{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id='top'></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# The Guardian Player Recorded Transfer Fees Data Engineering\n",
    "##### Notebook to engineer player recorded transfer data scraped from [The Guardian](https://www.theguardian.com/football/ng-interactive/2021/jun/07/mens-transfer-window-summer-2021-all-deals-from-europes-top-five-leagues).\n",
    "\n",
    "### By [Edd Webster](https://www.twitter.com/eddwebster)\n",
    "Notebook first written: 22/08/2021<br>\n",
    "Notebook last updated: 06/09/2021\n",
    "\n",
    "![title](../../img/logos/the-guardian-logo.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "___\n",
    "\n",
    "<a id='sectionintro'></a>\n",
    "\n",
    "## <a id='import_libraries'>Introduction</a>\n",
    "This notebook engineers transfer data data from the [Guardian](https://www.theguardian.com/football/ng-interactive/2021/jun/07/mens-transfer-window-summer-2021-all-deals-from-europes-top-five-leagues) provided by [Tom Worville](https://twitter.com/Worville/) (see Tweet [[link](https://twitter.com/Worville/status/1420035521988993034)]), and manipulates this landed data as DataFrames using [pandas](http://pandas.pydata.org/) and [matplotlib](https://matplotlib.org/) for visualisation.\n",
    "\n",
    "For more information about this notebook and the author, I'm available through all the following channels:\n",
    "*    [eddwebster.com](https://www.eddwebster.com/);\n",
    "*    edd.j.webster@gmail.com;\n",
    "*    [@eddwebster](https://www.twitter.com/eddwebster);\n",
    "*    [linkedin.com/in/eddwebster](https://www.linkedin.com/in/eddwebster/);\n",
    "*    [github/eddwebster](https://github.com/eddwebster/);\n",
    "*    [public.tableau.com/profile/edd.webster](https://public.tableau.com/profile/edd.webster);\n",
    "*    [kaggle.com/eddwebster](https://www.kaggle.com/eddwebster); and\n",
    "*    [hackerrank.com/eddwebster](https://www.hackerrank.com/eddwebster).\n",
    "\n",
    "![title](../../img/fifa21eddwebsterbanner.png)\n",
    "\n",
    "The accompanying GitHub repository for this notebook can be found [here](https://github.com/eddwebster/football_analytics) and a static version of this notebook can be found [here](https://nbviewer.jupyter.org/github/eddwebster/football_analytics/blob/master/notebooks/A%29%20Web%20Scraping/TransferMarkt%20Web%20Scraping%20and%20Parsing.ipynb)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "___\n",
    "\n",
    "<a id='sectioncontents'></a>\n",
    "\n",
    "## <a id='notebook_contents'>Notebook Contents</a>\n",
    "1.    [Notebook Dependencies](#section1)<br>\n",
    "2.    [Project Brief](#section2)<br>\n",
    "3.    [Data Sources](#section3)<br>\n",
    "      1.    [Introduction](#section3.1)<br>\n",
    "      2.    [Data Dictionary](#section3.2)<br>\n",
    "      3.    [Creating the DataFrame](#section3.3)<br>\n",
    "      4.    [Initial Data Handling](#section3.4)<br>\n",
    "      5.    [Export the Raw DataFrame](#section3.5)<br>         \n",
    "4.    [Data Engineering](#section4)<br>\n",
    "      1.    [Introduction](#section4.1)<br>\n",
    "      2.    [Columns of Interest](#section4.2)<br>\n",
    "      3.    [String Cleaning](#section4.3)<br>\n",
    "      4.    [Converting Data Types](#section4.4)<br>\n",
    "      5.    [Export the Engineered DataFrame](#section4.5)<br>\n",
    "5.    [Exploratory Data Analysis (EDA)](#section5)<br>\n",
    "      1.    [...](#section5.1)<br>\n",
    "      2.    [...](#section5.2)<br>\n",
    "      3.    [...](#section5.3)<br>\n",
    "6.    [Summary](#section6)<br>\n",
    "7.    [Next Steps](#section7)<br>\n",
    "8.    [Bibliography](#section8)<br>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "___\n",
    "\n",
    "<a id='section1'></a>\n",
    "\n",
    "## <a id='#section1'>1. Notebook Dependencies</a>\n",
    "This notebook was written using [Python 3](https://docs.python.org/3.7/) and requires the following libraries:\n",
    "*    [`Jupyter notebooks`](https://jupyter.org/) for this notebook environment with which this project is presented;\n",
    "*    [`NumPy`](http://www.numpy.org/) for multidimensional array computing;\n",
    "*    [`pandas`](http://pandas.pydata.org/) for data analysis and manipulation; and\n",
    "*    [`matplotlib`](https://matplotlib.org/contents.html?v=20200411155018) for data visualisations.\n",
    "\n",
    "All packages used for this notebook except for BeautifulSoup can be obtained by downloading and installing the [Conda](https://anaconda.org/anaconda/conda) distribution, available on all platforms (Windows, Linux and Mac OSX). Step-by-step guides on how to install Anaconda can be found for Windows [here](https://medium.com/@GalarnykMichael/install-python-on-windows-anaconda-c63c7c3d1444) and Mac [here](https://medium.com/@GalarnykMichael/install-python-on-mac-anaconda-ccd9f2014072), as well as in the Anaconda documentation itself [here](https://docs.anaconda.com/anaconda/install/)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Import Libraries and Modules"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Setup Complete\n"
     ]
    }
   ],
   "source": [
    "# Python ≥3.5 (ideally)\n",
    "import platform\n",
    "import sys, getopt\n",
    "assert sys.version_info >= (3, 5)\n",
    "import csv\n",
    "\n",
    "# Import Dependencies\n",
    "%matplotlib inline\n",
    "\n",
    "# Math Operations\n",
    "import numpy as np\n",
    "import math\n",
    "from math import pi\n",
    "\n",
    "# Datetime\n",
    "import datetime\n",
    "from datetime import date\n",
    "import time\n",
    "\n",
    "# Data Preprocessing\n",
    "import pandas as pd\n",
    "import os\n",
    "import re\n",
    "import random\n",
    "from io import BytesIO\n",
    "from pathlib import Path\n",
    "\n",
    "# Reading directories\n",
    "import glob\n",
    "import os\n",
    "from os.path import basename\n",
    "\n",
    "# Flatten lists\n",
    "from functools import reduce\n",
    "\n",
    "# Working with JSON\n",
    "import json\n",
    "from pandas.io.json import json_normalize\n",
    "\n",
    "# Web Scraping\n",
    "import requests\n",
    "from bs4 import BeautifulSoup\n",
    "import re\n",
    "\n",
    "# Currency Convert\n",
    "from forex_python.converter import CurrencyRates\n",
    "\n",
    "# APIs\n",
    "from tyrone_mings import * \n",
    "\n",
    "# Fuzzy Matching - Record Linkage\n",
    "import recordlinkage\n",
    "import jellyfish\n",
    "import numexpr as ne\n",
    "\n",
    "# Data Visualisation\n",
    "import matplotlib as mpl\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "plt.style.use('seaborn-whitegrid')\n",
    "import missingno as msno\n",
    "\n",
    "# Progress Bar\n",
    "from tqdm import tqdm\n",
    "\n",
    "# Display in Jupyter\n",
    "from IPython.display import Image, YouTubeVideo\n",
    "from IPython.core.display import HTML\n",
    "\n",
    "# Ignore Warnings\n",
    "import warnings\n",
    "warnings.filterwarnings(action=\"ignore\", message=\"^internal gelsd\")\n",
    "\n",
    "print('Setup Complete')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Python: 3.7.6\n",
      "NumPy: 1.20.3\n",
      "pandas: 1.3.2\n",
      "matplotlib: 3.4.2\n"
     ]
    }
   ],
   "source": [
    "# Python / module versions used here for reference\n",
    "print('Python: {}'.format(platform.python_version()))\n",
    "print('NumPy: {}'.format(np.__version__))\n",
    "print('pandas: {}'.format(pd.__version__))\n",
    "print('matplotlib: {}'.format(mpl.__version__))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Defined Variables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define today's date\n",
    "today = datetime.datetime.now().strftime('%d/%m/%Y').replace('/', '')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Defined Dictionaries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Defined Dictionaries\n",
    "\n",
    "## Seasons\n",
    "dict_seasons = {2016: '2016/2017',\n",
    "                2017: '2017/2018',\n",
    "                2018: '2018/2019',\n",
    "                2019: '2019/2020',\n",
    "                2020: '2020/2021',\n",
    "                2021: '2021/2022'\n",
    "               }\n",
    "\n",
    "## Positions\n",
    "dict_positions_grouped = {'GK': 'Goalkeeper',\n",
    "                          'D': 'Defender',\n",
    "                          'M': 'Midfielder',\n",
    "                          'W': 'Forward',    # I think 'W' in the dataset is 'Winger', therefore a forward\n",
    "                          'F': 'Forward',\n",
    "                      }"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Defined Filepaths"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Set up initial paths to subfolders\n",
    "base_dir = os.path.join('..', '..')\n",
    "data_dir = os.path.join(base_dir, 'data')\n",
    "data_dir_guardian = os.path.join(base_dir, 'data', 'guardian')\n",
    "img_dir = os.path.join(base_dir, 'img')\n",
    "fig_dir = os.path.join(base_dir, 'img', 'fig')\n",
    "video_dir = os.path.join(base_dir, 'video')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Notebook Settings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "pd.set_option('display.max_columns', None)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "\n",
    "<a id='section2'></a>\n",
    "\n",
    "## <a id='#section2'>2. Project Brief</a>\n",
