generated from LufsX/Challenge-SVM
This commit is contained in:
+117
-121
@@ -1,161 +1,157 @@
|
||||
# function.py
|
||||
import numpy as np
|
||||
import numpy as np
|
||||
from sklearn.svm import SVC
|
||||
from sklearn.model_selection import train_test_split, cross_val_score
|
||||
from sklearn.metrics import classification_report, accuracy_score
|
||||
from sklearn.preprocessing import StandardScaler
|
||||
|
||||
"""
|
||||
挑战说明:
|
||||
- 自行编写实现数据加载与预测病马死亡的支持向量机算法。
|
||||
"""
|
||||
挑战说明:
|
||||
- 自行编写实现数据加载与预测病马死亡的支持向量机算法。
|
||||
|
||||
注意事项:
|
||||
- 在 function.py 中实现支持向量机算法。
|
||||
- 可以自行导入其他库，需要在 requirements.txt 添加依赖，若未在 requirements.txt 中添加使用到的依赖，则无法自动评测，成绩为零。
|
||||
- 自动评测脚本仅会加载 train_svm、predict_svm 和 load_data 函数，请勿修改函数名。
|
||||
注意事项:
|
||||
- 在 function.py 中实现支持向量机算法。
|
||||
- 可以自行导入其他库，需要在 requirements.txt 添加依赖，若未在 requirements.txt 中添加使用到的依赖，则无法自动评测，成绩为零。
|
||||
- 自动评测脚本仅会加载 train_svm、predict_svm 和 load_data 函数，请勿修改函数名。
|
||||
|
||||
测评环境:
|
||||
- CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz
|
||||
- OS: Ubuntu 22.04.4 LTS
|
||||
- Python: 3.10.12
|
||||
- numpy: 2.1.1
|
||||
"""
|
||||
测评环境:
|
||||
- CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz
|
||||
- OS: Ubuntu 22.04.4 LTS
|
||||
- Python: 3.10.12
|
||||
- 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 = "202210423206"
|
||||
name = "詹宇豪"
|
||||
|
||||
"""
|
||||
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 = "202210423206"
|
||||
name = "詹宇豪"
|
||||
# 这里写自己的代码实现
|
||||
|
||||
# 数据加载函数
|
||||
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**。
|
||||
|
||||
# 这里写自己的代码实现
|
||||
import numpy as np
|
||||
from sklearn.svm import SVC
|
||||
from sklearn.model_selection import train_test_split, cross_val_score
|
||||
from sklearn.metrics import classification_report, accuracy_score
|
||||
from sklearn.preprocessing import StandardScaler
|
||||
Args:
|
||||
- filepath (str): 数据文件路径。
|
||||
|
||||
# 数据加载函数
|
||||
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**。
|
||||
Returns:
|
||||
- np.array: 特征数据。
|
||||
- np.array: 标签数据。
|
||||
"""
|
||||
data = []
|
||||
labels = []
|
||||
|
||||
Args:
|
||||
- filepath (str): 数据文件路径。
|
||||
with open(filepath, 'r') as file:
|
||||
for line in file:
|
||||
fields = line.strip().split()
|
||||
|
||||
Returns:
|
||||
- np.array: 特征数据。
|
||||
- np.array: 标签数据。
|
||||
"""
|
||||
data = []
|
||||
labels = []
|
||||
# 处理缺失值，用0填充
|
||||
fields = [0 if f == '?' else float(f) for f in fields]
|
||||
|
||||
with open(filepath, 'r') as file:
|
||||
for line in file:
|
||||
fields = line.strip().split()
|
||||
|
||||
# 处理缺失值，用0填充
|
||||
fields = [0 if f == '?' else float(f) for f in fields]
|
||||
|
||||
# 标签是倒数第6列
|
||||
label = int(fields[-6])
|
||||
# 标签是倒数第6列
|
||||
label = int(fields[-6])
|
||||
|
||||
# 特征为其他列（不包含倒数第6列标签）
|
||||
features = np.array(fields[: -6] + fields[-5:], dtype=float)
|
||||
features = np.array(fields[: -6] + fields[-5:], dtype=float)
|
||||
|
||||
# 标签映射：将 1->0, 2->1, 3->2
|
||||
if label == 1:
|
||||
label = 0
|
||||
elif label == 2:
|
||||
label = 1
|
||||
elif label == 3:
|
||||
label = 2
|
||||
else:
|
||||
print(f"无效标签，跳过此样本：{label}")
|
||||
continue # 跳过无效标签
|
||||
# 标签映射：将 1->0, 2->1, 3->2
|
||||
if label == 1:
|
||||
label = 0
|
||||
elif label == 2:
|
||||
label = 1
|
||||
elif label == 3:
|
||||
label = 2
|
||||
else:
|
||||
print(f"无效标签，跳过此样本：{label}")
|
||||
continue # 跳过无效标签
|
||||
|
||||
# 添加数据和标签
|
||||
data.append(features)
|
||||
labels.append(label)
|
||||
# 添加数据和标签
|
||||
data.append(features)
|
||||
labels.append(label)
|
||||
|
||||
# 转换为numpy数组
|
||||
data = np.array(data)
|
||||
labels = np.array(labels)
|
||||
# 转换为numpy数组
|
||||
data = np.array(data)
|
||||
labels = np.array(labels)
|
||||
|
||||
return data, labels
|
||||
return data, labels
|
||||
|
||||
|
||||
def train_svm(X, y, other_params=None):
