基于决策树的英雄联盟比赛胜负预测（含完整代码）

概要

我们将以一个以英雄联盟对局胜负预测任务为基础为例

构建一个决策树模型，从数据预处理到模型训练和评估，再到参数优化（不同max_depth下的准确率，不同min_samples_split下的准确率，不同impurity_t下的准确率）和结果可视化

成果

通过网格搜索找到了最优的决策树参数配置，并在测试集上取得了较高的准确率。通过绘制不同参数组合下的准确率图，直观地展示了参数对模型性能的影响

完整代码

from collections import Counter
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
import seaborn as sns
import matplotlib.pyplot as plt

# 固定随机种子
RANDOM_SEED = 2020

# 数据路径
csv_data = r'C:\Users\16397\Desktop\tree\tree\data/high_diamond_ranked_10min.csv'
data_df = pd.read_csv(csv_data, sep=',')  # 读入csv文件为pandas的DataFrame
data_df = data_df.drop(columns='gameId')  # 舍去对局标号列

print(data_df.iloc[0])  # 输出第一行数据
data_df.describe()  # 每列特征的简单统计信息

# 需要舍去的特征列
drop_features = ['blueGoldDiff', 'redGoldDiff',
                 'blueExperienceDiff', 'redExperienceDiff',
                 'blueCSPerMin', 'redCSPerMin',
                 'blueGoldPerMin', 'redGoldPerMin']
df = data_df.drop(columns=drop_features)  # 舍去特征列

# 取出要作差值的特征名字（除去red前缀）
info_names = [c[3:] for c in df.columns if c.startswith('red')]
for info in info_names:  # 对于每个特征名字
    df['br' + info] = df['blue' + info] - df['red' + info]  # 构造一个新的特征，由蓝色特征减去红色特征，前缀为br

# 原有的FirstBlood可删除
df = df.drop(columns=['blueFirstBlood', 'redFirstBlood'])

# 离散化每一列特征
discrete_df = df.copy()  # 先复制一份数据
for c in df.columns[1:]:  # 遍历每一列特征，跳过标签列
    unique_values = df[c].nunique()
    if unique_values <= 10:  # 如果特征取值少于等于10个，直接跳过
        continue
    # 使用等区间离散化
    discrete_df[c] = pd.cut(df[c], bins=10, labels=False)

# 准备数据
all_y = discrete_df['blueWins'].values  # 所有标签数据
feature_names = discrete_df.columns[1:]  # 所有特征的名称
all_x = discrete_df[feature_names].values  # 所有原始特征值，pandas的DataFrame.values取出为numpy的array矩阵

# 划分训练集和测试集
x_train, x_test, y_train, y_test = train_test_split(all_x, all_y, test_size=0.2, random_state=RANDOM_SEED)
all_y.shape, all_x.shape, x_train.shape, x_test.shape, y_train.shape, y_test.shape  # 输出数据行列信息


# 定义决策树类
class DecisionTree(object):
    def __init__(self, classes, features, max_depth=10, min_samples_split=10, impurity_t='entropy'):
        self.classes = classes
        self.features = features
        self.max_depth = max_depth
        self.min_samples_split = min_samples_split
        self.impurity_t = impurity_t
        self.root = None  # 定义根节点，未训练时为空

    def impurity(self, labels):
        if self.impurity_t == 'entropy':
            counter = Counter(labels)
            probabilities = [count / len(labels) for count in counter.values()]
            entropy = -sum(p * np.log2(p) for p in probabilities)
            return entropy
        elif self.impurity_t == 'gini':
            counter = Counter(labels)
            probabilities = [count / len(labels) for count in counter.values()]
            gini = 1 - sum(p ** 2 for p in probabilities)
            return gini
        else:
            raise ValueError("Unsupported impurity type")

    def gain(self, feature, labels):
        total_impurity = self.impurity(labels)
        values = np.unique(feature)
        weighted_impurity = 0
        for value in values:
            subset_labels = labels[feature == value]
            weight =