更新 function.py

function.py

@@ -28,7 +28,7 @@ name = "董秋"
 
 
 # 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=0.01, iterations=1000):
     """
     支持向量机训练函数。
 
@@ -41,21 +41,19 @@ def train_svm(X, y, other_params="你自己设置一些其它参数"):
     - numpy array: 训练得到的权重。
     """
     n_samples, n_features = X.shape
-    weights = np.zeros(n_features)  # 初始化权重
-    bias = 0  # 初始化偏置
+    n_classes = len(np.unique(y))
+    weights = np.zeros((n_classes, n_features))
     
     for _ in range(iterations):
         for idx, x_i in enumerate(X):
-            condition = y[idx] * (np.dot(x_i, weights) + bias) >= 1
-            if condition:
-                # 更新公式，不需要正则化项
-                weights -= learning_rate * (2 * lambda_param * weights)
-            else:
-                # 更新公式，包括误分类损失
-                weights -= learning_rate * (2 * lambda_param * weights - np.dot(x_i, y[idx]))
-                bias -= learning_rate * y[idx]
+            for c in range(n_classes):
+                y_i = 1 if y[idx] == c else -1
+                if y_i * (np.dot(weights[c], x_i)) < 1:
+                    weights[c] += learning_rate * (y_i * x_i - (2 * 1/iterations) * weights[c])
+                else:
+                    weights[c] -= learning_rate * (2 * 1/iterations) * weights[c]
     
-    return np.append(weights, bias)  # 将偏置合并到权重中
+    return weights
 
 def predict_svm(inX, weights):
     """
@@ -68,10 +66,8 @@ def predict_svm(inX, weights):
     Returns:
     - int: 预测的分类标签。
     """
-    w = weights[:-1]  # 分离权重和偏置
-    b = weights[-1]
-    linear_output = np.dot(inX, w) + b
-    return 1 if linear_output >= 0 else -1
+   scores = [np.dot(w, inX) for w in weights]
+    return np.argmax(scores)
 
 # 这里也写自己的代码实现
 def load_data(filepath):
@@ -87,27 +83,23 @@ def load_data(filepath):
     """
     data = []
     labels = []
-
     with open(filepath, 'r') as file:
         for line in file:
-            values = line.strip().split()
-            # 将缺失值用0填充，并将所有数据转换为浮点数
-            features = [float(v) if v != '?' else 0.0 for v in values[:-1]]
-            label = values[-1]  # 假设最后一列是标签列
-            
-            # 根据标签值进行三分类的标签转换
-            if label == '1':
-                labels.append(0)  # 存活
-            elif label == '2':
-                labels.append(1)  # 死亡
-            elif label == '3':
-                labels.append(2)  # 安乐死
-            
-            data.append(features)
-
-    X = np.array(data)
-    y = np.array(labels)
-    return X, y
+            line = line.strip().split()
+            if len(line) > 1:
+                label = line[0]
+                if label == "死亡":
+                    label = 0
+                elif label == "安乐死":
+                    label = 1
+                elif label == "存活":
+                    label = 2
+                labels.append(label)
+                
+                features = [float(x) if x != '?' else 0.0 for x in line[1:]]
+                data.append(features)
+    
+    return np.array(data), np.array(labels)
 
 
 if __name__ == "__main__":