{ "cells": [ { "cell_type": "code", "execution_count": 61, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "from mplsoccer.pitch import Pitch" ] }, { "cell_type": "code", "execution_count": 62, "metadata": {}, "outputs": [], "source": [ "#read in csv\n", "df = pd.read_csv('valladolidA.csv')" ] }, { "cell_type": "code", "execution_count": 63, "metadata": {}, "outputs": [], "source": [ "#filter df to get only the team we want\n", "df = df[df['teamId']=='Barcelona']" ] }, { "cell_type": "code", "execution_count": 64, "metadata": {}, "outputs": [], "source": [ "#now we want to find our passes and recipients and then filter for only passes\n", "df['passer'] = df['playerId']\n", "df['recipient'] = df['playerId'].shift(-1)\n", "\n", "#find passes and then only look for the successful passes\n", "passes = df[df['type']=='Pass']\n", "successful = passes[passes['outcome']=='Successful']" ] }, { "cell_type": "code", "execution_count": 65, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ideventIdminutesecondteamIdxyperiodtypeoutcomeplayerIdendXendYpasserrecipient
22248226929301.0Barcelona50.050.01PassSuccessful9.043.946.99.08.0
32248226941402.0Barcelona43.846.91PassSuccessful8.036.456.08.021.0
42248226951504.0Barcelona36.656.61PassSuccessful21.028.573.821.015.0
52248226973605.0Barcelona28.374.11PassSuccessful15.011.651.815.01.0
62248226975708.0Barcelona11.253.71PassSuccessful1.011.681.41.015.0
................................................
1651224825686710189314.0Barcelona76.731.82PassSuccessful8.076.743.08.010.0
1652224825686910199317.0Barcelona79.624.22PassSuccessful10.077.153.610.014.0
1653224825698310209318.0Barcelona77.156.42PassSuccessful14.069.056.914.044721.0
1654224825698910219320.0Barcelona68.355.22PassSuccessful44721.087.017.344721.02.0
1667224825708110279350.0Barcelona75.64.62PassSuccessful2.077.126.82.010.0
\n", "

635 rows × 15 columns

\n", "
" ], "text/plain": [ " id eventId minute second teamId x y period \\\n", "2 2248226929 3 0 1.0 Barcelona 50.0 50.0 1 \n", "3 2248226941 4 0 2.0 Barcelona 43.8 46.9 1 \n", "4 2248226951 5 0 4.0 Barcelona 36.6 56.6 1 \n", "5 2248226973 6 0 5.0 Barcelona 28.3 74.1 1 \n", "6 2248226975 7 0 8.0 Barcelona 11.2 53.7 1 \n", "... ... ... ... ... ... ... ... ... \n", "1651 2248256867 1018 93 14.0 Barcelona 76.7 31.8 2 \n", "1652 2248256869 1019 93 17.0 Barcelona 79.6 24.2 2 \n", "1653 2248256983 1020 93 18.0 Barcelona 77.1 56.4 2 \n", "1654 2248256989 1021 93 20.0 Barcelona 68.3 55.2 2 \n", "1667 2248257081 1027 93 50.0 Barcelona 75.6 4.6 2 \n", "\n", " type outcome playerId endX endY passer recipient \n", "2 Pass Successful 9.0 43.9 46.9 9.0 8.0 \n", "3 Pass Successful 8.0 36.4 56.0 8.0 21.0 \n", "4 Pass Successful 21.0 28.5 73.8 21.0 15.0 \n", "5 Pass Successful 15.0 11.6 51.8 15.0 1.0 \n", "6 Pass Successful 1.0 11.6 81.4 1.0 15.0 \n", "... ... ... ... ... ... ... ... \n", "1651 Pass Successful 8.0 76.7 43.0 8.0 10.0 \n", "1652 Pass Successful 10.0 77.1 53.6 10.0 14.0 \n", "1653 Pass Successful 14.0 69.0 56.9 14.0 44721.0 \n", "1654 Pass Successful 44721.0 87.0 17.3 44721.0 2.0 \n", "1667 Pass Successful 2.0 77.1 26.8 2.0 10.0 \n", "\n", "[635 rows x 15 columns]" ] }, "execution_count": 65, "metadata": {}, "output_type": "execute_result" } ], "source": [ "successful" ] }, { "cell_type": "code", "execution_count": 66, "metadata": {}, "outputs": [], "source": [ "#find the first subsititution and filter the successful dataframe to be less than that minute\n", "subs = df[df['type']=='SubstitutionOff']\n", "subs = subs['minute']\n", "firstSub = subs.min()\n", "\n", "successful = successful[successful['minute'] < firstSub]" ] }, { "cell_type": "code", "execution_count": 67, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ideventIdminutesecondteamIdxyperiodtypeoutcomeplayerIdendXendYpasserrecipient
22248226929301.0Barcelona50.050.01PassSuccessful9.043.946.99.08.0
32248226941402.0Barcelona43.846.91PassSuccessful8.036.456.08.021.0
42248226951504.0Barcelona36.656.61PassSuccessful21.028.573.821.015.0
52248226973605.0Barcelona28.374.11PassSuccessful15.011.651.815.01.0
62248226975708.0Barcelona11.253.71PassSuccessful1.011.681.41.015.0
................................................
123022482528777826930.0Barcelona83.142.82PassSuccessful9.089.921.59.02.0
123122482528817836932.0Barcelona90.523.02PassSuccessful2.078.636.92.08.0
123422482528977856936.0Barcelona84.627.72PassSuccessful8.090.314.38.02.0
123522482529057866937.0Barcelona90.714.32PassSuccessful2.088.415.32.08.0
123622482529137876938.0Barcelona88.415.32PassSuccessful8.080.133.08.016.0
\n", "

505 rows × 15 columns

\n", "
" ], "text/plain": [ " id eventId minute second teamId x y period \\\n", "2 2248226929 3 0 1.0 Barcelona 50.0 50.0 1 \n", "3 2248226941 4 0 2.0 Barcelona 43.8 46.9 1 \n", "4 2248226951 5 0 4.0 Barcelona 36.6 56.6 1 \n", "5 2248226973 6 0 5.0 Barcelona 28.3 74.1 1 \n", "6 2248226975 7 0 8.0 Barcelona 11.2 53.7 1 \n", "... ... ... ... ... ... ... ... ... \n", "1230 2248252877 782 69 30.0 Barcelona 83.1 42.8 2 \n", "1231 2248252881 783 69 32.0 Barcelona 90.5 23.0 2 \n", "1234 2248252897 785 69 36.0 Barcelona 84.6 27.7 2 \n", "1235 2248252905 786 69 37.0 Barcelona 90.7 14.3 2 \n", "1236 2248252913 787 69 38.0 Barcelona 88.4 15.3 2 \n", "\n", " type outcome playerId endX endY passer recipient \n", "2 Pass Successful 9.0 43.9 46.9 9.0 8.0 \n", "3 Pass Successful 8.0 36.4 56.0 8.0 21.0 \n", "4 Pass Successful 21.0 28.5 73.8 21.0 15.0 \n", "5 Pass Successful 15.0 11.6 51.8 15.0 1.0 \n", "6 Pass Successful 1.0 11.6 81.4 1.0 15.0 \n", "... ... ... ... ... ... ... ... \n", "1230 Pass Successful 9.0 89.9 21.5 9.0 2.0 \n", "1231 Pass Successful 2.0 78.6 36.9 2.0 8.0 \n", "1234 Pass Successful 8.0 90.3 14.3 8.0 2.0 \n", "1235 Pass Successful 2.0 88.4 15.3 2.0 8.0 \n", "1236 Pass Successful 8.0 80.1 33.0 8.0 16.0 \n", "\n", "[505 rows x 15 columns]" ] }, "execution_count": 67, "metadata": {}, "output_type": "execute_result" } ], "source": [ "successful" ] }, { "cell_type": "code", "execution_count": 68, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ ":4: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " successful['passer'] = pas\n", ":5: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " successful['recipient'] = rec\n" ] } ], "source": [ "#this makes it so our passer and recipients are float values\n", "pas = pd.to_numeric(successful['passer'],downcast='integer')\n", "rec = pd.to_numeric(successful['recipient'],downcast='integer')\n", "successful['passer'] = pas\n", "successful['recipient'] = rec" ] }, { "cell_type": "code", "execution_count": 69, "metadata": {}, "outputs": [], "source": [ "#now we need to find the average locations and counts of the passes\n", "average_locations = successful.groupby('passer').agg({'x':['mean'],'y':['mean','count']})\n", "average_locations.columns = ['x','y','count']" ] }, { "cell_type": "code", "execution_count": 70, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
xycount
passer
17.12400050.32400025
268.27435911.91538539
432.89583343.51875048
853.33292741.60853782
969.91666751.3833336
1063.20161342.35161362
1538.40909174.37818255
1669.59428669.47142935
1855.24255383.79361747
2155.66363652.26363655
2849.15686316.28235351
\n", "
" ], "text/plain": [ " x y count\n", "passer \n", "1 7.124000 50.324000 25\n", "2 68.274359 11.915385 39\n", "4 32.895833 43.518750 48\n", "8 53.332927 41.608537 82\n", "9 69.916667 51.383333 6\n", "10 63.201613 42.351613 62\n", "15 38.409091 74.378182 55\n", "16 69.594286 69.471429 35\n", "18 55.242553 83.793617 47\n", "21 55.663636 52.263636 55\n", "28 49.156863 16.282353 51" ] }, "execution_count": 70, "metadata": {}, "output_type": "execute_result" } ], "source": [ "average_locations" ] }, { "cell_type": "code", "execution_count": 71, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
ideventIdminutesecondteamIdxyperiodtypeoutcomeplayerIdendXendYpasserrecipient
22248226929301.0Barcelona50.050.01PassSuccessful9.043.946.998
32248226941402.0Barcelona43.846.91PassSuccessful8.036.456.0821
42248226951504.0Barcelona36.656.61PassSuccessful21.028.573.82115
52248226973605.0Barcelona28.374.11PassSuccessful15.011.651.8151
62248226975708.0Barcelona11.253.71PassSuccessful1.011.681.4115
................................................
123022482528777826930.0Barcelona83.142.82PassSuccessful9.089.921.592
123122482528817836932.0Barcelona90.523.02PassSuccessful2.078.636.928
123422482528977856936.0Barcelona84.627.72PassSuccessful8.090.314.382
123522482529057866937.0Barcelona90.714.32PassSuccessful2.088.415.328
123622482529137876938.0Barcelona88.415.32PassSuccessful8.080.133.0816
\n", "

505 rows × 15 columns

\n", "
" ], "text/plain": [ " id eventId minute second teamId x y period \\\n", "2 2248226929 3 0 1.0 Barcelona 50.0 50.0 1 \n", "3 2248226941 4 0 2.0 Barcelona 43.8 46.9 1 \n", "4 2248226951 5 0 4.0 Barcelona 36.6 56.6 1 \n", "5 2248226973 6 0 5.0 Barcelona 28.3 74.1 1 \n", "6 2248226975 7 0 8.0 Barcelona 11.2 53.7 1 \n", "... ... ... ... ... ... ... ... ... \n", "1230 2248252877 782 69 30.0 Barcelona 83.1 42.8 2 \n", "1231 2248252881 783 69 32.0 Barcelona 90.5 23.0 2 \n", "1234 2248252897 785 69 36.0 Barcelona 84.6 27.7 2 \n", "1235 2248252905 786 69 37.0 Barcelona 90.7 14.3 2 \n", "1236 