Survival Prediction.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 226,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np \n",
    "import pandas as pd\n",
    "import seaborn as sns \n",
    "import time\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.model_selection import train_test_split, GridSearchCV\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.tree import DecisionTreeClassifier\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 230,
   "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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Name</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Ticket</th>\n",
       "      <th>Fare</th>\n",
       "      <th>Cabin</th>\n",
       "      <th>Embarked</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Braund, Mr. Owen Harris</td>\n",
       "      <td>male</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>A/5 21171</td>\n",
       "      <td>7.2500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
       "      <td>female</td>\n",
       "      <td>38.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>PC 17599</td>\n",
       "      <td>71.2833</td>\n",
       "      <td>C85</td>\n",
       "      <td>C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Heikkinen, Miss. Laina</td>\n",
       "      <td>female</td>\n",
       "      <td>26.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>STON/O2. 3101282</td>\n",
       "      <td>7.9250</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
       "      <td>female</td>\n",
       "      <td>35.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>113803</td>\n",
       "      <td>53.1000</td>\n",
       "      <td>C123</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>Allen, Mr. William Henry</td>\n",
       "      <td>male</td>\n",
       "      <td>35.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>373450</td>\n",
       "      <td>8.0500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   PassengerId  Survived  Pclass  \\\n",
       "0            1         0       3   \n",
       "1            2         1       1   \n",
       "2            3         1       3   \n",
       "3            4         1       1   \n",
       "4            5         0       3   \n",
       "\n",
       "                                                Name     Sex   Age  SibSp  \\\n",
       "0                            Braund, Mr. Owen Harris    male  22.0      1   \n",
       "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
       "2                             Heikkinen, Miss. Laina  female  26.0      0   \n",
       "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
       "4                           Allen, Mr. William Henry    male  35.0      0   \n",
       "\n",
       "   Parch            Ticket     Fare Cabin Embarked  \n",
       "0      0         A/5 21171   7.2500   NaN        S  \n",
       "1      0          PC 17599  71.2833   C85        C  \n",
       "2      0  STON/O2. 3101282   7.9250   NaN        S  \n",
       "3      0            113803  53.1000  C123        S  \n",
       "4      0            373450   8.0500   NaN        S  "
      ]
     },
     "execution_count": 230,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train= pd.read_csv(\"train.csv\")\n",
    "test=pd.read_csv(\"test.csv\")\n",
    "\n",
    "train.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Exploratory Data Analysis and Data Cleaning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 231,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 891 entries, 0 to 890\n",
      "Data columns (total 12 columns):\n",
      "PassengerId    891 non-null int64\n",
      "Survived       891 non-null int64\n",
      "Pclass         891 non-null int64\n",
      "Name           891 non-null object\n",
      "Sex            891 non-null object\n",
      "Age            714 non-null float64\n",
      "SibSp          891 non-null int64\n",
      "Parch          891 non-null int64\n",
      "Ticket         891 non-null object\n",
      "Fare           891 non-null float64\n",
      "Cabin          204 non-null object\n",
      "Embarked       889 non-null object\n",
      "dtypes: float64(2), int64(5), object(5)\n",
      "memory usage: 83.6+ KB\n"
     ]
    }
   ],
   "source": [
    "train.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 232,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 418 entries, 0 to 417\n",
      "Data columns (total 11 columns):\n",
      "PassengerId    418 non-null int64\n",
      "Pclass         418 non-null int64\n",
      "Name           418 non-null object\n",
      "Sex            418 non-null object\n",
      "Age            332 non-null float64\n",
