Notebooks/Titanic-decision-tree.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "ee39865f",
   "metadata": {},
   "source": [
    "Decision Trees"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "94249f52",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Initial Imports\n",
    "\n",
    "import pandas as pd\n",
    "from path import Path\n",
    "from sklearn import tree\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
    "import re\n",
    "import sqlalchemy as db\n",
    "from sqlalchemy import create_engine\n",
    "import psycopg2\n",
    "import pickle\n",
    "from config import db_password"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "6d1e08b7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Connect to PostgreSQL database\n",
    "# Store connection string to local server as string.\n",
    "db_string = f\"postgresql://postgres:{db_password}@localhost:5432/titanic_project\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "5c124782",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create database engine.\n",
    "engine = create_engine(db_string)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "81456159",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[('Abbing, Mr. Anthony', 'male', 42.0, '3rd', 'S', 'United States', 5547.0, 7.11, 0.0, 0.0, 'no'),\n",
       " ('Abbott, Mr. Eugene Joseph', 'male', 13.0, '3rd', 'S', 'United States', 2673.0, 20.05, 0.0, 2.0, 'no'),\n",
       " ('Abbott, Mr. Rossmore Edward', 'male', 16.0, '3rd', 'S', 'United States', 2673.0, 20.05, 1.0, 1.0, 'no'),\n",
       " (\"Abbott, Mrs. Rhoda Mary 'Rosa'\", 'female', 39.0, '3rd', 'S', 'England', 2673.0, 20.05, 1.0, 1.0, 'yes'),\n",
       " ('Abelseth, Miss. Karen Marie', 'female', 16.0, '3rd', 'S', 'Norway', 348125.0, 7.13, 0.0, 0.0, 'yes'),\n",
       " ('Abelseth, Mr. Olaus Jørgensen', 'male', 25.0, '3rd', 'S', 'United States', 348122.0, 7.13, 0.0, 0.0, 'yes'),\n",
       " ('Abelson, Mr. Samuel', 'male', 30.0, '2nd', 'C', 'France', 3381.0, 24.0, 1.0, 0.0, 'no')]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Review data from the PostgreSQL database\n",
    "connection = engine.connect()\n",
    "metadata = db.MetaData()\n",
    "passenger_registry = db.Table('passenger_registry', metadata, autoload=True, autoload_with=engine)\n",
    "#Equivalent to 'SELECT * FROM passenger_registry'\n",
    "query = db.select([passenger_registry]) \n",
    "ResultProxy = connection.execute(query)\n",
    "ResultSet = ResultProxy.fetchall()\n",
    "ResultSet[:7]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "b74cb2ae",
   "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>name</th>\n",
       "      <th>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>class</th>\n",
       "      <th>embarked</th>\n",
       "      <th>country</th>\n",
       "      <th>ticketno</th>\n",
       "      <th>fare</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>survived</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Abbing, Mr. Anthony</td>\n",
       "      <td>male</td>\n",
       "      <td>42.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>United States</td>\n",
       "      <td>5547.0</td>\n",
       "      <td>7.11</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Abbott, Mr. Eugene Joseph</td>\n",
       "      <td>male</td>\n",
       "      <td>13.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>United States</td>\n",
       "      <td>2673.0</td>\n",
       "      <td>20.05</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Abbott, Mr. Rossmore Edward</td>\n",
       "      <td>male</td>\n",
       "      <td>16.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>United States</td>\n",
       "      <td>2673.0</td>\n",
       "      <td>20.05</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Abbott, Mrs. Rhoda Mary 'Rosa'</td>\n",
       "      <td>female</td>\n",
       "      <td>39.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>England</td>\n",
       "      <td>2673.0</td>\n",
       "      <td>20.05</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Abelseth, Miss. Karen Marie</td>\n",
       "      <td>female</td>\n",
       "      <td>16.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>Norway</td>\n",
       "      <td>348125.0</td>\n",
       "      <td>7.13</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                             name  gender   age class embarked        country  \\\n",
       "0             Abbing, Mr. Anthony    male  42.0   3rd        S  United States   \n",
       "1       Abbott, Mr. Eugene Joseph    male  13.0   3rd        S  United States   \n",
       "2     Abbott, Mr. Rossmore Edward    male  16.0   3rd        S  United States   \n",
       "3  Abbott, Mrs. Rhoda Mary 'Rosa'  female  39.0   3rd        S        England   \n",
       "4     Abelseth, Miss. Karen Marie  female  16.0   3rd        S         Norway   \n",
       "\n",
       "   ticketno   fare  sibsp  parch survived  \n",
       "0    5547.0   7.11    0.0    0.0       no  \n",
       "1    2673.0  20.05    0.0    2.0       no  \n",
       "2    2673.0  20.05    1.0    1.0       no  \n",
