222

function.py

@@ -1,5 +1,6 @@
 # function.py
 import numpy as np
+from sklearn.preprocessing import StandardScaler
 
 """
 实验说明:
@@ -26,7 +27,6 @@ name = "廖子豪"
 
 
 # 这里写自己的代码实现
-
 def load_data(filepath):
     """
     从文件中加载数据。
@@ -65,7 +65,7 @@ def load_data(filepath):
         print(f"Error loading data: {e}")
         # 返回空数组而不是None，以避免后续代码中出现错误
         return np.empty((0, 0)), np.empty(0)
-    
+
 def train_logreg(X, y, learning_rate=0.01, iterations=1000):
     """
     对率回归训练函数。
@@ -80,7 +80,9 @@ def train_logreg(X, y, learning_rate=0.01, iterations=1000):
     - numpy array: 训练得到的权重。
     """
     m, n = X.shape
-    weights = np.zeros(n)
+    # 添加偏置项
+    X = np.c_[np.ones((m, 1)), X]
+    weights = np.zeros(n + 1)
     for _ in range(iterations):
         for i in range(m):
             z = np.dot(X[i], weights)
@@ -99,6 +101,8 @@ def predict_logreg(inX, weights):
     Returns:
     - int: 预测的分类标签。
     """
+    # 添加偏置项
+    inX = np.c_[np.ones((1, 1)), inX]
     z = np.dot(inX, weights)
     y_pred = 1 / (1 + np.exp(-z))
     return 1 if y_pred > 0.5 else 0
@@ -110,9 +114,19 @@ if __name__ == "__main__":
     # 加载测试集
     X_test, y_test = load_data("./data/horse-colic.test")
 
+    # 特征缩放
+    scaler = StandardScaler()
+    X_train = scaler.fit_transform(X_train)
+    X_test = scaler.transform(X_test)
+
     # 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]}")
+    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
+
+    # 评估模型
+    y_pred_all = [predict_logreg(X_test[i], weights) for i in range(len(X_test))]
+    accuracy = np.mean(y_pred_all == y_test)
+    print(f"Accuracy: {accuracy}")