Starter_Notebook.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.05087,
     "end_time": "2020-11-22T06:37:57.456878",
     "exception": false,
     "start_time": "2020-11-22T06:37:57.406008",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Introduction :An interpretation of the data with respect to the Movie.\n",
    "                                                                 \n",
    "                                         \n",
    "In this notebook , the titanic dataset is explored with relevance to the perspectives that were been projected in the famous James Cameron movie Titanic based on the tragic story of the RMS Titanic , in the cold Atlantic Ocean. Now , lets not get deep in the story , which might lead us nowhere near to the solution. But if one may question , how the story has thrown light on this dataset , my answer is , the certain facts that were shown in the movie , which will be supported by the graphs as we go through the notebook ,helped me in Feature selection. \n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.048921,
     "end_time": "2020-11-22T06:37:57.554873",
     "exception": false,
     "start_time": "2020-11-22T06:37:57.505952",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "<img src=\"https://cdn.britannica.com/79/4679-050-BC127236/Titanic.jpg\">"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.049101,
     "end_time": "2020-11-22T06:37:57.653476",
     "exception": false,
     "start_time": "2020-11-22T06:37:57.604375",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "***Bon Voyage !!***"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.048886,
     "end_time": "2020-11-22T06:37:57.751316",
     "exception": false,
     "start_time": "2020-11-22T06:37:57.702430",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Playing with data :\n",
    "\n",
    "As the title suggests , I have no experience of how things are in Kaggle , thus the \"playing\" is sort of a , playing with borrowed toys."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
    "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5",
    "execution": {
     "iopub.execute_input": "2020-11-22T06:37:57.858233Z",
     "iopub.status.busy": "2020-11-22T06:37:57.857336Z",
     "iopub.status.idle": "2020-11-22T06:37:57.863722Z",
     "shell.execute_reply": "2020-11-22T06:37:57.862917Z"
    },
    "papermill": {
     "duration": 0.062127,
     "end_time": "2020-11-22T06:37:57.863844",
     "exception": false,
     "start_time": "2020-11-22T06:37:57.801717",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import numpy as np # linear algebra\n",
    "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
    "\n",
    "import os\n",
    "for dirname, _, filenames in os.walk('/kaggle/input'):\n",
    "    for filename in filenames:\n",
    "        print(os.path.join(dirname, filename))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "_cell_guid": "79c7e3d0-c299-4dcb-8224-4455121ee9b0",
    "_uuid": "d629ff2d2480ee46fbb7e2d37f6b5fab8052498a",
    "execution": {
     "iopub.execute_input": "2020-11-22T06:37:57.968450Z",
     "iopub.status.busy": "2020-11-22T06:37:57.967728Z",
     "iopub.status.idle": "2020-11-22T06:37:58.818322Z",
     "shell.execute_reply": "2020-11-22T06:37:58.816869Z"
    },
    "papermill": {
     "duration": 0.904174,
     "end_time": "2020-11-22T06:37:58.818451",
     "exception": false,
     "start_time": "2020-11-22T06:37:57.914277",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import sklearn\n",
    "import seaborn as sb"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.050353,
     "end_time": "2020-11-22T06:37:58.919123",
     "exception": false,
     "start_time": "2020-11-22T06:37:58.868770",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "* Loading the datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:37:59.025935Z",
     "iopub.status.busy": "2020-11-22T06:37:59.025065Z",
     "iopub.status.idle": "2020-11-22T06:37:59.061086Z",
     "shell.execute_reply": "2020-11-22T06:37:59.061652Z"
    },
    "papermill": {
     "duration": 0.092371,
     "end_time": "2020-11-22T06:37:59.061819",
     "exception": false,
     "start_time": "2020-11-22T06:37:58.969448",
     "status": "completed"
    },
    "tags": []
   },
   "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": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train = pd.read_csv('./kaggle/input/titanic/train.csv')\n",
    "test = pd.read_csv('./kaggle/input/titanic/test.csv')\n",
    "train.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.050301,
     "end_time": "2020-11-22T06:37:59.164502",
     "exception": false,
     "start_time": "2020-11-22T06:37:59.114201",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "* Combining the train and test datasets."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:37:59.278970Z",
     "iopub.status.busy": "2020-11-22T06:37:59.278200Z",
     "iopub.status.idle": "2020-11-22T06:37:59.280610Z",
     "shell.execute_reply": "2020-11-22T06:37:59.281201Z"
    },
    "papermill": {
     "duration": 0.065324,
     "end_time": "2020-11-22T06:37:59.281318",
     "exception": false,
     "start_time": "2020-11-22T06:37:59.215994",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "combine = [train,test]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.050817,
     "end_time": "2020-11-22T06:37:59.384880",
     "exception": false,
     "start_time": "2020-11-22T06:37:59.334063",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "* Checking the error or missing value percentages of each feature."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:37:59.494623Z",
     "iopub.status.busy": "2020-11-22T06:37:59.493741Z",
     "iopub.status.idle": "2020-11-22T06:37:59.503381Z",
     "shell.execute_reply": "2020-11-22T06:37:59.502833Z"
    },
    "papermill": {
     "duration": 0.067981,
     "end_time": "2020-11-22T06:37:59.503480",
     "exception": false,
     "start_time": "2020-11-22T06:37:59.435499",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "PassengerId 0.0\n",
      "Survived 0.0\n",
      "Pclass 0.0\n",
      "Name 0.0\n",
      "Sex 0.0\n",
      "Age 19.865319865319865\n",
      "SibSp 0.0\n",
      "Parch 0.0\n",
      "Ticket 0.0\n",
      "Fare 0.0\n",
      "Cabin 77.10437710437711\n",
      "Embarked 0.2244668911335578\n"
     ]
    }
   ],
   "source": [
    "for c in train.columns:\n",
    "    print(c, str(100*train[c].isnull().sum()/len(train)))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.050696,
     "end_time": "2020-11-22T06:37:59.605688",
     "exception": false,
     "start_time": "2020-11-22T06:37:59.554992",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "We see there are missing values in *Age* , *Cabin* and *Embarked* data. As the values of Cabin are in string , we are going to disregard it. According to the movie and common human sentiments , we will use the age values."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:37:59.713352Z",
     "iopub.status.busy": "2020-11-22T06:37:59.712625Z",
     "iopub.status.idle": "2020-11-22T06:37:59.715110Z",
     "shell.execute_reply": "2020-11-22T06:37:59.715625Z"
    },
    "papermill": {
     "duration": 0.058876,
     "end_time": "2020-11-22T06:37:59.715748",
     "exception": false,
     "start_time": "2020-11-22T06:37:59.656872",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "train['Age'] = train['Age'].fillna(train['Age'].mean())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.052653,
     "end_time": "2020-11-22T06:37:59.819378",
     "exception": false,
     "start_time": "2020-11-22T06:37:59.766725",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Here , I have replaced the missing values of age with the average of all the ages of the people who boarded the Titanic.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:37:59.932193Z",
     "iopub.status.busy": "2020-11-22T06:37:59.931299Z",
     "iopub.status.idle": "2020-11-22T06:37:59.939182Z",
     "shell.execute_reply": "2020-11-22T06:37:59.938133Z"
    },
    "papermill": {
     "duration": 0.068758,
     "end_time": "2020-11-22T06:37:59.939340",
     "exception": false,
     "start_time": "2020-11-22T06:37:59.870582",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "PassengerId 0.0\n",
      "Survived 0.0\n",
      "Pclass 0.0\n",
      "Name 0.0\n",
      "Sex 0.0\n",
      "Age 0.0\n",
      "SibSp 0.0\n",
      "Parch 0.0\n",
      "Ticket 0.0\n",
      "Fare 0.0\n",
      "Cabin 77.10437710437711\n",
      "Embarked 0.2244668911335578\n"
     ]
    }
   ],
   "source": [
    "for c in train.columns:\n",
    "    print(c, str(100*train[c].isnull().sum()/len(train)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.051558,
     "end_time": "2020-11-22T06:38:00.043610",
     "exception": false,
     "start_time": "2020-11-22T06:37:59.992052",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Now we can see that there are no missing values in Age column."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.051812,
     "end_time": "2020-11-22T06:38:00.147231",
     "exception": false,
     "start_time": "2020-11-22T06:38:00.095419",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "* Checking how many people from differnt class and sex had survived."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:00.273575Z",
     "iopub.status.busy": "2020-11-22T06:38:00.272749Z",
     "iopub.status.idle": "2020-11-22T06:38:00.277520Z",
     "shell.execute_reply": "2020-11-22T06:38:00.276739Z"
