{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>Country</th>\n",
       "      <th>Capital</th>\n",
       "      <th>Africa</th>\n",
       "      <th>Asia</th>\n",
       "      <th>C_America</th>\n",
       "      <th>Europe</th>\n",
       "      <th>N_America</th>\n",
       "      <th>Oceania</th>\n",
       "      <th>S_America</th>\n",
       "      <th>Population</th>\n",
       "      <th>Area</th>\n",
       "      <th>Density</th>\n",
       "      <th>GDP_millions</th>\n",
       "      <th>GDP_per_capita</th>\n",
       "      <th>Birth_rate</th>\n",
       "      <th>Death_rate</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>India</td>\n",
       "      <td>New Delhi</td>\n",
       "      <td>0</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>1373233170</td>\n",
       "      <td>1283232.0</td>\n",
       "      <td>1070.136320</td>\n",
       "      <td>11370978.8</td>\n",
       "      <td>8280.442862</td>\n",
       "      <td>18.7</td>\n",
       "      <td>7.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>Andorra</td>\n",
       "      <td>Andorra La Vella</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>0</td>\n",
       "      <td>77204</td>\n",
       "      <td>180.0</td>\n",
       "      <td>428.911111</td>\n",
       "      <td>3327.0</td>\n",
       "      <td>43093.622092</td>\n",
       "      <td>7.3</td>\n",
       "      <td>7.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>Sierra Leone</td>\n",
       "      <td>Freetown</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>7894921</td>\n",
       "      <td>27394.0</td>\n",
       "      <td>288.198912</td>\n",
       "      <td>11361.6</td>\n",
       "      <td>1439.102431</td>\n",
       "      <td>36.0</td>\n",
       "      <td>10.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>Luxembourg</td>\n",
       "      <td>Luxembourg</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>0</td>\n",
       "      <td>620853</td>\n",
       "      <td>993.0</td>\n",
       "      <td>625.229607</td>\n",
       "      <td>63428.4</td>\n",
       "      <td>102163.314021</td>\n",
       "      <td>11.6</td>\n",
       "      <td>7.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>Bahamas, The</td>\n",
       "      <td>Nassau</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>391369</td>\n",
       "      <td>3858.0</td>\n",
       "      <td>101.443494</td>\n",
       "      <td>11725.0</td>\n",
       "      <td>29958.939006</td>\n",
       "      <td>15.1</td>\n",
       "      <td>7.3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Country           Capital  Africa  Asia  C_America  Europe  N_America  \\\n",
       "0         India         New Delhi       0     1          0       0          0   \n",
       "1       Andorra  Andorra La Vella       0     0          0       1          0   \n",
       "2  Sierra Leone          Freetown       1     0          0       0          0   \n",
       "3    Luxembourg        Luxembourg       0     0          0       1          0   \n",
       "4  Bahamas, The            Nassau       0     0          1       0          0   \n",
       "\n",
       "   Oceania  S_America  Population       Area      Density  GDP_millions  \\\n",
       "0        0          0  1373233170  1283232.0  1070.136320    11370978.8   \n",
       "1        0          0       77204      180.0   428.911111        3327.0   \n",
       "2        0          0     7894921    27394.0   288.198912       11361.6   \n",
       "3        0          0      620853      993.0   625.229607       63428.4   \n",
       "4        0          0      391369     3858.0   101.443494       11725.0   \n",
       "\n",
       "   GDP_per_capita  Birth_rate  Death_rate  \n",
       "0     8280.442862        18.7         7.3  \n",
       "1    43093.622092         7.3         7.4  \n",
       "2     1439.102431        36.0        10.2  \n",
       "3   102163.314021        11.6         7.3  \n",
       "4    29958.939006        15.1         7.3  "
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import xlrd\n",
    "\n",
    "xlsx = xlrd.open_workbook(\"CSC 357 Week 2 Lesson.xlsx\", on_demand=True)\n",
    "with pd.ExcelFile(xlsx) as wb:\n",
    "    df = pd.read_excel(wb, \"info\")\n",
    "\n",
    "df.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>Africa</th>\n",
       "      <th>Asia</th>\n",
       "      <th>C_America</th>\n",
       "      <th>Europe</th>\n",
