import numpy as np
import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split, GridSearchCV

id = "202210423130"
name = "董秋"

def train_logreg(X, y, learning_rate=0.01, iterations=1000, lambda_reg=0.01):
    """
    对率回归训练函数。

    Args:
    - X (numpy array): 特征数据。
    - y (numpy array): 标签数据。

    Returns:
    - numpy array: 训练得到的权重。
    """
    m, n = X.shape
    weights = np.zeros(n)

    for i in range(iterations):
        z = np.dot(X, weights)
        predictions = 1 / (1 + np.exp(-z))
        gradient = np.dot(X.T, (predictions - y)) / m
        
        # L2正则化：将正则项添加到梯度上
        gradient += (lambda_reg / m) * weights

        # 更新权重
        weights -= learning_rate * gradient

        # 动态调整学习率
        learning_rate *= 0.95  # 每次迭代将学习率乘以0.99

    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)
    prediction_prob = 1 / (1 + np.exp(-z))
    return 1 if prediction_prob >= 0.5 else 0

def load_data(filepath):
    data = []
    labels = []

    with open(filepath, 'r') as f:
        for line in f:
            values = line.strip().replace('?', '0').split()
            try:
                values = [float(v) for v in values]
                if values[22] == 2 or values[22] == 3:
                    labels.append(0)
                elif values[22] == 1:
                    labels.append(1)
                else:
                    continue
                values = [0 if np.isnan(v) else v for v in values]
                data.append(values[:2] + values[3:23])
            except ValueError:
                continue

    return np.array(data), np.array(labels)

def preprocess_data(X):
    scaler = StandardScaler()
    return scaler.fit_transform(X)

if __name__ == "__main__":
    # 加载数据集
    X, y = load_data("./data/horse-colic.data")
    X = preprocess_data(X)
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

    # 定义参数网格
    param_grid = {
        'learning_rate': [0.01, 0.05, 0.1],
        'iterations': [500, 1000, 2000],
        'lambda_reg': [0.01, 0.1, 1]
    }

    # 网格搜索中定义的参数
    best_params = {'learning_rate': 0.1, 'iterations': 1000, 'lambda_reg': 0.01}

    # 使用最佳参数重新训练模型
    weights = train_logreg(X_train, y_train, 
                           learning_rate=best_params['learning_rate'], 
                           iterations=best_params['iterations'], 
                           lambda_reg=best_params['lambda_reg'])

    # 测试单个数据
    y_pred = predict_logreg(X_test[11], weights)
    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")