    },
    "papermill": {
     "duration": 0.077943,
     "end_time": "2020-11-22T06:38:00.277641",
     "exception": false,
     "start_time": "2020-11-22T06:38:00.199698",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   Pclass  Survived\n",
      "0       1  0.629630\n",
      "1       2  0.472826\n",
      "2       3  0.242363\n",
      "      Sex  Survived\n",
      "0  female  0.742038\n",
      "1    male  0.188908\n"
     ]
    }
   ],
   "source": [
    "dependencies_sex = train[['Sex', 'Survived']].groupby(['Sex'],as_index=False).mean()\n",
    "dependencies_Pclass = train[['Pclass', 'Survived']].groupby(['Pclass'],as_index=False).mean()\n",
    "\n",
    "print(dependencies_Pclass)\n",
    "print(dependencies_sex)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.05234,
     "end_time": "2020-11-22T06:38:00.384780",
     "exception": false,
     "start_time": "2020-11-22T06:38:00.332440",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "The large difference in the numbers shows that these two features - *Pclass* and *Sex* , have influence on the survival of the boarded passengers. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.051954,
     "end_time": "2020-11-22T06:38:00.488914",
     "exception": false,
     "start_time": "2020-11-22T06:38:00.436960",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Graphs that support my feature selection based on the movie."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.052556,
     "end_time": "2020-11-22T06:38:00.593845",
     "exception": false,
     "start_time": "2020-11-22T06:38:00.541289",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "* Starting off with the survivor count\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:00.705230Z",
     "iopub.status.busy": "2020-11-22T06:38:00.704363Z",
     "iopub.status.idle": "2020-11-22T06:38:00.881899Z",
     "shell.execute_reply": "2020-11-22T06:38:00.880919Z"
    },
    "papermill": {
     "duration": 0.235438,
     "end_time": "2020-11-22T06:38:00.882008",
     "exception": false,
     "start_time": "2020-11-22T06:38:00.646570",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Survived', ylabel='count'>"
      ]
     },
     "execution_count": 9,
     "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": [
    "sb.set_style('whitegrid')\n",
    "sb.countplot(x='Survived',data=train,palette='YlOrBr')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.053835,
     "end_time": "2020-11-22T06:38:00.991515",
     "exception": false,
     "start_time": "2020-11-22T06:38:00.937680",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "* Survivor Count based on Sex "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:01.114316Z",
     "iopub.status.busy": "2020-11-22T06:38:01.104256Z",
     "iopub.status.idle": "2020-11-22T06:38:01.253628Z",
     "shell.execute_reply": "2020-11-22T06:38:01.254121Z"
    },
    "papermill": {
     "duration": 0.209577,
     "end_time": "2020-11-22T06:38:01.254257",
     "exception": false,
     "start_time": "2020-11-22T06:38:01.044680",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Survived', ylabel='count'>"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEECAYAAAAlEzNMAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAAAXXUlEQVR4nO3de0zV9/3H8dc5wDkgFw1a2xnEgUrFEIKNERsnLcsUt0W7GUXF4ExbTV1cC50TWhRwU4HYEVcXtVobVlpheOtMV5PVy2qiK5s0XqpHrOjYUNsx5ibnTA4I5/eHkenPS1HPBfk8H395OJxv3+ebnvPk+z3nfI7F4/F4BAAwljXQAwAAAosQAIDhCAEAGI4QAIDhCAEAGC440APcr6NHj8putwd6DAB4pLjdbqWkpNzxukcuBHa7XYmJiYEeAwAeKQ6H467XcWoIAAxHCADAcIQAAAz3yL1GAAB309HRoaamJrW1tQV6lIAJDQ1VTEyMQkJCenwbQgCgz2hqalJkZKS++c1vymKxBHocv/N4PGppaVFTU5Pi4uJ6fDtODQHoM9ra2jRw4EAjIyBJFotFAwcOvO8jIkIAoE8xNQI3PMj9JwQAYDheIwCA+7Rp0yYdPnxYVqtVFotFubm5SkpKCvRYD8zIEHS42xVitwV6jF6BfQHcn7Nnz2r//v2qqqqSxWKRw+FQXl6edu/eHejRHpiRIQix25SfNCfQY/QKpZ9XBXoE4JESHR2tixcvavv27UpLS1NiYqK2b9+u+vp6rVy5UpI0YMAArV69WkeOHNHmzZv13nvv6de//rXa2tq0dOnSAN+D2/EaAQDch+joaG3YsEGfffaZZs2apSlTpujAgQNavny5ioqKVFlZqbS0NL399ttKT0/X6NGjlZeXp7/85S969dVXAz3+HRl5RAAAD6qxsVEREREqKSmRJJ04cUILFy5UW1ubVqxYIen6B9tuvI9/wYIFSk9P19q1axUc3DufcnvnVADQS9XX16uqqkobN26U3W5XXFycIiMj9fjjj6usrExDhgxRXV2dmpubJUlFRUUqKCjQunXrlJqaqv79+wf4HtyOEADAfZg8ebIaGho0c+ZM9evXTx6PR0uXLtUTTzyhvLw8dXZ2SpJWrVql3/zmNxo4cKDmzp2rsLAwLVu2TOvWrQvwPbidxePxeAI9xP1wOBxe+T4CXiy+jheL0Zd46/nhUXen/XCvfcOLxQBgOEIAAIYjBABgOEIAAIYjBABgOEIAoM/qcLf36u31FnyOAECf5e11xXzxduudO3fq3LlzWrJkide33VMcEQCA4TgiAAAv2blzpw4cOKC2tjY1Nzdr3rx52rdvn7744gstXbpUX375pf7whz/o2rVrioyMvO1TxpWVlfrwww9lsVj0ve99T/PmzfPL3IQAALzI5XLpnXfe0e9//3tVVFSopqZGtbW1qqioUFJSkioqKmS1WvXCCy/oxIkT3bc7e/asPvroI23dulUWi0Xz58/Xt771LcXHx/t8ZkIAAF50YxmHyMhIDR8+XBaLRf3791dHR4dCQkL06quvql+/fvryyy917dq17tudOXNGFy9e1Pz58yVJ//nPf/S3v/2NEADAo+ZuXx7f0dGhvXv3atu2bbp69aqmT5+um5d6i4+P14gRI/T222/LYrGooqJCCQkJfpmZEADoszrc7V59p8/DfLVrcHCwwsLCNH36dNlsNj322GP6xz/+0X39qFGj9PTTT2vOnDlqb29XcnKyHn/8cW+Nfk+sPmo4Vh9FX8Lqo9ex+igA4L4QAgAwHCEAAMMRAgAwHCEAAMMRAgB9VleHd1cL9fb2eguffY6gpaVF06dP1zvvvKPg4GDl5+fLYrFo5MiRKioqktVqVU1NjaqrqxUcHKxFixYpPT3dV+MAMJA1xKazr2R5bXsjfrX1ntd3dnZq4cKF+u9//6uNGzeqf//+XvnvTpgwQYcOHfLKtu7EJ0cEHR0dKiwsVGhoqCSppKREOTk52rp1qzwej/bt26fm5mZVVlaqurpaW7ZsUXl5udrb+2ZtAZihublZly9fVlVVldci4A8+OSIoKyvT7NmztWnTJknSyZMnNW7cOElSWlqaDh06JKvVqjFjxshms8lmsyk2NlanT59WcnKyL0YCAJ9bvny5/vrXv+q1116Ty+XS5cuXJUnLli3Tk08+qUmTJmnMmDFqbGzU+PHj1draquPHjysuLk5r1qzRmTNnVFpaqq6uLl25ckXLli3TU0891b39+vp6rVy5UpI0YMAArV69WpGRkQ89t9dDsHPnTkVHR2vixIndIfB4PN3rb4SHh6u1tVVOp/OWOxAeHi6n0/m123e73XI4HA81I588vNXD7k+gt+jo6NDVq1e7L4eFhXn9v3Hz9v+/vLw85efnKyoqSqNGjVJmZqYaGxtVWFioiooKXbhwQW+99ZYGDRqkZ555RpWVlVqyZIm+//3v66uvvtKpU6eUk5OjkSNH6qOPPlJNTY0SExPl8Xh09epVFRQUqLi4WMOHD9euXbu0YcMG/eQnP7njfrifx7XXQ7Bjxw5ZLBb96U9/ksPhUF5env71r391X+9yuRQVFaWIiAi5XK5bft6Tstntdp7IvYz9ib7C4XD45Mn/ZvfafmhoqKxWq86dO6cjR45o7969kiSn06mwsDANGDCgezXRfv36KSkpSZIUFRUlq9WqmJgYbdmyRaGhoXK5XIqIiFBYWJgsFovCwsJ0/vx5lZWVSbr+ZB8XF3fHeUJCQu64xMTdeD0E77//fve/s7OzVVxcrDVr1qi2tlapqak6ePCgxo8fr+TkZK1du1Zut1vt7e1qaGjw20p7AOBL8fHxmjZtmqZOnaqWlhZt27ZN0t1XJr1h1apVeuONNzR8+HC9+eabunDhwi3Xx8XFqaysTEOGDFFdXZ2am5u9Mq9fVh/Ny8vT8uXLVV5ervj4eGVkZCgoKEjZ2dnKysqSx+NRbm6u7Ha7P8YBYIiujvavfafP/W7PGvL1q4++9NJLKigoUE1NjZxOpxYvXtyj7U+bNk0//vGPNXDgQD3xxBPdrzHcUFxcrLy8PHV2dkq6Hg5vYPVRw7H6KPoSVh+9jtVHAQD3hRAAgOEIAYA+5RE72+11D3L/CQGAPiM0NFQtLS3GxsDj8ailpaV7VYee4juLAfQZMTExampq8trbKh9FoaGhiomJua/bEAIAfUZISIji4uICPcYjh1NDAGA4QgAAhiMEAGA4QgAAhiMEAGA4QgAAhiMEAGA4QgAAhiMEAGA4QgAAhiMEAGA4QgAAhiMEAGA4QgAAhiMEAGA4QgAAhiMEAGA4QgAAhiMEAGA4QgAAhiMEAGA4QgAAhiMEAGA4QgAAhiMEAGA4QgAAhiMEAGA4QgAAhiMEAGA4QgAAhgv2xUY7Ozu1bNkynT9/XkFBQSopKZHH41F+fr4sFotGjhypoqIiWa1W1dTUqLq6WsHBwVq0aJHS09N9MRIA4C58EoIDBw5Ikqqrq1VbW9sdgpycHKWmpqqwsFD79u1TSkqKKisrtWPHDrndbmVlZWnChAmy2Wy+GAsAcAc+CcF3vvMdPfvss5KkixcvatCgQfrjH/+ocePGSZLS0tJ06NAhWa1WjRkzRjabTTabTbGxsTp9+rSSk5N9MRYA4A58EgJJCg4OVl5enj7++GO9+eabOnDggCwWiyQpPDxcra2tcjqdioyM7L5NeHi4nE7nPbfrdrvlcDgearbExMSHun1f87D7E8CjzWchkKSysjItWbJEmZmZcrvd3T93uVyKiopSRESEXC7XLT+/OQx3YrfbeSL3MvYn0Pfd6w8+n7xr6IMPPtBbb70lSQoLC5PFYlFSUpJqa2slSQcPHtTYsWOVnJysuro6ud1utba2qqGhQQkJCb4YCQBwFz45Ipg8ebJee+01zZ07V9euXdPrr7+u4cOHa/ny5SovL1d8fLwyMjIUFBSk7OxsZWVlyePxKDc3V3a73RcjAQDuwuLxeDyBHuJ+OBwOr5zKyE+a44VpHn2ln1cFegQAfnCv504+UAYAhiMEAGA4QgAAhiMEAGA4QgAAhiMEAGA4QgAAhiMEAGA4QgAAhutRCLZt23bL5XfffdcnwwAA/O+eaw19+OGH2r9/v2pra/Xpp59Kuv7tY1988YXmzZvnlwEBAL51zxBMnDhRjz32mP79739r1qxZkiSr1aqhQ4f6ZTgAgO/dMwT9+/dXamqqUlNT1dLS0v2dAp2dnX4ZDgDgez1ahnrFihX65JNPNHjwYHk8HlksFlVXV/t6NgCAH/QoBMeOHdPevXtltfImIwDoa3r0zD5s2LBbvmoSANB39OiI4NKlS0pPT9ewYcMkiVNDANCH9CgEv/zlL309BwAgQHoUgl27dt32s8WLF3t9GACA//UoBIMGDZIkeTwenTp1Sl1dXT4dCgDgPz0KwezZs2+5/OKLL/pkGACA//UoBOfPn+/+d3Nzsy5duuSzgQAA/tWjEBQWFnb/2263a+nSpT4bCADgXz0KQWVlpS5fvqy///3viomJUXR0tK/nAgD4SY8+ULZnzx7Nnj1bGzdu1KxZs/S73/3O13MBAPykR0cEFRUV2rlzp8LDw+V0OvWjH/1Izz33nK9nA2Cwro52WUNsgR6jV/D1vuhRCCwWi8LDwyVJERERstvtPhsIACTJGmLT2VeyAj1GrzDiV1t9uv0ehSA2NlalpaUaO3as6urqFBsb69OhAAD+06PXCDIzM9W/f38dPnxYO3fu1Ny5c309FwDAT3oUgtLSUk2aNEmFhYXavn27SktLfT0XAMBPehSC4OBgjRgxQpI0dOhQvpcAAPqQHr1GMGTIEJWXlyslJUXHjx/X4MGDfT0XAMBPevSnfUlJiaKjo/XJJ58oOjpaJSUlvp4LAOAnPToisNvtmj9/vo9HAQAEAif7AcBwhAAADEcIAMBwPXqN4H50dHTo9ddf14ULF9Te3q5FixZpxIgRys/Pl8Vi0ciRI1VUVCSr1aqamhpVV1crODhYixYtUnp6urfHAQB8Da+HYPfu3RowYIDWrFmjy5cv64c//KFGjRqlnJwcpaamqrCwUPv27VNKSooqKyu1Y8cOud1uZWVlacKECbLZWGQKAPzJ6yGYMmWKMjIyui8HBQXp5MmTGjdunCQpLS1Nhw4dktVq1ZgxY2Sz2WSz2RQbG6vTp08rOTn5ntt3u91yOBwPNWNiYuJD3b6vedj9CfgCj9Nb+fJx6vUQ3Fil1Ol06uWXX1ZOTo7KyspksVi6r29tbZXT6VRkZOQtt3M6nV+7fbvdzv8gXsb+BHq/h32c3iskPnmx+NKlS5o3b56ee+45TZ069ZYlKVwul6KiohQRESGXy3XLz28OAwDAP7wegn/+8596/vnn9bOf/UwzZsyQJI0ePVq1tbWSpIMHD2rs2LFKTk5WXV2d3G63Wltb1dDQoISEBG+PAwD4Gl4/NbRx40ZduXJF69ev1/r16yVJBQUFWrlypcrLyxUfH6+MjAwFBQUpOztbWVlZ8ng8ys3N5QtvACAALB6PxxPoIe6Hw+Hwyjnt/KQ5Xpjm0Vf6eVWgRwDuim8ou84b31B2r+dOPlAGAIYjBABgOEIAAIYjBABgOEIAAIYjBABgOEIAAIYjBABgOEIAAIYjBABgOEIAAIYjBABgOEIAAIYjBABgOEIAAIYjBABgOEIAAIYjBABgOEIAAIYjBABgOEIAAIYjBABgOEIAAIYjBABgOEIAAIYjBABgOEIAAIYjBABgOEIAAIYjBABgOEIAAIYjBABgOEIAAIYjBABgOEIAAIYjBEAv0uFuD/QIMFCwrzZ87NgxvfHGG6qsrFRjY6Py8/NlsVg0cuRIFRUVyWq1qqamRtXV1QoODtaiRYuUnp7uq3GAR0KI3ab8pDmBHqNXKP28KtAjGMMnRwSbN2/WsmXL5Ha7JUklJSXKycnR1q1b5fF4tG/fPjU3N6uyslLV1dXasmWLysvL1d7OX0MA4G8+CUFsbKzWrVvXffnkyZMaN26cJCktLU2HDx/W8ePHNWbMGNlsNkVGRio2NlanT5/2xTgAgHvwyamhjIwMNTU1dV/2eDyyWCySpPDwcLW2tsrpdCoyMrL7d8LDw+V0Or922263Ww6H46HmS0xMfKjb9zUPuz/hPfy/ibvx5ePUZ68R3Mxq/d+Bh8vlUlRUlCIiIuRyuW75+c1huBu73c6DxcvYn0Dv97CP03uFxC/vGho9erRqa2slSQcPHtTYsWOVnJysuro6ud1utba2qqGhQQkJCf4YBwBwE78cEeTl5Wn58uUqLy9XfHy8MjIyFBQUpOzsbGVlZcnj8Sg3N1d2u90f4wAAbuKzEMTExKimpkaSFBcXp/fee++238nMzFRmZqavRgAA9AAfKAMAwxECADAcIQAAwxECw3V18GnuG9gXMJVf3jWE3ssaYtPZV7ICPUavMOJXWwM9AhAQHBEAgOEIAQAYjhAAgOEIAQAYjhAAgOEIAQAYjhAAgOEIAQAYjhAAgOEIAQAYjhAAgOEIAQAYjhAAgOEIAQAYjhAAgOEIAQAYjhAAgOEIAQAYjhAAgOEIAQAYjhAAgOEIAQAYjhAAgOEIAQAYjhAAgOEIAQAYjhAAgOEIAQAYjhAAgOEIAQAYjhAAgOGCAz1AV1eXiouLVV9fL5vNppUrV2rYsGGBHgsAjBHwI4K9e/eqvb1dv/3tb/XTn/5UpaWlgR4JAIwS8BDU1dVp4sSJkqSUlBR9/vnnAZ4IAMxi8Xg8nkAOUFBQoMmTJ+uZZ56RJD377LPau3evgoPvfNbq6NGjstvt/hwRAB55brdbKSkpd7wu4K8RREREyOVydV/u6uq6awQk3fWOAAAeTMBPDT311FM6ePCgpOt/7SckJAR4IgAwS8BPDd1419CZM2fk8Xi0evVqDR8+PJAjAYBRAh4CAEBgBfzUEAAgsAgBABiOEACA4QiBgbq6ulRYWKhZs2YpOztbjY2NgR4JuMWxY8eUnZ0d6DGMEfDPEcD/bl7W4+jRoyotLdWGDRsCPRYgSdq8ebN2796tsLCwQI9iDI4IDMSyHujNYmNjtW7dukCPYRRCYCCn06mIiIjuy0FBQbp27VoAJwL+JyMj456rC8D7CIGB7ndZDwB9GyEwEMt6ALgZfwYaaNKkSTp06JBmz57dvawHAHOxxAQAGI5TQwBgOEIAAIYjBABgOEIAAIYjBABgOEIA423atEnz58/X888/rxdeeOGhltxYtWqVLl68+MC3z83NVW1t7QPfHngQfI4ARjt79qz279+vqqoqWSwWORwO5eXlaffu3Q+0vYKCAi9PCPgeRwQwWnR0tC5evKjt27frq6++UmJiorZv367s7Gw1NDRIkqqqqrRu3To1NTVp6tSpys7O1ubNm/Xd735XNz6Gs2LFCn388cfdt5s+fbqampokSXv27NHKlSvV2tqql19+WdnZ2crOzlZ9fb0k6f3339cPfvADLViwgCXBERCEAEaLjo7Whg0b9Nlnn2nWrFmaMmWKDhw4cNffb25u1pYtW7RgwQI9+eSTOnLkiNrb2/XnP/9Z6enp3b83Y8YMffDBB5KkXbt2KTMzUxs3btT48eNVWVmpX/ziFyouLlZra6veffdd1dTUaP369ero6PD1XQZuw6khGK2xsVEREREqKSmRJJ04cUILFy7UoEGDun/n5g/fx8TEyGazSZIyMzO1a9cuNTc369vf/vYtC/dNmzZNc+bM0cyZM+V0OpWQkKAzZ87o008/1Z49eyRJV65c0blz5zRixIjubSYnJ/v8PgP/H0cEMFp9fb2Ki4vldrslSXFxcYqMjNSAAQPU3NwsSTp16lT371ut/3vIPP3003I4HNqxY4dmzJhxy3YjIiKUlJSkkpISTZ8+XZIUHx+v+fPnq7KyUmvXrtXUqVM1dOhQnT17Vm1tbers7JTD4fD1XQZuwxEBjDZ58mQ1NDRo5syZ6tevnzwej5YuXaqQkBD9/Oc/1ze+8Q0NHjz4jre1WCzKyMjQ4cOHNWzYsNuunzlzpl588cXuRf1eeuklFRQUqKamRk6nU4sXL1Z0dLReeeUVzZ49W9HR0XwrFwKCRecAwHCcGgIAwxECADAcIQAAwxECADAcIQAAwxECADAcIQAAw/0fzdvqgAtxAyIAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sb.set_style('whitegrid')\n",
    "sb.countplot(x='Survived',hue='Sex',data=train,palette='rocket')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.054314,
     "end_time": "2020-11-22T06:38:01.365418",
     "exception": false,
     "start_time": "2020-11-22T06:38:01.311104",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "* Survivor Count based on Class of Passenger"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:01.491280Z",
     "iopub.status.busy": "2020-11-22T06:38:01.490629Z",
     "iopub.status.idle": "2020-11-22T06:38:01.672002Z",
     "shell.execute_reply": "2020-11-22T06:38:01.672566Z"
    },
    "papermill": {
     "duration": 0.252569,
     "end_time": "2020-11-22T06:38:01.672699",
     "exception": false,
     "start_time": "2020-11-22T06:38:01.420130",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:xlabel='Survived', ylabel='count'>"
      ]
     },
     "execution_count": 11,
     "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": [
    "sb.set_style('whitegrid')\n",
    "sb.countplot(x='Survived',hue='Pclass',data=train,palette='icefire')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.057915,
     "end_time": "2020-11-22T06:38:01.805597",
     "exception": false,
     "start_time": "2020-11-22T06:38:01.747682",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "* Survival Count based on Age"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:01.942686Z",
     "iopub.status.busy": "2020-11-22T06:38:01.941722Z",
     "iopub.status.idle": "2020-11-22T06:38:02.791461Z",
     "shell.execute_reply": "2020-11-22T06:38:02.792048Z"
    },
    "papermill": {
     "duration": 0.926824,
     "end_time": "2020-11-22T06:38:02.792205",
     "exception": false,
     "start_time": "2020-11-22T06:38:01.865381",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x1b791b12940>"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x216 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "g = sb.FacetGrid(train, col='Survived')\n",
    "g.map(plt.hist, 'Age', bins=20)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.06276,
     "end_time": "2020-11-22T06:38:02.915898",
     "exception": false,
     "start_time": "2020-11-22T06:38:02.853138",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "* Splitting Titles from Names "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:03.049800Z",
     "iopub.status.busy": "2020-11-22T06:38:03.048696Z",
     "iopub.status.idle": "2020-11-22T06:38:03.052132Z",
     "shell.execute_reply": "2020-11-22T06:38:03.051625Z"
    },
    "papermill": {
     "duration": 0.076349,
     "end_time": "2020-11-22T06:38:03.052256",
     "exception": false,
     "start_time": "2020-11-22T06:38:02.975907",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "for dats in combine:\n",
    "    dats['Title'] = dats.Name.str.extract('([A-Za-z]+)\\.',expand=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.056916,
     "end_time": "2020-11-22T06:38:03.170185",
     "exception": false,
     "start_time": "2020-11-22T06:38:03.113269",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "* Grouping various Titles under Rare Category."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:03.298680Z",
     "iopub.status.busy": "2020-11-22T06:38:03.297891Z",
     "iopub.status.idle": "2020-11-22T06:38:03.300919Z",
     "shell.execute_reply": "2020-11-22T06:38:03.300447Z"
    },
    "papermill": {
     "duration": 0.073853,
     "end_time": "2020-11-22T06:38:03.301016",
     "exception": false,
     "start_time": "2020-11-22T06:38:03.227163",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "for dataset in combine:\n",
    "    dataset['Title'] = dataset['Title'].replace(['Lady', 'Countess','Capt', 'Col',\n",
    " \t'Don', 'Dr', 'Major', 'Rev', 'Sir', 'Jonkheer', 'Dona'], 'Rare')\n",
    "\n",
    "    dataset['Title'] = dataset['Title'].replace('Mlle', 'Miss')\n",
    "    dataset['Title'] = dataset['Title'].replace('Ms', 'Miss')\n",
    "    dataset['Title'] = dataset['Title'].replace('Mme', 'Mrs')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:03.433129Z",
     "iopub.status.busy": "2020-11-22T06:38:03.432194Z",
     "iopub.status.idle": "2020-11-22T06:38:03.436698Z",
     "shell.execute_reply": "2020-11-22T06:38:03.436215Z"
    },
    "papermill": {
     "duration": 0.078138,
     "end_time": "2020-11-22T06:38:03.436787",
     "exception": false,
     "start_time": "2020-11-22T06:38:03.358649",
     "status": "completed"
    },
    "tags": []
   },
   "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",
       "      <th>Title</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",
       "      <td>Mr</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",
       "      <td>Mrs</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",
       "      <td>Miss</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",
       "      <td>Mrs</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",
       "      <td>Mr</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 Title  \n",
       "0      0         A/5 21171   7.2500   NaN        S    Mr  \n",
       "1      0          PC 17599  71.2833   C85        C   Mrs  \n",
       "2      0  STON/O2. 3101282   7.9250   NaN        S  Miss  \n",
       "3      0            113803  53.1000  C123        S   Mrs  \n",
       "4      0            373450   8.0500   NaN        S    Mr  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.096868,
     "end_time": "2020-11-22T06:38:03.596780",
     "exception": false,
     "start_time": "2020-11-22T06:38:03.499912",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "* Label Encoding Titles. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:03.742410Z",
     "iopub.status.busy": "2020-11-22T06:38:03.740492Z",
     "iopub.status.idle": "2020-11-22T06:38:03.754272Z",
     "shell.execute_reply": "2020-11-22T06:38:03.755365Z"
    },
    "papermill": {
     "duration": 0.100091,
     "end_time": "2020-11-22T06:38:03.755685",
     "exception": false,
     "start_time": "2020-11-22T06:38:03.655594",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "title_mapping = {\"Mr\": 1, \"Miss\": 2, \"Mrs\": 3, \"Master\": 4, \"Rare\": 5}\n",
    "for dataset in combine:\n",
    "    dataset['Title'] = dataset['Title'].map(title_mapping)\n",
    "    dataset['Title'] = dataset['Title'].fillna(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:03.960378Z",
     "iopub.status.busy": "2020-11-22T06:38:03.959449Z",
     "iopub.status.idle": "2020-11-22T06:38:03.976779Z",
     "shell.execute_reply": "2020-11-22T06:38:03.977993Z"
    },
    "papermill": {
     "duration": 0.121401,
     "end_time": "2020-11-22T06:38:03.978194",
     "exception": false,
     "start_time": "2020-11-22T06:38:03.856793",
     "status": "completed"
    },
    "tags": []
   },
   "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",
       "      <th>Title</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",
       "      <td>1</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",
       "      <td>3</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",
       "      <td>2</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",
       "      <td>3</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",
       "      <td>1</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  Title  \n",
       "0      0         A/5 21171   7.2500   NaN        S      1  \n",
       "1      0          PC 17599  71.2833   C85        C      3  \n",
       "2      0  STON/O2. 3101282   7.9250   NaN        S      2  \n",
       "3      0            113803  53.1000  C123        S      3  \n",
       "4      0            373450   8.0500   NaN        S      1  "
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.090274,
