BankOfEngland_NMGHousehold.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "8c59561b",
   "metadata": {},
   "source": [
    "# Data Analysis of Bank of England/NMG Household Survey Data\n",
    "# by Melih Ekinci\n",
    "\n",
    "Data Source:\t\t\t2011-2021 NMG Research Surveys<br>\n",
    "Link:https://www.bankofengland.co.uk/statistics/research-datasets<br>\n",
    "\t\t\t\t\t\t\t\t\t\t\t\t\t\n",
    "Sample of survey:<br>\n",
    "            2011-\t995 households\t<br>\t\t\t\t\t\n",
    "\t\t\t2012-\t4003 households\t\t<br>\t\t\t\t\t\n",
    "\t\t\t2013-\t6006 households\t\t<br>\n",
    "\t\t\t2014-\t6001 households\t\t\t\t\t\t\t\t<br>\n",
    "\t\t\t2015-\t6007 households\t\t\t\t\t\t\t\t<br>\n",
    "\t\t\t2016-\t6011 households\t\t\t\t\t\t\t\t<br>\n",
    "\t\t\t2017-\t6018 households\t\t\t\t\t\t\t\t<br>\n",
    "\t\t\t2018-\t6000 households\t\t\t\t\t\t\t<br>\n",
    "\t\t\t2019-\t6051 households\t\t\t\t\t\t\t\t<br>\n",
    "\t\t\t2020-\t6032 households\t\t\t\t\t\t\t<br>\t\n",
    "\t\t\t2021-\t6051 households\t\t\t\t\t\t<br>\t\n",
    "\t\n",
    "Survey period:<br>\t\t2011-\t23-29 September 2011\t\t\t\t\t\t\t\t<br>\t\t\n",
    "\t\t2012-\t12 September - 3 October 2012\t\t\t\t\t\t\t\t\t<br>\t\n",
    "\t\t2013-\t12-30 September 2013\t\t\t\t\t\t\t\t\t\t<br>\n",
    "\t\t2014-\t3-24 September 2014\t\t\t\t\t\t\t\t\t\t<br>\n",
    "\t\t2015-\t2-22 September 2015\t\t\t\t\t\t\t\t\t\t<br>\n",
    "\t\t2016-\t31 August-19 September 2016\t\t\t\t\t\t\t\t<br>\t\t\n",
    "\t\t2017-\t6-26 September 2017\t\t\t\t\t\t\t\t\t<br>\t\n",
    "\t\t2018-\t5-26 September 2018\t\t\t\t\t\t\t\t<br>\t\t\n",
    "\t\t2019-\t4-24 September 2019\t\t\t\t\t\t\t<br>\t\t\t\n",
    "\t\t2020-\t25 August-15 September 2020\t\t\t\t<br>\t\t\t\t\t\t\n",
    "\t\t2021-\t1-21 September 2021\t\t\t\t\t<br>\t\t\t\t\t\n",
    "\t\t\t\t\t\t\t\t\t\t\t\t<br>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a2e280d9",
   "metadata": {},
   "source": [
    "## 1. Data Preparation"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "779d8341",
   "metadata": {},
   "source": [
    "In order to prepare a dataset of UK household income survey combined across several years, necessary libraries and excel file must be imported firstly. After importing the excel file, each sheet must assigned to a dataframe. Lastly, we will concat these dataframes into together to have a single dataframe contanining data for the years between 2011-2021."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5034495f",
   "metadata": {},
   "source": [
    "### 1.1 Importing data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5d351dca",
   "metadata": {},
   "source": [
    "Below, I imported the libraries that is needed in this work."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "3f029185",
   "metadata": {},
   "outputs": [],
   "source": [
    "#importing necessary libraries\n",
    "#pip install missingno\n",
    "#pip install matplotlib\n",
    "#pip install ggplot==0.4.7\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import itertools\n",
    "#import missingno as msno\n",
    "import matplotlib.pyplot as plt\n",
    "import os\n",
    "import warnings\n",
    "\n",
    "import seaborn as sns\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c9cab560",
   "metadata": {},
   "source": [
    "Changing the working directory to the file folder of choice."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "3ed2203c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Directory changed\n"
     ]
    }
   ],
   "source": [
    "#Changing working directory to a designated file\n",
    "os.chdir(r\"/Users/melihekinci/Documents/BoE\")\n",
    "print(\"Directory changed\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "70928962",
   "metadata": {},
   "source": [
    "Importing the excel file and listing sheet names."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "7308f736",
   "metadata": {},
   "outputs": [],
   "source": [
    "#reading the data\n",
    "xlsx = pd.ExcelFile('boe-nmg-household-survey-data.xlsx')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "09b3fa9e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Instructions',\n",
       " 'Data description',\n",
       " '2011-2021 PID-SUBSID',\n",
       " '2011',\n",
       " '2012',\n",
       " '2013',\n",
       " '2014',\n",
       " '2015',\n",
       " '2016',\n",
       " '2017',\n",
       " '2018',\n",
       " '2019',\n",
       " '2020',\n",
       " '2021']"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#listing sheet names in the data\n",
    "SheetList=xlsx.sheet_names\n",
    "SheetList"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0c8d7487",
   "metadata": {},
   "source": [
    "Next, data frames for each sheet is created using a dictionary."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "7a3d8d3f",
   "metadata": {},
   "outputs": [],
   "source": [
    "SheetDictionary={}\n",
    "#creating datasets for each sheet using dictionary\n",
    "for i in range(len(SheetList)):\n",
    "    SheetDictionary[SheetList[i]]=xlsx.parse(i)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "94eaff49",
   "metadata": {},
   "outputs": [],
   "source": [
    "#getting sheet names into a list.\n",
    "keys=list(SheetDictionary.keys())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5411cbd6",
   "metadata": {},
   "source": [
    "Let's add a column indicating the year of survey, also look at the number of features for each year. It is important to see whether each data frame has the same features and same number of features. Furthermore, names of these features should be written same in order to concatenate datasets properly. So, for the next step I'll check two things: <br>\n",
    "1) Number of features <br>\n",
    "2) Whether feature names are same across datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "807c04b2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "For the year 2011, number of features is 1423.\n",
      "For the year 2012, number of features is 1423.\n",
      "For the year 2013, number of features is 1423.\n",
      "For the year 2014, number of features is 1423.\n",
      "For the year 2015, number of features is 1423.\n",
      "For the year 2016, number of features is 1423.\n",
      "For the year 2017, number of features is 1423.\n",
      "For the year 2018, number of features is 1423.\n",
      "For the year 2019, number of features is 1423.\n",
      "For the year 2020, number of features is 1423.\n",
      "For the year 2021, number of features is 1923.\n"
     ]
    }
   ],
   "source": [
    "#adding a column indicating the year of survey for each data set\n",
    "for i in range(keys.index('2011'),len(keys)):\n",
    "    SheetDictionary[keys[i]][\"year\"]=int(keys[i])\n",
    "    print('For the year '+ str(keys[i]) +', number of features is '+ str(len(SheetDictionary[keys[i]].columns))+'.')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "00c24abf",
   "metadata": {},
   "source": [
    "So the number of features is different for the year 2021. Let's check whether the features are same for the years 2011-2020. We know that their number of features are same. My next step will be getting all feature names in a dataset so I can compare them. It's really important to **strip** and **lower case** features name before comparing them."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "a361f2e1",
   "metadata": {},
   "outputs": [],
   "source": [
    "column_names= pd.DataFrame()\n",
    "for i in range(keys.index('2011'),len(keys)):\n",
    "    if keys[i]!='2021':\n",
    "        column_names[keys[i]]=list(SheetDictionary[keys[i]].rename(str.lower, axis='columns').columns.str.strip())\n",
    "    else:\n",
    "        column_names[keys[i]]=pd.Series(list(SheetDictionary[keys[i]].rename(str.lower, axis='columns').columns.str.strip()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "9aece433",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>2011</th>\n",
       "      <th>2012</th>\n",
       "      <th>2013</th>\n",
       "      <th>2014</th>\n",
       "      <th>2015</th>\n",
       "      <th>2016</th>\n",
       "      <th>2017</th>\n",
       "      <th>2018</th>\n",
       "      <th>2019</th>\n",
       "      <th>2020</th>\n",
       "      <th>2021</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        2011       2012       2013       2014       2015       2016  \\\n",
       "0  we_factor  we_factor  we_factor  we_factor  we_factor  we_factor   \n",
       "1     subsid     subsid     subsid     subsid     subsid     subsid   \n",
       "2       dsoc       dsoc       dsoc       dsoc       dsoc       dsoc   \n",
       "3    dsocial    dsocial    dsocial    dsocial    dsocial    dsocial   \n",
       "4  fgenage_1  fgenage_1  fgenage_1  fgenage_1  fgenage_1  fgenage_1   \n",
       "\n",
       "        2017       2018       2019       2020       2021  \n",
       "0  we_factor  we_factor  we_factor  we_factor  we_factor  \n",
       "1     subsid     subsid     subsid     subsid     subsid  \n",
       "2       dsoc       dsoc       dsoc       dsoc       dsoc  \n",
       "3    dsocial    dsocial    dsocial    dsocial    dsocial  \n",