       "3    2673.0  20.05    1.0    1.0      yes  \n",
       "4  348125.0   7.13    0.0    0.0      yes  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#creating dataframe\n",
    "df_t = pd.DataFrame(ResultSet)\n",
    "df_t.columns = ResultSet[0].keys()\n",
    "df_t.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "6703fba0",
   "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>name</th>\n",
       "      <th>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>class</th>\n",
       "      <th>embarked</th>\n",
       "      <th>country</th>\n",
       "      <th>ticketno</th>\n",
       "      <th>fare</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>survived</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Abbing, Mr. Anthony</td>\n",
       "      <td>male</td>\n",
       "      <td>42.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>United States</td>\n",
       "      <td>5547.0</td>\n",
       "      <td>7.11</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Abbott, Mr. Eugene Joseph</td>\n",
       "      <td>male</td>\n",
       "      <td>13.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>United States</td>\n",
       "      <td>2673.0</td>\n",
       "      <td>20.05</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Abbott, Mr. Rossmore Edward</td>\n",
       "      <td>male</td>\n",
       "      <td>16.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>United States</td>\n",
       "      <td>2673.0</td>\n",
       "      <td>20.05</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Abbott, Mrs. Rhoda Mary 'Rosa'</td>\n",
       "      <td>female</td>\n",
       "      <td>39.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>England</td>\n",
       "      <td>2673.0</td>\n",
       "      <td>20.05</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Abelseth, Miss. Karen Marie</td>\n",
       "      <td>female</td>\n",
       "      <td>16.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>Norway</td>\n",
       "      <td>348125.0</td>\n",
       "      <td>7.13</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                             name  gender   age class embarked        country  \\\n",
       "0             Abbing, Mr. Anthony    male  42.0   3rd        S  United States   \n",
       "1       Abbott, Mr. Eugene Joseph    male  13.0   3rd        S  United States   \n",
       "2     Abbott, Mr. Rossmore Edward    male  16.0   3rd        S  United States   \n",
       "3  Abbott, Mrs. Rhoda Mary 'Rosa'  female  39.0   3rd        S        England   \n",
       "4     Abelseth, Miss. Karen Marie  female  16.0   3rd        S         Norway   \n",
       "\n",
       "   ticketno   fare  sibsp  parch survived  \n",
       "0    5547.0   7.11    0.0    0.0       no  \n",
       "1    2673.0  20.05    0.0    2.0       no  \n",
       "2    2673.0  20.05    1.0    1.0       no  \n",
       "3    2673.0  20.05    1.0    1.0      yes  \n",
       "4  348125.0   7.13    0.0    0.0      yes  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Convert Class to numeric\n",
    "mapping = {'victualling crew': 'crew', 'engineering crew': 'crew', 'restaurant staff': 'crew', 'deck crew': 'crew'}\n",
    "df_t = df_t.replace({'class' : mapping})\n",
    "df_t.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "586c6c05",
   "metadata": {},
   "source": [
    "# Drop Columns that are not needed. \n",
    "- Name is not needed so we will drop that.\n",
    "- Ticket Number won't add value to our analysis so we will drop that as well."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "cf81a8d6",
   "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>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>class</th>\n",
       "      <th>embarked</th>\n",
       "      <th>country</th>\n",
       "      <th>fare</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>survived</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>male</td>\n",
       "      <td>42.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>United States</td>\n",
       "      <td>7.11</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>male</td>\n",
       "      <td>13.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>United States</td>\n",
       "      <td>20.05</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>male</td>\n",
       "      <td>16.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>United States</td>\n",
       "      <td>20.05</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>female</td>\n",
       "      <td>39.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>England</td>\n",
       "      <td>20.05</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>female</td>\n",
       "      <td>16.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>Norway</td>\n",
       "      <td>7.13</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   gender   age class embarked        country   fare  sibsp  parch survived\n",
       "0    male  42.0   3rd        S  United States   7.11    0.0    0.0       no\n",
