From dd50836d0699e10865d4e958a8cb4798b1c3426c Mon Sep 17 00:00:00 2001
From: luderby <2339127037@qq.com>
Date: Wed, 13 Nov 2024 19:25:12 +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 | 99 ++++++++++++++++++++++++++++++-----------------------
 1 file changed, 57 insertions(+), 42 deletions(-)

diff --git a/function.py b/function.py
index 92c3b6f..f165935 100644
--- a/function.py
+++ b/function.py
@@ -25,59 +25,74 @@ def sigmoid(z):
 """
 id = "202210423223"
 name = "李顺潮"
-# 对率回归训练函数
-def train_logreg(X, y, learning_rate=0.01, iterations=1000):
-    X = np.hstack((np.ones((X.shape[0], 1)), X))  # 在特征前添加一列全为1的列
-    m, n = X.shape
-    weights = np.zeros(n)
 
-    for _ in range(iterations):
-        z = np.dot(X, weights)
-        predictions = 1 / (1 + np.exp(-z))
-        gradient = np.dot(X.T, (predictions - y)) / m
-        weights -= learning_rate * gradient
+# 对率回归训练函数  
+def train_logreg(X, y, learning_rate=0.01, iterations=1000, batch_size=32, init_weights=None):  
+    X = np.hstack((np.ones((X.shape[0], 1)), X))  # 在特征前添加一列全为1的列  
+    m, n = X.shape  
+    
+    # 初始化权重  
+    if init_weights is None:  
+        weights = np.random.randn(n) * 0.01  # 使用标准差为0.01的正态分布初始化权重  
+    else:  
+        weights = init_weights  
 
-    return weights
+    for _ in range(iterations):  
+        indices = np.random.permutation(m)  # 打乱数据  
+        X_shuffled = X[indices]  
+        y_shuffled = y[indices]  
 
-# 对率回归预测函数  
-# 对率回归预测函数，支持多类分类
-def predict_logreg(inX, weights):
-    inX = np.insert(inX, 0, 1)  # 在特征前添加1作为偏置项
-    prob = 1 / (1 + np.exp(-np.dot(inX, weights)))
+        for i in range(0, m, batch_size):  # 分批处理  
+            X_batch = X_shuffled[i:i + batch_size]  
+            y_batch = y_shuffled[i:i + batch_size]  
+            
+            predictions = sigmoid(np.dot(X_batch, weights))  
+            gradient = np.dot(X_batch.T, (predictions - y_batch)) / len(y_batch)  
+            weights -= learning_rate * gradient  
 
-    if prob < 0.5:
-        return 0
-    elif prob >= 0.5 and prob < 1.0:
-        return 1
-    else:
-        return 2  # 确保返回3个类别中的一个
+    return weights  
+
+# 逻辑回归预测函数  
+def predict_logreg(inX, weights):  
+    inX = np.insert(inX, 0, 1)  # 在特征前添加1作为偏置项  
+    prob = sigmoid(np.dot(inX, weights))  
+
+    return 1 if prob >= 0.5 else 0  # 二分类处理  
 
 # 从文件中加载数据  
-def load_data(filepath):
-    data = pd.read_csv(filepath, header=None, na_values='?', delim_whitespace=True)
-    data.fillna(0, inplace=True)
-    X = data.iloc[:, :-1].to_numpy()  # 特征
-    y = data.iloc[:, -1].to_numpy()    # 标签
-    return X, y 
-# 准确率计算函数
-def calculate_accuracy(X, y, weights):
-    predictions = np.array([predict_logreg(x, weights) for x in X])
-    accuracy = np.mean(predictions == y)
-    return accuracy
+def load_data(filepath):  
+    data = pd.read_csv(filepath, header=None, na_values='?', delim_whitespace=True)  
+    data.fillna(0, inplace=True)  
+    X = data.iloc[:, :-1].to_numpy()  # 特征  
+    y = data.iloc[:, -1].to_numpy()    # 标签  
+    return X, y   
+
+# 准确率计算函数  
+def calculate_accuracy(X, y, weights):  
+    predictions = np.array([predict_logreg(x, weights) for x in X])  
+    accuracy = np.mean(predictions == y)  
+    return accuracy  
 
 if __name__ == "__main__":  
     # 加载训练集和测试集  
-    X_train, y_train = load_data("E:\\Edge站内文件下载\\病马数据集\\horse-colic.data")
-    X_test, y_test = load_data( "E:\\Edge站内文件下载\\病马数据集\\horse-colic.test")
+    X_train, y_train = load_data("E:\\Edge站内文件下载\\病马数据集\\horse-colic.data")  
+    X_test, y_test = load_data("E:\\Edge站内文件下载\\病马数据集\\horse-colic.test")  
     
-    # 训练对率回归模型 
-    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)
-  
+    # 数据标准化  
+    scaler = StandardScaler()  
+    X_train = scaler.fit_transform(X_train)  
+    X_test = scaler.transform(X_test)  
+
+    # 训练对率回归模型  
+    learning_rate = 0.01  
+    iterations = 1000  
+    batch_size = 32  # 随机梯度下降的小批量大小  
+    weights = train_logreg(X_train, y_train, learning_rate=learning_rate, iterations=iterations, batch_size=batch_size)  
+
     # 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]}")  
 
-
-    # 计算并输出模型的准确率
-    accuracy = calculate_accuracy(X_test, y_test, weights)
-    print(f"模型的准确率: {accuracy:.4f}")
\ No newline at end of file
+    # 计算并输出模型的准确率  
+    accuracy = calculate_accuracy(X_test, y_test, weights)  
+    print(f"模型的准确率: {accuracy:.4f}")  
\ No newline at end of file