fantabeto/3_players_dataset_creation.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "b2cd2177",
   "metadata": {},
   "source": [
    "Players dataset creation\n",
    "\n",
    "The Fantacalcio players list is manually downloaded from https://www.fantacalcio.it/quotazioni-fantacalcio\n",
    "\n",
    "Here, the players database is generated, by merging the Fantacalcio list to stats downloaded from http://fbref.com"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "7c65df92",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5ab35d0c",
   "metadata": {},
   "source": [
    "Load fbref data for outfield players and goalkeepers.\n",
    "\n",
    "Generate fbref player list, adding player surname (with special characters replaced to normal ones)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "b2d7073e",
   "metadata": {},
   "outputs": [],
   "source": [
    "rcsv = pd.read_csv('fbref_data/outfield_players.csv')   \n",
    "outfield_players = pd.DataFrame(rcsv)\n",
    "\n",
    "rcsv = pd.read_csv('fbref_data/keepers_players.csv')   \n",
    "keeper_players = pd.DataFrame(rcsv)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "667970f6",
   "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>player</th>\n",
       "      <th>team</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Oliver Abildgaard</td>\n",
       "      <td>Hellas Verona</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Tammy Abraham</td>\n",
       "      <td>Roma</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Francesco Acerbi</td>\n",
       "      <td>Inter</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Yacine Adli</td>\n",
       "      <td>Milan</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Michel Aebischer</td>\n",
       "      <td>Bologna</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>567</th>\n",
       "      <td>Ciprian Tătărușanu</td>\n",
       "      <td>Milan</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>568</th>\n",
       "      <td>Pietro Terracciano</td>\n",
       "      <td>Fiorentina</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>569</th>\n",
       "      <td>Guglielmo Vicario</td>\n",
       "      <td>Empoli</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>570</th>\n",
       "      <td>Jeroen Zoet</td>\n",
       "      <td>Spezia</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>571</th>\n",
       "      <td>Petar Zovko</td>\n",
       "      <td>Spezia</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>572 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                 player           team\n",
       "0     Oliver Abildgaard  Hellas Verona\n",
       "1         Tammy Abraham           Roma\n",
       "2      Francesco Acerbi          Inter\n",
       "3           Yacine Adli          Milan\n",
       "4      Michel Aebischer        Bologna\n",
       "..                  ...            ...\n",
       "567  Ciprian Tătărușanu          Milan\n",
       "568  Pietro Terracciano     Fiorentina\n",
       "569   Guglielmo Vicario         Empoli\n",
       "570         Jeroen Zoet         Spezia\n",
       "571         Petar Zovko         Spezia\n",
       "\n",
       "[572 rows x 2 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "players = pd.concat(   [ outfield_players[['player', 'team']], keeper_players[['player', 'team']] ], axis = 0, ignore_index = True)\n",
    "\n",
    "keepers_ID = len(outfield_players)\n",
    "\n",
    "players"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "e1e64596",
   "metadata": {},
   "outputs": [],
   "source": [
    "import unicodedata\n",
    "\n",
    "def normalize_name(input_str):\n",
    "    nfkd_form = unicodedata.normalize('NFKD', input_str)\n",
    "    only_ascii = nfkd_form.encode('ASCII', 'ignore')\n",
    "    return only_ascii.decode('utf-8')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "3078d6f3",
   "metadata": {},
   "outputs": [],
   "source": [
    "players['surname'] = players['player']\n",
    "players['initial'] = players['player']\n",
    "\n",
    "for i in range(players.shape[0]):\n",
    "    players['surname'][i] = players['surname'][i].split(' ')[-1]\n",
    "    players['surname'][i] = normalize_name(players['surname'][i]).replace('\\'', '')\n",
    "    \n",
    "    \n",
    "    players['initial'][i] = players['player'][i][0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "ffd6091c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                         player           surname\n",
      "0             Oliver Abildgaard        Abildgaard\n",
      "1                 Tammy Abraham           Abraham\n",
      "2              Francesco Acerbi            Acerbi\n",
      "3                   Yacine Adli              Adli\n",
      "4              Michel Aebischer         Aebischer\n",
      "5              Felix Afena-Gyan        Afena-Gyan\n",
      "6                 Kevin Agudelo           Agudelo\n",
      "7                      Ola Aina              Aina\n",
      "8                 Emanuel Aiwum             Aiwum\n",
      "9        Jean-Daniel Akpa-Akpro        Akpa-Akpro\n",
      "10                 Luis Alberto           Alberto\n",
      "11     Agustín Álvarez Martínez          Martinez\n",
      "12                 Kelvin Amian             Amian\n",
      "13                 Bruno Amione            Amione\n",
      "14                 Bruno Amione            Amione\n",
      "15                 Ethan Ampadu            Ampadu\n",
      "16               Sofyan Amrabat           Amrabat\n",
      "17              Felipe Anderson          Anderson\n",
      "18                Janis Antiste           Antiste\n",
      "19               Marcos Antônio           Antonio\n",
      "20               Valentin Antov             Antov\n",
      "21             Marko Arnautović        Arnautovic\n",
      "22                Tolgay Arslan            Arslan\n",
      "23                       Arthur            Arthur\n",
      "24           Santiago Ascacíbar         Ascacibar\n",
      "25         Kristoffer Askildsen         Askildsen\n",
      "26             Kristjan Asllani           Asllani\n",
      "27                  Emil Audero            Audero\n",
      "28              Tommaso Augello           Augello\n",
      "29                   Kaan Ayhan             Ayhan\n",
      "30                   Jaime Báez              Baez\n",
      "31                Nedim Bajrami           Bajrami\n",
      "32                Nedim Bajrami           Bajrami\n",
      "33             Tommaso Baldanzi          Baldanzi\n",
      "34             Fodé Ballo-Touré       Ballo-Toure\n",
      "35                 Lameck Banda             Banda\n",
      "36           Filippo Bandinelli        Bandinelli\n",
      "37                Antonín Barák             Barak\n",
      "38                Antonín Barák             Barak\n",
      "39              Andrea Barberis          Barberis\n",
      "40               Nicolò Barella           Barella\n",
      "41                  Musa Barrow            Barrow\n",
      "42         Federico Baschirotto       Baschirotto\n",
      "43                   Toma Bašić             Basic\n",
      "44           Alessandro Bastoni           Bastoni\n",
      "45               Simone Bastoni           Bastoni\n",
      "46                 Brian Bayeye            Bayeye\n",
      "47                Rodrigo Becão             Becao\n",
      "48                  Julius Beck              Beck\n",
      "49              Raoul Bellanova         Bellanova\n",
      "50               Andrea Belotti           Belotti\n",
      "51                Marco Benassi           Benassi\n",
      "52                Marco Benassi           Benassi\n",
      "53              Ismaël Bennacer          Bennacer\n",
      "54             Domenico Berardi           Berardi\n",
      "55          Bartosz Bereszyński       Bereszynski\n",
      "56                         Beto              Beto\n",
      "57            Matteo Bianchetti        Bianchetti\n",
      "58            Alessandro Bianco            Bianco\n",
      "59                   Jaka Bijol             Bijol\n",
      "60            Cristiano Biraghi           Biraghi\n",
      "61           Samuele Birindelli        Birindelli\n",
      "62          Kristijan Bistrović         Bistrovic\n",
      "63                  Alexis Blin              Blin\n",
      "64                 Jeremie Boga              Boga\n",
      "65                 Emil Bohinen           Bohinen\n",
      "66          Giacomo Bonaventura       Bonaventura\n",
      "67           Federico Bonazzoli         Bonazzoli\n",
      "68                 Warren Bondo             Bondo\n",
      "69               Kevin Bonifazi          Bonifazi\n",
      "70             Leonardo Bonucci           Bonucci\n",
      "71                 Erik Botheim           Botheim\n",
      "72               Mehdi Bourabia          Bourabia\n",
      "73                 Edoardo Bove              Bove\n",
      "74                 Jayden Braaf             Braaf\n",
      "75             Domagoj Bradarić          Bradaric\n",
      "76                Josip Brekalo           Brekalo\n",
      "77               Gleison Bremer            Bremer\n",
      "78                  Dylan Bronn             Bronn\n",
      "79             Marcelo Brozović          Brozovic\n",
      "80           Cristian Buonaiuto         Buonaiuto\n",
      "81        Alessandro Buongiorno        Buongiorno\n",
      "82                   Juan Cabal             Cabal\n",
      "83              Liberato Cacace            Cacace\n",
      "84              Davide Calabria          Calabria\n",
      "85               Mattia Caldara           Caldara\n",
      "86               Luca Caldirola         Caldirola\n",
      "87             Hakan Çalhanoğlu        Calhanoglu\n",
      "88               Mohamed Camara            Camara\n",
      "89             Nicolò Cambiaghi         Cambiaghi\n",
      "90              Andrea Cambiaso          Cambiaso\n",
      "91           Matteo Cancellieri       Cancellieri\n",
      "92             Antonio Candreva          Candreva\n",
      "93             Gianluca Caprari           Caprari\n",
      "94             Francesco Caputo            Caputo\n",
      "95             Francesco Caputo            Caputo\n",
      "96               Andrea Carboni           Carboni\n",
      "97             Valentin Carboni           Carboni\n",
      "98                       Carlos            Carlos\n",
      "99            Marco Carnesecchi       Carnesecchi\n",
      "100               Nicolò Casale            Casale\n",
      "101         Michele Castagnetti       Castagnetti\n",
      "102         Gaetano Castrovilli       Castrovilli\n",
      "103              Danilo Cataldi           Cataldi\n",
      "104         Federico Ceccherini        Ceccherini\n",
      "105                Assan Ceesay            Ceesay\n",
      "106                  Emil Ceide             Ceide\n",
      "107                  Zeki Çelik             Celik\n",
      "108             Federico Chiesa            Chiesa\n",
      "109              Vlad Chiricheș         Chiriches\n",
      "110              Daniel Ciofani           Ciofani\n",
      "111                   Tio Cipot             Cipot\n",
      "112             Patrick Ciurria           Ciurria\n",
      "113                 Omar Colley            Colley\n",
      "114             Lorenzo Colombo           Colombo\n",
      "115              Andrea Colpani           Colpani\n",
      "116             Andrea Consigli          Consigli\n",
      "117                Andrea Conti             Conti\n",
      "118               Diego Coppola           Coppola\n",
      "119              Joaquín Correa            Correa\n",
      "120       Alessandro Cortinovis        Cortinovis\n",
      "121           Lassana Coulibaly         Coulibaly\n",
      "122             Bryan Cristante         Cristante\n",
      "123               Domen Črnigoj           Crnigoj\n",
      "124               Juan Cuadrado          Cuadrado\n",
      "125            Mickaël Cuisance          Cuisance\n",
      "126          Marco D'Alessandro       DAlessandro\n",
      "127           Danilo D'Ambrosio         DAmbrosio\n",
      "128               Luca D'Andrea           DAndrea\n",
      "129            Flavius Daniliuc          Daniliuc\n",
      "130                      Danilo            Danilo\n",
      "131              Matteo Darmian           Darmian\n",
      "132            Paweł Dawidowicz        Dawidowicz\n",
      "133        Charles De Ketelaere         Ketelaere\n",
      "134              Manuel De Luca              Luca\n",
      "135           Mattia De Sciglio           Sciglio\n",
      "136        Lorenzo De Silvestri         Silvestri\n",
      "137              Koni De Winter            Winter\n",
      "138             Grégoire Defrel            Defrel\n",
      "139      Duccio Degli Innocenti         Innocenti\n",
      "140               Merih Demiral           Demiral\n",
      "141                 Diego Demme             Demme\n",
      "142               Fabio Depaoli           Depaoli\n",
      "143               Fabio Depaoli           Depaoli\n",
      "144            Kastriot Dermaku           Dermaku\n",
      "145              Cyriel Dessers           Dessers\n",
      "146                Sergiño Dest              Dest\n",
      "147               Mattia Destro            Destro\n",
      "148             Gerard Deulofeu          Deulofeu\n",
      "149           Samuel Di Carmine           Carmine\n",
      "150       Federico Di Francesco         Francesco\n",
      "151         Michele Di Gregorio          Gregorio\n",
      "152         Giovanni Di Lorenzo           Lorenzo\n",