       "4  fgenage_1  fgenage_1  fgenage_1  fgenage_1  fgenage_1  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "column_names.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d252386d",
   "metadata": {},
   "source": [
    "Here I created a column based a condition to test whether all values are equal across 2011-2021. If any feature name is different in any year given a row, the column (Test1) will show 1 as a result."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "559798fb",
   "metadata": {},
   "outputs": [],
   "source": [
    "column_names['Test1'] = column_names.apply(lambda x: 0 if x['2011'] ==\n",
    "                     x['2012'] and x['2011'] ==x['2013'] and x['2011'] ==x['2014'] and x['2011'] ==x['2015'] and x['2011'] ==x['2016'] and x['2011'] ==x['2017'] and x['2011'] ==x['2018']\n",
    "                    and x['2011'] ==x['2019'] and x['2011'] ==x['2020'] else 1, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "2c142af9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>2011</th>\n",
       "      <th>2012</th>\n",
       "      <th>2013</th>\n",
       "      <th>2014</th>\n",
       "      <th>2015</th>\n",
       "      <th>2016</th>\n",
       "      <th>2017</th>\n",
       "      <th>2018</th>\n",
       "      <th>2019</th>\n",
       "      <th>2020</th>\n",
       "      <th>2021</th>\n",
       "      <th>Test1</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>we_factor</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>subsid</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>dsoc</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>dsocial</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>fgenage_1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        2011       2012       2013       2014       2015       2016  \\\n",
       "0  we_factor  we_factor  we_factor  we_factor  we_factor  we_factor   \n",
       "1     subsid     subsid     subsid     subsid     subsid     subsid   \n",
       "2       dsoc       dsoc       dsoc       dsoc       dsoc       dsoc   \n",
       "3    dsocial    dsocial    dsocial    dsocial    dsocial    dsocial   \n",
       "4  fgenage_1  fgenage_1  fgenage_1  fgenage_1  fgenage_1  fgenage_1   \n",
       "\n",
       "        2017       2018       2019       2020       2021  Test1  \n",
       "0  we_factor  we_factor  we_factor  we_factor  we_factor      0  \n",
       "1     subsid     subsid     subsid     subsid     subsid      0  \n",
       "2       dsoc       dsoc       dsoc       dsoc       dsoc      0  \n",
       "3    dsocial    dsocial    dsocial    dsocial    dsocial      0  \n",
       "4  fgenage_1  fgenage_1  fgenage_1  fgenage_1  fgenage_1      0  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "column_names.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "e6028b46",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Unique values for the test column: [0]\n",
      "Therefore, all of the 1423 features across the datasets belonging the years 2011-2020 are the same features.\n"
     ]
    }
   ],
   "source": [
    "print(\"Unique values for the test column: \"+str(column_names.Test1.unique()))\n",
    "print(\"Therefore, all of the 1423 features across the datasets belonging the years 2011-2020 are the same features.\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0a8fa1d6",
   "metadata": {},
   "source": [
    "### 1.2 Merging dataframes"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d179704d",
   "metadata": {},
   "source": [
    "So, we know that feature names and number are same for the years 2011-2020. For the year 2021, there might be additional features. In order to concatenate these datasets into one single dataset, we can use pd.concat function to match features accordingly. **It's important to keep feature names stripped and lower cased.**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "d92ac258",
   "metadata": {},
   "outputs": [],
   "source": [
    "#merging all data sets across years\n",
    "df_merged=SheetDictionary[keys[keys.index('2011')]].rename(str.lower, axis='columns').rename(str.strip, axis='columns')\n",
    "for i in range(keys.index('2012'),len(keys)):\n",
    "    df_merged=pd.concat([df_merged, SheetDictionary[keys[i]].rename(str.lower, axis='columns').rename(str.strip, axis='columns')],axis=0, ignore_index=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "f0fa1af0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>we_factor</th>\n",
       "      <th>subsid</th>\n",
       "      <th>dsoc</th>\n",
       "      <th>dsocial</th>\n",
       "      <th>fgenage_1</th>\n",
       "      <th>dage</th>\n",
       "      <th>dregion</th>\n",
       "      <th>fgen</th>\n",
       "      <th>qhousing</th>\n",
       "      <th>dhousing</th>\n",
       "      <th>...</th>\n",
       "      <th>cv12b_4</th>\n",
       "      <th>cv12b_5</th>\n",
       "      <th>cv12b_97</th>\n",
       "      <th>cv12c_1</th>\n",
       "      <th>cv12c_2</th>\n",
       "      <th>cv12c_3</th>\n",
       "      <th>cv12c_4</th>\n",
       "      <th>cv12c_97</th>\n",
       "      <th>ret2021sep</th>\n",
       "      <th>mh04</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.176425</td>\n",
       "      <td>22007620.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>23</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.931040</td>\n",
       "      <td>22238715.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>22</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.181808</td>\n",
       "      <td>20404925.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>59</td>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.000213</td>\n",
       "      <td>21839916.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>21</td>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.913671</td>\n",
       "      <td>23091998.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>24</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 1924 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   we_factor      subsid  dsoc  dsocial  fgenage_1  dage  dregion  fgen  \\\n",
       "0   1.176425  22007620.0   2.0      1.0         23     1        3     2   \n",
       "1   0.931040  22238715.0   5.0      5.0         22     1        3     1   \n",
       "2   1.181808  20404925.0   2.0      1.0         59     5        3     1   \n",
       "3   1.000213  21839916.0   5.0      5.0         21     1        9     1   \n",
       "4   0.913671  23091998.0   4.0      4.0         24     1        1     2   \n",
       "\n",
       "   qhousing  dhousing  ...  cv12b_4  cv12b_5  cv12b_97  cv12c_1  cv12c_2  \\\n",
       "0         4         4  ...      NaN      NaN       NaN      NaN      NaN   \n",
       "1         1         1  ...      NaN      NaN       NaN      NaN      NaN   \n",
       "2         2         2  ...      NaN      NaN       NaN      NaN      NaN   \n",
       "3         3         3  ...      NaN      NaN       NaN      NaN      NaN   \n",
       "4         4         4  ...      NaN      NaN       NaN      NaN      NaN   \n",
       "\n",
       "   cv12c_3  cv12c_4  cv12c_97  ret2021sep  mh04  \n",
       "0      NaN      NaN       NaN         NaN   NaN  \n",
       "1      NaN      NaN       NaN         NaN   NaN  \n",
       "2      NaN      NaN       NaN         NaN   NaN  \n",
       "3      NaN      NaN       NaN         NaN   NaN  \n",
       "4      NaN      NaN       NaN         NaN   NaN  \n",
       "\n",
       "[5 rows x 1924 columns]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#the final dataset to be cleansed/analyzed is ready.\n",
    "df_merged.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "29a78eb2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 59175 entries, 0 to 59174\n",
      "Columns: 1924 entries, we_factor to mh04\n",
      "dtypes: float64(1898), int64(23), object(3)\n",
      "memory usage: 868.6+ MB\n"
     ]
    }
   ],
   "source": [
    "df_merged.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "ecb6f50a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021])"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged.year.unique()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6a49c204",
   "metadata": {},
   "source": [
    "### 1.3 Data Quality"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a893ab33",
   "metadata": {},
   "source": [
    "Since we merged datasets properly, we can now try to understand quality of this dataset. For example, looking at missing value ratios for each column can be intuitive."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ae5c06e3",
   "metadata": {},
   "source": [
    "Below, I created a dataframe which has the features in dataset as index. Number of missing values and its ratio to total number of observations is listed."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "dbaa5a1c",
   "metadata": {},
   "outputs": [],
   "source": [
    "null=df_merged.isnull().sum().sort_values(ascending = False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "7a6ae7f7",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_null = pd.DataFrame(data=null, columns=['null_number'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "11638ded",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_null[\"null_ratio\"]=df_null[\"null_number\"]/59175*100"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "cb882147",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>null_number</th>\n",
