generated from LufsX/Challenge-SVM
This commit is contained in:
+89
-96
@@ -1,132 +1,125 @@
|
||||
# function.py
|
||||
import numpy as np
|
||||
data_columns=[]
|
||||
id = "202210423230"
|
||||
name = "尹家立"
|
||||
|
||||
import pandas as pd
|
||||
# 这里写自己的代码实现
|
||||
import numpy as np
|
||||
from sklearn.impute import SimpleImputer
|
||||
from sklearn.svm import SVC
|
||||
from sklearn.model_selection import train_test_split
|
||||
from sklearn.metrics import classification_report, accuracy_score
|
||||
from sklearn.preprocessing import StandardScaler
|
||||
|
||||
def load_data(data_path):
|
||||
NAN_THRES=0.5
|
||||
# 读取数据并指定列
|
||||
horse_data = pd.read_csv(data_path, header=None, sep=r"\s+")
|
||||
horse_data = horse_data.loc[:, :22] # 只取到死亡情况（前23列，索引0-22）
|
||||
horse_data.columns = data_columns # 指定列名
|
||||
horse_data = horse_data.replace("?", float('NaN')) # 替换缺失值标记
|
||||
# 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**。
|
||||
|
||||
# 删除无关或缺失值过多的特征
|
||||
col_del = ["Hospital Number"]
|
||||
for col in horse_data.columns:
|
||||
if horse_data[col].isna().sum() > len(horse_data) * NAN_THRES and col not in col_del:
|
||||
col_del.append(col)
|
||||
horse_data = horse_data.drop(columns=col_del)
|
||||
Args:
|
||||
- directory (str): 数据文件路径。
|
||||
|
||||
# 删除标签缺失的样本
|
||||
horse_data = horse_data.dropna(subset=['outcome']).reset_index(drop=True)
|
||||
|
||||
# 分离特征和标签
|
||||
x_data = horse_data.drop(columns=['outcome'])
|
||||
y_data = horse_data[['outcome']]
|
||||
|
||||
# 标签：保留三分类
|
||||
y_data['outcome'] = pd.to_numeric(y_data['outcome'], errors='coerce').astype('int32')
|
||||
|
||||
# 分离离散和连续特征
|
||||
x_discrete = x_data[list(set(columns_discrete) - set(col_del))]
|
||||
x_continue = x_data.drop(columns=x_discrete.columns)
|
||||
|
||||
# 离散特征 one-hot 编码
|
||||
for col in col_oneHot:
|
||||
if col in x_discrete.columns:
|
||||
column_onehot = pd.get_dummies(x_discrete[col], prefix=col)
|
||||
x_discrete = x_discrete.drop(columns=col)
|
||||
x_discrete = pd.concat([x_discrete, column_onehot], axis=1)
|
||||
|
||||
# 用众数填补离散特征缺失值
|
||||
imp = SimpleImputer(strategy='most_frequent')
|
||||
x_discrete = pd.DataFrame(imp.fit_transform(x_discrete), columns=x_discrete.columns)
|
||||
x_discrete = x_discrete.astype('int32')
|
||||
|
||||
# 用均值填补连续特征缺失值并归一化
|
||||
for col in x_continue.columns:
|
||||
x_continue[col] = pd.to_numeric(x_continue[col], errors='coerce').astype("float64")
|
||||
x_continue[col] = x_continue[col].fillna(x_continue[col].mean())
|
||||
x_continue = (x_continue - x_continue.mean()) / (x_continue.max() - x_continue.min())
|
||||
|
||||
# 合并特征和标签
|
||||
horse_data = pd.concat([x_discrete, x_continue, y_data], axis=1)
|
||||
horse_data = horse_data.sort_index(axis=1) # 排序列名，确保验证集和训练集一致
|
||||
|
||||
# 最终返回特征和标签
|
||||
return horse_data.drop(columns=['outcome']).values, horse_data['outcome'].values
|
||||
Returns:
|
||||
- np.array: 特征数据。
|
||||
- np.array: 标签数据。
|
||||
"""
|
||||
data = []
|
||||
labels = []
|
||||
|
||||
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])
|
||||
|
||||
# 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)
|
||||
|
||||
# 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)
|
||||
|
||||
# 转换为numpy数组
|
||||
data = np.array(data)
|
||||
labels = np.array(labels)
|
||||
|
||||
return data, labels
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
def train_svm(X, y, learning_rate=0.01, iterations=1000):
|
||||
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。
|
||||
- learning_rate (float): 学习率 默认值为0.01。
|
||||
- iterations (int): 训练迭代次数 默认值为1000。
|
||||
- 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:
|
||||
- numpy array: 训练得到的权重。
|
||||
- SVC: 训练好的SVM模型。
|
||||
"""
|
||||
m, n = X.shape
|
||||
weights = np.zeros(n)
|
||||
|
||||
for _ in range(iterations):
|
||||
for i in range(m):
|
||||
if y[i] * np.dot(X[i], weights) < 1:
|
||||
weights += learning_rate * (y[i] * X[i] + (-2 * (1 / iterations) * weights))
|
||||
else:
|
||||
weights += learning_rate * (-2 * (1 / iterations) * weights)
|
||||
return weights
|
||||
# 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)
|
||||
|
||||
return model
|
||||
|
||||
|
||||
def predict_svm(inX, weights):
|
||||
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。
|
||||
- weights (numpy array): 训练得到的权重。
|
||||
- model (SVC): 训练得到的支持向量机模型。
|
||||
|
||||
Returns:
|
||||
- int: 预测的分类标签。
|
||||
"""
|
||||
return 1 if np.dot(inX, weights) >= 0 else -1
|
||||
return model.predict(inX.reshape(1, -1))[0]
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 取得列信息
|
||||
with open("./data/horse-colic.names", 'r', encoding='utf-8') as f:
|
||||
data_names = f.read()
|
||||
data_columns = re.findall(r'(?<=[0-9]:).*', data_names)
|
||||
data_columns = [col.strip() for col in data_columns[:-3]]
|
||||
data_columns
|
||||
|
||||
# 离散列
|
||||
columns_discrete = ['surgery?', 'Age', 'temperature of extremities', 'peripheral pulse',
|
||||
'mucous membranes', 'capillary refill time', 'pain - a subjective judgement of the horse\'s pain level', 'peristalsis',
|
||||
'abdominal distension', 'nasogastric tube', 'nasogastric reflux', 'rectal examination - feces', 'abdomen', 'abdominocentesis appearance']
|
||||
|
||||
# 独热编码列
|
||||
col_oneHot = ['surgery?', 'Age']
|
||||
# 加载训练集
|
||||
# 加载数据
|
||||
X_train, y_train = load_data("./data/horse-colic.data")
|
||||
# 加载测试集
|
||||
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)
|
||||
|
||||
# 数据标准化
|
||||
scaler = StandardScaler()
|
||||
X_train = scaler.fit_transform(X_train)
|
||||
X_test = scaler.transform(X_test)
|
||||
|
||||
# 训练支持向量机模型
|
||||
weights = train_svm(X_train, y_train, learning_rate=0.01, iterations=1000)
|
||||
print("正在训练支持向量机模型...")
|
||||
svm_model = train_svm(X_train, y_train)
|
||||
|
||||
# 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
|
||||
y_pred = predict_svm(X_test[11], weights)
|
||||
print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
|
||||
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]}")
|
||||
|
||||
Reference in New Issue
Block a user