      "153              Ángel Di María             Maria\n",
      "154                 Boulaye Dia               Dia\n",
      "155                 Brahim Díaz              Diaz\n",
      "156            Federico Dimarco           Dimarco\n",
      "157                Koffi Djidji            Djidji\n",
      "158              Berat Djimsiti          Djimsiti\n",
      "159                        Dodô              Dodo\n",
      "160                   Josh Doig              Doig\n",
      "161           Nicolás Domínguez         Dominguez\n",
      "162               Giulio Donati            Donati\n",
      "163        Bartłomiej Drągowski         Dragowski\n",
      "164                 Ondrej Duda              Duda\n",
      "165             Denzel Dumfries          Dumfries\n",
      "166               Alfred Duncan            Duncan\n",
      "167                Paulo Dybala            Dybala\n",
      "168                  Edin Džeko             Dzeko\n",
      "169               Festy Ebosele           Ebosele\n",
      "170                 Enzo Ebosse            Ebosse\n",
      "171              Tyronne Ebuehi            Ebuehi\n",
      "172                     Éderson           Ederson\n",
      "173           Kingsley Ehizibue          Ehizibue\n",
      "174                 Albin Ekdal             Ekdal\n",
      "175              Emmanuel Ekong             Ekong\n",
      "176           Mikael Ellertsson        Ellertsson\n",
      "177                  Elif Elmas             Elmas\n",
      "178                Martin Erlic             Erlic\n",
      "179           Gonzalo Escalante         Escalante\n",
      "180          Salvatore Esposito          Esposito\n",
      "181              Nicolò Fagioli           Fagioli\n",
      "182           Wladimiro Falcone           Falcone\n",
      "183              Davide Faraoni           Faraoni\n",
      "184              Federico Fazio             Fazio\n",
      "185              Jacopo Fazzini           Fazzini\n",
      "186              Lewis Ferguson          Ferguson\n",
      "187                Alex Ferrari           Ferrari\n",
      "188                Alex Ferrari           Ferrari\n",
      "189             Salvador Ferrer            Ferrer\n",
      "190         Alessandro Florenzi          Florenzi\n",
      "191             Davide Frattesi          Frattesi\n",
      "192               Matteo Gabbia            Gabbia\n",
      "193           Manolo Gabbiadini        Gabbiadini\n",
      "194            Gianluca Gaetano           Gaetano\n",
      "195         Roberto Gagliardini       Gagliardini\n",
      "196                Adolfo Gaich             Gaich\n",
      "197       Pablo Galdames Millán            Millan\n",
      "198              Antonino Gallo             Gallo\n",
      "199              Federico Gatti             Gatti\n",
      "200            Valentin Gendrey           Gendrey\n",
      "201             Paolo Ghiglione         Ghiglione\n",
      "202                  Mario Gila              Gila\n",
      "203              Olivier Giroud            Giroud\n",
      "204           Pierluigi Gollini           Gollini\n",
      "205               Joan Gonzàlez          Gonzalez\n",
      "206            Nicolás González          Gonzalez\n",
      "207                Robin Gosens            Gosens\n",
      "208              Alberto Grassi            Grassi\n",
      "209                Koray Günter            Gunter\n",
      "210              Emmanuel Gyasi             Gyasi\n",
      "211             Norbert Gyömbér           Gyomber\n",
      "212           Christian Gytkjær            Gytkjr\n",
      "213                Nicolas Haas              Haas\n",
      "214            Samir Handanović        Handanovic\n",
      "215               Abdou Harroui           Harroui\n",
      "216               Hans Hateboer          Hateboer\n",
      "217              Liam Henderson         Henderson\n",
      "218                 Jack Hendry            Hendry\n",
      "219            Matheus Henrique          Henrique\n",
      "220                Thomas Henry             Henry\n",
      "221              Theo Hernández         Hernandez\n",
      "222                   Isak Hien              Hien\n",
      "223             Morten Hjulmand          Hjulmand\n",
      "224                   Emil Holm              Holm\n",
      "225               Martin Hongla            Hongla\n",
      "226               Petko Hristov           Hristov\n",
      "227               Ajdin Hrustic           Hrustic\n",
      "228                Elseid Hysaj             Hysaj\n",
      "229              Rasmus Højlund            Hjlund\n",
      "230                Roger Ibanez            Ibanez\n",
      "231                        Igor              Igor\n",
      "232              Jonathan Ikone             Ikone\n",
      "233                   Ivan Ilić              Ilic\n",
      "234         Samuel Iling-Junior      Iling-Junior\n",
      "235              Emirhan İlkhan            Ilkhan\n",
      "236               Ciro Immobile          Immobile\n",
      "237              Ardian Ismajli           Ismajli\n",
      "238                Armando Izzo              Izzo\n",
      "239                 Mato Jajalo            Jajalo\n",
      "240                  Juan Jesus             Jesus\n",
      "241       Þórir Jóhann Helgason          Helgason\n",
      "242                  Luka Jović             Jovic\n",
      "243         Hamed Junior Traorè            Traore\n",
      "244                Yayah Kallon            Kallon\n",
      "245               Pierre Kalulu            Kalulu\n",
      "246                Yann Karamoh           Karamoh\n",
      "247               Rick Karsdorp          Karsdorp\n",
      "248                Denso Kasius            Kasius\n",
      "249           Grigoris Kastanos          Kastanos\n",
      "250                  Moise Kean              Kean\n",
      "251                Jakub Kiwior            Kiwior\n",
      "252                  Simon Kjær               Kjr\n",
      "253            Teun Koopmeiners       Koopmeiners\n",
      "254                Filip Kostić            Kostic\n",
      "255            Christian Kouamé            Kouame\n",
      "256            Viktor Kovalenko         Kovalenko\n",
      "257        Julian Kristoffersen     Kristoffersen\n",
      "258            Raimonds Krollis           Krollis\n",
      "259                 Rade Krunić            Krunic\n",
      "260             Marash Kumbulla          Kumbulla\n",
      "261       Khvicha Kvaratskhelia     Kvaratskhelia\n",
      "262       Giorgos Kyriakopoulos     Kyriakopoulos\n",
      "263       Giorgos Kyriakopoulos     Kyriakopoulos\n",
      "264                 Sam Lammers           Lammers\n",
      "265                 Sam Lammers           Lammers\n",
      "266               Kevin Lasagna           Lasagna\n",
      "267            Armand Lauriente         Lauriente\n",
      "268            Valentino Lazaro            Lazaro\n",
      "269               Marko Lazetić           Lazetic\n",
      "270               Darko Lazović           Lazovic\n",
      "271              Manuel Lazzari           Lazzari\n",
      "272                 Rafael Leão              Leao\n",
      "273                 Mehdi Léris             Leris\n",
      "274               Karol Linetty           Linetty\n",
      "275           Marcin Listkowski        Listkowski\n",
      "276              Diego Llorente          Llorente\n",
      "277           Stanislav Lobotka           Lobotka\n",
      "278            Manuel Locatelli         Locatelli\n",
      "279            Luka Lochoshvili       Lochoshvili\n",
      "280             Ademola Lookman           Lookman\n",
      "281                Maxime Lopez             Lopez\n",
      "282               Matteo Lovato            Lovato\n",
      "283                Sandi Lovrić            Lovric\n",
      "284              Hirving Lozano            Lozano\n",
      "285                 Jhon Lucumí            Lucumi\n",
      "286          José Luis Palomino          Palomino\n",
      "287               Romelu Lukaku            Lukaku\n",
      "288                  Saša Lukić             Lukic\n",
      "289          Sebastiano Luperto           Luperto\n",
      "290     Charalambos Lykogiannis       Lykogiannis\n",
      "291             Giulio Maggiore          Maggiore\n",
      "292         Giangiacomo Magnani           Magnani\n",
      "293                Mike Maignan           Maignan\n",
      "294         Jean-Victor Makengo           Makengo\n",
      "295           Lorenzo Malagrida         Malagrida\n",
      "296              Daniel Maldini           Maldini\n",
      "297               Youssef Maleh             Maleh\n",
      "298               Youssef Maleh             Maleh\n",
      "299          Ruslan Malinovskyi       Malinovskyi\n",
      "300            Gianluca Mancini           Mancini\n",
      "301          Rolando Mandragora        Mandragora\n",
      "302          Riccardo Marchizza         Marchizza\n",
      "303          Gian Marco Ferrari           Ferrari\n",
      "304                  Pablo Marí              Mari\n",
      "305                Răzvan Marin             Marin\n",
      "306                      Marlon            Marlon\n",
      "307                Luca Marrone           Marrone\n",
      "308            Lautaro Martínez          Martinez\n",
      "309       Lucas Martínez Quarta            Quarta\n",
      "310                Adam Marušić           Marusic\n",
      "311                 Adam Masina            Masina\n",
      "312               Nemanja Matić             Matic\n",
      "313              Luís Maximiano         Maximiano\n",
      "314          Pasquale Mazzocchi         Mazzocchi\n",
      "315             Weston McKennie          McKennie\n",
      "316                  Gary Medel             Medel\n",
      "317              Soualiho Meïté             Meite\n",
      "318                  Alex Meret             Meret\n",
      "319         Yıldırım Mert Çetin             Cetin\n",
      "320              Junior Messias           Messias\n",
      "321            Tommaso Milanese          Milanese\n",
      "322           Nikola Milenković        Milenkovic\n",
      "323             Arkadiusz Milik             Milik\n",
      "324     Sergej Milinković-Savić  Milinkovic-Savic\n",
      "325      Vanja Milinković-Savić  Milinkovic-Savic\n",
      "326                 Kim Min-jae           Min-jae\n",
      "327           Aleksei Miranchuk         Miranchuk\n",
      "328               Fabio Miretti           Miretti\n",
      "329          Henrikh Mkhitaryan        Mkhitaryan\n",
      "330            Salvatore Molina            Molina\n",
      "331           Daniele Montevago         Montevago\n",
      "332             Lorenzo Montipò           Montipo\n",
      "333                 Nikola Moro              Moro\n",
      "334                   Dany Mota              Mota\n",
      "335               João Moutinho          Moutinho\n",
      "336                 Mert Müldür            Muldur\n",
      "337                 Luis Muriel            Muriel\n",
      "338              Jeison Murillo           Murillo\n",
      "339                Nicola Murru             Murru\n",
      "340                  Juan Musso             Musso\n",
      "341                Joakim Mæhle              Mhle\n",
      "342          Michel Ndary Adopo             Adopo\n",
      "343             Tanguy Ndombele          Ndombele\n",
      "344           Ilija Nestorovski       Nestorovski\n",
      "345                Cyril Ngonge            Ngonge\n",
      "346     Hans Nicolussi Caviglia          Caviglia\n",
      "347           Dimitris Nikolaou          Nikolaou\n",
      "348               Bram Nuytinck          Nuytinck\n",
      "349               Bram Nuytinck          Nuytinck\n",
      "350                M'Bala Nzola             Nzola\n",
      "351                Pedro Obiang            Obiang\n",
      "352             Guillermo Ochoa             Ochoa\n",
      "353               David Okereke           Okereke\n",
      "354                 Caleb Okoli             Okoli\n",
      "355             Mathías Olivera           Olivera\n",
      "356                 André Onana             Onana\n",
      "357                Divock Origi             Origi\n",
      "358           Riccardo Orsolini          Orsolini\n",
      "359              Victor Osimhen           Osimhen\n",
      "360                  Remi Oudin             Oudin\n",
      "361                  Adam Ounas             Ounas\n",
      "362              Simone Pafundi           Pafundi\n",
      "363             Flavio Paoletti          Paoletti\n",
      "364             Leandro Paredes           Paredes\n",
      "365              Fabiano Parisi            Parisi\n",
      "366               Mario Pašalić           Pasalic\n",
      "367                      Patric            Patric\n",
      "368                Rui Patrício          Patricio\n",
      "369                       Pedro             Pedro\n",
      "370             Gianluca Pegolo            Pegolo\n",
      "371             Pietro Pellegri          Pellegri\n",
      "372          Lorenzo Pellegrini        Pellegrini\n",
      "373                       Pepín             Pepin\n",
      "374             Roberto Pereyra           Pereyra\n",
      "375                Nehuén Pérez             Perez\n",
      "376                Mattia Perin             Perin\n",
      "377              Matteo Pessina           Pessina\n",
      "378              Andrea Petagna           Petagna\n",
      "379           Giuseppe Pezzella          Pezzella\n",
      "380            Krzysztof Piątek            Piatek\n",