       "      <th>null_ratio</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>boe87free_ps_6</th>\n",
       "      <td>59175</td>\n",
       "      <td>100.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>be2ab_4</th>\n",
       "      <td>59175</td>\n",
       "      <td>100.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>be2ab_6</th>\n",
       "      <td>59175</td>\n",
       "      <td>100.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>be2ab_7</th>\n",
       "      <td>59175</td>\n",
       "      <td>100.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>be2ab_8</th>\n",
       "      <td>59175</td>\n",
       "      <td>100.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                null_number  null_ratio\n",
       "boe87free_ps_6        59175       100.0\n",
       "be2ab_4               59175       100.0\n",
       "be2ab_6               59175       100.0\n",
       "be2ab_7               59175       100.0\n",
       "be2ab_8               59175       100.0"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_null.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "023bcea2",
   "metadata": {},
   "source": [
    "Also, I will look at number of features which has 0 missing values. There are only 24 features out of 1924 columns which has no missing observation."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "27d45f15",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>null_number</th>\n",
       "      <th>null_ratio</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>year</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>fgenage_1</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dage</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>fgen</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>qhousing</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dhousing</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>be13</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dregion</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>be2a</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>qbe15_97</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>qbe15_3</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>be23</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>qbe15_4</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>qbe15_5</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>qbe15_6</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>qbe15_7</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>qregion</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>qbe15_8</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>qbe15_11</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>qbe15_9</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>qbe15_10</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>qbe15_96</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>fbe03</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>we_factor</th>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           null_number  null_ratio\n",
       "year                 0         0.0\n",
       "fgenage_1            0         0.0\n",
       "dage                 0         0.0\n",
       "fgen                 0         0.0\n",
       "qhousing             0         0.0\n",
       "dhousing             0         0.0\n",
       "be13                 0         0.0\n",
       "dregion              0         0.0\n",
       "be2a                 0         0.0\n",
       "qbe15_97             0         0.0\n",
       "qbe15_3              0         0.0\n",
       "be23                 0         0.0\n",
       "qbe15_4              0         0.0\n",
       "qbe15_5              0         0.0\n",
       "qbe15_6              0         0.0\n",
       "qbe15_7              0         0.0\n",
       "qregion              0         0.0\n",
       "qbe15_8              0         0.0\n",
       "qbe15_11             0         0.0\n",
       "qbe15_9              0         0.0\n",
       "qbe15_10             0         0.0\n",
       "qbe15_96             0         0.0\n",
       "fbe03                0         0.0\n",
       "we_factor            0         0.0"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_null[df_null.null_ratio==0]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5eb4b830",
   "metadata": {},
   "source": [
    "I will drop all features that have no observations in it."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "df597ae5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>be10b_hidden</th>\n",
       "      <th>boe87incomev2_13</th>\n",
       "      <th>boe87_bandsv1v2_13</th>\n",
       "      <th>boe87_bandsv1v2_7</th>\n",
       "      <th>boe87incomev2_7</th>\n",
       "      <th>boe87incomev2_3</th>\n",
       "      <th>boe87_bandsv1v2_3</th>\n",
       "      <th>boe87incomev2_12</th>\n",
       "      <th>boe87incomev2_99</th>\n",
       "      <th>boe87_bandsv1v2_12</th>\n",
       "      <th>...</th>\n",
       "      <th>qbe15_6</th>\n",
       "      <th>qbe15_7</th>\n",
       "      <th>qregion</th>\n",
       "      <th>qbe15_8</th>\n",
       "      <th>qbe15_11</th>\n",
       "      <th>qbe15_9</th>\n",
       "      <th>qbe15_10</th>\n",
       "      <th>qbe15_96</th>\n",
       "      <th>fbe03</th>\n",
       "      <th>we_factor</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1.176425</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.931040</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1.181808</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>11</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1.000213</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.913671</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 1461 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   be10b_hidden  boe87incomev2_13  boe87_bandsv1v2_13  boe87_bandsv1v2_7  \\\n",
       "0           NaN               NaN                 NaN                NaN   \n",
       "1           NaN               NaN                 NaN                NaN   \n",
       "2           NaN               NaN                 NaN                NaN   \n",
       "3           NaN               NaN                 NaN                NaN   \n",
       "4           NaN               NaN                 NaN                NaN   \n",
       "\n",
       "   boe87incomev2_7  boe87incomev2_3  boe87_bandsv1v2_3  boe87incomev2_12  \\\n",
       "0              NaN              NaN                NaN               NaN   \n",
       "1              NaN              NaN                NaN               NaN   \n",
       "2              NaN              NaN                NaN               NaN   \n",
       "3              NaN              NaN                NaN               NaN   \n",
       "4              NaN              NaN                NaN               NaN   \n",
       "\n",
       "   boe87incomev2_99  boe87_bandsv1v2_12  ...  qbe15_6  qbe15_7  qregion  \\\n",
       "0               NaN                 NaN  ...        0        1        4   \n",
       "1               NaN                 NaN  ...        0        0        5   \n",
       "2               NaN                 NaN  ...        0        0        5   \n",
       "3               NaN                 NaN  ...        0        0       11   \n",
       "4               NaN                 NaN  ...        0        0        1   \n",
       "\n",
       "   qbe15_8  qbe15_11  qbe15_9  qbe15_10  qbe15_96  fbe03  we_factor  \n",
       "0        0         0        1         0         0      1   1.176425  \n",
       "1        0         0        0         0         0      1   0.931040  \n",
       "2        0         0        0         0         0      1   1.181808  \n",
       "3        0         0        0         0         0      1   1.000213  \n",
       "4        0         0        0         0         0      1   0.913671  \n",
       "\n",
       "[5 rows x 1461 columns]"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged2=df_merged[df_null[df_null.null_ratio!=100].index]\n",
    "df_merged2.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d747dae4",
   "metadata": {},
   "source": [
    "We have left with 1461 features, now we can focus on the features that is topic of analysis: household income and other 4-5 variables. <br> Features related to household income are qincome,qincome_v1,qincome_v2,qincome_free,qincomefree_v2. Let's check how these features evolve across years."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7dde25e0",
   "metadata": {},
   "source": [
    "As there are several variables related to income in data, I wanted to check all variables to see whether we can use them across 2011-2021 meaningfully."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "bcd5dff7",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_merged2[\"qincomefreev2_calc\"]=df_merged2[\"qincomefreev2_n_1\"]+df_merged2[\"qincomefreev2_n_2\"]+df_merged2[\"qincomefreev2_n_3\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "264fe7a3",
