'1224'

UQPyL/__init__.py

@@ -1,6 +1,6 @@
 from . import problems, surrogates, optimization, sensibility, DoE, utility
 
-__version__ = "2.0.10"
+__version__ = "2.0.11"
 __author__ = "wmtSky"
 
 __all__=[

UQPyL/optimization/__init__.py

@@ -1,4 +1,4 @@
-from .single_objective import GA, PSO, CSA, DE, SCE_UA, ML_SCE_UA, ASMO, ABC, Binary_GA, EGO
+from .single_objective import GA, PSO, CSA, DE, SCE_UA, ML_SCE_UA, ASMO, ABC, EGO
 from .multi_objective import NSGAII, MOEAD, MOASMO, RVEA
 # from .mathematics import Boxmin, Adam
 from .algorithmABC import Algorithm

UQPyL/optimization/single_objective/__init__.py

@@ -7,5 +7,4 @@
 from .csa import CSA
 from .asmo import ASMO
 from .abc import ABC
-from .ego import EGO
-from ._binary_ga import Binary_GA
+from .ego import EGO

UQPyL/sensibility/delta_test.py

@@ -85,7 +85,9 @@ def analyze(self, X: np.ndarray=None, Y: np.ndarray=None, verbose: bool=False) -
         X, Y=self.__check_and_scale_xy__(X, Y)
 
         n_input=self.n_input
+
         ##main process
+
         self.X_=X; self.Y_=Y
         optimizer=Binary_GA(self._cal_delta, self.n_input, population_size=n_input*2)
         best_paras, self.best_value, history_paras, _=optimizer.run()
@@ -95,6 +97,7 @@ def analyze(self, X: np.ndarray=None, Y: np.ndarray=None, verbose: bool=False) -
         HSP_paras=[self.labels[index] for index, value in enumerate(best_paras) if value==1]
 
         Si={'S1': S1_score, 'HSP':HSP_paras}
+
         self.Si=Si
 
         if verbose:

UQPyL/sensibility/mars_sa.py

@@ -1,7 +1,7 @@
 import numpy as np
 from typing import Optional, Tuple
 
-from ..surrogates import MARS, Surrogate
+from ..surrogates import MARS
 from ..utility import MinMaxScaler, Scaler
 from ..problems import ProblemABC as Problem
 from ..DoE import LHS, Sampler

UQPyL/surrogates/gp/gaussian_process.py

@@ -3,7 +3,7 @@
 from typing import Tuple, Optional, Literal
 
 from .kernel import BaseKernel, RBF
-from ..utility.boxmin import Boxmin
+from ..util.boxmin import Boxmin
 from ...problems import PracticalProblem
 from ..surrogateABC import Surrogate
 from ...optimization import Algorithm

UQPyL/surrogates/kriging/kriging.py

@@ -5,7 +5,7 @@
 
 
 from .kernel import BaseKernel, Guass
-from ..utility.boxmin import Boxmin
+from ..util.boxmin import Boxmin
 from ..surrogateABC import Surrogate
 from ...optimization.algorithmABC import Algorithm
 from ...optimization.single_objective import GA

UQPyL/surrogates/util/__init__.py

@@ -1,9 +0,0 @@
-'''
-Author: smasky (Mengtian Wu Hohai Unversity)
-Date: 2024-12-24 09:35:39
-LastEditTime: 2024-12-24 09:35:55
-LastEditors: smasky
-Description: 
-FilePath: \UQPyL\UQPyL\surrogates\utility\__init__.py
-You will never know unless you try
-'''

examples/example_surrogate.py

@@ -22,31 +22,31 @@
 # np.savetxt('xTrain.txt', xTrain); np.savetxt('yTrain.txt', yTrain.reshape(-1, 1))
 
 #-------------------Kriging----------------------------#
-# from UQPyL.surrogates.kriging import KRG
-# from UQPyL.surrogates.kriging.kernel import Guass, Cubic, Exp
-# from UQPyL.utility.scalers import MinMaxScaler, StandardScaler
-# from UQPyL.optimization import GA
-# from time import time
+from UQPyL.surrogates.kriging import KRG
+from UQPyL.surrogates.kriging.kernel import Guass, Cubic, Exp
+from UQPyL.utility.scalers import MinMaxScaler, StandardScaler
+from UQPyL.optimization import GA
+from time import time
 
-# kernel=Guass(theta=1.0, heterogeneous=True)
+kernel=Guass(theta=1.0, heterogeneous=True)
 # kernel=Cubic(theta=1.0, heterogeneous=True)
 # kernel=Exp(theta=1.0, heterogeneous=True)
 
-# optimizer = GA(maxFEs=1000, nPop=50, saveFlag=False, logFlag=False, verboseFreq=1)
+optimizer = GA(maxFEs=1000, nPop=50, saveFlag=False, logFlag=False, verboseFreq=1)
 
-#use Boxmin
-# krg=KRG(scalers=(MinMaxScaler(0,1), MinMaxScaler(0,1)), kernel=kernel, n_restart_optimize=0)
-#use optimization
-#krg=KRG(scalers=(MinMaxScaler(0,1), MinMaxScaler(0,1)), kernel=kernel, optimizer=optimizer, n_restart_optimize=0, fitMode='likelihood')
+# use Boxmin
+krg=KRG(scalers=(MinMaxScaler(0,1), MinMaxScaler(0,1)), kernel=kernel, n_restart_optimize=0)
+# use optimization
+# krg=KRG(scalers=(MinMaxScaler(0,1), MinMaxScaler(0,1)), kernel=kernel, optimizer=optimizer, n_restart_optimize=0, fitMode='likelihood')
 # krg.fit(xTrain, yTrain)
 
-#use autoTuner
-# tuner=autoTuner(optimizer=optimizer, model=krg)
-# paraList=tuner.getParaList() 
-# tuner.tune(xTrain, yTrain, paraList, ratio=10)
-# yPred=krg.predict(xTest)
-# value=r_square(yTest, yPred)
-# print(value)
+# use autoTuner
+tuner=autoTuner(optimizer=optimizer, model=krg)
+paraList=tuner.getParaList() 
+tuner.opTune(xTrain, yTrain, paraList, ratio=10)
+yPred=krg.predict(xTest)
+value=r_square(yTest, yPred)
+print(value)
 
 #-------------------Gaussian Process---------------------#
 # from UQPyL.surrogates.gp import GPR

pyproject.toml

@@ -12,7 +12,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "UQPyL"
-version = "2.0.10"
+version = "2.0.11"
 authors = [
     {name = "wmtSky", email = "wmtsky@hhu.edu.cn"}
 ]

setup.py

@@ -32,7 +32,7 @@
 setup(
     name="UQPyL",
     author="wmtSky",
-    version="2.0.10",
+    version="2.0.11",
     author_email="wmtsky@hhu.edu.cn",
     ext_modules=extensions,  
     packages=find_packages(),