       "1    male  13.0   3rd        S  United States  20.05    0.0    2.0       no\n",
       "2    male  16.0   3rd        S  United States  20.05    1.0    1.0       no\n",
       "3  female  39.0   3rd        S        England  20.05    1.0    1.0      yes\n",
       "4  female  16.0   3rd        S         Norway   7.13    0.0    0.0      yes"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Drop Unnecessary Columns\n",
    "df_t = df_t.drop(columns=['name', 'ticketno'])\n",
    "df_t.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1a1a5299",
   "metadata": {},
   "source": [
    "# Adjust gender column\n",
    "## Keep 'gender' column, but change the strings 'female' and 'male' to numerical 0 and 1, respectively, to allow machine learning to work on this column."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "c9f426d5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2207"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gender = {'female': 0, 'male': 1}\n",
    "# df_t = df_t.replace({'gender' : gender})\n",
    "df_t.replace({'gender': gender}, inplace=True)\n",
    "df_t.head()\n",
    "len(df_t)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9b5370a8",
   "metadata": {},
   "source": [
    "# Adjust survived column\n",
    "## Keep 'survived' column, but much like 'gender', change the strings 'no' and 'yes' to numerical 0 and 1, to allow machine learning to work on this column as well."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "2a225680",
   "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>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>class</th>\n",
       "      <th>embarked</th>\n",
       "      <th>country</th>\n",
       "      <th>fare</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>survived</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>42.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>United States</td>\n",
       "      <td>7.11</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>13.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>United States</td>\n",
       "      <td>20.05</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>16.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>United States</td>\n",
       "      <td>20.05</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>39.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>England</td>\n",
       "      <td>20.05</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>Norway</td>\n",
       "      <td>7.13</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   gender   age class embarked        country   fare  sibsp  parch  survived\n",
       "0       1  42.0   3rd        S  United States   7.11    0.0    0.0         0\n",
       "1       1  13.0   3rd        S  United States  20.05    0.0    2.0         0\n",
       "2       1  16.0   3rd        S  United States  20.05    1.0    1.0         0\n",
       "3       0  39.0   3rd        S        England  20.05    1.0    1.0         1\n",
       "4       0  16.0   3rd        S         Norway   7.13    0.0    0.0         1"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "survival = {'no': 0, 'yes': 1}\n",
    "df_t.replace({'survived': survival}, inplace=True)\n",
    "df_t.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bd015fb0",
   "metadata": {},
   "source": [
    "# Split Countries into groups based on geographical region\n",
    "## We will keep any countries with 50 or more passengers, and group all countries with less than 50 passengers into the following regions:\n",
    "- Europe: 'EUR'\n",
    "- Asia: 'ASA'\n",
    "- Australia/Oceania: 'AUS'\n",
    "- North America: 'NAM'\n",
    "- South America: 'SAM'\n",
    "- Africa: 'AFR'\n",
    "\n",
    "## Note the countries that remain as is (>=50 Passengers) are:\n",
    "- England: 'ENG'\n",
    "- United States: 'USA'\n",
    "- Ireland: 'IRL'\n",
    "- Sweden: 'SWE'\n",
    "- Lebanon: 'LBN'\n",
    "- Finland: 'FIN'\n",
    "\n",
    "## There are then a total of 12 country codes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "93e5f9fd",
   "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>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>class</th>\n",
       "      <th>embarked</th>\n",
       "      <th>country</th>\n",
       "      <th>fare</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>survived</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>42.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>USA</td>\n",
       "      <td>7.11</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>13.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>USA</td>\n",
       "      <td>20.05</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>16.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>USA</td>\n",
       "      <td>20.05</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>39.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>ENG</td>\n",
       "      <td>20.05</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>3rd</td>\n",
       "      <td>S</td>\n",
       "      <td>EUR</td>\n",
