Show sample_weight use in test2 notebook

Update revision to RC4
Lint Stree grapher

README.md

@@ -2,7 +2,7 @@
 
 # Stree
 
-Oblique Tree classifier based on SVM nodes
+Oblique Tree classifier based on SVM nodes. The nodes are built and splitted with sklearn LinearSVC models.Stree is a sklearn estimator and can be integrated in pipelines, grid searches, etc.
 
 ![Stree](https://raw.github.com/doctorado-ml/stree/master/example.png)
 
@@ -18,15 +18,15 @@ pip install git+https://github.com/doctorado-ml/stree
 
 ##### Slow launch but better integration
 
-* [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/Doctorado-ML/STree/master?urlpath=lab/tree/test.ipynb) Test notebook
+* [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/Doctorado-ML/STree/master?urlpath=lab/tree/notebooks/test.ipynb) Test notebook
 
 ##### Fast launch but have to run first commented out cell for setup
 
-* [![Test](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/test.ipynb) Test notebook
+* [![Test](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/test.ipynb) Test notebook
 
-* [![Test2](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/test2.ipynb) Another Test notebook
+* [![Test2](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/test2.ipynb) Another Test notebook
 
-* [![Test Graphics](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/test_graphs.ipynb) Test Graphics notebook
+* [![Test Graphics](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/Doctorado-ML/STree/blob/master/notebooks/test_graphs.ipynb) Test Graphics notebook
 
 ### Command line
 

data/.gitignore

@@ -1 +0,0 @@
-*

notebooks/adaboost.ipynb

@@ -0,0 +1,190 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import time\n",
+    "from sklearn.ensemble import AdaBoostClassifier\n",
+    "from sklearn.tree import DecisionTreeClassifier\n",
+    "from sklearn.svm import LinearSVC\n",
+    "from sklearn.model_selection import GridSearchCV, train_test_split\n",
+    "from sklearn.datasets import load_iris\n",
+    "from stree import Stree"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "if not os.path.isfile('data/creditcard.csv'):\n",
+    "    !wget --no-check-certificate --content-disposition http://nube.jccm.es/index.php/s/Zs7SYtZQJ3RQ2H2/download\n",
+    "    !tar xzf creditcard.tgz"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": "Fraud: 0.244% 196\nValid: 99.755% 80234\nX.shape (1196, 28)  y.shape (1196,)\nFraud: 16.722% 200\nValid: 83.278% 996\n"
+    }
+   ],
+   "source": [
+    "random_state=1\n",
+    "\n",
+    "def load_creditcard(n_examples=0):\n",
+    "    import pandas as pd\n",
+    "    import numpy as np\n",
+    "    import random\n",
+    "    df = pd.read_csv('data/creditcard.csv')\n",
+    "    print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n",
+    "    print(\"Valid: {0:.3f}% {1}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))\n",
+    "    y = df.Class\n",
+    "    X = df.drop(['Class', 'Time', 'Amount'], axis=1).values\n",
+    "    if n_examples > 0:\n",
+    "        # Take first n_examples samples\n",
+    "        X = X[:n_examples, :]\n",
+    "        y = y[:n_examples, :]\n",
+    "    else:\n",
+    "        # Take all the positive samples with a number of random negatives\n",
+    "        if n_examples < 0:\n",
+    "            Xt = X[(y == 1).ravel()]\n",
+    "            yt = y[(y == 1).ravel()]\n",
+    "            indices = random.sample(range(X.shape[0]), -1 * n_examples)\n",
+    "            X = np.append(Xt, X[indices], axis=0)\n",
+    "            y = np.append(yt, y[indices], axis=0)\n",
+    "    print(\"X.shape\", X.shape, \" y.shape\", y.shape)\n",
+    "    print(\"Fraud: {0:.3f}% {1}\".format(len(y[y == 1])*100/X.shape[0], len(y[y == 1])))\n",
+    "    print(\"Valid: {0:.3f}% {1}\".format(len(y[y == 0]) * 100 / X.shape[0], len(y[y == 0])))\n",
+    "    Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state, stratify=y)\n",
+    "    return Xtrain, Xtest, ytrain, ytest\n",
+    "\n",
+    "data = load_creditcard(-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": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": "Score Train:  0.986857825567503\nScore Test:  0.9805013927576601\nTook 0.12 seconds\n"
+    }
+   ],
+   "source": [
+    "now = time.time()\n",
+    "clf = Stree(max_depth=3, random_state=random_state)\n",
+    "clf.fit(Xtrain, ytrain)\n",
+    "print(\"Score Train: \", clf.score(Xtrain, ytrain))\n",
+    "print(\"Score Test: \", clf.score(Xtest, ytest))\n",
+    "print(f\"Took {time.time() - now:.2f} seconds\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": "Score Train:  0.997610513739546\nScore Test:  0.9721448467966574\nTook 7.80 seconds\n"
+    }
+   ],
+   "source": [
+    "now = time.time()\n",
+    "clf2 = AdaBoostClassifier(Stree(max_depth=3, random_state=random_state), n_estimators=100, random_state=random_state)\n",
+    "clf2.fit(Xtrain, ytrain)\n",
+    "print(\"Score Train: \", clf2.score(Xtrain, ytrain))\n",
+    "print(\"Score Test: \", clf2.score(Xtest, ytest))\n",
+    "print(f\"Took {time.time() - now:.2f} seconds\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": "Score Train:  0.9796893667861409\nScore Test:  0.9554317548746518\nTook 0.48 seconds\n"
+    }
+   ],
+   "source": [
+    "now = time.time()\n",
+    "clf3 = AdaBoostClassifier(LinearSVC(random_state=random_state), n_estimators=100, random_state=random_state, algorithm='SAMME')\n",
+    "clf3.fit(Xtrain, ytrain)\n",
+    "print(\"Score Train: \", clf3.score(Xtrain, ytrain))\n",
+    "print(\"Score Test: \", clf3.score(Xtest, ytest))\n",
+    "print(f\"Took {time.time() - now:.2f} seconds\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": "Score Train:  1.0\nScore Test:  0.9721448467966574\nTook 0.86 seconds\n"
+    }
+   ],
+   "source": [
+    "now = time.time()\n",
+    "clf4 = AdaBoostClassifier(DecisionTreeClassifier(max_depth=1, random_state=random_state), n_estimators=100, random_state=random_state)\n",
+    "clf4.fit(Xtrain, ytrain)\n",
+    "print(\"Score Train: \", clf4.score(Xtrain, ytrain))\n",
+    "print(\"Score Test: \", clf4.score(Xtest, ytest))\n",
+    "print(f\"Took {time.time() - now:.2f} seconds\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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)"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

notebooks/crcard_graphs.ipynb

@@ -9,10 +9,7 @@
     "#\n",
     "# Google Colab setup\n",
     "#\n",
-    "#import os\n",
+    "#!pip install git+https://github.com/doctorado-ml/stree"
-    "#os.chdir(\"/content\")\n",
-    "#!git clone https://github.com/Doctorado-ML/STree.git\n",
-    "#os.chdir(\"/content/STree\")"
    ]
   },
   {

notebooks/test.ipynb

@@ -9,10 +9,7 @@
     "#\n",
     "# Google Colab setup\n",
     "#\n",
-    "#import os\n",
+    "#!pip install git+https://github.com/doctorado-ml/stree"
-    "#os.chdir(\"/content\")\n",
-    "#!git clone https://github.com/Doctorado-ML/STree.git\n",
-    "#os.chdir(\"/content/STree\")"
    ]
   },
   {

