{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-09-01T03:38:26.157140Z",
     "start_time": "2019-09-01T03:38:26.142762Z"
    }
   },
   "outputs": [],
   "source": [
    "#!/usr/bin/python\n",
    "\n",
    "\n",
    "\"\"\"\n",
    "    Starter code for the validation mini-project.\n",
    "    The first step toward building your POI identifier!\n",
    "\n",
    "    Start by loading/formatting the data\n",
    "\n",
    "    After that, it's not our code anymore--it's yours!\n",
    "\"\"\"\n",
    "\n",
    "import pickle\n",
    "import sys\n",
    "sys.path.append(\"../tools/\")\n",
    "from feature_format import featureFormat, targetFeatureSplit\n",
    "\n",
    "data_dict = pickle.load(open(\"../final_project/final_project_dataset.pkl\", \"rb\") )\n",
    "\n",
    "### first element is our labels, any added elements are predictor\n",
    "### features. Keep this the same for the mini-project, but you'll\n",
    "### have a different feature list when you do the final project.\n",
    "features_list = [\"poi\", \"salary\"]\n",
    "\n",
    "data = featureFormat(data_dict, features_list, sort_keys = '../tools/python2_lesson13_keys.pkl')\n",
    "labels, features = targetFeatureSplit(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-09-01T03:47:44.785291Z",
     "start_time": "2019-09-01T03:47:44.777944Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "95"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-09-01T03:58:48.227230Z",
     "start_time": "2019-09-01T03:58:48.210049Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=None,\n",
       "                       max_features=None, 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, presort=False,\n",
       "                       random_state=None, splitter='best')"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "### it's all yours from here forward! \n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "from sklearn.decomposition import PCA\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "\n",
    "features_train, features_test, labels_train, labels_test = train_test_split(features, labels, test_size = 0.3, random_state = 42)\n",
    "\n",
    "clf = DecisionTreeClassifier()\n",
    "clf.fit(features_train, labels_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2019-09-01T03:58:50.429390Z",
     "start_time": "2019-09-01T03:58:50.421893Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7241379310344828"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clf.score(features_test, labels_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.3"
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}