LOL match 분석2

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.filterwarnings(action='ignore')

plt.rc('font',family='Malgun Gothic')

team_a = pd.read_csv("team1.csv",encoding='cp949',index_col=0)
team_b = pd.read_csv("team2.csv",encoding='cp949',index_col=0)
match_fin = pd.read_csv("match_data.csv",encoding='cp949')

#팀a와 팀b의 승패가 반대인지 정합성 검정을 실시해야합니다
#실행결과 정합성에 문제가 없음이 판단됩니다
for i in range(len(team_a)):
    wf_valid = team_a['win'].iloc[i]
    if team_b['win'].iloc[i] != wf_valid:
        pass
    else:
        print(str(i)+'행 데이터 정합성 문제')

#Null값 제거
match_fin = match_fin[~match_fin['gameDuration'].isnull()]

team_a['gameDuration'] = match_fin['gameDuration'].tolist()
team_b['gameDuration'] = match_fin['gameDuration'].tolist()
match_fin['gameDuration'].index = range(len(match_fin))
team_a['gameDuration'].index = range(len(team_a))
team_b['gameDuration'].index = range(len(team_b))

game_df = pd.concat([team_a,team_b],axis=0)
game_df.shape

#True and False로 되어있는 컬럼들을 1과 0으로 변환
col_lst = [col for col in game_df.columns if 'first' in col ]

dictionary = {True : 1, False:0}

for i in col_lst:
    game_df[i] = game_df[i].map(dictionary)

game_df['win'] = game_df['win'].str.replace('Fail','Lose')

game_df['game_time'] = game_df['gameDuration'] / 60

#게임 시간별 데이터 분할
game_part1 = game_df[game_df['game_time']>=30].sort_values('win')
game_part2 = game_df[game_df['game_time']>=40].sort_values('win')
game_part3 = game_df[game_df['game_time']<30].sort_values('win')
game_part4 = game_df[game_df['game_time']<20].sort_values('win')

#시각화를 위한 함수
def first_valid_visualize(df,target,variable):
    sns.pointplot(target,variable,data=df)
    plt.title(variable+' 변수의 승리확률')
    plt.show()

first_valid_visualize(game_df,'win','towerKills')

first_valid_visualize(game_df,'win','baronKills')

first_valid_visualize(game_df,'win','dragonKills')

def sequence_var_inf(variable):
    global game_part1, game_part2, game_part3, game_part4
    
    value1 = game_part4[variable].value_counts().keys().tolist()
    value2 = game_part3[variable].value_counts().keys().tolist()
    value3 = game_part1[variable].value_counts().keys().tolist()
    value4 = game_part2[variable].value_counts().keys().tolist()
    
    value1.sort()
    value2.sort()
    value3.sort()
    value4.sort()
    print('=============================')
    print('GameTime < 20 minute')
    print('=============================\n')
    for i in value1:
        try:
            a = game_part4[game_part4[variable]==i]['win'].value_counts().values[0]
        except:
            a = 0
        try:
            b = game_part4[game_part4[variable]==i]['win'].value_counts().values[1]
        except:
            b = 0
        print(variable+ ' 변수가 '+str(i)+' 일 때\n Win: {}\n Lose : {}\n'.format(a,b))
    
    print('=============================')
    print('GameTime < 30 minute')
    print('=============================\n')
    for i in value2:
        try:
            a = game_part3[game_part3[variable]==i]['win'].value_counts().values[0]
        except:
            a = 0
        try:
            b = game_part3[game_part3[variable]==i]['win'].value_counts().values[1]
        except:
            b = 0
        print(variable+' 변수가 '+str(i)+' 일 때\n Win : {}\n Lose: {}\n'.format(a,b))
    
    print('=============================')
    print('GameTime > 30 minute')
    print('=============================\n')
    for i in value3:
        try:
            a = game_part1[game_part1[variable]==i]['win'].value_counts().values[0]
        except:
            a = 0
        try:
            b = game_part1[game_part1[variable]==i]['win'].value_counts().values[1]
        except:
            b = 0
        print(variable+ ' 변수가 '+str(i)+' 일 때\n Win : {}\n Lose : {}\n'.format(a,b))
        
    print('=============================')
    print('GameTime > 40 minute')
    print('=============================\n')
    for i in value4:
        try:
            a = game_part2[game_part2[variable]==i]['win'].value_counts().values[0]
        except:
            a = 0
        try:
            b = game_part2[game_part2[variable]==i]['win'].value_counts().values[1]
        except:
            b = 0
        print(variable + ' 변수가 '+str(i)+' 일 때 \n Win: {}\n Lose: {}\n'.format(a,b))

sequence_var_inf('dragonKills')

sequence_var_inf('baronKills')

sequence_var_inf('inhibitorKills')

def kill_ratio(target,variable):
    global game_part1, game_part2, game_part3, game_part4
    
    fig = plt.figure(figsize=(20,20))
    fig.suptitle('게임 시간대별 승리 팀과 패배 팀의 ' + variable + ' 비율',size=30)
    ax1 = fig.add_subplot(221)
    ax2 = fig.add_subplot(222)
    ax3 = fig.add_subplot(223)
    ax4 = fig.add_subplot(224)
    
    ax1.set_title('GameTime < 20 minute',size = 20)
    ax2.set_title('GameTime < 30 minute',size = 20)
    ax3.set_title('GameTime > 30 minute',size = 20)
    ax4.set_title('GameTime > 40 minute',size = 20)
    
    sns.pointplot(target,variable,data=game_part4,ax=ax1)
    sns.pointplot(target,variable,data=game_part3,ax=ax2)
    sns.pointplot(target,variable,data=game_part1,ax=ax3)
    sns.pointplot(target,variable,data=game_part2,ax=ax4)

kill_ratio('win','dragonKills')

kill_ratio('win','towerKills')

kill_ratio('win','inhibitorKills')