - Up(3), <cgaf> - Leaf class=1 belief= 0.975989 "
+            "impurity=0.1634 counts=(array([0, 1]), array([ 17, 691]))",
+        ]
+        computed = []
+        expected_string = ""
+        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": 0.618,
+                "impurity linear": 0.9606666666666667,
+                "impurity rbf": 0.7133333333333334,
+                "impurity poly": 0.618,
+            },
+            "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_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)
+        clf2 = Stree(
+            kernel="rbf", random_state=self._random_state, normalize=True
+        )
+        self.assertEqual(0.768, clf.fit(X, y).score(X, y))
+        self.assertEqual(0.814, clf2.fit(X, y).score(X, y))
+        X, y = load_wine(return_X_y=True)
+        self.assertEqual(0.6741573033707865, clf.fit(X, y).score(X, y))
+        self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
+
+    def test_score_multiclass_poly(self):
+        X, y = load_dataset(
+            random_state=self._random_state,
+            n_classes=3,
+            n_features=5,
+            n_samples=500,
+        )
+        clf = Stree(
+            kernel="poly", random_state=self._random_state, C=10, degree=5
+        )
+        clf2 = Stree(
+            kernel="poly",
+            random_state=self._random_state,
+            normalize=True,
+        )
+        self.assertEqual(0.786, clf.fit(X, y).score(X, y))
+        self.assertEqual(0.818, clf2.fit(X, y).score(X, y))
+        X, y = load_wine(return_X_y=True)
+        self.assertEqual(0.702247191011236, clf.fit(X, y).score(X, y))
+        self.assertEqual(0.6067415730337079, clf2.fit(X, y).score(X, y))
+
+    def test_score_multiclass_linear(self):
+        X, y = load_dataset(
+            random_state=self._random_state,
+            n_classes=3,
+            n_features=5,
+            n_samples=1500,
+        )
+        clf = Stree(kernel="linear", random_state=self._random_state)
+        self.assertEqual(0.9533333333333334, clf.fit(X, y).score(X, y))
+        # Check with context based standardization
+        clf2 = Stree(
+            kernel="linear", random_state=self._random_state, normalize=True
+        )
+        self.assertEqual(0.9526666666666667, clf2.fit(X, y).score(X, y))
+        X, y = load_wine(return_X_y=True)
+        self.assertEqual(0.9831460674157303, clf.fit(X, y).score(X, y))
+        self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
+
+    def test_zero_all_sample_weights(self):
+        X, y = load_dataset(self._random_state)
+        with self.assertRaises(ValueError):
+            Stree().fit(X, y, np.zeros(len(y)))
+
+    def test_mask_samples_weighted_zero(self):
+        X = np.array(
+            [
+                [1, 1],
+                [1, 1],
+                [1, 1],
+                [2, 2],
+                [2, 2],
+                [2, 2],
+                [3, 3],
+                [3, 3],
+                [3, 3],
+            ]
+        )
+        y = np.array([1, 1, 1, 2, 2, 2, 5, 5, 5])
+        yw = np.array([1, 1, 1, 5, 5, 5, 5, 5, 5])
+        w = [1, 1, 1, 0, 0, 0, 1, 1, 1]
+        model1 = Stree().fit(X, y)
+        model2 = Stree().fit(X, y, w)
+        predict1 = model1.predict(X)
+        predict2 = model2.predict(X)
+        self.assertListEqual(y.tolist(), predict1.tolist())
+        self.assertListEqual(yw.tolist(), predict2.tolist())
+        self.assertEqual(model1.score(X, y), 1)
+        self.assertAlmostEqual(model2.score(X, y), 0.66666667)
+        self.assertEqual(model2.score(X, y, w), 1)
+
+    def test_depth(self):
+        X, y = load_dataset(
+            random_state=self._random_state,
+            n_classes=3,
+            n_features=5,
+            n_samples=1500,
+        )
+        clf = Stree(random_state=self._random_state)
+        clf.fit(X, y)