notebooks/test2.ipynb

@@ -0,0 +1,225 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#\n",
+    "# Google Colab setup\n",
+    "#\n",
+    "#!pip install git+https://github.com/doctorado-ml/stree"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from sklearn.svm import LinearSVC\n",
+    "from sklearn.tree import DecisionTreeClassifier\n",
+    "from sklearn.datasets import make_classification, load_iris, load_wine\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from stree import Stree\n",
+    "import time"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "if not os.path.isfile('data/creditcard.csv'):\n",
+    "    !wget --no-check-certificate --content-disposition http://nube.jccm.es/index.php/s/Zs7SYtZQJ3RQ2H2/download\n",
+    "    !tar xzf creditcard.tgz"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": "Fraud: 0.244% 196\nValid: 99.755% 80234\nX.shape (1196, 28)  y.shape (1196,)\nFraud: 16.472% 197\nValid: 83.528% 999\n"
+    }
+   ],
+   "source": [
+    "random_state=1\n",
+    "\n",
+    "def load_creditcard(n_examples=0):\n",
+    "    import pandas as pd\n",
+    "    import numpy as np\n",
+    "    import random\n",
+    "    df = pd.read_csv('data/creditcard.csv')\n",
+    "    print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n",
+    "    print(\"Valid: {0:.3f}% {1}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))\n",
+    "    y = df.Class\n",
+    "    X = df.drop(['Class', 'Time', 'Amount'], axis=1).values\n",
+    "    if n_examples > 0:\n",
+    "        # Take first n_examples samples\n",
+    "        X = X[:n_examples, :]\n",
+    "        y = y[:n_examples, :]\n",
+    "    else:\n",
+    "        # Take all the positive samples with a number of random negatives\n",
+    "        if n_examples < 0:\n",
+    "            Xt = X[(y == 1).ravel()]\n",
+    "            yt = y[(y == 1).ravel()]\n",
+    "            indices = random.sample(range(X.shape[0]), -1 * n_examples)\n",
+    "            X = np.append(Xt, X[indices], axis=0)\n",
+    "            y = np.append(yt, y[indices], axis=0)\n",
+    "    print(\"X.shape\", X.shape, \" y.shape\", y.shape)\n",
+    "    print(\"Fraud: {0:.3f}% {1}\".format(len(y[y == 1])*100/X.shape[0], len(y[y == 1])))\n",
+    "    print(\"Valid: {0:.3f}% {1}\".format(len(y[y == 0]) * 100 / X.shape[0], len(y[y == 0])))\n",
+    "    Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state, stratify=y)\n",
+    "    return Xtrain, Xtest, ytrain, ytest\n",
+    "\n",
+    "# data = load_creditcard(-5000) # Take all true samples + 5000 of the others\n",
+    "# data = load_creditcard(5000)  # Take the first 5000 samples\n",
+    "data = load_creditcard(-1000) # Take all the samples\n",
+    "\n",
+    "Xtrain = data[0]\n",
+    "Xtest = data[1]\n",
+    "ytrain = data[2]\n",
+    "ytest = data[3]\n",
+    "# Set weights inverse to its count class in dataset\n",
+    "weights = np.ones(Xtrain.shape[0],) * 1.00244\n",
+    "weights[ytrain==1] = 1.99755 "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": "Accuracy of Train without weights 0.996415770609319\nAccuracy of Train with    weights 0.994026284348865\nAccuracy of Tests without weights 0.9665738161559888\nAccuracy of Tests with    weights 0.9721448467966574\n"
+    }
+   ],
+   "source": [
+    "C = 23\n",
+    "print(\"Accuracy of Train without weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain).score(Xtrain, ytrain))\n",
+    "print(\"Accuracy of Train with    weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain, sample_weight=weights).score(Xtrain, ytrain))\n",
+    "print(\"Accuracy of Tests without weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain).score(Xtest, ytest))\n",
+    "print(\"Accuracy of Tests with    weights\", Stree(C=C, random_state=1).fit(Xtrain, ytrain, sample_weight=weights).score(Xtest, ytest))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": [
+     "outputPrepend"
+    ]
+   },
+   "outputs": [],
+   "source": [
+    "t = time.time()\n",
+    "for C in (.001, .01, 1, 5, 17):\n",
+    "    clf = Stree(C=C, random_state=random_state)\n",
+    "    clf.fit(Xtrain, ytrain)\n",
+    "    print(f\"************** C={C} ****************************\")\n",
+    "    print(f\"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}\")\n",
+    "    print(f\"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}\")\n",
+    "    print(clf)\n",
+    "    print(f\"**************************************************\")\n",
+    "print(f\"{time.time() - t:.4f} secs\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "from sklearn.svm import LinearSVC\n",
+    "from sklearn.calibration import CalibratedClassifierCV\n",
+    "scaler = StandardScaler()\n",
+    "cclf = CalibratedClassifierCV(base_estimator=LinearSVC(), cv=5)\n",
+    "cclf.fit(Xtrain, ytrain)\n",
+    "res = cclf.predict_proba(Xtest)\n",
+    "print(res[:4, :])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#check iterator\n",
+    "for i in list(clf):\n",
+    "    print(i)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#check iterator again\n",
+    "for i in clf:\n",
+    "    print(i)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Check if the classifier is a sklearn estimator\n",
+    "from sklearn.utils.estimator_checks import check_estimator\n",
+    "check_estimator(Stree())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Make checks one by one\n",
+    "c = 0\n",
+    "checks = check_estimator(Stree(), generate_only=True)\n",
+    "for check in checks:\n",
+    "    c += 1\n",
+    "    print(c, check[1])\n",
+    "    check[1](check[0])"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.7.6 64-bit ('general': venv)",
+   "language": "python",
+   "name": "python37664bitgeneralvenvfbd0a23e74cf4e778460f5ffc6761f39"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.6-final"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

