sy2

function.py

@@ -1,6 +1,5 @@
 # function.py
 import numpy as np
-
 """
 实验说明:
 - 自行编写实现数据加载与预测病马死亡的对率回归算法。
@@ -21,12 +20,12 @@ import numpy as np
 """
 请在这里填写学号和姓名，不填写即成绩无效。
 """
-id = "202210423xxx"
-name = "test_name"
+id = "202210423109"
+name = "孔祥芷"
 
 
 # 这里写自己的代码实现
-def train_logreg(X, y, other_params="你自己设置一些其它参数"):
+def train_logreg(X, y, numIter=1000, learning_rate=0.06, batch_size=128):
     """
     对率回归训练函数。
 
@@ -38,6 +37,27 @@ def train_logreg(X, y, other_params="你自己设置一些其它参数"):
     Returns:
     - numpy array: 训练得到的权重。
     """
+    m, n = X.shape  # m: 样本数, n: 特征数
+    weights = np.zeros(n)  # 参数初始化
+
+    for j in range(numIter):
+        # 随机打乱样本顺序
+        dataIndex = np.random.permutation(m)
+        for i in range(0, m, batch_size):
+            end = min(i + batch_size, m)
+            # 批量梯度下降
+            batch_X = X[dataIndex[i:end]]
+            batch_y = y[dataIndex[i:end]]
+            
+            # 计算梯度
+            z = np.dot(batch_X, weights)
+            h = 1 / (1 + np.exp(-z))  # 计算h
+            error = batch_y - h  # 计算误差
+            gradient = np.dot(batch_X.T, error) / len(batch_y)  # 计算梯度
+            weights += learning_rate * gradient  # 更新权重
+
+    return weights
+
 
 
 def predict_logreg(inX, weights):
@@ -51,6 +71,10 @@ def predict_logreg(inX, weights):
     Returns:
     - int: 预测的分类标签。
     """
+    z = np.dot(inX, weights)  # 线性组合
+    prob = 1 / (1 + np.exp(-z))  # 计算概率
+    return 1 if prob >= 0.5 else 0  # 返回分类标签
+
 
 
 # 这里也写自己的代码实现
@@ -66,8 +90,36 @@ def load_data(filepath):
     - np.array: 标签数据。
     """
 
+    file = open(filepath)
+    fr = file.readlines()
+    data_list = []
+    y = []
+    for data in fr:
+        data = data.strip()
+        data = data.split(' ')
+        data_25 = data[24]
+        y.append(data[22])
+        del data[-1]
+        del data[26]
+        del data[25]
+        del data[24]
+        del data[22]
+        del data[2]
+        for i in data_25:
+            data.append(i)
+        data = [0 if data_elem == '?' else float(data_elem) for data_elem in data]
+        data_list.append(data)
+    data_number = len(y)
+    y_train = np.array([1 if y[j] == '2' or y[j] == '3' else 0 for j in range(data_number)])
+    X = np.array(data_list)
+    X_train = np.insert(X, 0, 1, axis=1)
+    return X_train, y_train
+   
+
+
 
 if __name__ == "__main__":
+    '''
     # 以下代码可用于测试，可自行随意修改
     # 加载训练集
     X_train, y_train = load_data("./data/horse-colic.data")
@@ -80,4 +132,14 @@ if __name__ == "__main__":
 
     # 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]}")
+    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")'''
+    X_train, y_train = load_data("./data/horse-colic.data")
+    X_test, y_test = load_data("./data/horse-colic.test")
+    weights = train_logreg(X_train, y_train, numIter=1000, learning_rate=0.01)
+    error=0
+    for i in range(len(y_test)):
+        y_pred = predict_logreg(X_test[i], weights)
+        if y_pred != y_test[i]:
+            error+=1
+        print(f"预测结果: {y_pred}, 实际结果: {y_test[i]}")
+    print((len(y_test)-error)/len(y_test))