   "metadata": {},
   "outputs": [],
   "source": [
    "#var_income=list(df_merged2.columns[df_merged2.columns.str.contains(\"income\")])\n",
    "var_income=[\"qincome\",\"qincomev1\",\"qincomev2_1_1\",\"qincomefree_1\",\"qincomefreev2_n_1\",\"qincomefreev2_n_2\",\"qincomefreev2_n_3\",\"qincomefreev2_calc\",\"hincomev2_1\",\"hincomev2_2\",\"hincomev2_3\",\"incomev2comb\",\"combincome\"]\n",
    "var_income.append(\"year\")\n",
    "var_income.sort()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "30497934",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>combincome</th>\n",
       "      <th>hincomev2_1</th>\n",
       "      <th>hincomev2_2</th>\n",
       "      <th>hincomev2_3</th>\n",
       "      <th>incomev2comb</th>\n",
       "      <th>qincome</th>\n",
       "      <th>qincomefree_1</th>\n",
       "      <th>qincomefreev2_calc</th>\n",
       "      <th>qincomefreev2_n_1</th>\n",
       "      <th>qincomefreev2_n_2</th>\n",
       "      <th>qincomefreev2_n_3</th>\n",
       "      <th>qincomev1</th>\n",
       "      <th>qincomev2_1_1</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>year</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2011</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>16.504523</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2012</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>16.782913</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2013</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>16.729271</td>\n",
       "      <td>41376.935119</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2014</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>17.821030</td>\n",
       "      <td>36633.515647</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2015</th>\n",
       "      <td>NaN</td>\n",
       "      <td>10.050400</td>\n",
       "      <td>9.552790</td>\n",
       "      <td>8.876136</td>\n",
       "      <td>12.697602</td>\n",
       "      <td>NaN</td>\n",
       "      <td>37111.741182</td>\n",
       "      <td>53395.743073</td>\n",
       "      <td>21564.103796</td>\n",
       "      <td>18476.158967</td>\n",
       "      <td>17233.613636</td>\n",
       "      <td>11.233227</td>\n",
       "      <td>11.371859</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016</th>\n",
       "      <td>NaN</td>\n",
       "      <td>9.969889</td>\n",
       "      <td>9.525644</td>\n",
       "      <td>8.803180</td>\n",
       "      <td>12.590584</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>56333.778607</td>\n",
       "      <td>22104.384303</td>\n",
       "      <td>19046.750259</td>\n",
       "      <td>15658.438497</td>\n",
       "      <td>NaN</td>\n",
       "      <td>11.036284</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017</th>\n",
       "      <td>671.520398</td>\n",
       "      <td>9.781987</td>\n",
       "      <td>9.746865</td>\n",
       "      <td>8.956474</td>\n",
       "      <td>12.559987</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>58039.706349</td>\n",
       "      <td>22074.775710</td>\n",
       "      <td>20146.470852</td>\n",
       "      <td>15748.132300</td>\n",
       "      <td>NaN</td>\n",
       "      <td>10.819923</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018</th>\n",
       "      <td>731.733399</td>\n",
       "      <td>10.095000</td>\n",
       "      <td>9.914708</td>\n",
       "      <td>8.957284</td>\n",
       "      <td>12.794500</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>62129.710875</td>\n",
       "      <td>24716.298452</td>\n",
       "      <td>21429.505104</td>\n",
       "      <td>16377.762530</td>\n",
       "      <td>NaN</td>\n",
       "      <td>11.023328</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2019</th>\n",
       "      <td>722.720517</td>\n",
       "      <td>10.098000</td>\n",
       "      <td>9.779473</td>\n",
       "      <td>8.884615</td>\n",
       "      <td>12.773591</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>61527.681046</td>\n",
       "      <td>37282.195140</td>\n",
       "      <td>21684.883894</td>\n",
       "      <td>15106.296610</td>\n",
       "      <td>NaN</td>\n",
       "      <td>10.753562</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020</th>\n",
       "      <td>698.321668</td>\n",
       "      <td>9.945789</td>\n",
       "      <td>9.290446</td>\n",
       "      <td>7.812107</td>\n",
       "      <td>12.507294</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>57151.862697</td>\n",
       "      <td>24770.035273</td>\n",
       "      <td>20349.513764</td>\n",
       "      <td>12075.324690</td>\n",
       "      <td>NaN</td>\n",
       "      <td>10.372326</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2021</th>\n",
       "      <td>705.804924</td>\n",
       "      <td>10.069245</td>\n",
       "      <td>9.200553</td>\n",
       "      <td>7.374340</td>\n",
       "      <td>12.456949</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>60037.401124</td>\n",
       "      <td>26138.062500</td>\n",
       "      <td>20483.596011</td>\n",
       "      <td>11458.933333</td>\n",
       "      <td>NaN</td>\n",
       "      <td>10.470018</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      combincome  hincomev2_1  hincomev2_2  hincomev2_3  incomev2comb  \\\n",
       "year                                                                    \n",
       "2011         NaN          NaN          NaN          NaN           NaN   \n",
       "2012         NaN          NaN          NaN          NaN           NaN   \n",
       "2013         NaN          NaN          NaN          NaN           NaN   \n",
       "2014         NaN          NaN          NaN          NaN           NaN   \n",
       "2015         NaN    10.050400     9.552790     8.876136     12.697602   \n",
       "2016         NaN     9.969889     9.525644     8.803180     12.590584   \n",
       "2017  671.520398     9.781987     9.746865     8.956474     12.559987   \n",
       "2018  731.733399    10.095000     9.914708     8.957284     12.794500   \n",
       "2019  722.720517    10.098000     9.779473     8.884615     12.773591   \n",
       "2020  698.321668     9.945789     9.290446     7.812107     12.507294   \n",
       "2021  705.804924    10.069245     9.200553     7.374340     12.456949   \n",
       "\n",
       "        qincome  qincomefree_1  qincomefreev2_calc  qincomefreev2_n_1  \\\n",
       "year                                                                    \n",
       "2011  16.504523            NaN                 NaN                NaN   \n",
       "2012  16.782913            NaN                 NaN                NaN   \n",
       "2013  16.729271   41376.935119                 NaN                NaN   \n",
       "2014  17.821030   36633.515647                 NaN                NaN   \n",
       "2015        NaN   37111.741182        53395.743073       21564.103796   \n",
       "2016        NaN            NaN        56333.778607       22104.384303   \n",
       "2017        NaN            NaN        58039.706349       22074.775710   \n",
       "2018        NaN            NaN        62129.710875       24716.298452   \n",
       "2019        NaN            NaN        61527.681046       37282.195140   \n",
       "2020        NaN            NaN        57151.862697       24770.035273   \n",
       "2021        NaN            NaN        60037.401124       26138.062500   \n",
       "\n",
       "      qincomefreev2_n_2  qincomefreev2_n_3  qincomev1  qincomev2_1_1  \n",
       "year                                                                  \n",
       "2011                NaN                NaN        NaN            NaN  \n",
       "2012                NaN                NaN        NaN            NaN  \n",
       "2013                NaN                NaN        NaN            NaN  \n",
       "2014                NaN                NaN        NaN            NaN  \n",
       "2015       18476.158967       17233.613636  11.233227      11.371859  \n",
       "2016       19046.750259       15658.438497        NaN      11.036284  \n",
       "2017       20146.470852       15748.132300        NaN      10.819923  \n",
       "2018       21429.505104       16377.762530        NaN      11.023328  \n",
       "2019       21684.883894       15106.296610        NaN      10.753562  \n",
       "2020       20349.513764       12075.324690        NaN      10.372326  \n",
       "2021       20483.596011       11458.933333        NaN      10.470018  "
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged2[var_income].groupby(by=\"year\").mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b0eb5183",
   "metadata": {},
   "source": [
    "For the year 2011 and 2012, there is only categorical income feature available for analysis. For other years, there are  both categorical and continuous features related to income. For comparison between 2011 and 2021, I have to use categorical ones. I will use 2015 and afterwards to see trend of household income."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "660b4451",
   "metadata": {},
   "source": [
