本文目录导读：
我来提供一个完整的Python案例,用于统计和对比不同球员的赛季累计数据。
完整案例：NBA/篮球赛季数据统计对比
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from datetime import datetime
# 设置中文显示
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
class SeasonStatsAnalyzer:
"""赛季数据统计分析器"""
def __init__(self):
self.data = None
self.players = []
def generate_sample_data(self, num_players=5, games_per_season=20):
"""生成模拟数据"""
np.random.seed(42)
players_demo = [
('张三', 1995, '后卫'),
('李四', 1998, '前锋'),
('王五', 1996, '中锋'),
('赵六', 1999, '后卫'),
('钱七', 1997, '前锋')
]
seasons = ['2022-2023', '2023-2024', '2024-2025']
data_rows = []
for player_name, birth_year, position in players_demo[:num_players]:
# 基础能力参数
base_scoring = np.random.randint(15, 30)
base_rebound = np.random.randint(3, 12)
base_assist = np.random.randint(2, 8)
for season in seasons:
games = games_per_season
# 生成每场比赛数据
for game in range(games):
# 数据随时间趋势变化
trend_factor = 1 + (game / games) * np.random.normal(0.5, 0.2)
points = max(0, round(base_scoring * trend_factor + np.random.normal(3, 5)))
rebounds = max(0, round(base_rebound * trend_factor + np.random.normal(1, 2)))
assists = max(0, round(base_assist * trend_factor + np.random.normal(1, 2)))
data_rows.append({
'player': player_name,
'birth_year': birth_year,
'position': position,
'season': season,
'game_num': game + 1,
'points': points,
'rebounds': rebounds,
'assists': assists,
'turnovers': np.random.randint(0, 5),
'minutes': np.random.randint(20, 40)
})
self.data = pd.DataFrame(data_rows)
return self.data
def load_data(self, file_path):
"""从文件加载数据"""
try:
self.data = pd.read_csv(file_path)
return True
except:
print("数据加载失败")
return False
def calculate_season_totals(self, player_names=None):
"""计算赛季累计数据"""
if self.data is None:
return None
df = self.data.copy()
# 筛选球员
if player_names:
df = df[df['player'].isin(player_names)]
# 计算赛季累计
season_totals = df.groupby(['player', 'season']).agg({
'points': 'sum',
'rebounds': 'sum',
'assists': 'sum',
'turnovers': 'sum',
'minutes': 'sum',
'game_num': 'max' # 比赛场次
}).rename(columns={
'points': '总得分',
'rebounds': '总篮板',
'assists': '总助攻',
'turnovers': '总失误',
'minutes': '总时间',
'game_num': '比赛场次'
}).reset_index()
# 计算场均数据
season_totals['场均得分'] = season_totals['总得分'] / season_totals['比赛场次']
season_totals['场均篮板'] = season_totals['总篮板'] / season_totals['比赛场次']
season_totals['场均助攻'] = season_totals['总助攻'] / season_totals['比赛场次']
return season_totals
def compare_players(self, player_selection=None, stat='场均得分'):
"""对比球员数据"""
totals = self.calculate_season_totals(player_selection)
if totals is None:
print("没有数据可供分析")
return None
# 透视表格式
pivot_df = totals.pivot(index='season', columns='player', values=stat)
return pivot_df
def plot_comparison(self, stat='场均得分'):
"""绘制数据对比图"""
pivot_df = self.compare_players(stat=stat)
if pivot_df is None or pivot_df.empty:
print("没有数据可以绘图")
return
fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(12, 10))
# 赛季趋势比较
pivot_df.plot(kind='line', marker='o', ax=ax1, linewidth=2)
ax1.set_title(f'球员{stat}赛季趋势对比')
ax1.set_xlabel('赛季')
ax1.set_ylabel(stat)
ax1.legend(title='球员')
ax1.grid(True, alpha=0.3)
# 赛季总览对比
totals = self.calculate_season_totals()
latest_season = totals['season'].max()
latest_data = totals[totals['season'] == latest_season]
# 柱状图
x = np.arange(len(latest_data['player']))
width = 0.15
points = latest_data['总得分']
rebounds = latest_data['总篮板'] * 2 # 缩放以便可视化比较
assists = latest_data['总助攻'] * 3
bars1 = ax2.bar(x - width, points, width, label='总得分', color='crimson')
bars2 = ax2.bar(x, rebounds, width, label='总篮板(×2)', color='navy')
