use of sub-surrogate models

find_best_attributes_surrogate_openML_multi.py

@@ -0,0 +1,257 @@
+# main imports
+import os
+import sys
+import argparse
+import pandas as pd
+import numpy as np
+import logging
+import datetime
+import random
+
+# model imports
+from sklearn.model_selection import train_test_split
+from sklearn.model_selection import GridSearchCV
+from sklearn.linear_model import LogisticRegression
+from sklearn.ensemble import RandomForestClassifier, VotingClassifier
+
+import joblib
+import sklearn
+import sklearn.svm as svm
+from sklearn.utils import shuffle
+from sklearn.metrics import roc_auc_score
+from sklearn.model_selection import cross_val_score
+from sklearn.preprocessing import MinMaxScaler
+
+# modules and config imports
+sys.path.insert(0, '') # trick to enable import of main folder module
+
+import custom_config as cfg
+import models as mdl
+
+from optimization.ILSMultiSurrogate import ILSMultiSurrogate
+from macop.solutions.BinarySolution import BinarySolution
+
+from macop.operators.mutators.SimpleMutation import SimpleMutation
+from macop.operators.mutators.SimpleBinaryMutation import SimpleBinaryMutation
+from macop.operators.crossovers.SimpleCrossover import SimpleCrossover
+from macop.operators.crossovers.RandomSplitCrossover import RandomSplitCrossover
+
+from macop.operators.policies.UCBPolicy import UCBPolicy
+
+from macop.callbacks.BasicCheckpoint import BasicCheckpoint
+from macop.callbacks.UCBCheckpoint import UCBCheckpoint
+from optimization.callbacks.SurrogateCheckpoint import SurrogateCheckpoint
+from optimization.callbacks.MultiSurrogateCheckpoint import MultiSurrogateCheckpoint
+
+from sklearn.ensemble import RandomForestClassifier
+
+
+# default validator
+def validator(solution):
+
+    # at least 5 attributes
+    if list(solution._data).count(1) < 2:
+        return False
+
+    return True
+
+def train_model(X_train, y_train):
+
+    #print ('Creating model...')
+    # here use of SVM with grid search CV
+    Cs = [0.001, 0.01, 0.1, 1, 10, 100]
+    gammas = [0.001, 0.01, 0.1,10, 100]
+    param_grid = {'kernel':['rbf'], 'C': Cs, 'gamma' : gammas}
+
+    svc = svm.SVC(probability=True, class_weight='balanced')
+    #clf = GridSearchCV(svc, param_grid, cv=5, verbose=1, scoring=my_accuracy_scorer, n_jobs=-1)
+    clf = GridSearchCV(svc, param_grid, cv=4, verbose=0, n_jobs=-1)
+
+    clf.fit(X_train, y_train)
+
+    model = clf.best_estimator_
+
+    return model
+
+def loadDataset(filename):
+
+    ########################
+    # 1. Get and prepare data
+    ########################
+    dataset = pd.read_csv(filename, sep=',')
+
+    # change label as common
+    min_label_value = min(dataset.iloc[:, -1])
+    max_label_value = max(dataset.iloc[:, -1])
+
+    dataset.iloc[:, -1] = dataset.iloc[:, -1].replace(min_label_value, 0)
+    dataset.iloc[:, -1] = dataset.iloc[:, -1].replace(max_label_value, 1)
+
+    X_dataset = dataset.iloc[:, :-1]
+    y_dataset = dataset.iloc[:, -1]
+
+    problem_size = len(X_dataset.columns)
+
+    # min/max normalisation over feature
+    # create a scaler object
+    scaler = MinMaxScaler()
+    # fit and transform the data
+    X_dataset = np.array(pd.DataFrame(scaler.fit_transform(X_dataset), columns=X_dataset.columns))
+
+    # prepare train, validation and test datasets
+    X_train, X_test, y_train, y_test = train_test_split(X_dataset, y_dataset, test_size=0.3, shuffle=True)
+
+    return X_train, y_train, X_test, y_test, problem_size
+
+
+def main():
+
+    parser = argparse.ArgumentParser(description="Train and find best filters to use for model")
+
+    parser.add_argument('--data', type=str, help='open ml dataset filename prefix', required=True)
+    parser.add_argument('--every_ls', type=int, help='train every ls surrogate model', default=50) # default value
+    parser.add_argument('--k_division', type=int, help='number of expected sub surrogate model', required=True)
+    parser.add_argument('--k_dynamic', type=int, help='specify if indices for each sub surrogate model are changed or not for each training', default=0, choices=[0, 1])
