更新 function.py

function.py

@@ -1,85 +1,81 @@
-# function.py
 import numpy as np
 
-"""
+id="202210423210"
-实验说明:
+name="陈宇杰"
-- 自行编写实现数据加载与预测病马死亡的对率回归算法。
 
-注意事项:
+# Utility Functions
-- 在 function.py 中实现对率回归算法。
+def sigmoid(z):
-- 可以自行导入其他库，需要在 requirements.txt 添加依赖，若未在 requirements.txt 中添加使用到的依赖，则无法自动评测，成绩为零。
+    return 1 / (1 + np.exp(-z))
-- 自动评测脚本仅会加载 train_logreg、predict_logreg 和 load_data 函数，请勿修改函数名。
 
-测评环境:
+# Optimized Logistic Regression Training
-- CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz
+def train_logreg(X, y, learning_rate=0.01, iterations=1000, batch_size=128, lambda_reg=0.01):
-- OS: Ubuntu 22.04.4 LTS
+    m, n = X.shape
-- Python: 3.10.12
+    weights = np.random.randn(n) * 0.01  # Initialize weights with small random values for faster convergence
-- numpy: 2.1.1
+    prev_weights = np.copy(weights)
-"""
 
+    for j in range(iterations):
+        dataIndex = np.random.permutation(m)
+        for i in range(0, m, batch_size):
+            end = min(i + batch_size, m)
+            batch_X = X[dataIndex[i:end]]
+            batch_y = y[dataIndex[i:end]]
             
-"""
+            # Vectorized gradient calculation
-请在这里填写学号和姓名，不填写即成绩无效。
+            z = np.dot(batch_X, weights)
-姓名请直接**填写中文**
+            h = sigmoid(z)
-例如: name = "张三"
-"""
-id = "202210423xxx"
-name = "test_name"
             
+            error = batch_y - h
+            gradient = np.dot(batch_X.T, error) / len(batch_y)
+            gradient -= lambda_reg * weights / len(batch_y)
             
-# 这里写自己的代码实现
+            weights += learning_rate * gradient
-def train_logreg(X, y, other_params="你自己设置一些其它参数"):
-    """
-    对率回归训练函数。
 
-    Args:
+        # Early stopping: Check for convergence
-    - X (numpy array): 特征数据。
+        if np.linalg.norm(weights - prev_weights) < 1e-5:
-    - y (numpy array): 标签数据。
+            print(f"Converged after {j} iterations.")
-    - other_params (str): 其它参数，可选设置。若需设置其它参数，必须设置其默认值，否则将**无法通过**自动评测，**成绩为零**。
+            break
+        prev_weights = np.copy(weights)
 
-    Returns:
+    return weights
-    - numpy array: 训练得到的权重。
-    """
 
+def predict_logreg(X, weights):
+    probabilities = sigmoid(np.dot(X, weights))
+    return (probabilities >= 0.5).astype(int)
 
-def predict_logreg(inX, weights):
+# Load Data Function
-    """
-    对率回归预测函数。
-
-    Args:
-    - inX (numpy array): 输入待分类的样本。
-    - weights (numpy array): 训练得到的权重。
-
-    Returns:
-    - int: 预测的分类标签。
-    """
-
-
-# 这里也写自己的代码实现
 def load_data(filepath):
-    """
+    data, labels = [], []
-    从文件中加载数据，若不自行正确实现，则无法通过评测，**不记录成绩**。
+    with open(filepath, 'r') as file:
+        for line in file:
+            parts = line.strip().split()
+            features = [float(x) if x != '?' else 0.0 for x in parts[:-1]]
+            label = parts[-1]
+            data.append(features)
+            labels.append(1 if label in ['2', '3'] else 0)
 
-    Args:
+    data = np.array(data)
-    - directory (str): 数据文件路径。
+    labels = np.array(labels)
 
-    Returns:
+    # Normalize data
-    - np.array: 特征数据。
+    data_mean = np.mean(data, axis=0)
-    - np.array: 标签数据。
+    data_std = np.std(data, axis=0)
-    """
+    data = (data - data_mean) / (data_std + 1e-10)
     
+    return data, labels, data_mean, data_std
 
+# Load and Preprocess Data
 if __name__ == "__main__":
-    # 以下代码可用于测试，可自行随意修改
+    # Training data
-    # 加载训练集
+    X_train, y_train, data_mean, data_std = load_data("./data/horse-colic.data")
-    X_train, y_train = load_data("./data/horse-colic.data")
+    # Normalize test data using training mean and std
+    X_test, y_test, _, _ = load_data("./data/horse-colic.test")
+    X_test = (X_test - data_mean) / (data_std + 1e-10)
 
-    # 加载测试集
+    # Train model
-    X_test, y_test = load_data("./data/horse-colic.test")
+    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=2000, batch_size=64, lambda_reg=0.01)
 
-    # 训练对率回归模型
+    # Make predictions and calculate accuracy
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
+    y_pred = predict_logreg(X_test, weights)
+    accuracy = np.mean(y_pred == y_test)
     
-    # 测试单个数据
+    print(f"Accuracy: {accuracy:.2f}")
-    y_pred = predict_logreg(X_test[11], weights)
-    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")