notebooks/test_graphs.ipynb

@@ -0,0 +1,197 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#\n",
+    "# Google Colab setup\n",
+    "#\n",
+    "#!pip install git+https://github.com/doctorado-ml/stree"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "output_type": "error",
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'stree'",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-12-36af63297651>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdatasets\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mmake_blobs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msvm\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mLinearSVC\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 6\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mstree\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mStree\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mStree_grapher\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'stree'"
+     ]
+    }
+   ],
+   "source": [
+    "import time\n",
+    "import random\n",
+    "import numpy as np\n",
+    "from sklearn.datasets import make_blobs\n",
+    "from sklearn.svm import LinearSVC\n",
+    "from stree import Stree, Stree_grapher"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def build_data(random_state):\n",
+    "    random.seed(random_state)\n",
+    "    X, y = make_blobs(centers=10, n_features=3, n_samples=500, random_state=random_state)\n",
+    "    def make_binary(y):\n",
+    "        for i in range(2, 10):\n",
+    "            y[y==i] = random.randint(0, 1)\n",
+    "        return y\n",
+    "    y = make_binary(y)\n",
+    "    #print(X.shape, np.unique(y), y[y==0].shape, y[y==1].shape)\n",
+    "    return X, y"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "output_type": "error",
+     "ename": "NameError",
+     "evalue": "name 'Stree_grapher' is not defined",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-4-b909470cb406>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mbuild_data\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mgr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mStree_grapher\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mC\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m.01\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmax_iter\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m200\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m \u001b[0mgr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;31m#gr.save_all(save_folder='data/', save_prefix='7')\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mNameError\u001b[0m: name 'Stree_grapher' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "X, y = build_data(10)\n",
+    "gr = Stree_grapher(dict(C=.01, max_iter=200))\n",
+    "gr.fit(X, y)\n",
+    "#gr.save_all(save_folder='data/', save_prefix='7')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "output_type": "error",
+     "ename": "NameError",
+     "evalue": "name 'gr' is not defined",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-5-efa3db892bfd>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mgr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m: name 'gr' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "print(gr)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "output_type": "error",
+     "ename": "NameError",
+     "evalue": "name 'gr' is not defined",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-6-0e62f081c9aa>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mmatplotlib\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0mmatplotlib\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0muse\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Agg'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 3\u001b[0;31m \u001b[0mgr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msave_all\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msave_folder\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'data/'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m: name 'gr' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "import matplotlib\n",
+    "matplotlib.use('Agg')\n",
+    "gr.save_all(save_folder='data/')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "output_type": "error",
+     "ename": "NameError",
+     "evalue": "name 'gr' is not defined",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-7-b0484cfe9d26>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0;31m#%matplotlib inline\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0mget_ipython\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun_line_magic\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'matplotlib'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'widget'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0mgr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_tree_gr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mplot_hyperplane\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m: name 'gr' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "#Uncomment one of the following lines to display graphics: static(inline), dynamic(widget)\n",
+    "#%matplotlib inline\n",
+    "%matplotlib widget\n",
+    "gr._tree_gr.plot_hyperplane()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "output_type": "error",
+     "ename": "NameError",
+     "evalue": "name 'gr' is not defined",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-8-4277c1aacbe2>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[0mget_ipython\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun_line_magic\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'matplotlib'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'inline'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0;31m#%matplotlib widget\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0mgr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mplot_all\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m: name 'gr' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "#Uncomment one of the following lines to display graphics: static(inline), dynamic(widget)\n",
+    "%matplotlib inline\n",
+    "#%matplotlib widget\n",
+    "gr.plot_all()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.6-final"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

setup.py

@@ -1,8 +1,9 @@
 import setuptools
 
-__version__ = "0.9rc1"
+__version__ = "0.9rc4"
 __author__ = "Ricardo Montañana Gómez"
 
+
 def readme():
     with open('README.md') as f:
         return f.read()
@@ -12,14 +13,15 @@ setuptools.setup(
     name='STree',
     version=__version__,
     license='MIT License',
-    description='a python interface to oblique decision tree implementations',
+    description='Oblique decision tree with svm nodes',
     long_description=readme(),
     long_description_content_type='text/markdown',
     packages=setuptools.find_packages(),
     url='https://github.com/doctorado-ml/stree',
     author=__author__,
     author_email='ricardo.montanana@alu.uclm.es',
-    keywords='scikit-learn oblique-classifier oblique-decision-tree decision-tree svm svc',
+    keywords='scikit-learn oblique-classifier oblique-decision-tree decision-\
+    tree svm svc',
     classifiers=[
         'Development Status :: 4 - Beta',
         'License :: OSI Approved :: MIT License',
@@ -34,7 +36,6 @@ setuptools.setup(
         'matplotlib',
         'ipympl'
     ],
-    data_files=[('data', ['data/.gitignore'])],
     test_suite="stree.tests",
     zip_safe=False
 )

stree/Strees.py

@@ -7,21 +7,28 @@ Build an oblique tree classifier based on SVM Trees
 Uses LinearSVC
 '''
 
-import typing
 import os
 
 import numpy as np
 from sklearn.base import BaseEstimator, ClassifierMixin
 from sklearn.svm import LinearSVC
-from sklearn.utils.validation import check_X_y, check_array, check_is_fitted
+from sklearn.utils.multiclass import check_classification_targets
+from sklearn.utils.validation import check_X_y, check_array, check_is_fitted, \
+    _check_sample_weight
+
 
 class Snode:
-    def __init__(self, clf: LinearSVC, X: np.ndarray, y: np.ndarray, title: str):
+    """Nodes of the tree that keeps the svm classifier and if testing the
+    dataset assigned to it
+    """
+
+    def __init__(self, clf: LinearSVC, X: np.ndarray, y: np.ndarray,
+                 title: str):
         self._clf = clf
         self._vector = None if clf is None else clf.coef_
         self._interceptor = 0. if clf is None else clf.intercept_
         self._title = title
-        self._belief = 0.  # belief of the prediction in a leaf node based on samples
+        self._belief = 0.
         # Only store dataset in Testing
         self._X = X if os.environ.get('TESTING', 'NS') != 'NS' else None
         self._y = y
@@ -49,8 +56,8 @@ class Snode:
         return self._up
 
     def make_predictor(self):
-        """Compute the class of the predictor and its belief based on the subdataset of the node
+        """Compute the class of the predictor and its belief based on the
-        only if it is a leaf
+        subdataset of the node only if it is a leaf
         """
         if not self.is_leaf():
             return
@@ -60,7 +67,7 @@ class Snode:
             min_card = min(card)
             try:
                 self._belief = max_card / (max_card + min_card)
-            except:
+            except ZeroDivisionError:
                 self._belief = 0.
             self._class = classes[card == max_card][0]
         else:
@@ -69,7 +76,10 @@ class Snode:
 
     def __str__(self) -> str:
         if self.is_leaf():
-            return f"{self._title} - Leaf class={self._class} belief={self._belief:.6f} counts={np.unique(self._y, return_counts=True)}"
+            count_values = np.unique(self._y, return_counts=True)
+            result = f"{self._title} - Leaf class={self._class} belief="\
+                f"{self._belief: .6f} counts={count_values}"
+            return result
         else:
             return f"{self._title}"
 
@@ -97,67 +107,129 @@ class Siterator:
         self._push(node.get_down())
         return node
 
+
 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
+    inheriting from BaseEstimator implements get_params and set_params methods
+    inheriting from ClassifierMixin implement the attribute _estimator_type
+    with "classifier" as value
     """
 
-    def __init__(self, C: float = 1.0, max_iter: int = 1000, random_state: int = 0, use_predictions: bool = False):
+    def __init__(self, C: float = 1.0, max_iter: int = 1000,
-        self._max_iter = max_iter
+                 random_state: int = None, max_depth: int = None,
-        self._C = C
+                 tol: float = 1e-4, use_predictions: bool = False):
-        self._random_state = random_state
+        self.max_iter = max_iter
-        self._tree = None
+        self.C = C
-        self.__folder = 'data/'
+        self.random_state = random_state
-        self.__use_predictions = use_predictions
+        self.use_predictions = use_predictions
-        self.__trained = False
+        self.max_depth = max_depth
-        self.__proba = False
+        self.tol = tol
 
-    def get_params(self, deep=True):
+    def _more_tags(self) -> dict:
-        """Get dict with hyperparameters and its values to accomplish sklearn rules
+        """Required by sklearn to tell that this estimator is a binary classifier
-        """
-        return {"C": self._C, "random_state": self._random_state, 'max_iter': self._max_iter}
 
