id = "202210423201"
name = "陈瑞琪祥"

import numpy as np
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, accuracy_score
from sklearn.preprocessing import StandardScaler

# 数据加载函数
def load_data(filepath):
    data = []
    labels = []
    
    with open(filepath, 'r') as file:
        for line in file:
            fields = line.strip().split()
            fields = [0 if f == '?' else float(f) for f in fields]
            
            label = int(fields[-6])
            features = np.array(fields[:-6] + fields[-5:], dtype=float)
            
            if label in [1, 2, 3]:
                label = {1: 0, 2: 1, 3: 2}[label]
                data.append(features)
                labels.append(label)
            else:
                print(f"无效标签，跳过此样本：{label}")
    
    return np.array(data), np.array(labels)

def train_svm(X, y):
    """
    支持向量机训练函数。
    """
    scaler = StandardScaler()
    X_scaled = scaler.fit_transform(X)
    
    model = SVC(kernel='rbf', C=1.0, gamma='scale', random_state=42)
    model.fit(X_scaled, y)
    return model, scaler

def predict_svm(model, scaler, X):
    X_scaled = scaler.transform(X)
    return model.predict(X_scaled)

if __name__ == "__main__":
    # 加载数据
    X, y = load_data("./data/horse-colic.data")
    
    # 分割数据集
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
    
    # 训练SVM模型
    svm_model, scaler = train_svm(X_train, y_train)
    
    # 预测测试集
    y_pred = predict_svm(svm_model, scaler, X_test)
    
    # 评估模型
    accuracy = accuracy_score(y_test, y_pred)
    print(f"测试集准确率: {accuracy * 100:.2f}%")
    
    # 测试单个数据
    test_sample = X_test[11]  # 选择第12个样本（从0开始计数）
    y_pred_single = predict_svm(svm_model, scaler, test_sample.reshape(1, -1))
    print(f"\n单个样本预测结果: {y_pred_single[0]}, 实际结果: {y_test[11]}")