      "381             Roberto Piccoli           Piccoli\n",
      "382             Roberto Piccoli           Piccoli\n",
      "383              Charles Pickel            Pickel\n",
      "384            Andrea Pinamonti         Pinamonti\n",
      "385              Lorenzo Pirola            Pirola\n",
      "386                 Marko Pjaca             Pjaca\n",
      "387              Tommaso Pobega            Pobega\n",
      "388             Matteo Politano          Politano\n",
      "389             Marin Pongračić         Pongracic\n",
      "390                Stefan Posch             Posch\n",
      "391               Ivan Provedel          Provedel\n",
      "392            Ignacio Pussetto          Pussetto\n",
      "393              Niklas Pyyhtiä           Pyyhtia\n",
      "394          Fabio Quagliarella      Quagliarella\n",
      "395           Giacomo Quagliata         Quagliata\n",
      "396               Adrien Rabiot            Rabiot\n",
      "397            Nemanja Radonjić          Radonjic\n",
      "398            Ivan Radovanović       Radovanovic\n",
      "399                  Ionuț Radu              Radu\n",
      "400                Luca Ranieri           Ranieri\n",
      "401            Andrea Ranocchia         Ranocchia\n",
      "402           Filippo Ranocchia         Ranocchia\n",
      "403           Giacomo Raspadori         Raspadori\n",
      "404           Giacomo Raspadori         Raspadori\n",
      "405                  Ante Rebić             Rebic\n",
      "406              Arkadiusz Reca              Reca\n",
      "407           Panagiotis Retsos            Retsos\n",
      "408               Franck Ribéry            Ribery\n",
      "409               Samuele Ricci             Ricci\n",
      "410                Tomás Rincón            Rincon\n",
      "411             Pablo Rodríguez         Rodriguez\n",
      "412           Ricardo Rodríguez         Rodriguez\n",
      "413                     Rogério           Rogerio\n",
      "414           Alessio Romagnoli         Romagnoli\n",
      "415                 Luka Romero            Romero\n",
      "416              Marten de Roon              Roon\n",
      "417              Nicolò Rovella           Rovella\n",
      "418              Nicolò Rovella           Rovella\n",
      "419               Amir Rrahmani          Rrahmani\n",
      "420                        Ruan              Ruan\n",
      "421              Daniele Rugani            Rugani\n",
      "422              Matteo Ruggeri           Ruggeri\n",
      "423                   Mário Rui               Rui\n",
      "424           Abdelhamid Sabiri            Sabiri\n",
      "425         Alexis Saelemaekers      Saelemaekers\n",
      "426                 Jacopo Sala              Sala\n",
      "427             Lazar Samardzic         Samardzic\n",
      "428               Junior Sambia            Sambia\n",
      "429            Antonio Sanabria          Sanabria\n",
      "430               Leandro Sanca             Sanca\n",
      "431                 Alex Sandro            Sandro\n",
      "432              Nicola Sansone           Sansone\n",
      "433           Riccardo Saponara          Saponara\n",
      "434             Martin Satriano          Satriano\n",
      "435            Giorgio Scalvini          Scalvini\n",
      "436              Jerdy Schouten          Schouten\n",
      "437                Perr Schuurs           Schuurs\n",
      "438                  Demba Seck              Seck\n",
      "439                Jacopo Segre             Segre\n",
      "440              Vivaldo Semedo            Semedo\n",
      "441               Stefano Sensi             Sensi\n",
      "442                  Luigi Sepe              Sepe\n",
      "443          Leonardo Sernicola         Sernicola\n",
      "444         Stephan El Shaarawy          Shaarawy\n",
      "445            Eldor Shomurodov        Shomurodov\n",
      "446            Eldor Shomurodov        Shomurodov\n",
      "447             Marco Silvestri         Silvestri\n",
      "448            Giovanni Simeone           Simeone\n",
      "449              Wilfried Singo             Singo\n",
      "450          Leo Skiri Østigård           stigard\n",
      "451            Łukasz Skorupski         Skorupski\n",
      "452              Milan Škriniar          Skriniar\n",
      "453              Chris Smalling          Smalling\n",
      "454               Ola Solbakken         Solbakken\n",
      "455               Brandon Soppy             Soppy\n",
      "456               Brandon Soppy             Soppy\n",
      "457             Roberto Soriano           Soriano\n",
      "458                Joaquin Sosa              Sosa\n",
      "459             Riccardo Sottil            Sottil\n",
      "460                Matìas Soulé             Soule\n",
      "461              Adama Soumaoro          Soumaoro\n",
      "462         Leonardo Spinazzola        Spinazzola\n",
      "463            Marco Sportiello        Sportiello\n",
      "464            Petar Stojanović        Stojanovic\n",
      "465           Gabriel Strefezza         Strefezza\n",
      "466               Dávid Strelec           Strelec\n",
      "467               Isaac Success           Success\n",
      "468            Ibrahim Sulemana          Sulemana\n",
      "469           Wojciech Szczęsny          Szczesny\n",
      "470          Benjamin Tahirovic         Tahirovic\n",
      "471               Adrien Tameze            Tameze\n",
      "472          Ciprian Tătărușanu        Tatarusanu\n",
      "473         Filippo Terracciano       Terracciano\n",
      "474          Pietro Terracciano       Terracciano\n",
      "475               Aleksa Terzić            Terzic\n",
      "476             Florian Thauvin           Thauvin\n",
      "477                Malick Thiaw             Thiaw\n",
      "478         Kristian Thorstvedt        Thorstvedt\n",
      "479               Jeremy Toljan            Toljan\n",
      "480                Rafael Tolói             Toloi\n",
      "481               Fikayo Tomori            Tomori\n",
      "482               Sandro Tonali            Tonali\n",
      "483        William Troost-Ekong      Troost-Ekong\n",
      "484              Frank Tsadjout          Tsadjout\n",
      "485             Alessandro Tuia              Tuia\n",
      "486              Iyenoma Udogie            Udogie\n",
      "487               Samuel Umtiti            Umtiti\n",
      "488              Diego Valencia          Valencia\n",
      "489             Emanuele Valeri            Valeri\n",
      "490               Mattia Valoti            Valoti\n",
      "491               Johan Vásquez           Vasquez\n",
      "492               Matías Vecino            Vecino\n",
      "493               Miguel Veloso            Veloso\n",
      "494              Lorenzo Venuti            Venuti\n",
      "495               Daniele Verde             Verde\n",
      "496                Simone Verdi             Verdi\n",
      "497               Valerio Verre             Verre\n",
      "498           Guglielmo Vicario           Vicario\n",
      "499              Ronaldo Vieira            Vieira\n",
      "500              Ronaldo Vieira            Vieira\n",
      "501             Emanuel Vignato           Vignato\n",
      "502             Samuele Vignato           Vignato\n",
      "503               Tonny Vilhena           Vilhena\n",
      "504              Gonzalo Villar            Villar\n",
      "505                 Matías Viña              Vina\n",
      "506              Dušan Vlahović          Vlahovic\n",
      "507               Nikola Vlašić            Vlasic\n",
      "508    Joel Voelkerling Persson           Persson\n",
      "509              Mërgim Vojvoda           Vojvoda\n",
      "510            Cristian Volpato           Volpato\n",
      "511               Aster Vranckx           Vranckx\n",
      "512              Stefan de Vrij              Vrij\n",
      "513                      Walace            Walace\n",
      "514       Sebastian Walukiewicz       Walukiewicz\n",
      "515         Georginio Wijnaldum         Wijnaldum\n",
      "516                 Harry Winks             Winks\n",
      "517       Przemysław Wiśniewski        Wisniewski\n",
      "518                Gerard Yepes             Yepes\n",
      "519             Mattia Zaccagni          Zaccagni\n",
      "520               Denis Zakaria           Zakaria\n",
      "521             Nicola Zalewski          Zalewski\n",
      "522  Andre-Frank Zambo Anguissa          Anguissa\n",
      "523            Luca Zanimacchia       Zanimacchia\n",
      "524              Nicolò Zaniolo           Zaniolo\n",
      "525           Alessandro Zanoli            Zanoli\n",
      "526           Alessandro Zanoli            Zanoli\n",
      "527                Duván Zapata            Zapata\n",
      "528           Davide Zappacosta        Zappacosta\n",
      "529              Alessio Zerbin            Zerbin\n",
      "530             Piotr Zieliński         Zielinski\n",
      "531                  David Zima              Zima\n",
      "532              Joshua Zirkzee           Zirkzee\n",
      "533                 Jeroen Zoet              Zoet\n",
      "534                Nadir Zortea            Zortea\n",
      "535                Nadir Zortea            Zortea\n",
      "536                 Petar Zovko             Zovko\n",
      "537            Szymon Żurkowski         Zurkowski\n",
      "538            Szymon Żurkowski         Zurkowski\n",
      "539                 Milan Đurić              uric\n",
      "540               Filip Đuričić            uricic\n",
      "541                 Emil Audero            Audero\n",
      "542           Marco Carnesecchi       Carnesecchi\n",
      "543             Andrea Consigli          Consigli\n",
      "544         Michele Di Gregorio          Gregorio\n",
      "545        Bartłomiej Drągowski         Dragowski\n",
      "546           Wladimiro Falcone           Falcone\n",
      "547           Pierluigi Gollini           Gollini\n",
      "548            Samir Handanović        Handanovic\n",
      "549                Mike Maignan           Maignan\n",
      "550              Luís Maximiano         Maximiano\n",
      "551                  Alex Meret             Meret\n",
      "552      Vanja Milinković-Savić  Milinkovic-Savic\n",
      "553             Lorenzo Montipò           Montipo\n",
      "554                  Juan Musso             Musso\n",
      "555             Guillermo Ochoa             Ochoa\n",
      "556                 André Onana             Onana\n",
      "557                Rui Patrício          Patricio\n",
      "558             Gianluca Pegolo            Pegolo\n",
      "559                Mattia Perin             Perin\n",
      "560               Ivan Provedel          Provedel\n",
      "561                  Ionuț Radu              Radu\n",
      "562                  Luigi Sepe              Sepe\n",
      "563             Marco Silvestri         Silvestri\n",
      "564            Łukasz Skorupski         Skorupski\n",
      "565            Marco Sportiello        Sportiello\n",
      "566           Wojciech Szczęsny          Szczesny\n",
      "567          Ciprian Tătărușanu        Tatarusanu\n",
      "568          Pietro Terracciano       Terracciano\n",
      "569           Guglielmo Vicario           Vicario\n",
      "570                 Jeroen Zoet              Zoet\n",
      "571                 Petar Zovko             Zovko\n"
     ]
    }
   ],
   "source": [
    "print(players[['player', 'surname']].to_string())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9ab06a5c",
   "metadata": {},
   "source": [
    "Replace the surname for some specific players, according to config/name_fix.txt file.\n",
    "\n",
    "This is done for players for which the decoded fbref surname doesn't correspond to Fantacalcio list."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "3e759b1b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Ostigard\n",
      "Kim\n",
      "Hojlund\n",
      "Gytkjaer\n",
      "Augusto\n",
      "Maehle\n",
      "Kjaer\n",
      "Djuricic\n",
      "Djuric\n",
      "Cabral\n",
      "Alvarez\n"
     ]
    },
    {
     "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>FROM</th>\n",
       "      <th>TO</th>\n",
       "      <th>TEAM</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>stigard</td>\n",
       "      <td>Ostigard</td>\n",
       "      <td>Napoli</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Min-jae</td>\n",
       "      <td>Kim</td>\n",
       "      <td>Napoli</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Hjlund</td>\n",
       "      <td>Hojlund</td>\n",
       "      <td>Atalanta</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Gytkjr</td>\n",
       "      <td>Gytkjaer</td>\n",
       "      <td>Monza</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Carlos</td>\n",
       "      <td>Augusto</td>\n",
       "      <td>Monza</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Mhle</td>\n",
       "      <td>Maehle</td>\n",
       "      <td>Atalanta</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Kjr</td>\n",
       "      <td>Kjaer</td>\n",
       "      <td>Milan</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>uricic</td>\n",
       "      <td>Djuricic</td>\n",
       "      <td>Sampdoria</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>uric</td>\n",
       "      <td>Djuric</td>\n",
       "      <td>Hellas Verona</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Arthur</td>\n",
       "      <td>Cabral</td>\n",
       "      <td>Fiorentina</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Martinez</td>\n",
       "      <td>Alvarez</td>\n",
