diff --git a/function.py b/function.py
index 5d7a411..6bbbaad 100644
--- a/function.py
+++ b/function.py
@@ -26,71 +26,43 @@ name = "周佳成"
 
 
 # 这里写自己的代码实现
-import numpy as np  
 import pandas as pd  
-from sklearn.linear_model import LogisticRegression  
+import numpy as np  
 from sklearn.model_selection import train_test_split  
-from sklearn.metrics import accuracy_score  
-  
-# 加载数据  
-def load_data(train_url, test_url):  
-    # 由于直接下载数据并读取可能涉及网络连接，这里假设数据已下载并保存在本地路径  
-    # 用户需根据实际情况修改路径或实现数据下载逻辑  
-    train_data = pd.read_csv(train_url, sep='\s+', header=None, na_values='?')  
-    test_data = pd.read_csv(test_url, sep='\s+', header=None, na_values='?')  
-    return train_data, test_data  
-  
-# 数据预处理  
-def preprocess_data(data):  
-    # 用0填充缺失值  
-    data.fillna(0, inplace=True)  
-      
-    # 选择特征23作为目标变量，将其取值2和3合并为一个值0（死亡）  
-    data[22] = data[22].apply(lambda x: 0 if x in [2, 3] else 1)  
-      
-    # 去掉特征3、特征24~28  
-    data = data.drop([2, 23, 24, 25, 26, 27, 28], axis=1)  
-      
-    # 特征和标签分离  
-    X = data.iloc[:, :-1]  # 所有行，除了最后一列（目标变量）  
-    y = data.iloc[:, -1]   # 所有行，最后一列（目标变量）  
-      
-    return X, y  
-  
+from sklearn.linear_model import LogisticRegression  
+from sklearn.metrics import accuracy_score, classification_report  
+
+# 读取数据  
+data_path = 'C:\\Users\\star\\Desktop\\机器学习\\experiment-log\\data\\horse-colic.data'  
+data = pd.read_csv(data_path, header=None, delim_whitespace=True, na_values='?')  
+
+# 处理缺失值（用0填充）  
+data.fillna(0, inplace=True)  
+
+# 选择特征和目标变量  
+# 去掉特征3和特征24~28  
+features = data.iloc[:, :-5].values  # 假设最后一列是目标变量，前面的都是特征  
+target = data.iloc[:, -1].values  
+
+# 将目标变量中的2和3合并为0  
+target[target == 2] = 0  
+target[target == 3] = 0  
+
+# 将目标变量转换为二进制分类（0或1）  
+target = (target == 1).astype(int)  
+
+# 划分训练集和测试集  
+X_train, X_test, y_train, y_test = train_test_split(features, target, test_size=0.2, random_state=42)  
+
 # 训练对率回归模型  
-def train_logreg(X_train, y_train):  
-    model = LogisticRegression(max_iter=10000)  # 设置默认迭代次数以避免警告  
-    model.fit(X_train, y_train)  
-    return model  
-  
-# 使用对率回归模型进行预测  
-def predict_logreg(model, X_test):  
-    y_pred = model.predict(X_test)  
-    return y_pred  
-  
-# 主函数（用于演示整个流程）  
-def main():  
-    # 数据集URL（这里使用本地路径，实际使用时需替换为网络URL或下载后的路径）  
-    train_url = 'path_to_train_data.csv'  # 训练数据路径  
-    test_url = 'path_to_test_data.csv'    # 测试数据路径  
-      
-    # 加载数据  
-    train_data, test_data = load_data(train_url, test_url)  
-      
-    # 数据预处理  
-    X_train, y_train = preprocess_data(train_data)  
-    X_test, y_test = preprocess_data(test_data)  
-      
-    # 划分训练集和验证集（如果需要的话，这里仅作为示例）  
-    # 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  
-    model = train_logreg(X_train, y_train)  
-      
-    # 进行预测  
-    y_pred = predict_logreg(model, X_test)  
-      
-    # 计算准确率  
-    accuracy = accuracy_score(y_test, y_pred)  
+model = LogisticRegression(max_iter=1000)  
+model.fit(X_train, y_train)  
 
+# 预测并评估模型  
+y_pred = model.predict(X_test)  
+accuracy = accuracy_score(y_test, y_pred)  
+report = classification_report(y_test, y_pred)  
 
+print(f"Accuracy: {accuracy:.2f}")  
+print("Classification Report:")  
+print(report)