From 669a011bb1b3ea14e353bc60ccad7f80ff6ad132 Mon Sep 17 00:00:00 2001
From: DREMN2112 <z2117004628@gmail.com>
Date: Thu, 7 Nov 2024 17:06:01 +0800
Subject: [PATCH] =?UTF-8?q?=E6=9B=B4=E6=96=B0=20function.py?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 function.py | 44 +++++++++++++++++++++++---------------------
 1 file changed, 23 insertions(+), 21 deletions(-)

diff --git a/function.py b/function.py
index 4c21829..b4dc1d9 100644
--- a/function.py
+++ b/function.py
@@ -27,7 +27,7 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000):
     weights = np.zeros(X.shape[1])
     
     # 梯度下降
-    for _ in range(iterations):
+    for i in range(iterations):
         # 计算预测值
         predictions = sigmoid(np.dot(X, weights))
         
@@ -37,6 +37,11 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000):
         # 更新权重
         gradient = np.dot(X.T, error) / len(y)
         weights -= learning_rate * gradient
+        
+        # 每 100 次迭代输出一次损失
+        if i % 100 == 0:
+            loss = -np.mean(y * np.log(predictions) + (1 - y) * np.log(1 - predictions))
+            print(f"Iteration {i}, Loss: {loss:.4f}")
     
     return weights
 
@@ -58,45 +63,37 @@ def predict_logreg(inX, weights):
 
 def load_data(filepath):
     """
-    从文件中加载数据，处理缺失数据，并将 '?' 替换为列的中位数。
+    从文件中加载数据，并处理 '?' 为每列的均值。
     """
     data = []
     labels = []
-
+    
     with open(filepath, 'r') as file:
         for line in file:
             line = line.strip().split()
             if not line:
                 continue
-
-            # 将标签提取出来
+            # 将特征转换为浮点型，处理 '?' 为 NaN
+            features = [float(f) if f != '?' else np.nan for f in line[:-1]]
             label = int(line[-1])
-
-            # 将特征转换为浮动数组，'?' 替换为 np.nan
-            features = line[:-1]  # 去除标签部分
-            features = [float(f) if f != '?' else np.nan for f in features]
-            
-            # 将数据和标签分别加入到列表
             data.append(features)
             labels.append(label)
-
-    # 将列表转换为 numpy 数组
+    
     data = np.array(data)
     labels = np.array(labels)
-
-    # 计算每列的中位数，并用中位数替换 NaN
-    col_medians = np.nanmedian(data, axis=0)  # 计算每列的中位数
+    
+    # 计算每列的均值，并用均值替换 NaN
+    col_means = np.nanmean(data, axis=0)  # 计算每列的均值
     for i in range(data.shape[1]):
-        data[:, i] = np.where(np.isnan(data[:, i]), col_medians[i], data[:, i])
+        data[:, i] = np.where(np.isnan(data[:, i]), col_means[i], data[:, i])
 
-    # 对数据进行标准化 (均值为 0，标准差为 1)
+    # 标准化数据（均值为 0，标准差为 1）
     means = np.mean(data, axis=0)
     stds = np.std(data, axis=0)
     data = (data - means) / stds
 
     return data, labels
 
-
 if __name__ == "__main__":
     # 加载训练集
     X_train, y_train = load_data("./data/horse-colic.data")
@@ -104,9 +101,14 @@ if __name__ == "__main__":
     # 加载测试集
     X_test, y_test = load_data("./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)
+    # 训练对率回归模型，增加迭代次数为 5000 次
+    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=5000)
 
     # 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]}")
+
+    # 测试整体准确率
+    y_test_pred = np.array([predict_logreg(X_test[i], weights) for i in range(X_test.shape[0])])
+    accuracy = np.mean(y_test_pred == y_test)
+    print(f"测试集准确率: {accuracy:.4f}")