04.3_London_Housing_Prices.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "Tia3MP1SJpgj"
   },
   "source": [
    "# Springboard Data Science Career Track Unit 4 Challenge - Tier 3 Complete\n",
    "\n",
    "## Objectives\n",
    "Hey! Great job getting through those challenging DataCamp courses. You're learning a lot in a short span of time. \n",
    "\n",
    "In this notebook, you're going to apply the skills you've been learning, bridging the gap between the controlled environment of DataCamp and the *slightly* messier work that data scientists do with actual datasets!\n",
    "\n",
    "Here’s the mystery we’re going to solve: ***which boroughs of London have seen the greatest increase in housing prices, on average, over the last two decades?***\n",
    "\n",
    "\n",
    "A borough is just a fancy word for district. You may be familiar with the five boroughs of New York… well, there are 32 boroughs within Greater London [(here's some info for the curious)](https://en.wikipedia.org/wiki/London_boroughs). Some of them are more desirable areas to live in, and the data will reflect that with a greater rise in housing prices.\n",
    "\n",
    "***This is the Tier 3 notebook, which means it's not filled in at all: we'll just give you the skeleton of a project, the brief and the data. It's up to you to play around with it and see what you can find out! Good luck! If you struggle, feel free to look at easier tiers for help; but try to dip in and out of them, as the more independent work you do, the better it is for your learning!***\n",
    "\n",
    "This challenge will make use of only what you learned in the following DataCamp courses: \n",
    "- Prework courses (Introduction to Python for Data Science, Intermediate Python for Data Science)\n",
    "- Data Types for Data Science\n",
    "- Python Data Science Toolbox (Part One) \n",
    "- pandas Foundations\n",
    "- Manipulating DataFrames with pandas\n",
    "- Merging DataFrames with pandas\n",
    "\n",
    "Of the tools, techniques and concepts in the above DataCamp courses, this challenge should require the application of the following: \n",
    "- **pandas**\n",
    "    - **data ingestion and inspection** (pandas Foundations, Module One) \n",
    "    - **exploratory data analysis** (pandas Foundations, Module Two)\n",
    "    - **tidying and cleaning** (Manipulating DataFrames with pandas, Module Three) \n",
    "    - **transforming DataFrames** (Manipulating DataFrames with pandas, Module One)\n",
    "    - **subsetting DataFrames with lists** (Manipulating DataFrames with pandas, Module One) \n",
    "    - **filtering DataFrames** (Manipulating DataFrames with pandas, Module One) \n",
    "    - **grouping data** (Manipulating DataFrames with pandas, Module Four) \n",
    "    - **melting data** (Manipulating DataFrames with pandas, Module Three) \n",
    "    - **advanced indexing** (Manipulating DataFrames with pandas, Module Four) \n",
    "- **matplotlib** (Intermediate Python for Data Science, Module One)\n",
    "- **fundamental data types** (Data Types for Data Science, Module One) \n",
    "- **dictionaries** (Intermediate Python for Data Science, Module Two)\n",
    "- **handling dates and times** (Data Types for Data Science, Module Four)\n",
    "- **function definition** (Python Data Science Toolbox - Part One, Module One)\n",
    "- **default arguments, variable length, and scope** (Python Data Science Toolbox - Part One, Module Two) \n",
    "- **lambda functions and error handling** (Python Data Science Toolbox - Part One, Module Four) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "Ipgd2nV8Jpgl"
   },
   "source": [
    "## The Data Science Pipeline\n",
    "\n",
    "This is Tier Three, so we'll get you started. But after that, it's all in your hands! When you feel done with your investigations, look back over what you've accomplished, and prepare a quick presentation of your findings for the next mentor meeting. \n",
    "\n",
    "Data Science is magical. In this case study, you'll get to apply some complex machine learning algorithms. But as  [David Spiegelhalter](https://www.youtube.com/watch?v=oUs1uvsz0Ok) reminds us, there is no substitute for simply **taking a really, really good look at the data.** Sometimes, this is all we need to answer our question.\n",
    "\n",
    "Data Science projects generally adhere to the four stages of Data Science Pipeline:\n",
    "1. Sourcing and loading \n",
    "2. Cleaning, transforming, and visualizing \n",
    "3. Modeling \n",
    "4. Evaluating and concluding \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "zswDqbefJpgm"
   },
   "source": [
    "### 1. Sourcing and Loading \n",
    "\n",
    "Any Data Science project kicks off by importing  ***pandas***. The documentation of this wonderful library can be found [here](https://pandas.pydata.org/). As you've seen, pandas is conveniently connected to the [Numpy](http://www.numpy.org/) and [Matplotlib](https://matplotlib.org/) libraries. \n",
    "\n",
    "***Hint:*** This part of the data science pipeline will test those skills you acquired in the pandas Foundations course, Module One. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "aEau5nEvJpgm"
   },
   "source": [
    "#### 1.1. Importing Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 689,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "7Bt_Q_oPJpgn",
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Let's import the pandas, numpy libraries as pd, and np respectively. \n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "# Load the pyplot collection of functions from matplotlib, as plt \n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "koUrawxsJpgq"
   },
   "source": [
    "#### 1.2.  Loading the data\n",
    "Your data comes from the [London Datastore](https://data.london.gov.uk/): a free, open-source data-sharing portal for London-oriented datasets. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 690,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "AiLiD4v3Jpgr",
    "tags": []
   },
   "outputs": [],
   "source": [
    "# First, make a variable called url_LondonHousePrices, and assign it the following link, enclosed in quotation-marks as a string:\n",
    "# https://data.london.gov.uk/download/uk-house-price-index/70ac0766-8902-4eb5-aab5-01951aaed773/UK%20House%20price%20index.xls\n",
    "\n",
    "url_LondonHousePrices = \"https://data.london.gov.uk/download/uk-house-price-index/70ac0766-8902-4eb5-aab5-01951aaed773/UK%20House%20price%20index.xls\"\n",
    "\n",
    "# The dataset we're interested in contains the Average prices of the houses, and is actually on a particular sheet of the Excel file. \n",
    "# As a result, we need to specify the sheet name in the read_excel() method.\n",
    "# Put this data into a variable called properties.  \n",
    "properties = pd.read_excel(url_LondonHousePrices, sheet_name='Average price', index_col= None)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "POukEJXgJpgu"
   },
   "source": [
    "### 2. Cleaning, transforming, and visualizing\n",
    "This second stage is arguably the most important part of any Data Science project. The first thing to do is take a proper look at the data. Cleaning forms the majority of this stage, and can be done both before or after Transformation.\n",
    "\n",
    "The end goal of data cleaning is to have tidy data. When data is tidy: \n",
    "\n",
    "1. Each variable has a column.\n",
    "2. Each observation forms a row.\n",
    "\n",
    "Keep the end goal in mind as you move through this process, every step will take you closer. \n",
    "\n",
    "\n",
    "\n",
    "***Hint:*** This part of the data science pipeline should test those skills you acquired in: \n",
    "- Intermediate Python for data science, all modules.\n",
    "- pandas Foundations, all modules. \n",
    "- Manipulating DataFrames with pandas, all modules.\n",
    "- Data Types for Data Science, Module Four.\n",
    "- Python Data Science Toolbox - Part One, all modules"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "Te0Q548tnzZa"
   },
   "source": [
    "**2.1. Exploring your data** \n",
    "\n",
    "Think about your pandas functions for checking out a dataframe. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 691,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "Rxirxw_qoAJa",
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>City of London</th>\n",
       "      <th>Barking &amp; Dagenham</th>\n",
       "      <th>Barnet</th>\n",
       "      <th>Bexley</th>\n",
       "      <th>Brent</th>\n",
       "      <th>Bromley</th>\n",
       "      <th>Camden</th>\n",
       "      <th>Croydon</th>\n",
       "      <th>Ealing</th>\n",
       "      <th>...</th>\n",
       "      <th>NORTH WEST</th>\n",
       "      <th>YORKS &amp; THE HUMBER</th>\n",
       "      <th>EAST MIDLANDS</th>\n",
       "      <th>WEST MIDLANDS</th>\n",
       "      <th>EAST OF ENGLAND</th>\n",
       "      <th>LONDON</th>\n",
       "      <th>SOUTH EAST</th>\n",
       "      <th>SOUTH WEST</th>\n",
       "      <th>Unnamed: 47</th>\n",
       "      <th>England</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>NaT</td>\n",
       "      <td>E09000001</td>\n",
       "      <td>E09000002</td>\n",
       "      <td>E09000003</td>\n",
       "      <td>E09000004</td>\n",
       "      <td>E09000005</td>\n",
       "      <td>E09000006</td>\n",
       "      <td>E09000007</td>\n",
       "      <td>E09000008</td>\n",
       "      <td>E09000009</td>\n",
       "      <td>...</td>\n",
       "      <td>E12000002</td>\n",
       "      <td>E12000003</td>\n",
       "      <td>E12000004</td>\n",
       "      <td>E12000005</td>\n",
       "      <td>E12000006</td>\n",
       "      <td>E12000007</td>\n",
       "      <td>E12000008</td>\n",
       "      <td>E12000009</td>\n",
       "      <td>NaN</td>\n",
       "      <td>E92000001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1995-01-01</td>\n",
       "      <td>91448.98487</td>\n",
       "      <td>50460.2266</td>\n",
       "      <td>93284.51832</td>\n",
       "      <td>64958.09036</td>\n",
       "      <td>71306.56698</td>\n",
       "      <td>81671.47692</td>\n",
       "      <td>120932.8881</td>\n",
       "      <td>69158.16225</td>\n",
       "      <td>79885.89069</td>\n",
       "      <td>...</td>\n",
       "      <td>43958.48001</td>\n",
       "      <td>44803.42878</td>\n",
       "      <td>45544.52227</td>\n",
       "      <td>48527.52339</td>\n",
       "      <td>56701.5961</td>\n",
       "      <td>74435.76052</td>\n",
       "      <td>64018.87894</td>\n",
       "      <td>54705.1579</td>\n",
       "      <td>NaN</td>\n",
       "      <td>53202.77128</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1995-02-01</td>\n",
       "      <td>82202.77314</td>\n",
       "      <td>51085.77983</td>\n",
       "      <td>93190.16963</td>\n",
       "      <td>64787.92069</td>\n",
       "      <td>72022.26197</td>\n",
       "      <td>81657.55944</td>\n",
       "      <td>119508.8622</td>\n",
       "      <td>68951.09542</td>\n",
       "      <td>80897.06551</td>\n",
       "      <td>...</td>\n",
       "      <td>43925.42289</td>\n",
       "      <td>44528.80721</td>\n",
       "      <td>46051.57066</td>\n",
       "      <td>49341.29029</td>\n",
       "      <td>56593.59475</td>\n",
       "      <td>72777.93709</td>\n",
       "      <td>63715.02399</td>\n",
       "      <td>54356.14843</td>\n",
       "      <td>NaN</td>\n",
       "      <td>53096.1549</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1995-03-01</td>\n",
       "      <td>79120.70256</td>\n",
       "      <td>51268.96956</td>\n",
       "      <td>92247.52435</td>\n",
       "      <td>64367.49344</td>\n",
       "      <td>72015.76274</td>\n",
       "      <td>81449.31143</td>\n",
       "      <td>120282.2131</td>\n",
       "      <td>68712.44341</td>\n",
       "      <td>81379.86288</td>\n",
       "      <td>...</td>\n",
       "      <td>44434.8681</td>\n",
       "      <td>45200.46775</td>\n",
       "      <td>45383.82395</td>\n",
       "      <td>49442.17973</td>\n",
       "      <td>56171.18278</td>\n",
       "      <td>73896.84204</td>\n",
       "      <td>64113.60858</td>\n",
       "      <td>53583.07667</td>\n",
       "      <td>NaN</td>\n",
       "      <td>53201.2843</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1995-04-01</td>\n",
       "      <td>77101.20804</td>\n",
       "      <td>53133.50526</td>\n",
       "      <td>90762.87492</td>\n",
       "      <td>64277.66881</td>\n",
       "      <td>72965.63094</td>\n",
       "      <td>81124.41227</td>\n",
       "      <td>120097.899</td>\n",
       "      <td>68610.04641</td>\n",
       "      <td>82188.90498</td>\n",
       "      <td>...</td>\n",
       "      <td>44267.7796</td>\n",
       "      <td>45614.34341</td>\n",
       "      <td>46124.23045</td>\n",
       "      <td>49455.93299</td>\n",
       "      <td>56567.89582</td>\n",
       "      <td>74455.28754</td>\n",
       "      <td>64623.22395</td>\n",
       "      <td>54786.01938</td>\n",
       "      <td>NaN</td>\n",
       "      <td>53590.8548</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 49 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  Unnamed: 0 City of London Barking & Dagenham       Barnet       Bexley  \\\n",
       "0        NaT      E09000001          E09000002    E09000003    E09000004   \n",
       "1 1995-01-01    91448.98487         50460.2266  93284.51832  64958.09036   \n",
       "2 1995-02-01    82202.77314        51085.77983  93190.16963  64787.92069   \n",
       "3 1995-03-01    79120.70256        51268.96956  92247.52435  64367.49344   \n",
       "4 1995-04-01    77101.20804        53133.50526  90762.87492  64277.66881   \n",
       "\n",
