Model_Training.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 110,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.model_selection import train_test_split\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "outputs": [
    {
     "data": {
      "text/plain": "   id  A1_Score  A2_Score  A3_Score  A4_Score  A5_Score  A6_Score  A7_Score  \\\n0   1         1         1         1         1         0         0         1   \n1   2         1         1         0         1         0         0         0   \n2   3         1         1         0         1         1         0         1   \n3   4         1         1         0         1         0         0         1   \n4   5         1         0         0         0         0         0         0   \n\n   A8_Score  A9_Score  ...  gender       ethnicity jundice austim  \\\n0         1         0  ...       f  White-European      no     no   \n1         1         0  ...       m          Latino      no    yes   \n2         1         1  ...       m          Latino     yes    yes   \n3         1         0  ...       f  White-European      no    yes   \n4         1         0  ...       f               ?      no     no   \n\n   contry_of_res used_app_before result    age_desc  relation Class/ASD  \n0  United States              no      6  4-11 years      Self        NO  \n1         Brazil              no      5  4-11 years      Self        NO  \n2          Spain              no      8  4-11 years    Parent       YES  \n3  United States              no      6  4-11 years      Self        NO  \n4          Egypt              no      2  4-11 years         ?        NO  \n\n[5 rows x 22 columns]",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>id</th>\n      <th>A1_Score</th>\n      <th>A2_Score</th>\n      <th>A3_Score</th>\n      <th>A4_Score</th>\n      <th>A5_Score</th>\n      <th>A6_Score</th>\n      <th>A7_Score</th>\n      <th>A8_Score</th>\n      <th>A9_Score</th>\n      <th>...</th>\n      <th>gender</th>\n      <th>ethnicity</th>\n      <th>jundice</th>\n      <th>austim</th>\n      <th>contry_of_res</th>\n      <th>used_app_before</th>\n      <th>result</th>\n      <th>age_desc</th>\n      <th>relation</th>\n      <th>Class/ASD</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>...</td>\n      <td>f</td>\n      <td>White-European</td>\n      <td>no</td>\n      <td>no</td>\n      <td>United States</td>\n      <td>no</td>\n      <td>6</td>\n      <td>4-11 years</td>\n      <td>Self</td>\n      <td>NO</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>2</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>...</td>\n      <td>m</td>\n      <td>Latino</td>\n      <td>no</td>\n      <td>yes</td>\n      <td>Brazil</td>\n      <td>no</td>\n      <td>5</td>\n      <td>4-11 years</td>\n      <td>Self</td>\n      <td>NO</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>3</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>...</td>\n      <td>m</td>\n      <td>Latino</td>\n      <td>yes</td>\n      <td>yes</td>\n      <td>Spain</td>\n      <td>no</td>\n      <td>8</td>\n      <td>4-11 years</td>\n      <td>Parent</td>\n      <td>YES</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>4</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>...</td>\n      <td>f</td>\n      <td>White-European</td>\n      <td>no</td>\n      <td>yes</td>\n      <td>United States</td>\n      <td>no</td>\n      <td>6</td>\n      <td>4-11 years</td>\n      <td>Self</td>\n      <td>NO</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>5</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>...</td>\n      <td>f</td>\n      <td>?</td>\n      <td>no</td>\n      <td>no</td>\n      <td>Egypt</td>\n      <td>no</td>\n      <td>2</td>\n      <td>4-11 years</td>\n      <td>?</td>\n      <td>NO</td>\n    </tr>\n  </tbody>\n</table>\n<p>5 rows × 22 columns</p>\n</div>"
     },
     "execution_count": 111,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rawdf = pd.read_csv(\"csv_result-Autism-Child-Data.csv\") # This dataset is for child\n",
    "rawdf.head()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "### Data cleaning"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "outputs": [
    {
     "data": {
