更新 function.py

function.py

@@ -26,47 +26,37 @@ name = "周佳成"
 
 
 # 这里写自己的代码实现
-import pandas as pd  
 import numpy as np  
-from sklearn.model_selection import train_test_split  
+import pandas as pd  
 from sklearn.linear_model import LogisticRegression  
+from sklearn.model_selection import train_test_split  
 from sklearn.metrics import accuracy_score  
   
 def load_data():  
-    # 加载病马数据集  
+    # 下载并加载病马数据集  
     url = "http://archive.ics.uci.edu/ml/machine-learning-databases/horse-colic/horse-colic.data"  
     columns = [  
-        "surgery", "age", "hospital_num", "rectal_temp", "pulse", "resp_rate",  
+        "outcome", "surgery", "age", "hospital_num", "rectal_temp", # 部分列名示例，其余列名需根据数据集实际内容补充  
-        "temp_of_extremities", "peripheral_pulse", "mucous_membrane", "capillary_refill_time",  
+        # ... 其他特征列名  
-        "muscle_tone", "abdominal_distension", "nasal_discharge", "vomit", "heart_rate",  
+    ] + ["unused_" + str(i) for i in range(14, 29)]  # 假设最后15列为未使用特征  
-        "rectal_exam_fecal", "packed_cell_volume", "total_protein", "abdominocentesis_fluid",  
-        "abdominocentesis_fluid_appearance", "leukocyte_count", "outcome", "surgical_summary",  
-        "lesion_type", "lesion_site", "lesion_size"  
-    ]  
     data = pd.read_csv(url, header=None, names=columns, na_values='?')  
       
-    # 数据预处理  
+    # 处理缺失值，用0填充  
-    # 用0填充缺失值  
     data.fillna(0, inplace=True)  
       
-    # 将取值2（死亡）和3（安乐死）合并为一个值0（死亡），并重新编码为二分类问题  
+    # 选择特征和目标变量  
-    data['outcome'] = data['outcome'].apply(lambda x: 0 if x in [2, 3] else 1)  
+    X = data.drop(columns=["outcome", "age", "unused_" + str(i) for i in range(14, 29)])  
+    y = (data["outcome"] == 2) | (data["outcome"] == 3)  # 将2和3合并为0（死亡）  
+    y = y.astype(int)  
       
-    # 去掉特征3、特征24~28  
+    # 划分训练集和测试集（这里简单划分为70%训练和30%测试，实际比例可根据需要调整）  
-    data.drop(columns=['hospital_num', 'surgical_summary', 'lesion_type', 'lesion_site', 'lesion_size'], inplace=True)  
-      
-    # 特征和标签  
-    X = data.drop(columns=['outcome'])  
-    y = data['outcome']  
-      
-    # 划分训练集和测试集  
     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)  
       
     return X_train, X_test, y_train, y_test  
   
 def train_logreg(X_train, y_train):  
     # 训练对率回归模型  
-    model = LogisticRegression(max_iter=10000)  # 增加迭代次数以确保收敛  
+    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  
   
@@ -75,15 +65,9 @@ def predict_logreg(model, X_test):
     y_pred = model.predict(X_test)  
     return y_pred  
   
-def evaluate_model(y_test, y_pred):  
+# 示例用法（注意：这里的示例用法不会直接运行，因为需要加载数据集）  
-    # 评估模型性能  
-    accuracy = accuracy_score(y_test, y_pred)  
-    return accuracy  
-
-# 主函数（用于测试和展示）  
 if __name__ == "__main__":  
     X_train, X_test, y_train, y_test = load_data()  
-    model = train_logreg(X_train, y_train)  
+
-    y_pred = predict_logreg(model, X_test)  
+
-    accuracy = evaluate_model(y_test, y_pred)  
+
-    print(f"Model Accuracy: {accuracy:.4f}")