    "Now, I want to look at availability of social variables such as working status, age group, gender and marital status across years."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "3c67dfed",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>dage</th>\n",
       "      <th>fgen</th>\n",
       "      <th>qmarital</th>\n",
       "      <th>workingstatus</th>\n",
       "      <th>a20workingstatus</th>\n",
       "      <th>qworking</th>\n",
       "      <th>dworking</th>\n",
       "      <th>a20dworking</th>\n",
       "      <th>dhousing</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>year</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2011</th>\n",
       "      <td>3.676382</td>\n",
       "      <td>1.545729</td>\n",
       "      <td>2.093467</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.068342</td>\n",
       "      <td>1.454271</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.450251</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2012</th>\n",
       "      <td>3.706970</td>\n",
       "      <td>1.515613</td>\n",
       "      <td>2.362728</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.162878</td>\n",
       "      <td>1.438171</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.592805</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2013</th>\n",
       "      <td>3.704296</td>\n",
       "      <td>1.509158</td>\n",
       "      <td>2.308358</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.192141</td>\n",
       "      <td>1.438561</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4.035798</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2014</th>\n",
       "      <td>3.816531</td>\n",
       "      <td>1.486086</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.491918</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.443426</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.925846</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2015</th>\n",
       "      <td>3.738472</td>\n",
       "      <td>1.507907</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.323955</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.412519</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.178791</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016</th>\n",
       "      <td>3.811180</td>\n",
       "      <td>1.505240</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.348361</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.412577</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.199301</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017</th>\n",
       "      <td>3.807245</td>\n",
       "      <td>1.537554</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.555334</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.447657</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.906115</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018</th>\n",
       "      <td>3.884833</td>\n",
       "      <td>1.532167</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.314167</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.399167</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.751000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2019</th>\n",
       "      <td>4.027764</td>\n",
       "      <td>1.514295</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.483556</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.437118</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.783507</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020</th>\n",
       "      <td>3.844662</td>\n",
       "      <td>1.511273</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4.249337</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.401359</td>\n",
       "      <td>2.883952</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2021</th>\n",
       "      <td>3.908445</td>\n",
       "      <td>1.603867</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4.454801</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.432821</td>\n",
       "      <td>2.849281</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          dage      fgen  qmarital  workingstatus  a20workingstatus  qworking  \\\n",
       "year                                                                            \n",
       "2011  3.676382  1.545729  2.093467            NaN               NaN  5.068342   \n",
       "2012  3.706970  1.515613  2.362728            NaN               NaN  5.162878   \n",
       "2013  3.704296  1.509158  2.308358            NaN               NaN  5.192141   \n",
       "2014  3.816531  1.486086       NaN       3.491918               NaN       NaN   \n",
       "2015  3.738472  1.507907       NaN       3.323955               NaN       NaN   \n",
       "2016  3.811180  1.505240       NaN       3.348361               NaN       NaN   \n",
       "2017  3.807245  1.537554       NaN       3.555334               NaN       NaN   \n",
       "2018  3.884833  1.532167       NaN       3.314167               NaN       NaN   \n",
       "2019  4.027764  1.514295       NaN       3.483556               NaN       NaN   \n",
       "2020  3.844662  1.511273       NaN            NaN          4.249337       NaN   \n",
       "2021  3.908445  1.603867       NaN            NaN          4.454801       NaN   \n",
       "\n",
       "      dworking  a20dworking  dhousing  \n",
       "year                                   \n",
       "2011  1.454271          NaN  3.450251  \n",
       "2012  1.438171          NaN  3.592805  \n",
       "2013  1.438561          NaN  4.035798  \n",
       "2014  1.443426          NaN  2.925846  \n",
       "2015  1.412519          NaN  3.178791  \n",
       "2016  1.412577          NaN  3.199301  \n",
       "2017  1.447657          NaN  2.906115  \n",
       "2018  1.399167          NaN  2.751000  \n",
       "2019  1.437118          NaN  2.783507  \n",
       "2020       NaN     1.401359  2.883952  \n",
       "2021       NaN     1.432821  2.849281  "
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged2[[\"dage\",\"fgen\",\"qmarital\",\"workingstatus\",\"a20workingstatus\",\"qworking\",\"dworking\",\"a20dworking\",\"dhousing\",\"year\"]].groupby(by=\"year\").mean()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "940bfc84",
   "metadata": {},
   "source": [
    "I want to look at savings of these individuals, too."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "984a05dd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>be2a_hidden</th>\n",
       "      <th>be2afree_1</th>\n",
       "      <th>be2afree_dk_1</th>\n",
       "      <th>be2afree_dk_2</th>\n",
       "      <th>be2a</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>year</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2011</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>11.162814</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2012</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>10.191856</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2013</th>\n",
       "      <td>1.282317</td>\n",
       "      <td>810.491196</td>\n",
       "      <td>0.180997</td>\n",
       "      <td>0.072563</td>\n",
       "      <td>13.692807</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2014</th>\n",
       "      <td>NaN</td>\n",
       "      <td>862.085217</td>\n",
       "      <td>0.215631</td>\n",
       "      <td>0.113648</td>\n",
       "      <td>18.122480</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2015</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1223.641988</td>\n",
       "      <td>0.224738</td>\n",
       "      <td>0.132179</td>\n",
       "      <td>19.006825</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1713.429094</td>\n",
       "      <td>0.245051</td>\n",
       "      <td>0.163700</td>\n",
       "      <td>20.104475</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017</th>\n",
       "      <td>NaN</td>\n",
       "      <td>2523.003298</td>\n",
       "      <td>0.237288</td>\n",
       "      <td>0.158026</td>\n",
       "      <td>17.988202</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1756.278768</td>\n",
       "      <td>0.303167</td>\n",
       "      <td>0.145000</td>\n",
       "      <td>20.039167</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2019</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1199.499859</td>\n",
       "      <td>0.274996</td>\n",
       "      <td>0.139151</td>\n",
       "      <td>20.083292</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1947.913004</td>\n",
       "      <td>0.315153</td>\n",
       "      <td>0.137931</td>\n",
       "      <td>22.171088</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2021</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1630.364248</td>\n",
       "      <td>0.270534</td>\n",
       "      <td>0.139646</td>\n",
       "      <td>19.668319</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      be2a_hidden   be2afree_1  be2afree_dk_1  be2afree_dk_2       be2a\n",
       "year                                                                   \n",
       "2011          NaN          NaN            NaN            NaN  11.162814\n",
       "2012          NaN          NaN            NaN            NaN  10.191856\n",
       "2013     1.282317   810.491196       0.180997       0.072563  13.692807\n",