      "text/plain": "     A1_Score  A2_Score  A3_Score  A4_Score  A5_Score  A6_Score  A7_Score  \\\n0           1         1         1         1         0         0         1   \n1           1         1         0         1         0         0         0   \n2           1         1         0         1         1         0         1   \n3           1         1         0         1         0         0         1   \n4           1         0         0         0         0         0         0   \n..        ...       ...       ...       ...       ...       ...       ...   \n699         0         1         0         1         1         0         1   \n700         1         0         0         0         0         0         0   \n701         1         0         1         1         1         0         1   \n702         1         0         0         1         1         0         1   \n703         1         0         1         1         1         0         1   \n\n     A8_Score  A9_Score  A10_Score age gender jundice  result austim  \n0           1         0          0   5      f      no       6     no  \n1           1         0          1   5      m      no       5    yes  \n2           1         1          1   5      m     yes       8    yes  \n3           1         0          1   7      f      no       6    yes  \n4           1         0          0   7      f      no       2     no  \n..        ...       ...        ...  ..    ...     ...     ...    ...  \n699         1         1          1   5      f      no       7     no  \n700         1         0          1   7      m      no       3     no  \n701         1         0          1   5      f      no       7     no  \n702         0         1          1   7      m      no       6     no  \n703         1         1          1   5      f      no       8     no  \n\n[704 rows x 15 columns]",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>A1_Score</th>\n      <th>A2_Score</th>\n      <th>A3_Score</th>\n      <th>A4_Score</th>\n      <th>A5_Score</th>\n      <th>A6_Score</th>\n      <th>A7_Score</th>\n      <th>A8_Score</th>\n      <th>A9_Score</th>\n      <th>A10_Score</th>\n      <th>age</th>\n      <th>gender</th>\n      <th>jundice</th>\n      <th>result</th>\n      <th>austim</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>5</td>\n      <td>f</td>\n      <td>no</td>\n      <td>6</td>\n      <td>no</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>5</td>\n      <td>m</td>\n      <td>no</td>\n      <td>5</td>\n      <td>yes</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>5</td>\n      <td>m</td>\n      <td>yes</td>\n      <td>8</td>\n      <td>yes</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>7</td>\n      <td>f</td>\n      <td>no</td>\n      <td>6</td>\n      <td>yes</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>7</td>\n      <td>f</td>\n      <td>no</td>\n      <td>2</td>\n      <td>no</td>\n    </tr>\n    <tr>\n      <th>...</th>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n      <td>...</td>\n    </tr>\n    <tr>\n      <th>699</th>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>5</td>\n      <td>f</td>\n      <td>no</td>\n      <td>7</td>\n      <td>no</td>\n    </tr>\n    <tr>\n      <th>700</th>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>7</td>\n      <td>m</td>\n      <td>no</td>\n      <td>3</td>\n      <td>no</td>\n    </tr>\n    <tr>\n      <th>701</th>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>5</td>\n      <td>f</td>\n      <td>no</td>\n      <td>7</td>\n      <td>no</td>\n    </tr>\n    <tr>\n      <th>702</th>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>7</td>\n      <td>m</td>\n      <td>no</td>\n      <td>6</td>\n      <td>no</td>\n    </tr>\n    <tr>\n      <th>703</th>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>5</td>\n      <td>f</td>\n      <td>no</td>\n      <td>8</td>\n      <td>no</td>\n    </tr>\n  </tbody>\n</table>\n<p>704 rows × 15 columns</p>\n</div>"
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = rawdf[[\"A1_Score\",\"A2_Score\",\"A3_Score\",\"A4_Score\",\"A5_Score\",\"A6_Score\",\"A7_Score\",\"A8_Score\",\"A9_Score\",\"A10_Score\",\"age\",\"gender\",\"jundice\",\"result\",\"austim\"]]\n",
    "df"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "outputs": [
    {
     "data": {
      "text/plain": "   A1_Score  A2_Score  A3_Score  A4_Score  A5_Score  A6_Score  A7_Score  \\\n0         1         1         1         1         0         0         1   \n1         1         1         0         1         0         0         0   \n2         1         1         0         1         1         0         1   \n3         1         1         0         1         0         0         1   \n4         1         0         0         0         0         0         0   \n\n   A8_Score  A9_Score  A10_Score  age gender jundice  result austim  \n0         1         0          0    5      f      no       6     no  \n1         1         0          1    5      m      no       5    yes  \n2         1         1          1    5      m     yes       8    yes  \n3         1         0          1    7      f      no       6    yes  \n4         1         0          0    7      f      no       2     no  ",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>A1_Score</th>\n      <th>A2_Score</th>\n      <th>A3_Score</th>\n      <th>A4_Score</th>\n      <th>A5_Score</th>\n      <th>A6_Score</th>\n      <th>A7_Score</th>\n      <th>A8_Score</th>\n      <th>A9_Score</th>\n      <th>A10_Score</th>\n      <th>age</th>\n      <th>gender</th>\n      <th>jundice</th>\n      <th>result</th>\n      <th>austim</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>5</td>\n      <td>f</td>\n      <td>no</td>\n      <td>6</td>\n      <td>no</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>5</td>\n      <td>m</td>\n      <td>no</td>\n      <td>5</td>\n      <td>yes</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>5</td>\n      <td>m</td>\n      <td>yes</td>\n      <td>8</td>\n      <td>yes</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>7</td>\n      <td>f</td>\n      <td>no</td>\n      <td>6</td>\n      <td>yes</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>7</td>\n      <td>f</td>\n      <td>no</td>\n      <td>2</td>\n      <td>no</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
     },
     "execution_count": 113,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "index = []\n",
    "for i in range(df.shape[0]):\n",
    "    for j in range(df.shape[1]):\n",
    "        temp = df.iloc[i,j]\n",
    "        if temp == \"?\":\n",
    "            index.append(i)\n",
    "            break\n",
    "adf = df.drop(index)\n",
    "adf[['age']] = adf[['age']].apply(pd.to_numeric)\n",
    "adf.head()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "outputs": [
    {
     "data": {
      "text/plain": "   A1_Score  A2_Score  A3_Score  A4_Score  A5_Score  A6_Score  A7_Score  \\\n0         1         1         1         1         0         0         1   \n1         1         1         0         1         0         0         0   \n2         1         1         0         1         1         0         1   \n3         1         1         0         1         0         0         1   \n4         1         0         0         0         0         0         0   \n\n   A8_Score  A9_Score  A10_Score  age  result  gender_f  gender_m  jundice_no  \\\n0         1         0          0    5       6         1         0           1   \n1         1         0          1    5       5         0         1           1   \n2         1         1          1    5       8         0         1           0   \n3         1         0          1    7       6         1         0           1   \n4         1         0          0    7       2         1         0           1   \n\n   jundice_yes  \n0            0  \n1            0  \n2            1  \n3            0  \n4            0  ",
      "text/html": "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>A1_Score</th>\n      <th>A2_Score</th>\n      <th>A3_Score</th>\n      <th>A4_Score</th>\n      <th>A5_Score</th>\n      <th>A6_Score</th>\n      <th>A7_Score</th>\n      <th>A8_Score</th>\n      <th>A9_Score</th>\n      <th>A10_Score</th>\n      <th>age</th>\n      <th>result</th>\n      <th>gender_f</th>\n      <th>gender_m</th>\n      <th>jundice_no</th>\n      <th>jundice_yes</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>5</td>\n      <td>6</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>5</td>\n      <td>5</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1</td>\n      <td>5</td>\n      <td>8</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>7</td>\n      <td>6</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n      <td>0</td>\n      <td>7</td>\n      <td>2</td>\n      <td>1</td>\n      <td>0</td>\n      <td>1</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
     },
     "execution_count": 114,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "features_raw = adf[[\"A1_Score\",\"A2_Score\",\"A3_Score\",\"A4_Score\",\"A5_Score\",\"A6_Score\",\"A7_Score\",\"A8_Score\",\"A9_Score\",\"A10_Score\",\"age\",\"gender\",\"jundice\",\"result\"]]\n",
    "\n",
    "features_final = pd.get_dummies(features_raw)\n",
    "response_final = adf[[\"austim\"]]\n",
    "features_final.head()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "outputs": [],
   "source": [
    "# Split the data set\n",
    "from sklearn.model_selection import train_test_split\n",
    "x_train, x_test, y_train, y_test = train_test_split(features_final, response_final, test_size=0.3, random_state=3)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "## 1. Random Forest"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8447082494969818\n"
     ]
    },
    {
     "data": {
      "text/plain": "0.8436018957345972"
     },
     "execution_count": 116,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.model_selection import cross_val_score\n",
    "from sklearn import metrics\n",
    "# train-test split\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "\n",
    "rf = RandomForestClassifier(n_estimators=10, random_state=1)\n",
    "cv_result = cross_val_score(rf, features_final, response_final, cv=10)\n",
    "print(cv_result.mean())  # cv error\n",
    "\n",
    "rf.fit(x_train,y_train)\n",
    "\n",
    "rf_pred = [x for x in rf.predict(x_test)]\n",
    "\n",
    "accuracy = metrics.accuracy_score(rf_pred,y_test)\n",
