import numpy as np
from sklearn.model_selection import train_test_split, cross_val_score
from sklearn.ensemble import RandomForestClassifier
from sklearn.preprocessing import PolynomialFeatures, StandardScaler

id = "202210423104"
name = "张钦诚"

def load_data(filepath):
    data = []
    with open(filepath, 'r') as file:
        for line in file:
            line_data = line.strip().split()
            if line_data:
                try:
                    data.append([float(x) if x != '?' else np.nan for x in line_data])
                except ValueError as e:
                    print(f"Error processing line: {line}. Error: {e}")
    data = np.array(data)
    data = np.nan_to_num(data, nan=np.nanmean(data, axis=0))
    return data

def preprocess_data(X):
    # 标准化特征
    scaler = StandardScaler()
    X_standardized = scaler.fit_transform(X)

    # 增加多项式特征
    poly = PolynomialFeatures(degree=2, include_bias=False)
    X_poly = poly.fit_transform(X_standardized)
    return X_poly

def train_random_forest(X, y):
    model = RandomForestClassifier(n_estimators=113, max_depth=10, random_state=42)
    model.fit(X, y)
    return model

def predict(model, X):
    return model.predict(X)

if __name__ == "__main__":
    data = load_data("./data/horse-colic.data")
    X = data[:, :-1]
    y = data[:, -1]

    # 数据集划分
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

    # 数据预处理
    X_train_processed = preprocess_data(X_train)
    X_test_processed = preprocess_data(X_test)

    # 训练模型
    model = train_random_forest(X_train_processed, y_train)

    # 交叉验证
    cv_scores = cross_val_score(model, X_train_processed, y_train, cv=5)
    print(f"交叉验证准确率: {np.mean(cv_scores) * 100:.2f}%")

    # 预测
    y_pred = predict(model, X_test_processed)

    # 计算正确率
    accuracy = np.mean(y_pred == y_test)
    print(f"测试出的正确率: {accuracy * 100:.2f}%")