+    parser.add_argument('--ils', type=int, help='number of total iteration for ils algorithm', required=True)
+    parser.add_argument('--ls', type=int, help='number of iteration for Local Search algorithm', required=True)
+    parser.add_argument('--output', type=str, help='output surrogate model name')
+
+    args = parser.parse_args()
+
+    p_data_file = args.data
+    p_every_ls   = args.every_ls
+    p_k_division = args.k_division
+    p_k_dynamic = bool(args.k_dynamic)
+    p_ils_iteration = args.ils
+    p_ls_iteration  = args.ls
+    p_output = args.output
+
+    # load data from file and get problem size
+    X_train, y_train, X_test, y_test, problem_size = loadDataset(p_data_file)
+
+    # create `logs` folder if necessary
+    if not os.path.exists(cfg.output_logs_folder):
+        os.makedirs(cfg.output_logs_folder)
+
+    logging.basicConfig(format='%(asctime)s %(message)s', filename='data/logs/{0}.log'.format(p_output), level=logging.DEBUG)
+
+    # init solution (`n` attributes)
+    def init():
+        return BinarySolution([], problem_size).random(validator)
+
+    # define evaluate function here (need of data information)
+    def evaluate(solution):
+
+        start = datetime.datetime.now()
+
+        # get indices of filters data to use (filters selection from solution)
+        indices = []
+
+        for index, value in enumerate(solution._data): 
+            if value == 1: 
+                indices.append(index) 
+
+        print(f'Training SVM with {len(indices)} from {len(solution._data)} available features')
+
+        # keep only selected filters from solution
+        x_train_filters = X_train[:, indices]
+        x_test_filters = X_test[ :, indices]
+        
+        # model = mdl.get_trained_model(p_choice, x_train_filters, y_train_filters)
+        model = train_model(x_train_filters, y_train)
+
+        y_test_model = model.predict(x_test_filters)
+        y_test_predict = [ 1 if x > 0.5 else 0 for x in y_test_model ]
+        test_roc_auc = roc_auc_score(y_test, y_test_predict)
+
+        end = datetime.datetime.now()
+
+        diff = end - start
+
+        print("Real evaluation took: {}, score found: {}".format(divmod(diff.days * 86400 + diff.seconds, 60), test_roc_auc))
+
+        return test_roc_auc
+
+
+    # build all output folder and files based on `output` name
+    backup_model_folder = os.path.join(cfg.output_backup_folder, p_output)
+    surrogate_output_model = os.path.join(cfg.output_surrogates_model_folder, p_output)
+    surrogate_output_data = os.path.join(cfg.output_surrogates_data_folder, p_output)
+
+    if not os.path.exists(backup_model_folder):
+        os.makedirs(backup_model_folder)
+
+    if not os.path.exists(cfg.output_surrogates_model_folder):
+        os.makedirs(cfg.output_surrogates_model_folder)
+
+    if not os.path.exists(cfg.output_surrogates_data_folder):
+        os.makedirs(cfg.output_surrogates_data_folder)
+
+    backup_file_path = os.path.join(backup_model_folder, p_output + '.csv')
+    ucb_backup_file_path = os.path.join(backup_model_folder, p_output + '_ucbPolicy.csv')
+    surrogate_backup_file_path = os.path.join(cfg.output_surrogates_data_folder, p_output + '_train.csv')
+    surrogate_k_indices_backup_file_path = os.path.join(cfg.output_surrogates_data_folder, p_output + '_k_indices.csv')
+
+    # prepare optimization algorithm (only use of mutation as only ILS are used here, and local search need only local permutation)
+    operators = [SimpleBinaryMutation(), SimpleMutation()]
+    policy = UCBPolicy(operators)
+
+    # define first line if necessary
+    if not os.path.exists(surrogate_output_data):
+        folder, _ = os.path.split(surrogate_output_data)
+
+        if not os.path.exists(folder):
+            os.makedirs(folder)
+
+        with open(surrogate_output_data, 'w') as f:
+            f.write('x;y\n')
+
+
+    # custom start surrogate variable based on problem size
+    p_start = int(0.5 * problem_size)
+
+    # fixed minimal number of real evaluations
+    if p_start < 50:
+        p_start = 50
+