       "      <td>7.13</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   gender   age class embarked country   fare  sibsp  parch  survived\n",
       "0       1  42.0   3rd        S     USA   7.11    0.0    0.0         0\n",
       "1       1  13.0   3rd        S     USA  20.05    0.0    2.0         0\n",
       "2       1  16.0   3rd        S     USA  20.05    1.0    1.0         0\n",
       "3       0  39.0   3rd        S     ENG  20.05    1.0    1.0         1\n",
       "4       0  16.0   3rd        S     EUR   7.13    0.0    0.0         1"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "countrycode = {'England': 'ENG', \n",
    "'United States': 'USA', \n",
    "'Ireland': 'IRL', \n",
    "'Sweden': 'SWE', \n",
    "'Lebanon': 'LBN', \n",
    "'Finland': 'FIN', \n",
    "'Scotland': 'EUR', \n",
    "'Canada': 'NAM', \n",
    "'France': 'EUR', \n",
    "'Norway': 'EUR', \n",
    "'Belgium': 'EUR', \n",
    "'Northern Ireland': 'EUR', \n",
    "'Wales': 'EUR', \n",
    "'Bulgaria': 'EUR', \n",
    "'Switzerland': 'EUR', \n",
    "'Channel Islands': 'EUR', \n",
    "'Croatia (Modern)': 'EUR', \n",
    "'Croatia': 'EUR', \n",
    "'Italy': 'EUR', \n",
    "'Spain': 'EUR', \n",
    "'India': 'ASA', \n",
    "'Argentina': 'SAM', \n",
    "'Hungary': 'EUR', \n",
    "'Denmark': 'EUR', \n",
    "'Turkey': 'ASA', \n",
    "'Germany': 'EUR', \n",
    "'South Africa': 'AFR', \n",
    "'Australia': 'AUS', \n",
    "'Bosnia': 'EUR', \n",
    "'Slovenia': 'EUR', \n",
    "'Poland': 'EUR', \n",
    "'Austria': 'EUR', \n",
    "'Greece': 'EUR', \n",
    "'Netherlands': 'EUR', \n",
    "'Uruguay': 'SAM', \n",
    "'Peru': 'SAM', \n",
    "'Russia': 'EUR', \n",
    "'Siam': 'ASA', \n",
    "'Syria': 'ASA', \n",
    "'Japan': 'ASA', \n",
    "'Slovakia (Modern day)': 'EUR', \n",
    "'Mexico': 'NAM', \n",
    "'Latvia': 'EUR', \n",
    "'Guyana': 'SAM', \n",
    "'Egypt': 'AFR', \n",
    "'Cuba': 'NAM', \n",
    "'China/Hong Kong': 'ASA', \n",
    "'Yugoslavia': 'EUR'}\n",
    "df_t.replace({'country': countrycode}, inplace=True)\n",
    "df_t.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "9c83d021",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "gender        int64\n",
       "age         float64\n",
       "class        object\n",
       "embarked     object\n",
       "country      object\n",
       "fare        float64\n",
       "sibsp       float64\n",
       "parch       float64\n",
       "survived      int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_t.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "2f086906",
   "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>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>fare</th>\n",
       "      <th>sibsp</th>\n",
       "      <th>parch</th>\n",
       "      <th>survived</th>\n",
       "      <th>class_1st</th>\n",
       "      <th>class_2nd</th>\n",
       "      <th>class_3rd</th>\n",
       "      <th>class_crew</th>\n",
       "      <th>...</th>\n",
       "      <th>country_AUS</th>\n",
       "      <th>country_ENG</th>\n",
       "      <th>country_EUR</th>\n",
       "      <th>country_FIN</th>\n",
       "      <th>country_IRL</th>\n",
       "      <th>country_LBN</th>\n",
       "      <th>country_NAM</th>\n",
       "      <th>country_SAM</th>\n",
       "      <th>country_SWE</th>\n",
       "      <th>country_USA</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>42.0</td>\n",
       "      <td>7.11</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</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>0</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>13.0</td>\n",
       "      <td>20.05</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</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>0</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>16.0</td>\n",
       "      <td>20.05</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</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>0</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>39.0</td>\n",
       "      <td>20.05</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>7.13</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 26 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   gender   age   fare  sibsp  parch  survived  class_1st  class_2nd  \\\n",
       "0       1  42.0   7.11    0.0    0.0         0          0          0   \n",
       "1       1  13.0  20.05    0.0    2.0         0          0          0   \n",
       "2       1  16.0  20.05    1.0    1.0         0          0          0   \n",
       "3       0  39.0  20.05    1.0    1.0         1          0          0   \n",
       "4       0  16.0   7.13    0.0    0.0         1          0          0   \n",
       "\n",
       "   class_3rd  class_crew  ...  country_AUS  country_ENG  country_EUR  \\\n",
       "0          1           0  ...            0            0            0   \n",
       "1          1           0  ...            0            0            0   \n",
       "2          1           0  ...            0            0            0   \n",
       "3          1           0  ...            0            1            0   \n",