     "end_time": "2020-11-22T06:38:04.162554",
     "exception": false,
     "start_time": "2020-11-22T06:38:04.072280",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Now we can see that under the Column Title , instead of *Mr.* , *Mrs.* , *Miss* , etc. , there are numbers 1-5 , representing the 5 different Titles."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.118914,
     "end_time": "2020-11-22T06:38:04.371030",
     "exception": false,
     "start_time": "2020-11-22T06:38:04.252116",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "* Here we see how the survival of the passengers depend on the *Sex* and *Title*. ( There are 2 rows with Title as 5 , which represents the Rare category , and it implies that females of high classes were favoured over all )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:04.561625Z",
     "iopub.status.busy": "2020-11-22T06:38:04.561026Z",
     "iopub.status.idle": "2020-11-22T06:38:04.570772Z",
     "shell.execute_reply": "2020-11-22T06:38:04.571870Z"
    },
    "papermill": {
     "duration": 0.115679,
     "end_time": "2020-11-22T06:38:04.572033",
     "exception": false,
     "start_time": "2020-11-22T06:38:04.456354",
     "status": "completed"
    },
    "tags": []
   },
   "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>Title</th>\n",
       "      <th>Sex</th>\n",
       "      <th>Survived</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>male</td>\n",
       "      <td>0.156673</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>female</td>\n",
       "      <td>0.702703</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>female</td>\n",
       "      <td>0.793651</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>male</td>\n",
       "      <td>0.575000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>female</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>5</td>\n",
       "      <td>male</td>\n",
       "      <td>0.250000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Title     Sex  Survived\n",
       "0      1    male  0.156673\n",
       "1      2  female  0.702703\n",
       "2      3  female  0.793651\n",
       "3      4    male  0.575000\n",
       "4      5  female  1.000000\n",
       "5      5    male  0.250000"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "title_dependencies=train[['Title','Survived','Sex']].groupby(['Title','Sex'],as_index=False).mean()\n",
    "\n",
    "title_dependencies"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.076777,
     "end_time": "2020-11-22T06:38:04.718232",
     "exception": false,
     "start_time": "2020-11-22T06:38:04.641455",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Selecting the final features !!"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.082631,
     "end_time": "2020-11-22T06:38:04.882873",
     "exception": false,
     "start_time": "2020-11-22T06:38:04.800242",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "<img src=\"https://64.media.tumblr.com/37e6f5cd93269829406ccb5bbccf34e0/tumblr_pezn7j41oN1qzs7uio4_r1_400.gifv\">"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.061747,
     "end_time": "2020-11-22T06:38:05.039798",
     "exception": false,
     "start_time": "2020-11-22T06:38:04.978051",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "According to the movie , the Children and the Women , obviously in the decrasing order of their class , were allowed to board the life boats first. Remember the scene were the crew were shouthing , *\" Women and Children First !!\"*. Thus the selection of the *Sex* , *Age* and the *Pclass* as a valid feature for the prediction. As we have clearly seen that people of high social stature had a cent percent chance of survival , thus the *Title* column is also a valid feature. \n",
    "\n",
    "Now , the *Parch* and *SibSp* feature , which represents parents and children, and siblings and spouse , is also a valid feature , because parents and children were not to be separated , and siblings and spouse too. Thus , those passengers who were travelling alone were left behind. \n",
    "\n",
    "The reason behind dropping , *Cabin* , *Embarked* and *Ticket* feature is , that in the data *Ticket* , there are too many mixed data type , and that doesnt help us figure out the survival of the passengers ; in the *Cabin* data , there were too many missing values , although it might have been useful , because the cabin position had an inportant role in the survival as the lower cabins were filled with water first ; the *Embarked* data has nothing to do with the survival , because the port of embarkation did not determine the fate of the passengers, although , upon speculations one may find patterns in the data. \n",
    "\n",
    "What we can see is , that the prejudice of people of certain social backgrounds determined the survival of the passengers.  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:05.173001Z",
     "iopub.status.busy": "2020-11-22T06:38:05.172103Z",
     "iopub.status.idle": "2020-11-22T06:38:05.190423Z",
     "shell.execute_reply": "2020-11-22T06:38:05.191340Z"
    },
    "papermill": {
     "duration": 0.090433,
     "end_time": "2020-11-22T06:38:05.191492",
     "exception": false,
     "start_time": "2020-11-22T06:38:05.101059",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   Survived  Pclass     Sex   Age  SibSp  Parch     Fare  Title\n",
      "0         0       3    male  22.0      1      0   7.2500      1\n",
      "1         1       1  female  38.0      1      0  71.2833      3\n",
      "2         1       3  female  26.0      0      0   7.9250      2\n",
      "3         1       1  female  35.0      1      0  53.1000      3\n",
      "4         0       3    male  35.0      0      0   8.0500      1\n",
      "   Survived  Pclass  Sex   Age  SibSp  Parch     Fare  Title\n",
      "0         0       3    0  22.0      1      0   7.2500      1\n",
      "1         1       1    1  38.0      1      0  71.2833      3\n",
      "2         1       3    1  26.0      0      0   7.9250      2\n",
      "3         1       1    1  35.0      1      0  53.1000      3\n",
      "4         0       3    0  35.0      0      0   8.0500      1\n",
      "   Pclass  Sex   Age  SibSp  Parch     Fare  Title\n",
      "0       3    0  34.5      0      0   7.8292      1\n",
      "1       3    1  47.0      1      0   7.0000      3\n",
      "2       2    0  62.0      0      0   9.6875      1\n",
      "3       3    0  27.0      0      0   8.6625      1\n",
      "4       3    1  22.0      1      1  12.2875      3\n"
     ]
    }
   ],
   "source": [
    "train = train.drop(['Name', 'PassengerId', 'Cabin', 'Embarked','Ticket'], axis=1)\n",
    "test = test.drop(['Name', 'PassengerId', 'Cabin', 'Embarked','Ticket'], axis=1)\n",
    "\n",
    "combine=[train,test]\n",
    "\n",
    "print(train.head())\n",
    "\n",
    "for dataset in combine:\n",
    "    dataset['Sex'] = dataset['Sex'].map( {'female': 1, 'male': 0}).astype(int)\n",
    "\n",
    "print(train.head())\n",
    "print (test.head())\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.063008,
     "end_time": "2020-11-22T06:38:05.320246",
     "exception": false,
     "start_time": "2020-11-22T06:38:05.257238",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Splitting Training data "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:05.447838Z",
     "iopub.status.busy": "2020-11-22T06:38:05.447177Z",
     "iopub.status.idle": "2020-11-22T06:38:05.522310Z",
     "shell.execute_reply": "2020-11-22T06:38:05.521445Z"
    },
    "papermill": {
     "duration": 0.140725,
     "end_time": "2020-11-22T06:38:05.522421",
     "exception": false,
     "start_time": "2020-11-22T06:38:05.381696",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test , Y_train, Y_test = train_test_split(train.drop(['Survived'],axis=1),train['Survived'],test_size=0.10,random_state=None)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.059792,
     "end_time": "2020-11-22T06:38:05.642957",
     "exception": false,
     "start_time": "2020-11-22T06:38:05.583165",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Applying Logistic Regression :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:05.767124Z",
     "iopub.status.busy": "2020-11-22T06:38:05.766438Z",
     "iopub.status.idle": "2020-11-22T06:38:05.835824Z",
     "shell.execute_reply": "2020-11-22T06:38:05.835287Z"
    },
    "papermill": {
     "duration": 0.132439,
     "end_time": "2020-11-22T06:38:05.835914",
     "exception": false,
     "start_time": "2020-11-22T06:38:05.703475",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn import metrics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:05.964474Z",
     "iopub.status.busy": "2020-11-22T06:38:05.963570Z",
     "iopub.status.idle": "2020-11-22T06:38:05.974924Z",
     "shell.execute_reply": "2020-11-22T06:38:05.975634Z"
    },
    "papermill": {
     "duration": 0.079338,
     "end_time": "2020-11-22T06:38:05.975756",
     "exception": false,
     "start_time": "2020-11-22T06:38:05.896418",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "LogisticRegression(C=0.21, class_weight=None, dual=False, fit_intercept=True,\n",
       "                   intercept_scaling=1, l1_ratio=None, max_iter=100,\n",
       "                   multi_class='auto', n_jobs=None, penalty='l2',\n",
       "                   random_state=1, solver='liblinear', tol=0.0001, verbose=0,\n",
