{ "cells": [ { "cell_type": "markdown", "id": "3c7f88ba", "metadata": {}, "source": [ "## To identify the Best Players in Death over in IPL 2024" ] }, { "cell_type": "markdown", "id": "00f01088", "metadata": {}, "source": [ "Importing required libraries\n", "* We gratefully acknowledge **cricsheet.org** for providing the cricket statistics used in this analysis. Their comprehensive database was instrumental in compiling the data that enriches our understanding of the game." ] }, { "cell_type": "code", "execution_count": 1, "id": "29e92e73", "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "import math\n", "import matplotlib.pyplot as plt\n", "\n", "import warnings\n", "warnings.filterwarnings('ignore')\n", "\n", "pd.set_option('display.max_columns',None)\n", "pd.set_option('display.expand_frame_repr',False)\n", "pd.set_option('max_colwidth',-1)" ] }, { "cell_type": "markdown", "id": "91a64e64", "metadata": {}, "source": [ "* Downloaded data from cricsheet.org\n", "* reading the data using read_csv()" ] }, { "cell_type": "code", "execution_count": 2, "id": "fd50534a", "metadata": {}, "outputs": [], "source": [ "data = pd.read_csv('ipl_csv2/all_matches.csv')" ] }, { "cell_type": "code", "execution_count": 3, "id": "b30a7973", "metadata": {}, "outputs": [], "source": [ "match_df = data.copy()" ] }, { "cell_type": "code", "execution_count": 4, "id": "d8f4be70", "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", "
match_idseasonstart_datevenueinningsballbatting_teambowling_teamstrikernon_strikerbowlerruns_off_batextraswidesnoballsbyeslegbyespenaltywicket_typeplayer_dismissedother_wicket_typeother_player_dismissed
03359822007/082008-04-18M Chinnaswamy Stadium10.1Kolkata Knight RidersRoyal Challengers BangaloreSC GangulyBB McCullumP Kumar01NaNNaNNaN1.0NaNNaNNaNNaNNaN
\n", "
" ], "text/plain": [ " match_id season start_date venue innings ball batting_team bowling_team striker non_striker bowler runs_off_bat extras wides noballs byes legbyes penalty wicket_type player_dismissed other_wicket_type other_player_dismissed\n", "0 335982 2007/08 2008-04-18 M Chinnaswamy Stadium 1 0.1 Kolkata Knight Riders Royal Challengers Bangalore SC Ganguly BB McCullum P Kumar 0 1 NaN NaN NaN 1.0 NaN NaN NaN NaN NaN " ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "match_df.head(1)" ] }, { "cell_type": "markdown", "id": "bab40fa0", "metadata": {}, "source": [ "## Adding some more features to the data" ] }, { "cell_type": "code", "execution_count": 5, "id": "0c1d74aa", "metadata": {}, "outputs": [], "source": [ "match_df['isDot'] = match_df['runs_off_bat'] \\\n", " .apply(lambda x:1 if x==0 else 0)\n", "\n", "match_df['isOne'] = match_df['runs_off_bat'] \\\n", " .apply(lambda x:1 if x==1 else 0)\n", "\n", "match_df['isTwo'] = match_df['runs_off_bat'] \\\n", " .apply(lambda x:1 if x==2 else 0)\n", "\n", "match_df['isThree'] = match_df['runs_off_bat'] \\\n", " .apply(lambda x:1 if x==3 else 0)\n", "\n", "match_df['isFour'] = match_df['runs_off_bat'] \\\n", " .apply(lambda x:1 if x==4 else 0)\n", "\n", "match_df['isSix'] = match_df['runs_off_bat'] \\\n", " .apply(lambda x:1 if x==6 else 0)\n", "\n", "match_df['isBoundary'] = match_df['runs_off_bat'] \\\n", " .apply(lambda x:1 if x==6 or x==4 else 0)\n", "\n", "match_df['Over'] = match_df['ball'] \\\n", " .apply(lambda x:math.floor(x)+1)\n", "\n", "match_df['year']=pd.to_datetime(match_df['start_date']).dt.year\n" ] }, { "cell_type": "code", "execution_count": 6, "id": "d55f4241", "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", "