       "      <td>Sassuolo</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        FROM        TO           TEAM\n",
       "0    stigard  Ostigard         Napoli\n",
       "1    Min-jae       Kim         Napoli\n",
       "2     Hjlund   Hojlund       Atalanta\n",
       "3     Gytkjr  Gytkjaer          Monza\n",
       "4     Carlos   Augusto          Monza\n",
       "5       Mhle    Maehle       Atalanta\n",
       "6        Kjr     Kjaer          Milan\n",
       "7     uricic  Djuricic      Sampdoria\n",
       "8       uric    Djuric  Hellas Verona\n",
       "9     Arthur    Cabral     Fiorentina\n",
       "10  Martinez   Alvarez       Sassuolo"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rcsv = pd.read_csv('config/name_fix.txt')   \n",
    "name_fix = pd.DataFrame(rcsv)\n",
    "\n",
    "for i in range(name_fix.shape[0]):\n",
    "    for j in range(players.shape[0]):\n",
    "        if(players['surname'][j].lower() == name_fix['FROM'][i].lower() and players['team'][j].lower() == name_fix['TEAM'][i].lower()):\n",
    "            players['surname'][j] = name_fix['TO'][i]\n",
    "            print(name_fix['TO'][i])\n",
    "\n",
    "name_fix\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3c686d9f",
   "metadata": {},
   "source": [
    "Load players from Fantacalcio list."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "f96eaaa1",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2263921821.py:17: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  fc_players['surname'][i] = spl[-1]\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2263921821.py:18: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  fc_players['initial'][i] = ''\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2263921821.py:14: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  fc_players['surname'][i] = spl[-2]\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2263921821.py:15: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  fc_players['initial'][i] = spl[-1][0]\n"
     ]
    },
    {
     "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>id</th>\n",
       "      <th>r</th>\n",
       "      <th>name</th>\n",
       "      <th>team</th>\n",
       "      <th>surname</th>\n",
       "      <th>initial</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>572</td>\n",
       "      <td>P</td>\n",
       "      <td>Meret</td>\n",
       "      <td>Napoli</td>\n",
       "      <td>Meret</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2814</td>\n",
       "      <td>P</td>\n",
       "      <td>Provedel</td>\n",
       "      <td>Lazio</td>\n",
       "      <td>Provedel</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4964</td>\n",
       "      <td>P</td>\n",
       "      <td>Vicario</td>\n",
       "      <td>Empoli</td>\n",
       "      <td>Vicario</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>453</td>\n",
       "      <td>P</td>\n",
       "      <td>Szczesny</td>\n",
       "      <td>Juventus</td>\n",
       "      <td>Szczesny</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2134</td>\n",
       "      <td>P</td>\n",
       "      <td>Falcone</td>\n",
       "      <td>Lecce</td>\n",
       "      <td>Falcone</td>\n",
       "      <td></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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>538</th>\n",
       "      <td>5512</td>\n",
       "      <td>A</td>\n",
       "      <td>De Luca</td>\n",
       "      <td>Sampdoria</td>\n",
       "      <td>Luca</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>539</th>\n",
       "      <td>5837</td>\n",
       "      <td>A</td>\n",
       "      <td>Voelkerling Persson</td>\n",
       "      <td>Lecce</td>\n",
       "      <td>Persson</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>540</th>\n",
       "      <td>6113</td>\n",
       "      <td>A</td>\n",
       "      <td>Montevago</td>\n",
       "      <td>Sampdoria</td>\n",
       "      <td>Montevago</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>541</th>\n",
       "      <td>6143</td>\n",
       "      <td>A</td>\n",
       "      <td>Krollis</td>\n",
       "      <td>Spezia</td>\n",
       "      <td>Krollis</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>542</th>\n",
       "      <td>6160</td>\n",
       "      <td>A</td>\n",
       "      <td>Vivaldo</td>\n",
       "      <td>Udinese</td>\n",
       "      <td>Vivaldo</td>\n",
       "      <td></td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>543 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       id  r                 name       team    surname initial\n",
       "0     572  P                Meret     Napoli      Meret        \n",
       "1    2814  P             Provedel      Lazio   Provedel        \n",
       "2    4964  P              Vicario     Empoli    Vicario        \n",
       "3     453  P             Szczesny   Juventus   Szczesny        \n",
       "4    2134  P              Falcone      Lecce    Falcone        \n",
       "..    ... ..                  ...        ...        ...     ...\n",
       "538  5512  A              De Luca  Sampdoria       Luca        \n",
       "539  5837  A  Voelkerling Persson      Lecce    Persson        \n",
       "540  6113  A            Montevago  Sampdoria  Montevago        \n",
       "541  6143  A              Krollis     Spezia    Krollis        \n",
       "542  6160  A              Vivaldo    Udinese    Vivaldo        \n",
       "\n",
       "[543 rows x 6 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fc_data = pd.read_excel('fantacalcio/Quotazioni_Fantacalcio.xlsx', 'Tutti', header = 1)\n",
    "\n",
    "fc_players = fc_data [['Id', 'R', 'Nome', 'Squadra']]\n",
    "\n",
    "fc_players = fc_players.rename(columns = {'Id' : 'id', 'R': 'r', 'Nome' : 'name', 'Squadra' : 'team'})\n",
    "\n",
    "fc_players['surname'] = fc_players['name']\n",
    "fc_players['initial'] = fc_players['name']\n",
    "\n",
    "\n",
    "for i in range(fc_players.shape[0]):\n",
    "    spl = normalize_name( fc_players['name'][i].replace('\\'', '') ).split(' ')\n",
    "    if('.' in spl[-1]):\n",
    "        fc_players['surname'][i] = spl[-2]\n",
    "        fc_players['initial'][i] = spl[-1][0]\n",
    "    else:\n",
    "        fc_players['surname'][i] = spl[-1]\n",
    "        fc_players['initial'][i] = ''\n",
    "    \n",
    "fc_players\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d944c720",
   "metadata": {},
   "source": [
    "Associate players from Fantacalcio list to ID for FBref data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "9c50e4b5",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2200947104.py:4: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  fc_players['fb_ID'][i] = -1\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2200947104.py:11: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  fc_players['fb_ID'][i] = j\n"
     ]
    }
   ],
   "source": [
    "fc_players['fb_ID'] = fc_players['id']\n",
    "\n",
    "for i in range(fc_players.shape[0]):\n",
    "    fc_players['fb_ID'][i] = -1\n",
    "    \n",
    "    for j in range(players.shape[0]):\n",
    "        if(fc_players['team'][i].lower() in players['team'][j].lower()):\n",
    "            if(fc_players['surname'][i].lower() == players['surname'][j].lower()):              \n",
    "                # if(fc_players['initial'][i] == '' or fc_players['initial'][i].lower() == players['initial'][j].lower()):\n",
    "                if((fc_players['r'][i] == 'P') == (j >= keepers_ID)): # check wether they're a goalkeeper for both FBREF and Fantacalcio\n",
    "                    fc_players['fb_ID'][i] = j\n",
    "                \n",
    "        "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4e60fd2e",
   "metadata": {},
   "source": [
    "Print players for which the association failed.\n",
    "\n",
    "Most of them are players who didn't play a single Serie A game this season with their team. If that is the case, and there is data from their previous team, that is taken here.\n",
    "\n",
    "Others are ones for which the FBRef surname doesn't correspond to Fantacalcio one.\n",
    "\n",
    "\n",
    "For example, Cabral is Arthur for FBref.\n",
    "\n",
    "Correction is made in the name_fix code above."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "18f6c5f2",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\362391242.py:10: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  fc_players['fb_ID'][i] = j\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Gollini from previous team stats\n",
      "Mirante not found\n",
      "Sarr M. not found\n",
      "Lamanna not found\n",
      "Ujkani not found\n",
      "Berisha not found\n",
      "Marchetti not found\n",
      "Perilli not found\n",
      "Padelli not found\n",
      "Perisan not found\n",
      "Bardi not found\n",
      "Cordaz not found\n",
      "Pinsoglio not found\n",
      "Fiorillo not found\n",
      "Cragno not found\n",
      "Sirigu not found\n",
      "Cerofolini not found\n",
      "Rossi F. not found\n",
      "Ravaglia F. not found\n",
      "Brancolini not found\n",
      "Bleve not found\n",
      "Berardi A. not found\n",
      "Russo A. not found\n",
      "Gemello not found\n",
      "Ravaglia not found\n",
      "Boer not found\n",
      "Adamonis not found\n",
      "Marfella not found\n",
      "Piana not found\n",
      "Bagnolini not found\n",
      "Svilar not found\n",
      "Sorrentino A. not found\n",
      "Ciezkowski not found\n",
      "Saro not found\n",
      "Vasquez D. not found\n",
      "Turk not found\n",
      "Pellegrini Lu. not found\n",
      "Gravillon not found\n",
      "Gunter from previous team stats\n",
      "Ceccaroni not found\n",
      "Bereszynski from previous team stats\n",
      "Aiwu not found\n",
      "Zeefuik not found\n",
      "Romagnoli S. not found\n",
      "Tonelli not found\n",
      "Radu from previous team stats\n",
      "Paletta not found\n",
      "Fares not found\n",
      "Romagna not found\n",
      "Cassandro not found\n",
      "Amey not found\n",
      "Zanotti not found\n",
      "Buta not found\n",
      "Abankwah not found\n",
      "Guessand A. not found\n",
      "Guarino not found\n",
      "Pogba not found\n",
      "Ilic from previous team stats\n",
      "Machin not found\n",
      "Akpa Akpro not found\n",
      "Galdames not found\n",
      "Vignato from previous team stats\n",
      "Bakayoko not found\n",
      "Darboe not found\n",
      "Urbanski not found\n",
      "Bertini not found\n",
      "Trimboli not found\n",
      "Samek not found\n",
      "Ilkhan from previous team stats\n",
      "Acella not found\n",
      "Faticanti not found\n",
      "Ibrahimovic not found\n",
      "Oddei not found\n",
      "Raimondo not found\n",
      "Kaio Jorge not found\n",
      "Vivaldo not found\n"
     ]
    }
   ],
   "source": [
    "exceptions = ['pellegrini', 'berardi', 'romagnoli'] # exceptions for such players that have the same surname as others (Berardi A., Luca Pellegrini)\n",
    "\n",
    "for i in range(fc_players.shape[0]):\n",
    "    if(fc_players['fb_ID'][i] == -1):\n",
    "        found = False\n",
    "        for j in range(players.shape[0]):\n",
    "            if(fc_players['surname'][i].lower() == players['surname'][j].lower()):\n",
    "                if(not(players['surname'][j].lower() in exceptions)):\n",
    "                    if((fc_players['r'][i] == 'P') == (j >= keepers_ID)):\n",
    "                        fc_players['fb_ID'][i] = j\n",
    "                        found = True\n",
    "        if(found):\n",
    "            print(fc_players['name'][i] + ' from previous team stats')\n",
    "        else:\n",
    "            print(fc_players['name'][i] + ' not found')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "3b4a36af",
   "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>id</th>\n",
       "      <th>r</th>\n",
       "      <th>name</th>\n",
       "      <th>team</th>\n",
       "      <th>surname</th>\n",
       "      <th>initial</th>\n",
       "      <th>fb_ID</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>572</td>\n",
       "      <td>P</td>\n",
       "      <td>Meret</td>\n",
       "      <td>Napoli</td>\n",
       "      <td>Meret</td>\n",
       "      <td></td>\n",
       "      <td>551</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2814</td>\n",
       "      <td>P</td>\n",
       "      <td>Provedel</td>\n",
       "      <td>Lazio</td>\n",
       "      <td>Provedel</td>\n",
       "      <td></td>\n",
       "      <td>560</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4964</td>\n",
       "      <td>P</td>\n",
       "      <td>Vicario</td>\n",
       "      <td>Empoli</td>\n",
       "      <td>Vicario</td>\n",
       "      <td></td>\n",
       "      <td>569</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>453</td>\n",
       "      <td>P</td>\n",
       "      <td>Szczesny</td>\n",
       "      <td>Juventus</td>\n",
       "      <td>Szczesny</td>\n",
       "      <td></td>\n",
       "      <td>566</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2134</td>\n",
       "      <td>P</td>\n",
       "      <td>Falcone</td>\n",
       "      <td>Lecce</td>\n",
       "      <td>Falcone</td>\n",
       "      <td></td>\n",
       "      <td>546</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>538</th>\n",
       "      <td>5512</td>\n",
       "      <td>A</td>\n",
       "      <td>De Luca</td>\n",
       "      <td>Sampdoria</td>\n",
       "      <td>Luca</td>\n",
       "      <td></td>\n",
       "      <td>134</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>539</th>\n",
       "      <td>5837</td>\n",
       "      <td>A</td>\n",
