目录

1. 下载数据集

2. 数据预处理

3. 模型训练与选择

4. 预测

1. 下载数据集

下载后数据如下：

FIFA World Cup | Kaggle

2. 数据预处理

 reprocess_dataset() 方法是数据进行预处理。预处理过的数据如下：
 

save_dataset() 方法是对预处理过的数据，进行向量化。

完整代码如下：

import pandas as pd
import numpy as np
from sklearn.feature_extraction import DictVectorizer
import joblib
root_path = "models"

def reprocess_dataset():
    #load data
    results = pd.read_csv('datasets/WorldCupMatches.csv', encoding='gbk')

    #Adding goal difference and establishing who is the winner
    winner = []
    for i in range (len(results['Home Team Name'])):
        if results ['Home Team Goals'][i] > results['Away Team Goals'][i]:
            winner.append(results['Home Team Name'][i])
        elif results['Home Team Goals'][i] < results ['Away Team Goals'][i]:
            winner.append(results['Away Team Name'][i])
        else:
            winner.append('Draw')
    results['winning_team'] = winner

    #adding goal difference column
    results['goal_difference'] = np.absolute(results['Home Team Goals'] - results['Away Team Goals'])

    # narrowing to team patcipating in the world cup, totally there are 32 football teams in 2022
    worldcup_teams = ['Qatar','Germany','Denmark', 'Brazil','France','Belgium', 'Serbia',
                      'Spain','Croatia', 'Switzerland', 'England','Netherlands', 'Argentina',' Iran',
                      'Korea Republic','Saudi Arabia', 'Japan', 'Uruguay','Ecuador','Canada',
                      'Senegal', 'Poland', 'Portugal','Tunisia',  'Morocco','Cameroon','USA',
                      'Mexico','Wales','Australia','Costa Rica', 'Ghana']
    df_teams_home = results[results['Home Team Name'].isin(worldcup_teams)]
    df_teams_away = results[results['Away Team Name'].isin(worldcup_teams)]
    df_teams = pd.concat((df_teams_home, df_teams_away))
    df_teams.drop_duplicates()
    df_teams.count()

    #dropping columns that wll not affect matchoutcomes

    df_teams_new =df_teams[[ 'Home Team Name','Away Team Name','winning_team']]
    print(df_teams_new.head()  )

                   #Building the model
    #the prediction label: The winning_team column will show "2" if the home team has won, "1" if it was a tie, and "0" if the away team has won.

    df_teams_new = df_teams_new.reset_index(drop=True)
    df_teams_new.loc[df_teams_new.winning_team == df_teams_new['Home Team Name'],'winning_team']=2
    df_teams_new.loc[df_teams_new.winning_team == 'Draw', 'winning_team']=1
    df_teams_new.loc[df_teams_new.winning_team == df_teams_new['Away Team Name'], 'winning_team']=0

    print(df_teams_new.count()   )
    df_teams_new.to_csv('datasets/raw_train_data.csv', encoding='gbk', index =False)

def save_dataset():
    df_teams_new = pd.read_csv('datasets/raw_train_data.csv', encoding='gbk')

    feature = df_teams_new[[ 'Home Team Name','Away Team Name']]
    vec = DictVectorizer(sparse=False)

    print(feature.to_dict(orient='records'))
    X =vec.fit_transform(feature.to_dict(orient='records'))
    X = X.astype('int')
    print("===")
    print(vec.get_feature_names())
    print(vec.feature_names_)
    y = df_teams_new[[ 'winning_team']]
    y =y.astype('int')
    print(X.shape)
    print(y.shape)
    joblib.dump(vec, root_path+"/vec.joblib")
    np.savez('datasets/train_data', x= X, y = y)

if __name__ == '__main__':
    reprocess_dataset()
    save_dataset();

3. 模型训练与选择

用不同的传统机器学习方法进行训练，训练后的模型比较

可以看到随机森林模型在测试集上准确率最高，所以我们可以用它来做预测。

下面是完整训练代码：

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import matplotlib.ticker as ticker
import matplotlib.ticker as plticker
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn import svm
import sklearn as sklearn
from sklearn.feature_extraction import DictVectorizer
from sklearn.naive_bayes import  MultinomialNB
from sklearn.ensemble import RandomForestClassifier
import joblib
from sklearn.metrics import classification_report
from xgboost import XGBClassifier
from sklearn.metrics import confusion_matrix


root_path = "models_1"

def get_dataset():
    train_data = np.load('datasets/train_data.npz')

    return train_data

def train_by_LogisticRegression(train_data):
    X = train_data['x']
    y = train_data['y']

     # 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)
    joblib.dump(logreg, root_path+'/LogisticRegression_model.joblib')