+    print(f'Starting using surrogate after {p_start} reals training')
+
+    # custom ILS for surrogate use
+    algo = ILSMultiSurrogate(initalizer=init, 
+                        evaluator=evaluate, # same evaluator by defadefaultult, as we will use the surrogate function
+                        operators=operators, 
+                        policy=policy, 
+                        validator=validator,
+                        surrogates_file_path=surrogate_output_model,
+                        start_train_surrogates=p_start, # start learning and using surrogate after 1000 real evaluation
+                        solutions_file=surrogate_output_data,
+                        ls_train_surrogates=p_every_ls, # retrain surrogate every `x` iteration
+                        k_division=p_k_division,
+                        k_dynamic=p_k_dynamic,
+                        maximise=True)
+    
+    algo.addCallback(BasicCheckpoint(every=1, filepath=backup_file_path))
+    algo.addCallback(UCBCheckpoint(every=1, filepath=ucb_backup_file_path))
+    algo.addCallback(SurrogateCheckpoint(every=p_ls_iteration, filepath=surrogate_backup_file_path)) # try every LS like this
+    algo.addCallback(MultiSurrogateCheckpoint(every=p_ls_iteration, filepath=surrogate_k_indices_backup_file_path)) # try every LS like this
+
+    bestSol = algo.run(p_ils_iteration, p_ls_iteration)
+
+    # print best solution found
+    print("Found ", bestSol)
+
+    # save model information into .csv file
+    if not os.path.exists(cfg.results_information_folder):
+        os.makedirs(cfg.results_information_folder)
+
+    filename_path = os.path.join(cfg.results_information_folder, cfg.optimization_attributes_result_filename)
+
+    line_info = p_data_file + ';' + str(p_ils_iteration) + ';' + str(p_ls_iteration) + ';' + str(bestSol.data) + ';' + str(list(bestSol.data).count(1)) + ';' + str(bestSol.fitness())
+    with open(filename_path, 'a') as f:
+        f.write(line_info + '\n')
+    
+    print('Result saved into %s' % filename_path)
+
+
+if __name__ == "__main__":
+    main()

optimization/ILSMultiSurrogate.py

@@ -0,0 +1,375 @@
+"""Iterated Local Search Algorithm implementation using multiple-surrogate (weighted sum surrogate) as fitness approximation
+"""
+
+# main imports
+import os
+import logging
+import joblib
+import time
+import math
+import numpy as np
+import pandas as pd
+
+# module imports
+from macop.algorithms.Algorithm import Algorithm
+from .LSSurrogate import LocalSearchSurrogate
+from .utils.SurrogateAnalysis import SurrogateAnalysis
+
+from sklearn.linear_model import (LinearRegression, Lasso, Lars, LassoLars,
+                                    LassoCV, ElasticNet)
+
+from wsao.sao.problems.nd3dproblem import ND3DProblem
+from wsao.sao.surrogates.walsh import WalshSurrogate
+from wsao.sao.algos.fitter import FitterAlgo
+from wsao.sao.utils.analysis import SamplerAnalysis, FitterAnalysis, OptimizerAnalysis
+
+class ILSMultiSurrogate(Algorithm):
+    """Iterated Local Search used to avoid local optima and increave EvE (Exploration vs Exploitation) compromise using multiple-surrogate
+
+
+    Attributes:
+        initalizer: {function} -- basic function strategy to initialize solution
+        evaluator: {function} -- basic function in order to obtained fitness (mono or multiple objectives)
+        operators: {[Operator]} -- list of operator to use when launching algorithm
+        policy: {Policy} -- Policy class implementation strategy to select operators
+        validator: {function} -- basic function to check if solution is valid or not under some constraints
+        maximise: {bool} -- specify kind of optimization problem 
+        currentSolution: {Solution} -- current solution managed for current evaluation
+        bestSolution: {Solution} -- best solution found so far during running algorithm
+        ls_iteration: {int} -- number of evaluation for each local search algorithm
+        surrogates_file: {str} -- Surrogates model folder to load (models trained using https://gitlab.com/florianlprt/wsao)