+        self.assertEqual(6, clf.depth_)
+        X, y = load_wine(return_X_y=True)
+        clf = Stree(random_state=self._random_state)
+        clf.fit(X, y)
+        self.assertEqual(4, clf.depth_)
+
+    def test_nodes_leaves(self):
+        X, y = load_dataset(
+            random_state=self._random_state,
+            n_classes=3,
+            n_features=5,
+            n_samples=1500,
+        )
+        clf = Stree(random_state=self._random_state)
+        clf.fit(X, y)
+        nodes, leaves = clf.nodes_leaves()
+        self.assertEqual(25, nodes)
+        self.assertEquals(13, leaves)
+        X, y = load_wine(return_X_y=True)
+        clf = Stree(random_state=self._random_state)
+        clf.fit(X, y)
+        nodes, leaves = clf.nodes_leaves()
+        self.assertEqual(9, nodes)
+        self.assertEquals(5, leaves)
+
+    def test_nodes_leaves_artificial(self):
+        n1 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test1")
+        n2 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test2")
+        n3 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test3")
+        n4 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test4")
+        n5 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test5")
+        n6 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test6")
+        n1.set_up(n2)
+        n2.set_up(n3)
+        n2.set_down(n4)
+        n3.set_up(n5)
+        n4.set_down(n6)
+        clf = Stree(random_state=self._random_state)
+        clf.tree_ = n1
+        nodes, leaves = clf.nodes_leaves()
+        self.assertEqual(6, nodes)
+        self.assertEqual(2, leaves)
--- a/stree/tests/Strees_grapher_test.py
+++ b/stree/tests/Strees_grapher_test.py
@@ -1,226 +0,0 @@
-import os
-import imghdr
-import unittest
-
-import numpy as np
-import matplotlib
-import matplotlib.pyplot as plt
-import warnings
-from sklearn.datasets import make_classification
-
-from stree import Stree_grapher, Snode_graph, Snode
-
-
-def get_dataset(random_state=0, n_features=3):
-    X, y = make_classification(
-        n_samples=1500,
-        n_features=n_features,
-        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=random_state,
-    )
-    return X, y
-
-
-class Stree_grapher_test(unittest.TestCase):
-    def __init__(self, *args, **kwargs):
-        self._random_state = 1
-        self._clf = Stree_grapher(dict(random_state=self._random_state))
-        self._clf.fit(*get_dataset(self._random_state, n_features=4))
-        super().__init__(*args, **kwargs)
-
-    @classmethod
-    def setUp(cls):
-        os.environ["TESTING"] = "1"
-
-    def test_iterator(self):
-        """Check preorder iterator
-        """
-        expected = [
-            "root",
-            "root - Down",
-            "root - Down - Down, <cgaf> - Leaf class=1 belief= 0.976023 counts"
-            "=(array([0, 1]), array([ 17, 692]))",
-            "root - Down - Up",
-            "root - Down - Up - Down, <cgaf> - Leaf class=0 belief= 0.500000 "
-            "counts=(array([0, 1]), array([1, 1]))",
-            "root - Down - Up - Up, <cgaf> - Leaf class=0 belief= 0.888889 "
-            "counts=(array([0, 1]), array([8, 1]))",
-            "root - Up, <cgaf> - Leaf class=0 belief= 0.928205 counts=(array("
-            "[0, 1]), array([724,  56]))",
-        ]
-        computed = []
-        for node in self._clf:
-            computed.append(str(node))
-        self.assertListEqual(expected, computed)
-
-    def test_score(self):
-        X, y = get_dataset(self._random_state)
-        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, 0.86)
-
-    def test_score_4dims(self):
-        X, y = get_dataset(self._random_state, n_features=4)
-        accuracy_score = self._clf.score(X, y)
-        self.assertEqual(accuracy_score, 0.95)
-
-    def test_save_all(self):
-        folder_name = os.path.join(os.sep, "tmp", "stree")
