# function.py
import numpy as np
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score, roc_auc_score
from sklearn.ensemble import RandomForestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import VotingClassifier
"""
实验说明:
- 自行编写实现数据加载与预测病马死亡的对率回归算法。

注意事项:
- 在 function.py 中实现对率回归算法。
- 可以自行导入其他库，需要在 requirements.txt 添加依赖，若未在 requirements.txt 中添加使用到的依赖，则无法自动评测，成绩为零。
- 自动评测脚本仅会加载 train_logreg、predict_logreg 和 load_data 函数，请勿修改函数名。

测评环境:
- CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz
- OS: Ubuntu 22.04.4 LTS
- Python: 3.10.12
- numpy: 2.1.1
"""


"""
请在这里填写学号和姓名，不填写即成绩无效。
"""
id = "202210423221"
name = "廖子豪"


# 这里写自己的代码实现
def load_data(filepath):
    """
    从文件中加载数据。

    Args:
    - filepath (str): 数据文件路径。

    Returns:
    - np.array: 特征数据。
    - np.array: 标签数据。
    """
    file = open(filepath)
    fr = file.readlines()
    data_list = []
    y = []
    for data in fr:
        data = data.strip()
        data = data.split(' ')
        data_25 = data[24]
        y.append(data[22])
        del data[-1]
        del data[26]
        del data[25]
        del data[24]
        del data[22]
        del data[2]
        for i in data_25:
            data.append(i)
        data = [0 if data_elem == '?' else float(data_elem) for data_elem in data]
        data_list.append(data)
    data_number = len(y)
    y_train = np.array([1 if y[j] == '2' or y[j] == '3' else 0 for j in range(data_number)])
    X = np.array(data_list)
    X_train = np.insert(X, 0, 1, axis=1)  # 添加偏置项
    return X_train, y_train

def train_logreg(X, y, numIter=1000, learning_rate=0.06, batch_size=128, lambda_reg=0.01):
    """
    对率回归训练函数，加入L2正则化。

    Args:
    - X (numpy array): 特征数据。
    - y (numpy array): 标签数据。
    - numIter (int): 迭代次数。默认为1000。
    - learning_rate (float): 学习率。默认为0.06。
    - batch_size (int): 批量大小。默认为128。
    - lambda_reg (float): L2正则化参数。默认为0.01。

    Returns:
    - numpy array: 训练得到的权重。
    """
    m, n = X.shape  # m: 样本数, n: 特征数
    weights = np.zeros(n)  # 参数初始化

    for j in range(numIter):
        # 随机打乱样本顺序
        dataIndex = np.random.permutation(m)
        for i in range(0, m, batch_size):
            end = min(i + batch_size, m)
            # 批量梯度上升
            batch_X = X[dataIndex[i:end]]
            batch_y = y[dataIndex[i:end]]
            
            # 计算梯度
            z = np.dot(batch_X, weights)
            h = 1 / (1 + np.exp(-z))  # 计算h
            error = batch_y - h  # 计算误差
            gradient = np.dot(batch_X.T, error) / len(batch_y)  # 计算梯度
            # 添加L2正则化
            reg_term = 2 * lambda_reg * weights
            gradient -= reg_term / len(batch_y)
            weights += learning_rate * gradient  # 更新权重

    return weights

def predict_logreg(inX, weights):
    """
    对率回归预测函数。

    Args:
    - inX (numpy array): 输入待分类的样本。
    - weights (numpy array): 训练得到的权重。

    Returns:
    - int: 预测的分类标签。
    """
    z = np.dot(inX, weights)  # 线性组合
    prob = 1 / (1 + np.exp(-z))  # 计算概率
    return 1 if prob >= 0.5 else 0  # 返回分类标签

if __name__ == "__main__":
    # 加载训练集
    X_train, y_train = load_data("./data/horse-colic.data")

    # 加载测试集
    X_test, y_test = load_data("./data/horse-colic.test")

    # 特征缩放
    scaler = StandardScaler()
    X_train = scaler.fit_transform(X_train)
    X_test = scaler.transform(X_test)

    # 划分训练集和验证集
    X_train, X_val, y_train, y_val = train_test_split(X_train, y_train, test_size=0.2, random_state=42)

    # 训练对率回归模型，使用早停法
    best_weights = None
    best_auc = 0
    for iter in range(1, 1001):
        weights = train_logreg(X_train, y_train, numIter=iter, learning_rate=0.01, lambda_reg=0.1)
        y_pred = [predict_logreg(x, weights) for x in X_val]
        auc = roc_auc_score(y_val, y_pred)
        if auc > best_auc:
            best_auc = auc
            best_weights = weights
        if iter > 10 and auc == best_auc:
            break  # 早停

    # 使用最佳权重在测试集上评估模型
    y_pred_test = [predict_logreg(x, best_weights) for x in X_test]
    accuracy_test = accuracy_score(y_test, y_pred_test)
    print(f"Test Accuracy: {accuracy_test}")

    # 随机森林模型
    param_grid = {
        'n_estimators': [100, 200, 300],
        'max_depth': [5, 10, 15],
        'learning_rate': [0.01, 0.05, 0.1]
    }
    rf = RandomForestClassifier()
    grid_search = GridSearchCV(estimator=rf, param_grid=param_grid, cv=5, scoring='accuracy')
    grid_search.fit(X_train, y_train)
    best_rf = grid_search.best_estimator_
    print("Best parameters:", grid_search.best_params_)
    print("Best accuracy:", grid_search.best_score_)

    # 集成学习 - 投票分类器
    log_clf = LogisticRegression()
    rnd_clf = RandomForestClassifier(n_estimators=100, random_state=42)
    voting_clf = VotingClassifier(estimators=[('lr', log_clf), ('rf', rnd_clf)], voting='soft')
    voting_clf.fit(X_train, y_train)
    y_pred = voting_clf.predict(X_test)
    print("Voting classifier accuracy:", accuracy_score(y_test, y_pred))