match_idseasonstart_datevenueinningsballbatting_teambowling_teamstrikernon_strikerbowlerruns_off_batextraswidesnoballsbyeslegbyespenaltywicket_typeplayer_dismissedother_wicket_typeother_player_dismissedisDotisOneisTwoisThreeisFourisSixisBoundaryOveryear
255757142628720242024-05-01MA Chidambaram Stadium, Chepauk, Chennai217.5Punjab KingsChennai Super KingsSM CurranShashank SinghRJ Gleeson01NaNNaNNaN1.0NaNNaNNaNNaNNaN1000000182024
255758142628720242024-05-01MA Chidambaram Stadium, Chepauk, Chennai217.6Punjab KingsChennai Super KingsShashank SinghSM CurranRJ Gleeson20NaNNaNNaNNaNNaNNaNNaNNaNNaN0010000182024
\n", "
" ], "text/plain": [ " match_id season start_date venue innings ball batting_team bowling_team striker non_striker bowler runs_off_bat extras wides noballs byes legbyes penalty wicket_type player_dismissed other_wicket_type other_player_dismissed isDot isOne isTwo isThree isFour isSix isBoundary Over year\n", "255757 1426287 2024 2024-05-01 MA Chidambaram Stadium, Chepauk, Chennai 2 17.5 Punjab Kings Chennai Super Kings SM Curran Shashank Singh RJ Gleeson 0 1 NaN NaN NaN 1.0 NaN NaN NaN NaN NaN 1 0 0 0 0 0 0 18 2024\n", "255758 1426287 2024 2024-05-01 MA Chidambaram Stadium, Chepauk, Chennai 2 17.6 Punjab Kings Chennai Super Kings Shashank Singh SM Curran RJ Gleeson 2 0 NaN NaN NaN NaN NaN NaN NaN NaN NaN 0 0 1 0 0 0 0 18 2024" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "match_df.tail(2)" ] }, { "cell_type": "markdown", "id": "f2813cb4", "metadata": {}, "source": [ "### Filtering the data Selecting only Death overs and IPL season 2024" ] }, { "cell_type": "code", "execution_count": 7, "id": "9f6c11a1", "metadata": {}, "outputs": [], "source": [ "match_df= match_df[(match_df['Over']>16)&(match_df['year']==2024)]" ] }, { "cell_type": "code", "execution_count": 8, "id": "9da95cd1", "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", "
runs_off_bat
striker
A Badoni69
A Nortje3
AD Russell89
AJ Turner1
\n", "
" ], "text/plain": [ " runs_off_bat\n", "striker \n", "A Badoni 69 \n", "A Nortje 3 \n", "AD Russell 89 \n", "AJ Turner 1 " ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "pd.DataFrame(match_df.groupby(['striker'])['runs_off_bat'].sum()).head(4)" ] }, { "cell_type": "code", "execution_count": 9, "id": "551ba09c", "metadata": {}, "outputs": [], "source": [ "runs = pd.DataFrame(match_df \\\n", " .groupby(['striker'])['runs_off_bat'].sum()) \\\n", " .sort_values(by=['runs_off_bat'],ascending=False) \\\n", " .reset_index() \\\n", " .rename(columns={'runs_off_bat':'Runs'})" ] }, { "cell_type": "code", "execution_count": 10, "id": "620627e9", "metadata": {}, "outputs": [], "source": [ "balls = pd.DataFrame(match_df[pd.isnull(match_df['wides'])] \\\n", " .groupby(['striker'])['Over'].count()) \\\n", " .sort_values(by=['striker'],ascending=False) \\\n", " .reset_index() \\\n", " .rename(columns={'Over':'Balls faced'})" ] }, { "cell_type": "code", "execution_count": 11, "id": "13083723", "metadata": {}, "outputs": [], "source": [ "innings = pd.DataFrame(match_df \\\n", " .groupby(['striker'])['match_id']\\\n", " .apply(lambda x:len(list(np.unique(x))))) \\\n", " .sort_values(by=['striker'],ascending=False)\\\n", " .reset_index() \\\n", " .rename(columns={'match_id':'innings'})" ] }, { "cell_type": "code", "execution_count": 12, "id": "a890f8db", "metadata": {}, "outputs": [], "source": [ "dismissals = pd.DataFrame(match_df \\\n", " .groupby(['striker'])['player_dismissed'].count()) \\\n", " .sort_values(by=['striker'],ascending=False) \\\n", " .reset_index() \\\n", " .rename(columns={'player_dismissed':'dismissals'})" ] }, { "cell_type": "code", "execution_count": 13, "id": "57fd965a", "metadata": {}, "outputs": [], "source": [ "sixes = pd.DataFrame(match_df \\\n", " .groupby(['striker'])['isSix'].sum()) \\\n", " .sort_values(by=['striker'],ascending=False) \\\n", " .reset_index() \\\n", " .rename(columns={'isSix':'Sixes'})" ] }, { "cell_type": "code", "execution_count": 14, "id": "82efcd42", "metadata": {}, "outputs": [], "source": [ "fours = pd.DataFrame(match_df \\\n", " .groupby(['striker'])['isFour'].sum()) \\\n", " .sort_values(by=['striker'],ascending=False)\\\n", " .reset_index() \\\n", " .rename(columns={'isFour':'Fours'})" ] }, { "cell_type": "markdown", "id": "f4ac8388", "metadata": {}, "source": [ "#### Merging all the dataframes to combine all the required attributes" ] }, { "cell_type": "code", "execution_count": 15, "id": "12017e5b", "metadata": {}, "outputs": [], "source": [ "merge_df = pd.merge(innings,runs, on='striker') \\\n", " .merge(balls, on='striker') \\\n", " .merge(dismissals, on='striker') \\\n", " .merge(sixes, on='striker') \\\n", " .merge(fours, on='striker')" ] }, { "cell_type": "markdown", "id": "f309615e", "metadata": {}, "source": [ "### Adding more attributes to identify the best player" ] }, { "cell_type": "code", "execution_count": 16, "id": "64abf94d", "metadata": {}, "outputs": [], "source": [ "merge_df['Strike Rate']= 100*merge_df['Runs']/merge_df['Balls faced']\n", "merge_df['RPI']= merge_df['Runs']/merge_df['innings']\n", "merge_df['Average']= merge_df['Runs']/merge_df['dismissals']\n", "merge_df['Boundary']= merge_df['Sixes']+merge_df['Fours']\n", "merge_df['Boundary percentage']= merge_df['Boundary']/merge_df['Balls faced']*100\n", "merge_df['Balls per boundary']= merge_df['Balls faced']/merge_df['Boundary']" ] }, { "cell_type": "markdown", "id": "1b4f9468", "metadata": {}, "source": [ "#### Minimum 2 innings played in death overs" ] }, { "cell_type": "code", "execution_count": 17, "id": "22dfee9e", "metadata": {}, "outputs": [], "source": [ "df_death_over=merge_df[(merge_df['innings']>2)] \\\n", " .sort_values(by='Strike Rate', ascending=False) \\\n", " .reset_index() \\\n", " .head(10)" ] }, { "cell_type": "markdown", "id": "70c6964a", "metadata": {}, "source": [ "### Storing the data in csv file" ] }, { "cell_type": "code", "execution_count": 18, "id": "b9326b18", "metadata": {}, "outputs": [], "source": [ "df_death_over.to_csv(\"Death overs.csv\")" ] }, { "cell_type": "code", "execution_count": 19, "id": "ca28c978", "metadata": {}, "outputs": [], "source": [ "df_death_over = df_death_over.drop('index',axis=1)" ] }, { "cell_type": "code", "execution_count": 20, "id": "573cc419", "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", "
strikerinningsRunsBoundaryBoundary percentageStrike Rate
0T Stubbs51522446.153846292.307692
1R Shepherd4561050.000000280.000000
2SS Iyer5631041.666667262.500000
3H Klaasen41071638.095238254.761905
4R Parag359937.500000245.833333
5RR Pant4881438.888889244.444444
\n", "
" ], "text/plain": [ " striker innings Runs Boundary Boundary percentage Strike Rate\n", "0 T Stubbs 5 152 24 46.153846 292.307692 \n", "1 R Shepherd 4 56 10 50.000000 280.000000 \n", "2 SS Iyer 5 63 10 41.666667 262.500000 \n", "3 H Klaasen 4 107 16 38.095238 254.761905 \n", "4 R Parag 3 59 9 37.500000 245.833333 \n", "5 RR Pant 4 88 14 38.888889 244.444444 " ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df_death_over[['striker',\n", " 'innings',\n", " 'Runs',\n", " 'Boundary',\n", " 'Boundary percentage',\n", " 'Strike Rate']].head(6)" ] }, { "cell_type": "code", "execution_count": null, "id": "9bbe6902", "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": "3.9.7" } }, "nbformat": 4, "nbformat_minor": 5 }