-        if os.path.isdir(folder_name):
-            os.rmdir(folder_name)
-        file_names = [
-            os.path.join(folder_name, f"STnode{i}.png") for i in range(1, 8)
-        ]
-        with warnings.catch_warnings():
-            warnings.simplefilter("ignore")
-            matplotlib.use("Agg")
-            self._clf.save_all(save_folder=folder_name)
-        for file_name in file_names:
-            self.assertTrue(os.path.exists(file_name))
-            self.assertEqual("png", imghdr.what(file_name))
-            os.remove(file_name)
-        os.rmdir(folder_name)
-
-    def test_plot_all(self):
-        with warnings.catch_warnings():
-            warnings.simplefilter("ignore")
-            matplotlib.use("Agg")
-            num_figures_before = plt.gcf().number
-            self._clf.plot_all()
-            num_figures_after = plt.gcf().number
-        self.assertEqual(7, num_figures_after - num_figures_before)
-
-
-class Snode_graph_test(unittest.TestCase):
-    def __init__(self, *args, **kwargs):
-        self._random_state = 1
-        self._clf = Stree_grapher(dict(random_state=self._random_state))
-        self._clf.fit(*get_dataset(self._random_state))
-        super().__init__(*args, **kwargs)
-
-    @classmethod
-    def setUp(cls):
-        os.environ["TESTING"] = "1"
-
-    def test_plot_size(self):
-        default = self._clf._tree_gr.get_plot_size()
-        expected = (17, 3)
-        self._clf._tree_gr.set_plot_size(expected)
-        self.assertEqual(expected, self._clf._tree_gr.get_plot_size())
-        self._clf._tree_gr.set_plot_size(default)
-        self.assertEqual(default, self._clf._tree_gr.get_plot_size())
-
-    def test_attributes_in_leaves_graph(self):
-        """Check if the attributes in leaves have correct values so they form a
-        predictor
-        """
-
-        def check_leave(node: Snode_graph):
-            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 = 0.0
-            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_gr)
-
-    def test_nodes_graph_coefs(self):
-        """Check if the nodes of the tree have the right attributes filled
-        """
-
-        def run_tree(node: Snode_graph):
-            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_down())
-            run_tree(node.get_up())
-
-        run_tree(self._clf._tree_gr)
-
-    def test_save_hyperplane(self):
-        folder_name = "/tmp/"
-        file_name = os.path.join(folder_name, "STnode1.png")
-        with warnings.catch_warnings():
-            warnings.simplefilter("ignore")
-            matplotlib.use("Agg")
-            self._clf._tree_gr.save_hyperplane(folder_name)
-        self.assertTrue(os.path.exists(file_name))
-        self.assertEqual("png", imghdr.what(file_name))
-        os.remove(file_name)
-
-    def test_plot_hyperplane_with_distribution(self):
-        plt.close()
-        # select a pure node
-        node = self._clf._tree_gr.get_down().get_up().get_up()
-        with warnings.catch_warnings():
-            warnings.simplefilter("ignore")
-            matplotlib.use("Agg")
-            num_figures_before = plt.gcf().number
-            node.plot_hyperplane(plot_distribution=True)
-            num_figures_after = plt.gcf().number
-        self.assertEqual(1, num_figures_after - num_figures_before)
-
-    def test_plot_hyperplane_without_distribution(self):
-        plt.close()
-        with warnings.catch_warnings():
-            warnings.simplefilter("ignore")
-            matplotlib.use("Agg")
-            num_figures_before = plt.gcf().number
-            self._clf._tree_gr.plot_hyperplane(plot_distribution=False)
-            num_figures_after = plt.gcf().number
-        self.assertEqual(1, num_figures_after - num_figures_before)
-
-    def test_plot_distribution(self):
-        plt.close()
-        with warnings.catch_warnings():