-    def set_params(self, **parameters):
+        :return: the tag required
-        """Set hyperparmeters as specified by sklearn, needed in Gridsearchs
+        :rtype: dict
         """
-        for parameter, value in parameters.items():
+        return {'binary_only': True, 'requires_y': True}
-            setattr(self, parameter, value)
-        return self
 
     def _linear_function(self, data: np.array, node: Snode) -> np.array:
+        """Compute the distance of set of samples to a hyperplane, in
+        multiclass classification it should compute the distance to a
+        hyperplane of each class
+
+        :param data: dataset of samples
+        :type data: np.array
+        :param node: the node that contains the hyperplance coefficients
+        :type node: Snode
+        :return: array of distances of each sample to the hyperplane
+        :rtype: np.array
+        """
         coef = node._vector[0, :].reshape(-1, data.shape[1])
         return data.dot(coef.T) + node._interceptor[0]
 
-    def _split_data(self, node: Snode, data: np.ndarray, indices: np.ndarray) -> list:
+    def _split_array(self, origin: np.array, down: np.array) -> list:
-        if self.__use_predictions:
+        """Split an array in two based on indices passed as down and its complement
-            yp = node._clf.predict(data)
+
-            down = (yp == 1).reshape(-1, 1)
+        :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[:, 0]] if any(up) else None, \
+            origin[down[:, 0]] 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
+        """
+        if self.use_predictions:
             res = np.expand_dims(node._clf.decision_function(data), 1)
         else:
-            # doesn't work with multiclass as each sample has to do inner product with its own coeficients
+            """doesn't work with multiclass as each sample has to do inner
-            # computes positition of every sample is w.r.t. the hyperplane
+            product with its own coefficients computes positition of every
+            sample is w.r.t. the hyperplane
+            """
             res = self._linear_function(data, node)
-            down = res > 0
+        return res
-        up = ~down
-        data_down = data[down[:, 0]] if any(down) else None
-        indices_down = indices[down[:, 0]] if any(down) else None
-        res_down = res[down[:, 0]] if any(down) else None
-        data_up = data[up[:, 0]] if any(up) else None
-        indices_up = indices[up[:, 0]] if any(up) else None
-        res_up = res[up[:, 0]] if any(up) else None
-        return [data_up, indices_up, data_down, indices_down, res_up, res_down]
 
-    def fit(self, X: np.ndarray, y: np.ndarray, title: str = 'root') -> 'Stree':
+    def _split_criteria(self, data: np.array) -> np.array:
-        X, y = check_X_y(X, y.ravel())
+        """Set the criteria to split arrays
+
+        :param data: [description]
+        :type data: np.array
+        :return: [description]
+        :rtype: np.array
+        """
+        return data > 0
+
+    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
+
+        :raises ValueError: if parameters C or max_depth are out of bounds
+        :return: itself to be able to chain actions: fit().predict() ...
+        :rtype: Stree
+        """
+        # Check parameters are Ok.
+        if type(y).__name__ == 'np.ndarray':
+            y = y.ravel()
+        if self.C < 0:
+            raise ValueError(
+                f"Penalty term must be positive... got (C={self.C:f})")
+        self.__max_depth = np.iinfo(
+            np.int32).max if self.max_depth is None else self.max_depth
+        if self.__max_depth < 1:
+            raise ValueError(
+                f"Maximum depth has to be greater than 1... got (max_depth=\
+                    {self.max_depth})")
+        check_classification_targets(y)
+        X, y = check_X_y(X, y)
+        sample_weight = _check_sample_weight(sample_weight, X)
+        check_classification_targets(y)
+        # Initialize computed parameters
+        self.classes_, y = np.unique(y, return_inverse=True)
+        self.n_iter_ = self.max_iter
+        self.depth_ = 0
         self.n_features_in_ = X.shape[1]
-        self._tree = self.train(X, y.ravel(), title)
+        self.tree_ = self.train(X, y, sample_weight, 1, 'root')
         self._build_predictor()
-        self.__trained = True
         return self
 
     def _build_predictor(self):
         """Process the leaves to make them predictors
         """
-
         def run_tree(node: Snode):
             if node.is_leaf():
                 node.make_predictor()
@@ -165,69 +237,121 @@ class Stree(BaseEstimator, ClassifierMixin):
             run_tree(node.get_down())
             run_tree(node.get_up())
 
-        run_tree(self._tree)
+        run_tree(self.tree_)
 
-    def train(self, X: np.ndarray, y: np.ndarray, title: str = 'root') -> Snode:
+    def train(self, X: np.ndarray, y: np.ndarray, sample_weight: np.ndarray,
+              depth: int, title: str) -> Snode:
+        """Recursive function to split the original dataset into predictor
+        nodes (leaves)
+
+        :param X: samples dataset
+        :type X: np.ndarray
+        :param y: samples labels
+        :type y: np.ndarray
+        :param sample_weight: weight of samples (used in boosting)
+        :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
+        """
+        if depth > self.__max_depth:
+            return None
         if np.unique(y).shape[0] == 1:
             # only 1 class => pure dataset
             return Snode(None, X, y, title + ', <pure>')
         # Train the model
-        clf = LinearSVC(max_iter=self._max_iter, C=self._C,
+        clf = LinearSVC(max_iter=self.max_iter, random_state=self.random_state,
-                        random_state=self._random_state)
+                        C=self.C)  # , sample_weight=sample_weight)
-        clf.fit(X, y)
+        clf.fit(X, y, sample_weight=sample_weight)
         tree = Snode(clf, X, y, title)
-        X_U, y_u, X_D, y_d, _, _ = self._split_data(tree, X, y)
+        self.depth_ = max(depth, self.depth_)
+        down = self._split_criteria(self._distances(tree, X))
+        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)
         if X_U is None or X_D is None:
             # didn't part anything
             return Snode(clf, X, y, title + ', <cgaf>')
-        tree.set_up(self.train(X_U, y_u, title + ' - Up'))
+        tree.set_up(self.train(X_U, y_u, sw_u, depth + 1, title + ' - Up'))
-        tree.set_down(self.train(X_D, y_d, title + ' - Down'))
+        tree.set_down(self.train(X_D, y_d, sw_d, depth + 1, title + ' - Down'))
         return tree
 
     def _reorder_results(self, y: np.array, indices: np.array) -> np.array:
-        y_ordered = np.zeros(y.shape, dtype=int if y.ndim == 1 else float)
+        """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
+        """
+        if y.ndim > 1 and y.shape[1] > 1:
+            # if predict_proba return np.array of floats
+            y_ordered = np.zeros(y.shape, dtype=float)
+        else:
+            # return array of same type given in y
+            y_ordered = y.copy()
         indices = indices.astype(int)
         for i, index in enumerate(indices):
             y_ordered[index] = y[i]
         return y_ordered
 
     def predict(self, X: np.array) -> np.array:
-        def predict_class(xp: np.array, indices: np.array, node: Snode) -> 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
+        """
+        def predict_class(xp: np.array, indices: np.array,
+                          node: Snode) -> np.array:
             if xp is None:
                 return [], []
             if node.is_leaf():
                 # set a class for every sample in dataset
                 prediction = np.full((xp.shape[0], 1), node._class)
                 return prediction, indices
-            u, i_u, d, i_d, _, _ = self._split_data(node, xp, indices)
+            down = self._split_criteria(self._distances(node, xp))
-            k, l = predict_class(d, i_d, node.get_down())
+            X_U, X_D = self._split_array(xp, down)
-            m, n = predict_class(u, i_u, node.get_up())
+            i_u, i_d = self._split_array(indices, down)
-            return np.append(k, m), np.append(l, n)
+            prx_u, prin_u = predict_class(X_U, i_u, node.get_up())
-
+            prx_d, prin_d = predict_class(X_D, i_d, node.get_down())
+            return np.append(prx_u, prx_d), np.append(prin_u, prin_d)
         # sklearn check
-        check_is_fitted(self)
+        check_is_fitted(self, ['tree_'])
         # Input validation
         X = check_array(X)
         # setup prediction & make it happen
         indices = np.arange(X.shape[0])
-        return self._reorder_results(*predict_class(X, indices, self._tree))
+        result = self._reorder_results(
+            *predict_class(X, indices, self.tree_)).astype(int).ravel()
+        return self.classes_[result]
 
     def predict_proba(self, X: np.array) -> np.array:
-        """Computes an approximation of the probability of samples belonging to class 1 
+        """Computes an approximation of the probability of samples belonging to
-        (nothing more, nothing less)
+        class 0 and 1
-
         :param X: dataset
         :type X: np.array
+        :return: array array of shape (m, num_classes), probability of being
+        each class
+        :rtype: np.array
         """
-
+        def predict_class(xp: np.array, indices: np.array, dist: np.array,
-        def predict_class(xp: np.array, indices: np.array, dist: np.array, node: Snode) -> np.array:
+                          node: Snode) -> np.array:
             """Run the tree to compute predictions
 