       "4          1           0  ...            0            0            1   \n",
       "\n",
       "   country_FIN  country_IRL  country_LBN  country_NAM  country_SAM  \\\n",
       "0            0            0            0            0            0   \n",
       "1            0            0            0            0            0   \n",
       "2            0            0            0            0            0   \n",
       "3            0            0            0            0            0   \n",
       "4            0            0            0            0            0   \n",
       "\n",
       "   country_SWE  country_USA  \n",
       "0            0            1  \n",
       "1            0            1  \n",
       "2            0            1  \n",
       "3            0            0  \n",
       "4            0            0  \n",
       "\n",
       "[5 rows x 26 columns]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_t = pd.get_dummies(df_t)\n",
    "df_t.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "b0bef659",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "gender           0\n",
       "age              2\n",
       "fare           916\n",
       "sibsp          900\n",
       "parch          900\n",
       "survived         0\n",
       "class_1st        0\n",
       "class_2nd        0\n",
       "class_3rd        0\n",
       "class_crew       0\n",
       "embarked_B       0\n",
       "embarked_C       0\n",
       "embarked_Q       0\n",
       "embarked_S       0\n",
       "country_AFR      0\n",
       "country_ASA      0\n",
       "country_AUS      0\n",
       "country_ENG      0\n",
       "country_EUR      0\n",
       "country_FIN      0\n",
       "country_IRL      0\n",
       "country_LBN      0\n",
       "country_NAM      0\n",
       "country_SAM      0\n",
       "country_SWE      0\n",
       "country_USA      0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check for null values\n",
    "df_t.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "665a76d2",
   "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>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>survived</th>\n",
       "      <th>class_1st</th>\n",
       "      <th>class_2nd</th>\n",
       "      <th>class_3rd</th>\n",
       "      <th>class_crew</th>\n",
       "      <th>embarked_B</th>\n",
       "      <th>embarked_C</th>\n",
       "      <th>embarked_Q</th>\n",
       "      <th>...</th>\n",
       "      <th>country_AUS</th>\n",
       "      <th>country_ENG</th>\n",
       "      <th>country_EUR</th>\n",
       "      <th>country_FIN</th>\n",
       "      <th>country_IRL</th>\n",
       "      <th>country_LBN</th>\n",
       "      <th>country_NAM</th>\n",
       "      <th>country_SAM</th>\n",
       "      <th>country_SWE</th>\n",
       "      <th>country_USA</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>42.0</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>13.0</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>16.0</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>39.0</td>\n",
       "      <td>1</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>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>1</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>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 23 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   gender   age  survived  class_1st  class_2nd  class_3rd  class_crew  \\\n",
       "0       1  42.0         0          0          0          1           0   \n",
       "1       1  13.0         0          0          0          1           0   \n",
       "2       1  16.0         0          0          0          1           0   \n",
       "3       0  39.0         1          0          0          1           0   \n",
       "4       0  16.0         1          0          0          1           0   \n",
       "\n",
       "   embarked_B  embarked_C  embarked_Q  ...  country_AUS  country_ENG  \\\n",
       "0           0           0           0  ...            0            0   \n",
       "1           0           0           0  ...            0            0   \n",
       "2           0           0           0  ...            0            0   \n",
       "3           0           0           0  ...            0            1   \n",
       "4           0           0           0  ...            0            0   \n",
       "\n",
       "   country_EUR  country_FIN  country_IRL  country_LBN  country_NAM  \\\n",
       "0            0            0            0            0            0   \n",
       "1            0            0            0            0            0   \n",
       "2            0            0            0            0            0   \n",
       "3            0            0            0            0            0   \n",
       "4            1            0            0            0            0   \n",
       "\n",
       "   country_SAM  country_SWE  country_USA  \n",
       "0            0            0            1  \n",
       "1            0            0            1  \n",
       "2            0            0            1  \n",
