更新 function.py

function.py

@@ -26,59 +26,67 @@ def sigmoid(z):
 id = "202210423223"
 name = "李顺潮"
 
-# 对率回归训练函数
-def train_logreg(X, y, learning_rate=0.01, iterations=1000):
-    X = np.hstack((np.ones((X.shape[0], 1)), X))  # 在特征前添加一列全为1的列
-    m, n = X.shape
-    weights = np.zeros(n)
+# 逻辑回归训练函数  
+def train_logreg(X, y, learning_rate=0.01, iterations=1000):  
+    X = np.hstack((np.ones((X.shape[0], 1)), X))  # 在特征前添加一列全为1的列  
+    m, n = X.shape  
+    weights = np.zeros(n)  
 
-    for _ in range(iterations):
-        z = np.dot(X, weights)
-        predictions = 1 / (1 + np.exp(-z))
-        gradient = np.dot(X.T, (predictions - y)) / m
-        weights -= learning_rate * gradient
+    for _ in range(iterations):  
+        z = np.dot(X, weights)  
+        predictions = 1 / (1 + np.exp(-z))  
+        gradient = np.dot(X.T, (predictions - y)) / m  
+        weights -= learning_rate * gradient  
 
-    return weights
+    return weights  
 
-# 对率回归预测函数  
-# 对率回归预测函数，支持多类分类
-def predict_logreg(inX, weights):
-    inX = np.insert(inX, 0, 1)  # 在特征前添加1作为偏置项
-    prob = 1 / (1 + np.exp(-np.dot(inX, weights)))
+# 逻辑回归预测函数，支持多类分类  
+def predict_logreg(inX, weights):  
+    inX = np.insert(inX, 0, 1)  # 在特征前添加1作为偏置项  
+    prob = 1 / (1 + np.exp(-np.dot(inX, weights)))  
 
-    if prob < 0.5:
-        return 0
-    elif prob >= 0.5 and prob < 1.0:
-        return 1
-    else:
-        return 2  # 确保返回3个类别中的一个
+    if prob < 0.5:  
+        return 0  
+    elif prob >= 0.5 and prob < 1.0:  
+        return 1  
+    else:  
+        return 2  # 确保返回3个类别中的一个  
 
 # 从文件中加载数据  
-def load_data(filepath):
-    data = pd.read_csv(filepath, header=None, na_values='?', delim_whitespace=True)
-    data.fillna(data.mean(), inplace=True) # 用均值填充缺失值
-    X = data.iloc[:, :-1].to_numpy()  # 特征
-    y = data.iloc[:, -1].to_numpy()    # 标签
-    return X, y 
-# 准确率计算函数
-def calculate_accuracy(X, y, weights):
-    predictions = np.array([predict_logreg(x, weights) for x in X])
-    accuracy = np.mean(predictions == y)
-    return accuracy
+def load_data(filepath):  
+    data = pd.read_csv(filepath, header=None, na_values='?', delim_whitespace=True)  
+
+    # 用“0”填充缺失值  
+    data.fillna(0, inplace=True)  
+
+    # 合并特征23的取值  
+    data.iloc[:, 22] = data.iloc[:, 22].replace({2: 0, 3: 0})  # 将2和3替换为0  
+
+    # 去掉特征3和特征24至28  
+    data.drop(columns=[2, 23, 24, 25, 26, 27], inplace=True)  
+
+    X = data.iloc[:, :-1].to_numpy()  # 特征  
+    y = data.iloc[:, -1].to_numpy()    # 标签  
+    return X, y   
+
+# 准确率计算函数  
+def calculate_accuracy(X, y, weights):  
+    predictions = np.array([predict_logreg(x, weights) for x in X])  
+    accuracy = np.mean(predictions == y)  
+    return accuracy  
 
 if __name__ == "__main__":  
     # 加载训练集和测试集  
-    X_train, y_train = load_data("E:\\Edge站内文件下载\\病马数据集\\horse-colic.data")
-    X_test, y_test = load_data( "E:\\Edge站内文件下载\\病马数据集\\horse-colic.test")
+    X_train, y_train = load_data("..\\horse-colic.data")  
+    X_test, y_test = load_data("..\\horse-colic.test")  
     
-    # 训练对率回归模型 
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
+    # 训练逻辑回归模型   
+    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)  
   
     # 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]}")  
 
-
-    # 计算并输出模型的准确率
-    accuracy = calculate_accuracy(X_test, y_test, weights)
-    print(f"模型的准确率: {accuracy:.4f}")
+    # 计算并输出模型的准确率  
+    accuracy = calculate_accuracy(X_test, y_test, weights)  
+    print(f"模型的准确率: {accuracy:.4f}")