    "accuracy"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "## 2. SVM"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8703822937625756\n"
     ]
    },
    {
     "data": {
      "text/plain": "0.8530805687203792"
     },
     "execution_count": 117,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn import svm\n",
    "svc = svm.SVC(kernel='linear', C=1, gamma=2)\n",
    "cv_result = cross_val_score(svc, features_final, response_final, cv=10)\n",
    "print(cv_result.mean())\n",
    "\n",
    "svc.fit(x_train,y_train)\n",
    "svc_pred = svc.predict(x_test)\n",
    "accuracy = metrics.accuracy_score(svc_pred,y_test)\n",
    "accuracy"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "## 3. KNN"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8632595573440642\n"
     ]
    },
    {
     "data": {
      "text/plain": "0.8483412322274881"
     },
     "execution_count": 118,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn import neighbors\n",
    "knn = neighbors.KNeighborsClassifier(n_neighbors=10)\n",
    "cv_result = cross_val_score(knn, features_final, response_final, cv=10)\n",
    "print(cv_result.mean())\n",
    "\n",
    "knn.fit(x_train,y_train)\n",
    "knn_pred = knn.predict(x_test)\n",
    "accuracy = metrics.accuracy_score(knn_pred,y_test)\n",
    "accuracy\n"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "K=5: 0.8461971830985915\n",
      "K=6: 0.8661167002012071\n",
      "K=7: 0.85897384305835\n",
      "K=8: 0.8646881287726357\n",
      "K=9: 0.85897384305835\n",
      "K=10: 0.8632595573440642\n",
      "K=11: 0.8604225352112677\n",
      "K=12: 0.8632595573440645\n",
      "K=13: 0.8590140845070424\n",
      "K=14: 0.8675452716297787\n",
      "K=15: 0.8646881287726359\n",
      "K=16: 0.8689537223340041\n",
      "K=17: 0.8689537223340041\n",
      "K=18: 0.8703822937625756\n",
      "K=19: 0.8703822937625756\n"
     ]
    }
   ],
   "source": [
    "for i in range(5,20):\n",
    "    knn = neighbors.KNeighborsClassifier(n_neighbors=i)\n",
    "    cv_result = cross_val_score(knn, features_final, response_final, cv=10)\n",
    "    print(\"K={}: {}\".format(i,cv_result.mean()))"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "## 4. Naive Bayes"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8675452716297787\n"
     ]
    },
    {
     "data": {
      "text/plain": "0.8483412322274881"
     },
     "execution_count": 120,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.naive_bayes import MultinomialNB\n",
    "nb = MultinomialNB()\n",
    "cv_result = cross_val_score(nb, features_final, response_final, cv=10)\n",
    "print(cv_result.mean())\n",
    "\n",
    "nb.fit(x_train,y_train)\n",
    "nb_pred = nb.predict(x_test)\n",
    "accuracy = metrics.accuracy_score(nb_pred,y_test)\n",
    "accuracy"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "## 5. Lightgbm"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8703822937625756\n"
     ]
    },
    {
     "data": {
      "text/plain": "0.8530805687203792"
     },
     "execution_count": 121,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from lightgbm import LGBMClassifier as LGBM\n",
    "lgbmfit = LGBM(learning_rate=0.01,num_leaves=15)\n",
    "cv_result = cross_val_score(lgbmfit, features_final, response_final, cv=10)\n",
    "print(cv_result.mean())\n",
    "\n",
    "lgbmfit.fit(x_train,y_train)\n",
    "lgbmfit_pred = lgbmfit.predict(x_test)\n",
    "accuracy = metrics.accuracy_score(lgbmfit_pred,y_test)\n",
    "accuracy"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "## 6. HistGradientBoosting"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8475855130784709\n"
     ]
    }
   ],
   "source": [
    "from sklearn.ensemble import HistGradientBoostingClassifier as HGBC\n",
    "hgbcfit = HGBC(learning_rate=0.05,max_leaf_nodes=31, l2_regularization=1)\n",
    "cv_result = cross_val_score(hgbcfit, features_final, response_final, cv=10)\n",
    "print(cv_result.mean())\n",
    "\n",
    "hgbcfit.fit(x_train, y_train)\n",
    "hgbcfit_pred = hgbcfit.predict(x_test)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "### Compare different models"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "outputs": [
    {
     "data": {
      "text/plain": "<Figure size 432x288 with 1 Axes>",
      "image/png": "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\n"
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "modelname = ['RandomForest','SVM','KNN','Naive Bayes', 'LightGBM', 'HGBC']\n",
    "cv_acc = [0.8447, 0.8703, 0.8633, 0.8675, 0.8704, 0.8476]\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "plt.plot(modelname,cv_acc,color=\"red\",marker=\"o\")\n",
    "plt.xlabel('Training Model Name')\n",
    "plt.ylabel('CV accuracy')\n",
    "plt.grid()\n",
    "plt.show()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   }
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}