       "      <td>Voelkerling Persson</td>\n",
       "      <td>Lecce</td>\n",
       "      <td>Persson</td>\n",
       "      <td></td>\n",
       "      <td>508</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>540</th>\n",
       "      <td>6113</td>\n",
       "      <td>A</td>\n",
       "      <td>Montevago</td>\n",
       "      <td>Sampdoria</td>\n",
       "      <td>Montevago</td>\n",
       "      <td></td>\n",
       "      <td>331</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>541</th>\n",
       "      <td>6143</td>\n",
       "      <td>A</td>\n",
       "      <td>Krollis</td>\n",
       "      <td>Spezia</td>\n",
       "      <td>Krollis</td>\n",
       "      <td></td>\n",
       "      <td>258</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>542</th>\n",
       "      <td>6160</td>\n",
       "      <td>A</td>\n",
       "      <td>Vivaldo</td>\n",
       "      <td>Udinese</td>\n",
       "      <td>Vivaldo</td>\n",
       "      <td></td>\n",
       "      <td>-1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>543 rows × 7 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       id  r                 name       team    surname initial  fb_ID\n",
       "0     572  P                Meret     Napoli      Meret            551\n",
       "1    2814  P             Provedel      Lazio   Provedel            560\n",
       "2    4964  P              Vicario     Empoli    Vicario            569\n",
       "3     453  P             Szczesny   Juventus   Szczesny            566\n",
       "4    2134  P              Falcone      Lecce    Falcone            546\n",
       "..    ... ..                  ...        ...        ...     ...    ...\n",
       "538  5512  A              De Luca  Sampdoria       Luca            134\n",
       "539  5837  A  Voelkerling Persson      Lecce    Persson            508\n",
       "540  6113  A            Montevago  Sampdoria  Montevago            331\n",
       "541  6143  A              Krollis     Spezia    Krollis            258\n",
       "542  6160  A              Vivaldo    Udinese    Vivaldo             -1\n",
       "\n",
       "[543 rows x 7 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fc_players"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f06afbb6",
   "metadata": {},
   "source": [
    "Populate players dataset with stats from FBref, for outfield players and goalkeepers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "1d73a312",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2261782218.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy] = 0\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2261782218.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy] = 0\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2261782218.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy] = 0\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2261782218.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy] = 0\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2261782218.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy] = 0\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2261782218.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy] = 0\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2261782218.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy] = 0\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2261782218.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy] = 0\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2261782218.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy] = 0\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2261782218.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy] = 0\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2261782218.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy] = 0\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2261782218.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy] = 0\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2261782218.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy] = 0\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2261782218.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy] = 0\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2261782218.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy] = 0\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2261782218.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy] = 0\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\2261782218.py:9: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  fc_players[columns_to_copy[j]][i] = outfield_players[columns_to_copy[j]][fc_players['fb_ID'][i]]\n"
     ]
    }
   ],
   "source": [
    "#Data for Outfield players\n",
    "columns_to_copy = outfield_players.columns[4:]\n",
    "\n",
    "fc_players[columns_to_copy] = 0\n",
    "\n",
    "for i in range(fc_players.shape[0]):\n",
    "    if(fc_players['fb_ID'][i] != -1 and fc_players['r'][i] != 'P'):\n",
    "         for j in range(columns_to_copy.shape[0]):\n",
    "            fc_players[columns_to_copy[j]][i] = outfield_players[columns_to_copy[j]][fc_players['fb_ID'][i]]\n",
    "            "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "7acb93e3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['age', 'birth_year', 'gk_games', 'gk_games_starts', 'gk_minutes',\n",
       "       'gk_goals_against', 'gk_goals_against_per90',\n",
       "       'gk_shots_on_target_against', 'gk_saves', 'gk_save_pct', 'gk_wins',\n",
       "       'gk_ties', 'gk_losses', 'gk_clean_sheets', 'gk_clean_sheets_pct',\n",
       "       'gk_pens_att', 'gk_pens_allowed', 'gk_pens_saved', 'gk_pens_missed',\n",
       "       'minutes_90s', 'gk_free_kick_goals_against',\n",
       "       'gk_corner_kick_goals_against', 'gk_own_goals_against', 'gk_psxg',\n",
       "       'gk_psnpxg_per_shot_on_target_against', 'gk_psxg_net',\n",
       "       'gk_psxg_net_per90', 'gk_passes_completed_launched',\n",
       "       'gk_passes_launched', 'gk_passes_pct_launched', 'gk_passes',\n",
       "       'gk_passes_throws', 'gk_pct_passes_launched', 'gk_passes_length_avg',\n",
       "       'gk_goal_kicks', 'gk_pct_goal_kicks_launched',\n",
       "       'gk_goal_kick_length_avg', 'gk_crosses', 'gk_crosses_stopped',\n",
       "       'gk_crosses_stopped_pct', 'gk_def_actions_outside_pen_area',\n",
       "       'gk_def_actions_outside_pen_area_per90', 'gk_avg_distance_def_actions'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "keeper_players.columns[4:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "eb9127a9",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:4: PerformanceWarning: DataFrame is highly fragmented.  This is usually the result of calling `frame.insert` many times, which has poor performance.  Consider joining all columns at once using pd.concat(axis=1) instead. To get a de-fragmented frame, use `newframe = frame.copy()`\n",
      "  fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
      "C:\\Users\\nicol\\AppData\\Local\\Temp\\ipykernel_16864\\3664433845.py:11: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
      "  fc_players[columns_to_copy[j]][i] = keeper_players[columns_to_copy[j]][fc_players['fb_ID'][i] - delta_k]\n"
     ]
    }
   ],
   "source": [
    "#Data for Keepers\n",
    "columns_to_copy = keeper_players.columns[4:]\n",
    "\n",
    "fc_players[columns_to_copy[2:]] = 0 # add columns but do not override age and birth_year\n",
    "\n",
    "delta_k = outfield_players.shape[0]\n",
    "\n",
    "for i in range(fc_players.shape[0]):\n",
    "    if(fc_players['fb_ID'][i] != -1 and fc_players['r'][i] == 'P'):\n",
    "         for j in range(columns_to_copy.shape[0]):\n",
    "            fc_players[columns_to_copy[j]][i] = keeper_players[columns_to_copy[j]][fc_players['fb_ID'][i] - delta_k]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "da977789",
   "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>id</th>\n",
       "      <th>r</th>\n",
       "      <th>name</th>\n",
       "      <th>team</th>\n",
       "      <th>surname</th>\n",
       "      <th>initial</th>\n",
       "      <th>fb_ID</th>\n",
       "      <th>age</th>\n",
       "      <th>birth_year</th>\n",
       "      <th>games</th>\n",
       "      <th>...</th>\n",
       "      <th>gk_passes_length_avg</th>\n",
       "      <th>gk_goal_kicks</th>\n",
       "      <th>gk_pct_goal_kicks_launched</th>\n",
       "      <th>gk_goal_kick_length_avg</th>\n",
       "      <th>gk_crosses</th>\n",
       "      <th>gk_crosses_stopped</th>\n",
       "      <th>gk_crosses_stopped_pct</th>\n",
       "      <th>gk_def_actions_outside_pen_area</th>\n",
       "      <th>gk_def_actions_outside_pen_area_per90</th>\n",
       "      <th>gk_avg_distance_def_actions</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>572</td>\n",
       "      <td>P</td>\n",
       "      <td>Meret</td>\n",
       "      <td>Napoli</td>\n",
       "      <td>Meret</td>\n",
       "      <td></td>\n",
       "      <td>551</td>\n",
       "      <td>25-325</td>\n",
       "      <td>1997</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>26.7</td>\n",
       "      <td>128</td>\n",
       "      <td>19.5</td>\n",
       "      <td>27.1</td>\n",
       "      <td>221</td>\n",
       "      <td>6</td>\n",
       "      <td>2.7</td>\n",
       "      <td>24</td>\n",
       "      <td>1.14</td>\n",
       "      <td>17.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2814</td>\n",
       "      <td>P</td>\n",
       "      <td>Provedel</td>\n",
       "      <td>Lazio</td>\n",
       "      <td>Provedel</td>\n",
       "      <td></td>\n",
       "      <td>560</td>\n",
       "      <td>28-330</td>\n",
       "      <td>1994</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>33.0</td>\n",
       "      <td>120</td>\n",
       "      <td>34.2</td>\n",
       "      <td>34.5</td>\n",
       "      <td>279</td>\n",
       "      <td>7</td>\n",
       "      <td>2.5</td>\n",
       "      <td>39</td>\n",
       "      <td>1.86</td>\n",
       "      <td>18.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4964</td>\n",
       "      <td>P</td>\n",
       "      <td>Vicario</td>\n",
       "      <td>Empoli</td>\n",
       "      <td>Vicario</td>\n",
       "      <td></td>\n",
       "      <td>569</td>\n",
       "      <td>26-126</td>\n",
       "      <td>1996</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>34.0</td>\n",
       "      <td>108</td>\n",
       "      <td>47.2</td>\n",
       "      <td>42.4</td>\n",
       "      <td>426</td>\n",
       "      <td>25</td>\n",
       "      <td>5.9</td>\n",
       "      <td>12</td>\n",
       "      <td>0.57</td>\n",
       "      <td>10.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>453</td>\n",
       "      <td>P</td>\n",
       "      <td>Szczesny</td>\n",
       "      <td>Juventus</td>\n",
       "      <td>Szczesny</td>\n",
       "      <td></td>\n",
       "      <td>566</td>\n",
       "      <td>32-298</td>\n",
       "      <td>1990</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>35.0</td>\n",
       "      <td>72</td>\n",
       "      <td>41.7</td>\n",
       "      <td>38.7</td>\n",
       "      <td>178</td>\n",
       "      <td>4</td>\n",
       "      <td>2.2</td>\n",
       "      <td>12</td>\n",
       "      <td>0.83</td>\n",
       "      <td>15.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2134</td>\n",
       "      <td>P</td>\n",
       "      <td>Falcone</td>\n",
       "      <td>Lecce</td>\n",
       "      <td>Falcone</td>\n",
       "      <td></td>\n",
       "      <td>546</td>\n",
       "      <td>27-304</td>\n",
       "      <td>1995</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>41.3</td>\n",
       "      <td>163</td>\n",
       "      <td>76.1</td>\n",
       "      <td>51.7</td>\n",
       "      <td>316</td>\n",
       "      <td>15</td>\n",
       "      <td>4.7</td>\n",
       "      <td>20</td>\n",
       "      <td>0.95</td>\n",
       "      <td>12.5</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>538</th>\n",
       "      <td>5512</td>\n",
       "      <td>A</td>\n",
       "      <td>De Luca</td>\n",
       "      <td>Sampdoria</td>\n",
       "      <td>Luca</td>\n",
       "      <td></td>\n",
       "      <td>134</td>\n",
       "      <td>24-208</td>\n",
       "      <td>1998</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>539</th>\n",
       "      <td>5837</td>\n",
       "      <td>A</td>\n",
       "      <td>Voelkerling Persson</td>\n",
       "      <td>Lecce</td>\n",
       "      <td>Persson</td>\n",
       "      <td></td>\n",
       "      <td>508</td>\n",
       "      <td>20-026</td>\n",
       "      <td>2003</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>540</th>\n",
       "      <td>6113</td>\n",
       "      <td>A</td>\n",
       "      <td>Montevago</td>\n",
       "      <td>Sampdoria</td>\n",
       "      <td>Montevago</td>\n",
       "      <td></td>\n",
       "      <td>331</td>\n",
       "      <td>19-329</td>\n",
       "      <td>2003</td>\n",
       "      <td>6</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>541</th>\n",
       "      <td>6143</td>\n",
       "      <td>A</td>\n",
       "      <td>Krollis</td>\n",
       "      <td>Spezia</td>\n",
       "      <td>Krollis</td>\n",
       "      <td></td>\n",
       "      <td>258</td>\n",
       "      <td>21-105</td>\n",
       "      <td>2001</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>542</th>\n",
       "      <td>6160</td>\n",
       "      <td>A</td>\n",
       "      <td>Vivaldo</td>\n",
       "      <td>Udinese</td>\n",
       "      <td>Vivaldo</td>\n",
       "      <td></td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>543 rows × 158 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       id  r                 name       team    surname initial  fb_ID  \\\n",
