大数据分析——对世界杯比赛进行分析及预测

（一）选题背景：世界杯比赛是全球最大规模的国际足球赛事之一，吸引着数以亿计的观众。对于球迷和体育爱好者来  说，预测比赛结果是一项有趣且具有挑战性的任务。足球比赛结果的预测可以帮助球迷制定投注策略、提供比赛观看的参考以及评估球队和球员的表现。

（二）方案设计：从网站中下载相关的数据集，对数据进行整理，在python环境下，对数据进行预处理。最后使用决策树算法构建世界杯比赛预测模型，测试模型。

2.导入第三方库

 3.加载三个数据文件，并删除缺失值

 4.数据分析

 简单的分析一下世界杯的冠军情况

 5.数据预处理

 接着创建一个字典用来储存球队名称

 删除不必要的列同时计算每支队伍成为冠军的次数

 定义一个函数用于找出获胜队伍

 将team-name字典中的团队名称替换为id

 5.准备建模用到的X,y数据

 打乱数据

 6.模型构建

用svm支持向量机模型进行训练并打印模型的评估指标

 决策树模型更加准确 ，最终选择决策树算法作为模型选择。

7.模型预测

 这里使用2022年卡塔尔世界杯最后半决赛部分来检测模型效果

 预测正确

 预测正确

 预测正确

 可惜，预测失败

（四）实验源代码

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.utils import shuffle
from sklearn.metrics import classification_report, confusion_matrix
from sklearn.svm import SVC
import warnings
warnings.filterwarnings('ignore')
# 导入数据
matches = pd.read_csv('WorldCupMatches.csv')
players = pd.read_csv('WorldCupPlayers.csv')
cups = pd.read_csv('WorldCupsSummary.csv')
# 删除缺失值
matches = matches.dropna()
players = players.dropna()
cups = cups.dropna()

matches.head()
matches.head()
players.head()
# 世界杯赛冠军的数量
plt.figure(figsize=(12,6))
sns.countplot(x='Winner',data=cups)
plt.show()
# 用德国取代德国DR和德国FR，用俄罗斯取代苏联
def replace_name(df):
if(df['Home Team Name'] in ['German DR', 'Germany FR']):
df['Home Team Name'] = 'Germany'
elif(df['Home Team Name'] == 'Soviet Union'):
df['Home Team Name'] = 'Russia'
if(df['Away Team Name'] in ['German DR', 'Germany FR']):
df['Away Team Name'] = 'Germany'
elif(df['Away Team Name'] == 'Soviet Union'):
df['Away Team Name'] = 'Russia'
return df

matches = matches.apply(replace_name, axis='columns')
matches.head()
# 创建一个存储足球队的字典
team_name = {}
index = 0
for idx, row in matches.iterrows():
name = row['Home Team Name']
if(name not in team_name.keys()):
team_name[name] = index
index += 1
name = row['Away Team Name']
if(name not in team_name.keys()):
team_name[name] = index
index += 1

team_name
# 删除不必要的列
dropped_matches = matches.drop(['Datetime', 'Stadium', 'Referee', 'Assistant 1', 'Assistant 2', 'RoundID',
'Home Team Initials', 'Away Team Initials', 'Half-time Home Goals', 'Half-time Away Goals',
'Attendance', 'City', 'MatchID', 'Stage'], 1)
# 计算每支球队成为世界杯赛冠军的次数
championships = cups['Winner'].map(lambda p: 'Germany' if p=='Germany FR' else p).value_counts()
championships
# 加上“主队冠军”和“客场冠军”:获取世界杯冠军的次数
dropped_matches['Home Team Championship'] = 0
dropped_matches['Away Team Championship'] = 0

def count_championship(df):
if(championships.get(df['Home Team Name']) != None):
df['Home Team Championship'] = championships.get(df['Home Team Name'])
if(championships.get(df['Away Team Name']) != None):
df['Away Team Championship'] = championships.get(df['Away Team Name'])
return df