    "This Jupyter notebook is part of a series of notebooks to scrape, parse, engineer, unify, and the model, culminating in a an Expected Transfer (xTransfer) player performance vs. valuation model. This model aims to determine the under- and over-performing players based on their on-the-pitch output against transfer fee and wages.\n",
    "\n",
    "This particular notebook is one of several data engineering notebooks, that cleans recorded transfer fee player data from [Guardian](https://www.theguardian.com/football/ng-interactive/2021/jun/07/mens-transfer-window-summer-2021-all-deals-from-europes-top-five-leagues) using [pandas](http://pandas.pydata.org/).\n",
    "\n",
    "This notebook, along with the other notebooks in this project workflow are shown in the following diagram:\n",
    "\n",
    "![roadmap](../../img/football_analytics_data_roadmap.png)\n",
    "\n",
    "Links to these notebooks in the [`football_analytics`](https://github.com/eddwebster/football_analytics) GitHub repository can be found at the following:\n",
    "*    [Webscraping](https://github.com/eddwebster/football_analytics/tree/master/notebooks/1_data_scraping)\n",
    "     +    [FBref Player Stats Webscraping](https://github.com/eddwebster/football_analytics/blob/master/notebooks/1_data_scraping/FBref%20Player%20Stats%20Web%20Scraping.ipynb)\n",
    "     +    [TransferMarket Player Bio and Status Webscraping](https://github.com/eddwebster/football_analytics/blob/master/notebooks/1_data_scraping/TransferMarkt%20Player%20Bio%20and%20Status%20Web%20Scraping.ipynb)\n",
    "     +    [TransferMarket Player Valuation Webscraping](https://github.com/eddwebster/football_analytics/blob/master/notebooks/1_data_scraping/TransferMarkt%20Player%20Valuation%20Web%20Scraping.ipynb)\n",
    "     +    [TransferMarkt Player Recorded Transfer Fees Webscraping](https://github.com/eddwebster/football_analytics/blob/master/notebooks/1_data_scraping/TransferMarkt%20Player%20Recorded%20Transfer%20Fees%20Webscraping.ipynb)\n",
    "     +    [Capology Player Salary Webscraping](https://github.com/eddwebster/football_analytics/blob/master/notebooks/1_data_scraping/Capology%20Player%20Salary%20Web%20Scraping.ipynb)\n",
    "     +    [FBref Team Stats Webscraping](https://github.com/eddwebster/football_analytics/blob/master/notebooks/1_data_scraping/FBref%20Team%20Stats%20Web%20Scraping.ipynb)\n",
    "*    [Data Parsing](https://github.com/eddwebster/football_analytics/tree/master/notebooks/2_data_parsing)\n",
    "     +    [ELO Team Ratings Data Parsing](https://github.com/eddwebster/football_analytics/blob/master/notebooks/2_data_parsing/ELO%20Team%20Ratings%20Data%20Parsing.ipynb)\n",
    "*    [Data Engineering](https://github.com/eddwebster/football_analytics/tree/master/notebooks/3_data_engineering)\n",
    "     +    [FBref Player Stats Data Engineering](https://github.com/eddwebster/football_analytics/blob/master/notebooks/3_data_engineering/FBref%20Player%20Stats%20Data%20Engineering.ipynb)\n",
    "     +    [TransferMarket Player Bio and Status Data Engineering](https://github.com/eddwebster/football_analytics/blob/master/notebooks/3_data_engineering/TransferMarkt%20Player%20Bio%20and%20Status%20Data%20Engineering.ipynb)\n",
    "     +    [TransferMarket Player Valuation Data Engineering](https://github.com/eddwebster/football_analytics/blob/master/notebooks/3_data_engineering/TransferMarkt%20Player%20Valuation%20Data%20Engineering.ipynb)\n",
    "     +    [TransferMarkt Player Recorded Transfer Fees Data Engineering](https://github.com/eddwebster/football_analytics/blob/master/notebooks/3_data_engineering/TransferMarkt%20Player%20Recorded%20Transfer%20Fees%20Data%20Engineering.ipynb)\n",
    "     +    [Guardian Player Recorded Transfer Fees Data Engineering](https://github.com/eddwebster/football_analytics/blob/master/notebooks/3_data_engineering/Guardian%20Player%20Recorded%20Transfer%20Fees%20Data%20Engineering.ipynb)\n",
    "     +    [Capology Player Salary Data Engineering](https://github.com/eddwebster/football_analytics/blob/master/notebooks/3_data_engineering/Capology%20Player%20Salary%20Data%20Engineering.ipynb)\n",
    "     +    [FBref Team Stats Data Engineering](https://github.com/eddwebster/football_analytics/blob/master/notebooks/3_data_engineering/FBref%20Team%20Stats%20Data%20Engineering.ipynb)\n",
    "     +    [ELO Team Ratings Data Parsing](https://github.com/eddwebster/football_analytics/blob/master/notebooks/3_data_engineering/ELO%20Team%20Ratings%20Data%20Parsing.ipynb)\n",
    "     +    [TransferMarkt Team Recorded Transfer Fee Data Engineering](https://github.com/eddwebster/football_analytics/blob/master/notebooks/3_data_engineering/TransferMarkt%20Team%20Recorded%20Transfer%20Fee%20Data%20Engineering.ipynb) (aggregated from [TransferMarkt Player Recorded Transfer Fees notebook](https://github.com/eddwebster/football_analytics/blob/master/notebooks/3_data_engineering/TransferMarkt%20Player%20Recorded%20Transfer%20Fees%20Data%20Engineering.ipynb))\n",
    "     +    [Capology Team Salary Data Engineering](https://github.com/eddwebster/football_analytics/blob/master/notebooks/3_data_engineering/Capology%20Team%20Salary%20Data%20Engineering.ipynb) (aggregated from [Capology Player Salary notebook](https://github.com/eddwebster/football_analytics/blob/master/notebooks/3_data_engineering/Capology%20Player%20Salary%20Data%20Engineering.ipynb))\n",
    "*    [Data Unification](https://github.com/eddwebster/football_analytics/tree/master/notebooks/4_data_unification)\n",
    "     +    [Golden ID for Player Level Datasets](https://github.com/eddwebster/football_analytics/blob/master/notebooks/4_data_unification/Golden%20ID%20for%20Player%20Level%20Datasets.ipynb)\n",
    "     +    [Golden ID for Team Level Datasets](https://github.com/eddwebster/football_analytics/blob/master/notebooks/4_data_unification/Golden%20ID%20for%20Team%20Level%20Datasets.ipynb)\n",
    "*    [Production Datasets](https://github.com/eddwebster/football_analytics/tree/master/notebooks/5_production_datasets)\n",
    "     +    [Player Performance/Market Value Dataset](https://github.com/eddwebster/football_analytics/tree/master/notebooks/5_production_datasets/Player%20Performance/Market%20Value%20Dataset.ipynb)\n",
    "     +    [Team Performance/Market Value Dataset](https://github.com/eddwebster/football_analytics/tree/master/notebooks/5_production_datasets/Team%20Performance/Market%20Value%20Dataset.ipynb)\n",
    "*    [Expected Transfer (xTransfer) Modeling](https://github.com/eddwebster/football_analytics/tree/master/notebooks/6_data_analysis_and_projects/expected_transfer_modeling)\n",
    "     +    [Expected Transfer (xTransfer) Modeling](https://github.com/eddwebster/football_analytics/tree/master/notebooks/6_data_analysis_and_projects/expected_transfer_modeling/Expected%20Transfer%20%20Modeling.ipynb)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "\n",
    "<a id='section3'></a>\n",
    "\n",
    "## <a id='#section3'>3. Data Sources</a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id='section3.3.1'></a>\n",
    "\n",
    "### <a id='#section3.1'>3.1. Introduction</a>\n",
    "Before conducting our EDA, the data needs to be imported as a DataFrame in the Data Sources section [Section 3](#section3) and cleaned in the Data Engineering section [Section 4](#section4).\n",
    "\n",
    "We'll be using the [pandas](http://pandas.pydata.org/) library to import our data to this workbook as a DataFrame."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### <a id='#section3.2'>3.2. Data Dictionaries</a>\n",
    "The [Guardian](https://www.theguardian.com/football/ng-interactive/2021/jun/07/mens-transfer-window-summer-2021-all-deals-from-europes-top-five-leagues) dataset has six features (columns) with the following definitions and data types:\n",
    "\n",
    "| Feature     | Data type    |\n",
    "|------|-----|\n",
    "| `position_number`    | object     |\n",
    "| `position_description`    | object     |\n",
    "| `name`    | object     |\n",
    "| `dob`    | object     |\n",
    "| `nationality`    | object     |\n",
    "| `value`    | object     |"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id='section3.3'></a>\n",
    "\n",
    "### <a id='#section332'>3.3. Read in Data</a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Filename\n",
    "file_name = 'guardian_transfer_data'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import DataFrame as a CSV file\n",
    "df_guardian_transfers_all_raw = pd.read_csv(data_dir_guardian + f'/raw/' + f'{file_name}_latest.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### <a id='#section3.3'>3.3. Preliminary Data Handling</a>\n",
    "Let's quality of the dataset by looking first and last rows in pandas using the [head()](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.head.html) and [tail()](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.tail.html) methods."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>transfer_id</th>\n",
       "      <th>transfer_year</th>\n",
       "      <th>window_day</th>\n",
       "      <th>window_open</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>player_name</th>\n",
       "      <th>transfer_status</th>\n",
       "      <th>transfer_type</th>\n",
       "      <th>primary_player_position</th>\n",
       "      <th>price_in_pounds</th>\n",
       "      <th>previous_club</th>\n",
       "      <th>new_club</th>\n",
       "      <th>previous_league</th>\n",
       "      <th>new_league</th>\n",
       "      <th>big_deal</th>\n",
       "      <th>flow_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>Zito Luvumbo</td>\n",