       "      <th>N_America</th>\n",
       "      <th>Oceania</th>\n",
       "      <th>S_America</th>\n",
       "      <th>Population</th>\n",
       "      <th>Area</th>\n",
       "      <th>Density</th>\n",
       "      <th>GDP_millions</th>\n",
       "      <th>GDP_per_capita</th>\n",
       "      <th>Birth_rate</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>0</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>1373233170</td>\n",
       "      <td>1283232.0</td>\n",
       "      <td>1070.136320</td>\n",
       "      <td>11370978.8</td>\n",
       "      <td>8280.442862</td>\n",
       "      <td>18.7</td>\n",
       "    </tr>\n",
       "    <tr>\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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>77204</td>\n",
       "      <td>180.0</td>\n",
       "      <td>428.911111</td>\n",
       "      <td>3327.0</td>\n",
       "      <td>43093.622092</td>\n",
       "      <td>7.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</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>7894921</td>\n",
       "      <td>27394.0</td>\n",
       "      <td>288.198912</td>\n",
       "      <td>11361.6</td>\n",
       "      <td>1439.102431</td>\n",
       "      <td>36.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</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>0</td>\n",
       "      <td>620853</td>\n",
       "      <td>993.0</td>\n",
       "      <td>625.229607</td>\n",
       "      <td>63428.4</td>\n",
       "      <td>102163.314021</td>\n",
       "      <td>11.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>391369</td>\n",
       "      <td>3858.0</td>\n",
       "      <td>101.443494</td>\n",
       "      <td>11725.0</td>\n",
       "      <td>29958.939006</td>\n",
       "      <td>15.1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Africa  Asia  C_America  Europe  N_America  Oceania  S_America  Population  \\\n",
       "0       0     1          0       0          0        0          0  1373233170   \n",
       "1       0     0          0       1          0        0          0       77204   \n",
       "2       1     0          0       0          0        0          0     7894921   \n",
       "3       0     0          0       1          0        0          0      620853   \n",
       "4       0     0          1       0          0        0          0      391369   \n",
       "\n",
       "        Area      Density  GDP_millions  GDP_per_capita  Birth_rate  \n",
       "0  1283232.0  1070.136320    11370978.8     8280.442862        18.7  \n",
       "1      180.0   428.911111        3327.0    43093.622092         7.3  \n",
       "2    27394.0   288.198912       11361.6     1439.102431        36.0  \n",
       "3      993.0   625.229607       63428.4   102163.314021        11.6  \n",
       "4     3858.0   101.443494       11725.0    29958.939006        15.1  "
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "birth_data = df.drop(columns = [\"Country\", \"Capital\", \"Death_rate\"])\n",
    "death_data = df.drop(columns = [\"Country\", \"Capital\", \"Birth_rate\"])\n",
    "birth_data.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>Africa</th>\n",
       "      <th>Asia</th>\n",
       "      <th>C_America</th>\n",
       "      <th>Europe</th>\n",
       "      <th>N_America</th>\n",
       "      <th>Oceania</th>\n",
       "      <th>S_America</th>\n",
       "      <th>Population</th>\n",
       "      <th>Area</th>\n",
       "      <th>Density</th>\n",
       "      <th>GDP_millions</th>\n",
       "      <th>GDP_per_capita</th>\n",
       "      <th>Death_rate</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>0</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>1373233170</td>\n",
       "      <td>1283232.0</td>\n",
       "      <td>1070.136320</td>\n",
       "      <td>11370978.8</td>\n",
       "      <td>8280.442862</td>\n",
       "      <td>7.3</td>\n",
       "    </tr>\n",
       "    <tr>\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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>77204</td>\n",
       "      <td>180.0</td>\n",
       "      <td>428.911111</td>\n",
       "      <td>3327.0</td>\n",
       "      <td>43093.622092</td>\n",
       "      <td>7.4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</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>7894921</td>\n",
       "      <td>27394.0</td>\n",
       "      <td>288.198912</td>\n",