bars3 = ax2.bar(x + width, assists, width, label='总助攻(×3)', color='green')
ax2.set_title(f'{latest_season}赛季球员累计数据对比')
ax2.set_xlabel('球员')
ax2.set_ylabel('累计数值')
ax2.set_xticks(x)
ax2.set_xticklabels(latest_data['player'])
ax2.legend()
ax2.grid(True, alpha=0.3)
# 添加数据标签
for bars in [bars1, bars2, bars3]:
for bar in bars:
height = bar.get_height()
ax2.text(bar.get_x() + bar.get_width()/2., height,
f'{height:.0f}',
ha='center', va='bottom', fontsize=8)
plt.tight_layout()
plt.show()
def comprehensive_report(self, player_names=None):
"""生成综合报告"""
totals = self.calculate_season_totals(player_names)
if totals is None:
return None
report = {
'总得分榜': totals.nlargest(5, '总得分')[['player', 'season', '总得分']],
'场均得分榜': totals.nlargest(5, '场均得分')[['player', 'season', '场均得分']],
'总篮板榜': totals.nlargest(5, '总篮板')[['player', 'season', '总篮板']],
'总助攻榜': totals.nlargest(5, '总助攻')[['player', 'season', '总助攻']]
}
return report
def performance_trend_analysis(self, player_names=None):
"""分析球员表现趋势"""
if self.data is None:
return None
df = self.data.copy()
if player_names:
df = df[df['player'].isin(player_names)]
# 计算滚动平均
df['滚动均分'] = df.groupby(['player', 'season'])['points'].transform(
lambda x: x.expanding().mean()
)
# 计算进步/退步幅度
comparison = df.groupby(['player', 'season']).agg({
'points': 'sum',
'game_num': 'max'
}).reset_index()
comparison['场均得分'] = comparison['points'] / comparison['game_num']
# 赛季间对比
pivot = comparison.pivot(index='player', columns='season', values='场均得分')
# 计算变化
change_cols = []
seasons = pivot.columns.tolist()
for i in range(1, len(seasons)):
col_name = f'{seasons[i-1]}→{seasons[i]}变化'
pivot[col_name] = pivot[seasons[i]] - pivot[seasons[i-1]]
change_cols.append(col_name)
return pivot[change_cols]
# 主程序
def main():
print("=== 赛季数据统计对比系统 ===")
# 创建分析器
analyzer = SeasonStatsAnalyzer()
# 生成示例数据
print("正在生成模拟数据...")
analyzer.generate_sample_data(num_players=5, games_per_season=20)
# 显示数据概要
print("\n数据概要:")
print(f"总记录数: {len(analyzer.data)}")
print(f"球员列表: {analyzer.data['player'].unique().tolist()}")
print(f"赛季列表: {analyzer.data['season'].unique().tolist()}")
# 计算赛季累计数据
print("\n=== 赛季累计数据 ===")
season_totals = analyzer.calculate_season_totals()
print(season_totals.to_string(index=False))
# 绘制对比图
print("\n正在生成对比图表...")
analyzer.plot_comparison('场均得分')
# 显示排行报告
print("\n=== 综合排名 ===")
report = analyzer.comprehensive_report()
for title, df in report.items():
print(f"\n{title}:")
print(df.to_string(index=False))
# 趋势分析
print("\n=== 赛季进步/退步分析 ===")
trend_analysis = analyzer.performance_trend_analysis()
if trend_analysis is not None:
print(trend_analysis.to_string())
# 导出数据
print("\n正在导出数据...")
season_totals.to_csv('season_totals.csv', index=False, encoding='utf-8-sig')
print("数据已导出至 season_totals.csv")
if __name__ == "__main__":
main()
核心功能亮点
数据模拟与加载
- 自动生成多赛季、多球员的比赛数据
- 支持从CSV文件加载真实数据
累计统计功能
- 计算总得分、总篮板、总助攻等累计数据
- 自动计算场均数据
- 支持多赛季对比
可视化对比
- 赛季趋势折线图
- 球员累计数据柱状图
- 多维度排名视图
高级分析
- 球员间数据交互对比
- 赛季进步/退步分析
- 综合排名报告
使用场景
- 球员评估：评估不同球员的赛季表现
- 选秀分析：对比新秀赛季数据趋势
- 战术调整：分析不同位置的攻防数据
- 商业决策：评估球员的持续表现能力
扩展建议
# 1. 增加位置权重对比
def position_weighted_compare(self):
"""按位置权重对比"""
weights = {'后卫': 1.0, '前锋': 1.2, '中锋': 1.4}
self.data['weighted_points'] = self.data.apply(
lambda x: x['points'] * weights.get(x['position'], 1), axis=1
)
# 2. 增加效率值分析
def calculate_efficiency(self):
"""计算球员效率值"""
self.data['efficiency'] = (
self.data['points'] +
self.data['rebounds'] +
self.data['assists'] * 1.5 -
self.data['turnovers']
)
这个案例提供了完整的赛季数据统计对比解决方案,既适合学习也适合实际应用，你可以根据具体需求调整数据结构和分析维度。