       "      <td>done deal</td>\n",
       "      <td>loan</td>\n",
       "      <td>W</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Cagliari</td>\n",
       "      <td>Como</td>\n",
       "      <td>Serie A</td>\n",
       "      <td>Serie C</td>\n",
       "      <td>NaN</td>\n",
       "      <td>100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>David Juncà</td>\n",
       "      <td>done deal</td>\n",
       "      <td>free</td>\n",
       "      <td>D</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Celta Vigo</td>\n",
       "      <td>Girona</td>\n",
       "      <td>La Liga</td>\n",
       "      <td>Spanish Segunda</td>\n",
       "      <td>NaN</td>\n",
       "      <td>241</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>Giuseppe Pezzella</td>\n",
       "      <td>done deal</td>\n",
       "      <td>loan</td>\n",
       "      <td>D</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Parma</td>\n",
       "      <td>Atalanta</td>\n",
       "      <td>Serie B</td>\n",
       "      <td>Serie A</td>\n",
       "      <td>NaN</td>\n",
       "      <td>106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>Pablo Rosario</td>\n",
       "      <td>done deal</td>\n",
       "      <td>fee</td>\n",
       "      <td>M</td>\n",
       "      <td>5130000.0</td>\n",
       "      <td>PSV Eindhoven</td>\n",
       "      <td>Nice</td>\n",
       "      <td>Eredivisie</td>\n",
       "      <td>Ligue 1</td>\n",
       "      <td>Yes</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>Martín Calderón</td>\n",
       "      <td>done deal</td>\n",
       "      <td>undisclosed</td>\n",
       "      <td>M</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Real Madrid</td>\n",
       "      <td>Cádiz</td>\n",
       "      <td>La Liga</td>\n",
       "      <td>La Liga</td>\n",
       "      <td>NaN</td>\n",
       "      <td>265</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   transfer_id  transfer_year  window_day window_open   timestamp  \\\n",
       "0            1           2021          48  2021-06-09  2021-07-27   \n",
       "1            2           2021          48  2021-06-09  2021-07-27   \n",
       "2            1           2021          48  2021-06-09  2021-07-27   \n",
       "3            1           2021          48  2021-06-09  2021-07-27   \n",
       "4            1           2021          48  2021-06-09  2021-07-27   \n",
       "\n",
       "         player_name transfer_status transfer_type primary_player_position  \\\n",
       "0       Zito Luvumbo       done deal          loan                       W   \n",
       "1        David Juncà       done deal          free                       D   \n",
       "2  Giuseppe Pezzella       done deal          loan                       D   \n",
       "3      Pablo Rosario       done deal           fee                       M   \n",
       "4    Martín Calderón       done deal   undisclosed                       M   \n",
       "\n",
       "   price_in_pounds  previous_club  new_club previous_league       new_league  \\\n",
       "0              NaN       Cagliari      Como         Serie A          Serie C   \n",
       "1              NaN     Celta Vigo    Girona         La Liga  Spanish Segunda   \n",
       "2              NaN          Parma  Atalanta         Serie B          Serie A   \n",
       "3        5130000.0  PSV Eindhoven      Nice      Eredivisie          Ligue 1   \n",
       "4              NaN    Real Madrid     Cádiz         La Liga          La Liga   \n",
       "\n",
       "  big_deal  flow_id  \n",
       "0      NaN      100  \n",
       "1      NaN      241  \n",
       "2      NaN      106  \n",
       "3      Yes        8  \n",
       "4      NaN      265  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Display the first 5 rows of the raw DataFrame, df_guardian_transfers_all_raw\n",
    "df_guardian_transfers_all_raw.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>transfer_id</th>\n",
       "      <th>transfer_year</th>\n",
       "      <th>window_day</th>\n",
       "      <th>window_open</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>player_name</th>\n",
       "      <th>transfer_status</th>\n",
       "      <th>transfer_type</th>\n",
       "      <th>primary_player_position</th>\n",
       "      <th>price_in_pounds</th>\n",
       "      <th>previous_club</th>\n",
       "      <th>new_club</th>\n",
       "      <th>previous_league</th>\n",
       "      <th>new_league</th>\n",
       "      <th>big_deal</th>\n",
       "      <th>flow_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>7214</th>\n",
       "      <td>1</td>\n",
       "      <td>2017</td>\n",
       "      <td>-38</td>\n",
       "      <td>2017-07-01</td>\n",
       "      <td>2017-05-24</td>\n",
       "      <td>Joey Barton</td>\n",
       "      <td>done deal</td>\n",
       "      <td>released</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Burnley</td>\n",
       "      <td>Free agent</td>\n",
       "      <td>Premier League</td>\n",
       "      <td>Free agent</td>\n",
       "      <td>No</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7215</th>\n",
       "      <td>1</td>\n",
       "      <td>2017</td>\n",
       "      <td>-38</td>\n",
       "      <td>2017-07-01</td>\n",
       "      <td>2017-05-24</td>\n",
       "      <td>Matthias Ostrzolek</td>\n",
       "      <td>done deal</td>\n",
       "      <td>fee</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Hamburg</td>\n",
       "      <td>Hannover 96</td>\n",
       "      <td>1. Bundesliga</td>\n",
       "      <td>1. Bundesliga</td>\n",
       "      <td>No</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7216</th>\n",
       "      <td>1</td>\n",
       "      <td>2017</td>\n",
       "      <td>-38</td>\n",
       "      <td>2017-07-01</td>\n",
       "      <td>2017-05-24</td>\n",
       "      <td>Benoît Trémoulinas</td>\n",
       "      <td>done deal</td>\n",
       "      <td>released</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Sevilla</td>\n",
       "      <td>Free agent</td>\n",
       "      <td>La Liga</td>\n",
       "      <td>Free agent</td>\n",
       "      <td>No</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7217</th>\n",
       "      <td>1</td>\n",
       "      <td>2017</td>\n",
       "      <td>-38</td>\n",
       "      <td>2017-07-01</td>\n",
       "      <td>2017-05-24</td>\n",
       "      <td>Youri Tielemans</td>\n",
       "      <td>done deal</td>\n",
       "      <td>fee</td>\n",
       "      <td>NaN</td>\n",
       "      <td>21600000.0</td>\n",
       "      <td>Anderlecht</td>\n",
       "      <td>Monaco</td>\n",
       "      <td>Belgian Jupiler Pro League</td>\n",
       "      <td>Ligue 1</td>\n",
       "      <td>Yes</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7218</th>\n",
       "      <td>1</td>\n",
       "      <td>2017</td>\n",
       "      <td>-39</td>\n",
       "      <td>2017-07-01</td>\n",
       "      <td>2017-05-23</td>\n",
       "      <td>Juan Cuadrado</td>\n",
       "      <td>done deal</td>\n",
       "      <td>fee</td>\n",
       "      <td>NaN</td>\n",
       "      <td>17330000.0</td>\n",
       "      <td>Chelsea</td>\n",
       "      <td>Juventus</td>\n",
       "      <td>Premier League</td>\n",
       "      <td>Serie A</td>\n",
       "      <td>Yes</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      transfer_id  transfer_year  window_day window_open   timestamp  \\\n",
       "7214            1           2017         -38  2017-07-01  2017-05-24   \n",
       "7215            1           2017         -38  2017-07-01  2017-05-24   \n",
       "7216            1           2017         -38  2017-07-01  2017-05-24   \n",
       "7217            1           2017         -38  2017-07-01  2017-05-24   \n",
       "7218            1           2017         -39  2017-07-01  2017-05-23   \n",
       "\n",
       "             player_name transfer_status transfer_type  \\\n",
       "7214         Joey Barton       done deal      released   \n",
       "7215  Matthias Ostrzolek       done deal           fee   \n",
       "7216  Benoît Trémoulinas       done deal      released   \n",
       "7217     Youri Tielemans       done deal           fee   \n",
       "7218       Juan Cuadrado       done deal           fee   \n",
       "\n",
       "     primary_player_position  price_in_pounds previous_club     new_club  \\\n",
       "7214                     NaN              0.0       Burnley   Free agent   \n",
       "7215                     NaN              0.0       Hamburg  Hannover 96   \n",
       "7216                     NaN              0.0       Sevilla   Free agent   \n",
       "7217                     NaN       21600000.0    Anderlecht       Monaco   \n",
       "7218                     NaN       17330000.0       Chelsea     Juventus   \n",
       "\n",
       "                 previous_league     new_league big_deal  flow_id  \n",
       "7214              Premier League     Free agent       No        2  \n",
       "7215               1. Bundesliga  1. Bundesliga       No        1  \n",
       "7216                     La Liga     Free agent       No        1  \n",
       "7217  Belgian Jupiler Pro League        Ligue 1      Yes        1  \n",
       "7218              Premier League        Serie A      Yes        1  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Display the last five rows of the raw DataFrame, df_guardian_transfers_all_raw\n",