       "         Brent      Bromley       Camden      Croydon       Ealing  ...  \\\n",
       "0    E09000005    E09000006    E09000007    E09000008    E09000009  ...   \n",
       "1  71306.56698  81671.47692  120932.8881  69158.16225  79885.89069  ...   \n",
       "2  72022.26197  81657.55944  119508.8622  68951.09542  80897.06551  ...   \n",
       "3  72015.76274  81449.31143  120282.2131  68712.44341  81379.86288  ...   \n",
       "4  72965.63094  81124.41227   120097.899  68610.04641  82188.90498  ...   \n",
       "\n",
       "    NORTH WEST YORKS & THE HUMBER EAST MIDLANDS WEST MIDLANDS EAST OF ENGLAND  \\\n",
       "0    E12000002          E12000003     E12000004     E12000005       E12000006   \n",
       "1  43958.48001        44803.42878   45544.52227   48527.52339      56701.5961   \n",
       "2  43925.42289        44528.80721   46051.57066   49341.29029     56593.59475   \n",
       "3   44434.8681        45200.46775   45383.82395   49442.17973     56171.18278   \n",
       "4   44267.7796        45614.34341   46124.23045   49455.93299     56567.89582   \n",
       "\n",
       "        LONDON   SOUTH EAST   SOUTH WEST Unnamed: 47      England  \n",
       "0    E12000007    E12000008    E12000009         NaN    E92000001  \n",
       "1  74435.76052  64018.87894   54705.1579         NaN  53202.77128  \n",
       "2  72777.93709  63715.02399  54356.14843         NaN   53096.1549  \n",
       "3  73896.84204  64113.60858  53583.07667         NaN   53201.2843  \n",
       "4  74455.28754  64623.22395  54786.01938         NaN   53590.8548  \n",
       "\n",
       "[5 rows x 49 columns]"
      ]
     },
     "execution_count": 691,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "properties.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "tE9Sqt9-oAta"
   },
   "source": [
    "**2.2. Cleaning the data**\n",
    "\n",
    "You might find you need to transpose your dataframe, check out what its row indexes are, and reset the index. You  also might find you need to assign the values of the first row to your column headings  . (Hint: recall the .columns feature of DataFrames, as well as the iloc[] method).\n",
    "\n",
    "Don't be afraid to use StackOverflow for help  with this."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 692,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "cdAu1A3YoH_r",
    "tags": []
   },
   "outputs": [],
   "source": [
    "properties = properties.T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 693,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>337</th>\n",
       "      <th>338</th>\n",
       "      <th>339</th>\n",
       "      <th>340</th>\n",
       "      <th>341</th>\n",
       "      <th>342</th>\n",
       "      <th>343</th>\n",
       "      <th>344</th>\n",
       "      <th>345</th>\n",
       "      <th>346</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <td>NaT</td>\n",
       "      <td>1995-01-01 00:00:00</td>\n",
       "      <td>1995-02-01 00:00:00</td>\n",
       "      <td>1995-03-01 00:00:00</td>\n",
       "      <td>1995-04-01 00:00:00</td>\n",
       "      <td>1995-05-01 00:00:00</td>\n",
       "      <td>1995-06-01 00:00:00</td>\n",
       "      <td>1995-07-01 00:00:00</td>\n",
       "      <td>1995-08-01 00:00:00</td>\n",
       "      <td>1995-09-01 00:00:00</td>\n",
       "      <td>...</td>\n",
       "      <td>2023-01-01 00:00:00</td>\n",
       "      <td>2023-02-01 00:00:00</td>\n",
       "      <td>2023-03-01 00:00:00</td>\n",
       "      <td>2023-04-01 00:00:00</td>\n",
       "      <td>2023-05-01 00:00:00</td>\n",
       "      <td>2023-06-01 00:00:00</td>\n",
       "      <td>2023-07-01 00:00:00</td>\n",
       "      <td>2023-08-01 00:00:00</td>\n",
       "      <td>2023-09-01 00:00:00</td>\n",
       "      <td>2023-10-01 00:00:00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>City of London</th>\n",
       "      <td>E09000001</td>\n",
       "      <td>91448.98487</td>\n",
       "      <td>82202.77314</td>\n",
       "      <td>79120.70256</td>\n",
       "      <td>77101.20804</td>\n",
       "      <td>84409.14932</td>\n",
       "      <td>94900.51244</td>\n",
       "      <td>110128.0423</td>\n",
       "      <td>112329.4376</td>\n",
       "      <td>104473.1096</td>\n",
       "      <td>...</td>\n",
       "      <td>962674</td>\n",
       "      <td>868654</td>\n",
       "      <td>931058</td>\n",
       "      <td>905101</td>\n",
       "      <td>960392</td>\n",
       "      <td>982370</td>\n",
       "      <td>960158</td>\n",
       "      <td>888278</td>\n",
       "      <td>875234</td>\n",
       "      <td>948692</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Barking &amp; Dagenham</th>\n",
       "      <td>E09000002</td>\n",
       "      <td>50460.2266</td>\n",
       "      <td>51085.77983</td>\n",
       "      <td>51268.96956</td>\n",
       "      <td>53133.50526</td>\n",
       "      <td>53042.24852</td>\n",
       "      <td>53700.34831</td>\n",
       "      <td>52113.12157</td>\n",
       "      <td>52232.19868</td>\n",
       "      <td>51471.61353</td>\n",
       "      <td>...</td>\n",
       "      <td>352086</td>\n",
       "      <td>346059</td>\n",
       "      <td>344693</td>\n",
       "      <td>347710</td>\n",
       "      <td>348002</td>\n",
       "      <td>343972</td>\n",
       "      <td>340763</td>\n",
       "      <td>343731</td>\n",
       "      <td>344255</td>\n",
       "      <td>334460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Barnet</th>\n",
       "      <td>E09000003</td>\n",
       "      <td>93284.51832</td>\n",
       "      <td>93190.16963</td>\n",
       "      <td>92247.52435</td>\n",
       "      <td>90762.87492</td>\n",
       "      <td>90258.00033</td>\n",
       "      <td>90107.23471</td>\n",
       "      <td>91441.24768</td>\n",
       "      <td>92361.31512</td>\n",
       "      <td>93273.12245</td>\n",
       "      <td>...</td>\n",
       "      <td>597762</td>\n",
       "      <td>603522</td>\n",
       "      <td>596521</td>\n",
       "      <td>585644</td>\n",
       "      <td>572257</td>\n",
       "      <td>570542</td>\n",
       "      <td>575808</td>\n",
       "      <td>586501</td>\n",
       "      <td>589399</td>\n",
       "      <td>597538</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bexley</th>\n",
       "      <td>E09000004</td>\n",
       "      <td>64958.09036</td>\n",
       "      <td>64787.92069</td>\n",
       "      <td>64367.49344</td>\n",
       "      <td>64277.66881</td>\n",
       "      <td>63997.13588</td>\n",
       "      <td>64252.32335</td>\n",
       "      <td>63722.70055</td>\n",
       "      <td>64432.60005</td>\n",
       "      <td>64509.54767</td>\n",
       "      <td>...</td>\n",
       "      <td>402570</td>\n",
       "      <td>401263</td>\n",
       "      <td>395612</td>\n",
       "      <td>392642</td>\n",
       "      <td>385603</td>\n",
       "      <td>383969</td>\n",
       "      <td>387475</td>\n",
       "      <td>387360</td>\n",
       "      <td>389590</td>\n",
       "      <td>393227</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 347 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                          0                    1                    2    \\\n",
       "Unnamed: 0                NaT  1995-01-01 00:00:00  1995-02-01 00:00:00   \n",
       "City of London      E09000001          91448.98487          82202.77314   \n",
       "Barking & Dagenham  E09000002           50460.2266          51085.77983   \n",
       "Barnet              E09000003          93284.51832          93190.16963   \n",
       "Bexley              E09000004          64958.09036          64787.92069   \n",
       "\n",
       "                                    3                    4    \\\n",
       "Unnamed: 0          1995-03-01 00:00:00  1995-04-01 00:00:00   \n",
       "City of London              79120.70256          77101.20804   \n",
       "Barking & Dagenham          51268.96956          53133.50526   \n",
       "Barnet                      92247.52435          90762.87492   \n",
       "Bexley                      64367.49344          64277.66881   \n",
       "\n",
       "                                    5                    6    \\\n",
       "Unnamed: 0          1995-05-01 00:00:00  1995-06-01 00:00:00   \n",
       "City of London              84409.14932          94900.51244   \n",
       "Barking & Dagenham          53042.24852          53700.34831   \n",
       "Barnet                      90258.00033          90107.23471   \n",
       "Bexley                      63997.13588          64252.32335   \n",
       "\n",
       "                                    7                    8    \\\n",
       "Unnamed: 0          1995-07-01 00:00:00  1995-08-01 00:00:00   \n",
       "City of London              110128.0423          112329.4376   \n",
       "Barking & Dagenham          52113.12157          52232.19868   \n",
       "Barnet                      91441.24768          92361.31512   \n",
       "Bexley                      63722.70055          64432.60005   \n",
       "\n",
       "                                    9    ...                  337  \\\n",
       "Unnamed: 0          1995-09-01 00:00:00  ...  2023-01-01 00:00:00   \n",
       "City of London              104473.1096  ...               962674   \n",
       "Barking & Dagenham          51471.61353  ...               352086   \n",
       "Barnet                      93273.12245  ...               597762   \n",
       "Bexley                      64509.54767  ...               402570   \n",
       "\n",
       "                                    338                  339  \\\n",
       "Unnamed: 0          2023-02-01 00:00:00  2023-03-01 00:00:00   \n",
       "City of London                   868654               931058   \n",
       "Barking & Dagenham               346059               344693   \n",
       "Barnet                           603522               596521   \n",
       "Bexley                           401263               395612   \n",
       "\n",
       "                                    340                  341  \\\n",
       "Unnamed: 0          2023-04-01 00:00:00  2023-05-01 00:00:00   \n",
       "City of London                   905101               960392   \n",
       "Barking & Dagenham               347710               348002   \n",
       "Barnet                           585644               572257   \n",
       "Bexley                           392642               385603   \n",
       "\n",
       "                                    342                  343  \\\n",
       "Unnamed: 0          2023-06-01 00:00:00  2023-07-01 00:00:00   \n",
       "City of London                   982370               960158   \n",
       "Barking & Dagenham               343972               340763   \n",
       "Barnet                           570542               575808   \n",
       "Bexley                           383969               387475   \n",
       "\n",
       "                                    344                  345  \\\n",
       "Unnamed: 0          2023-08-01 00:00:00  2023-09-01 00:00:00   \n",
       "City of London                   888278               875234   \n",
       "Barking & Dagenham               343731               344255   \n",
       "Barnet                           586501               589399   \n",
       "Bexley                           387360               389590   \n",
       "\n",
       "                                    346  \n",
       "Unnamed: 0          2023-10-01 00:00:00  \n",
       "City of London                   948692  \n",
       "Barking & Dagenham               334460  \n",
       "Barnet                           597538  \n",
       "Bexley                           393227  \n",
       "\n",
       "[5 rows x 347 columns]"
      ]
     },
     "execution_count": 693,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "properties.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 694,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['Unnamed: 0', 'City of London', 'Barking & Dagenham', 'Barnet',\n",
       "       'Bexley', 'Brent', 'Bromley', 'Camden', 'Croydon', 'Ealing', 'Enfield',\n",
       "       'Greenwich', 'Hackney', 'Hammersmith & Fulham', 'Haringey', 'Harrow',\n",
       "       'Havering', 'Hillingdon', 'Hounslow', 'Islington',\n",
       "       'Kensington & Chelsea', 'Kingston upon Thames', 'Lambeth', 'Lewisham',\n",
       "       'Merton', 'Newham', 'Redbridge', 'Richmond upon Thames', 'Southwark',\n",
       "       'Sutton', 'Tower Hamlets', 'Waltham Forest', 'Wandsworth',\n",
       "       'Westminster', 'Unnamed: 34', 'Inner London', 'Outer London',\n",
       "       'Unnamed: 37', 'NORTH EAST', 'NORTH WEST', 'YORKS & THE HUMBER',\n",
       "       'EAST MIDLANDS', 'WEST MIDLANDS', 'EAST OF ENGLAND', 'LONDON',\n",
       "       'SOUTH EAST', 'SOUTH WEST', 'Unnamed: 47', 'England'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 694,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "properties.index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 695,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "properties = properties.reset_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 696,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "properties.columns = properties.iloc[0]\n",
    "properties = properties[1:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 697,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>NaT</th>\n",
       "      <th>1995-01-01 00:00:00</th>\n",
       "      <th>1995-02-01 00:00:00</th>\n",
       "      <th>1995-03-01 00:00:00</th>\n",
       "      <th>1995-04-01 00:00:00</th>\n",
       "      <th>1995-05-01 00:00:00</th>\n",
       "      <th>1995-06-01 00:00:00</th>\n",
       "      <th>1995-07-01 00:00:00</th>\n",
       "      <th>1995-08-01 00:00:00</th>\n",