       "2014          NaN   862.085217       0.215631       0.113648  18.122480\n",
       "2015          NaN  1223.641988       0.224738       0.132179  19.006825\n",
       "2016          NaN  1713.429094       0.245051       0.163700  20.104475\n",
       "2017          NaN  2523.003298       0.237288       0.158026  17.988202\n",
       "2018          NaN  1756.278768       0.303167       0.145000  20.039167\n",
       "2019          NaN  1199.499859       0.274996       0.139151  20.083292\n",
       "2020          NaN  1947.913004       0.315153       0.137931  22.171088\n",
       "2021          NaN  1630.364248       0.270534       0.139646  19.668319"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "var_saving=list(df_merged2.columns[df_merged2.columns.str.contains(\"be2a\")])\n",
    "var_saving.append(\"year\")\n",
    "df_merged2[var_saving].groupby(by=\"year\").mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "775d9f71",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>be24</th>\n",
       "      <th>boe60a</th>\n",
       "      <th>boe62a</th>\n",
       "      <th>boe55</th>\n",
       "      <th>boe65b</th>\n",
       "      <th>mq08</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>year</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2011</th>\n",
       "      <td>11.141709</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2012</th>\n",
       "      <td>9.760180</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2013</th>\n",
       "      <td>9.399267</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2014</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.269288</td>\n",
       "      <td>19.552741</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2015</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1.933743</td>\n",
       "      <td>1.758876</td>\n",
       "      <td>2.108041</td>\n",
       "      <td>18.005161</td>\n",
       "      <td>3.292992</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1.980467</td>\n",
       "      <td>1.731013</td>\n",
       "      <td>2.266345</td>\n",
       "      <td>19.129263</td>\n",
       "      <td>3.581933</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1.992220</td>\n",
       "      <td>1.681431</td>\n",
       "      <td>2.138252</td>\n",
       "      <td>17.741609</td>\n",
       "      <td>3.756065</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018</th>\n",
       "      <td>NaN</td>\n",
       "      <td>2.022379</td>\n",
       "      <td>1.758373</td>\n",
       "      <td>2.143167</td>\n",
       "      <td>17.777333</td>\n",
       "      <td>3.739333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2019</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1.970270</td>\n",
       "      <td>1.779352</td>\n",
       "      <td>2.140142</td>\n",
       "      <td>17.159313</td>\n",
       "      <td>3.974219</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1.948107</td>\n",
       "      <td>1.777439</td>\n",
       "      <td>2.214854</td>\n",
       "      <td>17.056532</td>\n",
       "      <td>3.984085</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2021</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1.939264</td>\n",
       "      <td>1.735614</td>\n",
       "      <td>2.159974</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.433317</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           be24    boe60a    boe62a     boe55     boe65b      mq08\n",
       "year                                                              \n",
       "2011  11.141709       NaN       NaN       NaN        NaN       NaN\n",
       "2012   9.760180       NaN       NaN       NaN        NaN       NaN\n",
       "2013   9.399267       NaN       NaN       NaN        NaN       NaN\n",
       "2014        NaN       NaN       NaN  2.269288  19.552741       NaN\n",
       "2015        NaN  1.933743  1.758876  2.108041  18.005161  3.292992\n",
       "2016        NaN  1.980467  1.731013  2.266345  19.129263  3.581933\n",
       "2017        NaN  1.992220  1.681431  2.138252  17.741609  3.756065\n",
       "2018        NaN  2.022379  1.758373  2.143167  17.777333  3.739333\n",
       "2019        NaN  1.970270  1.779352  2.140142  17.159313  3.974219\n",
       "2020        NaN  1.948107  1.777439  2.214854  17.056532  3.984085\n",
       "2021        NaN  1.939264  1.735614  2.159974        NaN  3.433317"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged2[[\"be24\",\"boe60a\",\"boe62a\",\"year\",\"boe55\",\"boe65b\",\"mq08\"]].groupby(by=\"year\").mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "2c62982a",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['be13b_1_1', 'be13b_1_2', 'boe65bfree_dk_1', 'boe65bfree_dk_2',\n",
       "       'boe65b', 'fq02', 'fq01', 'mq07', 'mq06', 'mq04', 'otheradults', 'mq01',\n",
       "       'mq02', 'mq08', 'mq03', 'typeresponse_1', 'qbe22b', 'subsid',\n",
       "       'dworking', 'be43', 'boe39', 'boe55', 'bod55', 'boe39a_2', 'boe39a_3',\n",
       "       'nochildren', 'boe39a_1', 'boe65afree_dk_1', 'boe65a',\n",
       "       'boe65afree_dk_2', 'be2afree_dk_1', 'be2afree_dk_2', 'be31e', 'qual',\n",
       "       'be31g', 'year', 'fgenage_1', 'dage', 'fgen', 'qhousing', 'dhousing',\n",
       "       'be13', 'dregion', 'be2a', 'qbe15_97', 'qbe15_3', 'be23', 'qbe15_4',\n",
       "       'qbe15_5', 'qbe15_6', 'qbe15_7', 'qregion', 'qbe15_8', 'qbe15_11',\n",
       "       'qbe15_9', 'qbe15_10', 'qbe15_96', 'fbe03', 'we_factor'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Columns that has missing value ratio lower than 30%\n",
    "df_merged3=df_merged[df_null[df_null.null_ratio<30].index]\n",
    "df_merged3.columns"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "25031909",
   "metadata": {},
   "source": [
    "## 2. Data Analysis"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b7e4a465",
   "metadata": {},
   "source": [
    "I will choose categorical and continuous income variables, age,housing, monthly savings and expectations over economy to analyze in this work."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e7e72090",
   "metadata": {},
   "source": [
    "Since income brackets are different for 2011, I will make 2 graphs looking at distributions separately."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "c4c9ff5d",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Created a new variable maps explanation of values using data description.\n",
    "df_merged2[\"qincome_mapped\"]=df_merged2[\"qincome\"].map({\n",
    "    1: 'Up to £4,499',\n",
    "    2: '£4,500 - £6,499',\n",
    "    3:'£6,500 - £7,499',\n",
    "    4:'£7,500 - £9,499',\n",
    "    5:'£9,500 - £11,499',\n",
    "    6:'£11,500 - £13,499',\n",
    "    7:'£13,500 - £15,499',\n",
    "    8:'£15,500 - £17,499',\n",
    "    9:'£17,500 - £24,999',\n",
    "    10:'£25,000 - £29,999',\n",
    "    11:'£30,000 - £39,999',\n",
    "    12:'£40,000 - £49,999',\n",
    "    13:'£50,000 - £74,999',\n",
    "    14:'£75,000 - £99,999',\n",
    "    15:'£100,000 or more',\n",
    "    97:'Unknown/Prefer Not to State',\n",
    "    96:'Unknown/Prefer Not to State'})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 154,
   "id": "ff113c53",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 800x480 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#df_merged2[df_merged2.year==2011][\"qincome_mapped\"].hist(alpha=0.5)\n",
    "plt.rcParams.update({'font.size': 13})\n",
    "income_category=['Up to £4,499',\n",
    "                 '£4,500 - £6,499',\n",
    "                 '£6,500 - £7,499',\n",
    "                 '£7,500 - £9,499',\n",
    "                 '£9,500 - £11,499',\n",
    "    '£11,500 - £13,499',\n",
    "    '£13,500 - £15,499',\n",
    "    '£15,500 - £17,499',\n",
    "    '£17,500 - £24,999',\n",
    "    '£25,000 - £29,999',\n",
    "    '£30,000 - £39,999',\n",
    "    '£40,000 - £49,999',\n",
    "    '£50,000 - £74,999',\n",
    "    '£75,000 - £99,999',\n",
    "    '£100,000 or more',\n",
    "    'Unknown/Prefer Not to State']\n",
    "fig = plt.figure(figsize=(10, 6), dpi=80)\n",
    "df_merged2[df_merged2.year==2011][\"qincome_mapped\"].value_counts().reindex(income_category).plot(kind='bar',color=\"purple\")\n",
    "plt.xticks(rotation='vertical')\n",
    "plt.xlabel(\"Income\")\n",
    "plt.ylabel(\"Number of individuals\")\n",
    "plt.title('Distribution of Household Income in 2011')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 146,
   "id": "366712f0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Looking at distributions for 2016 and 2021.\n",
    "order=['Less than 0',\n",
    "    '0',\n",
    "    '£1 – £2,499',\n",
    "    '£2,500 - £4,499',\n",
    "    '£4,500 - £6,499',\n",
    "    '£6,500 - £7,499',\n",
    "    '£7,500 - £9,499',\n",
    "    '£9,500 - £11,499',\n",
    "    '£11,500 - £13,499',\n",
    "    '£13,500 - £15,499',\n",
    "    '£15,500 - £17,499',\n",
    "    '£17,500 - £24,999',\n",
    "    '£25,000 - £34,999',\n",
    "    '£35,000 - £44,999',\n",
    "    '£45,000 - £54,999',\n",
    "    '£55,000 - £74,999',\n",
    "    '£75,000 - £99,999',\n",
    "    '£100,000 or more',\n",
    "    'Unknown/Prefer Not to State']\n",