       "3            0            0            0  \n",
       "4            0            0            0  \n",
       "\n",
       "[5 rows x 23 columns]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Drop columns with many null values; we won't be using these in our model.\n",
    "df_t.drop(columns = [\"fare\", \"sibsp\", \"parch\"], inplace=True)\n",
    "df_t.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "7515ed24",
   "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>gender</th>\n",
       "      <th>age</th>\n",
       "      <th>survived</th>\n",
       "      <th>class_1st</th>\n",
       "      <th>class_2nd</th>\n",
       "      <th>class_3rd</th>\n",
       "      <th>class_crew</th>\n",
       "      <th>embarked_B</th>\n",
       "      <th>embarked_C</th>\n",
       "      <th>embarked_Q</th>\n",
       "      <th>...</th>\n",
       "      <th>country_AUS</th>\n",
       "      <th>country_ENG</th>\n",
       "      <th>country_EUR</th>\n",
       "      <th>country_FIN</th>\n",
       "      <th>country_IRL</th>\n",
       "      <th>country_LBN</th>\n",
       "      <th>country_NAM</th>\n",
       "      <th>country_SAM</th>\n",
       "      <th>country_SWE</th>\n",
       "      <th>country_USA</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>42.0</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>13.0</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>16.0</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>39.0</td>\n",
       "      <td>1</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>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>1</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>...</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>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 23 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   gender   age  survived  class_1st  class_2nd  class_3rd  class_crew  \\\n",
       "0       1  42.0         0          0          0          1           0   \n",
       "1       1  13.0         0          0          0          1           0   \n",
       "2       1  16.0         0          0          0          1           0   \n",
       "3       0  39.0         1          0          0          1           0   \n",
       "4       0  16.0         1          0          0          1           0   \n",
       "\n",
       "   embarked_B  embarked_C  embarked_Q  ...  country_AUS  country_ENG  \\\n",
       "0           0           0           0  ...            0            0   \n",
       "1           0           0           0  ...            0            0   \n",
       "2           0           0           0  ...            0            0   \n",
       "3           0           0           0  ...            0            1   \n",
       "4           0           0           0  ...            0            0   \n",
       "\n",
       "   country_EUR  country_FIN  country_IRL  country_LBN  country_NAM  \\\n",
       "0            0            0            0            0            0   \n",
       "1            0            0            0            0            0   \n",
       "2            0            0            0            0            0   \n",
       "3            0            0            0            0            0   \n",
       "4            1            0            0            0            0   \n",
       "\n",
       "   country_SAM  country_SWE  country_USA  \n",
       "0            0            0            1  \n",
       "1            0            0            1  \n",
       "2            0            0            1  \n",
       "3            0            0            0  \n",
       "4            0            0            0  \n",
       "\n",
       "[5 rows x 23 columns]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Drop null values\n",
    "df_t.dropna(inplace= True)\n",
    "df_t.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "2a1963e4",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2205"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Define features set\n",
    "X = df_t.copy()\n",
    "X = X.drop(\"survived\", axis = 1)\n",
    "X.head()\n",
    "len(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "96c63a18",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Define target vector\n",
    "y = df_t[\"survived\"].values.reshape(-1, 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "af497745",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Splitting into Train and Test sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=78)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "428edee6",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Creating StandardScaler instance\n",
    "scaler = StandardScaler()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "d239f5fb",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Fitting Standard Scaler\n",
    "X_scaler = scaler.fit(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "72e2f076",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Scaling data\n",
    "X_train_scaled = X_scaler.transform(X_train)\n",