    "df_guardian_transfers_all_raw.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(7219, 16)\n"
     ]
    }
   ],
   "source": [
    "# Print the shape of the raw DataFrame, df_guardian_transfers_all_raw\n",
    "print(df_guardian_transfers_all_raw.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Index(['transfer_id', 'transfer_year', 'window_day', 'window_open',\n",
      "       'timestamp', 'player_name', 'transfer_status', 'transfer_type',\n",
      "       'primary_player_position', 'price_in_pounds', 'previous_club',\n",
      "       'new_club', 'previous_league', 'new_league', 'big_deal', 'flow_id'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "# Print the column names of the raw DataFrame, df_guardian_transfers_all_raw\n",
    "print(df_guardian_transfers_all_raw.columns)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The dataset has twelve features (columns)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "transfer_id                  int64\n",
       "transfer_year                int64\n",
       "window_day                   int64\n",
       "window_open                 object\n",
       "timestamp                   object\n",
       "player_name                 object\n",
       "transfer_status             object\n",
       "transfer_type               object\n",
       "primary_player_position     object\n",
       "price_in_pounds            float64\n",
       "previous_club               object\n",
       "new_club                    object\n",
       "previous_league             object\n",
       "new_league                  object\n",
       "big_deal                    object\n",
       "flow_id                      int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Data types of the features of the raw DataFrame, df_guardian_transfers_all_raw\n",
    "df_guardian_transfers_all_raw.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 7219 entries, 0 to 7218\n",
      "Data columns (total 16 columns):\n",
      " #   Column                   Non-Null Count  Dtype  \n",
      "---  ------                   --------------  -----  \n",
      " 0   transfer_id              7219 non-null   int64  \n",
      " 1   transfer_year            7219 non-null   int64  \n",
      " 2   window_day               7219 non-null   int64  \n",
      " 3   window_open              7219 non-null   object \n",
      " 4   timestamp                7219 non-null   object \n",
      " 5   player_name              7219 non-null   object \n",
      " 6   transfer_status          7216 non-null   object \n",
      " 7   transfer_type            7219 non-null   object \n",
      " 8   primary_player_position  5614 non-null   object \n",
      " 9   price_in_pounds          2077 non-null   float64\n",
      " 10  previous_club            7219 non-null   object \n",
      " 11  new_club                 7219 non-null   object \n",
      " 12  previous_league          7216 non-null   object \n",
      " 13  new_league               7217 non-null   object \n",
      " 14  big_deal                 2193 non-null   object \n",
      " 15  flow_id                  7219 non-null   int64  \n",
      "dtypes: float64(1), int64(4), object(11)\n",
      "memory usage: 902.5+ KB\n"
     ]
    }
   ],
   "source": [
    "# Info for the raw DataFrame, df_guardian_transfers_all_raw\n",
    "df_guardian_transfers_all_raw.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>transfer_id</th>\n",
       "      <th>transfer_year</th>\n",
       "      <th>window_day</th>\n",
       "      <th>price_in_pounds</th>\n",
       "      <th>flow_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>7219.000000</td>\n",
       "      <td>7219.000000</td>\n",
       "      <td>7219.000000</td>\n",
       "      <td>2.077000e+03</td>\n",
       "      <td>7219.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>1.033523</td>\n",
       "      <td>2018.758692</td>\n",
       "      <td>45.576673</td>\n",
       "      <td>8.547637e+06</td>\n",
       "      <td>65.337443</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.183817</td>\n",
       "      <td>1.287752</td>\n",
       "      <td>33.319495</td>\n",
       "      <td>1.270805e+07</td>\n",
       "      <td>83.022501</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>2017.000000</td>\n",
       "      <td>-47.000000</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>2018.000000</td>\n",
       "      <td>21.000000</td>\n",
       "      <td>1.800000e+06</td>\n",
       "      <td>7.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>2019.000000</td>\n",
       "      <td>45.000000</td>\n",
       "      <td>4.400000e+06</td>\n",
       "      <td>28.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>2020.000000</td>\n",
       "      <td>68.000000</td>\n",
       "      <td>1.052000e+07</td>\n",
       "      <td>95.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>3.000000</td>\n",
       "      <td>2021.000000</td>\n",
       "      <td>216.000000</td>\n",
       "      <td>1.980000e+08</td>\n",
       "      <td>425.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       transfer_id  transfer_year   window_day  price_in_pounds      flow_id\n",
       "count  7219.000000    7219.000000  7219.000000     2.077000e+03  7219.000000\n",
       "mean      1.033523    2018.758692    45.576673     8.547637e+06    65.337443\n",
       "std       0.183817       1.287752    33.319495     1.270805e+07    83.022501\n",
       "min       1.000000    2017.000000   -47.000000     0.000000e+00     1.000000\n",
       "25%       1.000000    2018.000000    21.000000     1.800000e+06     7.000000\n",
       "50%       1.000000    2019.000000    45.000000     4.400000e+06    28.000000\n",
       "75%       1.000000    2020.000000    68.000000     1.052000e+07    95.000000\n",
       "max       3.000000    2021.000000   216.000000     1.980000e+08   425.000000"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Description of the raw DataFrame, df_guardian_transfers_all_raw, showing some summary statistics for each numberical column in the DataFrame\n",
    "df_guardian_transfers_all_raw.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<AxesSubplot:>"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 2160x504 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot visualisation of the missing values for each feature of the raw DataFrame, df_guardian_transfers_all_raw\n",
    "msno.matrix(df_guardian_transfers_all_raw, figsize = (30, 7))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "transfer_status               3\n",
       "primary_player_position    1605\n",
       "price_in_pounds            5142\n",
       "previous_league               3\n",
       "new_league                    2\n",
       "big_deal                   5026\n",
       "dtype: int64"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Counts of missing values\n",
    "null_value_stats = df_guardian_transfers_all_raw.isnull().sum(axis=0)\n",
    "null_value_stats[null_value_stats != 0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The visualisation shows us very quickly that there a few missing values in the ... columns."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "\n",
    "<a id='section4'></a>\n",
    "\n",
    "## <a id='#section4'>4. Data Engineering</a>\n",
    "Before we answer the questions in the brief through [Exploratory Data Analysis (EDA)](#section5), we'll first need to clean and wrangle the datasets to a form that meet our needs."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### <a id='#section4.1'>4.1. Assign Raw DataFrames to New Engineered DataFrames</a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Assign Raw DataFrames to new Engineered DataFrames\n",
    "df_guardian_transfers_all = df_guardian_transfers_all_raw.copy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>transfer_id</th>\n",
       "      <th>transfer_year</th>\n",
       "      <th>window_day</th>\n",
       "      <th>window_open</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>player_name</th>\n",
       "      <th>transfer_status</th>\n",
       "      <th>transfer_type</th>\n",
       "      <th>primary_player_position</th>\n",
       "      <th>price_in_pounds</th>\n",
       "      <th>previous_club</th>\n",
       "      <th>new_club</th>\n",
       "      <th>previous_league</th>\n",
       "      <th>new_league</th>\n",
       "      <th>big_deal</th>\n",
       "      <th>flow_id</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>Zito Luvumbo</td>\n",
       "      <td>done deal</td>\n",
       "      <td>loan</td>\n",
       "      <td>W</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Cagliari</td>\n",
       "      <td>Como</td>\n",
       "      <td>Serie A</td>\n",
       "      <td>Serie C</td>\n",
       "      <td>NaN</td>\n",
       "      <td>100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>David Juncà</td>\n",
       "      <td>done deal</td>\n",
       "      <td>free</td>\n",
       "      <td>D</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Celta Vigo</td>\n",
       "      <td>Girona</td>\n",
       "      <td>La Liga</td>\n",
       "      <td>Spanish Segunda</td>\n",
       "      <td>NaN</td>\n",
       "      <td>241</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>Giuseppe Pezzella</td>\n",
       "      <td>done deal</td>\n",
       "      <td>loan</td>\n",
       "      <td>D</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Parma</td>\n",
       "      <td>Atalanta</td>\n",
       "      <td>Serie B</td>\n",
       "      <td>Serie A</td>\n",
