更新 function.py

function.py

@@ -23,12 +23,12 @@ import numpy as np
 姓名请直接**填写中文**
 例如: name = "张三"
 """
-id = "202210423xxx"
+id = "202210423222"
-name = "test_name"
+name = "邓龙树"
 
 
 # 这里写自己的代码实现
-def train_svm(X, y, other_params="你自己设置一些其它参数"):
+def train_svm(X, y, learning_rate=0.001, iterations=1000):
     """
     支持向量机训练函数。
 
@@ -40,6 +40,20 @@ def train_svm(X, y, other_params="你自己设置一些其它参数"):
     Returns:
     - numpy array: 训练得到的权重。
     """
+    n_samples, n_features = X.shape
+    # 初始化权重向量
+    weights = np.zeros(n_features)
+    eta = 0.001  # 学习率
+    epochs = 1000  # 迭代次数
+
+    for _ in range(epochs):
+        for idx, x_i in enumerate(X):
+            condition = y[idx] * (np.dot(x_i, weights))
+            if condition < 1:
+                weights = weights + eta * ( (y[idx] * x_i) - (2  / (n_samples * epochs)) * weights)
+            else:
+                weights = weights + eta * (- (2  / (n_samples * epochs)) * weights)
+    return weights
 
 
 def predict_svm(inX, weights):
@@ -53,9 +67,10 @@ def predict_svm(inX, weights):
     Returns:
     - int: 预测的分类标签。
     """
+    prediction = np.sign(np.dot(inX, weights))
+    return prediction if prediction!= 0 else -1
 
 
-# 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**。
@@ -67,10 +82,22 @@ def load_data(filepath):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
-
+    data = []
+    labels = []
+    with open(filepath, 'r') as file:
+        lines = file.readlines()
+        for line in lines:
+            line = line.strip().split()
+            if '?' not in line:  # 只处理不包含缺失值的行
+                features = [float(x) for x in line[:-1]]
+                label = float(line[-1])
+                if label == 0:
+                    label = -1  # 将类别0转换为 -1 ，符合SVM二分类的约定
+                data.append(features)
+                labels.append(label)
+    return np.array(data), np.array(labels)
 
 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")
 
@@ -78,8 +105,11 @@ if __name__ == "__main__":
     X_test, y_test = load_data("./data/horse-colic.test")
 
     # 训练支持向量机模型
-    weights = train_svm(X_train, y_train, learning_rate=0.01, iterations=1000)
+    weights = train_svm(X_train, y_train, learning_rate=0.001, iterations=1000)
 
     # 测试单个数据
-    y_pred = predict_svm(X_test[11], weights)
+
+    for i in range(len(X_test)):
+        y_pred = predict_svm(X_test[i], weights)
+        print(f"预测结果: {y_pred}, 实际结果: {y_test[i]}")
     print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")