From 707e868d06c2a0d4ad03390a41a28a8039f5c777 Mon Sep 17 00:00:00 2001
From: p4azsfjh3 <1172251193@qq.com>
Date: Fri, 25 Nov 2022 13:29:13 +0800
Subject: [PATCH] ADD file via upload

---
 nba.py | 170 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 170 insertions(+)
 create mode 100644 nba.py

diff --git a/nba.py b/nba.py
new file mode 100644
index 0000000..a1476e0
--- /dev/null
+++ b/nba.py
@@ -0,0 +1,170 @@
+import pandas as pd
+import math
+import csv
+import random
+import numpy as np
+from sklearn import linear_model
+from sklearn.model_selection import cross_val_score
+# 当每支队伍没有elo等级分时，赋予其基础elo等级分
+base_elo = 1600
+team_elos = {}
+team_stats = {}
+X = []
+y = []
+# 存放数据的目录
+folder = r'C:\Users\lenovo\Desktop\data'
+
+# 根据每支队伍的Miscellaneous Opponent，Team统计数据csv文件进行初始化
+def initialize_data(Mstat, Ostat, Tstat):
+    new_Mstat = Mstat.drop(['Rk', 'Arena'], axis=1)
+    new_Ostat = Ostat.drop(['Rk', 'G', 'MP'], axis=1)
+    new_Tstat = Tstat.drop(['Rk', 'G', 'MP'], axis=1)
+
+    team_stats1 = pd.merge(new_Mstat, new_Ostat, how='left', on='Team')
+    team_stats1 = pd.merge(team_stats1, new_Tstat, how='left', on='Team')
+    return team_stats1.set_index('Team', inplace=False, drop=True)
+
+def get_elo(team):
+    try:
+        return team_elos[team]
+    except:
+        # 当最初没有elo时，给每个队伍最初赋base_elo
+        team_elos[team] = base_elo
+        return team_elos[team]
+
+    # 计算每个球队的elo值
+def calc_elo(win_team, lose_team):
+        winner_rank = get_elo(win_team)
+        loser_rank = get_elo(lose_team)
+
+        rank_diff = winner_rank - loser_rank
+        exp = (rank_diff * -1) / 400
+        odds = 1 / (1 + math.pow(10, exp))
+        # 根据rank级别修改K值
+        if winner_rank < 2100:
+            k = 32
+        elif winner_rank >= 2100 and winner_rank < 2400:
+            k = 24
+        else:
+            k = 16
+
+        # 更新 rank 数值
+        new_winner_rank = round(winner_rank + (k * (1 - odds)))
+        new_loser_rank = round(loser_rank + (k * (0 - odds)))
+        return new_winner_rank, new_loser_rank
+
+def  build_dataSet(all_data):
+    print("Building data set..")
+    X = []
+    skip = 0
+    for index, row in all_data.iterrows():
+
+        Wteam = row['WTeam']
+        Lteam = row['LTeam']
+
+        #获取最初的elo或是每个队伍最初的elo值
+        team1_elo = get_elo(Wteam)
+        team2_elo = get_elo(Lteam)
+
+        # 给主场比赛的队伍加上100的elo值
+        if row['WLoc'] == 'H':
+            team1_elo += 100
+        else:
+            team2_elo += 100
+
+        # 把elo当为评价每个队伍的第一个特征值
+        team1_features = [team1_elo]
+        team2_features = [team2_elo]
+
+        # 添加我们从basketball reference.com获得的每个队伍的统计信息
+        for key, value in team_stats.loc[Wteam].iteritems():
+            team1_features.append(value)
+        for key, value in team_stats.loc[Lteam].iteritems():
+            team2_features.append(value)
+
+        # 将两支队伍的特征值随机的分配在每场比赛数据的左右两侧
+        # 并将对应的0/1赋给y值
+        if random.random() > 0.5:
+            X.append(team1_features + team2_features)
+            y.append(0)
+        else:
+            X.append(team2_features + team1_features)
+            y.append(1)
+
+        if skip == 0:
+            print('X',X)
+            skip = 1
+
+        # 根据这场比赛的数据更新队伍的elo值
+        new_winner_rank, new_loser_rank = calc_elo(Wteam, Lteam)
+        team_elos[Wteam] = new_winner_rank
+        team_elos[Lteam] = new_loser_rank
+
+    return np.nan_to_num(X), y
+
+if __name__ == '__main__':
+
+    Mstat = pd.read_csv(folder + '/15-16Miscellaneous_Stat.csv')
+    Ostat = pd.read_csv(folder + '/15-16Opponent_Per_Game_Stat.csv')
+    Tstat = pd.read_csv(folder + '/15-16Team_Per_Game_Stat.csv')
+
+    team_stats = initialize_data(Mstat, Ostat, Tstat)
+
+    result_data = pd.read_csv(folder + '/2015-2016_result.csv')
+    X, y = build_dataSet(result_data)
+
+    # 训练网络模型
+    print("Fitting on %d game samples.." % len(X))
+
+    model = linear_model.LogisticRegression()
+    model.fit(X, y)
+
+    # 利用10折交叉验证计算训练正确率
+    print("Doing cross-validation..")
+    print(cross_val_score(model, X, y, cv = 10, scoring='accuracy', n_jobs=-1).mean())
+
+
+    def predict_winner(team_1, team_2, model):
+        features = []
+
+        # team 1，客场队伍
+        features.append(get_elo(team_1))
+        for key, value in team_stats.loc[team_1].iteritems():
+            features.append(value)
+
+        # team 2，主场队伍
+        features.append(get_elo(team_2) + 100)
+        for key, value in team_stats.loc[team_2].iteritems():
+            features.append(value)
+
+        features = np.nan_to_num(features)
+        return model.predict_proba([features])
+
+
+    # 利用训练好的model在16-17年的比赛中进行预测
+
+    print('Predicting on new schedule..')
+    schedule1617 = pd.read_csv(folder + '/16-17Schedule.csv')
+    result = []
+    for index, row in schedule1617.iterrows():
+        team1 = row['Vteam']
+        team2 = row['Hteam']
+        pred = predict_winner(team1, team2, model)
+        prob = pred[0][0]
+        if prob > 0.5:
+            winner = team1
+            loser = team2
+            result.append([winner, loser, prob])
+        else:
+            winner = team2
+            loser = team1
+            result.append([winner, loser, 1 - prob])
+
+    with open('16-17Result.csv', 'w') as f:
+        writer = csv.writer(f)
+        writer.writerow(['win', 'lose', 'probability'])
+        writer.writerows(result)
+        print('done.')
+
+        pd.read_csv('16-17Result.csv', header=0)
+pd.read_csv('16-17Result.csv',header=0)