       "      <td>11361.6</td>\n",
       "      <td>1439.102431</td>\n",
       "      <td>10.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</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>0</td>\n",
       "      <td>620853</td>\n",
       "      <td>993.0</td>\n",
       "      <td>625.229607</td>\n",
       "      <td>63428.4</td>\n",
       "      <td>102163.314021</td>\n",
       "      <td>7.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>391369</td>\n",
       "      <td>3858.0</td>\n",
       "      <td>101.443494</td>\n",
       "      <td>11725.0</td>\n",
       "      <td>29958.939006</td>\n",
       "      <td>7.3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Africa  Asia  C_America  Europe  N_America  Oceania  S_America  Population  \\\n",
       "0       0     1          0       0          0        0          0  1373233170   \n",
       "1       0     0          0       1          0        0          0       77204   \n",
       "2       1     0          0       0          0        0          0     7894921   \n",
       "3       0     0          0       1          0        0          0      620853   \n",
       "4       0     0          1       0          0        0          0      391369   \n",
       "\n",
       "        Area      Density  GDP_millions  GDP_per_capita  Death_rate  \n",
       "0  1283232.0  1070.136320    11370978.8     8280.442862         7.3  \n",
       "1      180.0   428.911111        3327.0    43093.622092         7.4  \n",
       "2    27394.0   288.198912       11361.6     1439.102431        10.2  \n",
       "3      993.0   625.229607       63428.4   102163.314021         7.3  \n",
       "4     3858.0   101.443494       11725.0    29958.939006         7.3  "
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "death_data.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "birth_train, birth_test = train_test_split(birth_data, test_size=0.2, random_state=42)\n",
    "death_train, death_test = train_test_split(death_data, test_size=0.2, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Birth_rate        1.000000\n",
       "Africa            0.742076\n",
       "Oceania           0.000850\n",
       "Population       -0.030827\n",
       "C_America        -0.068494\n",
       "Area             -0.080206\n",
       "S_America        -0.084688\n",
       "N_America        -0.095789\n",
       "Asia             -0.104140\n",
       "GDP_millions     -0.139544\n",
       "Density          -0.194040\n",
       "GDP_per_capita   -0.534990\n",
       "Europe           -0.542382\n",
       "Name: Birth_rate, dtype: float64"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "birth_corr_matrix = birth_train.corr()\n",
    "birth_corr_matrix[\"Birth_rate\"].sort_values(ascending=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Death_rate        1.000000\n",
       "Europe            0.498187\n",
       "Africa            0.094868\n",
       "Area              0.089829\n",
       "N_America         0.030557\n",
       "GDP_millions      0.011293\n",
       "Population       -0.000442\n",
       "GDP_per_capita   -0.070903\n",
       "Density          -0.076134\n",
       "C_America        -0.115274\n",
       "S_America        -0.125681\n",
       "Oceania          -0.148835\n",
       "Asia             -0.383382\n",
       "Name: Death_rate, dtype: float64"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "death_corr_matrix = death_train.corr()\n",
    "death_corr_matrix[\"Death_rate\"].sort_values(ascending=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "metadata": {},
   "outputs": [],
   "source": [
    "birth_train_labels = birth_train[\"Birth_rate\"].copy()\n",
    "birth_train = birth_train.drop(\"Birth_rate\", axis=1)\n",
    "death_train_labels = death_train[\"Death_rate\"].copy()\n",
    "death_train = death_train.drop(\"Death_rate\", axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>Africa</th>\n",
       "      <th>Asia</th>\n",
       "      <th>C_America</th>\n",
       "      <th>Europe</th>\n",
       "      <th>N_America</th>\n",
       "      <th>Oceania</th>\n",
       "      <th>S_America</th>\n",
       "      <th>Population</th>\n",
       "      <th>Area</th>\n",
       "      <th>Density</th>\n",
       "      <th>GDP_millions</th>\n",
       "      <th>GDP_per_capita</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>-0.616872</td>\n",
       "      <td>-0.547723</td>\n",
       "      <td>-0.313993</td>\n",
