fix: Step7 UI坍塌修复+EventBus打通 + DRY抽离spxy/ks + GridSearchCV→RandomizedSearchCV + smoke test死链修复
This commit is contained in:
@ -13,6 +13,7 @@ import sys
|
||||
import os
|
||||
|
||||
from src.preprocessing.spectral_Preprocessing import Preprocessing
|
||||
from src.core.utils.split_methods import spxy, ks
|
||||
|
||||
# try:
|
||||
# from modeling import WaterQualityModeling
|
||||
@ -138,159 +139,12 @@ class WaterQualityInference:
|
||||
return X_train, X_test, y_train, y_test
|
||||
|
||||
def spxy(self, data, label, test_size=0.2):
|
||||
"""
|
||||
SPXY算法划分数据集（考虑X和Y空间的距离）
|
||||
|
||||
Args:
|
||||
data: shape (n_samples, n_features)
|
||||
label: shape (n_samples, )
|
||||
test_size: 测试集比例，默认: 0.2
|
||||
|
||||
Returns:
|
||||
X_train: (n_samples, n_features)
|
||||
X_test: (n_samples, n_features)
|
||||
y_train: (n_samples, )
|
||||
y_test: (n_samples, )
|
||||
"""
|
||||
# 确保 data 和 label 是 NumPy 数组
|
||||
data = data.to_numpy() if isinstance(data, pd.DataFrame) else data
|
||||
label = label.to_numpy() if isinstance(label, pd.Series) else label
|
||||
|
||||
# 备份原始数据和标签
|
||||
x_backup = data
|
||||
y_backup = label
|
||||
|
||||
M = data.shape[0]
|
||||
N = round((1 - test_size) * M)
|
||||
samples = np.arange(M)
|
||||
|
||||
# 归一化标签数据
|
||||
label = (label - np.mean(label)) / np.std(label)
|
||||
D = np.zeros((M, M))
|
||||
Dy = np.zeros((M, M))
|
||||
|
||||
# 计算样本之间的距离
|
||||
for i in range(M - 1):
|
||||
xa = data[i, :]
|
||||
ya = label[i]
|
||||
for j in range((i + 1), M):
|
||||
xb = data[j, :]
|
||||
yb = label[j]
|
||||
D[i, j] = np.linalg.norm(xa - xb)
|
||||
Dy[i, j] = np.linalg.norm(ya - yb)
|
||||
|
||||
# 距离归一化
|
||||
Dmax = np.max(D)
|
||||
Dymax = np.max(Dy)
|
||||
D = D / Dmax + Dy / Dymax
|
||||
|
||||
# 找到最远的两个点
|
||||
maxD = D.max(axis=0)
|
||||
index_row = D.argmax(axis=0)
|
||||
index_column = maxD.argmax()
|
||||
|
||||
m = np.zeros(N, dtype=int)
|
||||
m[0] = index_row[index_column]
|
||||
m[1] = index_column
|
||||
|
||||
dminmax = np.zeros(N)
|
||||
dminmax[1] = D[m[0], m[1]]
|
||||
|
||||
# 根据距离选择训练集
|
||||
for i in range(2, N):
|
||||
pool = np.delete(samples, m[:i])
|
||||
dmin = np.zeros(M - i)
|
||||
for j in range(M - i):
|
||||
indexa = pool[j]
|
||||
d = np.zeros(i)
|
||||
for k in range(i):
|
||||
indexb = m[k]
|
||||
if indexa < indexb:
|
||||
d[k] = D[indexa, indexb]
|
||||
else:
|
||||
d[k] = D[indexb, indexa]
|
||||
dmin[j] = np.min(d)
|
||||
dminmax[i] = np.max(dmin)
|
||||
index = np.argmax(dmin)
|
||||
m[i] = pool[index]
|
||||
|
||||
m_complement = np.delete(samples, m)
|
||||
|
||||
# 划分训练集和测试集
|
||||
X_train = data[m, :]
|
||||
y_train = y_backup[m]
|
||||
X_test = data[m_complement, :]
|
||||
y_test = y_backup[m_complement]
|
||||
|
||||
return X_train, X_test, y_train, y_test
|
||||
"""SPXY算法划分数据集（委托至 src.core.utils.split_methods.spxy）"""
|
||||
return spxy(data, label, test_size=test_size)
|
||||
|
||||
def ks(self, data, label, test_size=0.2):
|
||||
"""
|
||||
Kennard-Stone算法划分数据集
|
||||
|
||||
Args:
|
||||
data: shape (n_samples, n_features)
|
||||
label: shape (n_sample, )
|
||||
test_size: 测试集比例，默认: 0.2
|
||||
|
||||
Returns:
|
||||
X_train: (n_samples, n_features)
|
||||
X_test: (n_samples, n_features)
|
||||
y_train: (n_samples, )
|
||||
y_test: (n_samples, )
|
||||
"""
|
||||
# 确保 data 和 label 是 NumPy 数组
|
||||
data = data.to_numpy() if isinstance(data, pd.DataFrame) else data
|
||||
label = label.to_numpy() if isinstance(label, pd.Series) else label
|
||||
|
||||
M = data.shape[0]
|
||||
N = round((1 - test_size) * M)
|
||||
samples = np.arange(M)
|
||||
|
||||
D = np.zeros((M, M))
|
||||
|
||||
for i in range((M - 1)):
|
||||
xa = data[i, :]
|
||||
for j in range((i + 1), M):
|
||||
xb = data[j, :]
|
||||
D[i, j] = np.linalg.norm(xa - xb)
|
||||
|
||||
maxD = np.max(D, axis=0)
|
||||
index_row = np.argmax(D, axis=0)
|
||||
index_column = np.argmax(maxD)
|
||||
|
||||
m = np.zeros(N)
|
||||
m[0] = np.array(index_row[index_column])
|
||||
m[1] = np.array(index_column)
|
||||
m = m.astype(int)
|
||||
dminmax = np.zeros(N)
|
||||
dminmax[1] = D[m[0], m[1]]
|
||||
|
||||
for i in range(2, N):
|
||||
pool = np.delete(samples, m[:i])
|
||||
dmin = np.zeros((M - i))
|
||||
for j in range((M - i)):
|
||||
indexa = pool[j]
|
||||
d = np.zeros(i)
|
||||
for k in range(i):
|
||||
indexb = m[k]
|
||||
if indexa < indexb:
|
||||
d[k] = D[indexa, indexb]
|
||||
else:
|
||||
d[k] = D[indexb, indexa]
|
||||
dmin[j] = np.min(d)
|
||||
dminmax[i] = np.max(dmin)
|
||||
index = np.argmax(dmin)
|
||||
m[i] = pool[index]
|
||||
|
||||
m_complement = np.delete(np.arange(data.shape[0]), m)
|
||||
|
||||
X_train = data[m, :]
|
||||
y_train = label[m]
|
||||
X_test = data[m_complement, :]
|
||||
y_test = label[m_complement]
|
||||
|
||||
return X_train, X_test, y_train, y_test
|
||||
"""Kennard-Stone算法划分数据集（委托至 src.core.utils.split_methods.ks）"""
|
||||
return ks(data, label, test_size=test_size)
|
||||
|
||||
def split_data(self, X: np.ndarray, y: pd.Series, method: str = "random",
|
||||
test_size: float = 0.2, random_state: int = 42) -> Tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray]:
|
||||
|
||||
Reference in New Issue
Block a user