      "SibSp          418 non-null int64\n",
      "Parch          418 non-null int64\n",
      "Ticket         418 non-null object\n",
      "Fare           417 non-null float64\n",
      "Cabin          91 non-null object\n",
      "Embarked       418 non-null object\n",
      "dtypes: float64(2), int64(4), object(5)\n",
      "memory usage: 36.0+ KB\n"
     ]
    }
   ],
   "source": [
    "test.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 235,
   "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>PassengerId</th>\n",
       "      <th>Survived</th>\n",
       "      <th>Pclass</th>\n",
       "      <th>Age</th>\n",
       "      <th>SibSp</th>\n",
       "      <th>Parch</th>\n",
       "      <th>Fare</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>714.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "      <td>891.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>446.000000</td>\n",
       "      <td>0.383838</td>\n",
       "      <td>2.308642</td>\n",
       "      <td>29.699118</td>\n",
       "      <td>0.523008</td>\n",
       "      <td>0.381594</td>\n",
       "      <td>32.204208</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>257.353842</td>\n",
       "      <td>0.486592</td>\n",
       "      <td>0.836071</td>\n",
       "      <td>14.526497</td>\n",
       "      <td>1.102743</td>\n",
       "      <td>0.806057</td>\n",
       "      <td>49.693429</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.420000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>223.500000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>20.125000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>7.910400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>446.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>28.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>14.454200</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>668.500000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>38.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>31.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>891.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>80.000000</td>\n",
       "      <td>8.000000</td>\n",
       "      <td>6.000000</td>\n",
       "      <td>512.329200</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       PassengerId    Survived      Pclass         Age       SibSp  \\\n",
       "count   891.000000  891.000000  891.000000  714.000000  891.000000   \n",
       "mean    446.000000    0.383838    2.308642   29.699118    0.523008   \n",
       "std     257.353842    0.486592    0.836071   14.526497    1.102743   \n",
       "min       1.000000    0.000000    1.000000    0.420000    0.000000   \n",
       "25%     223.500000    0.000000    2.000000   20.125000    0.000000   \n",
       "50%     446.000000    0.000000    3.000000   28.000000    0.000000   \n",
       "75%     668.500000    1.000000    3.000000   38.000000    1.000000   \n",
       "max     891.000000    1.000000    3.000000   80.000000    8.000000   \n",
       "\n",
       "            Parch        Fare  \n",
       "count  891.000000  891.000000  \n",
       "mean     0.381594   32.204208  \n",
       "std      0.806057   49.693429  \n",
       "min      0.000000    0.000000  \n",
       "25%      0.000000    7.910400  \n",
       "50%      0.000000   14.454200  \n",
       "75%      0.000000   31.000000  \n",
       "max      6.000000  512.329200  "
      ]
     },
     "execution_count": 235,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Lets visualize our target variable."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 256,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x252c5b9f4a8>"
      ]
     },
     "execution_count": 256,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.countplot(train.Survived)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We have imbalanced classes in our target variable."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Age"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 236,
   "metadata": {},
   "outputs": [],
   "source": [
    "age_avg_train = train['Age'].mean()\n",
    "age_std_train = train['Age'].std()\n",
    "age_null_count = train['Age'].isnull().sum()\n",
    "age_null_random_list = np.random.randint(age_avg_train - age_std_train, age_avg_train + age_std_train, size=age_null_count)\n",
    "\n",
    "train['Age'][np.isnan(train['Age'])] = age_null_random_list\n",
    "train['Age'] = train['Age'].astype(int)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 237,
   "metadata": {},
   "outputs": [],
   "source": [
    "train['CategoricalAge'] = pd.cut(train['Age'], 5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x252c55ac2b0>"
      ]
     },
