用Python分析两队主客场战绩差异
下面给你一个完整的案例,展示如何用Python分析两队的主客场战绩差异。

数据准备
假设你有比赛数据(CSV格式),字段包括:主队、客队、主队得分、客队得分。
home_team,away_team,home_score,away_score,date 湖人,勇士,110,105,2024-01-01 勇士,湖人,98,102,2024-01-15 湖人,凯尔特人,115,108,2024-01-20 ...
核心代码实现
import pandas as pd
# 1. 读取数据
df = pd.read_csv('games.csv')
df['date'] = pd.to_datetime(df['date'])
def analyze_home_away(df, team):
"""分析指定球队的主客场战绩"""
# ---- 主场战绩 ----
home_games = df[df['home_team'] == team].copy()
home_games['win'] = home_games['home_score'] > home_games['away_score']
home_win = home_games['win'].sum()
home_total = len(home_games)
home_win_rate = home_win / home_total if home_total else 0
home_avg_diff = (home_games['home_score'] - home_games['away_score']).mean()
# ---- 客场战绩 ----
away_games = df[df['away_team'] == team].copy()
away_games['win'] = away_games['away_score'] > away_games['home_score']
away_win = away_games['win'].sum()
away_total = len(away_games)
away_win_rate = away_win / away_total if away_total else 0
away_avg_diff = (away_games['away_score'] - away_games['home_score']).mean()
return {
'球队': team,
'主场场次': home_total,
'主场胜场': home_win,
'主场胜率': round(home_win_rate, 3),
'主场净胜分': round(home_avg_diff, 2),
'客场场次': away_total,
'客场胜场': away_win,
'客场胜率': round(away_win_rate, 3),
'客场净胜分': round(away_avg_diff, 2),
'主客场胜率差': round(home_win_rate - away_win_rate, 3),
}
# 2. 分析两支球队
team_a, team_b = '湖人', '勇士'
result = pd.DataFrame([
analyze_home_away(df, team_a),
analyze_home_away(df, team_b)
])
print(result.T)
可视化对比
import matplotlib.pyplot as plt
import numpy as np
plt.rcParams['font.sans-serif'] = ['SimHei'] # 中文显示
plt.rcParams['axes.unicode_minus'] = False
teams = result['球队'].tolist()
home_rates = result['主场胜率'].tolist()
away_rates = result['客场胜率'].tolist()
x = np.arange(len(teams))
width = 0.35
fig, ax = plt.subplots(figsize=(8, 5))
ax.bar(x - width/2, home_rates, width, label='主场胜率', color='#4C72B0')
ax.bar(x + width/2, away_rates, width, label='客场胜率', color='#DD8452')
ax.set_ylabel('胜率')
ax.set_title('两队主客场胜率对比')
ax.set_xticks(x)
ax.set_xticklabels(teams)
ax.legend()
ax.set_ylim(0, 1)
for i, (h, a) in enumerate(zip(home_rates, away_rates)):
ax.text(i - width/2, h + 0.02, f'{h:.1%}', ha='center')
ax.text(i + width/2, a + 0.02, f'{a:.1%}', ha='center')
plt.tight_layout()
plt.show()
两队直接交锋的主客场差异
如果想看两队互相对阵时的主客场影响:
def head_to_head(df, team_a, team_b):
"""两队直接交锋:各自主场时的表现"""
# team_a 主场 vs team_b
a_home = df[(df['home_team']==team_a) & (df['away_team']==team_b)]
a_home_win = (a_home['home_score'] > a_home['away_score']).sum()
# team_b 主场 vs team_a
b_home = df[(df['home_team']==team_b) & (df['away_team']==team_a)]
b_home_win = (b_home['home_score'] > b_home['away_score']).sum()
print(f"【{team_a}主场 vs {team_b}】共{len(a_home)}场,{team_a}胜{a_home_win}场")
print(f"【{team_b}主场 vs {team_a}】共{len(b_home)}场,{team_b}胜{b_home_win}场")
head_to_head(df, team_a, team_b)
进阶分析思路
| 分析角度 | 方法 | 代码要点 |
|---|---|---|
| 主客场胜率差 | 主场胜率 - 客场胜率 | 差值越大,越"主场龙" |
| 净胜分差 | 主场净胜分 - 客场净胜分 | 反映攻防强度差异 |
| 时间趋势 | 按赛季/月份分组 | groupby(['season','is_home']) |
| 对手强度 | 结合对手排名加权 | 需额外对手数据 |
| 主客场拆分指标 | 得分、失分、篮板等 | 需分项数据字段 |
完整趋势分析示例
# 把每场比赛转成"长表",标记主客场
home = df[df['home_team'].isin([team_a, team_b])].assign(
team=df['home_team'], is_home='主场',
win=lambda d: d['home_score'] > d['away_score'])
away = df[df['away_team'].isin([team_a, team_b])].assign(
team=df['away_team'], is_home='客场',
win=lambda d: d['away_score'] > d['home_score'])
long_df = pd.concat([home, away], ignore_index=True)
# 按球队 + 主客场汇总
summary = long_df.groupby(['team', 'is_home'])['win'].agg(['mean', 'sum', 'count'])
print(summary)
分析结论要点
查看结果时重点关注:
- 主客场胜率差 > 0.15 → 主场优势明显("主场龙客场虫")
- 净胜分差 → 判断是运气(小分差)还是实力差异
- 两队对比 → 结合直接交锋记录,判断谁的主场更难攻克
如果你有具体的数据格式或数据来源(如NBA API、中超、CBA),可以告诉我,我可以给出更针对性的抓取和分析代码。
版权声明:本站文章为原创整理,转载请注明出处。