import?pandas?as?pd?
import?numpy?as?np?
import?matplotlib.pyplot?as?plt?
import?seaborn?as?sns?
import?matplotlib.ticker?as?ticker?
from?sklearn.model_selection?import?train_test_split
from?sklearn.linear_model?import?LogisticRegression

world_cup?=?pd.read_csv("World_Cup_2018_Dataset.csv")
results?=?pd.read_csv("results.csv")

world_cup.head()

winner?=?[]
for?i?in?range(len(results["home_team"])):
????if?results["home_score"][i]?>?results["away_score"][i]:
????????winner.append(results["home_team"][i])
????elif?results["home_score"][i]?<?results["away_score"][i]:
????????winner.append(results["away_team"][i])
????else:
????????winner.append("Draw")

results["winning_team"]?=?winner
results["goal_difference"]?=?np.absolute(results["home_score"]?-?results["away_score"])
results.head()

df?=?results[(results["home_team"]?==?"Argentina")?|?(results["away_team"]?==?"Argentina")]
argen?=?df.iloc[:]
argen.head()

year?=?[]
for?row?in?argen['date']:
????year.append(int(row[:4]))
argen["match_year"]?=?year
argen_1930?=?argen[argen.match_year?>=?1930]
argen_1930.head()

x?=?["Argentina","Loss","Draw"]
y?=?[474,?220,?173]
?
sns.barplot(x,?y)
plt.title("win?games?vs?loss?games")
plt.xlabel("win?vs?loss")
plt.ylabel("count")
plt.show()

world_cup_russia?=?["Australia",?"Iran",?"Japan",?"Korea?Republic",?"Saudi?Arabia",?"Egypt",?"Morocco",
???????????????????"Nigeria",?"Senegal",?"Tunisia",?"Costa?Rica",?"Mexico",?"Panama",?"Argentina",?"Brazil",?
????????????????????"Colombia",?"Peru",?"Uruguay",?"Belgium",?"Croatia",?"Denmark",?"England",?"France",?
????????????????????"Germany",?"Iceland",?"Poland",?"Portugal",?"Russia",?"Serbia",?"Spain",?"Sweden",?"Switzerland"]

df_team_home?=?results[results['home_team'].isin(world_cup_russia)]
df_team_away?=?results[results['away_team'].isin(world_cup_russia)]
df_teams?=?pd.concat((df_team_home,?df_team_away))
df_teams.drop_duplicates(inplace=True)
df_teams.tail()

year?=?[]
for?row?in?df_teams["date"]:
????year.append(int(row[:4]))
df_teams["match_year"]?=?year
df_teams_1930?=?df_teams[df_teams.match_year?>=?1930]
df_teams_1930.head()

df_teams_1930?=?df_teams.drop(['date',?'home_score',?'away_score',?'tournament',?'city',?'country',?'goal_difference',?'match_year'],?axis=1)
df_teams_1930.tail()

df_teams_1930?=?df_teams_1930.reset_index(drop=True)
df_teams_1930.loc[df_teams_1930.winning_team?==?df_teams_1930.home_team,'winning_team']=2
df_teams_1930.loc[df_teams_1930.winning_team?==?'Draw',?'winning_team']=1
df_teams_1930.loc[df_teams_1930.winning_team?==?df_teams_1930.away_team,?'winning_team']=0
df_teams_1930.tail()

#?convert?home?team?and?away?team?from?categorical?variables?to?continous?inputs?
#?Get?dummy?variables
final?=?pd.get_dummies(df_teams_1930,?prefix=['home_team',?'away_team'],?columns=['home_team',?'away_team'])
final.head()

#?Separate?X?and?y?sets
X?=?final.drop(['winning_team'],?axis=1)
y?=?final["winning_team"]
y?=?y.astype('int')

#?Separate?train?and?test?sets
X_train,?X_test,?y_train,?y_test?=?train_test_split(X,?y,?test_size=0.30,?random_state=42)

logreg?=?LogisticRegression()
logreg.fit(X_train,?y_train)
score?=?logreg.score(X_train,?y_train)
score2?=?logreg.score(X_test,?y_test)

print("Training?set?accuracy:?",?'%.3f'%(score))
print("Test?set?accuracy:?",?'%.3f'%(score2))

#?導(dǎo)入新的數(shù)據(jù)集，各球隊(duì)的世界排名
ranking?=?pd.read_csv('datasets/fifa_rankings.csv')?
#?2018年俄羅斯世界杯的對(duì)陣情況
fixtures?=?pd.read_csv('datasets/fixtures.csv')

pred_set?=?[]

#?插入兩個(gè)新的字段，主隊(duì)和客隊(duì)排名的字段
fixtures.insert(1,?'first_position',?fixtures['Home?Team'].map(ranking.set_index('Team')['Position']))
fixtures.insert(2,?'second_position',?fixtures['Away?Team'].map(ranking.set_index('Team')['Position']))

#?我們篩選出來在小組賽中的對(duì)陣情況
fixtures?=?fixtures.iloc[:48,?:]
fixtures.head()

#?Loop?to?add?teams?to?new?prediction?dataset?based?on?the?ranking?position?of?each?team
for?index,?row?in?fixtures.iterrows():
????if?row['first_position']?<?row['second_position']:
????????pred_set.append({'home_team':?row['Home?Team'],?'away_team':?row['Away?Team'],?'winning_team':?None})
????else:
????????pred_set.append({'home_team':?row['Away?Team'],?'away_team':?row['Home?Team'],?'winning_team':?None})
????????
pred_set?=?pd.DataFrame(pred_set)
backup_pred_set?=?pred_set

pred_set.head()

#?小組賽對(duì)決的預(yù)測(cè)?
predictions?=?logreg.predict(pred_set)
for?i?in?range(fixtures.shape[0]):
????print(backup_pred_set.iloc[i,?1]?+?"?and?"?+?backup_pred_set.iloc[i,?0])
????if?predictions[i]?==?2:
????????print("Winner:?"?+?backup_pred_set.iloc[i,?1])
????elif?predictions[i]?==?1:
????????print("Draw")
????elif?predictions[i]?==?0:
????????print("Winner:?"?+?backup_pred_set.iloc[i,?0])
????print('Probability?of?'?+?backup_pred_set.iloc[i,?1]?+?'?winning:?',?'%.3f'%(logreg.predict_proba(pred_set)[i][2]))
????print('Probability?of?Draw:?',?'%.3f'%(logreg.predict_proba(pred_set)[i][1]))
????print('Probability?of?'?+?backup_pred_set.iloc[i,?0]?+?'?winning:?',?'%.3f'%(logreg.predict_proba(pred_set)[i][0]))
????print("")

fixtures?=?pd.read_csv("datasets/fifa-world-cup-2022.csv")
fixtures.head()