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

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]
                
                # 合并特征23的取值
                if values[22] == 2 or values[22] == 3:  # 特征23（索引22）
                    labels.append(0)  # 死亡
                elif values[22] == 1:
                    labels.append(1)  # 生存
                else:
                    continue  # 无效标签，丢弃
                
                # 用0填充缺失值
                values = [0 if np.isnan(v) else v for v in values]
                
                # 去掉特征3（索引2）和特征24~28（索引23-27）
                data.append(values[:2] + values[3:23])  # 保留特征1, 2 和特征4-23
            except ValueError:
                continue

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

def preprocess_data(X):
    # 特征标准化
    scaler = StandardScaler()
    return scaler.fit_transform(X)

def train_logreg(X_train, y_train):
    # 定义要调优的超参数范围
    param_grid = {
        'C': [0.001, 0.01, 0.1, 1, 10, 100],  # 正则化参数
        'solver': ['liblinear', 'lbfgs'],     # 求解器
        'max_iter': [100, 500, 1000]          # 最大迭代次数
    }

    # 创建逻辑回归模型
    log_reg = LogisticRegression()

    # 创建网格搜索对象
    grid_search = GridSearchCV(estimator=log_reg, param_grid=param_grid, cv=5, scoring='accuracy')

    # 进行网格搜索
    grid_search.fit(X_train, y_train)

    return grid_search.best_estimator_

def predict_logreg(inX, weights):
    """
    逻辑回归预测函数。
    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

if __name__ == "__main__":
    # 加载数据集
    X, y = load_data("./data/horse-colic.data")
    X = preprocess_data(X)

    # 使用 train_test_split 打乱并随机抽取数据
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

    # 训练逻辑回归模型
    best_model = train_logreg(X_train, y_train)

    # 测试单个数据
    y_pred = best_model.predict(X_test[11].reshape(1, -1))  # 进行预测时需要调整输入形状
    print(f"预测结果: {y_pred[0]}, 实际结果: {y_test[11]}")