这个python案例是否考虑了密集赛程影响？

wen python案例 2026-09-09 195

我注意到您问的是“这个python案例”，但您没有提供具体的案例内容，我可以根据您的问题，为您提供一个考虑密集赛程影响的Python分析框架示例。

以下是一个考虑密集赛程影响的球队表现分析示例,它通常出现在体育数据分析中：

import pandas as pd
import numpy as np
from datetime import datetime, timedelta
class FootballScheduleAnalysis:
    """
    足球赛程密集程度分析器
    考虑了比赛间隔天数对球队表现的影响
    """
    def __init__(self, matches_df):
        """
        :param matches_df: DataFrame包含以下列:
            'date' - 比赛日期
            'team' - 球队名称
            'opponent' - 对手
            'result' - 结果 (W/L/D)
            'goals_for' - 进球数
            'goals_against' - 失球数
            'is_home' - 是否主场 (True/False)
        """
        self.matches = matches_df.copy()
        self.matches['date'] = pd.to_datetime(self.matches['date'])
        self.matches = self.matches.sort_values('date')
    def calculate_days_since_last_match(self, team):
        """
        计算每场比赛距离上一场的间隔天数
        """
        team_matches = self.matches[self.matches['team'] == team].copy()
        team_matches['days_rest'] = team_matches['date'].diff().dt.days
        # 赛季首场比赛设为14天（视为充足休息）
        team_matches['days_rest'] = team_matches['days_rest'].fillna(14)
        return team_matches
    def classify_schedule_density(self, days_rest):
        """
        将赛程密度分类:
        0-3天: 密集赛程 (背靠背或超紧密)
        4-6天: 中等密集
        7+天: 充足休息
        """
        if days_rest <= 3:
            return 'dense'  # 密集
        elif 4 <= days_rest <= 6:
            return 'medium'  # 中等
        else:
            return 'adequate'  # 充足
    def analyze_density_impact(self):
        """
        分析赛程密度对球队表现的影响
        """
        results = []
        for team in self.matches['team'].unique():
            team_data = self.calculate_days_since_last_match(team)
            team_data['density'] = team_data['days_rest'].apply(self.classify_schedule_density)
            # 计算不同密度下的胜率
            for density in ['dense', 'medium', 'adequate']:
                subset = team_data[team_data['density'] == density]
                if len(subset) > 0:
                    win_rate = (subset['result'] == 'W').mean()
                    avg_goals_for = subset['goals_for'].mean()
                    avg_goals_against = subset['goals_against'].mean()
                    results.append({
                        'team': team,
                        'density': density,
                        'matches': len(subset),
                        'win_rate': win_rate,
                        'avg_goals_for': avg_goals_for,
                        'avg_goals_against': avg_goals_against
                    })
        return pd.DataFrame(results)
    def team_density_comparison(self, team1, team2):
        """
        比较两支球队在密集赛程下的表现差异
        """
        analysis = self.analyze_density_impact()
        t1 = analysis[analysis['team'] == team1]
        t2 = analysis[analysis['team'] == team2]
        print(f"\n=== {team1} vs {team2} 密集赛程对比 ===")
        # 对比密集赛程下的表现
        dense_comparison = pd.merge(
            t1[t1['density'] == 'dense'],
            t2[t2['density'] == 'dense'],
            on='density',
            suffixes=(f'_{team1}', f'_{team2}')
        )
        print("\n密集赛程(<=3天间隔)下表现对比:")
        if not dense_comparison.empty:
            dense_row = dense_comparison.iloc[0]
            print(f"  {team1}: 胜率{dense_row[f'win_rate_{team1}']:.1%}, 场均进{dense_row[f'avg_goals_for_{team1}']:.2f}球")
            print(f"  {team2}: 胜率{dense_row[f'win_rate_{team2}']:.1%}, 场均进{dense_row[f'avg_goals_for_{team2}']:.2f}球")
        # 整体胜率对比（不考虑密度）
        all_t1 = self.matches[self.matches['team'] == team1]
        all_t2 = self.matches[self.matches['team'] == team2]
        print(f"\n整体胜率:")
        print(f"  {team1}: {(all_t1['result'] == 'W').mean():.1%}")
        print(f"  {team2}: {(all_t2['result'] == 'W').mean():.1%}")
    def fatigue_index_calculation(self):
        """
        计算疲劳指数（考虑近30天比赛场次加权）
        """
        reference_date = self.matches['date'].max()
        days_window = 30
        fatigue_data = []
        for team in self.matches['team'].unique():
            # 获取团队所有比赛
            team_matches = self.matches[self.matches['team'] == team].copy()
            for _, match in team_matches.iterrows():
                # 计算该场比赛前30天内的比赛场次
                window_start = match['date'] - timedelta(days=days_window)
                prior_matches = team_matches[
                    (team_matches['date'] >= window_start) & 
                    (team_matches['date'] < match['date'])
                ]
                # 疲劳指数 = 最近30天比赛场次 / 该队平均比赛间隔
                expected_days_between = 7  # 标准联赛通常7天一场
                fatigue_score = len(prior_matches) * expected_days_between / days_window
                # 加上距离上一场比赛的天数影响
                days_since_last = match['days_rest'] if 'days_rest' in match else 7
                rest_factor = min(days_since_last / 7, 1.0)
                adjusted_fatigue = fatigue_score * (1 - rest_factor * 0.3)
                fatigue_data.append({
                    'date': match['date'],
                    'team': team,
                    'fatigue_index': adjusted_fatigue,
                    'result': match['result'],
                    'is_home': match['is_home']
                })
        fatigue_df = pd.DataFrame(fatigue_data)
        return fatigue_df
    def density_correlation_analysis(self):
        """
        相关性分析：赛程密度与比赛结果的关系
        """
        # 准备数据集
        all_with_density = []
        for team in self.matches['team'].unique():
            team_data = self.calculate_days_since_last_match(team)
            team_data['density'] = team_data['days_rest'].apply(self.classify_schedule_density)
            # 将分类变量转换为哑变量
            density_dummies = pd.get_dummies(team_data['density'], prefix='density')
            team_data = pd.concat([team_data, density_dummies], axis=1)
            all_with_density.append(team_data)
        combined = pd.concat(all_with_density)
        # 简单相关性分析
        numeric_cols = ['density_dense', 'density_medium', 'days_rest']
        result_col = 'result'
        # 将结果转换为得分（W=3, D=1, L=0）
        combined['points'] = combined['result'].map({'W': 3, 'D': 1, 'L': 0})
        # 计算相关系数矩阵
        correlation_matrix = combined[numeric_cols + ['points']].corr()
        print("=== 赛程密度与得分相关性分析 ===")
        print(correlation_matrix)
        # 额外的回归分析（简化版）
        from scipy import stats
        # 检查密集赛程是否显著影响得分
        dense_points = combined[combined['density_dense'] == 1]['points']
        normal_points = combined[combined['density_dense'] == 0]['points']
        t_stat, p_value = stats.ttest_ind(dense_points, normal_points)
        print(f"\n独立t检验（密集 vs 非密集）:")
        print(f"  t统计量: {t_stat:.4f}")
        print(f"  p值: {p_value:.4f}")
        print(f"  显著水平: {'显著影响' if p_value < 0.05 else '无明显统计学差异'}")

使用时的主要功能：