+        start_train_surrogates: {int} -- number of evaluation expected before start training and use surrogate
+        surrogates: [{Surrogate}] -- Surrogates model instance loaded
+        ls_train_surrogates: {int} -- Specify if we need to retrain our surrogate model (every Local Search)
+        k_division: {int} -- number of expected division for current features problem
+        k_dynamic: {bool} -- specify if indices are changed for each time we train a new surrogate model
+        solutions_file: {str} -- Path where real evaluated solutions are saved in order to train surrogate again
+        callbacks: {[Callback]} -- list of Callback class implementation to do some instructions every number of evaluations and `load` when initializing algorithm
+    """
+    def __init__(self,
+                 initalizer,
+                 evaluator,
+                 operators,
+                 policy,
+                 validator,
+                 surrogate_file_path,
+                 start_train_surrogate,
+                 ls_train_surrogate,
+                 k_division,
+                 solutions_file,
+                 k_dynamic=False,
+                 maximise=True,
+                 parent=None):
+
+        # set real evaluator as default
+        super().__init__(initalizer, evaluator, operators, policy,
+                validator, maximise, parent)
+
+        self._n_local_search = 0
+        self._main_evaluator = evaluator
+
+        self._surrogate_file_path = surrogate_file_path
+        self._start_train_surrogate = start_train_surrogate
+
+        self._surrogate_evaluator = None
+        self._surrogate_analyser = None
+
+        self._ls_train_surrogate = ls_train_surrogate
+        self._solutions_file = solutions_file
+
+        self._k_division = k_division
+        self._k_dynamic = k_dynamic
+
+    def init_k_split_indices(self):
+        a = list(range(self._bestSolution._size))
+        n_elements = int(math.ceil(self._bestSolution._size / self._k_division)) # use of ceil to avoid loss of data
+        splitted_indices = [a[x:x+n_elements] for x in range(0, len(a), n_elements)]
+
+        return splitted_indices
+        
+
+    def train_surrogates(self):
+        """Retrain if necessary the whole surrogate fitness approximation function
+        """
+        # Following https://gitlab.com/florianlprt/wsao, we re-train the model
+        # ---------------------------------------------------------------------------
+        # cli_restart.py problem=nd3d,size=30,filename="data/statistics_extended_svdn" \
+        #        model=lasso,alpha=1e-5 \
+        #        surrogate=walsh,order=3 \
+        #        algo=fitter,algo_restarts=10,samplefile=stats_extended.csv \
+        #        sample=1000,step=10 \
+        #        analysis=fitter,logfile=out_fit.csv
+
+        # TODO : pass run samples directly using train and test
+        # TODO : use of multiprocessing commands for each surrogate
+        # TODO : save each surrogate model into specific folder
+
+        # 1. Data sets preparation (train and test)
+        
+        # dynamic number of samples based on dataset real evaluations
+        nsamples = None
+        with open(self._solutions_file, 'r') as f:
+            nsamples = len(f.readlines()) - 1 # avoid header
+
+        training_samples = int(0.7 * nsamples) # 70% used for learning part at each iteration
+        
+        df = pd.read_csv(self._solutions_file, sep=';')
+        # learning set and test set
+        learn = df.sample(nsamples)
+        test = df.drop(learn.index)
+
+        print(f'Training all surrogate models using {training_samples} of {nsamples} samples for train dataset')
+
+        # 2. for each sub space indices, learn new surrogate
+
+        if not os.path.exists(self._surrogate_file_path):
+            os.makedirs(self._surrogate_file_path)
+
+        for i, indices in enumerate(self._k_indices):
+
+            current_learn = learn[learn.iloc[indices]]
+
+            problem = ND3DProblem(size=len(indices)) # problem size based on best solution size (need to improve...)
