generated from LufsX/Challenge-SVM
This commit is contained in:
+33
-43
@@ -1,42 +1,24 @@
|
|||||||
id = "202210423230"
|
id = "202210423230"
|
||||||
name = "尹家立"
|
name = "尹家立"
|
||||||
|
|
||||||
# 这里写自己的代码实现
|
from sklearn.model_selection import GridSearchCV, train_test_split
|
||||||
import numpy as np
|
|
||||||
from sklearn.svm import SVC
|
from sklearn.svm import SVC
|
||||||
from sklearn.model_selection import train_test_split
|
|
||||||
from sklearn.metrics import classification_report, accuracy_score
|
from sklearn.metrics import classification_report, accuracy_score
|
||||||
from sklearn.preprocessing import StandardScaler
|
from sklearn.preprocessing import StandardScaler
|
||||||
|
import numpy as np
|
||||||
|
|
||||||
# 数据加载函数
|
# 数据加载函数保持不变
|
||||||
def load_data(filepath):
|
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。
|
|
||||||
|
|
||||||
Returns:
|
|
||||||
- np.array: 特征数据。
|
|
||||||
- np.array: 标签数据。
|
|
||||||
"""
|
|
||||||
data = []
|
data = []
|
||||||
labels = []
|
labels = []
|
||||||
|
|
||||||
with open(filepath, 'r') as file:
|
with open(filepath, 'r') as file:
|
||||||
for line in file:
|
for line in file:
|
||||||
fields = line.strip().split()
|
fields = line.strip().split()
|
||||||
|
|
||||||
# 处理缺失值,用0填充
|
|
||||||
fields = [0 if f == '?' else float(f) for f in fields]
|
fields = [0 if f == '?' else float(f) for f in fields]
|
||||||
|
|
||||||
# 标签是倒数第6列
|
|
||||||
label = int(fields[-6])
|
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:
|
if label == 1:
|
||||||
label = 0
|
label = 0
|
||||||
elif label == 2:
|
elif label == 2:
|
||||||
@@ -44,39 +26,48 @@ def load_data(filepath):
|
|||||||
elif label == 3:
|
elif label == 3:
|
||||||
label = 2
|
label = 2
|
||||||
else:
|
else:
|
||||||
print(f"无效标签,跳过此样本:{label}")
|
|
||||||
continue # 跳过无效标签
|
continue # 跳过无效标签
|
||||||
|
|
||||||
# 添加数据和标签
|
|
||||||
data.append(features)
|
data.append(features)
|
||||||
labels.append(label)
|
labels.append(label)
|
||||||
|
|
||||||
# 转换为numpy数组
|
|
||||||
data = np.array(data)
|
data = np.array(data)
|
||||||
labels = np.array(labels)
|
labels = np.array(labels)
|
||||||
|
|
||||||
return data, labels
|
return data, labels
|
||||||
|
|
||||||
|
# 训练支持向量机模型(调优)
|
||||||
def train_svm(X, y, other_params=None):
|
def train_svm(X, y, other_params=None):
|
||||||
"""
|
"""
|
||||||
支持向量机训练函数。
|
支持向量机训练函数,增加调优功能。
|
||||||
|
|
||||||
Args:
|
Args:
|
||||||
- X (numpy array): 特征数据。
|
- X (numpy array): 特征数据。
|
||||||
- y (numpy array): 标签数据。
|
- 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。
|
- other_params (str): 其他参数,暂时不使用。
|
||||||
|
|
||||||
Returns:
|
Returns:
|
||||||
- SVC: 训练好的SVM模型。
|
- SVC: 训练好的SVM模型。
|
||||||
"""
|
"""
|
||||||
# 使用高斯核(RBF核)训练SVM
|
# 参数网格
|
||||||
model = SVC(kernel='rbf', C=1.0, gamma='scale', random_state=42)
|
param_grid = {
|
||||||
model.fit(X, y)
|
'C': [0.1, 1, 10, 100],
|
||||||
|
'gamma': ['scale', 0.01, 0.1, 1],
|
||||||
|
'kernel': ['rbf', 'linear'],
|
||||||
|
'class_weight': [None, 'balanced']
|
||||||
|
}
|
||||||
|
|
||||||
return model
|
# 初始化SVM
|
||||||
|
svm = SVC(random_state=42)
|
||||||
|
|
||||||
|
# 网格搜索调参
|
||||||
|
grid_search = GridSearchCV(svm, param_grid, cv=5, scoring='accuracy', verbose=1, n_jobs=-1)
|
||||||
|
grid_search.fit(X, y)
|
||||||
|
|
||||||
|
# 输出最佳参数
|
||||||
|
print(f"最佳参数: {grid_search.best_params_}")
|
||||||
|
return grid_search.best_estimator_
|
||||||
|
|
||||||
|
# 单个样本预测函数保持不变
|
||||||
def predict_svm(inX, model):
|
def predict_svm(inX, model):
|
||||||
"""
|
"""
|
||||||
支持向量机预测函数。
|
支持向量机预测函数。
|
||||||
@@ -90,36 +81,35 @@ def predict_svm(inX, model):
|
|||||||
"""
|
"""
|
||||||
return model.predict(inX.reshape(1, -1))[0]
|
return model.predict(inX.reshape(1, -1))[0]
|
||||||
|
|
||||||
|
# 主程序
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
# 加载数据
|
# 加载数据
|
||||||
X_train, y_train = load_data("./data/horse-colic.data")
|
X, y = load_data("./data/horse-colic.data")
|
||||||
X_test, y_test = load_data("./data/horse-colic.test")
|
|
||||||
|
|
||||||
# 划分数据集
|
# 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)
|
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)
|
||||||
|
|
||||||
# 数据标准化
|
# 数据标准化
|
||||||
scaler = StandardScaler()
|
scaler = StandardScaler()
|
||||||
X_train = scaler.fit_transform(X_train)
|
X_train = scaler.fit_transform(X_train)
|
||||||
X_test = scaler.transform(X_test)
|
X_test = scaler.transform(X_test)
|
||||||
|
|
||||||
# 训练支持向量机模型
|
# 调优并训练SVM模型
|
||||||
print("正在训练支持向量机模型...")
|
print("正在调优支持向量机模型...")
|
||||||
svm_model = train_svm(X_train, y_train)
|
svm_model = train_svm(X_train, y_train)
|
||||||
|
|
||||||
# 预测测试集
|
# 测试集预测
|
||||||
y_pred = svm_model.predict(X_test)
|
y_pred = svm_model.predict(X_test)
|
||||||
|
|
||||||
# 输出评估结果
|
# 输出分类报告
|
||||||
print("\n分类报告:")
|
print("\n分类报告:")
|
||||||
print(classification_report(y_test, y_pred, target_names=["存活", "安乐死", "死亡"]))
|
print(classification_report(y_test, y_pred, target_names=["存活", "安乐死", "死亡"]))
|
||||||
|
|
||||||
# 输出准确率
|
# 输出测试集准确率
|
||||||
accuracy = accuracy_score(y_test, y_pred)
|
accuracy = accuracy_score(y_test, y_pred)
|
||||||
print(f"测试集准确率: {accuracy * 100:.2f}%")
|
print(f"测试集准确率: {accuracy * 100:.2f}%")
|
||||||
|
|
||||||
# 测试单个数据
|
# 测试单个样本
|
||||||
test_sample = X_test[11] # 选择第12个样本(从0开始计数)
|
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)
|
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]}")
|
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