       "      <td>NaN</td>\n",
       "      <td>106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>Pablo Rosario</td>\n",
       "      <td>done deal</td>\n",
       "      <td>fee</td>\n",
       "      <td>M</td>\n",
       "      <td>5130000.0</td>\n",
       "      <td>PSV Eindhoven</td>\n",
       "      <td>Nice</td>\n",
       "      <td>Eredivisie</td>\n",
       "      <td>Ligue 1</td>\n",
       "      <td>Yes</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>Martín Calderón</td>\n",
       "      <td>done deal</td>\n",
       "      <td>undisclosed</td>\n",
       "      <td>M</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Real Madrid</td>\n",
       "      <td>Cádiz</td>\n",
       "      <td>La Liga</td>\n",
       "      <td>La Liga</td>\n",
       "      <td>NaN</td>\n",
       "      <td>265</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   transfer_id  transfer_year  window_day window_open   timestamp  \\\n",
       "0            1           2021          48  2021-06-09  2021-07-27   \n",
       "1            2           2021          48  2021-06-09  2021-07-27   \n",
       "2            1           2021          48  2021-06-09  2021-07-27   \n",
       "3            1           2021          48  2021-06-09  2021-07-27   \n",
       "4            1           2021          48  2021-06-09  2021-07-27   \n",
       "\n",
       "         player_name transfer_status transfer_type primary_player_position  \\\n",
       "0       Zito Luvumbo       done deal          loan                       W   \n",
       "1        David Juncà       done deal          free                       D   \n",
       "2  Giuseppe Pezzella       done deal          loan                       D   \n",
       "3      Pablo Rosario       done deal           fee                       M   \n",
       "4    Martín Calderón       done deal   undisclosed                       M   \n",
       "\n",
       "   price_in_pounds  previous_club  new_club previous_league       new_league  \\\n",
       "0              NaN       Cagliari      Como         Serie A          Serie C   \n",
       "1              NaN     Celta Vigo    Girona         La Liga  Spanish Segunda   \n",
       "2              NaN          Parma  Atalanta         Serie B          Serie A   \n",
       "3        5130000.0  PSV Eindhoven      Nice      Eredivisie          Ligue 1   \n",
       "4              NaN    Real Madrid     Cádiz         La Liga          La Liga   \n",
       "\n",
       "  big_deal  flow_id  \n",
       "0      NaN      100  \n",
       "1      NaN      241  \n",
       "2      NaN      106  \n",
       "3      Yes        8  \n",
       "4      NaN      265  "
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_guardian_transfers_all.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### <a id='#section4.2'>4.2. String Cleaning</a>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Player"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Remove accents and create lowercase name\n",
    "df_guardian_transfers_all['player_name_lower'] = (df_guardian_transfers_all['player_name']\n",
    "                                                          .str.normalize('NFKD')\n",
    "                                                          .str.encode('ascii', errors='ignore')\n",
    "                                                          .str.decode('utf-8')\n",
    "                                                          .str.lower()\n",
    "                                                     )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "# First Name Lower\n",
    "df_guardian_transfers_all['first_name_lower'] = df_guardian_transfers_all['player_name_lower'].str.rsplit(' ', 0).str[0]\n",
    "\n",
    "# Last Name Lower\n",
    "df_guardian_transfers_all['last_name_lower'] = df_guardian_transfers_all['player_name_lower'].str.rsplit(' ', 1).str[-1]\n",
    "\n",
    "# First Initial Lower\n",
    "df_guardian_transfers_all['first_initial_lower'] = df_guardian_transfers_all['player_name_lower'].astype(str).str[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Season"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Map season to DataFrame\n",
    "df_guardian_transfers_all['season'] = df_guardian_transfers_all['transfer_year'].map(dict_seasons)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>transfer_id</th>\n",
       "      <th>transfer_year</th>\n",
       "      <th>window_day</th>\n",
       "      <th>window_open</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>player_name</th>\n",
       "      <th>transfer_status</th>\n",
       "      <th>transfer_type</th>\n",
       "      <th>primary_player_position</th>\n",
       "      <th>price_in_pounds</th>\n",
       "      <th>previous_club</th>\n",
       "      <th>new_club</th>\n",
       "      <th>previous_league</th>\n",
       "      <th>new_league</th>\n",
       "      <th>big_deal</th>\n",
       "      <th>flow_id</th>\n",
       "      <th>player_name_lower</th>\n",
       "      <th>first_name_lower</th>\n",
       "      <th>last_name_lower</th>\n",
       "      <th>first_initial_lower</th>\n",
       "      <th>season</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>Zito Luvumbo</td>\n",
       "      <td>done deal</td>\n",
       "      <td>loan</td>\n",
       "      <td>W</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Cagliari</td>\n",
       "      <td>Como</td>\n",
       "      <td>Serie A</td>\n",
       "      <td>Serie C</td>\n",
       "      <td>NaN</td>\n",
       "      <td>100</td>\n",
       "      <td>zito luvumbo</td>\n",
       "      <td>zito</td>\n",
       "      <td>luvumbo</td>\n",
       "      <td>z</td>\n",
       "      <td>2021/2022</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>David Juncà</td>\n",
       "      <td>done deal</td>\n",
       "      <td>free</td>\n",
       "      <td>D</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Celta Vigo</td>\n",
       "      <td>Girona</td>\n",
       "      <td>La Liga</td>\n",
       "      <td>Spanish Segunda</td>\n",
       "      <td>NaN</td>\n",
       "      <td>241</td>\n",
       "      <td>david junca</td>\n",
       "      <td>david</td>\n",
       "      <td>junca</td>\n",
       "      <td>d</td>\n",
       "      <td>2021/2022</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>Giuseppe Pezzella</td>\n",
       "      <td>done deal</td>\n",
       "      <td>loan</td>\n",
       "      <td>D</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Parma</td>\n",
       "      <td>Atalanta</td>\n",
       "      <td>Serie B</td>\n",
       "      <td>Serie A</td>\n",
       "      <td>NaN</td>\n",
       "      <td>106</td>\n",
       "      <td>giuseppe pezzella</td>\n",
       "      <td>giuseppe</td>\n",
       "      <td>pezzella</td>\n",
       "      <td>g</td>\n",
       "      <td>2021/2022</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>Pablo Rosario</td>\n",
       "      <td>done deal</td>\n",
       "      <td>fee</td>\n",
       "      <td>M</td>\n",
       "      <td>5130000.0</td>\n",
       "      <td>PSV Eindhoven</td>\n",
       "      <td>Nice</td>\n",
       "      <td>Eredivisie</td>\n",
       "      <td>Ligue 1</td>\n",
       "      <td>Yes</td>\n",
       "      <td>8</td>\n",
       "      <td>pablo rosario</td>\n",
       "      <td>pablo</td>\n",
       "      <td>rosario</td>\n",
       "      <td>p</td>\n",
       "      <td>2021/2022</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>Martín Calderón</td>\n",
       "      <td>done deal</td>\n",
       "      <td>undisclosed</td>\n",
       "      <td>M</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Real Madrid</td>\n",
       "      <td>Cádiz</td>\n",
       "      <td>La Liga</td>\n",
       "      <td>La Liga</td>\n",
       "      <td>NaN</td>\n",
       "      <td>265</td>\n",
       "      <td>martin calderon</td>\n",
       "      <td>martin</td>\n",
       "      <td>calderon</td>\n",
       "      <td>m</td>\n",
       "      <td>2021/2022</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   transfer_id  transfer_year  window_day window_open   timestamp  \\\n",
       "0            1           2021          48  2021-06-09  2021-07-27   \n",
       "1            2           2021          48  2021-06-09  2021-07-27   \n",
       "2            1           2021          48  2021-06-09  2021-07-27   \n",
       "3            1           2021          48  2021-06-09  2021-07-27   \n",
       "4            1           2021          48  2021-06-09  2021-07-27   \n",
       "\n",
       "         player_name transfer_status transfer_type primary_player_position  \\\n",
       "0       Zito Luvumbo       done deal          loan                       W   \n",
       "1        David Juncà       done deal          free                       D   \n",
       "2  Giuseppe Pezzella       done deal          loan                       D   \n",
       "3      Pablo Rosario       done deal           fee                       M   \n",
       "4    Martín Calderón       done deal   undisclosed                       M   \n",
       "\n",
       "   price_in_pounds  previous_club  new_club previous_league       new_league  \\\n",
       "0              NaN       Cagliari      Como         Serie A          Serie C   \n",
       "1              NaN     Celta Vigo    Girona         La Liga  Spanish Segunda   \n",
       "2              NaN          Parma  Atalanta         Serie B          Serie A   \n",
       "3        5130000.0  PSV Eindhoven      Nice      Eredivisie          Ligue 1   \n",
