Merge branch 'main' of https://github.com/Bin-Cao/Bgolearn

.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+Test/
+.Python
+.DS_Store
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

Bgolearn/BGOmin.py

@@ -1,7 +1,8 @@
-import copy
+import copy, os
 import warnings
 import numpy as np
 from scipy.stats import norm
+import multiprocess as mp
 
 # cal norm prob.
 def norm_des(x):
@@ -24,6 +25,7 @@ def __init__(self,Kriging_model,data_matrix, Measured_response, virtual_samples,
         self.ret_noise = ret_noise
         self.row_features = row_features
         warnings.filterwarnings('ignore')
+        os.environ["PYTHONWARNINGS"] = "ignore"
 
 
 
@@ -299,36 +301,50 @@ def PES(self, sam_num = 500):
             print('The input para. opt_num must be an int')
         return PES_list,np.array(return_x)
 
-
-    def Knowledge_G(self,MC_num = 50):
+    def __Knowledge_G_per_sample(self, func_bytes:bytes, MC_num:int, virtual_samples, v_sample_mean, v_sample_std, archive_sample_x, archive_sample_y, x_value, fea_num, ret_noise):
+        MC_batch_min = 0
+        for _ in range(MC_num):
+            # generate y value
+            y_value = np.random.normal(loc = v_sample_mean, scale = v_sample_std)
+            # update the sample x and sample y
+            archive_sample_x[-len(x_value):] = x_value
+            if isinstance(y_value, float):
+                archive_sample_y[-1] = y_value
+            elif isinstance(y_value, np.ndarray):
+                archive_sample_y[-len(y_value):] = y_value
+            # calculate the post mean
+            if ret_noise == True:
+                # return a callable model
+                post_mean, _ = func_bytes.fit_pre(archive_sample_x.reshape(-1, fea_num), archive_sample_y, virtual_samples, v_sample_std)
+            else:
+                post_mean, _ = func_bytes.fit_pre(archive_sample_x.reshape(-1, fea_num), archive_sample_y, virtual_samples)
+            MC_batch_min += post_mean.min()
+        return MC_batch_min
+
+    def Knowledge_G(self,MC_num = 50, Proc_num:int=None):
         """
         :param MC_num: number of Monte carol,  default 50
+        :param Proc_num: number of Processor,  default None (0)
         """
         current_min = self.virtual_samples_mean.min()
         KD_list = []
-        vir_num = len(self.virtual_samples)
-        for i in range(vir_num):
-            x_value = self.virtual_samples[i]
-            MC_batch_min = 0
-            for j in range(MC_num):
-                y_value = np.random.normal(loc = self.virtual_samples_mean[i],scale = self.virtual_samples_std[i])
-                archive_sample_x = copy.deepcopy(self.data_matrix)
-                archive_sample_y = copy.deepcopy(self.Measured_response)
-
-                archive_sample_x = np.append(archive_sample_x, x_value)
-                archive_sample_y = np.append(archive_sample_y, y_value)
-                fea_num = len(self.data_matrix[0])
-                if self.ret_noise == True:
-                    # return a callable model
-                    post_mean, _ = self.Kriging_model().fit_pre(archive_sample_x.reshape(-1, fea_num),archive_sample_y,self.virtual_samples,self.virtual_samples_std[i])
-                else:
-                    post_mean, _ = self.Kriging_model().fit_pre(archive_sample_x.reshape(-1, fea_num),archive_sample_y,self.virtual_samples)
-                MC_batch_min += post_mean.min()
-                MC_times = i * MC_num + j+1
-                if MC_times % 2000 == 0:
-                    print('The {num}-th Monte carol simulation'.format(num = MC_times))
-            MC_result = MC_batch_min / MC_num
-            KD_list.append( current_min - MC_result)
+        fea_num = len(self.data_matrix[0])
+        archive_sample_x = np.append(self.data_matrix[:], self.virtual_samples[0])
+        archive_sample_y = np.append(self.Measured_response[:], self.virtual_samples_mean[0])
+        K_model = self.Kriging_model()
+        results = []
+        if not Proc_num:
+            for x_value, v_sample_mean, v_sample_std in zip(self.virtual_samples, self.virtual_samples_mean, self.virtual_samples_std):
+                MC_batch_min= self.__Knowledge_G_per_sample(K_model, MC_num, self.virtual_samples, v_sample_mean, v_sample_std, archive_sample_x, archive_sample_y, x_value, fea_num, self.ret_noise)
+                MC_result = MC_batch_min / MC_num
+                KD_list.append( current_min - MC_result)
+        else:
+            with mp.get_context("spawn").Pool(Proc_num) as pool:
+                results=[pool.apply_async(self.__Knowledge_G_per_sample, args=(K_model, MC_num, self.virtual_samples, v_sample_mean, v_sample_std, archive_sample_x, archive_sample_y, x_value, fea_num, self.ret_noise)) for x_value, v_sample_mean, v_sample_std in zip(self.virtual_samples, self.virtual_samples_mean, self.virtual_samples_std)]
+                for idx, rst in enumerate(results):
+                    MC_batch_min = rst.get()
+                    MC_result = MC_batch_min / MC_num
+                    KD_list.append( current_min - MC_result)
         KD_list = np.array(KD_list)
 
         return_x = []

Bgolearn/BGOsampling.py

@@ -5,6 +5,7 @@
 import numpy as np
 import pandas as pd
 import copy
+from typing import Union
 from .BGOmax import Global_max
 from .BGOmin import Global_min
 from .BGOclf import Boundary
@@ -19,7 +20,7 @@
 from sklearn.model_selection import KFold
 
 class Bgolearn(object):
-    def fit(self,data_matrix, Measured_response, virtual_samples, Mission ='Regression', Classifier = 'GaussianProcess',noise_std = None, Kriging_model = None, opt_num = 1 ,min_search = True, CV_test = False, ):
+    def fit(self,data_matrix, Measured_response, virtual_samples, Mission ='Regression', Classifier = 'GaussianProcess',noise_std = None, Kriging_model = None, opt_num = 1 ,min_search = True, CV_test = False, )-> Union[Boundary, Global_max, Global_min]:
 
         """
         ================================================================