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

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

def train_by_svm(train_data):
    X = train_data['x']
    y = train_data['y']

    # 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)

    model = svm.SVC(kernel='linear', verbose=True, probability=True)
    model.fit(X_train, y_train)
    joblib.dump(model, root_path+'/svm_model.joblib')

    score = model.score(X_train, y_train)
    score2 = model.score(X_test, y_test)

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

def train_by_naive_bayes(train_data):
    X = train_data['x']
    y = train_data['y']

    # 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)

    model = MultinomialNB()
    model.fit(X_train, y_train)
    joblib.dump(model, root_path+'/naive_bayes_model.joblib')

    score = model.score(X_train, y_train)
    score2 = model.score(X_test, y_test)

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

def train_by_random_forest(train_data):
    X = train_data['x']
    y = train_data['y']

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

    model = RandomForestClassifier(criterion='gini', max_features='sqrt')
    model.fit(X_train, y_train)
    joblib.dump(model, root_path+'/random_forest_model.joblib')

    score = model.score(X_train, y_train)
    score2 = model.score(X_test, y_test)

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


def train_by_xgb(train_data):
    X = train_data['x']
    y = train_data['y']

    # 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)

    model = XGBClassifier(use_label_encoder=False)
    model.fit(X_train, y_train)
    joblib.dump(model, root_path+'/xgb_model.joblib')

    score = model.score(X_train, y_train)

    score2 = model.score(X_test, y_test)

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

    y_pred = model.predict(X_test)

    report = classification_report(y_test, y_pred, output_dict=True)
    # show_confusion_matrix(y_test, y_pred)
    print(report)

def show_confusion_matrix(y_true, y_pred, pic_name = "confusion_matrix"):
    confusion = confusion_matrix(y_true=y_true, y_pred=y_pred)
    print(confusion)

    sns.heatmap(confusion, annot=True, cmap= 'Blues', xticklabels=['0','1','2'], yticklabels=['0','1','2'], fmt = '.20g')
    plt.xlabel('Predicted class')
    plt.ylabel('Actual Class')
    plt.title(pic_name)
    # plt.savefig('pic/' + pic_name)
    plt.show()

if __name__ == '__main__':
    train_data = get_dataset()
    train_by_LogisticRegression(train_data)
    train_by_svm(train_data)
    train_by_naive_bayes(train_data)
    train_by_random_forest(train_data)
    train_by_xgb(train_data)

4. 预测

执行下面预测代码，结果是Ecuador胜于Qatar, 英国队胜于伊朗队。

[2]
[[0.05       0.22033333 0.72966667]]
Probability of  Ecuador  winning: 0.730
Probability of Draw: 0.220
Probability of  Qatar  winning: 0.050
[2]
[[0.02342857 0.21770455 0.75886688]]
Probability of  England  winning: 0.759
Probability of Draw: 0.218
Probability of   Iran  winning: 0.023

完整代码

import joblib

worldcup_teams = ['Qatar','Germany','Denmark', 'Brazil','France','Belgium', 'Serbia',
                  'Spain','Croatia', 'Switzerland', 'England','Netherlands', 'Argentina',' Iran',
                  'Korea Republic','Saudi Arabia', 'Japan', 'Uruguay','Ecuador','Canada',
                  'Senegal', 'Poland', 'Portugal','Tunisia',  'Morocco','Cameroon','USA',
                  'Mexico','Wales','Australia','Costa Rica', 'Ghana']
root_path = "models_1"
def verify_team_name(team_name):

    for worldcup_team in worldcup_teams:
        if team_name==worldcup_team:
            return True
    return False


def predict(model_dir =root_path+'/LogisticRegression_model.joblib', team_a='France', team_b = 'Mexico'):

    if not verify_team_name(team_a):
        print(team_a, ' is not correct')
        return
    if not verify_team_name(team_b) :
        print(team_b, ' is not correct')
        return

    logreg = joblib.load(model_dir)

    input_x = [{'Home Team Name': team_a, 'Away Team Name': team_b}]

    vec = joblib.load(root_path+"/vec.joblib")
    input_x = vec.transform(input_x)

    result = logreg.predict(input_x)
    print(result)
    result1 = logreg.predict_proba(input_x)



    print(result1)
    print('Probability of ',team_a , ' winning:', '%.3f'%result1[0][2])
    print('Probability of Draw:', '%.3f' % result1[0][1])
    print('Probability of ', team_b, ' winning:', '%.3f' % result1[0][0])

if __name__ == '__main__':
    team_a = 'Ecuador'
    team_b = 'Qatar'
    predict('models/random_forest_model.joblib', team_a, team_b)
    team_a = 'England'
    team_b = ' Iran'


    predict('models/random_forest_model.joblib', team_a, team_b)