dropped_matches = dropped_matches.apply(count_championship, axis='columns')
dropped_matches.head()
# 定义一个函数用于找出谁赢了:主场胜:1，客场胜:2，平局:0
dropped_matches['Winner'] = '-'
def find_winner(df):
if(int(df['Home Team Goals']) == int(df['Away Team Goals'])):
df['Winner'] = 0
elif(int(df['Home Team Goals']) > int(df['Away Team Goals'])):
df['Winner'] = 1
else:
df['Winner'] = 2
return df

dropped_matches = dropped_matches.apply(find_winner, axis='columns')
dropped_matches.head()
# 将team_name字典中的团队名称替换为id
def replace_team_name_by_id(df):
df['Home Team Name'] = team_name[df['Home Team Name']]
df['Away Team Name'] = team_name[df['Away Team Name']]
return df

teamid_matches = dropped_matches.apply(replace_team_name_by_id, axis='columns')
teamid_matches.head()
# 删除不必要的列
teamid_matches = teamid_matches.drop(['Year', 'Home Team Goals', 'Away Team Goals'], 1)
teamid_matches.head()
X = teamid_matches[['Home Team Name', 'Away Team Name', 'Home Team Championship','Away Team Championship']]
X = np.array(X).astype('float64')
# 附加数据:只需将“主队名称”替换为“客场球队名称”，将“主队冠军”替换为“客场球队冠军”，然后替换结果
_X = X.copy()
_X[:,0] = X[:,1]
_X[:,1] = X[:,0]
_X[:,2] = X[:,3]
_X[:,3] = X[:,2]
y = dropped_matches['Winner']
y = np.array(y).astype('int')
y = np.reshape(y,(1,850))
y = y[0]
_y = y.copy()
for i in range(len(_y)):
if(_y[i]==1):
_y[i] = 2
elif(_y[i] ==2):
_y[i] = 1
X = np.concatenate((X,_X), axis= 0)
y = np.concatenate((y,_y))
print(X)
print(y)
# 打乱数据，然后拆分数据集为训练集和测试集
X,y = shuffle(X,y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
# 用SVM支持向量机模型进行训练
svm_model = SVC(kernel='rbf', class_weight='balanced', probability=True)
svm_model.fit(X, y)
print("Predicting on the test set")
y_pred = svm_model.predict(X_test)
print(svm_model.score(X_test,y_test))
print(classification_report(y_test, y_pred))
print(confusion_matrix(y_test, y_pred, labels=range(3)))
# 构建决策树模型
from sklearn.tree import DecisionTreeClassifier
tree_model = DecisionTreeClassifier()
tree_model.fit(X, y)
print("Predicting on the test set")
y_pred = tree_model.predict(X_test)
print(tree_model.score(X_test,y_test))
print(classification_report(y_test, y_pred))
print(confusion_matrix(y_test, y_pred))
# 定义一个预测函数，需要传递两个球队名称，输出两个获胜的概率
def prediction(team1, team2):
id1 = team_name[team1]
id2 = team_name[team2]
championship1 = championships.get(team1) if championships.get(team1) != None else 0
championship2 = championships.get(team2) if championships.get(team2) != None else 0
x = np.array([id1, id2, championship1, championship2]).astype('float64')
x = np.reshape(x, (1,-1))
_y = svm_model.predict_proba(x)[0]
text = ('Chance for '+team1+' to win '+team2+' is {}\nChance for '+team2+' to win '+team1+' is {}\nChance for '+team1+' and '+team2+' draw is {}').format(_y[1]*100,_y[2]*100,_y[0]*100)
return _y[0], text
# 预测英格兰对法国的比赛
prob, text = prediction('England', 'France')
print(text)
# 预测阿根廷对克罗地亚的比赛
prob, text = prediction('Argentina', 'Croatia')
print(text)
# 预测法国对摩洛哥的比赛
prob, text = prediction('France', 'Morocco')
print(text)
# 预测克罗地亚对摩洛哥的比赛
prob, text = prediction('Croatia', 'Morocco')
print(text)
# 预测阿根廷对法国的比赛
prob, text = prediction('Argentina','France')
print(text)

（五）总结：通过这次python实战，我学到了许多新知识，丰富了经验，缩小了实践和理论的差距。在今后的生活中，我将继续学习不断提升理论涵养，深入实践，提供自身综合素质。