更新 function.py

function.py

@@ -1,62 +1,98 @@
 import numpy as np
 
-id = "202210423218"
+"""
-name = "唐一鸣"
+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。
+"""
+
+id = "202210423xxx"
+name = "test_name"
+
+def load_data(filepath):
+    """
+    从文件中加载数据。
+
+    Args:
+    - filepath (str): 数据文件路径。
+
+    Returns:
+    - np.array: 特征数据。
+    - np.array: 标签数据。
+    """
+    data = []
+    labels = []
+
+    with open(filepath, 'r') as file:
+        for line in file:
+            # 用空格分割每一行
+            parts = line.strip().split()
+            # 将特征和标签分开，假设最后一列为标签
+            features = parts[:-1]
+            label = parts[-1]
+            
+            # 用-1替换缺失值（或你可以选择其他处理方式）
+            features = [float(x) if x != '?' else -1 for x in features]
+            data.append(features)
+            labels.append(int(label))
+
+    return np.array(data), np.array(labels)
 
 def sigmoid(z):
+    """Sigmoid 激活函数"""
     return 1 / (1 + np.exp(-z))
 
-def train_logreg(X, y, other_params=""):
+def train_logreg(X, y, learning_rate=0.01, iterations=1000):
+    """
+    对率回归训练函数。
+
+    Args:
+    - X (numpy array): 特征数据。
+    - y (numpy array): 标签数据。
+    - learning_rate (float): 学习率。
+    - iterations (int): 迭代次数。
+
+    Returns:
+    - numpy array: 训练得到的权重。
+    """
     m, n = X.shape
     weights = np.zeros(n)
-    learning_rate = 0.01
+    
-    num_iterations = 1000
+    for _ in range(iterations):
-
-    for _ in range(num_iterations):
         linear_model = np.dot(X, weights)
-        y_predicted = sigmoid(linear_model)
+        predictions = sigmoid(linear_model)
-        gradient = np.dot(X.T, (y_predicted - y)) / m
+
+        # 计算梯度
+        gradient = np.dot(X.T, (predictions - y)) / m
         weights -= learning_rate * gradient
 
     return weights
 
 def predict_logreg(inX, weights):
-    prob = sigmoid(np.dot(inX, weights))
+    """
-    return 1 if prob >= 0.5 else 0
+    对率回归预测函数。
 
-def load_data(filepath):
+    Args:
-    with open(filepath, 'r') as f:
+    - inX (numpy array): 输入待分类的样本。
-        lines = f.readlines()
+    - weights (numpy array): 训练得到的权重。
 
-    data = []
+    Returns:
-    for line in lines:
+    - int: 预测的分类标签。
-        row = line.strip().split()
+    """
-        row = [float(x) if x != '?' else np.nan for x in row]
+    probability = sigmoid(np.dot(inX, weights))
-        data.append(row)
+    return 1 if probability >= 0.5 else 0
-
-    data = np.array(data)
-
-    # 用均值替代缺失值
-    for i in range(data.shape[1] - 1):  # 只处理特征列
-        if np.any(np.isnan(data[:, i])):
-            mean_value = np.nanmean(data[:, i])
-            data[:, i] = np.where(np.isnan(data[:, i]), mean_value, data[:, i])
-
-    # 特征为前n-1列，标签为最后一列
-    X = data[:, :-1]
-    y = data[:, -1]
-
-    return X, y
 
 if __name__ == "__main__":
+    # 加载训练集
     X_train, y_train = load_data("./data/horse-colic.data")
+
+    # 加载测试集
     X_test, y_test = load_data("./data/horse-colic.test")
 
-    weights = train_logreg(X_train, y_train)
+    # 训练对率回归模型
+    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
 
     # 测试单个数据
-    test_index = 11  # 选择要测试的索引
+    y_pred = predict_logreg(X_test[11], weights)
-    y_pred = predict_logreg(X_test[test_index], 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[test_index]}")