       "0     572  P                Meret     Napoli      Meret            551   \n",
       "1    2814  P             Provedel      Lazio   Provedel            560   \n",
       "2    4964  P              Vicario     Empoli    Vicario            569   \n",
       "3     453  P             Szczesny   Juventus   Szczesny            566   \n",
       "4    2134  P              Falcone      Lecce    Falcone            546   \n",
       "..    ... ..                  ...        ...        ...     ...    ...   \n",
       "538  5512  A              De Luca  Sampdoria       Luca            134   \n",
       "539  5837  A  Voelkerling Persson      Lecce    Persson            508   \n",
       "540  6113  A            Montevago  Sampdoria  Montevago            331   \n",
       "541  6143  A              Krollis     Spezia    Krollis            258   \n",
       "542  6160  A              Vivaldo    Udinese    Vivaldo             -1   \n",
       "\n",
       "        age  birth_year  games  ...  gk_passes_length_avg  gk_goal_kicks  \\\n",
       "0    25-325        1997      0  ...                  26.7            128   \n",
       "1    28-330        1994      0  ...                  33.0            120   \n",
       "2    26-126        1996      0  ...                  34.0            108   \n",
       "3    32-298        1990      0  ...                  35.0             72   \n",
       "4    27-304        1995      0  ...                  41.3            163   \n",
       "..      ...         ...    ...  ...                   ...            ...   \n",
       "538  24-208        1998      1  ...                   0.0              0   \n",
       "539  20-026        2003      3  ...                   0.0              0   \n",
       "540  19-329        2003      6  ...                   0.0              0   \n",
       "541  21-105        2001      1  ...                   0.0              0   \n",
       "542       0           0      0  ...                   0.0              0   \n",
       "\n",
       "     gk_pct_goal_kicks_launched  gk_goal_kick_length_avg  gk_crosses  \\\n",
       "0                          19.5                     27.1         221   \n",
       "1                          34.2                     34.5         279   \n",
       "2                          47.2                     42.4         426   \n",
       "3                          41.7                     38.7         178   \n",
       "4                          76.1                     51.7         316   \n",
       "..                          ...                      ...         ...   \n",
       "538                         0.0                      0.0           0   \n",
       "539                         0.0                      0.0           0   \n",
       "540                         0.0                      0.0           0   \n",
       "541                         0.0                      0.0           0   \n",
       "542                         0.0                      0.0           0   \n",
       "\n",
       "     gk_crosses_stopped  gk_crosses_stopped_pct  \\\n",
       "0                     6                     2.7   \n",
       "1                     7                     2.5   \n",
       "2                    25                     5.9   \n",
       "3                     4                     2.2   \n",
       "4                    15                     4.7   \n",
       "..                  ...                     ...   \n",
       "538                   0                     0.0   \n",
       "539                   0                     0.0   \n",
       "540                   0                     0.0   \n",
       "541                   0                     0.0   \n",
       "542                   0                     0.0   \n",
       "\n",
       "     gk_def_actions_outside_pen_area  gk_def_actions_outside_pen_area_per90  \\\n",
       "0                                 24                                   1.14   \n",
       "1                                 39                                   1.86   \n",
       "2                                 12                                   0.57   \n",
       "3                                 12                                   0.83   \n",
       "4                                 20                                   0.95   \n",
       "..                               ...                                    ...   \n",
       "538                                0                                   0.00   \n",
       "539                                0                                   0.00   \n",
       "540                                0                                   0.00   \n",
       "541                                0                                   0.00   \n",
       "542                                0                                   0.00   \n",
       "\n",
       "     gk_avg_distance_def_actions  \n",
       "0                           17.2  \n",
       "1                           18.2  \n",
       "2                           10.9  \n",
       "3                           15.8  \n",
       "4                           12.5  \n",
       "..                           ...  \n",
       "538                          0.0  \n",
       "539                          0.0  \n",
       "540                          0.0  \n",
       "541                          0.0  \n",
       "542                          0.0  \n",
       "\n",
       "[543 rows x 158 columns]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fc_players"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "81a17f84",
   "metadata": {},
   "source": [
    "Load votes database, to add data to players database (mean vote and its standard deviation)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "6a0e43cd",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "\n",
    "votes = pd.read_excel('mid_outputs/players_votes.xlsx', index_col = 0)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6c1b733a",
   "metadata": {},
   "source": [
    "Compute the average Serie A Goal Keeper mean vote and vote std"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "61fac91a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "vote_avg    6.211716\n",
      "vote_std    0.441335\n",
      "dtype: float64\n"
     ]
    },
    {
     "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>vote_avg</th>\n",
       "      <th>vote_std</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6.261905</td>\n",
       "      <td>0.478566</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6.261905</td>\n",
       "      <td>0.365769</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6.476190</td>\n",
       "      <td>0.392677</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6.033333</td>\n",
       "      <td>0.339935</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6.309524</td>\n",
       "      <td>0.361089</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6.285714</td>\n",
       "      <td>0.424585</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>6.000000</td>\n",
       "      <td>0.436436</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>6.115385</td>\n",
       "      <td>0.287820</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>6.366667</td>\n",
       "      <td>0.426875</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>6.142857</td>\n",
       "      <td>0.412393</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>6.178571</td>\n",
       "      <td>0.305143</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>6.357143</td>\n",
       "      <td>0.440315</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>6.375000</td>\n",
       "      <td>0.616610</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>6.261905</td>\n",
       "      <td>0.569441</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>6.285714</td>\n",
       "      <td>0.451754</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>6.261905</td>\n",
       "      <td>0.502826</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>6.119048</td>\n",
       "      <td>0.509546</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>6.105263</td>\n",
       "      <td>0.306892</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>6.131579</td>\n",
       "      <td>0.482376</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>5.972222</td>\n",
       "      <td>0.389880</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>5.928571</td>\n",
       "      <td>0.371154</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>6.062500</td>\n",
       "      <td>0.526634</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>6.071429</td>\n",
       "      <td>0.494872</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>6.428571</td>\n",
       "      <td>0.562429</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>6.500000</td>\n",
       "      <td>0.577350</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    vote_avg  vote_std\n",
       "0   6.261905  0.478566\n",
       "1   6.261905  0.365769\n",
       "2   6.476190  0.392677\n",
       "3   6.033333  0.339935\n",
       "4   6.309524  0.361089\n",
       "5   6.285714  0.424585\n",
       "6   6.000000  0.436436\n",
       "7   6.115385  0.287820\n",
       "8   6.366667  0.426875\n",
       "9   6.142857  0.412393\n",
       "10  6.178571  0.305143\n",
       "11  6.357143  0.440315\n",
       "12  6.375000  0.616610\n",
       "13  6.261905  0.569441\n",
       "14  6.285714  0.451754\n",
       "15  6.261905  0.502826\n",
       "16  6.119048  0.509546\n",
       "17  6.105263  0.306892\n",
       "18  6.131579  0.482376\n",
       "19  5.972222  0.389880\n",
       "20  5.928571  0.371154\n",
       "21  6.062500  0.526634\n",
       "22  6.071429  0.494872\n",
       "23  6.428571  0.562429\n",
       "24  6.500000  0.577350"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "min_votes = 6\n",
    "\n",
    "perf_df_P = pd.DataFrame(columns = ['vote_avg', 'vote_std'])\n",
    "\n",
    "for i in range(fc_players.shape[0]): \n",
    "    if(fc_players.loc[i]['r'] == 'P'):\n",
    "        v = np.array([])\n",
    "        for j in range(votes.shape[0]):\n",
    "            if(fc_players['name'][i] == votes['player'][j]):\n",
    "                v = np.append(v, votes['vote'][j])\n",
    "\n",
    "        if(v.shape[0] >= min_votes - 1):\n",
    "            row_df = pd.DataFrame(data = [[np.mean(v), np.std(v)]], columns = perf_df_P.columns)\n",
    "            perf_df_P = pd.concat([perf_df_P, row_df], ignore_index = True)\n",
    "\n",
    "\n",
    "print(perf_df_P.mean())\n",
    "\n",
    "perf_df_P\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dbb344e2",
   "metadata": {},
   "source": [
    "Add to players data their mean vote (and its standard deviation).\n",
    "\n",
    "For players who don't have a minimum amount of games, more data to reach this value is computed, according to the average Serie A player vote (and std). For goalkeepers, this values are different.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "c9312080",
   "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>vote_avg</th>\n",
       "      <th>vote_std</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6.261905</td>\n",
       "      <td>0.478566</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6.261905</td>\n",
       "      <td>0.365769</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6.476190</td>\n",
       "      <td>0.392677</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6.033333</td>\n",
       "      <td>0.339935</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6.309524</td>\n",
       "      <td>0.361089</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>538</th>\n",
       "      <td>5.947397</td>\n",
       "      <td>0.490100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>539</th>\n",
       "      <td>5.694209</td>\n",
       "      <td>0.383547</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>540</th>\n",
       "      <td>5.623932</td>\n",
       "      <td>0.280948</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>541</th>\n",
       "      <td>6.124287</td>\n",
       "      <td>0.483769</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>542</th>\n",
       "      <td>6.215679</td>\n",
       "      <td>0.378965</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>543 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     vote_avg  vote_std\n",
       "0    6.261905  0.478566\n",
       "1    6.261905  0.365769\n",
       "2    6.476190  0.392677\n",
       "3    6.033333  0.339935\n",
       "4    6.309524  0.361089\n",
       "..        ...       ...\n",
       "538  5.947397  0.490100\n",
       "539  5.694209  0.383547\n",
       "540  5.623932  0.280948\n",
       "541  6.124287  0.483769\n",
       "542  6.215679  0.378965\n",
       "\n",
       "[543 rows x 2 columns]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "min_votes = 6\n",
    "\n",
    "#outfield players\n",
    "mean_def = 6\n",
    "std_def = 0.58\n",
    "\n",
    "#goalkeepers\n",
    "mean_def_P = 6.22\n",
    "std_def_P = 0.43\n",
    "\n",
    "\n",
    "perf_df = pd.DataFrame(columns = ['vote_avg', 'vote_std'])\n",
    "\n",
    "for i in range(fc_players.shape[0]):\n",
    "    v = np.array([])\n",
    "    for j in range(votes.shape[0]):\n",
    "        if(fc_players['name'][i] == votes['player'][j]):\n",
    "            v = np.append(v, votes['vote'][j])\n",
    "    \n",
    "    mean_def_i = mean_def\n",
    "    std_def_i = std_def\n",
    "    \n",
    "    if(fc_players['r'][i] == 'P'):\n",
    "        mean_def_i = mean_def_P\n",
    "        std_def_i = std_def_P\n",