2248252913 787 69 38.0 Barcelona 88.4 15.3 2 \n", "\n", " type outcome playerId endX endY passer recipient \n", "2 Pass Successful 9.0 43.9 46.9 9 8 \n", "3 Pass Successful 8.0 36.4 56.0 8 21 \n", "4 Pass Successful 21.0 28.5 73.8 21 15 \n", "5 Pass Successful 15.0 11.6 51.8 15 1 \n", "6 Pass Successful 1.0 11.6 81.4 1 15 \n", "... ... ... ... ... ... ... ... \n", "1230 Pass Successful 9.0 89.9 21.5 9 2 \n", "1231 Pass Successful 2.0 78.6 36.9 2 8 \n", "1234 Pass Successful 8.0 90.3 14.3 8 2 \n", "1235 Pass Successful 2.0 88.4 15.3 2 8 \n", "1236 Pass Successful 8.0 80.1 33.0 8 16 \n", "\n", "[505 rows x 15 columns]" ] }, "execution_count": 71, "metadata": {}, "output_type": "execute_result" } ], "source": [ "successful" ] }, { "cell_type": "code", "execution_count": 72, "metadata": {}, "outputs": [], "source": [ "#now we need to find the number of passes between each player\n", "pass_between = successful.groupby(['passer','recipient']).id.count().reset_index()\n", "pass_between.rename({'id':'pass_count'},axis='columns',inplace=True)\n", "\n", "#merge the average location dataframe. We need to merge on the passer first then the recipient\n", "pass_between = pass_between.merge(average_locations, left_on='passer',right_index=True)\n", "pass_between = pass_between.merge(average_locations, left_on='recipient',right_index=True,suffixes=['', '_end'])" ] }, { "cell_type": "code", "execution_count": 73, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
passerrecipientpass_countxycountx_endy_endcount_end
01237.12400050.3240002568.27435911.91538539
1842132.89583343.5187504868.27435911.91538539
2682853.33292741.6085378268.27435911.91538539
3592269.91666751.383333668.27435911.91538539
39102663.20161342.3516136268.27435911.91538539
..............................
521510138.40909174.3781825563.20161342.35161362
6016101069.59428669.4714293563.20161342.35161362
701810755.24255383.7936174763.20161342.35161362
7721101455.66363652.2636365563.20161342.35161362
872810549.15686316.2823535163.20161342.35161362
\n", "

90 rows × 9 columns

\n", "
" ], "text/plain": [ " passer recipient pass_count x y count x_end \\\n", "0 1 2 3 7.124000 50.324000 25 68.274359 \n", "18 4 2 1 32.895833 43.518750 48 68.274359 \n", "26 8 2 8 53.332927 41.608537 82 68.274359 \n", "35 9 2 2 69.916667 51.383333 6 68.274359 \n", "39 10 2 6 63.201613 42.351613 62 68.274359 \n", ".. ... ... ... ... ... ... ... \n", "52 15 10 1 38.409091 74.378182 55 63.201613 \n", "60 16 10 10 69.594286 69.471429 35 63.201613 \n", "70 18 10 7 55.242553 83.793617 47 63.201613 \n", "77 21 10 14 55.663636 52.263636 55 63.201613 \n", "87 28 10 5 49.156863 16.282353 51 63.201613 \n", "\n", " y_end count_end \n", "0 11.915385 39 \n", "18 11.915385 39 \n", "26 11.915385 39 \n", "35 11.915385 39 \n", "39 11.915385 39 \n", ".. ... ... \n", "52 42.351613 62 \n", "60 42.351613 62 \n", "70 42.351613 62 \n", "77 42.351613 62 \n", "87 42.351613 62 \n", "\n", "[90 rows x 9 columns]" ] }, "execution_count": 73, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pass_between" ] }, { "cell_type": "code", "execution_count": 74, "metadata": {}, "outputs": [], "source": [ "#set minimum threshold of combinations.. I like 5 for high passing teams. 2 or 3 for low passing.\n", "pass_between = pass_between[pass_between['pass_count']>5]" ] }, { "cell_type": "code", "execution_count": 75, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