             :param xp: subdataset of samples
             :type xp: np.array
-            :param indices: indices of subdataset samples to rebuild original order
+            :param indices: indices of subdataset samples to rebuild original
+            order
             :type indices: np.array
-            :param dist: distances of every sample to the hyperplane or the father node
+            :param dist: distances of every sample to the hyperplane or the
+            father node
             :type dist: np.array
             :param node: node of the leaf with the class
             :type node: Snode
@@ -241,71 +365,68 @@ class Stree(BaseEstimator, ClassifierMixin):
                 prediction = np.full((xp.shape[0], 1), node._class)
                 prediction_proba = dist
                 return np.append(prediction, prediction_proba, axis=1), indices
-            u, i_u, d, i_d, r_u, r_d = self._split_data(node, xp, indices)
+            distances = self._distances(node, xp)
-            k, l = predict_class(d, i_d, r_d, node.get_down())
+            down = self._split_criteria(distances)
-            m, n = predict_class(u, i_u, r_u, node.get_up())
+            X_U, X_D = self._split_array(xp, down)
-            return np.append(k, m), np.append(l, n)
+            i_u, i_d = self._split_array(indices, down)
+            di_u, di_d = self._split_array(distances, down)
+            prx_u, prin_u = predict_class(X_U, i_u, di_u, node.get_up())
+            prx_d, prin_d = predict_class(X_D, i_d, di_d, node.get_down())
+            return np.append(prx_u, prx_d), np.append(prin_u, prin_d)
 
         # sklearn check
-        check_is_fitted(self)
+        check_is_fitted(self, ['tree_'])
         # Input validation
         X = check_array(X)
         # setup prediction & make it happen
         indices = np.arange(X.shape[0])
-        result, indices = predict_class(X, indices, [], self._tree)
+        empty_dist = np.empty((X.shape[0], 1), dtype=float)
+        result, indices = predict_class(X, indices, empty_dist, self.tree_)
         result = result.reshape(X.shape[0], 2)
-        # Turn distances to hyperplane into probabilities based on fitting distances
+        # Turn distances to hyperplane into probabilities based on fitting
-        # of samples to its hyperplane that classified them, to the sigmoid function
+        # distances of samples to its hyperplane that classified them, to the
+        # sigmoid function
+        # Probability of being 1
         result[:, 1] = 1 / (1 + np.exp(-result[:, 1]))
+        # Probability of being 0
+        result[:, 0] = 1 - result[:, 1]
         return self._reorder_results(result, indices)
 
     def score(self, X: np.array, y: np.array) -> float:
-        """Return accuracy
+        """Compute accuracy of the prediction
-        """
-        if not self.__trained:
-            self.fit(X, y)
-        yp = self.predict(X).reshape(y.shape)
-        right = (yp == y).astype(int)
-        return np.sum(right) / len(y)
 
-    def __iter__(self):
+        :param X: dataset of samples to make predictions
-        return Siterator(self._tree)
+        :type X: np.array
+        :param y: samples labels
+        :type y: np.array
+        :return: accuracy of the prediction
+        :rtype: float
+        """
+        # sklearn check
+        check_is_fitted(self)
+        yp = self.predict(X).reshape(y.shape)
+        return np.mean(yp == y)
+
+    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
+        """
+        try:
+            tree = self.tree_
+        except AttributeError:
+            tree = None
+        return Siterator(tree)
 
     def __str__(self) -> str:
+        """String representation of the tree
+
+        :return: description of nodes in the tree in preorder
+        :rtype: str
+        """
         output = ''
         for i in self:
             output += str(i) + '\n'
         return output
-
-    def _save_datasets(self, tree: Snode, catalog: typing.TextIO, number: int):
-        """Save the dataset of the node in a csv file
-
-        :param tree: node with data to save
-        :type tree: Snode
-        :param catalog: catalog file handler
-        :type catalog: typing.TextIO
-        :param number: sequential number for the generated file name
-        :type number: int
-        """
-        data = np.append(tree._X, tree._y.reshape(-1, 1), axis=1)
-        name = f"{self.__folder}dataset{number}.csv"
-        np.savetxt(name, data, delimiter=",")
-        catalog.write(f"{name}, - {str(tree)}")
-        if tree.is_leaf():
-            return
-        self._save_datasets(tree.get_down(), catalog, number + 1)
-        self._save_datasets(tree.get_up(), catalog, number + 2)
-
-    def get_catalog_name(self):
-        return self.__folder + "catalog.txt"
-
-    def save_sub_datasets(self):
-        """Save the every dataset stored in the tree to check with manual classifier
-        """
-        if not os.path.isdir(self.__folder):
-            os.mkdir(self.__folder)
-        with open(self.get_catalog_name(), 'w', encoding='utf-8') as catalog:
-            self._save_datasets(self._tree, catalog, 1)
-
-
-

stree/Strees_grapher.py

@@ -15,6 +15,7 @@ from mpl_toolkits.mplot3d import Axes3D
 
 from .Strees import Stree, Snode, Siterator
 
+
 class Snode_graph(Snode):
 
     def __init__(self, node: Stree):
@@ -45,7 +46,8 @@ class Snode_graph(Snode):
         ax.set_ylim(self._ylimits)
         ax.set_zlim(self._zlimits)
 
-    def save_hyperplane(self, save_folder: str = './', save_prefix: str = '', save_seq: int = 1):
+    def save_hyperplane(self, save_folder: str = './', save_prefix: str = '',
+                        save_seq: int = 1):
         _, fig = self.plot_hyperplane()
         name = f"{save_folder}{save_prefix}STnode{save_seq}.png"
         fig.savefig(name, bbox_inches='tight')
@@ -53,8 +55,7 @@ class Snode_graph(Snode):
 
     def _get_cmap(self):
         cmap = 'jet'
-        if self._is_pure():
+        if self._is_pure() and self._class == 1:
-            if self._class == 1:
             cmap = 'jet_r'
         return cmap
 