    "        \n",
    "    if(v.shape[0] < min_votes):\n",
    "         for k in range(min_votes - v.shape[0]):\n",
    "            v = np.append( v, np.random.normal(mean_def_i, std_def_i) )\n",
    "    \n",
    "    row_df = pd.DataFrame(data = [[np.mean(v), np.std(v)]], columns = perf_df.columns)\n",
    "    perf_df = pd.concat([perf_df, row_df], ignore_index = True)\n",
    "    \n",
    "perf_df\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "b2570ce5",
   "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>id</th>\n",
       "      <th>r</th>\n",
       "      <th>name</th>\n",
       "      <th>team</th>\n",
       "      <th>surname</th>\n",
       "      <th>initial</th>\n",
       "      <th>fb_ID</th>\n",
       "      <th>age</th>\n",
       "      <th>birth_year</th>\n",
       "      <th>games</th>\n",
       "      <th>...</th>\n",
       "      <th>gk_pct_goal_kicks_launched</th>\n",
       "      <th>gk_goal_kick_length_avg</th>\n",
       "      <th>gk_crosses</th>\n",
       "      <th>gk_crosses_stopped</th>\n",
       "      <th>gk_crosses_stopped_pct</th>\n",
       "      <th>gk_def_actions_outside_pen_area</th>\n",
       "      <th>gk_def_actions_outside_pen_area_per90</th>\n",
       "      <th>gk_avg_distance_def_actions</th>\n",
       "      <th>vote_avg</th>\n",
       "      <th>vote_std</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>572</td>\n",
       "      <td>P</td>\n",
       "      <td>Meret</td>\n",
       "      <td>Napoli</td>\n",
       "      <td>Meret</td>\n",
       "      <td></td>\n",
       "      <td>551</td>\n",
       "      <td>25-325</td>\n",
       "      <td>1997</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>19.5</td>\n",
       "      <td>27.1</td>\n",
       "      <td>221</td>\n",
       "      <td>6</td>\n",
       "      <td>2.7</td>\n",
       "      <td>24</td>\n",
       "      <td>1.14</td>\n",
       "      <td>17.2</td>\n",
       "      <td>6.261905</td>\n",
       "      <td>0.478566</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2814</td>\n",
       "      <td>P</td>\n",
       "      <td>Provedel</td>\n",
       "      <td>Lazio</td>\n",
       "      <td>Provedel</td>\n",
       "      <td></td>\n",
       "      <td>560</td>\n",
       "      <td>28-330</td>\n",
       "      <td>1994</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>34.2</td>\n",
       "      <td>34.5</td>\n",
       "      <td>279</td>\n",
       "      <td>7</td>\n",
       "      <td>2.5</td>\n",
       "      <td>39</td>\n",
       "      <td>1.86</td>\n",
       "      <td>18.2</td>\n",
       "      <td>6.261905</td>\n",
       "      <td>0.365769</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4964</td>\n",
       "      <td>P</td>\n",
       "      <td>Vicario</td>\n",
       "      <td>Empoli</td>\n",
       "      <td>Vicario</td>\n",
       "      <td></td>\n",
       "      <td>569</td>\n",
       "      <td>26-126</td>\n",
       "      <td>1996</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>47.2</td>\n",
       "      <td>42.4</td>\n",
       "      <td>426</td>\n",
       "      <td>25</td>\n",
       "      <td>5.9</td>\n",
       "      <td>12</td>\n",
       "      <td>0.57</td>\n",
       "      <td>10.9</td>\n",
       "      <td>6.476190</td>\n",
       "      <td>0.392677</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>453</td>\n",
       "      <td>P</td>\n",
       "      <td>Szczesny</td>\n",
       "      <td>Juventus</td>\n",
       "      <td>Szczesny</td>\n",
       "      <td></td>\n",
       "      <td>566</td>\n",
       "      <td>32-298</td>\n",
       "      <td>1990</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>41.7</td>\n",
       "      <td>38.7</td>\n",
       "      <td>178</td>\n",
       "      <td>4</td>\n",
       "      <td>2.2</td>\n",
       "      <td>12</td>\n",
       "      <td>0.83</td>\n",
       "      <td>15.8</td>\n",
       "      <td>6.033333</td>\n",
       "      <td>0.339935</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2134</td>\n",
       "      <td>P</td>\n",
       "      <td>Falcone</td>\n",
       "      <td>Lecce</td>\n",
       "      <td>Falcone</td>\n",
       "      <td></td>\n",
       "      <td>546</td>\n",
       "      <td>27-304</td>\n",
       "      <td>1995</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>76.1</td>\n",
       "      <td>51.7</td>\n",
       "      <td>316</td>\n",
       "      <td>15</td>\n",
       "      <td>4.7</td>\n",
       "      <td>20</td>\n",
       "      <td>0.95</td>\n",
       "      <td>12.5</td>\n",
       "      <td>6.309524</td>\n",
       "      <td>0.361089</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>538</th>\n",
       "      <td>5512</td>\n",
       "      <td>A</td>\n",
       "      <td>De Luca</td>\n",
       "      <td>Sampdoria</td>\n",
       "      <td>Luca</td>\n",
       "      <td></td>\n",
       "      <td>134</td>\n",
       "      <td>24-208</td>\n",
       "      <td>1998</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.947397</td>\n",
       "      <td>0.490100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>539</th>\n",
       "      <td>5837</td>\n",
       "      <td>A</td>\n",
       "      <td>Voelkerling Persson</td>\n",
       "      <td>Lecce</td>\n",
       "      <td>Persson</td>\n",
       "      <td></td>\n",
       "      <td>508</td>\n",
       "      <td>20-026</td>\n",
       "      <td>2003</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.694209</td>\n",
       "      <td>0.383547</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>540</th>\n",
       "      <td>6113</td>\n",
       "      <td>A</td>\n",
       "      <td>Montevago</td>\n",
       "      <td>Sampdoria</td>\n",
       "      <td>Montevago</td>\n",
       "      <td></td>\n",
       "      <td>331</td>\n",
       "      <td>19-329</td>\n",
       "      <td>2003</td>\n",
       "      <td>6</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.623932</td>\n",
       "      <td>0.280948</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>541</th>\n",
       "      <td>6143</td>\n",
       "      <td>A</td>\n",
       "      <td>Krollis</td>\n",
       "      <td>Spezia</td>\n",
       "      <td>Krollis</td>\n",
       "      <td></td>\n",
       "      <td>258</td>\n",
       "      <td>21-105</td>\n",
       "      <td>2001</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6.124287</td>\n",
       "      <td>0.483769</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>542</th>\n",
       "      <td>6160</td>\n",
       "      <td>A</td>\n",
       "      <td>Vivaldo</td>\n",
       "      <td>Udinese</td>\n",
       "      <td>Vivaldo</td>\n",
       "      <td></td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6.215679</td>\n",
       "      <td>0.378965</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>543 rows × 160 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       id  r                 name       team    surname initial  fb_ID  \\\n",
       "0     572  P                Meret     Napoli      Meret            551   \n",
       "1    2814  P             Provedel      Lazio   Provedel            560   \n",
       "2    4964  P              Vicario     Empoli    Vicario            569   \n",
       "3     453  P             Szczesny   Juventus   Szczesny            566   \n",
       "4    2134  P              Falcone      Lecce    Falcone            546   \n",
       "..    ... ..                  ...        ...        ...     ...    ...   \n",
       "538  5512  A              De Luca  Sampdoria       Luca            134   \n",
       "539  5837  A  Voelkerling Persson      Lecce    Persson            508   \n",
       "540  6113  A            Montevago  Sampdoria  Montevago            331   \n",
       "541  6143  A              Krollis     Spezia    Krollis            258   \n",
       "542  6160  A              Vivaldo    Udinese    Vivaldo             -1   \n",
       "\n",
       "        age  birth_year  games  ...  gk_pct_goal_kicks_launched  \\\n",
       "0    25-325        1997      0  ...                        19.5   \n",
       "1    28-330        1994      0  ...                        34.2   \n",
       "2    26-126        1996      0  ...                        47.2   \n",
       "3    32-298        1990      0  ...                        41.7   \n",
       "4    27-304        1995      0  ...                        76.1   \n",
       "..      ...         ...    ...  ...                         ...   \n",
       "538  24-208        1998      1  ...                         0.0   \n",
       "539  20-026        2003      3  ...                         0.0   \n",
       "540  19-329        2003      6  ...                         0.0   \n",
       "541  21-105        2001      1  ...                         0.0   \n",
       "542       0           0      0  ...                         0.0   \n",
       "\n",
       "     gk_goal_kick_length_avg  gk_crosses  gk_crosses_stopped  \\\n",
       "0                       27.1         221                   6   \n",
       "1                       34.5         279                   7   \n",
       "2                       42.4         426                  25   \n",
       "3                       38.7         178                   4   \n",
       "4                       51.7         316                  15   \n",
       "..                       ...         ...                 ...   \n",
       "538                      0.0           0                   0   \n",
       "539                      0.0           0                   0   \n",
       "540                      0.0           0                   0   \n",
       "541                      0.0           0                   0   \n",
       "542                      0.0           0                   0   \n",
       "\n",
       "     gk_crosses_stopped_pct  gk_def_actions_outside_pen_area  \\\n",
       "0                       2.7                               24   \n",
       "1                       2.5                               39   \n",
       "2                       5.9                               12   \n",
       "3                       2.2                               12   \n",
       "4                       4.7                               20   \n",
       "..                      ...                              ...   \n",
       "538                     0.0                                0   \n",
       "539                     0.0                                0   \n",
       "540                     0.0                                0   \n",
       "541                     0.0                                0   \n",
       "542                     0.0                                0   \n",
       "\n",
       "     gk_def_actions_outside_pen_area_per90  gk_avg_distance_def_actions  \\\n",
       "0                                     1.14                         17.2   \n",
       "1                                     1.86                         18.2   \n",
       "2                                     0.57                         10.9   \n",
       "3                                     0.83                         15.8   \n",
       "4                                     0.95                         12.5   \n",
       "..                                     ...                          ...   \n",
       "538                                   0.00                          0.0   \n",
       "539                                   0.00                          0.0   \n",
       "540                                   0.00                          0.0   \n",
       "541                                   0.00                          0.0   \n",
       "542                                   0.00                          0.0   \n",
       "\n",
       "     vote_avg  vote_std  \n",
       "0    6.261905  0.478566  \n",
       "1    6.261905  0.365769  \n",
       "2    6.476190  0.392677  \n",
       "3    6.033333  0.339935  \n",
       "4    6.309524  0.361089  \n",
       "..        ...       ...  \n",
       "538  5.947397  0.490100  \n",
       "539  5.694209  0.383547  \n",
       "540  5.623932  0.280948  \n",
       "541  6.124287  0.483769  \n",
       "542  6.215679  0.378965  \n",
       "\n",
       "[543 rows x 160 columns]"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fc_players = pd.concat([fc_players, perf_df], axis = 1)\n",
    "\n",
    "fc_players"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "f7620abe",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'gk_shots_on_target_against'"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fc_players.columns[123]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c550c370",
   "metadata": {},
   "source": [
    "For goalkeepers who didn't play a miminum amount of games, data is weightly averaged with one of the main goalkeeper of their same team."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "700b7a7d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Zoet, 0.5\n",
      "Pegolo, 0.33333333333333337\n",
      "Gollini, 0.5\n",
      "Mirante, 0.0\n",
      "Sarr M., 0.0\n",
      "Lamanna, 0.0\n",
      "Ujkani, 0.0\n",
      "Berisha, 0.0\n",
      "Marchetti, 0.0\n",
      "Perilli, 0.0\n",
      "Padelli, 0.0\n",
      "Perisan, 0.0\n",
      "Bardi, 0.0\n",
      "Cordaz, 0.0\n",
      "Pinsoglio, 0.0\n",
      "Fiorillo, 0.0\n",
      "Cragno, 0.0\n",
      "Sirigu, 0.0\n",
      "Cerofolini, 0.0\n",
      "Rossi F., 0.0\n",
      "Ravaglia F., 0.0\n",
      "Brancolini, 0.0\n",
      "Bleve, 0.0\n",
      "Berardi A., 0.0\n",
      "Russo A., 0.0\n",
      "Gemello, 0.0\n",
      "Ravaglia, 0.0\n",
      "Boer, 0.0\n",
      "Adamonis, 0.0\n",
      "Marfella, 0.0\n",
      "Zovko, 0.16666666666666663\n",