+            model = Lasso(alpha=1e-5)
+            surrogate = WalshSurrogate(order=2, size=problem.size, model=model)
+            analysis = FitterAnalysis(logfile=f"train_surrogate_{i}.log", problem=problem)
+            algo = FitterAlgo(problem=problem, surrogate=surrogate, analysis=analysis, seed=problem.seed)
+
+            print(f"Start fitting again the surrogate model n°{i}")
+            for r in range(10):
+                print(f"Iteration n°{r}: for fitting surrogate n°{i}")
+                algo.run_samples(learn=current_learn, test=test, step=10)
+
+            # keep well ordered surrogate into file manager
+            str_index = str(i)
+
+            while len(str_index) < 6:
+                str_index = "0" + str_index
+
+            joblib.dump(algo, os.path.join(self._surrogate_file_path, 'surrogate_{str_indec}'))
+
+
+    def load_surrogates(self):
+        """Load algorithm with surrogate model and create lambda evaluator function
+        """
+
+        # need to first train surrogate if not exist
+        if not os.path.exists(self._surrogate_file_path):
+            self.train_surrogates()
+
+        self._surrogates = []
+
+        surrogates_path = sorted(os.listdir(self._surrogate_file_path))
+
+        for surrogate_p in surrogates_path:
+            model_path = os.path.join(self._surrogate_file_path, surrogate_p)
+            surrogate_model = joblib.load(model_path)
+
+            self._surrogates.append(surrogate_model)
+
+    
+    def surrogate_evaluator(self, solution):
+        """Compute mean of each surrogate model using targeted indices
+
+        Args:
+            solution: {Solution} -- current solution to evaluate using multi-surrogate evaluation
+
+        Return:
+            mean: {float} -- mean score of surrogate models
+        """
+        scores = []
+        solution_data = np.array(solution._data)
+
+        # for each indices set, get trained surrogate model and made prediction score
+        for i, indices in enumerate(self._k_indices):
+            current_data = solution_data[indices]
+            current_score = self._surrogates[i].surrogate.predict([current_data])[0]
+            scores.append(current_score)
+
+        return sum(scores) / len(scores)
+            
+    def surrogates_coefficient_of_determination(self):
+        """Compute r² for each sub surrogate model
+
+        Return:
+            r_squared: {float} -- mean score of r_squred obtained from surrogate models
+        """
+
+        r_squared_scores = []
+
+        # for each indices set, get r^2 surrogate model and made prediction score
+        for i, _ in enumerate(self._k_indices):
+
+            r_squared = self._surrogates[i].analysis.coefficient_of_determination(self._surrogates[i].surrogate)
+            r_squared_scores.append(r_squared)
+
+        return sum(r_squared_scores) / len(r_squared_scores)
+
+
+
+    def add_to_surrogate(self, solution):
+
+        # save real evaluated solution into specific file for surrogate
+        with open(self._solutions_file, 'a') as f:
+
+            line = ""
+
+            for index, e in enumerate(solution._data):
+
+                line += str(e)
+                
+                if index < len(solution._data) - 1:
+                    line += ","
+
+            line += ";"
+            line += str(solution._score)
+
+            f.write(line + "\n")
+
+    def run(self, evaluations, ls_evaluations=100):
+        """
+        Run the iterated local search algorithm using local search (EvE compromise)
+
+        Args:
+            evaluations: {int} -- number of global evaluations for ILS
+            ls_evaluations: {int} -- number of Local search evaluations (default: 100)
+
+        Returns:
+            {Solution} -- best solution found
+        """
+
+        # by default use of mother method to initialize variables
+        super().run(evaluations)
+
+        # initialize current solution
+        self.initRun()
+
+        # based on best solution found, initialize k pool indices
+        self._k_indices = self.init_k_split_indices()
+