       "      <th>...</th>\n",
       "      <th>2023-01-01 00:00:00</th>\n",
       "      <th>2023-02-01 00:00:00</th>\n",
       "      <th>2023-03-01 00:00:00</th>\n",
       "      <th>2023-04-01 00:00:00</th>\n",
       "      <th>2023-05-01 00:00:00</th>\n",
       "      <th>2023-06-01 00:00:00</th>\n",
       "      <th>2023-07-01 00:00:00</th>\n",
       "      <th>2023-08-01 00:00:00</th>\n",
       "      <th>2023-09-01 00:00:00</th>\n",
       "      <th>2023-10-01 00:00:00</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>City of London</td>\n",
       "      <td>E09000001</td>\n",
       "      <td>91448.98487</td>\n",
       "      <td>82202.77314</td>\n",
       "      <td>79120.70256</td>\n",
       "      <td>77101.20804</td>\n",
       "      <td>84409.14932</td>\n",
       "      <td>94900.51244</td>\n",
       "      <td>110128.0423</td>\n",
       "      <td>112329.4376</td>\n",
       "      <td>...</td>\n",
       "      <td>962674</td>\n",
       "      <td>868654</td>\n",
       "      <td>931058</td>\n",
       "      <td>905101</td>\n",
       "      <td>960392</td>\n",
       "      <td>982370</td>\n",
       "      <td>960158</td>\n",
       "      <td>888278</td>\n",
       "      <td>875234</td>\n",
       "      <td>948692</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Barking &amp; Dagenham</td>\n",
       "      <td>E09000002</td>\n",
       "      <td>50460.2266</td>\n",
       "      <td>51085.77983</td>\n",
       "      <td>51268.96956</td>\n",
       "      <td>53133.50526</td>\n",
       "      <td>53042.24852</td>\n",
       "      <td>53700.34831</td>\n",
       "      <td>52113.12157</td>\n",
       "      <td>52232.19868</td>\n",
       "      <td>...</td>\n",
       "      <td>352086</td>\n",
       "      <td>346059</td>\n",
       "      <td>344693</td>\n",
       "      <td>347710</td>\n",
       "      <td>348002</td>\n",
       "      <td>343972</td>\n",
       "      <td>340763</td>\n",
       "      <td>343731</td>\n",
       "      <td>344255</td>\n",
       "      <td>334460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Barnet</td>\n",
       "      <td>E09000003</td>\n",
       "      <td>93284.51832</td>\n",
       "      <td>93190.16963</td>\n",
       "      <td>92247.52435</td>\n",
       "      <td>90762.87492</td>\n",
       "      <td>90258.00033</td>\n",
       "      <td>90107.23471</td>\n",
       "      <td>91441.24768</td>\n",
       "      <td>92361.31512</td>\n",
       "      <td>...</td>\n",
       "      <td>597762</td>\n",
       "      <td>603522</td>\n",
       "      <td>596521</td>\n",
       "      <td>585644</td>\n",
       "      <td>572257</td>\n",
       "      <td>570542</td>\n",
       "      <td>575808</td>\n",
       "      <td>586501</td>\n",
       "      <td>589399</td>\n",
       "      <td>597538</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Bexley</td>\n",
       "      <td>E09000004</td>\n",
       "      <td>64958.09036</td>\n",
       "      <td>64787.92069</td>\n",
       "      <td>64367.49344</td>\n",
       "      <td>64277.66881</td>\n",
       "      <td>63997.13588</td>\n",
       "      <td>64252.32335</td>\n",
       "      <td>63722.70055</td>\n",
       "      <td>64432.60005</td>\n",
       "      <td>...</td>\n",
       "      <td>402570</td>\n",
       "      <td>401263</td>\n",
       "      <td>395612</td>\n",
       "      <td>392642</td>\n",
       "      <td>385603</td>\n",
       "      <td>383969</td>\n",
       "      <td>387475</td>\n",
       "      <td>387360</td>\n",
       "      <td>389590</td>\n",
       "      <td>393227</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Brent</td>\n",
       "      <td>E09000005</td>\n",
       "      <td>71306.56698</td>\n",
       "      <td>72022.26197</td>\n",
       "      <td>72015.76274</td>\n",
       "      <td>72965.63094</td>\n",
       "      <td>73704.04743</td>\n",
       "      <td>74310.48167</td>\n",
       "      <td>74127.03788</td>\n",
       "      <td>73547.0411</td>\n",
       "      <td>...</td>\n",
       "      <td>551662</td>\n",
       "      <td>535332</td>\n",
       "      <td>527101</td>\n",
       "      <td>525558</td>\n",
       "      <td>523687</td>\n",
       "      <td>526985</td>\n",
       "      <td>525460</td>\n",
       "      <td>552411</td>\n",
       "      <td>554568</td>\n",
       "      <td>542864</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 348 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "0          Unnamed: 0        NaT 1995-01-01 00:00:00 1995-02-01 00:00:00  \\\n",
       "1      City of London  E09000001         91448.98487         82202.77314   \n",
       "2  Barking & Dagenham  E09000002          50460.2266         51085.77983   \n",
       "3              Barnet  E09000003         93284.51832         93190.16963   \n",
       "4              Bexley  E09000004         64958.09036         64787.92069   \n",
       "5               Brent  E09000005         71306.56698         72022.26197   \n",
       "\n",
       "0 1995-03-01 00:00:00 1995-04-01 00:00:00 1995-05-01 00:00:00  \\\n",
       "1         79120.70256         77101.20804         84409.14932   \n",
       "2         51268.96956         53133.50526         53042.24852   \n",
       "3         92247.52435         90762.87492         90258.00033   \n",
       "4         64367.49344         64277.66881         63997.13588   \n",
       "5         72015.76274         72965.63094         73704.04743   \n",
       "\n",
       "0 1995-06-01 00:00:00 1995-07-01 00:00:00 1995-08-01 00:00:00  ...  \\\n",
       "1         94900.51244         110128.0423         112329.4376  ...   \n",
       "2         53700.34831         52113.12157         52232.19868  ...   \n",
       "3         90107.23471         91441.24768         92361.31512  ...   \n",
       "4         64252.32335         63722.70055         64432.60005  ...   \n",
       "5         74310.48167         74127.03788          73547.0411  ...   \n",
       "\n",
       "0 2023-01-01 00:00:00 2023-02-01 00:00:00 2023-03-01 00:00:00  \\\n",
       "1              962674              868654              931058   \n",
       "2              352086              346059              344693   \n",
       "3              597762              603522              596521   \n",
       "4              402570              401263              395612   \n",
       "5              551662              535332              527101   \n",
       "\n",
       "0 2023-04-01 00:00:00 2023-05-01 00:00:00 2023-06-01 00:00:00  \\\n",
       "1              905101              960392              982370   \n",
       "2              347710              348002              343972   \n",
       "3              585644              572257              570542   \n",
       "4              392642              385603              383969   \n",
       "5              525558              523687              526985   \n",
       "\n",
       "0 2023-07-01 00:00:00 2023-08-01 00:00:00 2023-09-01 00:00:00  \\\n",
       "1              960158              888278              875234   \n",
       "2              340763              343731              344255   \n",
       "3              575808              586501              589399   \n",
       "4              387475              387360              389590   \n",
       "5              525460              552411              554568   \n",
       "\n",
       "0 2023-10-01 00:00:00  \n",
       "1              948692  \n",
       "2              334460  \n",
       "3              597538  \n",
       "4              393227  \n",
       "5              542864  \n",
       "\n",
       "[5 rows x 348 columns]"
      ]
     },
     "execution_count": 697,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "properties.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "o1uLbJAsoIjK"
   },
   "source": [
    "**2.3. Cleaning the data (part 2)**\n",
    "\n",
    "You might we have to **rename** a couple columns. How do you do this? The clue's pretty bold..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 698,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "GKkmn1AnoVZS",
    "tags": []
   },
   "outputs": [],
   "source": [
    "properties = properties.rename(columns={'Unnamed: 0': 'Borough', pd.NaT: 'ID'})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 699,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Borough</th>\n",
       "      <th>ID</th>\n",
       "      <th>1995-01-01 00:00:00</th>\n",
       "      <th>1995-02-01 00:00:00</th>\n",
       "      <th>1995-03-01 00:00:00</th>\n",
       "      <th>1995-04-01 00:00:00</th>\n",
       "      <th>1995-05-01 00:00:00</th>\n",
       "      <th>1995-06-01 00:00:00</th>\n",
       "      <th>1995-07-01 00:00:00</th>\n",
       "      <th>1995-08-01 00:00:00</th>\n",
       "      <th>...</th>\n",
       "      <th>2023-01-01 00:00:00</th>\n",
       "      <th>2023-02-01 00:00:00</th>\n",
       "      <th>2023-03-01 00:00:00</th>\n",
       "      <th>2023-04-01 00:00:00</th>\n",
       "      <th>2023-05-01 00:00:00</th>\n",
       "      <th>2023-06-01 00:00:00</th>\n",
       "      <th>2023-07-01 00:00:00</th>\n",
       "      <th>2023-08-01 00:00:00</th>\n",
       "      <th>2023-09-01 00:00:00</th>\n",
       "      <th>2023-10-01 00:00:00</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>City of London</td>\n",
       "      <td>E09000001</td>\n",
       "      <td>91448.98487</td>\n",
       "      <td>82202.77314</td>\n",
       "      <td>79120.70256</td>\n",
       "      <td>77101.20804</td>\n",
       "      <td>84409.14932</td>\n",
       "      <td>94900.51244</td>\n",
       "      <td>110128.0423</td>\n",
       "      <td>112329.4376</td>\n",
       "      <td>...</td>\n",
       "      <td>962674</td>\n",
       "      <td>868654</td>\n",
       "      <td>931058</td>\n",
       "      <td>905101</td>\n",
       "      <td>960392</td>\n",
       "      <td>982370</td>\n",
       "      <td>960158</td>\n",
       "      <td>888278</td>\n",
       "      <td>875234</td>\n",
       "      <td>948692</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Barking &amp; Dagenham</td>\n",
       "      <td>E09000002</td>\n",
       "      <td>50460.2266</td>\n",
       "      <td>51085.77983</td>\n",
       "      <td>51268.96956</td>\n",
       "      <td>53133.50526</td>\n",
       "      <td>53042.24852</td>\n",
       "      <td>53700.34831</td>\n",
       "      <td>52113.12157</td>\n",
       "      <td>52232.19868</td>\n",
       "      <td>...</td>\n",
       "      <td>352086</td>\n",
       "      <td>346059</td>\n",
       "      <td>344693</td>\n",
       "      <td>347710</td>\n",
       "      <td>348002</td>\n",
       "      <td>343972</td>\n",
       "      <td>340763</td>\n",
       "      <td>343731</td>\n",
       "      <td>344255</td>\n",
       "      <td>334460</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Barnet</td>\n",
       "      <td>E09000003</td>\n",
       "      <td>93284.51832</td>\n",
       "      <td>93190.16963</td>\n",
       "      <td>92247.52435</td>\n",
       "      <td>90762.87492</td>\n",
       "      <td>90258.00033</td>\n",
       "      <td>90107.23471</td>\n",
       "      <td>91441.24768</td>\n",
       "      <td>92361.31512</td>\n",
       "      <td>...</td>\n",
       "      <td>597762</td>\n",
       "      <td>603522</td>\n",
       "      <td>596521</td>\n",
       "      <td>585644</td>\n",
       "      <td>572257</td>\n",
       "      <td>570542</td>\n",
       "      <td>575808</td>\n",
       "      <td>586501</td>\n",
       "      <td>589399</td>\n",
       "      <td>597538</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Bexley</td>\n",
       "      <td>E09000004</td>\n",
       "      <td>64958.09036</td>\n",
       "      <td>64787.92069</td>\n",
       "      <td>64367.49344</td>\n",
       "      <td>64277.66881</td>\n",
       "      <td>63997.13588</td>\n",
       "      <td>64252.32335</td>\n",
       "      <td>63722.70055</td>\n",
       "      <td>64432.60005</td>\n",
       "      <td>...</td>\n",
       "      <td>402570</td>\n",
       "      <td>401263</td>\n",
       "      <td>395612</td>\n",
       "      <td>392642</td>\n",
       "      <td>385603</td>\n",
       "      <td>383969</td>\n",
       "      <td>387475</td>\n",
       "      <td>387360</td>\n",
       "      <td>389590</td>\n",
       "      <td>393227</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Brent</td>\n",
       "      <td>E09000005</td>\n",
       "      <td>71306.56698</td>\n",
       "      <td>72022.26197</td>\n",
       "      <td>72015.76274</td>\n",
       "      <td>72965.63094</td>\n",
       "      <td>73704.04743</td>\n",
       "      <td>74310.48167</td>\n",
       "      <td>74127.03788</td>\n",
       "      <td>73547.0411</td>\n",
       "      <td>...</td>\n",
       "      <td>551662</td>\n",
       "      <td>535332</td>\n",
       "      <td>527101</td>\n",
       "      <td>525558</td>\n",
       "      <td>523687</td>\n",
       "      <td>526985</td>\n",
       "      <td>525460</td>\n",
       "      <td>552411</td>\n",
       "      <td>554568</td>\n",
       "      <td>542864</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 348 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "0             Borough         ID 1995-01-01 00:00:00 1995-02-01 00:00:00  \\\n",
       "1      City of London  E09000001         91448.98487         82202.77314   \n",
       "2  Barking & Dagenham  E09000002          50460.2266         51085.77983   \n",
       "3              Barnet  E09000003         93284.51832         93190.16963   \n",
       "4              Bexley  E09000004         64958.09036         64787.92069   \n",
       "5               Brent  E09000005         71306.56698         72022.26197   \n",
       "\n",