@@ -66,16 +67,20 @@ class Snode_graph(Snode):
         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
+            # Can't plot hyperplane of leaves with one label because it hasn't
+            # classiffier
             # get the splitting hyperplane
-            def hyperplane(x, y): return (-self._interceptor - self._vector[0][0] * x
+            def hyperplane(x, y): return (-self._interceptor
-                                          - self._vector[0][1] * y) / self._vector[0][2]
+                                          - self._vector[0][0] * x
+                                          - self._vector[0][1] * y) \
+                / self._vector[0][2]
 
             tmpx = np.linspace(self._X[:, 0].min(), self._X[:, 0].max())
             tmpy = np.linspace(self._X[:, 1].min(), self._X[:, 1].max())
             xx, yy = np.meshgrid(tmpx, tmpy)
-            ax.plot_surface(xx, yy, hyperplane(xx, yy), alpha=.5, antialiased=True,
+            ax.plot_surface(xx, yy, hyperplane(xx, yy), alpha=.5,
-                            rstride=1, cstride=1, cmap='seismic')
+                            antialiased=True, rstride=1, cstride=1,
+                            cmap='seismic')
             self._set_graphics_axis(ax)
         if plot_distribution:
             self.plot_distribution(ax)
@@ -97,6 +102,7 @@ class Snode_graph(Snode):
         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
@@ -114,7 +120,7 @@ class Stree_grapher(Stree):
     def __del__(self):
         try:
             os.environ.pop('TESTING')
-        except:
+        except KeyError:
             pass
         plt.close('all')
 
@@ -143,7 +149,7 @@ class Stree_grapher(Stree):
             self._pca = PCA(n_components=3)
             X = self._pca.fit_transform(X)
         res = super().fit(X, y)
-        self._tree_gr = self._copy_tree(self._tree)
+        self._tree_gr = self._copy_tree(self.tree_)
         self._fitted = True
         return res
 
@@ -164,6 +170,8 @@ class Stree_grapher(Stree):
         :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,
@@ -179,4 +187,3 @@ class Stree_grapher(Stree):
 
     def __iter__(self):
         return Siterator(self._tree_gr)
-

stree/tests/Strees_test.py

@@ -1,4 +1,3 @@
-import csv
 import os
 import unittest
 
@@ -22,18 +21,22 @@ class Stree_test(unittest.TestCase):
     def tearDownClass(cls):
         try:
             os.environ.pop('TESTING')
-        except:
+        except KeyError:
             pass
 
     def _get_Xy(self):
-        X, y = make_classification(n_samples=1500, n_features=3, n_informative=3,
+        X, y = make_classification(n_samples=1500, n_features=3,
-                                   n_redundant=0, n_repeated=0, n_classes=2, n_clusters_per_class=2,
+                                   n_informative=3, n_redundant=0,
-                                   class_sep=1.5, flip_y=0, weights=[0.5, 0.5], random_state=self._random_state)
+                                   n_repeated=0, n_classes=2,
+                                   n_clusters_per_class=2, class_sep=1.5,
+                                   flip_y=0, weights=[0.5, 0.5],
+                                   random_state=self._random_state)
         return X, y
 
     def _check_tree(self, node: Snode):
-        """Check recursively that the nodes that are not leaves have the correct 
+        """Check recursively that the nodes that are not leaves have the
-        number of labels and its sons have the right number of elements in their dataset
+        correct number of labels and its sons have the right number of elements
+        in their dataset
 
         Arguments:
             node {Snode} -- node to check
@@ -53,11 +56,11 @@ class Stree_test(unittest.TestCase):
         for i in unique_y:
             try:
                 number_down = count_d[i]
-            except:
+            except IndexError:
                 number_down = 0
             try:
                 number_up = count_u[i]
-            except:
+            except IndexError:
                 number_up = 0
             self.assertEqual(count_y[i], number_down + number_up)
         # Is the partition made the same as the prediction?
@@ -71,7 +74,7 @@ class Stree_test(unittest.TestCase):
     def test_build_tree(self):
         """Check if the tree is built the same way as predictions of models
         """
-        self._check_tree(self._clf._tree)
+        self._check_tree(self._clf.tree_)
 
     def _get_file_data(self, file_name: str) -> tuple:
         """Return X, y from data, y is the last column in array
@@ -89,7 +92,8 @@ class Stree_test(unittest.TestCase):
         fx = np.delete(data, column_y, axis=1)
         return fx, fy
 
-    def _find_out(self, px: np.array, x_original: np.array, y_original) -> list:
+    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:
@@ -107,18 +111,6 @@ class Stree_test(unittest.TestCase):
                     res.append(y_original[row])
         return res
 
-    def test_subdatasets(self):
-        """Check if the subdatasets files have the same labels as the original dataset
-        """
-        self._clf.save_sub_datasets()
-        with open(self._clf.get_catalog_name()) as cat_file:
-            catalog = csv.reader(cat_file, delimiter=',')
-            for row in catalog:
-                X, y = self._get_Xy()
-                x_file, y_file = self._get_file_data(row[0])
-                y_original = np.array(self._find_out(x_file, X, y), dtype=int)
-                self.assertTrue(np.array_equal(y_file, y_original))
-
     def test_single_prediction(self):
         X, y = self._get_Xy()
         yp = self._clf.predict((X[0, :].reshape(-1, X.shape[1])))
@@ -135,22 +127,25 @@ class Stree_test(unittest.TestCase):
         X, y = self._get_Xy()
         accuracy_score = self._clf.score(X, y)
         yp = self._clf.predict(X)
-        right = (yp == y).astype(int)
+        accuracy_computed = np.mean(yp == y)
-        accuracy_computed = sum(right) / len(y)
         self.assertEqual(accuracy_score, accuracy_computed)
-        self.assertGreater(accuracy_score, 0.8)
+        self.assertGreater(accuracy_score, 0.9)
 
     def test_single_predict_proba(self):
-        """Check that element 28 has a prediction different that the current label
+        """Check that element 28 has a prediction different that the current
+        label
         """
         # Element 28 has a different prediction than the truth
         decimals = 5
+        prob = 0.29026400766
         X, y = self._get_Xy()
         yp = self._clf.predict_proba(X[28, :].reshape(-1, X.shape[1]))
-        self.assertEqual(0, yp[0:, 0])
+        self.assertEqual(np.round(1 - prob, decimals),
+                         np.round(yp[0:, 0], decimals))
         self.assertEqual(1, y[28])
+
         self.assertAlmostEqual(
-            round(0.29026400766, decimals),
+            round(prob, decimals),
             round(yp[0, 1], decimals),
             decimals
         )
@@ -161,11 +156,16 @@ class Stree_test(unittest.TestCase):
         decimals = 5
         X, y = self._get_Xy()
         yp = self._clf.predict_proba(X[:num, :])
-        self.assertListEqual(y[:num].tolist(), yp[:, 0].tolist())
+        self.assertListEqual(
-        expected_proba = [0.88395641, 0.36746962, 0.84158767, 0.34106833, 0.14269291, 0.85193236,
+            y[:num].tolist(), np.argmax(yp[:num], axis=1).tolist())
-                          0.29876058, 0.7282164, 0.85958616, 0.89517877, 0.99745224, 0.18860349,
+        expected_proba = [0.88395641, 0.36746962, 0.84158767, 0.34106833,
-                          0.30756427, 0.8318412, 0.18981198, 0.15564624, 0.25740655, 0.22923355,
+                          0.14269291, 0.85193236,
-                          0.87365959, 0.49928689, 0.95574351, 0.28761257, 0.28906333, 0.32643692,
+                          0.29876058, 0.7282164, 0.85958616, 0.89517877,
+                          0.99745224, 0.18860349,
+                          0.30756427, 0.8318412, 0.18981198, 0.15564624,
+                          0.25740655, 0.22923355,
+                          0.87365959, 0.49928689, 0.95574351, 0.28761257,
+                          0.28906333, 0.32643692,
                           0.29788483, 0.01657364, 0.81149083]
         expected = np.round(expected_proba, decimals=decimals).tolist()
         computed = np.round(yp[:, 1], decimals=decimals).tolist()
@@ -173,9 +173,10 @@ class Stree_test(unittest.TestCase):
             self.assertAlmostEqual(expected[i], computed[i], decimals)
 