       "4              NaN    Real Madrid     Cádiz         La Liga          La Liga   \n",
       "\n",
       "  big_deal  flow_id  player_name_lower first_name_lower last_name_lower  \\\n",
       "0      NaN      100       zito luvumbo             zito         luvumbo   \n",
       "1      NaN      241        david junca            david           junca   \n",
       "2      NaN      106  giuseppe pezzella         giuseppe        pezzella   \n",
       "3      Yes        8      pablo rosario            pablo         rosario   \n",
       "4      NaN      265    martin calderon           martin        calderon   \n",
       "\n",
       "  first_initial_lower     season  \n",
       "0                   z  2021/2022  \n",
       "1                   d  2021/2022  \n",
       "2                   g  2021/2022  \n",
       "3                   p  2021/2022  \n",
       "4                   m  2021/2022  "
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_guardian_transfers_all.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Position"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['W', 'D', 'M', 'F', 'GK', nan]"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lst_postions = list(df_guardian_transfers_all['primary_player_position'].unique())\n",
    "lst_postions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Map grouped positions to DataFrame\n",
    "df_guardian_transfers_all['primary_player_position_grouped'] = df_guardian_transfers_all['primary_player_position'].map(dict_positions_grouped)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##### Goalkeeper / Outfielder"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Separate Goalkeeper and Outfielders\n",
    "df_guardian_transfers_all['outfielder_goalkeeper'] = np.where(df_guardian_transfers_all['primary_player_position_grouped'] == 'Goalkeeper', 'Goalkeeper', 'Outfielder')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### <a id='#section4.3'>4.3. Filter Players in 'Big 5' European Leagues and MLS</a>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['Serie C',\n",
       " 'Spanish Segunda',\n",
       " 'Serie A',\n",
       " 'Ligue 1',\n",
       " 'La Liga',\n",
       " 'Serie B',\n",
       " 'Qatar Stars League',\n",
       " 'Premier League',\n",
       " 'Portugal Liga NOS',\n",
       " 'Serie D',\n",
       " '3. Bundesliga',\n",
       " 'Scottish Premiership',\n",
       " 'Ligue 2',\n",
       " 'National',\n",
       " 'Swiss Challenge League',\n",
       " 'MLS',\n",
       " 'National 2',\n",
       " '2. Bundesliga',\n",
       " 'Bayern Regionaliga',\n",
       " '1. Bundesliga',\n",
       " 'Turkish Super Lig',\n",
       " 'League One',\n",
       " 'Championship',\n",
       " 'Segunda B',\n",
       " 'Danish SuperLiga',\n",
       " 'Russian Premier League',\n",
       " 'National League',\n",
       " 'Belgian Jupiler Pro League',\n",
       " 'Eredivisie',\n",
       " 'Saudi Professional League',\n",
       " 'Swiss Superleague',\n",
       " 'UAE Gulf League',\n",
       " 'J League',\n",
       " 'Austrian Bundesliga',\n",
       " 'Croatian 1.HNL',\n",
       " 'Free agent',\n",
       " 'NL South',\n",
       " 'Austrian Bundeliga',\n",
       " 'K-League',\n",
       " 'Greek Super League',\n",
       " 'Super League',\n",
       " 'League Two',\n",
       " 'Liga MX',\n",
       " 'Austrian 2. Liga',\n",
       " 'Polish Ekstraklasa',\n",
       " 'Dutch Kampioen Divisie',\n",
       " 'Fortuna Liga',\n",
       " 'Romanian Liga 1',\n",
       " 'Serbian Super Liga',\n",
       " nan,\n",
       " 'Brazilian Serie A',\n",
       " 'Estonian League',\n",
       " 'Ukrainian Premier League',\n",
       " 'Colombian Primera',\n",
       " 'Bulgarian League',\n",
       " 'Serbian Prva Liga',\n",
       " 'Scottish Championship',\n",
       " 'Cyprus',\n",
       " 'Allsvenskan',\n",
       " 'Czech First League',\n",
       " 'A-League',\n",
       " 'Poland 3. Liga',\n",
       " 'Dutch Kampioen',\n",
       " 'Bulgaria',\n",
       " 'Croatian top flight',\n",
       " 'Belgium',\n",
       " 'Greek Superleague 1',\n",
       " 'Superliga',\n",
       " 'Spal',\n",
       " 'Slovenian Prva Liga',\n",
       " 'Belgian Proximus',\n",
       " 'Algeria',\n",
       " 'Slovenian Liga',\n",
       " 'National League North',\n",
       " 'Greece Superleague',\n",
       " 'Pescara',\n",
       " 'Ereste Divisie',\n",
       " 'Chinese Super League',\n",
       " '1. HNL',\n",
       " 'Regionalliga',\n",
       " 'Belgian D2',\n",
       " 'Danubio',\n",
       " 'Eliteserien',\n",
       " 'Eerste Amateur',\n",
       " 'Slovak Fortuna Liga',\n",
       " 'Bulgarian Liga',\n",
       " 'Belgian Second Division',\n",
       " 'France CFA',\n",
       " 'Saudi League',\n",
       " 'Bundesliga 2.',\n",
       " 'Belgian Proximus League',\n",
       " 'Retired',\n",
       " 'Eerste Divisie',\n",
       " 'Azerbaijan League',\n",
       " 'Northern Premier League',\n",
       " 'Bourg-en-Bresse',\n",
       " 'Championnat National',\n",
       " 'Poland Ekstraklasa',\n",
       " 'Hungarian NB I',\n",
       " 'Argentina Primera Division',\n",
       " 'Cypriot First Division',\n",
       " 'Mouscron',\n",
       " 'Chilean Primera',\n",
       " 'Belgian Super League',\n",
       " '3.Liga',\n",
       " 'Norwegian Eliteserien',\n",
       " 'Croatia HNL Liga',\n",
       " 'QPR',\n",
       " 'National League South',\n",
       " 'Ecuador Liga Pro',\n",
       " 'Greece Super League',\n",
       " 'Regionalliga West',\n",
       " 'Portuguese Primeira Liga',\n",
       " 'Evo-Stik League South',\n",
       " 'retired',\n",
       " 'Portuguese Segunda Liga',\n",
       " 'Kazakh League',\n",
       " 'Regionalliga Südwest',\n",
       " 'Spanish Segunda B',\n",
       " 'Russian Premier Liga',\n",
       " 'Argentina Primeira',\n",
       " 'Slovak Super Liga',\n",
       " 'Qatari Stars League',\n",
       " 'NI Premiership',\n",
       " 'Cyprus First Division',\n",
       " 'Ecuador Serie A',\n",
       " 'Croatian League',\n",
       " 'Czech League',\n",
       " 'Polish 1 Liga',\n",
       " 'Cypriot League',\n",
       " 'Cercle Brugge',\n",
       " 'Turkish Süper Lig',\n",
       " 'Parva Liga',\n",
       " 'Belgian B Division',\n",
       " 'Eredivise',\n",
       " 'USL',\n",
       " 'Bostik Football League',\n",
       " 'Lega Pro',\n",
       " '2 Bundesliga',\n",
       " 'Kazakh Premier Liga',\n",
       " 'Slovakian Fortuna Liga',\n",
       " 'Kazakh Premier League',\n",
       " 'Qatari Stars Leagur',\n",
       " 'Israeli Premier League',\n",
       " 'Slovakia Fortuna Liga',\n",
       " 'Bulgarian First League',\n",
       " 'Israeli Ligat',\n",
       " 'League of Ireland',\n",
       " 'Belgian First Division',\n",
       " 'Southern League',\n",
       " 'Uruguayan Primera División',\n",
       " '2. Bungesliga',\n",
       " 'Maltese Premier League',\n",
       " 'Turkey Super Lig',\n",
       " 'Liga Pro',\n",
       " 'Cyprus 1. Division',\n",
       " 'Ecuador Primera',\n",
       " 'UAE Arabian Gulf League',\n",
       " 'Chilean Primera División',\n",
       " 'Austrian First League',\n",
       " 'Serie  B',\n",
       " 'Brasileiro',\n",
       " 'Southern League Premier Division',\n",
       " 'Tercera División de México',\n",
       " 'Premier League (Israel)',\n",
       " 'Liga Super (Malaysia)',\n",
       " 'National 1',\n",
       " 'US Orléans',\n",
       " 'Belgian second division',\n",
       " 'Primera División (Mexico)',\n",
       " 'Premier League (Russia)',\n",
       " 'Premier League (Kazakhstan)']"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lst_leagues = list(df_guardian_transfers_all['new_league'].unique())\n",
    "lst_leagues"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Filter plays in the 'Big 5' European Leagues and MLS\n",
    "\n",
    "## Define list of countries\n",
    "lst_big5_mls_leagues = ['Serie A', 'Ligue 1', 'La Liga', 'Premier League', '1. Bundesliga', 'MLS']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_guardian_transfers_all['previous_league_isbig5'] = np.where(df_guardian_transfers_all['previous_league'].isin(lst_big5_mls_leagues), True, False)\n",
    "df_guardian_transfers_all['new_league_isbig5'] = np.where(df_guardian_transfers_all['new_league'].isin(lst_big5_mls_leagues), True, False)\n",
    "df_guardian_transfers_all['isbig5transfer'] = np.where((df_guardian_transfers_all['previous_league_isbig5'] == True) | (df_guardian_transfers_all['new_league_isbig5'] == True), True, False)\n",
    "df_guardian_transfers_all = df_guardian_transfers_all[df_guardian_transfers_all['isbig5transfer'] == True]\n",
    "df_guardian_transfers_big5 = df_guardian_transfers_all.drop(['previous_league_isbig5', 'new_league_isbig5', 'isbig5transfer'], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(7214, 26)"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_guardian_transfers_all.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(7214, 23)"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_guardian_transfers_big5.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>transfer_id</th>\n",
       "      <th>transfer_year</th>\n",
       "      <th>window_day</th>\n",
       "      <th>window_open</th>\n",
       "      <th>timestamp</th>\n",
       "      <th>player_name</th>\n",
       "      <th>transfer_status</th>\n",
       "      <th>transfer_type</th>\n",
       "      <th>primary_player_position</th>\n",
       "      <th>price_in_pounds</th>\n",
       "      <th>previous_club</th>\n",