       "                   warm_start=False)"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "modelLR= LogisticRegression(solver='liblinear',C=0.21,random_state=1)\n",
    "modelLR.fit(X_train,Y_train)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:06.113607Z",
     "iopub.status.busy": "2020-11-22T06:38:06.112905Z",
     "iopub.status.idle": "2020-11-22T06:38:06.116961Z",
     "shell.execute_reply": "2020-11-22T06:38:06.116487Z"
    },
    "papermill": {
     "duration": 0.074762,
     "end_time": "2020-11-22T06:38:06.117073",
     "exception": false,
     "start_time": "2020-11-22T06:38:06.042311",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "Y_pred_log=modelLR.predict(X_test)\n",
    "acc_LR = metrics.accuracy_score(Y_test, Y_pred_log)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:06.254511Z",
     "iopub.status.busy": "2020-11-22T06:38:06.253452Z",
     "iopub.status.idle": "2020-11-22T06:38:06.259093Z",
     "shell.execute_reply": "2020-11-22T06:38:06.258630Z"
    },
    "papermill": {
     "duration": 0.073413,
     "end_time": "2020-11-22T06:38:06.259208",
     "exception": false,
     "start_time": "2020-11-22T06:38:06.185795",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 1 1 0 0 0 1 0 1 1 0 1 0 0 1 0 1 1 0 0 0 0 0 1 0 0 1 1 0 0 0 0 0 0 1 0 0\n",
      " 1 1 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 1 0 0 0 0 1 0 0 0 0 1 1 0 0 1 0 0 1 1 1\n",
      " 1 0 0 0 1 1 0 0 1 0 0 0 1 0 0 1]\n",
      "We see that Logistic regression gives an Accuracy of  75.55555555555556 % on the traing set.\n"
     ]
    }
   ],
   "source": [
    "print(Y_pred_log)\n",
    "print(\"We see that Logistic regression gives an Accuracy of \",acc_LR*100,\"% on the traing set.\")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.064406,
     "end_time": "2020-11-22T06:38:06.387933",
     "exception": false,
     "start_time": "2020-11-22T06:38:06.323527",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Applying Decision Tree:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:06.532840Z",
     "iopub.status.busy": "2020-11-22T06:38:06.531938Z",
     "iopub.status.idle": "2020-11-22T06:38:06.613336Z",
     "shell.execute_reply": "2020-11-22T06:38:06.612839Z"
    },
    "papermill": {
     "duration": 0.15776,
     "end_time": "2020-11-22T06:38:06.613444",
     "exception": false,
     "start_time": "2020-11-22T06:38:06.455684",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:06.753408Z",
     "iopub.status.busy": "2020-11-22T06:38:06.752799Z",
     "iopub.status.idle": "2020-11-22T06:38:06.759686Z",
     "shell.execute_reply": "2020-11-22T06:38:06.759189Z"
    },
    "papermill": {
     "duration": 0.079926,
     "end_time": "2020-11-22T06:38:06.759814",
     "exception": false,
     "start_time": "2020-11-22T06:38:06.679888",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "dtree = DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=1,\n",
    "                       max_features=7, max_leaf_nodes=None,\n",
    "                       min_impurity_decrease=0.0, min_impurity_split=None,\n",
    "                       min_samples_leaf=1, min_samples_split=2,\n",
    "                       min_weight_fraction_leaf=0.0,\n",
    "                       random_state=None, splitter='best')\n",
    "dtree.fit(X_train, Y_train)\n",
    "y_pred_tree = dtree.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:06.897499Z",
     "iopub.status.busy": "2020-11-22T06:38:06.896593Z",
     "iopub.status.idle": "2020-11-22T06:38:06.902370Z",
     "shell.execute_reply": "2020-11-22T06:38:06.901671Z"
    },
    "papermill": {
     "duration": 0.07602,
     "end_time": "2020-11-22T06:38:06.902502",
     "exception": false,
     "start_time": "2020-11-22T06:38:06.826482",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 1 1 0 0 0 0 0 1 1 0 1 1 0 1 0 1 1 1 1 0 0 0 1 0 0 1 0 0 0 0 0 0 0 1 0 0\n",
      " 1 1 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 1 0 0 0 0 1 0 0 0 0 1 1 0 0 1 0 0 1 1 1\n",
      " 1 0 0 0 1 1 0 0 0 0 0 0 1 0 0 0]\n",
      "We see that Decision Tree gives an Accuracy of  70.0 % on the traing set.\n"
     ]
    }
   ],
   "source": [
    "acc_DT = metrics.accuracy_score(y_pred_tree, Y_test)\n",
    "print(y_pred_tree)\n",
    "print(\"We see that Decision Tree gives an Accuracy of \",acc_DT*100,\"% on the traing set.\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.063406,
     "end_time": "2020-11-22T06:38:07.031307",
     "exception": false,
     "start_time": "2020-11-22T06:38:06.967901",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Applying Ramndom Forest :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:07.162430Z",
     "iopub.status.busy": "2020-11-22T06:38:07.161642Z",
     "iopub.status.idle": "2020-11-22T06:38:07.186726Z",
     "shell.execute_reply": "2020-11-22T06:38:07.185938Z"
    },
    "papermill": {
     "duration": 0.092494,
     "end_time": "2020-11-22T06:38:07.186832",
     "exception": false,
     "start_time": "2020-11-22T06:38:07.094338",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:07.324879Z",
     "iopub.status.busy": "2020-11-22T06:38:07.324020Z",
     "iopub.status.idle": "2020-11-22T06:38:07.385260Z",
     "shell.execute_reply": "2020-11-22T06:38:07.384746Z"
    },
    "papermill": {
     "duration": 0.131904,
     "end_time": "2020-11-22T06:38:07.385357",
     "exception": false,
     "start_time": "2020-11-22T06:38:07.253453",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "rforest = RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
    "            max_depth=None, max_features=7, max_leaf_nodes=None,\n",
    "            min_impurity_decrease=0.0, min_impurity_split=None,\n",
    "            min_samples_leaf=1, min_samples_split=2,\n",
    "            min_weight_fraction_leaf=0.0, n_estimators=20, n_jobs=1,\n",
    "            oob_score=False, random_state=42, verbose=0, warm_start=False)\n",
    "rforest.fit(X_train, Y_train)\n",
    "y_pred_forest = rforest.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:07.517120Z",
     "iopub.status.busy": "2020-11-22T06:38:07.515893Z",
     "iopub.status.idle": "2020-11-22T06:38:07.519863Z",
     "shell.execute_reply": "2020-11-22T06:38:07.520480Z"
    },
    "papermill": {
     "duration": 0.073758,
     "end_time": "2020-11-22T06:38:07.520623",
     "exception": false,
     "start_time": "2020-11-22T06:38:07.446865",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 1 0 1 0 0 0 0 1 0 0 1 0 1 1 0 1 1 0 0 0 1 0 1 0 0 1 1 0 0 0 0 0 0 1 1 0\n",
      " 1 0 0 1 1 0 0 0 0 0 0 1 0 0 0 0 0 1 0 0 0 0 1 0 0 0 0 1 1 0 0 1 0 0 1 1 1\n",
      " 1 0 0 0 1 1 0 0 0 0 0 0 1 0 0 0]\n",
      "We see that Random Forest classifier gives an Accuracy of  77.77777777777779 % on the traing set.\n"
     ]
    }
   ],
   "source": [
    "acc_RF = metrics.accuracy_score(y_pred_forest, Y_test)\n",
    "print(y_pred_forest)\n",
    "print(\"We see that Random Forest classifier gives an Accuracy of \",acc_RF*100,\"% on the traing set.\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.062558,
     "end_time": "2020-11-22T06:38:07.655277",
     "exception": false,
     "start_time": "2020-11-22T06:38:07.592719",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Applying SVC :\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:07.784886Z",
     "iopub.status.busy": "2020-11-22T06:38:07.784137Z",
     "iopub.status.idle": "2020-11-22T06:38:07.787186Z",
     "shell.execute_reply": "2020-11-22T06:38:07.786700Z"
    },
    "papermill": {
     "duration": 0.069712,
     "end_time": "2020-11-22T06:38:07.787284",
     "exception": false,
     "start_time": "2020-11-22T06:38:07.717572",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "from sklearn.svm import SVC"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:07.931337Z",
     "iopub.status.busy": "2020-11-22T06:38:07.930351Z",
     "iopub.status.idle": "2020-11-22T06:38:07.963056Z",
     "shell.execute_reply": "2020-11-22T06:38:07.962522Z"
    },
    "papermill": {
     "duration": 0.109125,
     "end_time": "2020-11-22T06:38:07.963170",
     "exception": false,
     "start_time": "2020-11-22T06:38:07.854045",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "svc = SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n",
    "  decision_function_shape='ovr', degree=3, gamma='auto', kernel='rbf',\n",
    "  max_iter=-1, probability=False, random_state=None, shrinking=True,\n",
    "  tol=0.001, verbose=False)\n",
    "svc.fit(X_train, Y_train)\n",
    "y_pred_svc = svc.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:08.095389Z",
     "iopub.status.busy": "2020-11-22T06:38:08.094581Z",
     "iopub.status.idle": "2020-11-22T06:38:08.098264Z",
     "shell.execute_reply": "2020-11-22T06:38:08.098890Z"
    },
    "papermill": {
     "duration": 0.072979,
     "end_time": "2020-11-22T06:38:08.099048",
     "exception": false,
     "start_time": "2020-11-22T06:38:08.026069",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 1 1 1 0 0 0 0 1 1 0 1 0 1 0 0 0 1 1 1 0 0 0 1 0 0 1 1 1 0 1 0 0 0 1 1 0\n",
      " 0 0 0 1 1 0 0 0 0 1 0 1 0 0 0 0 0 1 0 0 0 0 1 0 0 0 0 1 1 0 0 1 0 0 1 1 0\n",
      " 1 0 0 1 0 1 0 0 0 0 0 0 0 0 0 1]\n",
      "We see that SVC classifier gives an Accuracy of  73.33333333333333 % on the traing set.\n"
     ]
    }
   ],
   "source": [
    "acc_SVC = metrics.accuracy_score(y_pred_svc, Y_test)\n",
    "print(y_pred_svc)\n",
    "print(\"We see that SVC classifier gives an Accuracy of \",acc_SVC*100,\"% on the traing set.\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.062658,