-            warnings.simplefilter("ignore")
-            matplotlib.use("Agg")
-            num_figures_before = plt.gcf().number
-            self._clf._tree_gr.plot_distribution()
-            num_figures_after = plt.gcf().number
-        self.assertEqual(1, num_figures_after - num_figures_before)
-
-    def test_set_axis_limits(self):
-        node = Snode_graph(Snode(None, None, None, "test"))
-        limits = (-2, 2), (-3, 3), (-4, 4)
-        node.set_axis_limits(limits)
-        computed = node.get_axis_limits()
-        x, y, z = limits
-        xx, yy, zz = computed
-        self.assertEqual(x, xx)
-        self.assertEqual(y, yy)
-        self.assertEqual(z, zz)
-
-    def test_cmap_change(self):
-        node = Snode_graph(Snode(None, None, None, "test"))
-        self.assertEqual("jet", node._get_cmap())
-        # make node pure
-        node._belief = 1.0
-        node._class = 1
-        self.assertEqual("jet_r", node._get_cmap())
--- a/stree/tests/Strees_test.py
+++ b/stree/tests/Strees_test.py
@@ -1,355 +0,0 @@
-import os
-import unittest
-
-import numpy as np
-from sklearn.datasets import make_classification, load_iris
-
-from stree import Stree, Snode
-
-
-def get_dataset(random_state=0, n_classes=2):
-    X, y = make_classification(
-        n_samples=1500,
-        n_features=3,
-        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
-
-
-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:
-            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
-        """
-        import warnings
-
-        warnings.filterwarnings("ignore")
-        for kernel in self._kernels:
-            clf = Stree(kernel=kernel, random_state=self._random_state)
-            clf.fit(*get_dataset(self._random_state))
-            self._check_tree(clf.tree_)
-
-    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 = get_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 = get_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_score(self):
-        X, y = get_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_single_vs_multiple_prediction(self):
-        """Check if predicting sample by sample gives the same result as
-        predicting all samples at once
-        """
-        X, y = get_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",
-            "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 = []
-        expected_string = ""
-        clf = Stree(kernel="linear", random_state=self._random_state)
-        clf.fit(*get_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))
-
-    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(*get_dataset(self._random_state))
-
-    def test_exception_if_bogus_split_criteria(self):
-        tclf = Stree(split_criteria="duck")
-        with self.assertRaises(ValueError):
-            tclf.fit(*get_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(*get_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(*get_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):
-        tcl_split = Stree(min_samples_split=3)
-        tcl_nosplit = Stree(min_samples_split=4)
-        dataset = [[1], [2], [3]], [1, 1, 0]
-        tcl_split.fit(*dataset)
-        self.assertIsNotNone(tcl_split.tree_.get_down())
-        self.assertIsNotNone(tcl_split.tree_.get_up())
-        tcl_nosplit.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": get_dataset(random_state=self._random_state, n_classes=3),
-            "Iris": load_iris(return_X_y=True),
-        }
-        outcomes = {
-            "Synt": {
-                "max_samples linear": 0.9533333333333334,
-                "max_samples rbf": 0.836,
-                "max_samples poly": 0.9473333333333334,
-                "min_distance linear": 0.9533333333333334,
-                "min_distance rbf": 0.836,
-                "min_distance poly": 0.9473333333333334,
-            },