       "      <th>new_club</th>\n",
       "      <th>previous_league</th>\n",
       "      <th>new_league</th>\n",
       "      <th>big_deal</th>\n",
       "      <th>flow_id</th>\n",
       "      <th>player_name_lower</th>\n",
       "      <th>first_name_lower</th>\n",
       "      <th>last_name_lower</th>\n",
       "      <th>first_initial_lower</th>\n",
       "      <th>season</th>\n",
       "      <th>primary_player_position_grouped</th>\n",
       "      <th>outfielder_goalkeeper</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>Zito Luvumbo</td>\n",
       "      <td>done deal</td>\n",
       "      <td>loan</td>\n",
       "      <td>W</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Cagliari</td>\n",
       "      <td>Como</td>\n",
       "      <td>Serie A</td>\n",
       "      <td>Serie C</td>\n",
       "      <td>NaN</td>\n",
       "      <td>100</td>\n",
       "      <td>zito luvumbo</td>\n",
       "      <td>zito</td>\n",
       "      <td>luvumbo</td>\n",
       "      <td>z</td>\n",
       "      <td>2021/2022</td>\n",
       "      <td>Forward</td>\n",
       "      <td>Outfielder</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>David Juncà</td>\n",
       "      <td>done deal</td>\n",
       "      <td>free</td>\n",
       "      <td>D</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Celta Vigo</td>\n",
       "      <td>Girona</td>\n",
       "      <td>La Liga</td>\n",
       "      <td>Spanish Segunda</td>\n",
       "      <td>NaN</td>\n",
       "      <td>241</td>\n",
       "      <td>david junca</td>\n",
       "      <td>david</td>\n",
       "      <td>junca</td>\n",
       "      <td>d</td>\n",
       "      <td>2021/2022</td>\n",
       "      <td>Defender</td>\n",
       "      <td>Outfielder</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>Giuseppe Pezzella</td>\n",
       "      <td>done deal</td>\n",
       "      <td>loan</td>\n",
       "      <td>D</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Parma</td>\n",
       "      <td>Atalanta</td>\n",
       "      <td>Serie B</td>\n",
       "      <td>Serie A</td>\n",
       "      <td>NaN</td>\n",
       "      <td>106</td>\n",
       "      <td>giuseppe pezzella</td>\n",
       "      <td>giuseppe</td>\n",
       "      <td>pezzella</td>\n",
       "      <td>g</td>\n",
       "      <td>2021/2022</td>\n",
       "      <td>Defender</td>\n",
       "      <td>Outfielder</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>Pablo Rosario</td>\n",
       "      <td>done deal</td>\n",
       "      <td>fee</td>\n",
       "      <td>M</td>\n",
       "      <td>5130000.0</td>\n",
       "      <td>PSV Eindhoven</td>\n",
       "      <td>Nice</td>\n",
       "      <td>Eredivisie</td>\n",
       "      <td>Ligue 1</td>\n",
       "      <td>Yes</td>\n",
       "      <td>8</td>\n",
       "      <td>pablo rosario</td>\n",
       "      <td>pablo</td>\n",
       "      <td>rosario</td>\n",
       "      <td>p</td>\n",
       "      <td>2021/2022</td>\n",
       "      <td>Midfielder</td>\n",
       "      <td>Outfielder</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "      <td>2021</td>\n",
       "      <td>48</td>\n",
       "      <td>2021-06-09</td>\n",
       "      <td>2021-07-27</td>\n",
       "      <td>Martín Calderón</td>\n",
       "      <td>done deal</td>\n",
       "      <td>undisclosed</td>\n",
       "      <td>M</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Real Madrid</td>\n",
       "      <td>Cádiz</td>\n",
       "      <td>La Liga</td>\n",
       "      <td>La Liga</td>\n",
       "      <td>NaN</td>\n",
       "      <td>265</td>\n",
       "      <td>martin calderon</td>\n",
       "      <td>martin</td>\n",
       "      <td>calderon</td>\n",
       "      <td>m</td>\n",
       "      <td>2021/2022</td>\n",
       "      <td>Midfielder</td>\n",
       "      <td>Outfielder</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7214</th>\n",
       "      <td>1</td>\n",
       "      <td>2017</td>\n",
       "      <td>-38</td>\n",
       "      <td>2017-07-01</td>\n",
       "      <td>2017-05-24</td>\n",
       "      <td>Joey Barton</td>\n",
       "      <td>done deal</td>\n",
       "      <td>released</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Burnley</td>\n",
       "      <td>Free agent</td>\n",
       "      <td>Premier League</td>\n",
       "      <td>Free agent</td>\n",
       "      <td>No</td>\n",
       "      <td>2</td>\n",
       "      <td>joey barton</td>\n",
       "      <td>joey</td>\n",
       "      <td>barton</td>\n",
       "      <td>j</td>\n",
       "      <td>2017/2018</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Outfielder</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7215</th>\n",
       "      <td>1</td>\n",
       "      <td>2017</td>\n",
       "      <td>-38</td>\n",
       "      <td>2017-07-01</td>\n",
       "      <td>2017-05-24</td>\n",
       "      <td>Matthias Ostrzolek</td>\n",
       "      <td>done deal</td>\n",
       "      <td>fee</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Hamburg</td>\n",
       "      <td>Hannover 96</td>\n",
       "      <td>1. Bundesliga</td>\n",
       "      <td>1. Bundesliga</td>\n",
       "      <td>No</td>\n",
       "      <td>1</td>\n",
       "      <td>matthias ostrzolek</td>\n",
       "      <td>matthias</td>\n",
       "      <td>ostrzolek</td>\n",
       "      <td>m</td>\n",
       "      <td>2017/2018</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Outfielder</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7216</th>\n",
       "      <td>1</td>\n",
       "      <td>2017</td>\n",
       "      <td>-38</td>\n",
       "      <td>2017-07-01</td>\n",
       "      <td>2017-05-24</td>\n",
       "      <td>Benoît Trémoulinas</td>\n",
       "      <td>done deal</td>\n",
       "      <td>released</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.0</td>\n",
       "      <td>Sevilla</td>\n",
       "      <td>Free agent</td>\n",
       "      <td>La Liga</td>\n",
       "      <td>Free agent</td>\n",
       "      <td>No</td>\n",
       "      <td>1</td>\n",
       "      <td>benoit tremoulinas</td>\n",
       "      <td>benoit</td>\n",
       "      <td>tremoulinas</td>\n",
       "      <td>b</td>\n",
       "      <td>2017/2018</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Outfielder</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7217</th>\n",
       "      <td>1</td>\n",
       "      <td>2017</td>\n",
       "      <td>-38</td>\n",
       "      <td>2017-07-01</td>\n",
       "      <td>2017-05-24</td>\n",
       "      <td>Youri Tielemans</td>\n",
       "      <td>done deal</td>\n",
       "      <td>fee</td>\n",
       "      <td>NaN</td>\n",
       "      <td>21600000.0</td>\n",
       "      <td>Anderlecht</td>\n",
       "      <td>Monaco</td>\n",
       "      <td>Belgian Jupiler Pro League</td>\n",
       "      <td>Ligue 1</td>\n",
       "      <td>Yes</td>\n",
       "      <td>1</td>\n",
       "      <td>youri tielemans</td>\n",
       "      <td>youri</td>\n",
       "      <td>tielemans</td>\n",
       "      <td>y</td>\n",
       "      <td>2017/2018</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Outfielder</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7218</th>\n",
       "      <td>1</td>\n",
       "      <td>2017</td>\n",
       "      <td>-39</td>\n",
       "      <td>2017-07-01</td>\n",
       "      <td>2017-05-23</td>\n",
       "      <td>Juan Cuadrado</td>\n",
       "      <td>done deal</td>\n",
       "      <td>fee</td>\n",
       "      <td>NaN</td>\n",
       "      <td>17330000.0</td>\n",
       "      <td>Chelsea</td>\n",
       "      <td>Juventus</td>\n",
       "      <td>Premier League</td>\n",
       "      <td>Serie A</td>\n",
       "      <td>Yes</td>\n",
       "      <td>1</td>\n",
       "      <td>juan cuadrado</td>\n",
       "      <td>juan</td>\n",
       "      <td>cuadrado</td>\n",
       "      <td>j</td>\n",
       "      <td>2017/2018</td>\n",
       "      <td>NaN</td>\n",
       "      <td>Outfielder</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>7214 rows × 23 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      transfer_id  transfer_year  window_day window_open   timestamp  \\\n",
       "0               1           2021          48  2021-06-09  2021-07-27   \n",
       "1               2           2021          48  2021-06-09  2021-07-27   \n",
       "2               1           2021          48  2021-06-09  2021-07-27   \n",
       "3               1           2021          48  2021-06-09  2021-07-27   \n",
       "4               1           2021          48  2021-06-09  2021-07-27   \n",
       "...           ...            ...         ...         ...         ...   \n",
       "7214            1           2017         -38  2017-07-01  2017-05-24   \n",
       "7215            1           2017         -38  2017-07-01  2017-05-24   \n",
       "7216            1           2017         -38  2017-07-01  2017-05-24   \n",
       "7217            1           2017         -38  2017-07-01  2017-05-24   \n",
       "7218            1           2017         -39  2017-07-01  2017-05-23   \n",
       "\n",
       "             player_name transfer_status transfer_type  \\\n",
       "0           Zito Luvumbo       done deal          loan   \n",
       "1            David Juncà       done deal          free   \n",
       "2      Giuseppe Pezzella       done deal          loan   \n",
       "3          Pablo Rosario       done deal           fee   \n",