     "end_time": "2020-11-22T06:38:08.225397",
     "exception": false,
     "start_time": "2020-11-22T06:38:08.162739",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Applying Gradient Boosting:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:08.356537Z",
     "iopub.status.busy": "2020-11-22T06:38:08.355825Z",
     "iopub.status.idle": "2020-11-22T06:38:10.366768Z",
     "shell.execute_reply": "2020-11-22T06:38:10.365592Z"
    },
    "papermill": {
     "duration": 2.077781,
     "end_time": "2020-11-22T06:38:10.366888",
     "exception": false,
     "start_time": "2020-11-22T06:38:08.289107",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "from xgboost import XGBClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:10.503984Z",
     "iopub.status.busy": "2020-11-22T06:38:10.503272Z",
     "iopub.status.idle": "2020-11-22T06:38:11.107031Z",
     "shell.execute_reply": "2020-11-22T06:38:11.107703Z"
    },
    "papermill": {
     "duration": 0.677368,
     "end_time": "2020-11-22T06:38:11.107880",
     "exception": false,
     "start_time": "2020-11-22T06:38:10.430512",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\ACER\\anaconda3\\lib\\site-packages\\xgboost\\sklearn.py:1146: UserWarning: The use of label encoder in XGBClassifier is deprecated and will be removed in a future release. To remove this warning, do the following: 1) Pass option use_label_encoder=False when constructing XGBClassifier object; and 2) Encode your labels (y) as integers starting with 0, i.e. 0, 1, 2, ..., [num_class - 1].\n",
      "  warnings.warn(label_encoder_deprecation_msg, UserWarning)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[19:49:04] WARNING: C:/Users/Administrator/workspace/xgboost-win64_release_1.4.0/src/learner.cc:1095: Starting in XGBoost 1.3.0, the default evaluation metric used with the objective 'binary:logistic' was changed from 'error' to 'logloss'. Explicitly set eval_metric if you'd like to restore the old behavior.\n"
     ]
    }
   ],
   "source": [
    "xgb=XGBClassifier(learning_rate=0.05, n_estimators=500)\n",
    "xgb.fit(X_train,Y_train)\n",
    "y_pred_xgb=xgb.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:11.298381Z",
     "iopub.status.busy": "2020-11-22T06:38:11.297491Z",
     "iopub.status.idle": "2020-11-22T06:38:11.303080Z",
     "shell.execute_reply": "2020-11-22T06:38:11.303567Z"
    },
    "papermill": {
     "duration": 0.097555,
     "end_time": "2020-11-22T06:38:11.303687",
     "exception": false,
     "start_time": "2020-11-22T06:38:11.206132",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 1 0 1 0 0 0 0 1 0 0 1 0 1 1 0 1 1 0 0 0 1 0 1 0 0 1 1 0 0 0 0 0 0 1 1 0\n",
      " 0 0 0 1 1 0 0 0 0 0 0 1 0 0 0 0 0 1 0 0 0 0 1 0 0 0 0 1 1 0 0 1 0 0 1 1 1\n",
      " 1 0 0 0 1 1 0 0 0 0 0 0 1 0 0 0]\n",
      "We see that XGB classifier gives an Accuracy of  78.88888888888889 % on the traing set.\n"
     ]
    }
   ],
   "source": [
    "acc_XGB= metrics.accuracy_score(y_pred_xgb,Y_test)\n",
    "print(y_pred_xgb)\n",
    "print(\"We see that XGB classifier gives an Accuracy of \",acc_XGB*100,\"% on the traing set.\")                               "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.063527,
     "end_time": "2020-11-22T06:38:11.432442",
     "exception": false,
     "start_time": "2020-11-22T06:38:11.368915",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Applying Artificial Neural Network:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:11.569353Z",
     "iopub.status.busy": "2020-11-22T06:38:11.568563Z",
     "iopub.status.idle": "2020-11-22T06:38:16.145000Z",
     "shell.execute_reply": "2020-11-22T06:38:16.143858Z"
    },
    "papermill": {
     "duration": 4.648938,
     "end_time": "2020-11-22T06:38:16.145130",
     "exception": false,
     "start_time": "2020-11-22T06:38:11.496192",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import keras\n",
    "from keras.layers import Dense\n",
    "from keras.models import Sequential\n",
    "from sklearn.metrics import classification_report"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.06379,
     "end_time": "2020-11-22T06:38:16.275448",
     "exception": false,
     "start_time": "2020-11-22T06:38:16.211658",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "Using sequential model to stack two ***14*** unit hidden layer , with ***1*** output layer."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:16.415118Z",
     "iopub.status.busy": "2020-11-22T06:38:16.414205Z",
     "iopub.status.idle": "2020-11-22T06:38:18.444255Z",
     "shell.execute_reply": "2020-11-22T06:38:18.443721Z"
    },
    "papermill": {
     "duration": 2.102899,
     "end_time": "2020-11-22T06:38:18.444379",
     "exception": false,
     "start_time": "2020-11-22T06:38:16.341480",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "nn  = Sequential()\n",
    "nn.add(Dense(units= 14, activation = 'relu', input_dim=7, kernel_initializer=\"uniform\"))\n",
    "nn.add(Dense(units= 14, activation = 'relu',kernel_initializer=\"uniform\"))\n",
    "nn.add(Dense(units= 1, activation = 'sigmoid',kernel_initializer=\"uniform\"))\n",
    "nn.compile(optimizer='adam',\n",
    "              loss='mean_squared_error',\n",
    "              metrics=['accuracy'])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:18.589642Z",
     "iopub.status.busy": "2020-11-22T06:38:18.588730Z",
     "iopub.status.idle": "2020-11-22T06:38:21.909266Z",
     "shell.execute_reply": "2020-11-22T06:38:21.910002Z"
    },
    "papermill": {
     "duration": 3.398542,
     "end_time": "2020-11-22T06:38:21.910141",
     "exception": false,
     "start_time": "2020-11-22T06:38:18.511599",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0, 1, 1, 0, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1]\n"
     ]
    }
   ],
   "source": [
    "nn.fit(X_train,Y_train, batch_size=32,epochs=50,verbose= 0)\n",
    "\n",
    "nn_pred = nn.predict(X_test)\n",
    "nn_pred = [ 1 if y>=0.5 else 0 for y in nn_pred]\n",
    "print(nn_pred)\n",
    "\n",
    "acc_NN = metrics.accuracy_score(Y_test, nn_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:22.045646Z",
     "iopub.status.busy": "2020-11-22T06:38:22.044823Z",
     "iopub.status.idle": "2020-11-22T06:38:22.050179Z",
     "shell.execute_reply": "2020-11-22T06:38:22.049549Z"
    },
    "papermill": {
     "duration": 0.074662,
     "end_time": "2020-11-22T06:38:22.050280",
     "exception": false,
     "start_time": "2020-11-22T06:38:21.975618",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "We can see that the neural network gives an Accuracy of  75.55555555555556 % on the training set.\n"
     ]
    }
   ],
   "source": [
    "print(\"We can see that the neural network gives an Accuracy of \",acc_NN*100 , \"% on the training set.\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.065085,
     "end_time": "2020-11-22T06:38:22.181452",
     "exception": false,
     "start_time": "2020-11-22T06:38:22.116367",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Getting the best Classifier:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:22.324780Z",
     "iopub.status.busy": "2020-11-22T06:38:22.324118Z",
     "iopub.status.idle": "2020-11-22T06:38:22.328556Z",
     "shell.execute_reply": "2020-11-22T06:38:22.329548Z"
    },
    "papermill": {
     "duration": 0.081725,
     "end_time": "2020-11-22T06:38:22.329693",
     "exception": false,
     "start_time": "2020-11-22T06:38:22.247968",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                          Model     Score\n",
      "4  Gradient Boosting Classifier  0.788889\n",
      "2                 Random Forest  0.777778\n",
      "0           Logistic Regression  0.755556\n",
      "5     Artificial Neural Network  0.755556\n",
      "3       Support Vector Machines  0.733333\n",
      "1                 Decision Tree  0.700000\n"
     ]
    }
   ],
   "source": [
    "models = pd.DataFrame({\n",
    "    'Model': ['Logistic Regression','Decision Tree','Random Forest','Support Vector Machines',\n",
    "              'Gradient Boosting Classifier','Artificial Neural Network'],\n",
    "    'Score': [acc_LR, acc_DT, acc_RF, \n",
    "              acc_SVC, acc_XGB, acc_NN]})\n",
    "best_model=models.sort_values(by='Score', ascending=False)\n",
    "print(best_model)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.065013,
     "end_time": "2020-11-22T06:38:22.461804",
     "exception": false,
     "start_time": "2020-11-22T06:38:22.396791",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "* Fetching the best Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:22.597440Z",
     "iopub.status.busy": "2020-11-22T06:38:22.596801Z",
     "iopub.status.idle": "2020-11-22T06:38:22.601434Z",
     "shell.execute_reply": "2020-11-22T06:38:22.601945Z"
    },
    "papermill": {
     "duration": 0.074705,
     "end_time": "2020-11-22T06:38:22.602063",
     "exception": false,
     "start_time": "2020-11-22T06:38:22.527358",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Gradient Boosting Classifier\n"
     ]
    }
   ],
   "source": [
    "best=best_model['Model'].iloc[0]\n",
    "\n",
    "print(str(best))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Hyper-parameter Tuning"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Hyper-parameters are the model configuration argument specified by the developer to guide the learning process for a specific dataset.\n",
    "\n",