     "execution_count": 117,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=[10,5])\n",
    "sns.countplot(train.CategoricalAge, hue=train['Survived'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 238,
   "metadata": {},
   "outputs": [],
   "source": [
    "train.loc[train['Age']<=16, 'Age' ]=0\n",
    "train.loc[(train['Age']>16) & (train['Age']<=32), 'Age']=1\n",
    "train.loc[(train['Age']>32) & (train['Age']<=48), 'Age']=2\n",
    "train.loc[(train['Age']>48) & (train['Age']<=64), 'Age']=3\n",
    "train.loc[train['Age']>64, 'Age' ]=4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 239,
   "metadata": {},
   "outputs": [],
   "source": [
    "age_avg_test = test['Age'].mean()\n",
    "age_std_test = test['Age'].std()\n",
    "age_null_count = test['Age'].isnull().sum()\n",
    "age_null_random_list = np.random.randint(age_avg_test - age_std_test, age_avg_test + age_std_test, size=age_null_count)\n",
    "\n",
    "test['Age'][np.isnan(test['Age'])] = age_null_random_list\n",
    "test['Age'] = test['Age'].astype(int)\n",
    "\n",
    "test.loc[test['Age']<=16, 'Age' ]=0\n",
    "test.loc[(test['Age']>16) & (test['Age']<=32), 'Age']=1\n",
    "test.loc[(test['Age']>32) & (test['Age']<=48), 'Age']=2\n",
    "test.loc[(test['Age']>48) & (test['Age']<=64), 'Age']=3\n",
    "test.loc[test['Age']>64, 'Age' ]=4"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Title"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 240,
   "metadata": {},
   "outputs": [],
   "source": [
    "train['Title']=train['Name'].str.extract(' ([A-Za-z]+)\\.')\n",
    "\n",
    "train['Namelength']= train['Name'].apply(len)\n",
    "\n",
    "train['Title']=train['Title'].replace(['Major', 'Lady', 'Sir', 'Col', 'Capt', 'Countess','Jonkheer','Don', 'Rev', 'Dr' ], 'Rare')\n",
    "train['Title']=train['Title'].replace(['Mme', 'Ms','Mlle'], 'Miss')\n",
    "\n",
    "train['Title'] = train['Title'].map({\"Mr\": 1, \"Miss\": 2, \"Mrs\": 3, \"Master\": 4, \"Rare\": 5})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 241,
   "metadata": {},
   "outputs": [],
   "source": [
    "test['Title']=test['Name'].str.extract(' ([A-Za-z]+)\\.')\n",
    "\n",
    "test['Namelength']= test['Name'].apply(len)\n",
    "\n",
    "test['Title']=test['Title'].replace(['Major', 'Lady', 'Sir', 'Col', 'Capt', 'Countess','Jonkheer','Don', 'Rev', 'Dr' ], 'Rare')\n",
    "test['Title']=test['Title'].replace(['Mme', 'Ms','Mlle'], 'Miss')\n",
    "\n",
    "test['Title'] = test['Title'].map({\"Mr\": 1, \"Miss\": 2, \"Mrs\": 3, \"Master\": 4, \"Rare\": 5})\n",
    "\n",
    "\n",
    "test['Title']=test['Title'].fillna('5')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Fare"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 178,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    891.000000\n",
       "mean      32.204208\n",
       "std       49.693429\n",
       "min        0.000000\n",
       "25%        7.910400\n",
       "50%       14.454200\n",
       "75%       31.000000\n",
       "max      512.329200\n",
       "Name: Fare, dtype: float64"
      ]
     },
     "execution_count": 178,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.Fare.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 242,
   "metadata": {},
   "outputs": [],
   "source": [
    "train.loc[train['Fare']<=7.91, 'Fare' ]=0\n",
    "train.loc[(train['Fare']>7.91) & (train['Fare']<=14.454), 'Fare']=1\n",
    "train.loc[(train['Fare']>14.454) & (train['Fare']<=31), 'Fare']=2\n",
    "train.loc[(train['Fare']>31), 'Fare']=3\n",
    "train['Fare']=train['Fare'].astype(int)\n",
    "\n",
    "test['Fare'].fillna(35.62, inplace=True)\n",
    "test.loc[test['Fare']<=7.91, 'Fare' ]=0\n",
    "test.loc[(test['Fare']>7.91) & (test['Fare']<=14.454), 'Fare']=1\n",
    "test.loc[(test['Fare']>14.454) & (test['Fare']<=31), 'Fare']=2\n",
    "test.loc[(test['Fare']>31), 'Fare']=3\n",
    "test['Fare']=test['Fare'].astype(int)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### SibSp, Parch, Embarked, Sex"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 243,
   "metadata": {},
   "outputs": [],
   "source": [
    "train['Family']= train['SibSp'] + train['Parch']+1\n",
    "test['Family']= test['SibSp'] + test['Parch']+1\n",
    "\n",
    "train['Embarked']=train['Embarked'].fillna('S')\n",
    "\n",
    "train['Embarked'] = train['Embarked'].map( {'S': 0, 'C': 1, 'Q': 2} ).astype(int)\n",
    "test['Embarked'] = test['Embarked'].map( {'S': 0, 'C': 1, 'Q': 2} ).astype(int)\n",
    "\n",
    "train['Sex'] = train['Sex'].map( {'female': 0, 'male': 1} ).astype(int)\n",
    "test['Sex'] = test['Sex'].map( {'female': 0, 'male': 1} ).astype(int)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 244,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((891, 8), (418, 8))"
