generated from LufsX/Challenge-SVM
This commit is contained in:
+43
-9
@@ -17,42 +17,64 @@ import numpy as np
|
||||
- numpy: 2.1.1
|
||||
"""
|
||||
|
||||
|
||||
"""
|
||||
请在这里填写学号和姓名,不填写即成绩无效。
|
||||
姓名请直接**填写中文**
|
||||
例如: name = "张三"
|
||||
"""
|
||||
id = "202210423xxx"
|
||||
name = "test_name"
|
||||
id = "202210423217"
|
||||
name = "吴俊煯"
|
||||
|
||||
|
||||
# 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。
|
||||
|
||||
Args:
|
||||
- X (numpy array): 特征数据。
|
||||
- y (numpy array): 标签数据。
|
||||
- other_params (str): 其它参数,可选设置。若需设置其它参数,必须设置其默认值,否则将**无法通过**自动评测,**成绩为零**。
|
||||
- learning_rate (float): 学习率。
|
||||
- iterations (int): 迭代次数。
|
||||
|
||||
Returns:
|
||||
- numpy array: 训练得到的权重。
|
||||
"""
|
||||
n_samples, n_features = X.shape
|
||||
# 初始化权重和偏置
|
||||
weights = np.zeros(n_features)
|
||||
bias = 0
|
||||
|
||||
# 训练过程
|
||||
for _ in range(iterations):
|
||||
for idx, x_i in enumerate(X):
|
||||
# 计算预测值
|
||||
linear_output = np.dot(x_i, weights) + bias
|
||||
# 计算预测标签
|
||||
y_predicted = np.sign(linear_output)
|
||||
|
||||
# 更新权重和偏置
|
||||
if y_predicted != y[idx]:
|
||||
weights += learning_rate * (y[idx] * x_i)
|
||||
bias += learning_rate * y[idx]
|
||||
|
||||
return weights, bias
|
||||
|
||||
|
||||
def predict_svm(inX, weights):
|
||||
def predict_svm(inX, weights, bias):
|
||||
"""
|
||||
支持向量机预测函数。
|
||||
|
||||
Args:
|
||||
- inX (numpy array): 输入待分类的样本。
|
||||
- weights (numpy array): 训练得到的权重。
|
||||
- bias (float): 训练得到的偏置。
|
||||
|
||||
Returns:
|
||||
- int: 预测的分类标签。
|
||||
"""
|
||||
linear_output = np.dot(inX, weights) + bias
|
||||
return 1 if linear_output >= 0 else -1
|
||||
|
||||
|
||||
# 这里也写自己的代码实现
|
||||
@@ -61,12 +83,19 @@ 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。
|
||||
- filepath (str): 数据文件路径。
|
||||
|
||||
Returns:
|
||||
- np.array: 特征数据。
|
||||
- np.array: 标签数据。
|
||||
"""
|
||||
data = np.loadtxt(filepath, delimiter=',', dtype=str)
|
||||
X = data[:, :-1].astype(float) # 特征数据
|
||||
y = data[:, -1] # 标签数据
|
||||
|
||||
# 将标签转换为 -1 和 1
|
||||
y = np.where(y == '1', 1, -1) # 假设标签为 '1' 表示死亡,其他为存活
|
||||
return X, y
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
@@ -78,8 +107,13 @@ 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, 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)
|
||||
y_pred = predict_svm(X_test[11], weights, bias)
|
||||
print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
|
||||
|
||||
# 计算准确率
|
||||
correct_predictions = sum(predict_svm(x, weights, bias) == y for x, y in zip(X_test, y_test))
|
||||
accuracy = correct_predictions / len(y_test)
|
||||
print(f"测试集准确率: {accuracy * 100:.2f}%")
|
||||
Reference in New Issue
Block a user