    "Hyperparameters are important because they directly control the behaviour of the training algorithm and have a significant impact on the performance of the model is being trained. “A good choice of hyperparameters can really make an algorithm shine”.\n",
    "\n",
    "A range of different optimization algorithms may be used, although two of the simplest and most common methods are random search and grid search.\n",
    "\n",
    "- Random Search. Define a search space as a bounded domain of hyperparameter values and randomly sample points in that domain.\n",
    "- Grid Search. Define a search space as a grid of hyperparameter values and evaluate every position in the grid.\n",
    "\n",
    "Let's use Grid Search.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Let's define parameter grids for all models**\n",
    "> The parameter grid to explore, as a dictionary mapping estimator parameters to sequences of allowed values. \n",
    "\n",
    "Note: Tuning Artificial Neural Network is a tedious work and need different approach let's skip that."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "# let's not use all the parameters\n",
    "PARAM_GRIDS = {\n",
    "    'Logistic Regression': {\n",
    "        'solver': ['newton-cg', 'lbfgs', 'liblinear'],\n",
    "        'penalty': ['l2'],\n",
    "        'C': [100, 10, 1.0, 0.2, 0.1, 0.01]\n",
    "    },\n",
    "    'Decision Tree': {\n",
    "        'max_depth': [2, 3, 5, 10, 20],\n",
    "        'min_samples_leaf': [5, 10, 20, 50, 100],\n",
    "        'criterion': [\"gini\", \"entropy\"]\n",
    "    },\n",
    "    'Random Forest': {\n",
    "        'criterion' : ['gini', 'entropy'],\n",
    "        'min_samples_leaf' : [1, 2, 4, 8], \n",
    "        'min_samples_split' : [2, 4, 10, 12, 16, 20],\n",
    "        'n_estimators': [50, 100, 200, 400, 700, 1000],\n",
    "    },\n",
    "    'Support Vector Machine': {\n",
    "        'kernel': ['poly', 'rbf', 'sigmoid'],\n",
    "        'C': [50, 10, 1.0, 0.1, 0.01],\n",
    "        'gamma': ['scale']\n",
    "    },\n",
    "    'Gradient Boosting Classifier':{\n",
    "        'n_estimators': [10, 100, 1000],\n",
    "        'learning_rate': [0.001, 0.01, 0.1],\n",
    "        'subsample':  [0.5, 0.7, 1.0],\n",
    "        'max_depth': [3, 7, 9]\n",
    "    }\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import GridSearchCV\n",
    "\n",
    "def get_best_params(x, y, estimator, param_grid, scoring='accuracy', cv=10, n_jobs=-1):\n",
    "    \"\"\" \n",
    "        Exhaustive search over specified parameter values for an estimator\n",
    "        :param x: input variables\n",
    "        :param y: output variables\n",
    "        :param estimator: estimator object\n",
    "        :param param_grid: dict or list of dictionaries\n",
    "        :param scoring: str, callable, list, tuple or dict, default='accuracy'\n",
    "        :param cv: int, cross-validation generator or an iterable, default=10\n",
    "        :param n_jobs: int, default=-1\n",
    "        :return:  returns the best model parameters from a search over a parameter_grid  \n",
    "    \"\"\"\n",
    "    gs = GridSearchCV(estimator=estimator, param_grid=param_grid, scoring=scoring, cv=cv, n_jobs=n_jobs)\n",
    "    return gs.fit(x, y)    "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.066164,
     "end_time": "2020-11-22T06:38:22.735459",
     "exception": false,
     "start_time": "2020-11-22T06:38:22.669295",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Fitting the test set on the Best Classifier:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:22.882565Z",
     "iopub.status.busy": "2020-11-22T06:38:22.880185Z",
     "iopub.status.idle": "2020-11-22T06:38:22.889699Z",
     "shell.execute_reply": "2020-11-22T06:38:22.888837Z"
    },
    "papermill": {
     "duration": 0.087877,
     "end_time": "2020-11-22T06:38:22.889845",
     "exception": false,
     "start_time": "2020-11-22T06:38:22.801968",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pclass 0.0\n",
      "Sex 0.0\n",
      "Age 20.574162679425836\n",
      "SibSp 0.0\n",
      "Parch 0.0\n",
      "Fare 0.23923444976076555\n",
      "Title 0.0\n",
      "..............Before\n",
      "\n",
      "\n",
      "Pclass 0.0\n",
      "Sex 0.0\n",
      "Age 0.0\n",
      "SibSp 0.0\n",
      "Parch 0.0\n",
      "Fare 0.0\n",
      "Title 0.0\n",
      "..............After\n"
     ]
    }
   ],
   "source": [
    "test.head()\n",
    "for c in test.columns:\n",
    "    print(c, str(100*test[c].isnull().sum()/len(test)))\n",
    "print(\"..............Before\")    \n",
    "\n",
    "test['Age'] = test['Age'].fillna(test['Age'].mean())\n",
    "test['Fare'] = test['Fare'].fillna(test['Fare'].mean())\n",
    "print(\"\\n\")\n",
    "for c in test.columns:\n",
    "    print(c, str(100*test[c].isnull().sum()/len(test)))\n",
    "print(\"..............After\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.066589,
     "end_time": "2020-11-22T06:38:23.024010",
     "exception": false,
     "start_time": "2020-11-22T06:38:22.957421",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "***Selecting the Best Model and fitting it to the Test data :***"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:23.182397Z",
     "iopub.status.busy": "2020-11-22T06:38:23.180844Z",
     "iopub.status.idle": "2020-11-22T06:38:23.492169Z",
     "shell.execute_reply": "2020-11-22T06:38:23.492808Z"
    },
    "papermill": {
     "duration": 0.401861,
     "end_time": "2020-11-22T06:38:23.492970",
     "exception": false,
     "start_time": "2020-11-22T06:38:23.091109",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\ACER\\anaconda3\\lib\\site-packages\\xgboost\\sklearn.py:1146: UserWarning: The use of label encoder in XGBClassifier is deprecated and will be removed in a future release. To remove this warning, do the following: 1) Pass option use_label_encoder=False when constructing XGBClassifier object; and 2) Encode your labels (y) as integers starting with 0, i.e. 0, 1, 2, ..., [num_class - 1].\n",
      "  warnings.warn(label_encoder_deprecation_msg, UserWarning)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[19:53:02] WARNING: C:/Users/Administrator/workspace/xgboost-win64_release_1.4.0/src/learner.cc:1095: Starting in XGBoost 1.3.0, the default evaluation metric used with the objective 'binary:logistic' was changed from 'error' to 'logloss'. Explicitly set eval_metric if you'd like to restore the old behavior.\n",
      "[19:53:03] WARNING: C:/Users/Administrator/workspace/xgboost-win64_release_1.4.0/src/learner.cc:1095: Starting in XGBoost 1.3.0, the default evaluation metric used with the objective 'binary:logistic' was changed from 'error' to 'logloss'. Explicitly set eval_metric if you'd like to restore the old behavior.\n",
      "[0 0 0 0 1 0 1 0 1 0 0 0 1 0 1 1 0 0 1 0 0 1 1 0 1 0 1 0 0 0 0 0 1 0 1 0 0\n",
      " 0 0 0 0 1 0 1 1 0 0 0 1 1 0 0 1 1 0 0 0 0 0 1 0 0 0 1 1 1 1 0 0 1 1 0 1 0\n",
      " 1 1 0 1 0 1 1 0 0 0 0 0 1 1 1 1 0 0 1 0 0 0 1 0 1 0 1 0 0 0 1 0 0 0 0 0 0\n",
      " 1 1 1 1 0 0 1 1 1 1 0 1 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 1 0 0 0\n",
      " 1 0 1 0 0 1 0 0 1 1 1 1 1 1 1 0 0 1 0 0 1 0 0 0 0 0 0 1 1 0 1 1 0 0 1 0 1\n",
      " 0 1 0 0 0 0 0 1 0 1 0 1 1 0 1 1 1 1 1 0 0 1 0 1 0 0 0 0 1 0 0 1 0 1 0 1 0\n",
      " 1 0 1 1 0 1 0 0 0 1 0 0 0 0 0 0 1 1 1 1 0 0 0 0 1 0 1 0 1 0 0 0 0 0 0 0 1\n",
      " 0 0 0 1 1 0 0 0 0 0 0 0 0 1 1 0 1 0 0 0 0 0 1 1 1 1 0 0 0 0 0 0 0 0 1 0 0\n",
      " 1 0 0 0 0 0 0 0 1 1 0 1 0 0 0 0 0 0 1 1 0 0 0 0 0 0 0 1 1 0 1 0 0 0 1 0 0\n",
      " 1 0 0 0 0 0 0 0 0 0 1 0 1 0 0 0 1 1 0 0 0 1 0 1 0 0 1 0 1 1 0 1 0 0 0 1 0\n",
      " 0 1 0 0 1 1 0 0 0 0 0 0 1 1 0 1 0 0 0 0 0 1 1 0 0 1 0 1 0 0 1 0 1 0 0 0 0\n",
      " 0 1 1 1 1 1 0 1 0 0 0]\n",
      "Gradient Boosting Classifier\n"
     ]
    }
   ],
   "source": [
    "x, y = train.drop(['Survived'],axis=1),train['Survived']\n",
    "\n",
    "if best == 'Logistic Regression':\n",
    "    estimator = LogisticRegression()\n",
    "    \n",
    "    gs = get_best_params(x, y, estimator, PARAM_GRIDS['Logistic Regression']) # start GridSearchCv for LR\n",
    "    \n",
    "    modelLR = LogisticRegression(**gs.best_params_, random_state=1)\n",
    "    modelLR.fit(x, y)\n",
    "    test_pred=modelLR.predict(test)\n",
    "    print(test_pred)\n",
    "    print('Logistic Regression')\n",
    "    \n",
    "if best == 'Decision Tree':\n",
    "    estimator = DecisionTreeClassifier()\n",
    "    \n",
    "    gs = get_best_params(x, y, estimator, PARAM_GRIDS['Decision Tree']) # start GridSearchCv for DT\n",
    "                \n",
    "    dtree = DecisionTreeClassifier(**gs.best_params_)\n",
    "    dtree.fit(x, y)\n",
    "    test_pred=dtree.predict(test)\n",
    "    print(test_pred)\n",
    "    print('Decision Tree')\n",
    "    \n",
    "if best =='Random Forest':\n",
    "    estimator = RandomForestClassifier()\n",
    "    \n",
    "    gs = get_best_params(x, y, estimator, PARAM_GRIDS['Random Forest']) # start GridSearchCv for RF\n",
    "     \n",
    "    rforest = RandomForestClassifier(**gs.best_params_)\n",
    "    rforest.fit(x, y)\n",
    "    test_pred=rforest.predict(test)\n",
    "    print(test_pred)\n",
    "    print('Random Forest')\n",
    "    \n",
    "if best == 'Support Vector Machine':\n",
    "    estimator = SVC()\n",
    "    \n",
    "    gs = get_best_params(x, y, estimator, PARAM_GRIDS['Support Vector Machine']) # start GridSearchCv for SVM\n",
    "\n",
