更新 function.py

function.py

@@ -4,12 +4,18 @@ id = "202210423201"
 name = "陈瑞琪祥"
 
 def load_data(filepath):
-    # 使用numpy的genfromtxt函数加载数据，并处理缺失值
-    data = np.genfromtxt(filepath, delimiter=',', filling_values=np.nan)
-    # 将字符串'?'替换为nan
-    data = np.where(data == '?', np.nan, data)
-    # 将数据转换为float类型
-    data = data.astype(float)
+    try:
+        # 使用numpy的genfromtxt函数加载数据，并处理缺失值
+        data = np.genfromtxt(filepath, delimiter=',', dtype=float, filling_values=np.nan)
+    except ValueError:
+        print("数据加载错误，可能是由于数据格式不正确。")
+        return None, None
+
+    # 检查数据是否为二维数组
+    if data.ndim != 2:
+        print("数据不是二维数组，无法继续处理。")
+        return None, None
+
     # 分离特征和标签
     X = data[:, :-1]
     y = data[:, -1].astype(int)
@@ -29,9 +35,6 @@ def train_svm(X, y, learning_rate=0.01, iterations=1000, regularization=1.0):
                 weights -= learning_rate * (2 * regularization * weights - np.dot(x_i, y[idx]))
                 bias -= learning_rate * y[idx]
 
-        # Update bias
-        bias -= learning_rate * np.sum(y * (1 - y * (np.dot(X, weights) - bias)))
-
     return weights, bias
 
 def predict_svm(inX, weights, bias):
@@ -40,14 +43,18 @@ def predict_svm(inX, weights, bias):
 if __name__ == "__main__":
     # 加载训练集
     X_train, y_train = load_data("./data/horse-colic.data")
+    if X_train is None or y_train is None:
+        print("训练数据加载失败。")
+    else:
+        # 加载测试集
+        X_test, y_test = load_data("./data/horse-colic.test")
+        if X_test is None or y_test is None:
+            print("测试数据加载失败。")
+        else:
+            # 训练支持向量机模型
+            weights, bias = train_svm(X_train, y_train, learning_rate=0.01, iterations=1000)
 
-    # 加载测试集
-    X_test, y_test = load_data("./data/horse-colic.test")
-
-    # 训练支持向量机模型
-    weights, bias = train_svm(X_train, y_train, learning_rate=0.01, iterations=1000)
-
-    # 测试单个数据
-    y_pred = predict_svm(X_test[11], weights, bias)
-    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
+            # 测试单个数据
+            y_pred = predict_svm(X_test[11], weights, bias)
+            print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")