     def build_models(self):
-        """Build and train two models, model_clf will use the sklearn classifier to
+        """Build and train two models, model_clf will use the sklearn
-        compute predictions and split data. model_computed will use vector of
+        classifier to compute predictions and split data. model_computed will
-        coefficients to compute both predictions and splitted data
+        use vector of coefficients to compute both predictions and splitted
+        data
         """
         model_clf = Stree(random_state=self._random_state,
                           use_predictions=True)
@@ -187,8 +188,9 @@ class Stree_test(unittest.TestCase):
         return model_clf, model_computed, X, y
 
     def test_use_model_predict(self):
-        """Check that we get the same results wether we use the estimator in nodes
+        """Check that we get the same results wether we use the estimator in
-        to compute labels or we use the hyperplane and the position of samples wrt to it
+        nodes to compute labels or we use the hyperplane and the position of
+        samples wrt to it
         """
         use_clf, use_math, X, _ = self.build_models()
         self.assertListEqual(
@@ -213,14 +215,15 @@ class Stree_test(unittest.TestCase):
         )
 
     def test_single_vs_multiple_prediction(self):
-        """Check if predicting sample by sample gives the same result as predicting
+        """Check if predicting sample by sample gives the same result as
-        all samples at once
+        predicting all samples at once
         """
         X, _ = self._get_Xy()
         # Compute prediction line by line
         yp_line = np.array([], dtype=int)
         for xp in X:
-            yp_line = np.append(yp_line, self._clf.predict(xp.reshape(-1, X.shape[1])))
+            yp_line = np.append(yp_line, self._clf.predict(
+                xp.reshape(-1, X.shape[1])))
         # Compute prediction at once
         yp_once = self._clf.predict(X)
         #
@@ -232,17 +235,54 @@ class Stree_test(unittest.TestCase):
         expected = [
             'root',
             'root - Down',
-            'root - Down - Down, <cgaf> - Leaf class=1 belief=0.975989 counts=(array([0, 1]), array([ 17, 691]))',
+            '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 - Down, <cgaf> - Leaf class=1 belief= 0.750000 '
-            'root - Down - Up - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([7]))',
+            'counts=(array([0, 1]), array([1, 3]))',
-            'root - Up, <cgaf> - Leaf class=0 belief=0.928297 counts=(array([0, 1]), array([725,  56]))',
+            'root - Down - Up - Up, <pure> - Leaf class=0 belief= 1.000000 '
+            'counts=(array([0]), array([7]))',
+            'root - Up, <cgaf> - Leaf class=0 belief= 0.928297 counts=(array('
+            '[0, 1]), array([725,  56]))',
         ]
         computed = []
         for node in self._clf:
             computed.append(str(node))
         self.assertListEqual(expected, computed)
 
+    def test_is_a_sklearn_classifier(self):
+        import warnings
+        from sklearn.exceptions import ConvergenceWarning
+        warnings.filterwarnings('ignore', category=ConvergenceWarning)
+        warnings.filterwarnings('ignore', category=RuntimeWarning)
+        from sklearn.utils.estimator_checks import check_estimator
+        check_estimator(Stree())
+
+    def test_exception_if_C_is_negative(self):
+        tclf = Stree(C=-1)
+        with self.assertRaises(ValueError):
+            tclf.fit(*self._get_Xy())
+
+    def test_check_max_depth_is_positive_or_None(self):
+        tcl = Stree()
+        self.assertIsNone(tcl.max_depth)
+        tcl = Stree(max_depth=1)
+        self.assertGreaterEqual(1, tcl.max_depth)
+        with self.assertRaises(ValueError):
+            tcl = Stree(max_depth=-1)
+            tcl.fit(*self._get_Xy())
+
+    def test_check_max_depth(self):
+        depth = 3
+        tcl = Stree(random_state=self._random_state, max_depth=depth)
+        tcl.fit(*self._get_Xy())
+        self.assertEqual(depth, tcl.depth_)
+
+    def test_unfitted_tree_is_iterable(self):
+        tcl = Stree()
+        self.assertEqual(0, len(list(tcl)))
+
+
 class Snode_test(unittest.TestCase):
 
     def __init__(self, *args, **kwargs):
@@ -255,19 +295,24 @@ class Snode_test(unittest.TestCase):
 
     @classmethod
     def tearDownClass(cls):
+        """[summary]
+        """
         try:
             os.environ.pop('TESTING')
-        except:
+        except KeyError:
             pass
 
     def _get_Xy(self):
-        X, y = make_classification(n_samples=1500, n_features=3, n_informative=3,
+        X, y = make_classification(n_samples=1500, n_features=3,
-                                   n_redundant=0, n_repeated=0, n_classes=2, n_clusters_per_class=2,
+                                   n_informative=3, n_redundant=0, n_classes=2,
-                                   class_sep=1.5, flip_y=0, weights=[0.5, 0.5], random_state=self._random_state)
+                                   n_repeated=0, n_clusters_per_class=2,
+                                   class_sep=1.5, flip_y=0, weights=[0.5, 0.5],
+                                   random_state=self._random_state)
         return X, y
 
     def test_attributes_in_leaves(self):
-        """Check if the attributes in leaves have correct values so they form a predictor
+        """Check if the attributes in leaves have correct values so they form a
+        predictor
         """
 
         def check_leave(node: Snode):
@@ -282,7 +327,7 @@ class Snode_test(unittest.TestCase):
             if len(classes) > 1:
                 try:
                     belief = max_card / (max_card + min_card)
-                except:
+                except ZeroDivisionError:
                     belief = 0.
             else:
                 belief = 1
@@ -291,7 +336,7 @@ class Snode_test(unittest.TestCase):
             class_computed = classes[card == max_card]
             self.assertEqual(class_computed, node._class)
 
-        check_leave(self._clf._tree)
+        check_leave(self._clf.tree_)
 
     def test_nodes_coefs(self):
         """Check if the nodes of the tree have the right attributes filled
@@ -309,5 +354,4 @@ class Snode_test(unittest.TestCase):
             run_tree(node.get_down())
             run_tree(node.get_up())
 