       "0 1995-03-01 00:00:00 1995-04-01 00:00:00 1995-05-01 00:00:00  \\\n",
       "1         79120.70256         77101.20804         84409.14932   \n",
       "2         51268.96956         53133.50526         53042.24852   \n",
       "3         92247.52435         90762.87492         90258.00033   \n",
       "4         64367.49344         64277.66881         63997.13588   \n",
       "5         72015.76274         72965.63094         73704.04743   \n",
       "\n",
       "0 1995-06-01 00:00:00 1995-07-01 00:00:00 1995-08-01 00:00:00  ...  \\\n",
       "1         94900.51244         110128.0423         112329.4376  ...   \n",
       "2         53700.34831         52113.12157         52232.19868  ...   \n",
       "3         90107.23471         91441.24768         92361.31512  ...   \n",
       "4         64252.32335         63722.70055         64432.60005  ...   \n",
       "5         74310.48167         74127.03788          73547.0411  ...   \n",
       "\n",
       "0 2023-01-01 00:00:00 2023-02-01 00:00:00 2023-03-01 00:00:00  \\\n",
       "1              962674              868654              931058   \n",
       "2              352086              346059              344693   \n",
       "3              597762              603522              596521   \n",
       "4              402570              401263              395612   \n",
       "5              551662              535332              527101   \n",
       "\n",
       "0 2023-04-01 00:00:00 2023-05-01 00:00:00 2023-06-01 00:00:00  \\\n",
       "1              905101              960392              982370   \n",
       "2              347710              348002              343972   \n",
       "3              585644              572257              570542   \n",
       "4              392642              385603              383969   \n",
       "5              525558              523687              526985   \n",
       "\n",
       "0 2023-07-01 00:00:00 2023-08-01 00:00:00 2023-09-01 00:00:00  \\\n",
       "1              960158              888278              875234   \n",
       "2              340763              343731              344255   \n",
       "3              575808              586501              589399   \n",
       "4              387475              387360              389590   \n",
       "5              525460              552411              554568   \n",
       "\n",
       "0 2023-10-01 00:00:00  \n",
       "1              948692  \n",
       "2              334460  \n",
       "3              597538  \n",
       "4              393227  \n",
       "5              542864  \n",
       "\n",
       "[5 rows x 348 columns]"
      ]
     },
     "execution_count": 699,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "properties.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "jy8BzXHmoWEw"
   },
   "source": [
    "**2.4.Transforming the data**\n",
    "\n",
    "Remember what Wes McKinney said about tidy data? \n",
    "\n",
    "You might need to **melt** your DataFrame here. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 700,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "S2wM0qLuo2Zt",
    "tags": []
   },
   "outputs": [],
   "source": [
    "properties = pd.melt(properties, id_vars=['Borough', 'ID'], var_name='Date', value_name='Avg_Price')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "7kIsgAo7o3mf"
   },
   "source": [
    "Remember to make sure your column data types are all correct. Average prices, for example, should be floating point numbers... "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 701,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "ZcR4IHbcpOaq",
    "tags": []
   },
   "outputs": [],
   "source": [
    "properties['Avg_Price'] = properties['Avg_Price'].astype(float)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "knLUXHLypOtw"
   },
   "source": [
    "**2.5. Cleaning the data (part 3)**\n",
    "\n",
    "Do we have an equal number of observations in the ID, Average Price, Month, and London Borough columns? Remember that there are only 32 London Boroughs. How many entries do you have in that column? \n",
    "\n",
    "Check out the contents of the London Borough column, and if you find null values, get rid of them however you see fit. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 702,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Borough      16608\n",
       "ID           15570\n",
       "Date         16608\n",
       "Avg_Price    15570\n",
       "dtype: int64"
      ]
     },
     "execution_count": 702,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "properties.count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 703,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "properties = properties.dropna()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 704,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Borough      15570\n",
       "ID           15570\n",
       "Date         15570\n",
       "Avg_Price    15570\n",
       "dtype: int64"
      ]
     },
     "execution_count": 704,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "properties.count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 705,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "boroughs_list = properties['Borough'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 706,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['City of London', 'Barking & Dagenham', 'Barnet', 'Bexley',\n",
       "       'Brent', 'Bromley', 'Camden', 'Croydon', 'Ealing', 'Enfield',\n",
       "       'Greenwich', 'Hackney', 'Hammersmith & Fulham', 'Haringey',\n",
       "       'Harrow', 'Havering', 'Hillingdon', 'Hounslow', 'Islington',\n",
       "       'Kensington & Chelsea', 'Kingston upon Thames', 'Lambeth',\n",
       "       'Lewisham', 'Merton', 'Newham', 'Redbridge',\n",
       "       'Richmond upon Thames', 'Southwark', 'Sutton', 'Tower Hamlets',\n",
       "       'Waltham Forest', 'Wandsworth', 'Westminster', 'Inner London',\n",
       "       'Outer London', 'NORTH EAST', 'NORTH WEST', 'YORKS & THE HUMBER',\n",
       "       'EAST MIDLANDS', 'WEST MIDLANDS', 'EAST OF ENGLAND', 'LONDON',\n",
       "       'SOUTH EAST', 'SOUTH WEST', 'England'], dtype=object)"
      ]
     },
     "execution_count": 706,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "boroughs_list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 707,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "45"
      ]
     },
     "execution_count": 707,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(boroughs_list)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 708,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "non_boroughs = ['Inner London', 'Outer London', \n",
    "               'NORTH EAST', 'NORTH WEST', 'YORKS & THE HUMBER', \n",
    "               'EAST MIDLANDS', 'WEST MIDLANDS',\n",
    "              'EAST OF ENGLAND', 'LONDON', 'SOUTH EAST', \n",
    "              'SOUTH WEST', 'England']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 709,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "12"
      ]
     },
     "execution_count": 709,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(non_boroughs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 710,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "df = properties[~properties.Borough.isin(non_boroughs)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 711,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Borough</th>\n",
       "      <th>ID</th>\n",
       "      <th>Date</th>\n",
       "      <th>Avg_Price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>City of London</td>\n",
       "      <td>E09000001</td>\n",
       "      <td>1995-01-01</td>\n",
       "      <td>91448.98487</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Barking &amp; Dagenham</td>\n",
       "      <td>E09000002</td>\n",
       "      <td>1995-01-01</td>\n",
       "      <td>50460.22660</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Barnet</td>\n",
       "      <td>E09000003</td>\n",
       "      <td>1995-01-01</td>\n",
       "      <td>93284.51832</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Bexley</td>\n",
       "      <td>E09000004</td>\n",
       "      <td>1995-01-01</td>\n",
       "      <td>64958.09036</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Brent</td>\n",
       "      <td>E09000005</td>\n",
       "      <td>1995-01-01</td>\n",
       "      <td>71306.56698</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              Borough         ID       Date    Avg_Price\n",
       "0      City of London  E09000001 1995-01-01  91448.98487\n",
       "1  Barking & Dagenham  E09000002 1995-01-01  50460.22660\n",
       "2              Barnet  E09000003 1995-01-01  93284.51832\n",
       "3              Bexley  E09000004 1995-01-01  64958.09036\n",
       "4               Brent  E09000005 1995-01-01  71306.56698"
      ]
     },
     "execution_count": 711,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "PGEx6mJsp6dG"
   },
   "source": [
    "**2.6. Visualizing the data**\n",
    "\n",
    "To visualize the data, why not subset on a particular London Borough? Maybe do a line plot of Month against Average Price?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 712,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "nAg5pT9cqHAR",
    "tags": []
   },
   "outputs": [],
   "source": [
    "brent = df[df['Borough'] == 'Brent']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 713,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'Price')"
      ]
     },
     "execution_count": 713,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlYAAAG1CAYAAAA7nbquAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8pXeV/AAAACXBIWXMAAA9hAAAPYQGoP6dpAAByUElEQVR4nO3dd1yT1/4H8E8CSRhCZIcAAipOnGhdbdEqaOvoXlpae3vtctSqba/93dva3lu1rbVDb9ftbm3p0m5x1FW3gii4J0uQHXZCkvP7I+TRiCJoIAE+79crryt5vnly8jRXPp5znnNkQggBIiIiIrpmckc3gIiIiKitYLAiIiIishMGKyIiIiI7YbAiIiIishMGKyIiIiI7YbAiIiIishMGKyIiIiI7YbAiIiIishMGKyIiIiI7YbAiIiIishOHB6ucnBw88MAD8PPzg4eHB/r374/k5GTpuBACCxYsgFarhbu7O0aOHImDBw/anEOv12PmzJnw9/eHp6cnJk2ahOzsbJuakpISJCQkQK1WQ61WIyEhAaWlpTY1mZmZmDhxIjw9PeHv749Zs2bBYDDY1KSlpSE2Nhbu7u4ICQnByy+/DO4KRERERICDg1VJSQlGjBgBhUKB1atX49ChQ3jjjTfQsWNHqea1117D0qVLsXz5cuzZswcajQZxcXEoLy+XambPno1Vq1YhMTERW7duRUVFBSZMmACTySTVTJ48GampqUhKSkJSUhJSU1ORkJAgHTeZTBg/fjwqKyuxdetWJCYm4scff8TcuXOlmrKyMsTFxUGr1WLPnj1YtmwZlixZgqVLlzbvhSIiIqJWQebITZj/8Y9/YNu2bfjrr78ueVwIAa1Wi9mzZ+O5554DYOmdCgoKwquvvorHHnsMOp0OAQEB+PLLL3HvvfcCAM6ePYuwsDD88ccfGDt2LA4fPoxevXph586dGDJkCABg586dGDZsGI4cOYLu3btj9erVmDBhArKysqDVagEAiYmJmDp1KvLz8+Ht7Y333nsP8+fPx7lz56BSqQAAixcvxrJly5CdnQ2ZTHbFz2w2m3H27Fl4eXk1qp6IiIgcTwiB8vJyaLVayOUN9EsJB+rZs6eYPXu2uOuuu0RAQIDo37+/+PDDD6XjJ0+eFABESkqKzesmTZokHnzwQSGEEH/++acAIIqLi21q+vbtK1544QUhhBAff/yxUKvV9d5frVaLTz75RAghxL/+9S/Rt29fm+PFxcUCgNiwYYMQQoiEhAQxadIkm5qUlBQBQJw6deqSn7GmpkbodDrpcejQIQGADz744IMPPvhohY+srKwGs40rHOjUqVN47733MGfOHDz//PPYvXs3Zs2aBZVKhQcffBB5eXkAgKCgIJvXBQUFISMjAwCQl5cHpVIJHx+fejXW1+fl5SEwMLDe+wcGBtrUXPw+Pj4+UCqVNjURERH13sd6LDIyst57LFq0CC+99FK957OysuDt7X3pC0NEREROpaysDGFhYfDy8mqwzqHBymw2Y9CgQVi4cCEAYMCAATh48CDee+89PPjgg1LdxUNmQogrDqNdXHOpenvUiLqR1Mu1Z/78+ZgzZ470s/U/jLe3N4MVERFRK3Ol/OHQyevBwcHo1auXzXM9e/ZEZmYmAECj0QCA1GNklZ+fL/UUaTQaGAwGlJSUNFhz7ty5eu9fUFBgU3Px+5SUlKC2trbBmvz8fAD1e9WsVCqVFKIYpoiIiNo2hwarESNG4OjRozbPHTt2DOHh4QCAyMhIaDQarFu3TjpuMBiwefNmDB8+HAAQExMDhUJhU5Obm4v09HSpZtiwYdDpdNi9e7dUs2vXLuh0Opua9PR05ObmSjVr166FSqVCTEyMVLNlyxabJRjWrl0LrVZbb4iQiIiI2qEGZ2A1s927dwtXV1fxyiuviOPHj4sVK1YIDw8P8dVXX0k1ixcvFmq1WqxcuVKkpaWJ+++/XwQHB4uysjKp5vHHHxehoaFi/fr1IiUlRdx0002iX79+wmg0SjXjxo0Tffv2FTt27BA7duwQffr0ERMmTJCOG41GER0dLUaPHi1SUlLE+vXrRWhoqJgxY4ZUU1paKoKCgsT9998v0tLSxMqVK4W3t7dYsmRJoz+zTqcTAIROp7vay0ZEREQtrLG/vx263AIA/Pbbb5g/fz6OHz+OyMhIzJkzB9OmTZOOCyHw0ksv4YMPPkBJSQmGDBmC//73v4iOjpZqampq8Mwzz+Drr79GdXU1Ro8ejXfffRdhYWFSTXFxMWbNmoVffvkFADBp0iQsX77cZs2szMxMPPnkk9iwYQPc3d0xefJkLFmyRFpaAbAsEDp9+nTs3r0bPj4+ePzxx/HCCy80eumEsrIyqNVq6HS6yw4Lmkwm1NbWNup85JwUCgVcXFwc3QwiIrKTxvz+Bhy8jlV71NB/GCEE8vLy6q0IT61Tx44dodFouF4ZEVEb0Nhg5dC7AsmWNVQFBgbCw8ODv5BbKSEEqqqqpBsbgoODHdwiIiJqKQxWTsJkMkmhys/Pz9HNoWvk7u4OwHLXaGBgIIcFiYjaCYdvwkwW1jlVHh4eDm4J2Yv1vyXnyxERtR8MVk6Gw39tB/9bEhG1PwxWRERERHbCYEXtlkwmw08//eToZhARURvCYEV2s337dri4uGDcuHEt+r4RERGQyWSQyWTw8PBAdHQ0Pvjggyu+Ljc3FzfffHMLtJCIiNoLBiuym08++QQzZ87E1q1bpf0eW8rLL7+M3NxcHDhwALfddhsef/xxfPvtt5estW5JpNFobBZ/JSKitsVsFjCZW3a5TgYrsovKykp89913eOKJJzBhwgR89tlnACz7K/7jH/+wqS0oKIBCocDGjRsBWHqOxo8fD3d3d0RGRuLrr79GREQE3nrrrUa/v5eXFzQaDbp27Yr//Oc/iIqKkob5Ro4ciRkzZmDOnDnw9/dHXFwcgPpDgdnZ2bjvvvvg6+sLT09PDBo0CLt27ZKO//rrr4iJiYGbmxs6d+6Ml156CUajsekXi4iIml1JpQGDXlmPGV+ntOj7ch0rJyaEQHWtySHv7a5wadJdbd9++y26d++O7t2744EHHsDMmTPxr3/9C1OmTMHrr7+ORYsWSef79ttvERQUhNjYWADAgw8+iMLCQmzatAkKhQJz5syRFte8Wm5ubjbLHHz++ed44oknsG3bNlxqs4GKigrExsYiJCQEv/zyCzQaDVJSUmA2mwEAa9aswQMPPIB33nkHN9xwA06ePIlHH30UAPDiiy9eU1uJiMj+UrNLUVxpQNLBPJRWGdDRQ9ki78tg5cSqa03o9cIah7z3oZfHwkPZ+K/Hxx9/jAceeAAAMG7cOFRUVODPP//Evffei6effhpbt27FDTfcAAD4+uuvMXnyZMjlchw5cgTr16/Hnj17MGjQIADARx99hKioqKtqt9FoxFdffYW0tDQ88cQT0vNdu3bFa6+9dtnXff311ygoKMCePXvg6+srvcbqlVdewT/+8Q889NBDAIDOnTvj3//+N5599lkGKyIiJ5RTUg0AEALYfboY8b01LfK+HAqka3b06FHs3r0b9913HwDA1dUV9957Lz755BMEBAQgLi4OK1asAACcPn0aO3bswJQpU6TXurq6YuDAgdL5unbtCh8fnya14bnnnkOHDh3g7u6O6dOn45lnnsFjjz0mHbeGtstJTU3FgAEDpFB1seTkZLz88svo0KGD9Jg2bRpyc3NRVVXVpLYSEVHzyymtlv6841RRi70ve6ycmLvCBYdeHuuw926sjz/+GEajESEhIdJzQggoFAqUlJRgypQpeOqpp7Bs2TJ8/fXX6N27N/r16yfVXUpT9wZ/5plnMHXqVHh4eCA4OLjeMKanp2eDr7duQXM5ZrMZL730Eu644456x9zc3JrUViIian7ZJeeD1c5TxS32vgxWTkwmkzVpOM4RjEYjvvjiC7zxxhuIj4+3OXbnnXdixYoVePjhh/HYY48hKSkJX3/9NRISEqSaHj16wGg0Yt++fYiJiQEAnDhxAqWlpU1qh7+/v83QXVP17dsXH330EYqLiy/ZazVw4EAcPXr0mt6DiIhaTk7J+dGEw7llKKk0wMez+edZcSiQrslvv/2GkpISPPLII4iOjrZ53HXXXfj444/h6emJW2+9Ff/6179w+PBhTJ48WXp9jx49MGbMGDz66KPYvXs39u3bh0cffRTu7u4tuiXM/fffD41Gg9tuuw3btm3DqVOn8OOPP2LHjh0AgBdeeAFffPEFFixYgIMHD+Lw4cP49ttv8c9//rPF2khERI1nHQpUulqizsaj13ZTVGMxWNE1+fjjjzFmzBio1ep6x+68806kpqYiJSUFU6ZMwf79+3HDDTegU6dONnVffPEFgoKCcOONN+L222/HtGnT4OXl1aJDbEqlEmvXrkVgYCBuueUW9OnTB4sXL4aLi2VIdOzYsfjtt9+wbt06DB48GEOHDsXSpUsRHh7eYm0kIqLGMRjNyC/XAwAmX2f5nfPlzowWeW+ZaOpkFromZWVlUKvV0Ol08Pb2lp6vqanB6dOnERkZ2e7n7GRnZyMsLAzr16/H6NGjHd2cq8b/pkREjpFRVInY1zfBTSHHX8/ehBGLN8BgMuOXGSPQN7TjVZ3zcr+/L8YeK3K4DRs24JdffsHp06exfft23HfffYiIiMCNN97o6KYREVErZJ24HtLRHQFeKozvGwwA+HJH8/daMViRw9XW1uL5559H7969cfvttyMgIEBaLHTFihU2Sxxc+Ojdu7ejm05ERE7IuoZViI8HAODuQaEAgI1HC5p813lTOfctZ9QujB07FmPHXnpZiUmTJmHIkCGXPKZQKJqzWURE1Epll57vsQKAgZ18oHKVo7BCj5MFlega2KHZ3pvBipyal5cXvLy8HN0MIiJqRTKLKgEAoT6WYOWmcMHATj7YcaoIu04XNWuw4lAgERERtSl7zpQAAPqEnL9jfUhnyxqFzb1YKIOVk7Fu+kutH/9bEhG1vKziKuSUVsNVLkNM+Pnt0YZ29gMA7DxV1Oh5VkII/HfjCbzy+6FGv4ZDgU5CqVRCLpfj7NmzCAgIgFKpbNEFMsl+hBAwGAwoKCiAXC6HUtkyO6oTEdH5fQH7hXWEp+p8zOkf1hFKVzkKyvX4KTUHtw8IbfA8Qgj86+d0fLUzEwAQ1/XySyxciMHKScjlckRGRiI3Nxdnz551dHPIDjw8PNCpUyfI5ewYJiJqKTvrgtXQzrbbk7kpXPDg0HB8tPU05n63Hz4eSozsHnjZ82w4ki+FKgA4klfeqPdnsHIiSqUSnTp1gtFohMlkcnRz6Bq4uLjA1dWVvY5ERC1ICIGdJy3Balhn/3rHn7+lJwoq9Pg59Sy+3ZPVYLA6kV9h8/PRcwxWrZJMJoNCoeBSAkRERE1UUKHHWV0N5DJgYHjHesflchkm9dPi59SzyCyuqn+CCxRXGgAAXm6uKK8x4lgje6w4RkFERERtQlaxZf2qYLU7PJSX7jvq5GtZNDSzqKrBCenWYHV9V0vP15G8ska1gcGKiIiI2oTsEksvVEjd+lWXElq3Gnu53ghdde1l66zBakikL1zkMuiqjY1qA4MVERERtQk5dSuuhzYQrNyVLgjwUgFAg8OBxVWWYKVRu6NLgGej28BgRURERG2CdfNla6/U5UjDgQ0Fq7oeK78OSvQMbtxSCwCDFREREbURUrDqePkeK6BpwcrHg8GKiIiI2iHrHKuGhgIBIKwuWFknu1/MYDSjvMYyp8rPU4k7Bobgl5kjGtUGLrdARERErZ4QAjlNHArMukyPVWnd/Cq5DFC7KyCXy+AmGrdxM3usiIiIqNUrrDBAbzRDJgM0arcGa680FFh0wTCgXN60hZ4ZrIiIiKjVsw4DarzdoHRtON6E+VqGCnNKq1FrMtc7XmINVp5N3+uVwYqIiIhavcYstWAV5OUGLzdXmMwCh87WX/jT2mPly2BFRERE7dGZwkoAV55fBVi2thna2Q8AsO1kYb3jJXVzrPwYrIiIiKi9qak1YcWuTABA/7COjXrNiC51wepE/WBVVMGhQCIiImqnPtt+Brm6GmjVbrh3cFijXnN9lGUPwL1nSlBTa7I5xh4rIiIiapfMZoEPt5wCAMyJ7w43hUujXtcloAMCvVTQG81IziiRnt99uhhpOToAlrsCm4rBioiIiJzC1uOFKKrQN+k1JwsqUFxpgLvCBbf21zb6dTKZTOq1mvvdfuw4WYQfk7Nxzwc7sC+zFIBlO5um4gKhRERE5HBbjhXgwU92Y3gXP3w9bWijX5eSaelt6huqhsKlaf1Fs0d3Q2pWKU4VVOKBj3fB7aJlGvw7qJp0PoA9VkRERNQMcnXV9eYuNWTPmWIAwPaTRdLSCRc6kld2yedTMkoBAAPDfZrcxk5+Hvht5vW4rb8WJrNApcGE6BBv/PvW3kgYGo7BEb5NPid7rIiIiMiuktJzMf3rfRjVPQAfPTS4Ua+5cD2pX/efxeOxXaSf954pxj0f7ECQtxu2PDvKpmfK2mM1oJF3A17MQ+mKN+/tj24aL2w4nI9Fd/RBVJDXVZ0LYI8VERFRq5ZdUoX/bTnVpN6h5nQ0rxyPf5UCk1lg/eH8RrfrUK5tsLKqqTXh2R8OwCyAXF0Nth4/vzyCrroWx/MrAFxdj5WVTCbDkyO74ocnhl9TqAIYrIiIiFq119ccxSt/HMbn2884uikAgLf/PGbz84Fs3RVfU1xpQK6uBgDgKpfh4NkyLFp9GAajGR9vPY1TdYt/AsCqfTnSn1OzSgFY9v67mvlQzYHBioiIqBU7mlcOwDI3yRlkFFn27HOvW/bAOneqIYfreqsi/Dzw5EjLEOAHm09hydqjUu/VlCGdAABrD+WhQm8EAOyrGwYc2Kmj/T7ANWKwIiIiaqXMZoEzRZbenL1nimG8xIbCLe1cmWW5hAl9gwE0LlhZ51f10npjTnx3vHpnHwDAVzszcCSvHHIZMC++OyL9PVFTa8bXuzIAACl1yyJcyzCgvTFYERERtVLnymtQU2sJU5UGk808JUcwmswoqrQEq1vqglXymRKYzAJf7DiDRasPw2wWqKk1wWQW0uus7e4V7A0AuCsmDMFqN1QZLPOzBkX4wsdTicdjOwMA3lh7DCcLKi7osWKwIiIiomt0uqDS5uddp67cO9SciioNEAJwkcswoos/OqhcUa434nBuGV74+SA+2HwKv6flIv7NLZi0fCuEEBBCYNcpyzBmdIgagOX1dw4Mlc4b1zMIAHDPoDBc39UfeqMZ0z7fi/IaI9wUcnTXXNuEc3tisCIiImqlThddFKxOO3ae1bkyywR0/w5KKF3PB54LhwNf+f0wMourcPBsGUqrapGWo8NZXQ08lC4Y2tlPqrsr5nywGt0zEIDl7r1Fd/SB0kUuTWjvG9qxyQuDNifnaQkRERE1ibXHakDd5O3G3IHXnPLr5lcFerkBAEI6ugOwDVZ5deELAM7qqrHmYB4AYGT3AJt9/iL8PfHaXX2x8PY+6BzQQXo+zNcDDwwNl352pmFAgMGKiIio1bJOXB/V3dKjk1+uh97ouPWs8sstwSrI27L0gVYKViWXrM/T1WDNwXMAgPhemnrH7xkUhsl1dwNe6MlRXeChtISwGCeauA5w5XUiIqJWyzocNrCTDzyULqgymHC2tAaR/p4OaU9+uaU3KsDaY+VjCVYF5ZfeWHnnqSKcyK+Aq1yGUT0CG/0+/h1U+O/kgUjOKMFNTXhdS2CPFRER0TUwmwW+3HEGB7JLW/R9jSYzsoota0ZFBnhKw27ZJVUt2o4LnZOGAi09VqF1bbIKVlsCl8JFBgD480g+AKC31htqd0WT3mtUj0DMG9sdLnLZNbXZ3hwarBYsWACZTGbz0GjOdwUKIbBgwQJotVq4u7tj5MiROHjwoM059Ho9Zs6cCX9/f3h6emLSpEnIzs62qSkpKUFCQgLUajXUajUSEhJQWlpqU5OZmYmJEyfC09MT/v7+mDVrFgwGg01NWloaYmNj4e7ujpCQELz88ssQQoCIiNqvXw+cxb9+Poi73t8hzRdqCZnFVag1Cbgp5Aj2dkOojzVY1d+ouKUU1PVYBXlbApT2omD1eGwXHFgQjzlx3QEAp+rmiHUNdJ67+q6Vw3usevfujdzcXOmRlpYmHXvttdewdOlSLF++HHv27IFGo0FcXBzKy8ulmtmzZ2PVqlVITEzE1q1bUVFRgQkTJsBkOj/GPHnyZKSmpiIpKQlJSUlITU1FQkKCdNxkMmH8+PGorKzE1q1bkZiYiB9//BFz586VasrKyhAXFwetVos9e/Zg2bJlWLJkCZYuXdrMV4iIiJzZ17syAQAGoxlPrkhBZlHL9BgdqVtxvXuQF+RyGUJ9PAAAOdcQrI7klTVqQc/Lsc6xsvZYWYcCrYLVbvB2U0g9V1ZdAzugrXD4HCtXV1ebXiorIQTeeust/N///R/uuOMOAMDnn3+OoKAgfP3113jssceg0+nw8ccf48svv8SYMWMAAF999RXCwsKwfv16jB07FocPH0ZSUhJ27tyJIUOGAAD+97//YdiwYTh69Ci6d++OtWvX4tChQ8jKyoJWqwUAvPHGG5g6dSpeeeUVeHt7Y8WKFaipqcFnn30GlUqF6OhoHDt2DEuXLsWcOXMgkzlXVyQRETW/UwUV2HW6GHIZEOHniVOFldh9phid/Dya/b2twaqHxrKoZojPtQ0Fms0CD3y0CyVVtfhzTiwirmKelnW5hcC6yesdVK5Quyugq64FcL4HS9OGg5XDe6yOHz8OrVaLyMhI3HfffTh16hQA4PTp08jLy0N8fLxUq1KpEBsbi+3btwMAkpOTUVtba1Oj1WoRHR0t1ezYsQNqtVoKVQAwdOhQqNVqm5ro6GgpVAHA2LFjodfrkZycLNXExsZCpVLZ1Jw9exZnzpy57OfT6/UoKyuzeRARUdvw7d4sAMDI7oG4sVsAAOBIE1Y/r9QbUVRx6YndV2J9H+taUdc6FJhdUo3CCgNMZoHV6U0f0jSZBQorLFNorEOBgO1woLWnSqu27clisLKTIUOG4IsvvsCaNWvwv//9D3l5eRg+fDiKioqQl2f5jxoUFGTzmqCgIOlYXl4elEolfHx8GqwJDKx/x0BgYKBNzcXv4+PjA6VS2WCN9WdrzaUsWrRImtulVqsRFhbW8EUhIqJWY/PRAgDAHQNDpIBz9Fx5Qy+RCCHwwMe7EPv6JuTqmh6GpB6rYGuwsvSSXW2wOnZBu69mrlhxpSWUyWSAn6dSet46qV7lKodv3fNB6vOdFEoXOcIuGjJszRwarG6++Wbceeed6NOnD8aMGYPff/8dgGXIz+riITYhxBWH3S6uuVS9PWqsE9cbas/8+fOh0+mkR1ZWVoNtJyKi1qFCb5RC1HWRvlKwsgaeKzlZUIl9maWo0Bux7tC5Jr13pd6IzLo7AqWhwLoAc668BgZj0zdjPpZ/vt2pWaVNDntnSy31gV4quF6wErq1J03b0V36falydYF/B0vIivT3tKlv7Zzqk3h6eqJPnz44fvy4NO/q4t6g/Px8qadIo9HAYDCgpKSkwZpz5+p/YQsKCmxqLn6fkpIS1NbWNliTn2+5TfTinqwLqVQqeHt72zyIiKh1KijX49WkI7jrve1I3J0JISzBIdDLDd2CvKSa4krDFc4E/Hn4/O+mTXU9X4BlrtOCXw7i6W9T8WNyNlIyS1Brsg1K1kAX6KWSeoH8OyihcpVDCFxVD9ixiwLh2oNNC3vWxUrD/WznZmk7Wob/Lp6wbp1n1ZaGAQEnC1Z6vR6HDx9GcHAwIiMjodFosG7dOum4wWDA5s2bMXz4cABATEwMFAqFTU1ubi7S09OlmmHDhkGn02H37t1Sza5du6DT6Wxq0tPTkZubK9WsXbsWKpUKMTExUs2WLVtslmBYu3YttFotIiIi7H8xiIjIqVQbTLjtv9vw3qaT2JtRgoV/HAYADKjbUqWDyhWdfC3DcUfyLj/PSlddi+SMYqy/IFhtP1mImlrL3ex7M0rw2fYzWLUvB3O/34873t2OWd/ssznHkVzrMOD5f6zLZDKpdyir+CqC1bkKAEC3IEvQOVVQ0aTXZ9TdDRlx0cT90T2D0CXAE3dcsKkyAATXzbPqwmBlP/PmzcPmzZtx+vRp7Nq1C3fddRfKysrw0EMPQSaTYfbs2Vi4cCFWrVqF9PR0TJ06FR4eHpg8eTIAQK1W45FHHsHcuXPx559/Yt++fXjggQekoUUA6NmzJ8aNG4dp06Zh586d2LlzJ6ZNm4YJEyage3fLOhrx8fHo1asXEhISsG/fPvz555+YN28epk2bJvUwTZ48GSqVClOnTkV6ejpWrVqFhQsX8o5AIqJ24rcDZ5FTWi3NHzLXLWM4sG6fPuD8RPKjlxkOzNPVYMKyv3DnezukbV683VxRU2vGrtOWZQ4uXO7Aeu4txwpgNp9fN/FoXXDrqbFd/8ka7DKKbTdnvhKTWeBEXZAaEGYJijW1TRtOvFyPVZeADvhz7kibTZUBYPJ1nTAo3Ae39teiLXFosMrOzsb999+P7t2744477oBSqcTOnTsRHm7ZXPHZZ5/F7Nmz8eSTT2LQoEHIycnB2rVr4eV1/ov05ptv4rbbbsM999yDESNGwMPDA7/++itcXM5v5LhixQr06dMH8fHxiI+PR9++ffHll19Kx11cXPD777/Dzc0NI0aMwD333IPbbrsNS5YskWrUajXWrVuH7OxsDBo0CE8++STmzJmDOXPmtMCVIiIiR1tRt17VIzdE4oYof+n5CzcB7mGdZ5VbP1hlFFViykc7bXqTemi8cEufYADA0rVHcba0GnvrgtW/JvTC948Ph7vCBZUGk7R9DQActq5hdVGwsm5WbF14s7EyiiphMJrhppAjqq7Hqrq2aXsOnu+xatwyDaN6BOKHJ4ajS0Db6rFy6DpWiYmJDR6XyWRYsGABFixYcNkaNzc3LFu2DMuWLbtsja+vL7766qsG36tTp0747bffGqzp06cPtmzZ0mANERG1Pek5OqRmlULhIsPdMWGICvTCX8cL4aaQo+cFw3HWkHBxj9H2k4V47MtklNcYEax2w5v39sfW44UYF62Bi1yG39NysT9bh9vf3YYqgyXQDI7wgYtchugQb+w5U4K0nFJ0DewAIYS01IJ14rqVdY/A04VNC1bWOwKjAr3gXre5cU2Tg5W1x6r51/ByZg5fIJSIiMiZmc0C//7tEABgbG8NArxUGN0jEE+P6YYIfw8oXc8P/lgX6cwpPd8rVVZTi9mJqSivMSIm3AfLJw9AsNodQzv7STW/z7wBD36yC2fqen08lC7oVRfY+oR0xJ4zJTiQrcPtA0KRV1aDshojXOUydAm07R3qHGD5uaH5UTml1fBQuMDngiURTkpby3SAu8ISrJrSY1VeUyutYcVgRURERJf1xY4z2HW6GO4KFzwz1jI3Vy6X4akxUfVqrYth5ulqYDILuMhleGPNUeSX6xHh54EVfx8CN4VLvdd18vPAS7dG46FPLDdaDezkIy1B0CfUErBWp+WhtKoWAXXbxXQO8ITK1fZcnf0tPWZZJdUwGM02oQ+w3LEYt3Qz/DuosPbpG6W2nKnr4Yr095Se0zdhjpV1GNDPUwkvt6ZtptzWONVdgURERM5ECIHlG08CAObf0qPexOyLBXmp4CKXodYkUFCuR2GFHl/uzAAA/Oe2PpcMVVax3QIwpqdlQevhXc/3ZvUJ6QgAyCurwap9Ofhwi2WHkouHAQEgyFsFD6ULTGYhrXN1oeSMYlQZTMgsrsIPydnS82cuGMZrSo/VyYIK/P3zPZiwbKv0+vaOwYqIiOgivx04i+lfp+BkQSUKK/Rwkctwz6Ar75zh6iKHpm47l5zSKuw9UwyzsExSv/6CCe+X89Z9A/Dmvf3wtxGR0nOdL7Nnn3XF9QvJZLIG51ml5eikP7+36aS0PtbpQksIi/T3hEphiQZXmmN1ILsUN7/1F9YfzpeeC/NlsGKwIiIiusjSdcfw+4FcvJp0BADQJcCzwd6mC52fZ1WDvXVLKgyK8GnoJZIOKlfcPiDU5r3kchkevbEzIv09ccfAEOn5Hpr6wQq4cAJ7/XlWaTnn19fKKa1GUnpe3fwoy36FERcMBdYYGw5WP6eehcFkRr+wjvBSWWYW9dZyEWzOsSIiIrqA3miS5gxZF/HsFdz4wGDdWianpBp7M+qCVbjvNbXp+Vt64vlbekJXVYuVKTl1dwuqL1l74ZILZTW1+HZ3FiL8PTGiqx/S63qsRnT1w7YTRUg6mCcFMT9PJbzdFOeHAg0Nz7GyLoI65bpOiO8dhL+OF2JMz8vvRNJeMFgRERFd4ExhFUx1i3HWbQmLXk3oibEGq5MFFVKQiQlvXI/Vlag9FFg/JxYVeiMCvdwuWRNVt5L5ukPncKaoEjtPWdbFcpHLYDILuMplmHVTFLadKMLmowUY3cMyryuiLmCdn7zecI/V0QvW0uroocTEfm1roc+rxWBFRER0AeuaThfqFXzp3qFLsQ4Frk7LhdEsEOStkraasYcr7a0X1ysIPTReOJJXjqJTxXBTyNFBpZCG+7oFeWFwhC8CvVTIL9fjm92WhU+tC3s2ZvK6ZWK+ATIZpD0SyYJzrIiIiC5wPL/+3KSel5gofjnWHqvKuoU+B0X4tujWZ24KF3yQEANvN0vfyat39sWXj1wnHQ/1cYdcLsOYXpZhO+vWOpH+HnWvt0QDo1nU2/zZytpbFe7rIS0oShYMVkRERBc4kW8JDR3qJmRrvN3g10HV6Ndb17KyutUBQ2Thfp5Y8/SN+Gn6CNzaPwQ9g72x+I4+8PNUYurwCADAhLqtdKwuHgoELn9noHV+1aWWfGjvGKyIiIgucOycpcfqbyMiIJNZ1pdqipALgtXI7gGI762xa/saK1jtjv5hHaWf77uuE5L/FYfhXS3LPgzv6o837+2HqMAO0KrdpJXgVRcsKnq5jZiPXmavQuIcKyIiIonBaJZWIb/vuk64e1CYtNJ5Y7krXTCmZxDOFFXijbv7NUcz7eb2AaG4fUCozXMymQxuCjlqas2X7bE6LPVYMVhdjMGKiIgIQFZxFf7z+yEYzQIdVK4IVrtd9dyojx4aBCFEi86tsic3hUu9YKWrqsWpwgqoXF2QnlMGmQzoe0GPGFkwWBEREQF4bc1RrDloWbfqrpjQaw5FrTVUAZY7A0tRazMU+OyP+7Hm4DlpcvuEvlqbYU+yYLAiIiICcCTXMrz19n39cWv/kCtUt21ul1hyYcuxQgCWeVcyGTDrpq4OaZuz4+R1IiJq92pNZmlvvcER17ZKelsgbWtzQbDy66CU/nxPTBiiuH7VJbHHioiI2r2MokoYzQKeShcEqy+9onl74naJjZgr9EYAwC8zRqDPZbbTIQYrIiJqxzYeycesb/ZJi2V2DfJq1XOj7MXN1XYoUAiBihpLsAr0uvpJ/e0BhwKJiKjd+jk1B+V6I1btywFwfp+99s66mrq+bvK63miGsW7/xA5u7JNpCIMVERG1W0fybPcFZLCysA4FWnusrMOAAOCh4BY2DWGwIiKidslgNOPERfsCRgUxWAH1J69bhwE7qFwhl3MYsCEMVkRE1C6dLKiQhresogJ5pxtQf7kFa4+Vdf9EujxeISIiapes+911CfDEuTI9vN1cueBlHevkdesCodZg5aniMOCVMFgREVG7ZN3vbkRXf/z9+s5QuMo4zFXHXWm73II0FOimcFibWgsGKyIiapeO5Fp6rHpovNHJz8PBrXEu53usbIcCvTgUeEWcY0VERO2OEAKH67aw6RHMeVUXsy63YA1W5Zxj1WgMVkRE1O4cPFuG/HI9VK5y9NAwWF1MdfHk9RrrHCsGqythsCIionbn97RcAMBNPQLhoWRYuJibq3WOlWXyeqV1KJCLg14RgxUREbUrQgj8UResxvcNdnBrnJN1KJDLLTQdgxUREbUrB8+WIaOoCm4KOW7qEejo5jgl6+R1vXWOlXRXIIPVlTBYERFRu/L17kwAwOgeQRwGvIzzK69b17GqBcA5Vo3BYEVERG1aeo4OS9ceRZXBiOJKA35MzgYAPDgs3MEtc17WdaysQ4GVesv/crmFK+MVIiKiNu3lXw9h95li6E1mdFC6Qm80o0+IGtdF+jq6aU5L5crlFq4WrxAREbVZRpMZB3JKAQCfbz8Ducyysvoj10dCJuMq65dTb/J6jWUokHOsroxXiIiI2qxj5yqkeULW/72+qz8m9tM6sllOzzrHSn/RXoHssboyzrEiIqI2a392KQDAv4MKgGXD5f9OGQgX7gnYoI7ulj0BDSYzCiv00hwrBqsr4xUiIqI2a39WKQDg7kGhuK1/CEJ83BkOGsFT5YouAZ44WVCJlIyS8z1WHAq8IvZYERFRm5VaF6z6hXZEd40XQ1UTDOjkAwDYfrJIeo7X78oYrIiIqE2qNphwPL8CANA/rKNjG9MKWa/Z1hOFAABXuQwqV8aGK+EVIiKiNmnzsQKYzAJatRs0ajdHN6fVsQarE3XhtIObK++kbAQGKyIiapN+2pcDALwD8Cr10HhB4XI+SAXU3QBADWOwIiKiNkdXVYsNR/IBALcNCHFwa1onVxc5ugR0kH5+/paeDmxN68FgRUREbUZl3d1rvxw4C4PJjB4aL/QM9nZwq1qvJ0d1RdfADvh06mCM4obVjcLp/URE1CZ8tzcL81em4eZojTTh+q6YUAe3qnWb1E+LSRxKbRIGKyIiavWyiquw4JeDMJkFfjuQCwDorfXGg8MiHNswanc4FEhERK3ei78cRJXBhK6BHaB0lcNd4YK37u0PJZcHoBbGHisiImrV8nQ10kT19x+IgafKBWYBhHR0d3DLqD1isCIiolZtzcE8AMDATh3RNbDDFaqJmhf7SImIqNUprNCjptayMXBSuiVY3Rwd7MgmEQFgsCIiolYmo6gS17+6Afd+uBP55TXYddqyl924aI2DW0bEYEVERK3M6vQ81NSasT+rFPd9uBNmYbkDMMzXw9FNI2KwIiKi1sU6UR0AThVUQi4D5t/MVcHJOTBYERFRq6GrrkVyRgkAINzP0kP1z/G9cH2UvyObRSThXYFERNRq/HW8ACazQFRgB3z72DCcKarEwE4+jm4WkYTBioiIWgW90YTPtp0BAIzqEQhfTyV8PZWObRTRRZxmKHDRokWQyWSYPXu29JwQAgsWLIBWq4W7uztGjhyJgwcP2rxOr9dj5syZ8Pf3h6enJyZNmoTs7GybmpKSEiQkJECtVkOtViMhIQGlpaU2NZmZmZg4cSI8PT3h7++PWbNmwWAw2NSkpaUhNjYW7u7uCAkJwcsvvwwhhF2vAxER1SeEwLM/HMDejBJ4qVxx/3WdHN0koktyimC1Z88efPjhh+jbt6/N86+99hqWLl2K5cuXY8+ePdBoNIiLi0N5eblUM3v2bKxatQqJiYnYunUrKioqMGHCBJhMJqlm8uTJSE1NRVJSEpKSkpCamoqEhATpuMlkwvjx41FZWYmtW7ciMTERP/74I+bOnSvVlJWVIS4uDlqtFnv27MGyZcuwZMkSLF26tBmvDBERAcAPydn4OfUsXOUyvJ8Qg0h/T0c3iejShIOVl5eLqKgosW7dOhEbGyueeuopIYQQZrNZaDQasXjxYqm2pqZGqNVq8f777wshhCgtLRUKhUIkJiZKNTk5OUIul4ukpCQhhBCHDh0SAMTOnTulmh07dggA4siRI0IIIf744w8hl8tFTk6OVPPNN98IlUoldDqdEEKId999V6jValFTUyPVLFq0SGi1WmE2mxv9eXU6nQAgnZeIiBqWp6sW0S8mifDnfhPvbjzh6OZQO9XY398O77GaPn06xo8fjzFjxtg8f/r0aeTl5SE+Pl56TqVSITY2Ftu3bwcAJCcno7a21qZGq9UiOjpaqtmxYwfUajWGDBki1QwdOhRqtdqmJjo6GlqtVqoZO3Ys9Ho9kpOTpZrY2FioVCqbmrNnz+LMmTOX/Xx6vR5lZWU2DyIiarxPtp1GeY0R/cI6YtoNkY5uDlGDHBqsEhMTkZKSgkWLFtU7lpdn2aIgKCjI5vmgoCDpWF5eHpRKJXx8fBqsCQwMrHf+wMBAm5qL38fHxwdKpbLBGuvP1ppLWbRokTS3S61WIyws7LK1RERU394zluUVHhoWDlcXh/cHEDXIYd/QrKwsPPXUU/jqq6/g5uZ22TqZTGbzsxCi3nMXu7jmUvX2qBF1E9cbas/8+fOh0+mkR1ZWVoNtJyKi8/RGE9KydQDAZRWoVXBYsEpOTkZ+fj5iYmLg6uoKV1dXbN68Ge+88w5cXV0v2xuUn58vHdNoNDAYDCgpKWmw5ty5c/Xev6CgwKbm4vcpKSlBbW1tgzX5+ZbVfy/uybqQSqWCt7e3zYOIiBrn4NkyGExm+HoqpQVBiZyZw4LV6NGjkZaWhtTUVOkxaNAgTJkyBampqejcuTM0Gg3WrVsnvcZgMGDz5s0YPnw4ACAmJgYKhcKmJjc3F+np6VLNsGHDoNPpsHv3bqlm165d0Ol0NjXp6enIzc2VatauXQuVSoWYmBipZsuWLTZLMKxduxZarRYRERH2v0BERISUulXWB3bqeMXRCiJn4LAFQr28vBAdHW3znKenJ/z8/KTnZ8+ejYULFyIqKgpRUVFYuHAhPDw8MHnyZACAWq3GI488grlz58LPzw++vr6YN28e+vTpI02G79mzJ8aNG4dp06bhgw8+AAA8+uijmDBhArp37w4AiI+PR69evZCQkIDXX38dxcXFmDdvHqZNmyb1ME2ePBkvvfQSpk6diueffx7Hjx/HwoUL8cILL/D/7EREzWRfZikAYACHAamVcOqV15999llUV1fjySefRElJCYYMGYK1a9fCy8tLqnnzzTfh6uqKe+65B9XV1Rg9ejQ+++wzuLi4SDUrVqzArFmzpLsHJ02ahOXLl0vHXVxc8Pvvv+PJJ5/EiBEj4O7ujsmTJ2PJkiVSjVqtxrp16zB9+nQMGjQIPj4+mDNnDubMmdMCV4KIqH1KybT2WDFYUesgE4JLh7eksrIyqNVq6HQ6zrciImpAYYUeg/6zHjIZkL5gLDxVTt0XQG1cY39/875VIiJySkdyLbtshPt6MFRRq8FgRURETulInmVB5R4a9u5T68FgRURETulwXY9Vz2AGK2o9GKyIiMgpHc6t67EK9rpCJZHzYLAiIiKnU2sy40R+BQCgF3usqBVhsCIiIqdzqqASBpMZHVSuCOno7ujmEDUagxURETmd8xPXvSCXcxFmaj0YrIiIyOlYJ65zfhW1NgxWRETkdKwT13lHILU2DFZEROR0uIYVtVYMVkRE5FSKKw04V6YHAHTXcCiQWhcGKyIicipH6oYBw/080IFb2VArw2BFRERO5VDu+TsCiVobBisiInIqR/K4lQ21XgxWRETkNGpqTdh1uggAJ65T68TBayIicrjtJwvxw95sFFUakFVcDf8OSgzr7OfoZhE1GYMVERE5lNks8OwPB5BdUg0AkMuAt+8bALWHwsEtI2o6BisiInKoLccLkF1SDS+VKwZH+mJs7yCM6Orv6GYRXRUGKyIicoh1h85h4R+HYRYCAHBnTCgWTOrt4FYRXRsGKyIianFCCCxafRinCyul56YM6eTAFhHZB4MVERG1uJ2ninGqoBIeShd0C/JCv1A1ooK4bhW1fgxWRETU4lbsygAA3D4gBK/c3sfBrSGyH65jRURELWrj0XysTs8DAEwZEu7g1hDZF4MVERG1mKN55Zi+IgUms8DdMaHopeUioNS2MFgREVGLeXfTCVQZTBjexY9DgNQmMVgREVGL0FXVSkOA/7i5B5Su/BVEbQ+/1URE1CJ+Ss2BwWhGD40X+oSoHd0combBYEVERC3i++QsAMB9g8Mgk8kc3Bqi5sFgRUREza5Sb8TBs2UAgFv6BDu4NUTNh8GKiIia3ZG8cggBBHqpEOjt5ujmEDWbawpWJ06cwJo1a1BdbdmRXNTt90RERHShQ7mW3iour0Bt3VUFq6KiIowZMwbdunXDLbfcgtzcXADA3//+d8ydO9euDSQiotbvUN0wYK9gBitq264qWD399NNwdXVFZmYmPDw8pOfvvfdeJCUl2a1xRETUNrDHitqLq9orcO3atVizZg1CQ0Ntno+KikJGRoZdGkZERG2D0WTGkVz2WFH7cFU9VpWVlTY9VVaFhYVQqVTX3CgiImo7zhRVQm80w0Ppggg/T0c3h6hZXVWwuvHGG/HFF