-            "Iris": {
-                "max_samples linear": 0.98,
-                "max_samples rbf": 1.0,
-                "max_samples poly": 1.0,
-                "min_distance linear": 0.98,
-                "min_distance rbf": 1.0,
-                "min_distance poly": 1.0,
-            },
-        }
-        for name, dataset in datasets.items():
-            px, py = dataset
-            for criteria in ["max_samples", "min_distance"]:
-                for kernel in self._kernels:
-                    clf = Stree(
-                        C=1e4,
-                        max_iter=1e4,
-                        kernel=kernel,
-                        random_state=self._random_state,
-                    )
-                    clf.fit(px, py)
-                    outcome = outcomes[name][f"{criteria} {kernel}"]
-                    self.assertAlmostEqual(outcome, clf.score(px, py))
-
-
-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(*get_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:
-                try:
-                    belief = max_card / (max_card + min_card)
-                except ZeroDivisionError:
-                    belief = 0.0
-            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_)
-            if node.is_leaf():
-                return
-            run_tree(node.get_down())
-            run_tree(node.get_up())
-
-        run_tree(self._clf.tree_)
-
-    def test_make_predictor_on_leaf(self):
-        test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], "test")
-        test.make_predictor()
-        self.assertEqual(1, test._class)
-        self.assertEqual(0.75, test._belief)
-
-    def test_make_predictor_on_not_leaf(self):
-        test = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], "test")
-        test.set_up(Snode(None, [1], [1], "another_test"))
-        test.make_predictor()
-        self.assertIsNone(test._class)
-        self.assertEqual(0, test._belief)
-
-    def test_make_predictor_on_leaf_bogus_data(self):
-        test = Snode(None, [1, 2, 3, 4], [], "test")
-        test.make_predictor()
-        self.assertIsNone(test._class)
--- a/stree/tests/init.py
+++ b/stree/tests/init.py
@@ -1,9 +1,5 @@
-from .Strees_test import Stree_test, Snode_test
-from .Strees_grapher_test import Stree_grapher_test, Snode_graph_test
+from .Stree_test import Stree_test
+from .Snode_test import Snode_test
+from .Splitter_test import Splitter_test

-__all__ = [
-    "Stree_test",
-    "Snode_test",
-    "Stree_grapher_test",
-    "Snode_graph_test",
-]
+__all__ = ["Stree_test", "Snode_test", "Splitter_test"]
--- a/stree/tests/utils.py
+++ b/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
Author	SHA1	Message	Date
Ricardo Montañana	9cb69ebc75	Implement hyperparam. context based normalization	2021-04-15 02:13:30 +02:00
Ricardo Montañana	b55f59a3ec	Fix compute number of nodes	2021-04-13 22:31:05 +02:00
Ricardo Montañana	783d105099	Add another nodes, leaves test	2021-04-09 10:56:54 +02:00
Ricardo Montañana	c36f685263	Fix unintended nested if in partition	2021-04-08 08:27:31 +02:00
Ricardo Montañana	0f89b044f1	Refactor train method	2021-04-07 01:02:30 +02:00
Ricardo Montañana Gómez	6ba973dfe1	Add a method that return nodes and leaves (#27 ) (#30 ) Add a test Fix #27	2021-03-23 14:30:32 +01:00
Ricardo Montañana Gómez	460c63a6d0	Fix depth sometimes is wrong (#26 ) (#29 ) Add a test to the tests set Add depth to node description Fix iterator and str test due to this addon	2021-03-23 14:08:53 +01:00
Ricardo Montañana Gómez	f438124057	Fix mistakes (#24 ) (#28 ) Put pandas requirements in notebooks clean requirements.txt	2021-03-23 13:27:32 +01:00