       "4        Martín Calderón       done deal   undisclosed   \n",
       "...                  ...             ...           ...   \n",
       "7214         Joey Barton       done deal      released   \n",
       "7215  Matthias Ostrzolek       done deal           fee   \n",
       "7216  Benoît Trémoulinas       done deal      released   \n",
       "7217     Youri Tielemans       done deal           fee   \n",
       "7218       Juan Cuadrado       done deal           fee   \n",
       "\n",
       "     primary_player_position  price_in_pounds  previous_club     new_club  \\\n",
       "0                          W              NaN       Cagliari         Como   \n",
       "1                          D              NaN     Celta Vigo       Girona   \n",
       "2                          D              NaN          Parma     Atalanta   \n",
       "3                          M        5130000.0  PSV Eindhoven         Nice   \n",
       "4                          M              NaN    Real Madrid        Cádiz   \n",
       "...                      ...              ...            ...          ...   \n",
       "7214                     NaN              0.0        Burnley   Free agent   \n",
       "7215                     NaN              0.0        Hamburg  Hannover 96   \n",
       "7216                     NaN              0.0        Sevilla   Free agent   \n",
       "7217                     NaN       21600000.0     Anderlecht       Monaco   \n",
       "7218                     NaN       17330000.0        Chelsea     Juventus   \n",
       "\n",
       "                 previous_league       new_league big_deal  flow_id  \\\n",
       "0                        Serie A          Serie C      NaN      100   \n",
       "1                        La Liga  Spanish Segunda      NaN      241   \n",
       "2                        Serie B          Serie A      NaN      106   \n",
       "3                     Eredivisie          Ligue 1      Yes        8   \n",
       "4                        La Liga          La Liga      NaN      265   \n",
       "...                          ...              ...      ...      ...   \n",
       "7214              Premier League       Free agent       No        2   \n",
       "7215               1. Bundesliga    1. Bundesliga       No        1   \n",
       "7216                     La Liga       Free agent       No        1   \n",
       "7217  Belgian Jupiler Pro League          Ligue 1      Yes        1   \n",
       "7218              Premier League          Serie A      Yes        1   \n",
       "\n",
       "       player_name_lower first_name_lower last_name_lower first_initial_lower  \\\n",
       "0           zito luvumbo             zito         luvumbo                   z   \n",
       "1            david junca            david           junca                   d   \n",
       "2      giuseppe pezzella         giuseppe        pezzella                   g   \n",
       "3          pablo rosario            pablo         rosario                   p   \n",
       "4        martin calderon           martin        calderon                   m   \n",
       "...                  ...              ...             ...                 ...   \n",
       "7214         joey barton             joey          barton                   j   \n",
       "7215  matthias ostrzolek         matthias       ostrzolek                   m   \n",
       "7216  benoit tremoulinas           benoit     tremoulinas                   b   \n",
       "7217     youri tielemans            youri       tielemans                   y   \n",
       "7218       juan cuadrado             juan        cuadrado                   j   \n",
       "\n",
       "         season primary_player_position_grouped outfielder_goalkeeper  \n",
       "0     2021/2022                         Forward            Outfielder  \n",
       "1     2021/2022                        Defender            Outfielder  \n",
       "2     2021/2022                        Defender            Outfielder  \n",
       "3     2021/2022                      Midfielder            Outfielder  \n",
       "4     2021/2022                      Midfielder            Outfielder  \n",
       "...         ...                             ...                   ...  \n",
       "7214  2017/2018                             NaN            Outfielder  \n",
       "7215  2017/2018                             NaN            Outfielder  \n",
       "7216  2017/2018                             NaN            Outfielder  \n",
       "7217  2017/2018                             NaN            Outfielder  \n",
       "7218  2017/2018                             NaN            Outfielder  \n",
       "\n",
       "[7214 rows x 23 columns]"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_guardian_transfers_big5"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### <a id='#section4.4'>4.4. Filter for 2017/2018 Season Onwards</a>\n",
    "This step is not required as the data only goes as far back as the 17/18 season."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['2021/2022', '2020/2021', '2019/2020', '2018/2019', '2017/2018']"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lst_seasons = list(df_guardian_transfers_all['season'].unique())\n",
    "lst_seasons"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "lst_seasons_1718_2122 = ['2017/2018', '2018/2019', '2019/2020', '2020/2021', '2021/2022']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_guardian_transfers_all_1718_2122 = df_guardian_transfers_all[df_guardian_transfers_all['season'].isin(lst_seasons_1718_2122)]\n",
    "df_guardian_transfers_big5_1718_2122 = df_guardian_transfers_all[df_guardian_transfers_all['season'].isin(lst_seasons_1718_2122)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(7214, 26)"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_guardian_transfers_all.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "\n",
    "<a id='section5'></a>\n",
    "\n",
    "## <a id='#section5'>5. Exporting the Engineered DataFrames</a>\n",
    "Export the two engineered [The Guardian](https://www.theguardian.com/uk) DataFrames as CSV files."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## Filename\n",
    "file_name = 'tm_player_joined_big5_mls'\n",
    "\n",
    "## Full season string\n",
    "full_season_string = '2016/2017 - 2021/2022'\n",
    "\n",
    "## Short season string\n",
    "short_season_string = '1617-2122'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Export DataFrame as a CSV file\n",
    "\n",
    "## Export a copy to the 'archive' subfolder of the TM folder, including the date\n",
    "df_tm_market_value_bio_status_select.to_csv(data_dir_tm + f'/engineered/{short_season_string}/joined/archive/' + f'{file_name}_{short_season_string}_last_updated_{today}.csv', index=None, header=True)\n",
    "\n",
    "## Export another copy to the TM folder called 'latest' (can be overwritten)\n",
    "df_tm_market_value_bio_status_select.to_csv(data_dir_tm + f'/engineered/{short_season_string}/joined/' + f'{file_name}_{short_season_string}_latest.csv', index=None, header=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Export DataFrame as a CSV file\n",
    "\n",
    "## All data\n",
    "df_guardian_transfers_all.to_csv(data_dir_tm + f'/engineered/transfers/archive/' + f'tm_player_transfers_all_last_updated_{today}.csv', index=None, header=True)\n",
    "df_guardian_transfers_all.to_csv(data_dir_tm + f'/engineered/transfers/' + f'tm_transfers_player_all_latest.csv', index=None, header=True)\n",
    "df_guardian_transfers_all.to_csv(data_dir + f'/export/' + f'tm_transfers_player_all_latest.csv', index=None, header=True)\n",
    "\n",
    "\n",
    "## 'Big 5' European Leagues\n",
    "df_transfers_big5.to_csv(data_dir_tm + f'/engineered/transfers/archive/' + f'tm_player_transfers_big5_last_updated_{today}.csv', index=None, header=True)\n",
    "df_transfers_big5.to_csv(data_dir_tm + f'/engineered/transfers/' + f'tm_player_transfers_big5_latest.csv', index=None, header=True)\n",
    "df_transfers_big5.to_csv(data_dir + f'/export/' + f'tm_player_transfers_big5_latest.csv', index=None, header=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <a id='#section6'>6. Summary</a>\n",
    "This Jupyter notebook engineered scraped football data from [The Guardian](https://www.theguardian.com/uk) using [pandas](http://pandas.pydata.org/) for data manipulation through DataFrames."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <a id='#section7'>7. Next Steps</a>\n",
    "The step is to use this data to..."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <a id='#section8'>8. References</a>\n",
    "*    \n",
    "*    \n",
    "*    "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "\n",
    "***Visit my website [eddwebster.com](https://www.eddwebster.com) or my [GitHub Repository](https://github.com/eddwebster) for more projects. If you'd like to get in contact, my Twitter handle is [@eddwebster](http://www.twitter.com/eddwebster) and my email is: edd.j.webster@gmail.com.***"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "[Back to the top](#top)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.6"
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "oldHeight": 642,
   "position": {
    "height": "664px",
    "left": "1119px",
    "right": "20px",
    "top": "-7px",
    "width": "489px"
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "varInspector_section_display": "block",
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}