passerrecipientpass_countxycountx_endy_endcount_end
2682853.33292741.6085378268.27435911.91538539
39102663.20161342.3516136268.27435911.91538539
832821049.15686316.2823535168.27435911.91538539
2784853.33292741.6085378232.89583343.51875048
50154938.40909174.3781825532.89583343.51875048
842841349.15686316.2823535132.89583343.51875048
11281168.27435911.9153853953.33292741.60853782
1948632.89583343.5187504853.33292741.60853782
411081763.20161342.3516136253.33292741.60853782
51158638.40909174.3781825553.33292741.60853782
68188655.24255383.7936174753.33292741.60853782
762181355.66363652.2636365553.33292741.60853782
852881349.15686316.2823535153.33292741.60853782
214152032.89583343.5187504838.40909174.37818255
30815653.33292741.6085378238.40909174.37818255
711815755.24255383.7936174738.40909174.37818255
782115755.66363652.2636365538.40909174.37818255
31816853.33292741.6085378269.59428669.47142935
531516638.40909174.3781825569.59428669.47142935
7218161055.24255383.7936174769.59428669.47142935
32818653.33292741.6085378255.24255383.79361747
5415181538.40909174.3781825555.24255383.79361747
6216181169.59428669.4714293555.24255383.79361747
23421632.89583343.5187504855.66363652.26363655
338211053.33292741.6085378255.66363652.26363655
4610211263.20161342.3516136255.66363652.26363655
5515211038.40909174.3781825555.66363652.26363655
731821955.24255383.7936174755.66363652.26363655
16228768.27435911.9153853949.15686316.28235351
24428732.89583343.5187504849.15686316.28235351
348281153.33292741.6085378249.15686316.28235351
471028763.20161342.3516136249.15686316.28235351
812128755.66363652.2636365549.15686316.28235351
48151638.40909174.378182557.12400050.32400025
132101168.27435911.9153853963.20161342.35161362
298102353.33292741.6085378263.20161342.35161362
6016101069.59428669.4714293563.20161342.35161362
701810755.24255383.7936174763.20161342.35161362
7721101455.66363652.2636365563.20161342.35161362
\n", "
" ], "text/plain": [ " passer recipient pass_count x y count x_end \\\n", "26 8 2 8 53.332927 41.608537 82 68.274359 \n", "39 10 2 6 63.201613 42.351613 62 68.274359 \n", "83 28 2 10 49.156863 16.282353 51 68.274359 \n", "27 8 4 8 53.332927 41.608537 82 32.895833 \n", "50 15 4 9 38.409091 74.378182 55 32.895833 \n", "84 28 4 13 49.156863 16.282353 51 32.895833 \n", "11 2 8 11 68.274359 11.915385 39 53.332927 \n", "19 4 8 6 32.895833 43.518750 48 53.332927 \n", "41 10 8 17 63.201613 42.351613 62 53.332927 \n", "51 15 8 6 38.409091 74.378182 55 53.332927 \n", "68 18 8 6 55.242553 83.793617 47 53.332927 \n", "76 21 8 13 55.663636 52.263636 55 53.332927 \n", "85 28 8 13 49.156863 16.282353 51 53.332927 \n", "21 4 15 20 32.895833 43.518750 48 38.409091 \n", "30 8 15 6 53.332927 41.608537 82 38.409091 \n", "71 18 15 7 