{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "%matplotlib inline"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "\n# Default DL85Classifier\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "collapsed": false
      },
      "outputs": [],
      "source": [
        "import numpy as np\nfrom sklearn.metrics import confusion_matrix\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import accuracy_score, make_scorer\nfrom sklearn.model_selection import KFold\nfrom sklearn.model_selection import cross_val_score\nimport time\nfrom dl85 import DL85Classifier\n\ndataset = np.genfromtxt(\"../datasets/anneal.txt\", delimiter=' ')\nX, y = dataset[:, 1:], dataset[:, 0]\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)\n\n\nprint(\"######################################################################\\n\"\n      \"#                      DL8.5 default classifier                      #\\n\"\n      \"######################################################################\")\nclf = DL85Classifier(max_depth=2)\nstart = time.perf_counter()\nprint(\"Model building...\")\nclf.fit(X, y)\nduration = time.perf_counter() - start\nprint(\"Model built. Duration of building =\", round(duration, 4))\ny_pred = clf.predict(X_test)\nprint(\"Confusion Matrix below\")\nprint(confusion_matrix(y_test, y_pred))\nprint(\"Accuracy DL8.5 on training set =\", round(clf.accuracy_, 4))\nprint(\"Accuracy DL8.5 on test set =\", round(accuracy_score(y_test, y_pred), 4), \"\\n\\n\\n\")\n\n\nprint(\"##############################################################\\n\"\n      \"#     DL8.5 classifier : Manual cross-validation (5-fold)    #\\n\"\n      \"##############################################################\")\nkf = KFold(n_splits=5, random_state=42, shuffle=True)\ntraining_accuracies = []\ntest_accuracies = []\nstart = time.perf_counter()\nprint(\"Model building...\")\nfor train_index, test_index in kf.split(X):\n    data_train = X[train_index]\n    target_train = y[train_index]\n    data_test = X[test_index]\n    target_test = y[test_index]\n    clf = DL85Classifier(max_depth=2)\n    clf.fit(data_train, target_train)\n    preds = clf.predict(data_test)\n    training_accuracies.append(clf.accuracy_)\n    test_accuracies.append(accuracy_score(target_test, preds))\nduration = time.perf_counter() - start\nprint(\"Model built. Duration of building =\", round(duration, 4))\nprint(\"Average accuracy on training set =\", round(np.mean(training_accuracies), 4))\nprint(\"Average accuracy on test set =\", round(np.mean(test_accuracies), 4), \"\\n\\n\\n\")\n\n\nprint(\"##############################################################\\n\"\n      \"#   DL8.5 classifier : Automatic cross-validation (5-fold)   #\\n\"\n      \"##############################################################\")\nclf = DL85Classifier(max_depth=2)\nstart = time.perf_counter()\nprint(\"Model building...\")\nscores = cross_val_score(clf, X, y, cv=5)\nduration = time.perf_counter() - start\nprint(\"Model built. Duration of building =\", round(duration, 4))\nprint(\"Average accuracy on test set =\", round(np.mean(scores), 4))"
      ]
    }
  ],
  "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": "3.8.6"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}