    "fig, ax = plt.subplots(figsize=(10, 6))\n",
    "ax = sns.countplot(x=\"incomev2comb_mapped\", hue=\"year\", data=df_merged2[(df_merged2.year==2016) | (df_merged2.year==2021)], order=order,palette='inferno')\n",
    "plt.xticks(rotation='vertical')\n",
    "ax.set_xlabel(\"Income\", fontsize = 12)\n",
    "ax.set_ylabel(\"Number of Individuals\", fontsize = 12)\n",
    "plt.legend(title='Year',loc='upper left')\n",
    "plt.title(\"Distribution of Household Income in 2016 and 2021\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5333e592",
   "metadata": {},
   "source": [
    "It can be said that distribution of income generally stays the same between the years 2016 and 2021. However, there is a noticable increase in right tail of the distribution, indicating that percentage of income group > 75,00 sterlin increased more compared to other income groups."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0116ce9b",
   "metadata": {},
   "source": [
    "Now, let's see trend of average the household income between the years 2015-2021."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "e3997a95",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>qincomefreev2_calc</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>year</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2015</th>\n",
       "      <td>53395.743073</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2016</th>\n",
       "      <td>56333.778607</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017</th>\n",
       "      <td>58039.706349</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018</th>\n",
       "      <td>62129.710875</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2019</th>\n",
       "      <td>61527.681046</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020</th>\n",
       "      <td>57151.862697</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2021</th>\n",
       "      <td>60037.401124</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      qincomefreev2_calc\n",
       "year                    \n",
       "2015        53395.743073\n",
       "2016        56333.778607\n",
       "2017        58039.706349\n",
       "2018        62129.710875\n",
       "2019        61527.681046\n",
       "2020        57151.862697\n",
       "2021        60037.401124"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged2[df_merged2.year>2014][[\"qincomefreev2_calc\",\"year\"]].groupby(by=\"year\").mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 170,
   "id": "2f0928db",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "data=df_merged2[df_merged2.year>2014][[\"qincomefreev2_calc\",\"year\"]].groupby(by=\"year\").mean()\n",
    "fig, ax = plt.subplots(figsize=(8, 5))\n",
    "sns.lineplot(data=data, x=\"year\", y=\"qincomefreev2_calc\",marker='*',color='#965786')\n",
    "ax.set_ylim(50000, 65000)\n",
    "ax.set_xlabel(\"Year\", fontsize = 12)\n",
    "ax.set_ylabel(\"Average Household Income (£)\", fontsize = 12)\n",
    "ylabels = ['{:,.0f}'.format(x) for x in ax.get_yticks()]\n",
    "ax.set_yticklabels(ylabels)\n",
    "# label points on the plot\n",
    "for x, y in zip(data.index, data['qincomefreev2_calc']):\n",
    " # the position of the data label relative to the data point can be adjusted by adding/subtracting a value from the x &/ y coordinates\n",
    " plt.text(x = x, # x-coordinate position of data label\n",
    " y = y-150, # y-coordinate position of data label, adjusted to be 150 below the data point\n",
    " s = '{:,.0f}'.format(y), # data label, formatted to ignore decimals\n",
    " color = 'white').set_backgroundcolor(\"#965786\") # set colour of line\n",
    "\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 162,
   "id": "85e287e4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(figsize=(8, 5))\n",
    "data2=df_merged2[df_merged2.year>2014]\n",
    "ax = sns.boxplot(x=\"year\", y=\"qincomefreev2_calc\", data=data2)\n",
    "ax.set_xlabel(\"Year\", fontsize = 12)\n",
    "ax.set_ylabel(\"Household Income (£)\", fontsize = 12)\n",
    "ax.set_ylim(0, 200000)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "cf19437a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count       397.000000\n",
       "mean      53395.743073\n",
       "std       32834.209872\n",
       "min           0.000000\n",
       "25%       31000.000000\n",
       "50%       48000.000000\n",
       "75%       70000.000000\n",
       "max      191000.000000\n",
       "Name: qincomefreev2_calc, dtype: float64"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged2[(df_merged2.year==2015) &  (df_merged2.qincomefreev2_calc!=np.nan)].qincomefreev2_calc.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "b3214b67",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "47094    44500.0\n",
       "47096    45000.0\n",
       "47110     7400.0\n",
       "47118    48000.0\n",
       "47124    74000.0\n",
       "          ...   \n",
       "53076    80000.0\n",
       "53083    81000.0\n",
       "53090    18000.0\n",
       "53102    45000.0\n",
       "53107    30000.0\n",
       "Name: qincomefreev2_calc, Length: 823, dtype: float64"
      ]
     },
     "execution_count": 49,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged2[(df_merged2.year==2020) &  (df_merged2.qincomefreev2_calc>=0)].qincomefreev2_calc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 176,
   "id": "29dd9106",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count       804.000000\n",
       "mean      56333.778607\n",
       "std       47331.817307\n",
       "min           0.000000\n",
       "25%       30000.000000\n",
       "50%       48000.000000\n",
       "75%       70000.000000\n",
       "max      700000.000000\n",
       "Name: qincomefreev2_calc, dtype: float64"
      ]
     },
     "execution_count": 176,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged2[(df_merged2.year==2016) &  (df_merged2.qincomefreev2_calc!=np.nan) ].qincomefreev2_calc.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 165,
   "id": "4784b41a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count       756.000000\n",
       "mean      58039.706349\n",
       "std       46972.137792\n",
       "min           0.000000\n",
       "25%       29416.250000\n",
       "50%       49000.000000\n",
       "75%       74461.000000\n",
       "max      320000.000000\n",
       "Name: qincomefreev2_calc, dtype: float64"
      ]
     },
     "execution_count": 165,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged2[(df_merged2.year==2017) &  (df_merged2.qincomefreev2_calc!=np.nan)].qincomefreev2_calc.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 166,
   "id": "6c120d29",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count       754.000000\n",
       "mean      62129.710875\n",
       "std       47638.349263\n",
       "min           0.000000\n",
       "25%       32000.000000\n",
       "50%       52100.000000\n",
       "75%       80000.000000\n",
       "max      400000.000000\n",
       "Name: qincomefreev2_calc, dtype: float64"
      ]
     },
     "execution_count": 166,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged2[(df_merged2.year==2018) &  (df_merged2.qincomefreev2_calc!=np.nan)].qincomefreev2_calc.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 167,
   "id": "37d30103",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count       765.000000\n",
       "mean      61527.681046\n",
       "std       39330.352114\n",
       "min           0.000000\n",
       "25%       34000.000000\n",
       "50%       52000.000000\n",
       "75%       80000.000000\n",
       "max      260000.000000\n",
       "Name: qincomefreev2_calc, dtype: float64"
      ]
     },
     "execution_count": 167,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged2[(df_merged2.year==2019) &  (df_merged2.qincomefreev2_calc!=np.nan)].qincomefreev2_calc.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 168,
   "id": "f45e7904",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count       823.000000\n",
       "mean      57151.862697\n",
       "std       37590.332788\n",
       "min           0.000000\n",
       "25%       31000.000000\n",
       "50%       49514.000000\n",
       "75%       77000.000000\n",
       "max      280000.000000\n",
       "Name: qincomefreev2_calc, dtype: float64"
      ]
     },
     "execution_count": 168,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged2[(df_merged2.year==2020) &  (df_merged2.qincomefreev2_calc!=np.nan)].qincomefreev2_calc.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 169,
   "id": "7c9212bc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count       890.000000\n",
       "mean      60037.401124\n",
       "std       44155.506482\n",
       "min           0.000000\n",
       "25%       30000.000000\n",
       "50%       50000.000000\n",
       "75%       81000.000000\n",
       "max      300000.000000\n",
       "Name: qincomefreev2_calc, dtype: float64"
      ]
     },
     "execution_count": 169,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_merged2[(df_merged2.year==2021) &  (df_merged2.qincomefreev2_calc!=np.nan)].qincomefreev2_calc.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8933abbc",
