{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Cross-validation using sklearn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.9853431 , 0.98533333, 0.974     , 0.96533333, 0.96      ,\n",
       "       0.97933333, 0.99      , 0.99333333, 1.        , 1.        ])"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Import the function for implementing cross validation\n",
    "from sklearn.model_selection import cross_val_score\n",
    "\n",
    "# Use that function to print the cross validation score for 10 folds\n",
    "cross_val_score(model,features,target,cv=10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Setting up GridSearch parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Generate values for maximum depth\n",
    "depth = [i for i in range(5,21,1)]\n",
    "\n",
    "# Generate values for minimum sample size\n",
    "samples = [i for i in range(50,500,50)]\n",
    "\n",
    "# Create the dictionary with parameters to be checked\n",
    "parameters = dict(max_depth=depth, min_samples_leaf=samples)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Implementing GridSearch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'max_depth': 5, 'min_samples_leaf': 50}\n"
     ]
    }
   ],
   "source": [
    "# import the GridSearchCV function\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "# set up parameters: done\n",
    "parameters = dict(max_depth=depth, min_samples_leaf=samples)\n",
    "\n",
    "# initialize the param_search function using the GridSearchCV function, initial model and parameters above\n",
    "param_search = GridSearchCV(model, parameters, cv = 3)\n",
    "\n",
    "# fit the param_search to the training dataset\n",
    "param_search.fit(features_train, target_train)\n",
    "\n",
    "# print the best parameters found\n",
    "print(param_search.best_params_)"
   ]
  }
 ],
 "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"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}