python案例认为角球数量大概会是多少？

wen python案例 2026-09-05 214

本文目录导读：

基于历史数据的统计分析
蒙特卡洛模拟预测
机器学习简单预测模型
基于比赛状态的动态预测
使用建议

我来为你编写几个有趣的Python案例来分析预测角球数量！

基于历史数据的统计分析

import random
import statistics
from collections import Counter
class CornerKickPredictor:
    def __init__(self):
        # 历史比赛数据模拟
        self.match_data = {
            '英超': [8, 12, 6, 10, 9, 11, 7, 13, 8, 10, 5, 12, 9, 8, 10],
            '西甲': [9, 11, 7, 8, 10, 6, 12, 9, 8, 11, 7, 10, 9, 12, 8],
            '欧冠': [10, 8, 12, 9, 7, 11, 13, 8, 9, 10, 6, 12, 8, 9, 11]
        }
    def basic_statistics(self, league):
        """基础统计分析"""
        if league not in self.match_data:
            return "不支持的联赛"
        data = self.match_data[league]
        return {
            '平均角球数': round(statistics.mean(data), 2),
            '中位数': statistics.median(data),
            '标准差': round(statistics.stdev(data), 2),
            '最少': min(data),
            '最多': max(data),
            '常见数量': Counter(data).most_common(3)
        }
    def probability_distribution(self, league):
        """计算各角球数量的概率"""
        if league not in self.match_data:
            return {}
        data = self.match_data[league]
        total = len(data)
        distribution = {}
        for corners in range(0, 16):
            count = data.count(corners)
            distribution[corners] = round(count / total, 3)
        return distribution
# 使用示例
predictor = CornerKickPredictor()
stats = predictor.basic_statistics('英超')
print("英超角球数据分析：")
for key, value in stats.items():
    print(f"  {key}: {value}")

蒙特卡洛模拟预测

import random
import matplotlib.pyplot as plt
class MonteCarloCornerPredictor:
    def __init__(self, home_strength=50, away_strength=50):
        self.home_attack = home_strength
        self.away_defense = away_strength
    def simulate_single_match(self):
        """模拟单场比赛角球"""
        # 基础角球范围
        base_corners = random.uniform(8, 12)
        # 球队实力影响
        home_advantage = random.uniform(0.9, 1.1)
        strength_effect = (self.home_attack - self.away_defense) / 100
        # 比赛风格影响（进攻型球队角球多）
        style_factor = random.choice([0.8, 0.9, 1.0, 1.0, 1.1, 1.2])
        # 随机因素
        random_factor = random.uniform(0.7, 1.5)
        total_corners = base_corners * home_advantage * (1 + strength_effect) * style_factor * random_factor
        return round(total_corners, 0)
    def monte_carlo_predict(self, simulations=10000):
        """蒙特卡洛模拟多次比赛"""
        results = []
        for _ in range(simulations):
            corners = self.simulate_single_match()
            results.append(corners)
        return {
            '平均预测': round(sum(results) / len(results), 2),
            '最可能范围': f"{sorted(results)[len(results)//4]} - {sorted(results)[3*len(results)//4]}",
            '超过10个概率': round(sum(1 for r in results if r >= 10) / len(results) * 100, 2)
        }
# 使用示例
simulator = MonteCarloCornerPredictor(home_strength=65, away_strength=55)
prediction = simulator.monte_carlo_predict(10000)
print("\n蒙特卡洛模拟预测结果：")
for key, value in prediction.items():
    print(f"  {key}: {value}")

机器学习简单预测模型

import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
class CornerRegressionPredictor:
    def __init__(self):
        # 特征：控球率%, 射门次数, 射正次数, 威胁进攻次数
        self.X = np.array([
            [55, 12, 5, 30],
            [48, 10, 3, 25],
            [60, 15, 7, 40],
            [45, 8, 2, 18],
            [52, 11, 4, 28],
            [63, 14, 6, 35],
            [40, 6, 1, 12],
            [58, 13, 5, 32],
            [50, 9, 3, 22],
            [62, 16, 8, 38]
        ])
        # 实际角球数（目标变量）
        self.y = np.array([9, 7, 12, 5, 8, 11, 4, 10, 7, 13])
        # 训练模型
        self.model = LinearRegression()
        self.X_train, self.X_test, self.y_train, self.y_test = train_test_split(
            self.X, self.y, test_size=0.2, random_state=42
        )
        self.model.fit(self.X_train, self.y_train)
    def predict(self, possession, shots, on_target, dangerous_attacks):
        """预测角球数量"""
        features = np.array([[possession, shots, on_target, dangerous_attacks]])
        prediction = self.model.predict(features)
        return round(prediction[0], 1)
    def model_accuracy(self):
        """评估模型精度"""
        score = self.model.score(self.X_test, self.y_test)
        return score
# 使用示例
predictor_ml = CornerRegressionPredictor()
features = [58, 14, 6, 35]  # 控球率58%, 14次射门, 6次射正, 35次威胁进攻
prediction = predictor_ml.predict(*features)
print(f"\n机器学习预测结果：")
print(f"  预测角球数: {prediction}")

基于比赛状态的动态预测

class DynamicCornerPredictor:
    def predict_during_match(self, minute, current_corners, game_state):
        """
        根据比赛进程动态预测
        minute: 比赛分钟（1-90）
        current_corners: 当前角球数
        game_state: 'neutral', 'home_leading', 'away_leading', 'draw'
        """
        # 计算剩余时间中的角球基础概率
        remaining_time = 90 - minute
        time_factor = remaining_time / 90
        # 根据比赛状态调整
        state_multipliers = {
            'neutral': 1.0,
            'home_leading': 0.8,  # 领先方可能控球多但角球可能少
            'away_leading': 1.2,  # 落后方积极进攻
            'draw': 1.0
        }
        # 基础角球速率（每分钟）
        base_rate = 0.15
        if minute < 15:  # 开场阶段角球较少
            base_rate *= 0.8
        elif minute > 80:  # 最后阶段进攻激烈
            base_rate *= 1.3
        # 预测剩余时间角球数
        expected_remaining = (remaining_time * base_rate * 
                            state_multipliers[game_state])
        # 动态预测
        final_prediction = current_corners + expected_remaining
        # 比赛状态下限（至少追加2个角球在领先情况下）
        if game_state in ['home_leading', 'away_leading']:
            final_prediction = max(final_prediction, current_corners + 2)
        return {
            '半场预测': round(current_corners + expected_remaining * 0.5, 1),
            '全场预测': round(final_prediction, 1),
            '置信度': round(min(90, minute + expected_remaining * 10) / 100, 2)
        }
# 动态预测示例
dynamic_predictor = DynamicCornerPredictor()
mid_match_prediction = dynamic_predictor.predict_during_match(
    minute=60, 
    current_corners=7, 
    game_state='draw'
)
print(f"\n比赛进行到60分钟，当前角球数7个：")
print(f"  半场预测: {mid_match_prediction['半场预测']} 个")
print(f"  全场预测: {mid_match_prediction['全场预测']} 个")