    "    svc = SVC(**gs.best_params_)\n",
    "    svc.fit(x, y)\n",
    "    test_pred=svc.predict(test)\n",
    "    print(test_pred)\n",
    "    print('Support Vector Machines')\n",
    "\n",
    "if best == 'Gradient Boosting Classifier':\n",
    "    estimator = XGBClassifier()\n",
    "    \n",
    "    gs = get_best_params(x, y, estimator, PARAM_GRIDS['Gradient Boosting Classifier']) # start GridSearchCv for GBC\n",
    "    \n",
    "    xgb=XGBClassifier(**gs.best_params_)\n",
    "    xgb.fit(x, y)\n",
    "    test_pred=xgb.predict(test)\n",
    "    print(test_pred)\n",
    "    print('Gradient Boosting Classifier')\n",
    "    \n",
    "if best == 'Artificial Neural Network':\n",
    "    nn.fit(train.drop(['Survived'],axis=1),train['Survived'], epochs=500 , verbose=0)\n",
    "    test_pred=nn.predict(test)\n",
    "    test_pred = [ 1 if y>=0.5 else 0 for y in test_pred]\n",
    "    print(test_pred)\n",
    "    print('Artificial Neural Network')\n",
    "    "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.081045,
     "end_time": "2020-11-22T06:38:23.655524",
     "exception": false,
     "start_time": "2020-11-22T06:38:23.574479",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "**Fetching the Survival Data of the test set from the *gender_submission.csv* file .**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:23.804678Z",
     "iopub.status.busy": "2020-11-22T06:38:23.803651Z",
     "iopub.status.idle": "2020-11-22T06:38:23.815700Z",
     "shell.execute_reply": "2020-11-22T06:38:23.816231Z"
    },
    "papermill": {
     "duration": 0.087881,
     "end_time": "2020-11-22T06:38:23.816358",
     "exception": false,
     "start_time": "2020-11-22T06:38:23.728477",
     "status": "completed"
    },
    "tags": []
   },
   "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>Survived</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Survived\n",
       "0         0\n",
       "1         1\n",
       "2         0\n",
       "3         0\n",
       "4         1"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_data=pd.read_csv('./kaggle/input/titanic/gender_submission.csv')\n",
    "test_data = test_data.drop(['PassengerId'], axis=1)\n",
    "\n",
    "test_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:23.967700Z",
     "iopub.status.busy": "2020-11-22T06:38:23.965444Z",
     "iopub.status.idle": "2020-11-22T06:38:23.970642Z",
     "shell.execute_reply": "2020-11-22T06:38:23.969916Z"
    },
    "papermill": {
     "duration": 0.085648,
     "end_time": "2020-11-22T06:38:23.970776",
     "exception": false,
     "start_time": "2020-11-22T06:38:23.885128",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Here we see that the test data has an Accuracy of  89.23444976076556 % \n"
     ]
    }
   ],
   "source": [
    "test_data.values.tolist()\n",
    "test_acc = metrics.accuracy_score(test_data, test_pred)\n",
    "\n",
    "print(\"Here we see that the test data has an Accuracy of \",test_acc*100,\"% \")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.073309,
     "end_time": "2020-11-22T06:38:24.118683",
     "exception": false,
     "start_time": "2020-11-22T06:38:24.045374",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "* Adding the predictions to the Test set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:24.265068Z",
     "iopub.status.busy": "2020-11-22T06:38:24.264195Z",
     "iopub.status.idle": "2020-11-22T06:38:24.272251Z",
     "shell.execute_reply": "2020-11-22T06:38:24.271686Z"
    },
    "papermill": {
     "duration": 0.083405,
     "end_time": "2020-11-22T06:38:24.272351",
     "exception": false,
     "start_time": "2020-11-22T06:38:24.188946",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "test_predict = pd.DataFrame(test_pred, columns= ['Survived'])\n",
    "test_new= pd.read_csv('./kaggle/input/titanic/test.csv')\n",
    "new_test = pd.concat([test_new, test_predict], axis=1, join='inner')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:24.677314Z",
     "iopub.status.busy": "2020-11-22T06:38:24.676420Z",
     "iopub.status.idle": "2020-11-22T06:38:24.724287Z",
     "shell.execute_reply": "2020-11-22T06:38:24.724979Z"
    },
    "papermill": {
     "duration": 0.247143,
     "end_time": "2020-11-22T06:38:24.725207",
     "exception": false,
     "start_time": "2020-11-22T06:38:24.478064",
     "status": "completed"
    },
    "tags": []
   },
   "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>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",
       "      <th>Survived</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>892</td>\n",
       "      <td>3</td>\n",
       "      <td>Kelly, Mr. James</td>\n",
       "      <td>male</td>\n",
       "      <td>34.5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>330911</td>\n",
       "      <td>7.8292</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>893</td>\n",
       "      <td>3</td>\n",
       "      <td>Wilkes, Mrs. James (Ellen Needs)</td>\n",
       "      <td>female</td>\n",
       "      <td>47.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>363272</td>\n",
       "      <td>7.0000</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>894</td>\n",
       "      <td>2</td>\n",
       "      <td>Myles, Mr. Thomas Francis</td>\n",
       "      <td>male</td>\n",
       "      <td>62.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>240276</td>\n",
       "      <td>9.6875</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Q</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>895</td>\n",
       "      <td>3</td>\n",
       "      <td>Wirz, Mr. Albert</td>\n",
       "      <td>male</td>\n",
       "      <td>27.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>315154</td>\n",
       "      <td>8.6625</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>896</td>\n",
       "      <td>3</td>\n",
       "      <td>Hirvonen, Mrs. Alexander (Helga E Lindqvist)</td>\n",
       "      <td>female</td>\n",
       "      <td>22.0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3101298</td>\n",
       "      <td>12.2875</td>\n",
       "      <td>NaN</td>\n",
       "      <td>S</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   PassengerId  Pclass                                          Name     Sex  \\\n",
       "0          892       3                              Kelly, Mr. James    male   \n",
       "1          893       3              Wilkes, Mrs. James (Ellen Needs)  female   \n",
       "2          894       2                     Myles, Mr. Thomas Francis    male   \n",
       "3          895       3                              Wirz, Mr. Albert    male   \n",
       "4          896       3  Hirvonen, Mrs. Alexander (Helga E Lindqvist)  female   \n",
       "\n",
       "    Age  SibSp  Parch   Ticket     Fare Cabin Embarked  Survived  \n",
       "0  34.5      0      0   330911   7.8292   NaN        Q         0  \n",
       "1  47.0      1      0   363272   7.0000   NaN        S         0  \n",
       "2  62.0      0      0   240276   9.6875   NaN        Q         0  \n",
       "3  27.0      0      0   315154   8.6625   NaN        S         0  \n",
       "4  22.0      1      1  3101298  12.2875   NaN        S         1  "
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_test.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.123241,
     "end_time": "2020-11-22T06:38:25.068670",
     "exception": false,
     "start_time": "2020-11-22T06:38:24.945429",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "The new Test set with Survived Column"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.104137,
     "end_time": "2020-11-22T06:38:25.286925",
     "exception": false,
     "start_time": "2020-11-22T06:38:25.182788",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "* Submitting the predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2020-11-22T06:38:25.569952Z",
     "iopub.status.busy": "2020-11-22T06:38:25.568134Z",
     "iopub.status.idle": "2020-11-22T06:38:25.737786Z",
     "shell.execute_reply": "2020-11-22T06:38:25.738884Z"
    },
    "papermill": {
     "duration": 0.283746,
     "end_time": "2020-11-22T06:38:25.739067",
     "exception": false,
     "start_time": "2020-11-22T06:38:25.455321",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "submit=new_test[['PassengerId','Survived']]\n",
    "submit.to_csv('predictions.csv',index=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.091298,
     "end_time": "2020-11-22T06:38:25.930317",
     "exception": false,
     "start_time": "2020-11-22T06:38:25.839019",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "<img src=\"https://upload.wikimedia.org/wikipedia/commons/thumb/9/9c/Titanic_wreck_bow.jpg/1200px-Titanic_wreck_bow.jpg\">"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.071565,
     "end_time": "2020-11-22T06:38:26.078284",
     "exception": false,
     "start_time": "2020-11-22T06:38:26.006719",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "#                         *The End*                                                   "
   ]
  },
  {
   "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": "3.8.5"
  },
  "papermill": {
   "duration": 33.869984,
   "end_time": "2020-11-22T06:38:27.338596",
   "environment_variables": {},
   "exception": null,
   "input_path": "__notebook__.ipynb",
   "output_path": "__notebook__.ipynb",
   "parameters": {},
   "start_time": "2020-11-22T06:37:53.468612",
   "version": "2.1.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}