day-4-machine-learning-part-I/01 - Introduction to Scikit-learn.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Introduction to Scikit-learn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-07-03T13:43:59.300421Z",
     "start_time": "2019-07-03T13:43:58.842365Z"
    }
   },
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-07-03T13:44:01.152318Z",
     "start_time": "2019-07-03T13:44:00.389160Z"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.datasets import load_digits\n",
    "from sklearn.model_selection import train_test_split\n",
    "digits = load_digits()\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    digits.data, digits.target, random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-07-03T13:44:02.859902Z",
     "start_time": "2019-07-03T13:44:02.849867Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1347, 64)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-07-03T13:45:02.666371Z",
     "start_time": "2019-07-03T13:45:02.660535Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([141, 139, 133, 138, 143, 134, 129, 131, 126, 133])"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.bincount(y_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Really Simple API\n",
    "-------------------\n",
    "0) Import your model class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-07-03T13:45:08.321513Z",
     "start_time": "2019-07-03T13:45:08.173079Z"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.svm import LinearSVC"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1) Instantiate an object and set the parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-07-03T13:45:55.054291Z",
     "start_time": "2019-07-03T13:45:55.050028Z"
    }
   },
   "outputs": [],
   "source": [
    "svm = LinearSVC()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "2) Fit the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-07-03T13:46:06.155975Z",
     "start_time": "2019-07-03T13:46:06.041900Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/lgaalves/miniconda3/lib/python3.6/site-packages/sklearn/svm/base.py:931: ConvergenceWarning: Liblinear failed to converge, increase the number of iterations.\n",
      "  \"the number of iterations.\", ConvergenceWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "LinearSVC(C=1.0, class_weight=None, dual=True, fit_intercept=True,\n",
       "     intercept_scaling=1, loss='squared_hinge', max_iter=1000,\n",
       "     multi_class='ovr', penalty='l2', random_state=None, tol=0.0001,\n",
       "     verbose=0)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "svm.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "3) Apply / evaluate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-07-03T13:46:15.963016Z",
     "start_time": "2019-07-03T13:46:15.949172Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[2 9 9 ... 7 7 8]\n",
      "[2 8 9 ... 7 7 8]\n"
     ]
    }
   ],
   "source": [
    "print(svm.predict(X_train))\n",
    "print(y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-07-03T13:46:21.307158Z",
     "start_time": "2019-07-03T13:46:21.300009Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.994060876020787"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "svm.score(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-07-03T13:46:22.964592Z",
     "start_time": "2019-07-03T13:46:22.956700Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9355555555555556"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "svm.score(X_test, y_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "And again\n",
    "---------"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-07-03T13:47:26.465624Z",
     "start_time": "2019-07-03T13:47:26.359330Z"
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-07-03T13:47:29.997192Z",
     "start_time": "2019-07-03T13:47:29.993527Z"
    }
   },
   "outputs": [],
   "source": [
    "rf = RandomForestClassifier(n_estimators=50)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-07-03T13:47:30.895192Z",
     "start_time": "2019-07-03T13:47:30.760765Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
       "            max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
       "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "            min_samples_leaf=1, min_samples_split=2,\n",
       "            min_weight_fraction_leaf=0.0, n_estimators=50, n_jobs=None,\n",
       "            oob_score=False, random_state=None, verbose=0,\n",
       "            warm_start=False)"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rf.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-07-03T13:47:31.550535Z",
     "start_time": "2019-07-03T13:47:31.533217Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9822222222222222"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rf.score(X_test, y_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Exercises\n",
    "Load the iris dataset from the ``sklearn.datasets`` module using the ``load_iris`` function.\n",
    "\n",
    "Split it into training and test set using ``train_test_split``.\n",
    "\n",
    "\n",
    "Then train an evaluate a classifier of your choice. Try ``sklearn.neighbors.KNeighborsClassifier`` for example.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-07-03T13:52:22.435143Z",
     "start_time": "2019-07-03T13:52:22.428981Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "       0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
       "       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
       "       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X, y = iris.data, iris.target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-07-03T13:50:21.233303Z",
     "start_time": "2019-07-03T13:50:21.219773Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "test set score of knn: 0.973684\n"
     ]
    }
   ],
   "source": [
    "# %load solutions/train_iris.py\n",
    "from sklearn.datasets import load_iris\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "iris = load_iris()\n",
    "X, y = iris.data, iris.target\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y)\n",
    "\n",
    "knn = KNeighborsClassifier(n_neighbors=3)\n",
    "knn.fit(X_train, y_train)\n",
    "\n",
    "print(\"test set score of knn: %f\" % knn.score(X_test, y_test))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-07-03T13:50:13.940337Z",
     "start_time": "2019-07-03T13:50:13.855102Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.98"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "\n",
    "clf=KNeighborsClassifier()\n",
    "clf.fit(X_train, y_train)\n",
    "clf.score(X_test, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "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": "3.6.8"
  },
  "latex_envs": {
   "LaTeX_envs_menu_present": true,
   "autoclose": false,
   "autocomplete": true,
   "bibliofile": "biblio.bib",
   "cite_by": "apalike",
   "current_citInitial": 1,
   "eqLabelWithNumbers": true,
   "eqNumInitial": 1,
   "hotkeys": {
    "equation": "Ctrl-E",
    "itemize": "Ctrl-I"
   },
   "labels_anchors": false,
   "latex_user_defs": false,
   "report_style_numbering": false,
   "user_envs_cfg": false
  },
  "toc": {
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}