mlessentials/Lab08/Exercise8.02/Exercise_8_2.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1517,
     "status": "ok",
     "timestamp": 1596621730956,
     "user": {
      "displayName": "Mahesh Dhyani",
      "photoUrl": "",
      "userId": "02713575687182950579"
     },
     "user_tz": -330
    },
    "id": "kHxgHJ7M-USR"
   },
   "outputs": [],
   "source": [
    "from sklearn import datasets, svm, model_selection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 2142,
     "status": "ok",
     "timestamp": 1596621731595,
     "user": {
      "displayName": "Mahesh Dhyani",
      "photoUrl": "",
      "userId": "02713575687182950579"
     },
     "user_tz": -330
    },
    "id": "POj6Wyt9-jMf"
   },
   "outputs": [],
   "source": [
    "# load data\n",
    "digits = datasets.load_digits()\n",
    "\n",
    "# target\n",
    "y = digits.target\n",
    "\n",
    "# features\n",
    "X = digits.data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 2144,
     "status": "ok",
     "timestamp": 1596621731603,
     "user": {
      "displayName": "Mahesh Dhyani",
      "photoUrl": "",
      "userId": "02713575687182950579"
     },
     "user_tz": -330
    },
    "id": "REhQ33GDkyzP"
   },
   "outputs": [],
   "source": [
    "# support vector machine classifier\n",
    "clr = svm.SVC(gamma='scale')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 2129,
     "status": "ok",
     "timestamp": 1596621731604,
     "user": {
      "displayName": "Mahesh Dhyani",
      "photoUrl": "",
      "userId": "02713575687182950579"
     },
     "user_tz": -330
    },
    "id": "sqIcOIZLFQH3"
   },
   "outputs": [],
   "source": [
    "# hyperparameter grid. contains linear and polynomial kernels\n",
    "grid = [\n",
    "  {'kernel': ['linear']},\n",
    "  {'kernel': ['poly'], 'degree': [2, 3, 4]}\n",
    " ]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 2123,
     "status": "ok",
     "timestamp": 1596621731605,
     "user": {
      "displayName": "Mahesh Dhyani",
      "photoUrl": "",
      "userId": "02713575687182950579"
     },
     "user_tz": -330
    },
    "id": "_VVGUOSqLdRv"
   },
   "outputs": [],
   "source": [
    "# setting up the grid search to score on accuracy and evaluate over 10 folds\n",
    "cv_spec = model_selection.GridSearchCV(estimator=clr, param_grid=grid, scoring='accuracy', cv=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 230
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 4730,
     "status": "ok",
     "timestamp": 1596621734235,
     "user": {
      "displayName": "Mahesh Dhyani",
      "photoUrl": "",
      "userId": "02713575687182950579"
     },
     "user_tz": -330
    },
    "id": "YwxAHVSelu9X",
    "outputId": "59845557-6880-4ac6-871f-daa9979382f9"
   },
   "outputs": [],
   "source": [
    "# start the grid search\n",
    "cv_spec.fit(X, y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 55
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 4711,
     "status": "ok",
     "timestamp": 1596621734237,
     "user": {
      "displayName": "Mahesh Dhyani",
      "photoUrl": "",
      "userId": "02713575687182950579"
     },
     "user_tz": -330
    },
    "id": "llqjhh0SPGom",
    "outputId": "876c3251-dc52-4087-d47d-5420b5cf76ea"
   },
   "outputs": [],
   "source": [
    "# what is the available information\n",
    "print(cv_spec.cv_results_.keys())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 532
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 4691,
     "status": "ok",
     "timestamp": 1596621734238,
     "user": {
      "displayName": "Mahesh Dhyani",
      "photoUrl": "",
      "userId": "02713575687182950579"
     },
     "user_tz": -330
    },
    "id": "e9-x48AYQqBG",
    "outputId": "f1825539-978c-4d9f-c53e-17a33390d06a"
   },
   "outputs": [],
   "source": [
    "cv_spec.cv_results_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 106
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 4663,
     "status": "ok",
     "timestamp": 1596621734239,
     "user": {
      "displayName": "Mahesh Dhyani",
      "photoUrl": "",
      "userId": "02713575687182950579"
     },
     "user_tz": -330
    },
    "id": "YckzWb92QJt-",
    "outputId": "a65f7018-a780-4b1a-85a4-4b8d0a613505"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# convert the dictionary of results to a pandas dataframe\n",
    "results = pd.DataFrame(cv_spec.cv_results_)\n",
    "\n",
    "print(\n",
    "# show the hyperparameterizations\n",
    "results.loc[:,['params','mean_test_score']].sort_values('mean_test_score', ascending=False)\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 3684,
     "status": "ok",
     "timestamp": 1596621734240,
     "user": {
      "displayName": "Mahesh Dhyani",
      "photoUrl": "",
      "userId": "02713575687182950579"
     },
     "user_tz": -330
    },
    "id": "J941cuZKnhXO"
   },
   "outputs": [],
   "source": [
    "# visualize the result\n",
    "(\n",
    "    results.loc[:,['params','mean_test_score']]\n",
    "    .sort_values('mean_test_score', ascending=True)\n",
    "    .plot.barh(x='params', xlim=(0.8))\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Exercise_8_2.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": "3.8.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}