    "X_test_scaled = X_scaler.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "577ba4d6",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Scaling data\n",
    "X_train_scaled = X_scaler.transform(X_train)\n",
    "X_test_scaled = X_scaler.transform(X_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "87294e71",
   "metadata": {},
   "source": [
    "## Fitting the Decision Tree Model\n",
    "We determined that the decision tree model would help us assess survivability of the disaster for a few reasons. Due to assessing likelihood of survival based on classifications such as age, gender, class, point of embarkation, and nationality. Our goal is to feed the existing information into the training portion of the model and review the actual outcomes based on these classifications, to then allow the test portion to form predictions on how the classifications impacted outcomes. \n",
    "\n",
    "Most of our input data are of the type \"Categorical Variable\". This includes gender and survived, which are each binary in our model. We used panda's get_dummies method to obtain a binary result for the categorical variables with more than two options. This includes point of embarkation as well as nationality.\n",
    "\n",
    "Finally, one variable is a \"Continuous Variable\", specifically, age. The age of the passenger can be any value from 0 to the maximum age. All of these variables are fed into the model and then the decision tree machine learning model predicts the likelihood of survivability (as a binary Yes/No result) for the test data. Then, we use flask and our html web page to predict the same based on the input received."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "1013790e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Creating the decision tree classifier instance\n",
    "model = tree.DecisionTreeClassifier()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "6dd951e4",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Fitting the model\n",
    "model = model.fit(X_train_scaled, y_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "878cd537",
   "metadata": {},
   "source": [
    "## Making Predictions Using the Tree Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "07c032d8",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Making predictions using the testing data\n",
    "predictions = model.predict(X_test_scaled)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "1a30c122",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Calculating the confusion matrix\n",
    "cm = confusion_matrix(y_test, predictions)\n",
    "cm_df = pd.DataFrame(\n",
    "    cm, index=[\"Actual 0\", \"Actual 1\"], columns=[\"Predicted 0\", \"Predicted 1\"]\n",
    ")\n",
    "\n",
    "# Calculating the accuracy score\n",
    "acc_score = accuracy_score(y_test, predictions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "0a1d1834",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Confusion Matrix\n"
     ]
    },
    {
     "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>Predicted 0</th>\n",
       "      <th>Predicted 1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Actual 0</th>\n",
       "      <td>335</td>\n",
       "      <td>37</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Actual 1</th>\n",
       "      <td>89</td>\n",
       "      <td>91</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          Predicted 0  Predicted 1\n",
       "Actual 0          335           37\n",
       "Actual 1           89           91"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy Score : 0.7717391304347826\n",
      "Classification Report\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.79      0.90      0.84       372\n",
      "           1       0.71      0.51      0.59       180\n",
      "\n",
      "    accuracy                           0.77       552\n",
      "   macro avg       0.75      0.70      0.72       552\n",
      "weighted avg       0.76      0.77      0.76       552\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Displaying results\n",
    "print(\"Confusion Matrix\")\n",
    "display(cm_df)\n",
    "print(f\"Accuracy Score : {acc_score}\")\n",
    "print(\"Classification Report\")\n",
    "print(classification_report(y_test, predictions))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "2c21ca9e",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('../webapp/model/titanic_model.pkl', 'wb') as file:\n",
    "    pickle.dump(model, file)\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "60f4aedc",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Save scaler to file\n",
    "with open('../webapp/model/titanic_scaler.pkl', 'wb') as file:\n",
    "    pickle.dump(X_scaler, file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "06d98d98",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_t.to_csv('../Resources/titanic_clean.csv', encoding='utf-8', index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c0c677a7",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "mlenv",
   "language": "python",
   "name": "mlenv"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}