From a97fb09c9d9c2c17071d25a5c787ead6af40b9c9 Mon Sep 17 00:00:00 2001
From: lzh <2233673261@qq.com>
Date: Sat, 2 Nov 2024 20:43:22 +0800
Subject: [PATCH] 444

---
 function.py | 117 ++++++++++++++++++++--------------------------------
 1 file changed, 44 insertions(+), 73 deletions(-)

diff --git a/function.py b/function.py
index d14be28..505db58 100644
--- a/function.py
+++ b/function.py
@@ -25,6 +25,43 @@ 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。
+
+    Args:
+    - filepath (str): 数据文件路径。
+
+    Returns:
+    - np.array: 特征数据。
+    - np.array: 标签数据。
+    """
+    file = open(filepath)
+    fr = file.readlines()
+    data_list = []
+    y = []
+    for data in fr:
+        data = data.strip()
+        data = data.split(' ')
+        data_25 = data[24]
+        y.append(data[22])
+        del data[-1]
+        del data[26]
+        del data[25]
+        del data[24]
+        del data[22]
+        del data[2]
+        for i in data_25:
+            data.append(i)
+        data = [0 if data_elem == '?' else float(data_elem) for data_elem in data]
+        data_list.append(data)
+    data_number = len(y)
+    y_train = np.array([1 if y[j] == '2' or y[j] == '3' else 0 for j in range(data_number)])
+    X = np.array(data_list)
+    X_train = np.insert(X, 0, 1, axis=1)  # 添加偏置项
+    return X_train, y_train
+
 def train_logreg(X, y, numIter=1000, learning_rate=0.06, batch_size=128, lambda_reg=0.01):
     """
     对率回归训练函数，加入L2正则化。
@@ -37,21 +74,6 @@ def train_logreg(X, y, numIter=1000, learning_rate=0.06, batch_size=128, lambda_
     - batch_size (int): 批量大小。默认为128。
     - lambda_reg (float): L2正则化参数。默认为0.01。
 
-    Returns:
-    - numpy array: 训练得到的权重。
-    """
-def train_logreg(X, y, numIter=1000, learning_rate=0.06, batch_size=128, lambda_reg=0.01):
-    """
-    使用梯度上升的对率回归训练函数，加入L2正则化。
-
-    Args:
-    - X (numpy array): 特征数据。
-    - y (numpy array): 标签数据。
-    - numIter (int): 迭代次数。默认为1000。
-    - learning_rate (float): 学习率。默认为0.06。
-    - batch_size (int): 批量大小。默认为128。
-    - lambda_reg (float): L2正则化参数。默认为0.01。
-
     Returns:
     - numpy array: 训练得到的权重。
     """
@@ -79,9 +101,6 @@ def train_logreg(X, y, numIter=1000, learning_rate=0.06, batch_size=128, lambda_
 
     return weights
 
-
-
-
 def predict_logreg(inX, weights):
     """
     对率回归预测函数。
@@ -97,52 +116,7 @@ def predict_logreg(inX, weights):
     prob = 1 / (1 + np.exp(-z))  # 计算概率
     return 1 if prob >= 0.5 else 0  # 返回分类标签
 
-
-
-# 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**。
-
-    Args:
-    - directory (str): 数据文件路径。
-
-    Returns:
-    - np.array: 特征数据。
-    - np.array: 标签数据。
-    """
-
-    file = open(filepath)
-    fr = file.readlines()
-    data_list = []
-    y = []
-    for data in fr:
-        data = data.strip()
-        data = data.split(' ')
-        data_25 = data[24]
-        y.append(data[22])
-        del data[-1]
-        del data[26]
-        del data[25]
-        del data[24]
-        del data[22]
-        del data[2]
-        for i in data_25:
-            data.append(i)
-        data = [0 if data_elem == '?' else float(data_elem) for data_elem in data]
-        data_list.append(data)
-    data_number = len(y)
-    y_train = np.array([1 if y[j] == '2' or y[j] == '3' else 0 for j in range(data_number)])
-    X = np.array(data_list)
-    X_train = np.insert(X, 0, 1, axis=1)
-    return X_train, y_train
-   
-
-
-
 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")
 
@@ -150,18 +124,15 @@ if __name__ == "__main__":
     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)
+    weights = train_logreg(X_train, y_train, numIter=1000, learning_rate=0.01, lambda_reg=0.2)
 
-    # 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]}")'''
-    X_train, y_train = load_data("./data/horse-colic.data")
-    X_test, y_test = load_data("./data/horse-colic.test")
-    weights = train_logreg(X_train, y_train, numIter=1000, learning_rate=0.01,lambda_reg=0.2)
-    error=0
+    # 测试模型
+    error = 0
+    accuracy_list = []
     for i in range(len(y_test)):
         y_pred = predict_logreg(X_test[i], weights)
         if y_pred != y_test[i]:
-            error+=1
+            error += 1
         print(f"预测结果: {y_pred}, 实际结果: {y_test[i]}")
-    print((len(y_test)-error)/len(y_test))
\ No newline at end of file
+    accuracy = (len(y_test) - error) / len(y_test)
+    print(f"Accuracy: {accuracy}")
\ No newline at end of file