|
||||
"""
|
||||
支持向量机训练函数。
|
||||
def train_svm(X, y, other_params=None):
|
||||
"""
|
||||
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。
|
||||
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。
|
||||
|
||||
Returns:
|
||||
- SVC: 训练好的SVM模型。
|
||||
"""
|
||||
Returns:
|
||||
- SVC: 训练好的SVM模型。
|
||||
"""
|
||||
# 使用高斯核（RBF核）训练SVM
|
||||
model = SVC(kernel='rbf', C=1.0, gamma='scale', random_state=42)
|
||||
model.fit(X, y)
|
||||
model = SVC(kernel='rbf', C=1.0, gamma='scale', random_state=42)
|
||||
model.fit(X, y)
|
||||
|
||||
return model
|
||||
return model
|
||||
|
||||
|
||||
def predict_svm(inX, model):
|
||||
"""
|
||||
支持向量机预测函数。
|
||||
def predict_svm(inX, model):
|
||||
"""
|
||||
支持向量机预测函数。
|
||||
|
||||
Args:
|
||||
- inX (numpy array): 输入待分类的样本。
|
||||
- model (SVC): 训练得到的支持向量机模型。
|
||||
Args:
|
||||
- inX (numpy array): 输入待分类的样本。
|
||||
- model (SVC): 训练得到的支持向量机模型。
|
||||
|
||||
Returns:
|
||||
- int: 预测的分类标签。
|
||||
"""
|
||||
return model.predict(inX.reshape(1, -1))[0]
|
||||
Returns:
|
||||
- int: 预测的分类标签。
|
||||
"""
|
||||
return model.predict(inX.reshape(1, -1))[0]
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 加载数据
|
||||
X_train, y_train = load_data("./data/horse-colic.data")
|
||||
X_test, y_test = load_data("./data/horse-colic.test")
|
||||
if __name__ == "__main__":
|
||||
# 加载数据
|
||||
X_train, y_train = load_data("./data/horse-colic.data")
|
||||
X_test, y_test = load_data("./data/horse-colic.test")
|
||||
|
||||
# 划分数据集
|
||||
X_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.2, random_state=42, stratify=y_train)
|
||||
# 划分数据集
|
||||
X_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.2, random_state=42, stratify=y_train)
|
||||
|
||||
# 数据标准化
|
||||
scaler = StandardScaler()
|
||||
X_train = scaler.fit_transform(X_train)
|
||||
X_test = scaler.transform(X_test)
|
||||
# 数据标准化
|
||||
scaler = StandardScaler()
|
||||
X_train = scaler.fit_transform(X_train)
|
||||
X_test = scaler.transform(X_test)
|
||||
|
||||
# 交叉验证评估
|
||||
print("正在进行交叉验证评估...")
|
||||
# 交叉验证评估
|
||||
print("正在进行交叉验证评估...")
|
||||
|
||||
# 使用交叉验证计算准确率，设置10折交叉验证
|
||||
svm_model = SVC(kernel='rbf', C=1.0, gamma='scale', random_state=41)
|
||||
cv_scores = cross_val_score(svm_model, X_train, y_train, cv=10, scoring='accuracy')
|
||||
# 使用交叉验证计算准确率，设置10折交叉验证
|
||||
svm_model = SVC(kernel='rbf', C=1.0, gamma='scale', random_state=41)
|
||||
cv_scores = cross_val_score(svm_model, X_train, y_train, cv=10, scoring='accuracy')
|
||||
|
||||
# 输出交叉验证的准确率
|
||||
print(f"交叉验证准确率: {cv_scores.mean():.4f} ± {cv_scores.std():.4f}")
|
||||
# 输出交叉验证的准确率
|
||||
print(f"交叉验证准确率: {cv_scores.mean():.4f} ± {cv_scores.std():.4f}")
|
||||
|
||||
# 训练支持向量机模型
|
||||
print("正在训练支持向量机模型...")
|
||||
svm_model.fit(X_train, y_train)
|
||||
# 训练支持向量机模型
|
||||
print("正在训练支持向量机模型...")
|
||||
svm_model.fit(X_train, y_train)
|
||||
|
||||
# 预测测试集
|
||||
y_pred = svm_model.predict(X_test)
|
||||
# 预测测试集
|
||||
y_pred = svm_model.predict(X_test)
|
||||
|
||||
# 输出评估结果
|
||||
print("\n分类报告:")
|
||||
print(classification_report(y_test, y_pred, target_names=["存活", "安乐死", "死亡"]))
|
||||
# 输出评估结果
|
||||
print("\n分类报告:")
|
||||
print(classification_report(y_test, y_pred, target_names=["存活", "安乐死", "死亡"]))
|
||||
|
||||
# 输出准确率
|
||||
accuracy = accuracy_score(y_test, y_pred)
|
||||
print(f"测试集准确率: {accuracy * 100:.2f}%")
|
||||
# 输出准确率
|
||||
accuracy = accuracy_score(y_test, y_pred)
|
||||
print(f"测试集准确率: {accuracy * 100:.2f}%")
|
||||
|
||||
# 测试单个数据
|
||||
# 测试单个数据
|
||||
test_sample = X_test[11] # 选择第12个样本（从0开始计数）
|
||||
y_pred_single = predict_svm(test_sample, svm_model)
|
||||
print(f"\n单个样本预测结果: {y_pred_single}, 实际结果: {y_test[11]}")
|
||||
y_pred_single = predict_svm(test_sample, svm_model)
|
||||
print(f"\n单个样本预测结果: {y_pred_single}, 实际结果: {y_test[11]}")
|
||||
Reference in New Issue
Block a user