       "      <td>-0.587220</td>\n",
       "      <td>-0.113961</td>\n",
       "      <td>3.630677</td>\n",
       "      <td>-0.261712</td>\n",
       "      <td>-0.101264</td>\n",
       "      <td>3.356525</td>\n",
       "      <td>-0.210259</td>\n",
       "      <td>0.181815</td>\n",
       "      <td>0.935520</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>-0.616872</td>\n",
       "      <td>-0.547723</td>\n",
       "      <td>-0.313993</td>\n",
       "      <td>-0.587220</td>\n",
       "      <td>-0.113961</td>\n",
       "      <td>3.630677</td>\n",
       "      <td>-0.261712</td>\n",
       "      <td>-0.257790</td>\n",
       "      <td>-0.362200</td>\n",
       "      <td>0.016860</td>\n",
       "      <td>-0.254971</td>\n",
       "      <td>-0.243053</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>-0.616872</td>\n",
       "      <td>-0.547723</td>\n",
       "      <td>-0.313993</td>\n",
       "      <td>1.702939</td>\n",
       "      <td>-0.113961</td>\n",
       "      <td>-0.275431</td>\n",
       "      <td>-0.261712</td>\n",
       "      <td>-0.246636</td>\n",
       "      <td>-0.356950</td>\n",
       "      <td>-0.136961</td>\n",
       "      <td>-0.247924</td>\n",
       "      <td>-0.419685</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>-0.616872</td>\n",
       "      <td>1.825742</td>\n",
       "      <td>-0.313993</td>\n",
       "      <td>-0.587220</td>\n",
       "      <td>-0.113961</td>\n",
       "      <td>-0.275431</td>\n",
       "      <td>-0.261712</td>\n",
       "      <td>0.058688</td>\n",
       "      <td>-0.313464</td>\n",
       "      <td>0.015897</td>\n",
       "      <td>0.467978</td>\n",
       "      <td>0.617741</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>-0.616872</td>\n",
       "      <td>-0.547723</td>\n",
       "      <td>-0.313993</td>\n",
       "      <td>1.702939</td>\n",
       "      <td>-0.113961</td>\n",
       "      <td>-0.275431</td>\n",
       "      <td>-0.261712</td>\n",
       "      <td>-0.249666</td>\n",
       "      <td>-0.341158</td>\n",
       "      <td>-0.198096</td>\n",
       "      <td>-0.239894</td>\n",
       "      <td>0.343716</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Africa      Asia  C_America    Europe  N_America   Oceania  S_America  \\\n",
       "0 -0.616872 -0.547723  -0.313993 -0.587220  -0.113961  3.630677  -0.261712   \n",
       "1 -0.616872 -0.547723  -0.313993 -0.587220  -0.113961  3.630677  -0.261712   \n",
       "2 -0.616872 -0.547723  -0.313993  1.702939  -0.113961 -0.275431  -0.261712   \n",
       "3 -0.616872  1.825742  -0.313993 -0.587220  -0.113961 -0.275431  -0.261712   \n",
       "4 -0.616872 -0.547723  -0.313993  1.702939  -0.113961 -0.275431  -0.261712   \n",
       "\n",
       "   Population      Area   Density  GDP_millions  GDP_per_capita  \n",
       "0   -0.101264  3.356525 -0.210259      0.181815        0.935520  \n",
       "1   -0.257790 -0.362200  0.016860     -0.254971       -0.243053  \n",
       "2   -0.246636 -0.356950 -0.136961     -0.247924       -0.419685  \n",
       "3    0.058688 -0.313464  0.015897      0.467978        0.617741  \n",
       "4   -0.249666 -0.341158 -0.198096     -0.239894        0.343716  "
      ]
     },
     "execution_count": 96,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "scaler = StandardScaler()\n",
    "birth_train = pd.DataFrame(scaler.fit_transform(birth_train))\n",
    "death_train = pd.DataFrame(scaler.fit_transform(death_train))\n",
    "birth_train.columns = [\"Africa\", \"Asia\", \"C_America\", \"Europe\", \"N_America\", \"Oceania\", \"S_America\",\n",
    "                       \"Population\", \"Area\", \"Density\", \"GDP_millions\", \"GDP_per_capita\"]\n",
    "death_train.columns = [\"Africa\", \"Asia\", \"C_America\", \"Europe\", \"N_America\", \"Oceania\", \"S_America\",\n",
    "                       \"Population\", \"Area\", \"Density\", \"GDP_millions\", \"GDP_per_capita\"]\n",
    "birth_train.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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>Africa</th>\n",
       "      <th>Asia</th>\n",
       "      <th>C_America</th>\n",
       "      <th>Europe</th>\n",
       "      <th>N_America</th>\n",
       "      <th>Oceania</th>\n",
       "      <th>S_America</th>\n",
       "      <th>Population</th>\n",
       "      <th>Area</th>\n",
       "      <th>Density</th>\n",
       "      <th>GDP_millions</th>\n",