19IP8tkMpjNZrz++usYNWqU3RpHREStW4XeiJd/OwzA0lsll3P9Kmrbrmoo8PXXX8fIkSOxd+9eGAwGPPvsszh48CCKi4uxbds2e7eRiIgcyGwWeOWPw+gS0AGTh3Rq0mvnfJuKLccK4K5wwZz4bs3UQiLncVU9Vr169cKBAwdw3XXXIS4uDpWVlbjjjjuwb98+dOnSxd5tJCIiB0rJLMHHW09jwS8HYTCaG/26s6XVWHf4HADgq78PwfAu/s3VRCKncVU9VgCg0Wjw0ksv2bMtRETkhPZn6wAABpMZh3PL0C+sY6NetzIlG0IAQyJ9ERPu04wtJHIeV9Vj9emnn+L777+v9/z333+Pzz///JobRUREziMtu1T68/4L/twQIQR+SM4GANw9KKwZWkXknK4qWC1evBj+/vW7dAMDA7Fw4cJrbhQRETmPAzk66c+pmaWNes3yDSdwpqgKHkoX3BytaaaWETmfqwpWGRkZiIyMrPd8eHg4MjMzr7lRRETkHMpranGqoFL6OTWrtF5Neo4O208USj9/vv0M3lh3DAAwL747PFVXPeuEqNW5qm97YGAgDhw4gIiICJvn9+/fDz8/P3u0i4iInEB6jmVhTx8PBUqqanGqsBK6qlqoPRQAgIyiStzx3nYYjGY8FtsZ9w/uhEWrLcsrzIvvhr9dX/8f4URt2VX1WN13332YNWsWNm7cCJPJBJPJhA0bNuCpp57CfffdZ+82EhGRgxyom1M1tLMfwv0sC0MnZxYDsMyjuvBOwQ82n0Lcm5tRU2vG8C5+mD6qq0PaTORIVxWs/vOf/2DIkCEYPXo03N3d4e7ujvj4eNx0002cY0VE1IZY51f1De2IG6MCAAAfbz0NANh6ohAbjxZA4SLD3Lhu8FK5otYkoHKV45Xb+0Am42Kg1P5c1VCgUqnEt99+i3//+9/Yv38/3N3d0adPH4SHh9u7fURE5EBp2dZgpcbEfsFI3JOJbSeKsPNUEf5IywUA3Ds4DDNHR2HajZ2x+VgBtGp3RPpz6xpqn65pRmG3bt3QrRtX0iUiaotKqwzILK4CAERr1VB7KHDv4DB8tTMT7/x5HBlFlmOjewYBANwULhjbm3cAUvvW6GA1Z84c/Pvf/4anpyfmzJnTYO3SpUuvuWFERORYaXXDgBF+HtJk9SdGdsU3u7Ow/WQRAEDpIseQSF+HtZHI2TQ6WO3btw+1tbUAgJSUlMuOnXNMnYiobThQNwzYJ7Sj9FxIR3fE9wrC6vQ8AMDgSB94KLmcApFVo//fsHHjRunPmzZtao62EBGRE7HeEdg3RG3z/NThEVKwuqFuQjsRWTT5rkCj0QhXV1ekp6c3R3uIiMhJXDhx/ULXRfpiULgPlK5yxPcKckTTiJxWk/tvXV1dER4eDpPJ1BztISIiJ1BQrsdZXQ1kMqD3RT1WMpkMn//tOpTV1CJY7e6gFhI5p6tax+qf//wn5s+fj+LiYnu3h4iIWojJLLB07VGsPZhX71h63cT1LgEd0OESW9J4qlwZqogu4apmHL7zzjs4ceIEtFotwsPD4elpu15JSkqKXRpHRETNZ+ORfLyz4QTcFHL89exNCPBSScesE9cvnl9FRA27qmB12223QSaTQQhh7/YQEVEz+GTraeSV1WBOXDfsOFUEP08lNh8rAADU1JrxweaT+L/xPaU7u60T1/uEMlgRNUWTglVVVRWeeeYZ/PTTT6itrcXo0aOxbNky+Pv7N1f7iIjoGp0prMTLvx0CAKxMyUZhhQEqVzk61q1NBQCfbDuNL3Zm4KnRUXhyZJcLtrJhsCJqiibNsXrxxRfx2WefYfz48bj//vuxfv16PPHEE1f95u+99x769u0Lb29veHt7Y9iwYVi9erV0XAiBBQsWQKvVwt3dHSNHjsTBgwdtzqHX6zFz5kz4+/vD09MTkyZNQnZ2tk1NSUkJEhISoFaroVarkZCQgNLSUpuazMxMTJw4EZ6envD398esWbNgMBhsatLS0hAbGwt3d3eEhITg5ZdfZq8dETm9b3ZnSn8urLD8vaY3mnGuTA9XuQz9wzrCLACD0YzPt59BXlkNCsr1cJHL0CuYwYqoKZoUrFauXImPP/4YH374Id5++238/vvv+Omnn676DsHQ0FAsXrwYe/fuxd69e3HTTTfh1ltvlcLTa6+9hqVLl2L58uXYs2cPNBoN4uLiUF5eLp1j9uzZWLVqFRITE7F161ZUVFRgwoQJNm2aPHkyUlNTkZSUhKSkJKSmpiIhIUE6bjKZMH78eFRWVmLr1q1ITEzEjz/+iLlz50o1ZWVliIuLg1arxZ49e7Bs2TIsWbKEq8wTORkhBOZ9vx/TvtgLg9Hs6OY4nN5owvfJln9sPjuuOx4eEYHnxvWQjseE++Crvw/BD48Pg5tCjvxyPVam5AAAogI7wF3p4pB2E7VaogkUCoXIzs62ec7NzU1kZmY25TQN8vHxER999JEwm81Co9GIxYsXS8dqamqEWq0W77//vhBCiNLSUqFQKERiYqJUk5OTI+RyuUhKShJCCHHo0CEBQOzcuVOq2bFjhwAgjhw5IoQQ4o8//hByuVzk5ORINd98841QqVRCp9MJIYR49913hVqtFjU1NVLNokWLhFarFWazudGfT6fTCQDSeYnIvlalZIvw534T4c/9Jr7Yflp6/pyuWkxa9pcY/84WseCXdFFQXlPvtesP5YkJ7/wl0nNKW7DFV3a2tEqUVhma/LriCr2Y8XWKCH/uNzHklfWi1mgSQghhNpvFLW9vEeHP/Sbe3XhCqn/go50i/LnfRJ8Xk0T4c7+JZ7/fb7fPQNTaNfb3d5N6rEwmE5RKpc1zrq6uMBqN1xzwTCYTEhMTUVlZiWHDhuH06dPIy8tDfHy8VKNSqRAbG4vt27cDAJKTk1FbW2tTo9VqER0dLdXs2LEDarUaQ4YMkWqGDh0KtVptUxMdHQ2tVivVjB07Fnq9HsnJyVJNbGwsVCqVTc3Zs2dx5syZy34uvV6PsrIymwcRNY8qgxGLVx+Rfn77zxO494MdmP51Cv6xMg37s3VIzynDp9vOIP7NLdh4JF+q1VXX4tkfDiAtR4cla446ovmXtPdMMW58bSOue2U95q88gAp9w3/fJqXn4W+f7cG/fkpH7Osb8ev+s5DLgLnx3eDqYvkrXyaT4b+TB+LpMd0wdXiE9Nrru1rmy5bVWN5j8pBOzfOhiNqwJk1eF0Jg6tSpNuGipqYGjz/+uM2SCytXrmz0OdPS0jBs2DDU1NSgQ4cOWLVqFXr16iWFnqAg21V9g4KCkJGRAQDIy8uDUqmEj49PvZq8vDypJjAwsN77BgYG2tRc/D4+Pj5QKpU2NREREfXex3osMjLykp9v0aJFeOmll654HYjo2r2/6STyymoQ6uMOIYCc0moUVuil465yGV6c1BsrdmbgSF45/v7FXswY1RUGkxmHc8tQVGmZf7TxaAFOF1Yi0t/zcm/VImpNZjy/Kg21JgFA4JvdWTiRX4HPHr4OnpdYW6qwQo9nvt+P8gvCVw+NFxbf2Rf9wzra1Eb4e+KpMVE2z10f5Q/UTXON7RaAfhe9hoiurEnB6qGHHqr33AMPPHBNDejevTtSU1NRWlqKH3/8EQ899BA2b94sHb94U2chxBU3er645lL19qgRdRPXG2rP/PnzMWfOHOnnsrIyhIWFNdh+Imq6rOIqfLDlFADgn+N7QuXqghd/OYgbu/ljw+F8nNXV4MlRXZEwNBz3DgrDcz8ewKp9OXj7z+M25wn380BGURU+3HIKC2+PdujG8p9tO4Nj5yrg66nEwtv74Jkf9mPPmRI8sSIFn04dDBe5bdveWHsU5XojogI7YGhnP/QNVeOOgaH16i6np8YbIR3dcVZXjVmjo678AiKqp0nB6tNPP7V7A5RKJbp27QoAGDRoEPbs2YO3334bzz33HABLb1BwcLBUn5+fL/UUaTQaGAwGlJSU2PRa5efnY/jw4VLNuXPn6r1vQUGBzXl27dplc7ykpAS1tbU2NdbeqwvfB6jfq3YhlUpl08NHRM3j9TVHoTeaMayzH8b21kAmk2FUD0tvtS6+FgfP6jCsix8AQOkqxxt390Ow2g1pOTpE+nuiptaEXsHeiPD3xNRP9+Cb3Zk4nFuGLx+5Dl5uiobeulmYzQKfbT8DAHh2bHeMi9ZAo3bD/R/uxJZjBXh9zVH84+bzk9DTc3RI3JMFAFh4Rx8MjvBt8nvK5TJ89fchKK7UIybc58ovIKJ6rmpLm+YkhIBer0dkZCQ0Gg3WrVsnHTMYDNi8ebMUmmJiYqBQKGxqcnNzkZ6eLtUMGzYMOp0Ou3fvlmp27doFnU5nU5Oeno7c3FypZu3atVCpVIiJiZFqtmzZYrMEw9q1a6HVausNERJRy6qpNSGpbluW52/pWa+XSe2hwPCu/jbPy+UyPDuuB758ZAhevjUar93VD1NHRCK2WwCeGdsdnkoXpGaV4qd9OS36Wax2nCpCTmk1vNxccduAEABA/7COePWuvgCA9zefxNzv9qPKYIQQAi//eghCABP7aa8qVFlF+nsiJvzqX0/U3l3Vyuv28vzzz+Pmm29GWFgYysvLkZiYiE2bNiEpKQkymQyzZ8/GwoULERUVhaioKCxcuBAeHh6YPHkyAECtVuORRx7B3Llz4efnB19fX8ybNw99+vTBmDFjAAA9e/bEuHHjMG3aNHzwwQcAgEcffRQTJkxA9+7dAQDx8fHo1asXEhIS8Prrr6O4uBjz5s3DtGnT4O3tDcCyZMNLL72EqVOn4vnnn8fx48excOFCvPDCCw4dKiAiYPfpYhiMZgSr3RAd4n1N55LJZJg+qisq9Ua8u+kkDuU65oaT7/daep8m9dPCTXF+yYNJ/bTI01Vj8eoj+DElG7pqA26ODsbuM8VwU8gx/4JeLCJqeQ4NVufOnUNCQgJyc3OhVqvRt29fJCUlIS4uDgDw7LPPorq6Gk8++SRKSkowZMgQrF27Fl5eXtI53nzzTbi6uuKee+5BdXU1Ro8ejc8++wwuLuf/IlqxYgVmzZol3T04adIkLF++XDru4uKC33//HU8++SRGjBgBd3d3TJ48GUuWLJFq1Go11q1bh+nTp2PQoEHw8fHBnDlzbOZPEZFj/HXcsjXLDVH+dvuHTm+tZWHMg2dbLlgJIWAWwNnSaqxOt/TA3T2o/pzMR2/sgugQNaZ+sgfrD+dj/WHLtIQnYrtC25EbIxM5kkwILh3eksrKyqBWq6HT6aTeMCK6NuPe2oIjeeV45/4BmNRPe+UXNMLpwkqMWrIJSlc5Dr00VlqqoDkIIfDL/rN4Y+0x1NSaoHZX4Hh+BWLCffDD48MuGxY/23YaC361bFVzW38tltzdr1nbSdSeNfb3t0N7rIiIrlV+WQ2O5Fl2YxhRNzndHsJ9PeCpdEGlwYSTBZXorvG68ouu0s+pZzH721Tp5/xyPbzdXPH2ff0b7IF7aHgEKg0mCCHwxMiujb77j4iaD4MVEbVqW44XAgB6a73h18F+d+DK5TL0DPbG3owSHMrVNVuwEkLgo62WZSLuvy4M4X6eWJ2Wi3ljuyPUx6PB11rngxGR82CwIqJWbcMRy3IqN/WovxDwteqtrQtWZ8tw+wC7nx4AcKBuNXilqxzPjO0BX08lHo/t0jxvRkTNjoPxRNRqGYxm/HXM0mPVPMHKMoF9f5bO7ue2+mqnZSeJ8X2C4eupvEI1ETk7BisiarX2nilGud4IP08l+oV2tPv5h3a2zNnak1GMXF213c+vq6rFrwfOAgAeGMp9+YjaAgYrImqVzpXV4JNtpwEAo3oEQt4ME7c7+XngughfCAGsaoaFQn9MyUZNrRk9NF4Y2IkrnRO1BQxWRNTq5OlqMO6tLdL6TfZaYuFS7oyxrHr+Y3I27Lk6jRACK3ZZhgGnDA3nQsNEbQSDFRG1Ool7MlFSVYsIPw98/NAg3NgtoNne65Y+wXBTyHGyoNKui4X+dbwQJwsq4al0we11W9YQUevHYEVErYrJLPBd3WbDT8d1w+iel98E3R683BQY0cUfALD9ZKFdzimEwBtrjwIA7hkchg4q3qBN1FYwWBFRq7LleAHO6mrQ0UOBsb01LfKew+oWHt1xsuiaz2U0mfHVrkzsz9bBQ+nCdaiI2hj+M4mIWo2Mokr838o0AMDtA0JsNiduTtLdgWdKYDSZr3rbmOJKA+5+fztOFlQCAB65PhL+dlzUlIgcjz1WRNQq1JrMSPh4N87qatA5wLNFe3p6BXtD7a5Ahd6ItJz6a1o1dlL7m+uO4WRBJdTuCjxyfSR7q4jaIAYrImoV9p4pQWZxFTp6KJD46NAW7emRy2UYEukLANhxynY48L8bT6D3i2uQmlXa4DmO5pVLdwG+/0AM/jWhV4v1uBFRy2GwIqJWYdMxy9IKo7oHItDLrcXf/1LzrI6fK8eb646hymDCD8lZl31tVnEV/v7FHpgFMK63RjoXEbU9DFZE1CpsPloAABjZvfmWVmiINQztPVMCg9EMk1ngxV8Owmi2DANuO3Hpie21JjMe+HgXsoqrEe7ngQWTerdYm4mo5XHyOhE5tfWHzmHzsQIcySuHXAbcGOWYYNUt0As+HgqUVNVib0YxVuzMxPaTRVC6ymEyC5wurER2SRVCfTxsXpeSUYKMIssQ5nePDUOQd8v3thFRy2GwIiKntf1EIR79ci/qOoXQL6wjfBy0UbFcLsPQzn5YnZ6HmV/vQ1GlAQoXGd6+tz/+99cppGSWYtLybegZ7IU37+2PA1k6ZJdUIa9MDwAY2S2AoYqoHWCwIiKnlJxRjJnf7INZAOF+Higs1+OhYREObdOwLpZgVVRpAAC8OyUGcb2CcDi3DCmZpSiuNGDbiSK88NNBbDiSD4PJDDeFZcbFyO6Bjmw6EbUQBisicjrvbjqB15IsK5P3CvbGyieHO8UddMM6n590fseAEMT1sqz6PqpHIN7ZcAJyGWAWQNLBPKmuptYMmQy4Icq/xdtLRC2Pk9eJyKlU6o1Y9ucJAMDdMaFY8fchThGqAKBrYAf0C+uIUB93PD++p/T8gE4++Pxv12HD3JHoF9ZRer6jhwIA0DdEDT8uBErULjBYEZFTSUrPQ3WtCZH+nnjtrr4Om1N1KTKZDD89ORwb542st45WbLcARPh7Ym5cN8hlwK39tXj9rn7wVLrggaHhDmoxEbU0DgUSkcMZTWbojWZ4qlyxcl82AMtQm0wmc3DL6pPJZFC4XL5dN3YLwI75o+HrqYTCRY70l8Y65ecgoubBYEVEDrXpaD7mfLcfxZUGqN0V0FXXAgBuGxDi4JZdvQvv/mOoImpfGKyIyGF+P5CLGd+kwLrVnjVUxfcKQpivRwOvJCJyTgxWROQQFXojFvx6EEIAdw4MxfxbeqCk0gA3hQtCOro7unlERFeFwYqIHOK9TSdQUK5HhJ8HFt3RB0pXeYturExE1BwYrIioWQghkKurwbYThThXVoOHhkfAy82y/MDPqTl4b9NJAMDzt/SE0pU3KBNR28BgRUTXbM+ZYuTqajC+TzBc5DKsOZiH/1uVhsIKg1Szcl8OQjq640C2TppLdc+gUGmRTSKitoDBiqidq9Ab4eYqh6tL03uNhBB4588TeOvPYxAC+HjracyJ64Z53+1Hud4IF7kMvbXeyC/T41RBJU4VVAIAZDLgoWEReGFCL941R0RtCoMVUTu25VgBnvgqGaE+Hvj2saHo6NG0xTh/SM7Gm+uPAQBUrnLszyrFQ5/sBmDZMPnbR4fCTeGCwgo9lm84gQAvFUZ1D0Sorzu864YFiYjaEk5sIGqntp0oxN+/2ItKgwlHz5Xj0S+SUW0wNfr1JrPAu3XzpGaNjsKWZ0dhXG8NAEDhIsOrd/aRtqLx76DCgkm9MX1UV/TSejNUEVGbxR4ronYop7Qa079OgcFoxg1R/kjNLMXuM8W4+4PteGZsD2SXVGH7ySKM6OKP+waHQS6vP1yXlJ6H04WVULsr8NiNneGpcsX7CTHYfboY7goX9NB4O+CTERE5FoMVUTtjMgvM+DoFpVW16BuqxkcPDUJatg6PfpmM9JwyaSgPsCzguWpfNj57+Dp4qs7/dZGnq8HCPw4DAKYOj7A5dl2kb8t9GCIiJ8NgRdTO/JicjX2ZpfByc8V/Jw+EytUFgyJ88fP0EVi0+jBO5FdA6SrH4AhffL83G3vOlGDG1ymI8PcEAIT6eOCrnRnIKa1GhJ8H/nZ9pIM/ERGR82CwImpHqgxGvLHuKADgqdFRNtvGhPl64N0pMTb1E/pqcf+HO7HxaAFwtMDmmMbbDV8+MgRqd86XIiKyYrAiakc+3XYG58r0CPN1R8Kw8CvWx4T7YMk9/fDq6iO4LtIXnioXZBVXY1gXP9w5MBQBXlwpnYjoQgxWRO1Epd6Ij/46BQCYE9cNKleXRr1uUj8tJvXTNmfTiIjaDC63QNROfLUzAyVVtYjw88DEvgxKRETNgcGKqB0oKNfj/c2WNaeeHNX1qlZZJyKiK+PfrkRtnNFkxvyVB1BSVYseGi/cPiDE0U0iImqzOMeKqA37cmcG3lh7FKVVtVC6yPHWff2hYG8VEVGzYbAiaqP2nCnGCz+nQwhA7a7ACxN6cTV0IqJmxmBF1AaU1dTip305GNU9EGeKKrFqXw62nSiEEMAdA0Lw2l19Oa+KiKgFMFgRtQH/tyodv+4/C1f5IRjNQno+pKM7Ftzam6GKiKiFMFgRtXIZRZX4/cBZAIDRLCCXAfdf1wn9QjsivncQvN24MjoRUUthsCJqZcxmga92ZWDnqSJ09FDiZH4FzAIY2T0AM2+KgrebK6KCvBzdTCKidonBiqgVqTaY8PhXydh8rKDesSdHdkVMuI8DWkVERFYMVkStyPubT2LzsQK4KeR49IbOgEyGwgo9ogI7YHAEQxURkaMxWBG1EgXlemmvvyV398MEbktDROR0eKsQUSsghMDi1UdQaTChX6ga4/sEO7pJRER0CQxWRK3Am+uO4ceUbMhkwD9u7gmZTOboJhER0SVwKJDICdWazNKq6V0DO+CdDScAAC/fGo1hXfwc3DoiIrocBisiJ7R49RF8szvL5rmnRkchYWi4g1pERESNwWBF5CSEEJjz3X6sO3QOFXojAMC/gxKFFQZM7KfF7DFRDm4hERFdCYMVkZP483A+Vu3LAQDIZMDMm6LwtxERSM4owY3dAjivioioFXDo5PVFixZh8ODB8PLyQmBgIG677TYcPXrUpkYIgQULFkCr1cLd3R0jR47EwYMHbWr0ej1mzpwJf39/eHp6YtKkScjOzrapKSkpQUJCAtRqNdRqNRISElBaWmpTk5mZiYkTJ8LT0xP+/v6YNWsWDAaDTU1aWhpiY2Ph7u6OkJAQvPzyyxBCgOhaGE1mvJp0BAAwdXgEdj8/BnPiuqGjhxKjewZBwb3+iIhaBYf+bb1582ZMnz4dO3fuxLp162A0GhEfH4/Kykqp5rXXXsPSpUuxfPly7NmzBxqNBnFxcSgvL5dqZs+ejVWrViExMRFbt25FRUUFJkyYAJPJJNVMnjwZqampSEpKQlJSElJTU5GQkCAdN5lMGD9+PCorK7F161YkJibixx9/xNy5c6WasrIyxMXFQavVYs+ePVi2bBmWLFmCpUuXNvOVorZuxa5MHM+vQEcPBZ6O64YAL5Wjm0RERFdDOJH8/HwBQGzevFkIIYTZbBYajUYsXrxYqqmpqRFqtVq8//77QgghSktLhUKhEImJiVJNTk6OkMvlIikpSQghxKFDhwQAsXPnTqlmx44dAoA4cuSIEEKIP/74Q8jlcpGTkyPVfPPNN0KlUgmdTieEEOLdd98VarVa1NTUSDWLFi0SWq1WmM3mRn1GnU4nAEjnJMosqhQ9/7VahD/3m/h8+2lHN4eIiC6hsb+/nWp8QafTAQB8fX0BAKdPn0ZeXh7i4+OlGpVKhdjYWGzfvh0AkJycjNraWpsarVaL6OhoqWbHjh1Qq9UYMmSIVDN06FCo1WqbmujoaGi151ezHjt2LPR6PZKTk6Wa2NhYqFQqm5qzZ8/izJkzl/xMer0eZWVlNg8iKyEEnl+VhiqDCddF+OKBIbzrj4ioNXOaYCWEwJw5c3D99dcjOjoaAJCXlwcACAoKsqkNCgqSjuXl5UGpVMLHx6fBmsDAwHrvGRgYaFNz8fv4+PhAqVQ2WGP92VpzsUWLFknzutRqNcLCwq5wJag9+X5vNv46XgiVqxyL7+wDuZwT1ImIWjOnCVYzZszAgQMH8M0339Q7dvHdUEKIK94hdXHNpertUSPqJq5frj3z58+HTqeTHllZWZeso/ansEKPf/9+CAAwJ64bOgd0cHCLiIjoWjlFsJo5cyZ++eUXbNy4EaGhodLzGo0GQP3eoPz8fKmnSKPRwGAwoKSkpMGac+fO1XvfgoICm5qL36ekpAS1tbUN1uTn5wOo36tmpVKp4O3tbfMgAoAvd2SgvMaI3lpvPHJ9pKObQ0REduDQYCWEwIwZM7By5Ups2LABkZG2v1wiIyOh0Wiwbt066TmDwYDNmzdj+PDhAICYmBgoFAqbmtzcXKSnp0s1w4YNg06nw+7du6WaXbt2QafT2dSkp6cjNzdXqlm7di1UKhViYmKkmi1bttgswbB27VpotVpERETY6apQe1BTa8KKXRkAgCdGdoErl1MgImobmnkSfYOeeOIJoVarxaZNm0Rubq70qKqqkmoWL14s1Gq1WLlypUhLSxP333+/CA4OFmVlZVLN448/LkJDQ8X69etFSkqKuOmmm0S/fv2E0WiUasaNGyf69u0rduzYIXbs2CH69OkjJkyYIB03Go0iOjpajB49WqSkpIj169eL0NBQMWPGDKmmtLRUBAUFifvvv1+kpaWJlStXCm9vb7FkyZJGf2beFUhCCPHdnkwR/txvYujC9cJgNDm6OUREdAWN/f3t0GAF4JKPTz/9VKoxm83ixRdfFBqNRqhUKnHjjTeKtLQ0m/NUV1eLGTNmCF9fX+Hu7i4mTJggMjMzbWqKiorElClThJeXl/Dy8hJTpkwRJSUlNjUZGRli/Pjxwt3dXfj6+ooZM2bYLK0ghBAHDhwQN9xwg1CpVEKj0YgFCxY0eqkFIRisSAijySxuWrJRhD/3m/jvxuOObg4RETVCY39/y4TgsuEtqaysDGq1GjqdjvOt2qmf9uVg9repULsr8Ndzo+DtpnB0k4iI6Aoa+/ubEzuIWpDJLPD2n8cBAI/e2JmhioiojWGwImpBm47m43RhJTp6KPDQ8AhHN4eIiOyMwYqoBSXusaxjdufAUHRQuTq4NUREZG8MVkQtJL+sBhuOWNY9u/86rsBPRNQWMVgRtZAfU3JgMgsMCvdB10AvRzeHiIiaAYMVUQtJSrcsPntnTOgVKomIqLVisCJqAbm6auzP1kEmA8b0vPT2R0RE1PoxWBG1gPWHLHtVDuzkgwAvlYNbQ0REzYXBiqgFrK0LVvG92FtFRNSWMVgRNbPDuWXYfrIIABDHYEVE1KYxWBE1I5NZYP7KNJjMAuN6a9A5oIOjm0RERM2IKxQS2VlNrQkfbz2No3nlSM4oQU5pNTqoXLFgUm9HN42IiJoZgxWRHZnNAk9/m4rV6XnSc55KFyy+sw80ajcHtoyIiFoCgxWRHb265ghWp+dB6SLHU2Oi0D3IC9dH+cNN4eLophERUQtgsCKyk7UH8/DB5lMAgNfv7otb+4c4uEVERNTSGKyIrpEQAnszSjD3+/0AgEeuj2SoIiJqpxisiK6C2Szw8/4cvLX+OArK9ag1mVFrErguwhf/uLmHo5tHREQOwmBF1ERCCPzfT2n4ZneWzfPjemvw5r39oXDhKiZERO0VgxVRE7225ii+2Z0FuQyYE9cNY3trYDCZ0VPjDblc5ujmERGRAzFYETXBxiP5eG/TSQDAojv64N7BnRzcIiIiciYcsyBqpDxdDZ754QAA4OEREQxVRERUD4MVUSMcyC7F7e9uQ2GFHlGBHfDcOE5QJyKi+jgUSNSAmloTnl+ZhlWpORAC6BLgiU+mDuaCn0REdEkMVkQNeOnXg1i5LwcAMLGfFv+5NRpqD4WDW0VERM6KwYroEowmMz7eehrf7M6CTAZ8MnUwRnUPdHSziIjIyTFYUbtVqTfCTeEClwuWSMgoqsQHW07hr+MFyCquBgDMHNWVoYqIiBqFwYrapc3HCjDti73w91RiXHQwPFUucFe64IPNp6CrrgUAqN0VmBvfDQ8MCXdwa4mIqLVgsKJ2J7ukCk8l7oPBaMZZXQ0+2Xba5ni/sI6YOaorhnT2hZcb51MREVHjMVhRu1KpN+KxL5NRWlWLvqFqTB0egfScMtSazCis0KNzgCdm3hTFu/6IiOiqMFhRu1ChN2LjkXx8vSsTB8+Wwc9Tif9OHogwXw/cMdDRrSMioraCwYraNCEEPt56Gss2nJDmTqlc5fjooUEI8/VwcOuIiKitYbCiNu3jrafxn98PAwDC/TxwY1QA7ooJRb+wjo5tGBERtUkMVtRmbThyDq/8YQlV8+K74YmRXW2WViAiIrI3Bitqk7KKq/D0t/shBDB5SCdMH9UVMhlDFRERNS9uwkxtjtFkxsxv9kFXXYt+YR2xYGJvhioiImoRDFbU5ry36SRSs0rh5eaK5fcPgNKVX3MiImoZ/I1DbcqRvDK8/edxAMDLt/bmnX9ERNSiGKyoTXl7/XEYzQJxvYJwW/8QRzeHiIjaGQYrajNO5Jcj6WAeAGBefHfOqyIiohbHYEVtxlvrj0MIYGzvIHTXeDm6OURE1A4xWFGb8N3eLPx2IBcyGTDzpihHN4eIiNopBitq9U7kl+NfP6UDAOaM6YboELWDW0RERO0VgxW1amazwD9+TIPeaMYNUf6YPqqro5tERETtGFdep1braF45/vfXKezNKIGH0gWL7+wLObesISIiB2Kwolbp4Fkdbv/vdhhMZgDAP27ugZCO7g5uFRERtXcMVtTqmMwCz69Mg8FkRky4D2bc1BWjugc6ullEREQMVtT6LNtwHPuzdfByc8V7UwYi0NvN0U0iIiICwMnr1Mq8t+kk3lpv2bLm/27pyVBFREROhcGKWo2k9Dy8mnQEADAvvhvuu66Tg1tERERki8GKWoWMoko88/1+AMDfRkRiBhcBJSIiJ8RgRU5PCIH5K9NQrjdicIQP5t/Sw9FNIiIiuiQGK3J6P6XmYPvJIqhc5Xjj7v5QuPBrS0REzom/ociplVYZ8J/fDgMAZo2OQic/Dwe3iIiI6PIYrMhpmMwCpwoqIISQnns16SiKKg2ICuyAaTd0dmDriIiIrozrWJFTyNPV4MkVyUjJLMXQzr5IGBqB1KwSfLM7EwDwyu19oHTlvwOIiMi5MVhRixFCoKSqFqcLK3H8XDk0ajccO1eOxN1ZOF1UCWtH1c5Txdh5qlh63d9GROK6SF8HtZqIiKjxHNoFsGXLFkycOBFarRYymQw//fSTzXEhBBYsWACtVgt3d3eMHDkSBw8etKnR6/WYOXMm/P394enpiUmTJiE7O9umpqSkBAkJCVCr1VCr1UhISEBpaalNTWZmJiZOnAhPT0/4+/tj1qxZMBgMNjVpaWmIjY2Fu7s7QkJC8PLLL9sMW1F9pVUGbDtRiMWrj2Dgv9dh4L/X4c73tuMfK9Mw9dM9WPjHEZwqtISqPiFqfD1tCO4dFIbBET4Y3sUPnz48GC9M7OXoj0FERNQoDu2xqqysRL9+/fDwww/jzjvvrHf8tddew9KlS/HZZ5+hW7du+M9//oO4uDgcPXoUXl5eAIDZs2fj119/RWJiIvz8/DB37lxMmDABycnJcHFxAQBMnjwZ2dnZSEpKAgA8+uijSEhIwK+//goAMJlMGD9+PAICArB161YUFRXhoYceghACy5YtAwCUlZUhLi4Oo0aNwp49e3Ds2DFMnToVnp6emDt3bktcrlZFCIEVuzLxn98PoabWbHMs0EuFbkFeyCmthspVjr9dH4mbegTCv4MKADC8i78jmkxERHTthJMAIFatWiX9bDabhUajEYsXL5aeq6mpEWq1Wrz//vtCCCFKS0uFQqEQiYmJUk1OTo6Qy+UiKSlJCCHEoUOHBACxc+dOqWbHjh0CgDhy5IgQQog//vhDyOVykZOTI9V88803QqVSCZ1OJ4QQ4t133xVqtVrU1NRINYsWLRJarVaYzeZGf06dTicASOdti46fKxP3f7hDhD/3mwh/7jdx/at/ike/2CPWHswTNbVGRzePiIioyRr7+9tpZwOfPn0aeXl5iI+Pl55TqVSIjY3F9u3bAQDJycmora21qdFqtYiOjpZqduzYAbVajSFDhkg1Q4cOhVqttqmJjo6GVquVasaOHQu9Xo/k5GSpJjY2FiqVyqbm7NmzOHPmzGU/h16vR1lZmc2jLUvJLMGty7dJ6079c3xPbJ43Ch8kDEJcryCoXF0c3UQiIqJm47TBKi8vDwAQFBRk83xQUJB0LC8vD0qlEj4+Pg3WBAYG1jt/YGCgTc3F7+Pj4wOlUtlgjfVna82lLFq0SJrbpVarERYW1vAHb8WSM0ow9ZPdqDSYcF2kL9bPicXfb+gMuVzm6KYRERG1CKcNVlYyme0vZSFEvecudnHNpertUSPqJq431J758+dDp9NJj6ysrAbb3hqV19Tig80ncf+HO1FWY8SgcB989vBghPlyMU8iImpfnHa5BY1GA8DSGxQcHCw9n5+fL/UUaTQaGAwGlJSU2PRa5efnY/jw4VLNuXPn6p2/oKDA5jy7du2yOV5SUoLa2lqbmot7pvLz8wHU71W7kEqlshk+bCsyi6pQXWvCnjPFeHX1EZTrjQCAm6M1WHJ3P3gonfarRURE1GyctscqMjISGo0G69atk54zGAzYvHmzFJpiYmKgUChsanJzc5Geni7VDBs2DDqdDrt375Zqdu3aBZ1OZ1OTnp6O3NxcqWbt2rVQqVSIiYmRarZs2WKzBMPatWuh1WoRERFh/wvghExmgZ2nivDEV8m48fWNGPvWFvzzp3SU643oEuCJRXf0wX8nD4SniqGKiIjaJ4f+BqyoqMCJEyekn0+fPo3U1FT4+vqiU6dOmD17NhYuXIioqChERUVh4cKF8PDwwOTJkwEAarUajzzyCObOnQs/Pz/4+vpi3rx56NOnD8aMGQMA6NmzJ8aNG4dp06bhgw8+AGBZbmHChAno3r07ACA+Ph69evVCQkICXn/9dRQXF2PevHmYNm0avL29AViWbHjppZcwdepUPP/88zh+/DgWLlyIF1544YpDk61dZlEVPvzrJJLSz6GwQg8AkMmADipXyGUyPDU6Cg8Nj4AL51IREVF71/w3KF7exo0bBYB6j4ceekgIYVly4cUXXxQajUaoVCpx4403irS0NJtzVFdXixkzZghfX1/h7u4uJkyYIDIzM21qioqKxJQpU4SXl5fw8vISU6ZMESUlJTY1GRkZYvz48cLd3V34+vqKGTNm2CytIIQQBw4cEDfccINQqVRCo9GIBQsWNGmpBSFa33ILH/11SnT7vz+kpRP6Llgj5n2XKo7mlQkhRJM/PxERUWvU2N/fMiG4dHhLKisrg1qthk6nk3rDnFXi7kz8Y2UaAGB4Fz88FtsFw7v4QeHitCPIREREzaKxv785GYYuKSWzBP/8KR0AMPOmrpgT163ND3kSERFdK3Y9UD1ms8CLPx+E0Swwvm8wQxUREVEjMVhRPV/vzkRajg5eKle8NKk3QxUREVEjcSiwnTObBVan52HriUKcKaxElcGI/dk6AMDM0V2ljZGJiIjoyhis2rET+eV4fmU6dp8ptnneVS7DA0PD8fCISAe1jIiIqHVisGqHampNeHfjCby3+SRqTQLuChdMGdIJvUO8IZfJMLCTD7ejISIiugoMVm1Yhd6I5344gI1H8zG8iz86B3iiUm/EX8cLkVlcBQC4qUcgXr61N0J9GKSIiIiuFYNVG7U/qxTzvt+P4/kVAID1h88Bh88fD/RS4aVJvTEuWsPJ6URERHbCYOVEdFW1kMkBL5XrVYcdIQTe3XQSS9YehRCWALVgUm+cKapEaVUtFC4ydA3sgDE9g+DlprDzJyAiImrfGKwc7ER+BZLSc7H20DkcqLsbT+2uwOAIH+iNZrgpXBAT7oPBET7oGewNd4ULCir0yCquRk2tCV0COiDIWwWjWSA1qxQrU3Lwze5MAMBt/bX414Re8OOdfURERC2CW9q0MOuS+E9/uR25VTLsOFXUpNcrXeQwmMw2z3m5ucJkFqgymKTn/jm+J/5+Q2e7tJmIiKi945Y2Tu6H5GzIVR6Qy4AbuwVgXG8NRvcMgpebKw7nlmFfZik6uLmirLoWe84UIzmjBIUVBhhMZshkQLC3G9wULsgorkJ5jREA4OupxLDOfrh9QAjG9Apy8CckIiJqf9hj1cKsiXfxTynw8fHGLX2CG31Hnq66FmXVtQjydoPS1bJovt5owplCyx1+UYEdIJdzIjoREZG9NbbHisGqhTX2PwwRERE5j8b+/uZegURERER2wmBFREREZCcMVkRERER2wmBFREREZCcMVkRERER2wmBFREREZCcMVkRERER2wmBFREREZCcMVkRERER2wmBFREREZCcMVkRERER2wmBFREREZCcMVkRERER2wmBFREREZCeujm5AeyOEAACUlZU5uCVERETUWNbf29bf45fDYNXCysvLAQBhYWEObgkRERE1VXl5OdRq9WWPy8SVohfZldlsRrdu3ZCcnAyZTHbV5xk8eDD27NlzTW1xlnOUlZUhLCwMWVlZ8Pb2dmhbnOUc9jhPW7uuztIWZ7qu9jqPM5zDXtfVHm1pa+dwpu+ss5zjas4jhEB5eTm0Wi3k8svPpGKPVQuTy+VQKpUNpt3GcHFxuea/fJzlHFbe3t7XdC5n+Tz2uib2Ok9bua7O1hZnuK72Oo+znAO49utqr7a0pXNYOcN31lnOcbXnaczvbk5ed4Dp06fzHM3AWT6Pva6Js1zbtnZN2tJ1tdd5nOUc9uIsn8dZzmEvzvJ5nOn/O5fCoUByuLKyMqjVauh0Orv9y4x4XZsLr2vz4HVtPry2LYs9VuRwKpUKL774IlQqlaOb0qbwujYPXtfmwevafHhtWxZ7rIiIiIjshD1WRERERHbCYEVERERkJwxWRERERHbCYEVERERkJwxWdM22bNmCiRMnQqvVQiaT4aeffrI5fu7cOUydOhVarRYeHh4YN24cjh8/blNz8uRJ3H777QgICIC3tzfuuecenDt3zqYmJSUFcXFx6NixI/z8/PDoo4+ioqKiuT+ewyxatAiDBw+Gl5cXAgMDcdttt+Ho0aM2NUIILFiwAFqtFu7u7hg5ciQOHjxoU6PX6zFz5kz4+/vD09MTkyZNQnZ29iXfU6/Xo3///pDJZEhNTW2uj+ZQLXld+Z29umv74YcfYuTIkfD29oZMJkNpaell35PfWQt7Xdf29p1tDgxWdM0qKyvRr18/LF++vN4xIQRuu+02nDp1Cj///DP27duH8PBwjBkzBpWVldLr4+PjIZPJsGHDBmzbtg0GgwETJ06E2WwGAJw9exZjxoxB165dsWvXLiQlJeHgwYOYOnVqS37UFrV582ZMnz4dO3fuxLp162A0GhEfHy9dNwB47bXXsHTpUixfvhx79uyBRqNBXFyctCclAMyePRurVq1CYmIitm7dioqKCkyYMAEmk6neez777LPQarUt8vkcpaWuK7+zV39tq6qqMG7cODz//PNXfE9+Zy3scV3b43e2WQgiOwIgVq1aJf189OhRAUCkp6dLzxmNRuHr6yv+97//CSGEWLNmjZDL5UKn00k1xcXFAoBYt26dEEKIDz74QAQGBgqTySTV7Nu3TwAQx48fb+ZP5Rzy8/MFALF582YhhBBms1loNBqxePFiqaampkao1Wrx/vvvCyGEKC0tFQqFQiQmJko1OTk5Qi6Xi6SkJJvz//HHH6JHjx7i4MGDAoDYt29f838oJ9Bc15Xf2au7thfauHGjACBKSkoueX5+Z+17XfmdtQ/2WFGz0uv1AAA3NzfpORcXFyiVSmzdulWqkclkNovXubm5QS6X29QolUqbjS/d3d0BQKpp63Q6HQDA19cXAHD69Gnk5eUhPj5eqlGpVIiNjcX27dsBAMnJyaitrbWp0Wq1iI6OlmoAy3DttGnT8OWXX8LDw6MlPo7TaK7ryu/s1V3bxuJ31v7Xld9Z+2CwombVo0cPhIeHY/78+SgpKYHBYMDixYuRl5eH3NxcAMDQoUPh6emJ5557DlVVVaisrMQzzzwDs9ks1dx0003Iy8vD66+/DoPBgJKSEqk721rTlgkhMGfOHFx//fWIjo4GAOTl5QEAgoKCbGqDgoKkY3l5eVAqlfDx8blsjRACU6dOxeOPP45BgwY190dxKs15Xfmdvbpr29hz8ztr/+va3r+z9sJgRc1KoVDgxx9/xLFjx+Dr6wsPDw9s2rQJN998M1xcXAAAAQEB+P777/Hrr7+iQ4cO0p5WAwcOlGp69+6Nzz//HG+88QY8PDyg0WjQuXNnBAUFSTVt2YwZM3DgwAF888039Y7JZDKbn4UQ9Z672IU1y5YtQ1lZGebPn2+/BrcSzXld+Z2177W9EL+zzXNd2/t31l4YrKjZxcTEIDU1FaWlpcjNzUVSUhKKiooQGRkp1cTHx+PkyZPIz89HYWEhvvzyS+Tk5NjUTJ48GXl5ecjJyUFRUREWLFiAgoICm5q2aObMmfjll1+wceNGhIaGSs9rNBoAqPcv0vz8fOlfrhqNRvqX5+VqNmzYgJ07d0KlUsHV1RVdu3YFAAwaNAgPPfRQs30uR2vu6wrwO3s117Yx+J1tnusKtN/vrF05ZmoXtVW4aPL6pRw7dkzI5XKxZs2ay9b8+eefQiaTiSNHjly25uOPPxYeHh6Xndja2pnNZjF9+nSh1WrFsWPHLnlco9GIV199VXpOr9dfcpL1t99+K9WcPXvWZpJ1RkaGSEtLkx5r1qwRAMQPP/wgsrKymvlTtryWuq6Xwu/sla/thS43yZrf2frH7XFdL6Wtf2ebA4MVXbPy8nKxb98+6e6RpUuXin379omMjAwhhBDfffed2Lhxozh58qT46aefRHh4uLjjjjtszvHJJ5+IHTt2iBMnTogvv/xS+Pr6ijlz5tjULFu2TCQnJ4ujR4+K5cuXC3d3d/H222+32OdsaU888YRQq9Vi06ZNIjc3V3pUVVVJNYsXLxZqtVqsXLlSpKWlifvvv18EBweLsrIyqebxxx8XoaGhYv369SIlJUXcdNNNol+/fsJoNF7yfU+fPt2m77BqyevK7+zVXdvc3Fyxb98+8b///U8AEFu2bBH79u0TRUVFl3xffmftd13b23e2OTBY0TWz/uvn4sdDDz0khBDi7bffFqGhoUKhUIhOnTqJf/7zn0Kv19uc47nnnhNBQUFCoVCIqKgo8cYbbwiz2WxTk5CQIHx9fYVSqRR9+/YVX3zxRUt9RIe41DUFID799FOpxmw2ixdffFFoNBqhUqnEjTfeKNLS0mzOU11dLWbMmCF8fX2Fu7u7mDBhgsjMzLzs+7b1X1IteV35nb26a/viiy9e8TwX4nfWfte1vX1nm4NMCCHsPLpIRERE1C5x8joRERGRnTBYEREREdkJgxURERGRnTBYEREREdkJgxURERGRnTBYEREREdkJgxURERGRnTBYEREREdkJgxUR0QWmTp0KmUwGmUwGhUKBoKAgxMXF4ZNPPoHZbG70eT777DN07Nix+RpKRE6JwYqI6CLjxo1Dbm4uzpw5g9WrV2PUqFF46qmnMGHCBBiNRkc3j4icGIMVEdFFVCoVNBoNQkJCMHDgQDz//PP4+eefsXr1anz22WcAgKVLl6JPnz7w9PREWFgYnnzySVRUVAAANm3ahIcffhg6nU7q/VqwYAEAwGAw4Nlnn0VISAg8PT0xZMgQbNq0yTEflIjsjsGKiKgRbrrpJvTr1w8rV64EAMjlcrzzzjtIT0/H559/jg0bNuDZZ58FAAwfPhxvvfUWvL29kZubi9zcXMybNw8A8PDDD2Pbtm1ITEzEgQMHcPfdd2PcuHE4fvy4wz4bEdkPN2EmIrrA1KlTUVpaip9++qnesfvuuw8HDhzAoUOH6h37/vvv8cQTT6CwsBCAZY7V7NmzUVpaKtWcPHkSUVFRyM7OhlarlZ4fM2YMrrvuOixcuNDun4eIWparoxtARNRaCCEgk8kAABs3bsTChQtx6NAhlJWVwWg0oqamBpWVlfD09Lzk61NSUiCEQLdu3Wye1+v18PPza/b2E1HzY7AiImqkw4cPIzIyEhkZGbjlllvw+OOP49///jd8fX2xdetWPPLII6itrb3s681mM1xcXJCcnAwXFxebYx06dGju5hNRC2CwIiJqhA0bNiAtLQ1PP/009u7dC6PRiDfeeANyuWWq6nfffWdTr1QqYTKZbJ4bMGAATCYT8vPzccMNN7RY24mo5TBYERFdRK/XIy8vDyaTCefOnUNSUhIWLVqECRMm4MEHH0RaWhqMRiOWLVuGiRMnYtu2bXj//fdtzhEREYGKigr8+eef6NevHzw8PNCtWzdMmTIFDz74IN544w0MGDAAhYWF2LBhA/r06YNbbrnFQZ+YiOyFdwUSEV0kKSkJwcHBiIiIwLhx47Bx40a88847+Pnnn+Hi4oL+/ftj6dKlePXVVxEdHY0VK1Zg0aJFNucYPnw4Hn/8cdx7770ICAjAa6+9BgD49NNP8eCDD2Lu3Lno3r07Jk2ahF27diEsLMwRH5WI7Ix3BRIRERHZCXusiIiIiOyEwYqIiIjIThisiIiIiOyEwYqIiIjIThisiIiIiOyEwYqIiIjIThisiIiIiOyEwYqIiIjIThisiIiIiOyEwYqIiIjIThisiIiIiOyEwYqIiIjITv4fSwC4Y6/sZREAAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = brent.plot(kind='line', x='Date', y='Avg_Price')\n",
    "ax.set_ylabel('Price')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "aWTPqSJeqHnC"
   },
   "source": [
    "To limit the number of data points you have, you might want to extract the year from every month value your *Month* column. \n",
    "\n",
    "To this end, you *could* apply a ***lambda function***. Your logic could work as follows:\n",
    "1. look through the `Month` column\n",
    "2. extract the year from each individual value in that column \n",
    "3. store that corresponding year as separate column. \n",
    "\n",
    "Whether you go ahead with this is up to you. Just so long as you answer our initial brief: which boroughs of London have seen the greatest house price increase, on average, over the past two decades? "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 714,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "e0DF92cyqnu8",
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/pg/_pplhw5n751gy32hg8r8_xsw0000gn/T/ipykernel_47954/300266712.py:1: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
      "Try using .loc[row_indexer,col_indexer] = value instead\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  df['Year'] = df['Date'].apply(lambda x: x.year)\n"
     ]
    }
   ],
   "source": [
    "df['Year'] = df['Date'].apply(lambda x: x.year)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 715,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Borough</th>\n",
       "      <th>ID</th>\n",
       "      <th>Date</th>\n",
       "      <th>Avg_Price</th>\n",
       "      <th>Year</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>City of London</td>\n",
       "      <td>E09000001</td>\n",
       "      <td>1995-01-01</td>\n",
       "      <td>91448.98487</td>\n",
       "      <td>1995</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Barking &amp; Dagenham</td>\n",
       "      <td>E09000002</td>\n",
       "      <td>1995-01-01</td>\n",
       "      <td>50460.22660</td>\n",
       "      <td>1995</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Barnet</td>\n",
       "      <td>E09000003</td>\n",
       "      <td>1995-01-01</td>\n",
       "      <td>93284.51832</td>\n",
       "      <td>1995</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Bexley</td>\n",
       "      <td>E09000004</td>\n",
       "      <td>1995-01-01</td>\n",
       "      <td>64958.09036</td>\n",
       "      <td>1995</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Brent</td>\n",
       "      <td>E09000005</td>\n",
       "      <td>1995-01-01</td>\n",
       "      <td>71306.56698</td>\n",
       "      <td>1995</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              Borough         ID       Date    Avg_Price  Year\n",
       "0      City of London  E09000001 1995-01-01  91448.98487  1995\n",
       "1  Barking & Dagenham  E09000002 1995-01-01  50460.22660  1995\n",
       "2              Barnet  E09000003 1995-01-01  93284.51832  1995\n",
       "3              Bexley  E09000004 1995-01-01  64958.09036  1995\n",
       "4               Brent  E09000005 1995-01-01  71306.56698  1995"
      ]
     },
     "execution_count": 715,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Ask Oscar about this ^\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 716,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "df = df.groupby(by=['Borough', 'Year']).mean('Avg_Price').reset_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 717,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Borough</th>\n",
       "      <th>Year</th>\n",
       "      <th>Avg_Price</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Barking &amp; Dagenham</td>\n",
       "      <td>1995</td>\n",
       "      <td>5.181797e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Barking &amp; Dagenham</td>\n",
       "      <td>1996</td>\n",
       "      <td>5.171819e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Barking &amp; Dagenham</td>\n",
       "      <td>1997</td>\n",
       "      <td>5.597426e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Barking &amp; Dagenham</td>\n",
       "      <td>1998</td>\n",
       "      <td>6.028582e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Barking &amp; Dagenham</td>\n",
       "      <td>1999</td>\n",
       "      <td>6.532093e+04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>952</th>\n",
       "      <td>Westminster</td>\n",
       "      <td>2019</td>\n",
       "      <td>9.559986e+05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>953</th>\n",
       "      <td>Westminster</td>\n",
       "      <td>2020</td>\n",
       "      <td>9.604692e+05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>954</th>\n",
       "      <td>Westminster</td>\n",
       "      <td>2021</td>\n",
       "      <td>9.627774e+05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>955</th>\n",
       "      <td>Westminster</td>\n",
       "      <td>2022</td>\n",
       "      <td>1.016474e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>956</th>\n",
       "      <td>Westminster</td>\n",
       "      <td>2023</td>\n",
       "      <td>1.005680e+06</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>957 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                Borough  Year     Avg_Price\n",
       "0    Barking & Dagenham  1995  5.181797e+04\n",
       "1    Barking & Dagenham  1996  5.171819e+04\n",
       "2    Barking & Dagenham  1997  5.597426e+04\n",
       "3    Barking & Dagenham  1998  6.028582e+04\n",
       "4    Barking & Dagenham  1999  6.532093e+04\n",
       "..                  ...   ...           ...\n",
       "952         Westminster  2019  9.559986e+05\n",
       "953         Westminster  2020  9.604692e+05\n",
       "954         Westminster  2021  9.627774e+05\n",
       "955         Westminster  2022  1.016474e+06\n",
       "956         Westminster  2023  1.005680e+06\n",
       "\n",
       "[957 rows x 3 columns]"
      ]
     },
     "execution_count": 717,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 718,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Borough       object\n",
       "Year           int64\n",
       "Avg_Price    float64\n",
       "dtype: object"
      ]
     },
     "execution_count": 718,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "2knuTxAEqoJ4"
   },
   "source": [
    "**3. Modeling**\n",
    "\n",
    "Consider creating a function that will calculate a ratio of house prices, comparing the price of a house in 2018 to the price in 1998.\n",
    "\n",
    "Consider calling this function create_price_ratio.\n",
    "\n",
    "You'd want this function to:\n",
    "1. Take a filter of dfg, specifically where this filter constrains the London_Borough, as an argument. For example, one admissible argument should be: dfg[dfg['London_Borough']=='Camden'].\n",