   "metadata": {},
   "source": [
    "Let's look at this trend in terms of age group."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "id": "e64fe2ad",
   "metadata": {},
   "outputs": [],
   "source": [
    "#mapping age groups into a variable\n",
    "df_merged2[\"dage_mapped\"]=df_merged2[\"dage\"].map({\n",
    "    1: '18-24',\n",
    "    2: '25-34',\n",
    "    3: '35-44',\n",
    "    4: '45-54',\n",
    "    5: '55-64',\n",
    "    6: '65+'})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "id": "6cc2c6cd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(figsize=(8, 5))\n",
    "ax.set_xlabel(\"Year\", fontsize = 12)\n",
    "ax.set_ylabel(\"Average Household Income (£)\", fontsize = 12)\n",
    "palette = sns.color_palette(\"hls\", 6)\n",
    "sns.lineplot(data=df_merged2[df_merged2.year>2014][[\"qincomefreev2_calc\",\"year\",\"dage_mapped\"]].groupby([\"year\",\"dage_mapped\"]).mean(), x=\"year\", y=\"qincomefreev2_calc\",hue=\"dage_mapped\",palette=palette)\n",
    "ax.set_ylim(20000, 80000)\n",
    "ylabels = ['{:,.0f}'.format(x) for x in ax.get_yticks()]\n",
    "ax.set_yticklabels(ylabels)\n",
    "plt.legend(title='Age',loc='lower left')\n",
    "plt.title(\"Average Household Income by Age\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cacc8c06",
   "metadata": {},
   "source": [
    "Individuals decide housing standards based on their income. I want to see how these groups changed in the past years.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "id": "6cc4e83d",
   "metadata": {},
   "outputs": [],
   "source": [
    "#mapping housing groups into a variable\n",
    "df_merged2[\"dhousing_mapped\"]=df_merged2[\"dhousing\"].map({\n",
    "    1: 'Owned Mortg',\n",
    "    2: 'Owned Outright',\n",
    "    3: 'Rent LA',\n",
    "    4: 'Rent Private',\n",
    "    5: 'Other/DK/Ref'})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 145,
   "id": "27d8de71",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#preparing line plot\n",
    "fig, ax = plt.subplots(figsize=(8, 5))\n",
    "ax.set_ylabel(\"Average Household Income (£)\", fontsize = 12)\n",
    "palette = sns.color_palette(\"hls\", 4)\n",
    "ax=sns.lineplot(data=df_merged2[(df_merged2.year>2014)][[\"qincomefreev2_calc\",\"year\",\"dhousing_mapped\"]].groupby([\"year\",\"dhousing_mapped\"]).mean(), x=\"year\", y=\"qincomefreev2_calc\",hue=\"dhousing_mapped\",palette=palette)\n",
    "ax.set_xlabel(\"Year\", fontsize = 12)\n",
    "ax.set_ylabel(\"Average Household Income (£)\", fontsize = 12)\n",
    "ylabels = ['{:,.0f}'.format(x) for x in ax.get_yticks()]\n",
    "ax.set_yticklabels(ylabels)\n",
    "plt.legend(title='Housing',loc='lower left')\n",
    "plt.title(\"Average Household Income by Housing\")\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "85c7885c",
   "metadata": {},
   "source": [
    "It can be said that people who lives on rent affected by the pandemic more."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6681925f",
   "metadata": {},
   "source": [
    "Below, I plotted figures related to expectations of individuals about economy and monthly saving rate."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "id": "0d32464a",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_merged2[\"mq08_mapped\"]=df_merged2[\"mq08\"].map({\n",
    "    1: 'Get a lot better',\n",
    "    2: 'Get a little better',\n",
    "    3: \"Stay the same\",\n",
    "    4: \"Get  a little worse\",\n",
    "    5: \"Get  a lot worse\",\n",
    "    6: \"Don't know / Prefer not to state\",\n",
    "    7: \"Don't know / Prefer not to state\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 153,
   "id": "758efc63",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 648x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(figsize=(9, 6))\n",
    "ax.set_ylabel(\"Average Household Income (£)\", fontsize = 12)\n",
    "palette = sns.color_palette(\"hls\", 6)\n",
    "ax=sns.lineplot(data=df_merged2[(df_merged2.year>2014)][[\"qincomefreev2_calc\",\"year\",\"mq08_mapped\"]].groupby([\"year\",\"mq08_mapped\"]).mean(), x=\"year\", y=\"qincomefreev2_calc\",hue=\"mq08_mapped\",palette=palette)\n",
    "ax.set_xlabel(\"Year\", fontsize = 12)\n",
    "ax.set_ylabel(\"Average Household Income (£)\", fontsize = 12)\n",
    "ylabels = ['{:,.0f}'.format(x) for x in ax.get_yticks()]\n",
    "ax.set_yticklabels(ylabels)\n",
    "plt.legend(title='Expectations About Economy',loc='upper right')\n",
    "plt.title(\"Average Household Income by Expectations About Economy Over the Next 12 Months\")\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 151,
   "id": "8237ac99",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x360 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(figsize=(8, 5))\n",
    "\n",
    "palette = sns.color_palette(\"hls\", 4)\n",
    "ax=sns.lineplot(data=df_merged2[df_merged2.year>2014][[\"qincomefreev2_calc\",\"year\",\"be2afree_1\"]].groupby([\"year\"]).mean(), x=\"year\", y=\"qincomefreev2_calc\",palette=palette)\n",
    "ax.set_ylabel(\"Average Household Income (£)\", fontsize = 12)\n",
    "ax.set_xlabel(\"Year\", fontsize = 12)\n",
    "ylabels = ['{:,.0f}'.format(x) for x in ax.get_yticks()]\n",
    "ax.set_yticklabels(ylabels)\n",
    "ax2 = ax.twinx()\n",
    "ax1=sns.lineplot(data=df_merged2[df_merged2.year>2014][[\"qincomefreev2_calc\",\"year\",\"be2afree_1\"]].groupby([\"year\"]).mean(),ax=ax2, x=\"year\", y=\"be2afree_1\",color='y')\n",
    "ax1.set_ylabel(\"Average Monthly Saving (£)\", fontsize = 12,color='y')\n",
    "ylabels = ['{:,.0f}'.format(x) for x in ax1.get_yticks()]\n",
    "ax1.set_yticklabels(ylabels)\n",
    "plt.title(\"Average Household Income and Average Monthly Saving\")\n",
    "plt.show()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0601305d",
   "metadata": {},
   "source": [
    "Looking at other variables to see whether there are any interesting relationships/development."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "b20d06d2",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_merged2[\"be13_mapped\"]=df_merged2[\"be13\"].map({\n",
    "    1: 'Yes',\n",
    "    2: 'No',\n",
    "    97: \"Don't know / Prefer not to state\",\n",
    "    98: \"Don't know / Prefer not to state\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "id": "488f232a",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_merged2[\"boe55_mapped\"]=df_merged2[\"boe55\"].map({\n",
    "    1: 'Not a problem',\n",
    "    2: 'Quite difficult',\n",
    "    3: \"Extremely difficult\",\n",
    "    4: \"Virtually impossible\",\n",
    "    5: \"Don't know / Prefer not to state\",\n",
    "    6: \"Don't know / Prefer not to state\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "id": "0c5c4733",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>year</th>\n",
       "      <th>boe55_mapped</th>\n",
       "      <th>qincomefreev2_calc</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2015</td>\n",
       "      <td>Don't know / Prefer not to state</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2015</td>\n",
       "      <td>Extremely difficult</td>\n",
       "      <td>47831.519231</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2015</td>\n",
       "      <td>Not a problem</td>\n",
       "      <td>53444.989474</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2015</td>\n",
       "      <td>Quite difficult</td>\n",
       "      <td>54994.735931</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2015</td>\n",
       "      <td>Virtually impossible</td>\n",
       "      <td>48937.526316</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   year                      boe55_mapped  qincomefreev2_calc\n",
       "0  2015  Don't know / Prefer not to state                 NaN\n",
       "1  2015               Extremely difficult        47831.519231\n",
       "2  2015                     Not a problem        53444.989474\n",
       "3  2015                   Quite difficult        54994.735931\n",
       "4  2015              Virtually impossible        48937.526316"
      ]
     },
     "execution_count": 72,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data=df_merged2[(df_merged2.year>2014)][[\"qincomefreev2_calc\",\"year\",\"boe55_mapped\"]].groupby([\"year\",\"boe55_mapped\"]).mean().reset_index()\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "id": "e9cac4b9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1008x360 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "data=df_merged2[(df_merged2.year>2014)][[\"qincomefreev2_calc\",\"year\",\"be13_mapped\"]].groupby([\"year\",\"be13_mapped\"]).mean().reset_index()\n",
    "\n",
    "fig, ax = plt.subplots(figsize=(14, 5))\n",
    "\n",
    "ax=sns.barplot(data=data, x=\"be13_mapped\", y=\"qincomefreev2_calc\",hue=\"year\",palette=palette)\n",
    "ax.set_xlabel(\"Year\", fontsize = 12)\n",
    "ax.set_ylabel(\"Average Household Income (£)\", fontsize = 12)\n",
    "ylabels = ['{:,.0f}'.format(x) for x in ax.get_yticks()]\n",
    "ax.set_yticklabels(ylabels)\n",
    "plt.legend(title='Housing',loc='upper left')\n",
    "plt.title(\"Average Household Income by Difficulty in Housing Payments\")\n",
    "plt.show()\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}