      "Piana, 0.0\n",
      "Bagnolini, 0.0\n",
      "Luis Maximiano, 0.16666666666666663\n",
      "Svilar, 0.0\n",
      "Sorrentino A., 0.0\n",
      "Ciezkowski, 0.0\n",
      "Saro, 0.0\n",
      "Vasquez D., 0.0\n",
      "Turk, 0.0\n"
     ]
    }
   ],
   "source": [
    "min_gk_games = 6\n",
    "\n",
    "fc_players_newgk = fc_players.copy()\n",
    "\n",
    "columns_to_avg = fc_players.columns[123:] # from gk_games to end\n",
    "\n",
    "for i in range(fc_players.shape[0]):\n",
    "    if(fc_players['r'][i] == 'P'):\n",
    "        if(fc_players['gk_games'][i] < min_gk_games):\n",
    "            for j in range(fc_players.shape[0]):\n",
    "                if(fc_players['team'][i] == fc_players['team'][j] and fc_players['gk_games'][j] >= min_gk_games):\n",
    "                    break\n",
    "                    \n",
    "            weight = 1 - (min_gk_games - fc_players['gk_games'][i]) / min_gk_games\n",
    "            \n",
    "            fc_players_newgk.at[i, columns_to_avg] = fc_players.loc[i][columns_to_avg] * weight + (1 - weight) * fc_players.loc[j][columns_to_avg]\n",
    "            \n",
    "            print(fc_players['name'][i] + ', ' + str(weight))\n",
    "            \n",
    "        "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "2d9eee99",
   "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>id</th>\n",
       "      <th>r</th>\n",
       "      <th>name</th>\n",
       "      <th>team</th>\n",
       "      <th>surname</th>\n",
       "      <th>initial</th>\n",
       "      <th>fb_ID</th>\n",
       "      <th>age</th>\n",
       "      <th>birth_year</th>\n",
       "      <th>games</th>\n",
       "      <th>...</th>\n",
       "      <th>gk_pct_goal_kicks_launched</th>\n",
       "      <th>gk_goal_kick_length_avg</th>\n",
       "      <th>gk_crosses</th>\n",
       "      <th>gk_crosses_stopped</th>\n",
       "      <th>gk_crosses_stopped_pct</th>\n",
       "      <th>gk_def_actions_outside_pen_area</th>\n",
       "      <th>gk_def_actions_outside_pen_area_per90</th>\n",
       "      <th>gk_avg_distance_def_actions</th>\n",
       "      <th>vote_avg</th>\n",
       "      <th>vote_std</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>572</td>\n",
       "      <td>P</td>\n",
       "      <td>Meret</td>\n",
       "      <td>Napoli</td>\n",
       "      <td>Meret</td>\n",
       "      <td></td>\n",
       "      <td>551</td>\n",
       "      <td>25-325</td>\n",
       "      <td>1997</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>19.5</td>\n",
       "      <td>27.1</td>\n",
       "      <td>221.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>2.7</td>\n",
       "      <td>24.0</td>\n",
       "      <td>1.14</td>\n",
       "      <td>17.2</td>\n",
       "      <td>6.261905</td>\n",
       "      <td>0.478566</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2814</td>\n",
       "      <td>P</td>\n",
       "      <td>Provedel</td>\n",
       "      <td>Lazio</td>\n",
       "      <td>Provedel</td>\n",
       "      <td></td>\n",
       "      <td>560</td>\n",
       "      <td>28-330</td>\n",
       "      <td>1994</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>34.2</td>\n",
       "      <td>34.5</td>\n",
       "      <td>279.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>2.5</td>\n",
       "      <td>39.0</td>\n",
       "      <td>1.86</td>\n",
       "      <td>18.2</td>\n",
       "      <td>6.261905</td>\n",
       "      <td>0.365769</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4964</td>\n",
       "      <td>P</td>\n",
       "      <td>Vicario</td>\n",
       "      <td>Empoli</td>\n",
       "      <td>Vicario</td>\n",
       "      <td></td>\n",
       "      <td>569</td>\n",
       "      <td>26-126</td>\n",
       "      <td>1996</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>47.2</td>\n",
       "      <td>42.4</td>\n",
       "      <td>426.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>5.9</td>\n",
       "      <td>12.0</td>\n",
       "      <td>0.57</td>\n",
       "      <td>10.9</td>\n",
       "      <td>6.476190</td>\n",
       "      <td>0.392677</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>453</td>\n",
       "      <td>P</td>\n",
       "      <td>Szczesny</td>\n",
       "      <td>Juventus</td>\n",
       "      <td>Szczesny</td>\n",
       "      <td></td>\n",
       "      <td>566</td>\n",
       "      <td>32-298</td>\n",
       "      <td>1990</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>41.7</td>\n",
       "      <td>38.7</td>\n",
       "      <td>178.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>2.2</td>\n",
       "      <td>12.0</td>\n",
       "      <td>0.83</td>\n",
       "      <td>15.8</td>\n",
       "      <td>6.033333</td>\n",
       "      <td>0.339935</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2134</td>\n",
       "      <td>P</td>\n",
       "      <td>Falcone</td>\n",
       "      <td>Lecce</td>\n",
       "      <td>Falcone</td>\n",
       "      <td></td>\n",
       "      <td>546</td>\n",
       "      <td>27-304</td>\n",
       "      <td>1995</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>76.1</td>\n",
       "      <td>51.7</td>\n",
       "      <td>316.0</td>\n",
       "      <td>15.0</td>\n",
       "      <td>4.7</td>\n",
       "      <td>20.0</td>\n",
       "      <td>0.95</td>\n",
       "      <td>12.5</td>\n",
       "      <td>6.309524</td>\n",
       "      <td>0.361089</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",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>538</th>\n",
       "      <td>5512</td>\n",
       "      <td>A</td>\n",
       "      <td>De Luca</td>\n",
       "      <td>Sampdoria</td>\n",
       "      <td>Luca</td>\n",
       "      <td></td>\n",
       "      <td>134</td>\n",
       "      <td>24-208</td>\n",
       "      <td>1998</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.947397</td>\n",
       "      <td>0.490100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>539</th>\n",
       "      <td>5837</td>\n",
       "      <td>A</td>\n",
       "      <td>Voelkerling Persson</td>\n",
       "      <td>Lecce</td>\n",
       "      <td>Persson</td>\n",
       "      <td></td>\n",
       "      <td>508</td>\n",
       "      <td>20-026</td>\n",
       "      <td>2003</td>\n",
       "      <td>3</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.694209</td>\n",
       "      <td>0.383547</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>540</th>\n",
       "      <td>6113</td>\n",
       "      <td>A</td>\n",
       "      <td>Montevago</td>\n",
       "      <td>Sampdoria</td>\n",
       "      <td>Montevago</td>\n",
       "      <td></td>\n",
       "      <td>331</td>\n",
       "      <td>19-329</td>\n",
       "      <td>2003</td>\n",
       "      <td>6</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.623932</td>\n",
       "      <td>0.280948</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>541</th>\n",
       "      <td>6143</td>\n",
       "      <td>A</td>\n",
       "      <td>Krollis</td>\n",
       "      <td>Spezia</td>\n",
       "      <td>Krollis</td>\n",
       "      <td></td>\n",
       "      <td>258</td>\n",
       "      <td>21-105</td>\n",
       "      <td>2001</td>\n",
       "      <td>1</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6.124287</td>\n",
       "      <td>0.483769</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>542</th>\n",
       "      <td>6160</td>\n",
       "      <td>A</td>\n",
       "      <td>Vivaldo</td>\n",
       "      <td>Udinese</td>\n",
       "      <td>Vivaldo</td>\n",
       "      <td></td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>6.215679</td>\n",
       "      <td>0.378965</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>543 rows × 160 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       id  r                 name       team    surname initial  fb_ID  \\\n",
       "0     572  P                Meret     Napoli      Meret            551   \n",
       "1    2814  P             Provedel      Lazio   Provedel            560   \n",
       "2    4964  P              Vicario     Empoli    Vicario            569   \n",
       "3     453  P             Szczesny   Juventus   Szczesny            566   \n",
       "4    2134  P              Falcone      Lecce    Falcone            546   \n",
       "..    ... ..                  ...        ...        ...     ...    ...   \n",
       "538  5512  A              De Luca  Sampdoria       Luca            134   \n",
       "539  5837  A  Voelkerling Persson      Lecce    Persson            508   \n",
       "540  6113  A            Montevago  Sampdoria  Montevago            331   \n",
       "541  6143  A              Krollis     Spezia    Krollis            258   \n",
       "542  6160  A              Vivaldo    Udinese    Vivaldo             -1   \n",
       "\n",
       "        age  birth_year  games  ...  gk_pct_goal_kicks_launched  \\\n",
       "0    25-325        1997      0  ...                        19.5   \n",
       "1    28-330        1994      0  ...                        34.2   \n",
       "2    26-126        1996      0  ...                        47.2   \n",
       "3    32-298        1990      0  ...                        41.7   \n",
       "4    27-304        1995      0  ...                        76.1   \n",
       "..      ...         ...    ...  ...                         ...   \n",
       "538  24-208        1998      1  ...                         0.0   \n",
       "539  20-026        2003      3  ...                         0.0   \n",
       "540  19-329        2003      6  ...                         0.0   \n",
       "541  21-105        2001      1  ...                         0.0   \n",
       "542       0           0      0  ...                         0.0   \n",
       "\n",
       "     gk_goal_kick_length_avg  gk_crosses  gk_crosses_stopped  \\\n",
       "0                       27.1       221.0                 6.0   \n",
       "1                       34.5       279.0                 7.0   \n",
       "2                       42.4       426.0                25.0   \n",
       "3                       38.7       178.0                 4.0   \n",
       "4                       51.7       316.0                15.0   \n",
       "..                       ...         ...                 ...   \n",
       "538                      0.0         0.0                 0.0   \n",
       "539                      0.0         0.0                 0.0   \n",
       "540                      0.0         0.0                 0.0   \n",
       "541                      0.0         0.0                 0.0   \n",
       "542                      0.0         0.0                 0.0   \n",
       "\n",
       "     gk_crosses_stopped_pct  gk_def_actions_outside_pen_area  \\\n",
       "0                       2.7                             24.0   \n",
       "1                       2.5                             39.0   \n",
       "2                       5.9                             12.0   \n",
       "3                       2.2                             12.0   \n",
       "4                       4.7                             20.0   \n",
       "..                      ...                              ...   \n",
       "538                     0.0                              0.0   \n",
       "539                     0.0                              0.0   \n",
       "540                     0.0                              0.0   \n",
       "541                     0.0                              0.0   \n",
       "542                     0.0                              0.0   \n",
       "\n",
       "     gk_def_actions_outside_pen_area_per90  gk_avg_distance_def_actions  \\\n",
       "0                                     1.14                         17.2   \n",
       "1                                     1.86                         18.2   \n",
       "2                                     0.57                         10.9   \n",
       "3                                     0.83                         15.8   \n",
       "4                                     0.95                         12.5   \n",
       "..                                     ...                          ...   \n",
       "538                                   0.00                          0.0   \n",
       "539                                   0.00                          0.0   \n",
       "540                                   0.00                          0.0   \n",
       "541                                   0.00                          0.0   \n",
       "542                                   0.00                          0.0   \n",
       "\n",
       "     vote_avg  vote_std  \n",
       "0    6.261905  0.478566  \n",
       "1    6.261905  0.365769  \n",
       "2    6.476190  0.392677  \n",
       "3    6.033333  0.339935  \n",
       "4    6.309524  0.361089  \n",
       "..        ...       ...  \n",
       "538  5.947397  0.490100  \n",
       "539  5.694209  0.383547  \n",
       "540  5.623932  0.280948  \n",
       "541  6.124287  0.483769  \n",
       "542  6.215679  0.378965  \n",
       "\n",
       "[543 rows x 160 columns]"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fc_players = fc_players_newgk\n",
    "\n",
    "fc_players"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2b13240e",
   "metadata": {},
   "source": [
    "Save to file."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "8336c025",
   "metadata": {},
   "outputs": [],
   "source": [
    "fc_players.to_excel('mid_outputs/players_stats.xlsx')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f3fc9b1b",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}