       "      <th>GDP_per_capita</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>0</td>\n",
       "      <td>-0.616872</td>\n",
       "      <td>-0.547723</td>\n",
       "      <td>-0.313993</td>\n",
       "      <td>-0.587220</td>\n",
       "      <td>-0.113961</td>\n",
       "      <td>3.630677</td>\n",
       "      <td>-0.261712</td>\n",
       "      <td>-0.101264</td>\n",
       "      <td>3.356525</td>\n",
       "      <td>-0.210259</td>\n",
       "      <td>0.181815</td>\n",
       "      <td>0.935520</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>-0.616872</td>\n",
       "      <td>-0.547723</td>\n",
       "      <td>-0.313993</td>\n",
       "      <td>-0.587220</td>\n",
       "      <td>-0.113961</td>\n",
       "      <td>3.630677</td>\n",
       "      <td>-0.261712</td>\n",
       "      <td>-0.257790</td>\n",
       "      <td>-0.362200</td>\n",
       "      <td>0.016860</td>\n",
       "      <td>-0.254971</td>\n",
       "      <td>-0.243053</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>-0.616872</td>\n",
       "      <td>-0.547723</td>\n",
       "      <td>-0.313993</td>\n",
       "      <td>1.702939</td>\n",
       "      <td>-0.113961</td>\n",
       "      <td>-0.275431</td>\n",
       "      <td>-0.261712</td>\n",
       "      <td>-0.246636</td>\n",
       "      <td>-0.356950</td>\n",
       "      <td>-0.136961</td>\n",
       "      <td>-0.247924</td>\n",
       "      <td>-0.419685</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>-0.616872</td>\n",
       "      <td>1.825742</td>\n",
       "      <td>-0.313993</td>\n",
       "      <td>-0.587220</td>\n",
       "      <td>-0.113961</td>\n",
       "      <td>-0.275431</td>\n",
       "      <td>-0.261712</td>\n",
       "      <td>0.058688</td>\n",
       "      <td>-0.313464</td>\n",
       "      <td>0.015897</td>\n",
       "      <td>0.467978</td>\n",
       "      <td>0.617741</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>-0.616872</td>\n",
       "      <td>-0.547723</td>\n",
       "      <td>-0.313993</td>\n",
       "      <td>1.702939</td>\n",
       "      <td>-0.113961</td>\n",
       "      <td>-0.275431</td>\n",
       "      <td>-0.261712</td>\n",
       "      <td>-0.249666</td>\n",
       "      <td>-0.341158</td>\n",
       "      <td>-0.198096</td>\n",
       "      <td>-0.239894</td>\n",
       "      <td>0.343716</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     Africa      Asia  C_America    Europe  N_America   Oceania  S_America  \\\n",
       "0 -0.616872 -0.547723  -0.313993 -0.587220  -0.113961  3.630677  -0.261712   \n",
       "1 -0.616872 -0.547723  -0.313993 -0.587220  -0.113961  3.630677  -0.261712   \n",
       "2 -0.616872 -0.547723  -0.313993  1.702939  -0.113961 -0.275431  -0.261712   \n",
       "3 -0.616872  1.825742  -0.313993 -0.587220  -0.113961 -0.275431  -0.261712   \n",
       "4 -0.616872 -0.547723  -0.313993  1.702939  -0.113961 -0.275431  -0.261712   \n",
       "\n",
       "   Population      Area   Density  GDP_millions  GDP_per_capita  \n",
       "0   -0.101264  3.356525 -0.210259      0.181815        0.935520  \n",
       "1   -0.257790 -0.362200  0.016860     -0.254971       -0.243053  \n",
       "2   -0.246636 -0.356950 -0.136961     -0.247924       -0.419685  \n",
       "3    0.058688 -0.313464  0.015897      0.467978        0.617741  \n",
       "4   -0.249666 -0.341158 -0.198096     -0.239894        0.343716  "
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "death_train.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LinearRegression\n",
    "lin_reg = LinearRegression()\n",
    "birth_lr = lin_reg.fit(birth_train, birth_train_labels)\n",
    "death_lr = lin_reg.fit(death_train, death_train_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "RMSE for Birth Rate:  15.211499774254994 \n",
      "RMSE for Death Rate:  2.108474856168463\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import mean_squared_error\n",
    "birth_pred = birth_lr.predict(birth_train)\n",
    "birth_mse = mean_squared_error(birth_train_labels, birth_pred)\n",
    "birth_rmse = np.sqrt(birth_mse)\n",
    "death_pred = death_lr.predict(death_train)\n",
    "death_mse = mean_squared_error(death_train_labels, death_pred)\n",
    "death_rmse = np.sqrt(death_mse)\n",
    "print(\"RMSE for Birth Rate: \", birth_rmse, \"\\nRMSE for Death Rate: \", death_rmse)"
   ]
  }
 ],
 "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}