55.242553 83.793617 47 38.409091 \n", "78 21 15 7 55.663636 52.263636 55 38.409091 \n", "31 8 16 8 53.332927 41.608537 82 69.594286 \n", "53 15 16 6 38.409091 74.378182 55 69.594286 \n", "72 18 16 10 55.242553 83.793617 47 69.594286 \n", "32 8 18 6 53.332927 41.608537 82 55.242553 \n", "54 15 18 15 38.409091 74.378182 55 55.242553 \n", "62 16 18 11 69.594286 69.471429 35 55.242553 \n", "23 4 21 6 32.895833 43.518750 48 55.663636 \n", "33 8 21 10 53.332927 41.608537 82 55.663636 \n", "46 10 21 12 63.201613 42.351613 62 55.663636 \n", "55 15 21 10 38.409091 74.378182 55 55.663636 \n", "73 18 21 9 55.242553 83.793617 47 55.663636 \n", "16 2 28 7 68.274359 11.915385 39 49.156863 \n", "24 4 28 7 32.895833 43.518750 48 49.156863 \n", "34 8 28 11 53.332927 41.608537 82 49.156863 \n", "47 10 28 7 63.201613 42.351613 62 49.156863 \n", "81 21 28 7 55.663636 52.263636 55 49.156863 \n", "48 15 1 6 38.409091 74.378182 55 7.124000 \n", "13 2 10 11 68.274359 11.915385 39 63.201613 \n", "29 8 10 23 53.332927 41.608537 82 63.201613 \n", "60 16 10 10 69.594286 69.471429 35 63.201613 \n", "70 18 10 7 55.242553 83.793617 47 63.201613 \n", "77 21 10 14 55.663636 52.263636 55 63.201613 \n", "\n", " y_end count_end \n", "26 11.915385 39 \n", "39 11.915385 39 \n", "83 11.915385 39 \n", "27 43.518750 48 \n", "50 43.518750 48 \n", "84 43.518750 48 \n", "11 41.608537 82 \n", "19 41.608537 82 \n", "41 41.608537 82 \n", "51 41.608537 82 \n", "68 41.608537 82 \n", "76 41.608537 82 \n", "85 41.608537 82 \n", "21 74.378182 55 \n", "30 74.378182 55 \n", "71 74.378182 55 \n", "78 74.378182 55 \n", "31 69.471429 35 \n", "53 69.471429 35 \n", "72 69.471429 35 \n", "32 83.793617 47 \n", "54 83.793617 47 \n", "62 83.793617 47 \n", "23 52.263636 55 \n", "33 52.263636 55 \n", "46 52.263636 55 \n", "55 52.263636 55 \n", "73 52.263636 55 \n", "16 16.282353 51 \n", "24 16.282353 51 \n", "34 16.282353 51 \n", "47 16.282353 51 \n", "81 16.282353 51 \n", "48 50.324000 25 \n", "13 42.351613 62 \n", "29 42.351613 62 \n", "60 42.351613 62 \n", "70 42.351613 62 \n", "77 42.351613 62 " ] }, "execution_count": 75, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pass_between" ] }, { "cell_type": "code", "execution_count": 76, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "#plot the pitch\n", "\n", "pitch = pitch = Pitch(pitch_type='statsbomb', orientation='horizontal',\n", " pitch_color='#22312b', line_color='#c7d5cc', figsize=(13, 8),\n", " constrained_layout=True, tight_layout=False)\n", "fig, ax = pitch.draw()\n", "\n", "#plot the arrows\n", "\n", "arrows = pitch.arrows(1.2*pass_between.x,.8*pass_between.y,1.2*pass_between.x_end,.8*pass_between.y_end,\n", " width = 5, headwidth = 5, color = 'w', ax = ax, zorder = 1, alpha = .5)\n", "\n", "#plot the nodes\n", "\n", "nodes = pitch.scatter(1.2*average_locations.x,.8*average_locations.y,\n", " s = 300, color = '#d3d3d3', edgecolors = 'black', linewidth = 2.5, alpha = 1, zorder = 1, ax=ax)\n", "\n", "#make annotations" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.3" } }, "nbformat": 4, "nbformat_minor": 4 }