更新 function.py

function.py

@@ -21,63 +21,65 @@ 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 = "202210423206"
+name = "詹宇豪"
 
 
 # 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"):
-    """
-    对率回归训练函数。
-
-    Args:
-    - X (numpy array): 特征数据。
-    - y (numpy array): 标签数据。
-    - 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**。
-
-    Returns:
-    - numpy array: 训练得到的权重。
-    """
 
 
-def predict_logreg(inX, weights):
-    """
-    对率回归预测函数。
+  def load_data(filepath, k_features=20):
+    data, labels = [], []
+    with open(filepath, 'r') as file:
+        for line in file:
+            line = line.strip().split()
+            if line:
+                features = [float(feature) if feature.replace('.', '', 1).isdigit() else np.nan for feature in line[:-1]]
+                label = int(line[-1])
+                data.append(features)
+                labels.append(label)
 
-    Args:
-    - inX (numpy array): 输入待分类的样本。
-    - weights (numpy array): 训练得到的权重。
+    data, labels = np.array(data), np.array(labels)
+    imputer = SimpleImputer(strategy='mean')
+    data = imputer.fit_transform(data)
+    
+    mean, std_dev = data.mean(axis=0), data.std(axis=0)
+    std_dev[std_dev == 0] = 1
+    data = (data - mean) / std_dev
 
-    Returns:
-    - int: 预测的分类标签。
-    """
+    selector = SelectKBest(f_classif, k=k_features)
+    data = selector.fit_transform(data, labels)
 
+    return data, labels
 
-# 这里也写自己的代码实现
-def load_data(filepath):
-    """
-    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**。
+def sigmoid(z):
+    return 1 / (1 + np.exp(-z))
 
-    Args:
-    - directory (str): 数据文件路径。
+def train_logreg(X, y, initial_lr=0.005, iterations=5000, regularization=0.01, decay=0.0001):
+    m, n = X.shape
+    weights = np.zeros(n)
+    learning_rate = initial_lr
 
-    Returns:
-    - np.array: 特征数据。
-    - np.array: 标签数据。
-    """
+    for i in range(iterations):
+        predictions = sigmoid(np.dot(X, weights))
+        errors = y - predictions
+        gradient = (np.dot(X.T, errors) - regularization * weights) / m
+        weights += learning_rate * gradient
+        learning_rate = initial_lr / (1 + decay * i)
 
+    return weights
 
+def predict_logreg(X, weights, threshold=0.5):
+    probabilities = sigmoid(np.dot(X, weights))
+    return (probabilities >= threshold).astype(int)
+
+# 测试代码
 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")
+    X_train, y_train = load_data("./data/horse-colic.data", k_features=20)
+    X_test, y_test = load_data("./data/horse-colic.test", k_features=20)
 
-    # 加载测试集
-    X_test, y_test = load_data("./data/horse-colic.test")
+    weights = train_logreg(X_train, y_train, initial_lr=0.005, iterations=5000, regularization=0.01, decay=0.0001)
 
-    # 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
-    y_pred = predict_logreg(X_test[11], weights)
-    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
+    y_pred = predict_logreg(X_test, weights, threshold=0.5)
+    accuracy = np.mean(y_pred == y_test)
+    print(f"测试集准确率: {accuracy:.2f}")