      ]
     },
     "execution_count": 244,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.drop(['PassengerId','Name', 'Ticket','SibSp','Embarked','Cabin','Parch','CategoricalAge'], axis=1, inplace=True)\n",
    "test.drop(['Name', 'Ticket','SibSp','Embarked','Cabin','Parch'], axis=1, inplace=True)\n",
    "\n",
    "train.shape, test.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Predictive Modeling"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 183,
   "metadata": {},
   "outputs": [],
   "source": [
    "y=np.asarray(train['Survived'])\n",
    "\n",
    "train.drop(['Survived'], axis=1, inplace=True)\n",
    "\n",
    "x=np.asarray(train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Logistic Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 204,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "It took 0.011 minutes to run.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0.7379460928924473"
      ]
     },
     "execution_count": 204,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ts= time.time()\n",
    "parameter=[{'C':[10,7,5,2,1,0.1,0.01]}]\n",
    "\n",
    "LR= LogisticRegression()\n",
    "\n",
    "LRgrid=GridSearchCV(LR, parameter, cv=7,scoring='f1')\n",
    "\n",
    "LRgrid.fit(x, y)\n",
    "\n",
    "print(\"\\nIt took\",np.round((time.time()-ts)/60,3),\"minutes to run.\" )\n",
    "\n",
    "LRgrid.best_score_"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### K Nearest Neigbours"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 215,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "It took 0.165 minutes to run.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0.740264588546065"
      ]
     },
     "execution_count": 215,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ts= time.time()\n",
    "parameter=[{'n_neighbors':[5,6,7,8,9,10,11,12,13,14,15],\n",
    "           'weights':['distance', 'uniform'],\n",
    "           'p':[1,2]}]\n",
    "\n",
    "KNN= KNeighborsClassifier()\n",
    "\n",
    "KNNgrid=GridSearchCV(KNN, parameter, cv=7,scoring='f1')\n",
    "\n",
    "KNNgrid.fit(x, y)\n",
    "\n",
    "print(\"\\nIt took\",np.round((time.time()-ts)/60,3),\"minutes to run.\" )\n",
    "\n",
    "KNNgrid.best_score_"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Decision Trees"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 213,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "It took 0.446 minutes to run.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0.7802134854523467"
      ]
     },
     "execution_count": 213,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ts= time.time()\n",
    "\n",
    "parameter=[{'criterion':[\"entropy\",\"gini\"],\n",
    "           'max_depth':[2,3,4,5,6],\n",
    "           'min_samples_leaf':[1,2,3,4,5,6,7,8,],\n",
    "           'min_samples_split':[2,3,4,5,6]}]\n",
    "\n",
    "DT= DecisionTreeClassifier()\n",
    "\n",
    "DTgrid=GridSearchCV(DT, parameter, cv=7,scoring='f1')\n",
    "\n",
    "DTgrid.fit(x, y)\n",
    "\n",
    "print(\"\\nIt took\",np.round((time.time()-ts)/60,3),\"minutes to run.\" )\n",
    "\n",
    "DTgrid.best_score_"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Ensemble Model: \n",
    "#### Random Forest"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 216,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "It took 17.603 minutes to run.\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0.7762353116091573"
      ]
     },
     "execution_count": 216,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ts= time.time()\n",
    "parameter=[{'n_estimators':[50,100],\n",
    "           'max_depth':[3,4,5,6,7],\n",
    "           'min_samples_split':[2,3,4,5],\n",
    "           'max_features':[1,2,3,4,5]}]\n",
    "\n",
    "RF=RandomForestClassifier(n_jobs=-1)\n",
    "\n",
    "RFgrid=GridSearchCV(RF, parameter, cv=7,scoring='f1')\n",
    "\n",
    "RFgrid.fit(x, y)\n",
    "print(\"\\nIt took\",np.round((time.time()-ts)/60,3),\"minutes to run.\" )\n",
    "RFgrid.best_score_"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Predictions of test data using Descision Tree Classifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 224,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "idd=np.asarray(test['PassengerId'])\n",
    "xx=np.asarray(test.drop('PassengerId', axis=1))\n",
    "predict= DTgrid.predict(xx)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 228,
   "metadata": {},
   "outputs": [],
   "source": [
    "Submission = pd.DataFrame({ 'PassengerId': idd,\n",
    "                            'Survived': predict })\n",
    "Submission.to_csv(\"submit.csv\", index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}