Ricardo Montañana Gómez	147dad684c	Weight0samples error (#23 ) * Add Hyperparameters description to README Comment get_subspace method Add environment info for binder (runtime.txt) * Complete source comments Change docstring type to numpy update hyperameters table and explanation * Fix problem with zero weighted samples Solve WARNING: class label x specified in weight is not found with a different approach * Allow update of scikitlearn to latest version	2021-01-19 11:40:46 +01:00
Ricardo Montañana Gómez	3bdac9bd60	Complete source comments (#22 ) * Add Hyperparameters description to README Comment get_subspace method Add environment info for binder (runtime.txt) * Complete source comments Change docstring type to numpy update hyperameters table and explanation * Update Jupyter notebooks	2021-01-19 10:44:59 +01:00
Ricardo Montañana Gómez	e4ac5075e5	Add main workflow action (#20 ) * Add main workflow action * lock scikit-learn version to 0.23.2 * exchange codeship badge with githubs	2021-01-11 13:46:30 +01:00
Ricardo Montañana Gómez	36816074ff	Combinatorial explosion (#19 ) * Remove itertools combinations from subspaces * Generates 5 random subspaces at most	2021-01-10 13:32:22 +01:00
Ricardo Montañana	475ad7e752	Fix mistakes in function comments	2020-11-11 19:14:36 +01:00
Ricardo Montañana Gómez	1c869e154e	Enhance partition (#16 ) #15 Create impurity function in Stree (consistent name, same criteria as other splitter parameter) Create test for the new function Update init test Update test splitter parameters Rename old impurity function to partition_impurity close #15 * Complete implementation of splitter_type = impurity with tests Remove max_distance & min_distance splitter types * Fix mistake in computing multiclass node belief Set default criterion for split to entropy instead of gini Set default max_iter to 1e5 instead of 1e3 change up-down criterion to match SVC multiclass Fix impurity method of splitting nodes Update jupyter Notebooks	2020-11-03 11:36:05 +01:00
Ricardo Montañana	f5706c3159	Update version and notebooks	2020-06-28 10:44:29 +02:00
Ricardo Montañana	be552fdd6c	Add test for getting 3 feature_sets in Splitter Add ensemble notebook	2020-06-28 02:45:08 +02:00
Ricardo Montañana	5e3a8e3ec5	Change adaboost notebook	2020-06-27 23:34:15 +02:00
Ricardo Montañana	554ec03c32	Get only 3 sets for best split Fix flaky test in Splitter_test	2020-06-27 18:29:40 +02:00
Ricardo Montañana	4b7e4a3fb0	better solution to the sklearn bagging problem Add better tests enhance .coveragerc	2020-06-26 11:22:45 +02:00
Ricardo Montañana	76723993fd	Solve Warning class label not found when bagging	2020-06-25 13:07:50 +02:00
Ricardo Montañana	ecd0b86f4d	Solve the mistake of min and max distance The split criteria functions min and max distance return classes while max_samples return distances positives and negatives to hyperplane of the class with more samples in node	2020-06-17 00:13:52 +02:00
Ricardo Montañana	3e52a4746c	Fix entroy and information_gain functions	2020-06-16 13:56:02 +02:00
Ricardo Montañana Gómez	a20e45e8e7	Merge pull request #10 from Doctorado-ML/add_subspaces #2 Add subspaces	2020-06-15 11:30:53 +02:00
Ricardo Montañana	9334951d1b	#2 Cosmetic and style updates	2020-06-15 11:09:11 +02:00
Ricardo Montañana	736ab7ef20	#2 update benchmark notebook	2020-06-15 10:33:51 +02:00
Ricardo Montañana	c94bc068bd	#2 Refactor Stree & create Splitter Add and test splitter parameter	2020-06-15 00:22:57 +02:00
Ricardo Montañana	502ee72799	#2 Add predict and score support Add a test in features notebook Show max_features in main.py	2020-06-14 14:00:21 +02:00
Ricardo Montañana	f1ee4de37b	#2 - Add gini and entropy measures rename get_dataset to load_dataset add features and impurity to __str__ of node	2020-06-14 03:08:55 +02:00
Ricardo Montañana	ae1c199e21	# 2 - add max_features parameters	2020-06-13 17:58:45 +02:00
Ricardo Montañana	1bfe273a70	Fix problem in _min_distance Remove grapher (moved to another repo)	2020-06-12 00:50:25 +02:00
Ricardo Montañana Gómez	647d21bdb5	Merge pull request #9 from Doctorado-ML/add_multiclass #6 Add multiclass	2020-06-11 16:30:16 +02:00