    "2. Get the Average Price for that Borough, for the years 1998 and 2018.\n",
    "4. Calculate the ratio of the Average Price for 1998 divided by the Average Price for 2018.\n",
    "5. Return that ratio.\n",
    "\n",
    "Once you've written this function, you ultimately want to use it to iterate through all the unique London_Boroughs and work out the ratio capturing the difference of house prices between 1998 and 2018.\n",
    "\n",
    "Bear in mind: you don't have to write a function like this if you don't want to. If you can solve the brief otherwise, then great! \n",
    "\n",
    "***Hint***: This section should test the skills you acquired in:\n",
    "- Python Data Science Toolbox - Part One, all modules"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 719,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "def create_price_ratio(x):\n",
    "    price_1995 = float(x['Avg_Price'][x['Year']==1995])\n",
    "    price_2023 = float(x['Avg_Price'][x['Year']==2023])\n",
    "    ratio = price_2023 / price_1995\n",
    "    return ratio"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 720,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/pg/_pplhw5n751gy32hg8r8_xsw0000gn/T/ipykernel_47954/3212550447.py:2: FutureWarning: Calling float on a single element Series is deprecated and will raise a TypeError in the future. Use float(ser.iloc[0]) instead\n",
      "  price_1995 = float(x['Avg_Price'][x['Year']==1995])\n",
      "/var/folders/pg/_pplhw5n751gy32hg8r8_xsw0000gn/T/ipykernel_47954/3212550447.py:3: FutureWarning: Calling float on a single element Series is deprecated and will raise a TypeError in the future. Use float(ser.iloc[0]) instead\n",
      "  price_2023 = float(x['Avg_Price'][x['Year']==2023])\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "7.347171874965135"
      ]
     },
     "execution_count": 720,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "create_price_ratio(df[df['Borough']=='Brent'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 721,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "cKTyr437UgDa",
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Ask Oscar about this ^\n",
    "\n",
    "boroughs_list = df['Borough'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 722,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Barking & Dagenham', 'Barnet', 'Bexley', 'Brent', 'Bromley',\n",
       "       'Camden', 'City of London', 'Croydon', 'Ealing', 'Enfield',\n",
       "       'Greenwich', 'Hackney', 'Hammersmith & Fulham', 'Haringey',\n",
       "       'Harrow', 'Havering', 'Hillingdon', 'Hounslow', 'Islington',\n",
       "       'Kensington & Chelsea', 'Kingston upon Thames', 'Lambeth',\n",
       "       'Lewisham', 'Merton', 'Newham', 'Redbridge',\n",
       "       'Richmond upon Thames', 'Southwark', 'Sutton', 'Tower Hamlets',\n",
       "       'Waltham Forest', 'Wandsworth', 'Westminster'], dtype=object)"
      ]
     },
     "execution_count": 722,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "boroughs_list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 723,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/var/folders/pg/_pplhw5n751gy32hg8r8_xsw0000gn/T/ipykernel_47954/3212550447.py:2: FutureWarning: Calling float on a single element Series is deprecated and will raise a TypeError in the future. Use float(ser.iloc[0]) instead\n",
      "  price_1995 = float(x['Avg_Price'][x['Year']==1995])\n",
      "/var/folders/pg/_pplhw5n751gy32hg8r8_xsw0000gn/T/ipykernel_47954/3212550447.py:3: FutureWarning: Calling float on a single element Series is deprecated and will raise a TypeError in the future. Use float(ser.iloc[0]) instead\n",
      "  price_2023 = float(x['Avg_Price'][x['Year']==2023])\n"
     ]
    }
   ],
   "source": [
    "ratios = {}\n",
    "for x in boroughs_list:\n",
    "    bor = df[df['Borough'] == x]\n",
    "    ratios[x] = create_price_ratio(bor)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 724,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'Barking & Dagenham': 6.649683576108962,\n",
       " 'Barnet': 6.400840595915073,\n",
       " 'Bexley': 6.0961542314585015,\n",
       " 'Brent': 7.347171874965135,\n",
       " 'Bromley': 6.123446759127447,\n",
       " 'Camden': 7.091508785669645,\n",
       " 'City of London': 9.36833045964029,\n",
       " 'Croydon': 6.001939182407025,\n",
       " 'Ealing': 6.316608850251452,\n",
       " 'Enfield': 6.13614912612903,\n",
       " 'Greenwich': 6.712854277781165,\n",
       " 'Hackney': 9.462698270302507,\n",
       " 'Hammersmith & Fulham': 6.219940957953884,\n",
       " 'Haringey': 7.482612442017318,\n",
       " 'Harrow': 6.108843845737517,\n",
       " 'Havering': 6.194745553534498,\n",
       " 'Hillingdon': 6.07510009048479,\n",
       " 'Hounslow': 6.273251370921286,\n",
       " 'Islington': 7.394090183633763,\n",
       " 'Kensington & Chelsea': 6.957437306708718,\n",
       " 'Kingston upon Thames': 6.602656857310926,\n",
       " 'Lambeth': 8.156413792256238,\n",
       " 'Lewisham': 7.775369710945311,\n",
       " 'Merton': 7.065654435439171,\n",
       " 'Newham': 7.553457504662543,\n",
       " 'Redbridge': 6.506576302138604,\n",
       " 'Richmond upon Thames': 6.892033191910892,\n",
       " 'Southwark': 8.345302699684195,\n",
       " 'Sutton': 6.166617652499978,\n",
       " 'Tower Hamlets': 7.154851518643157,\n",
       " 'Waltham Forest': 8.201603463315813,\n",
       " 'Wandsworth': 7.0173999147744786,\n",
       " 'Westminster': 7.522522773013808}"
      ]
     },
     "execution_count": 724,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ratios"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 725,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "ratios_df = pd.DataFrame(ratios.items(), columns=['Borough', 'Ratio'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 726,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "ratios_df = ratios_df.sort_values(by='Ratio', ascending=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 727,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Borough</th>\n",
       "      <th>Ratio</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Hackney</td>\n",
       "      <td>9.462698</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>City of London</td>\n",
       "      <td>9.368330</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>Southwark</td>\n",
       "      <td>8.345303</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>30</th>\n",
       "      <td>Waltham Forest</td>\n",
       "      <td>8.201603</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>Lambeth</td>\n",
       "      <td>8.156414</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>Lewisham</td>\n",
       "      <td>7.775370</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>Newham</td>\n",
       "      <td>7.553458</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32</th>\n",
       "      <td>Westminster</td>\n",
       "      <td>7.522523</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Haringey</td>\n",
       "      <td>7.482612</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Islington</td>\n",
       "      <td>7.394090</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Brent</td>\n",
       "      <td>7.347172</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>Tower Hamlets</td>\n",
       "      <td>7.154852</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Camden</td>\n",
       "      <td>7.091509</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>Merton</td>\n",
       "      <td>7.065654</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>31</th>\n",
       "      <td>Wandsworth</td>\n",
       "      <td>7.017400</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>Kensington &amp; Chelsea</td>\n",
       "      <td>6.957437</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>Richmond upon Thames</td>\n",
       "      <td>6.892033</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Greenwich</td>\n",
       "      <td>6.712854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Barking &amp; Dagenham</td>\n",
       "      <td>6.649684</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>Kingston upon Thames</td>\n",
       "      <td>6.602657</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>Redbridge</td>\n",
       "      <td>6.506576</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Barnet</td>\n",
       "      <td>6.400841</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Ealing</td>\n",
       "      <td>6.316609</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>Hounslow</td>\n",
       "      <td>6.273251</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Hammersmith &amp; Fulham</td>\n",
       "      <td>6.219941</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>Havering</td>\n",
       "      <td>6.194746</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>Sutton</td>\n",
       "      <td>6.166618</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Enfield</td>\n",
       "      <td>6.136149</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Bromley</td>\n",
       "      <td>6.123447</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Harrow</td>\n",
       "      <td>6.108844</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Bexley</td>\n",
       "      <td>6.096154</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>Hillingdon</td>\n",
       "      <td>6.075100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Croydon</td>\n",
       "      <td>6.001939</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 Borough     Ratio\n",
       "11               Hackney  9.462698\n",
       "6         City of London  9.368330\n",
       "27             Southwark  8.345303\n",
       "30        Waltham Forest  8.201603\n",
       "21               Lambeth  8.156414\n",
       "22              Lewisham  7.775370\n",
       "24                Newham  7.553458\n",
       "32           Westminster  7.522523\n",
       "13              Haringey  7.482612\n",
       "18             Islington  7.394090\n",
       "3                  Brent  7.347172\n",
       "29         Tower Hamlets  7.154852\n",
       "5                 Camden  7.091509\n",
       "23                Merton  7.065654\n",
       "31            Wandsworth  7.017400\n",
       "19  Kensington & Chelsea  6.957437\n",
       "26  Richmond upon Thames  6.892033\n",
       "10             Greenwich  6.712854\n",
       "0     Barking & Dagenham  6.649684\n",
       "20  Kingston upon Thames  6.602657\n",
       "25             Redbridge  6.506576\n",
       "1                 Barnet  6.400841\n",
       "8                 Ealing  6.316609\n",
       "17              Hounslow  6.273251\n",
       "12  Hammersmith & Fulham  6.219941\n",
       "15              Havering  6.194746\n",
       "28                Sutton  6.166618\n",
       "9                Enfield  6.136149\n",
       "4                Bromley  6.123447\n",
       "14                Harrow  6.108844\n",
       "2                 Bexley  6.096154\n",
       "16            Hillingdon  6.075100\n",
       "7                Croydon  6.001939"
      ]
     },
     "execution_count": 727,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ratios_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 728,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='Borough'>"
      ]
     },
     "execution_count": 728,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ratios_df.plot(kind='bar', x='Borough', y='Ratio')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 729,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "7.011329319919488"
      ]
     },
     "execution_count": 729,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ratios_df['Ratio'].mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 730,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "6.892033191910892"
      ]
     },
     "execution_count": 730,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ratios_df['Ratio'].median()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 731,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9166813085921682"
      ]
     },
     "execution_count": 731,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ratios_df['Ratio'].std()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "NzYUI7FxJpgv"
   },
   "source": [
    "### 4. Conclusion\n",
    "What can you conclude? Type out your conclusion below. \n",
    "\n",
    "Look back at your notebook. Think about how you might summarize what you have done, and prepare a quick presentation on it to your mentor at your next meeting. \n",
    "\n",
    "We hope you enjoyed this practical project. It should have consolidated your data hygiene and pandas skills by looking at a real-world problem involving just the kind of dataset you might encounter as a budding data scientist. Congratulations, and looking forward to seeing you at the next step in the course! "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can conclude that all of London's boroughs saw an increase in average housing prices from 1995 to 2023, with an average increase ratio across all boroughs of 7.01, a median of 6.89, and a standard deviation of 0.92. This means that the average price of housing in a London borough in 2023 is approximately 7 times more than it was in 1995.\n",
    "\n",
    "Hackney had the greatest average increase in housing prices by 2023, with the average housing price in this borough increasing to approximately 9.46 times what it was in 1995. Croydon saw the lowest increase, but housing prices here were still 6 times larger in 2023 than they were in 1995."
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Springboard Data Science Career Track Unit 4 Challenge - Tier 3 Complete .ipynb",
   "provenance": []
  },
  "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}