-        run_tree(self._clf._tree)
+        run_tree(self._clf.tree_)
-

test2.ipynb

@@ -1,194 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#\n",
-    "# Google Colab setup\n",
-    "#\n",
-    "#import os\n",
-    "#os.chdir(\"/content\")\n",
-    "#!git clone https://github.com/Doctorado-ML/STree.git\n",
-    "#os.chdir(\"/content/STree\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "import pandas as pd\n",
-    "from sklearn.svm import LinearSVC\n",
-    "from sklearn.tree import DecisionTreeClassifier\n",
-    "from sklearn.datasets import make_classification, load_iris, load_wine\n",
-    "from sklearn.model_selection import train_test_split\n",
-    "from stree import Stree\n",
-    "import time"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "if not os.path.isfile('data/creditcard.csv'):\n",
-    "    !wget --no-check-certificate --content-disposition http://nube.jccm.es/index.php/s/Zs7SYtZQJ3RQ2H2/download\n",
-    "    !tar xzf creditcard.tgz"
-   ]
-  },
-  {
-   "cell_type": "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"
-    }
-   ],
-   "source": [
-    "random_state=1\n",
-    "\n",
-    "def load_creditcard(n_examples=0):\n",
-    "    import pandas as pd\n",
-    "    import numpy as np\n",
-    "    import random\n",
-    "    df = pd.read_csv('data/creditcard.csv')\n",
-    "    print(\"Fraud: {0:.3f}% {1}\".format(df.Class[df.Class == 1].count()*100/df.shape[0], df.Class[df.Class == 1].count()))\n",
-    "    print(\"Valid: {0:.3f}% {1}\".format(df.Class[df.Class == 0].count()*100/df.shape[0], df.Class[df.Class == 0].count()))\n",
-    "    y = df.Class\n",
-    "    X = df.drop(['Class', 'Time', 'Amount'], axis=1).values\n",
-    "    if n_examples > 0:\n",
-    "        # Take first n_examples samples\n",
-    "        X = X[:n_examples, :]\n",
-    "        y = y[:n_examples, :]\n",
-    "    else:\n",
-    "        # Take all the positive samples with a number of random negatives\n",
-    "        if n_examples < 0:\n",
-    "            Xt = X[(y == 1).ravel()]\n",
-    "            yt = y[(y == 1).ravel()]\n",
-    "            indices = random.sample(range(X.shape[0]), -1 * n_examples)\n",
-    "            X = np.append(Xt, X[indices], axis=0)\n",
-    "            y = np.append(yt, y[indices], axis=0)\n",
-    "    print(\"X.shape\", X.shape, \" y.shape\", y.shape)\n",
-    "    print(\"Fraud: {0:.3f}% {1}\".format(len(y[y == 1])*100/X.shape[0], len(y[y == 1])))\n",
-    "    print(\"Valid: {0:.3f}% {1}\".format(len(y[y == 0]) * 100 / X.shape[0], len(y[y == 0])))\n",
-    "    Xtrain, Xtest, ytrain, ytest = train_test_split(X, y, train_size=0.7, shuffle=True, random_state=random_state, stratify=y)\n",
-    "    return Xtrain, Xtest, ytrain, ytest\n",
-    "\n",
-    "# data = load_creditcard(-5000) # Take all true samples + 5000 of the others\n",
-    "# data = load_creditcard(5000)  # Take the first 5000 samples\n",
-    "data = load_creditcard(-1000) # Take all the samples\n",
-    "\n",
-    "Xtrain = data[0]\n",
-    "Xtest = data[1]\n",
-    "ytrain = data[2]\n",
-    "ytest = data[3]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "output_type": "stream",
-     "name": "stdout",
-     "text": "************** C=0.001 ****************************\nClassifier's accuracy (train): 0.9521\nClassifier's accuracy (test) : 0.9598\nroot\nroot - Down, <cgaf> - Leaf class=1 belief=0.980519 counts=(array([0, 1]), array([  6, 302]))\nroot - Up, <cgaf> - Leaf class=0 belief=0.940217 counts=(array([0, 1]), array([692,  44]))\n\n**************************************************\n************** C=0.01 ****************************\nClassifier's accuracy (train): 0.9521\nClassifier's accuracy (test) : 0.9643\nroot\nroot - Down\nroot - Down - Down, <cgaf> - Leaf class=1 belief=0.986842 counts=(array([0, 1]), array([  4, 300]))\nroot - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([1]))\nroot - Up, <cgaf> - Leaf class=0 belief=0.937754 counts=(array([0, 1]), array([693,  46]))\n\n**************************************************\n************** C=1 ****************************\nClassifier's accuracy (train): 0.9636\nClassifier's accuracy (test) : 0.9688\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([308]))\nroot - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([8]))\nroot - Up, <cgaf> - Leaf class=0 belief=0.947802 counts=(array([0, 1]), array([690,  38]))\n\n**************************************************\n************** C=5 ****************************\nClassifier's accuracy (train): 0.9665\nClassifier's accuracy (test) : 0.9621\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([308]))\nroot - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([11]))\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([1]))\nroot - Up - Up\nroot - Up - Up - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up\nroot - Up - Up - Up - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief=0.951456 counts=(array([0, 1]), array([686,  35]))\n\n**************************************************\n************** C=17 ****************************\nClassifier's accuracy (train): 0.9741\nClassifier's accuracy (test) : 0.9576\nroot\nroot - Down\nroot - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([306]))\nroot - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([10]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([3]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([2]))\nroot - Up - Up\nroot - Up - Up - Down\nroot - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([3]))\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([2]))\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([1]))\nroot - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([7]))\nroot - Up - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([4]))\nroot - Up - Up - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief=0.961538 counts=(array([0, 1]), array([675,  27]))\n\n**************************************************\n0.7816 secs\n"
-    }
-   ],
-   "source": [
-    "t = time.time()\n",
-    "for C in (.001, .01, 1, 5, 17):\n",
-    "    clf = Stree(C=C, random_state=random_state)\n",
-    "    clf.fit(Xtrain, ytrain)\n",
-    "    print(f\"************** C={C} ****************************\")\n",
-    "    print(f\"Classifier's accuracy (train): {clf.score(Xtrain, ytrain):.4f}\")\n",
-    "    print(f\"Classifier's accuracy (test) : {clf.score(Xtest, ytest):.4f}\")\n",
-    "    print(clf)\n",
-    "    print(f\"**************************************************\")\n",
-    "print(f\"{time.time() - t:.4f} secs\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "from sklearn.preprocessing import StandardScaler\n",
-    "from sklearn.svm import LinearSVC\n",
-    "from sklearn.calibration import CalibratedClassifierCV\n",
-    "scaler = StandardScaler()\n",
-    "cclf = CalibratedClassifierCV(base_estimator=LinearSVC(), cv=5)\n",
-    "cclf.fit(Xtrain, ytrain)\n",
-    "res = cclf.predict_proba(Xtest)\n",
-    "#an array containing probabilities of belonging to the 1st class"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "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([306]))\nroot - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([10]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([3]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([2]))\nroot - Up - Up\nroot - Up - Up - Down\nroot - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([3]))\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([2]))\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([1]))\nroot - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([7]))\nroot - Up - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([4]))\nroot - Up - Up - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief=0.961538 counts=(array([0, 1]), array([675,  27]))\n"
-    }
-   ],
-   "source": [
-    "#check iterator\n",
-    "for i in list(clf):\n",
-    "    print(i)"
-   ]
-  },
-  {
-   "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([306]))\nroot - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([10]))\nroot - Up\nroot - Up - Down\nroot - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([3]))\nroot - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([2]))\nroot - Up - Up\nroot - Up - Up - Down\nroot - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([1]))\nroot - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([3]))\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([2]))\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([1]))\nroot - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([2]))\nroot - Up - Up - Up - Up - Up\nroot - Up - Up - Up - Up - Up - Down\nroot - Up - Up - Up - Up - Up - Down - Down, <pure> - Leaf class=1 belief=1.000000 counts=(array([1]), array([7]))\nroot - Up - Up - Up - Up - Up - Down - Up, <pure> - Leaf class=0 belief=1.000000 counts=(array([0]), array([4]))\nroot - Up - Up - Up - Up - Up - Up, <cgaf> - Leaf class=0 belief=0.961538 counts=(array([0, 1]), array([675,  27]))\n"
-    }
-   ],
-   "source": [
-    "#check iterator again\n",
-    "for i in clf:\n",
-    "    print(i)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.6-final"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}