+        # enable resuming for ILS
+        self.resume()
+
+        # count number of surrogate obtained and restart using real evaluations done
+        nsamples = None
+        with open(self._solutions_file, 'r') as f:
+            nsamples = len(f.readlines()) - 1 # avoid header
+
+        if self.getGlobalEvaluation() < nsamples:
+            print(f'Restart using {nsamples} of {self._start_train_surrogate} real evaluations obtained')
+            self._numberOfEvaluations = nsamples
+
+        if self._start_train_surrogate > self.getGlobalEvaluation():
+        
+            # get `self.start_train_surrogate` number of real evaluations and save it into surrogate dataset file
+            # using randomly generated solutions (in order to cover seearch space)
+            while self._start_train_surrogate > self.getGlobalEvaluation():
+                
+                newSolution = self._initializer()
+
+                # evaluate new solution
+                newSolution.evaluate(self._evaluator)
+
+                # add it to surrogate pool
+                self.add_to_surrogate(newSolution)
+
+                self.increaseEvaluation()
+
+        # train surrogate on real evaluated solutions file
+        self.train_surrogates()
+        self.load_surrogates()
+
+        # local search algorithm implementation
+        while not self.stop():
+
+            # set current evaluator based on used or not of surrogate function
+            self._evaluator = self.surrogate_evaluator if self._start_train_surrogate <= self.getGlobalEvaluation() else self._main_evaluator
+
+            # create new local search instance
+            # passing global evaluation param from ILS
+            ls = LocalSearchSurrogate(self._initializer,
+                         self._evaluator,
+                         self._operators,
+                         self._policy,
+                         self._validator,
+                         self._maximise,
+                         parent=self)
+
+            # add same callbacks
+            for callback in self._callbacks:
+                ls.addCallback(callback)
+
+            # create and search solution from local search
+            newSolution = ls.run(ls_evaluations)
+
+            # if better solution than currently, replace it (solution saved in training pool, only if surrogate process is in a second process step)
+            # Update : always add new solution into surrogate pool, not only if solution is better
+            #if self.isBetter(newSolution) and self.start_train_surrogate < self.getGlobalEvaluation():
+            if self._start_train_surrogate <= self.getGlobalEvaluation():
+
+                # if better solution found from local search, retrained the found solution and test again
+                # without use of surrogate
+                fitness_score = self._main_evaluator(newSolution)
+                # self.increaseEvaluation() # dot not add evaluation
+
+                newSolution.score = fitness_score
+
+                # if solution is really better after real evaluation, then we replace
+                if self.isBetter(newSolution):
+                    self._bestSolution = newSolution
+
+                self.add_to_surrogate(newSolution)
+
+                self.progress()
+
+            # check using specific dynamic criteria based on r^2
+            r_squared = self.surrogates_coefficient_of_determination()
+            training_surrogate_every = int(r_squared * self._ls_train_surrogate)
+            print(f"=> R^2 of surrogate is of {r_squared}. Retraining model every {training_surrogate_every} LS")
+
+            # avoid issue when lauching every each local search
+            if training_surrogate_every <= 0:
+                training_surrogate_every = 1
+
+            # check if necessary or not to train again surrogate
+            if self._n_local_search % training_surrogate_every == 0 and self._start_train_surrogate <= self.getGlobalEvaluation():
+
+                # reinitialization of k_indices for the new training
+                if self._k_dynamic:
+                    print(f"Reinitialization of k_indices using `k={self._k_division} `for the new training")
+                    self.init_k_split_indices()
+
+                # train again surrogate on real evaluated solutions file
+                start_training = time.time()
+                self.train_surrogates()
+                training_time = time.time() - start_training
+
+                self._surrogate_analyser = SurrogateAnalysis(training_time, training_surrogate_every, r_squared, self.getGlobalMaxEvaluation(), self._n_local_search)
+
+                # reload new surrogate function
+                self.load_surrogates()
+
+            # increase number of local search done
+            self._n_local_search += 1
+
+            self.information()
+
+        logging.info(f"End of {type(self).__name__}, best solution found {self._bestSolution}")
+
+        self.end()
+        return self._bestSolution
+
+    def addCallback(self, callback):
+        """Add new callback to algorithm specifying usefull parameters
+
+        Args:
+            callback: {Callback} -- specific Callback instance
+        """
+        # specify current main algorithm reference
+        if self.getParent() is not None:
+            callback.setAlgo(self.getParent())
+        else:
+            callback.setAlgo(self)
+
+        # set as new
+        self._callbacks.append(callback)

optimization/ILSSurrogate.py

@@ -10,6 +10,7 @@ import time
 # module imports
 from macop.algorithms.Algorithm import Algorithm
 from .LSSurrogate import LocalSearchSurrogate
+from .utils.SurrogateAnalysis import SurrogateAnalysis
 
 from sklearn.linear_model import (LinearRegression, Lasso, Lars, LassoLars,
                                     LassoCV, ElasticNet)
@@ -20,17 +21,6 @@ from wsao.sao.algos.fitter import FitterAlgo
 from wsao.sao.utils.analysis import SamplerAnalysis, FitterAnalysis, OptimizerAnalysis
 
 
-# quick object for surrogate logging data
-class SurrogateAnalysis():
-
-    def __init__(self, time, every_ls, r2, evaluations, n_local_search):
-        self._time = time
-        self._every_ls = every_ls
-        self._r2 = r2
-        self._evaluations = evaluations
-        self._n_local_search = n_local_search
-
-
 class ILSSurrogate(Algorithm):
     """Iterated Local Search used to avoid local optima and increave EvE (Exploration vs Exploitation) compromise using surrogate
 

optimization/callbacks/MultiSurrogateCheckpoint.py

@@ -0,0 +1,96 @@
+"""Basic Checkpoint class implementation
+"""
+
+# main imports
+import os
+import logging
+import numpy as np
+
+# module imports
+from macop.callbacks.Callback import Callback
+from macop.utils.color import macop_text, macop_line
+
+
+class SurrogateCheckpoint(Callback):
+    """
+    SurrogateCheckpoint is used for logging training data information about surrogate
+
+    Attributes:
+        algo: {Algorithm} -- main algorithm instance reference
+        every: {int} -- checkpoint frequency used (based on number of evaluations)
+        filepath: {str} -- file path where checkpoints will be saved
+    """
+    def run(self):
+        """
+        Check if necessary to do backup based on `every` variable
+        """
+        # get current best solution
+        k_indices = self._algo._k_indices
+
+        # Do nothing is surrogate analyser does not exist
+        if k_indices is None:
+            return
+
+        currentEvaluation = self._algo.getGlobalEvaluation()
+
+        # backup if necessary
+        if currentEvaluation % self._every == 0:
+
+            logging.info(f"Multi surrogate analysis checkpoint is done into {self._filepath}")
+
+            line = str(currentEvaluation) + ';'
+
+            for indices in k_indices:
+                
+                indices_data = ""
+                indices_size = len(indices)
+
+                for index, val in enumerate(indices):
+                    indices_data += str(val)
+
+                    if index < indices_size - 1:
+                        indices_data += ' '
+
+                line += indices_data + ';'
+
+            line += '\n'
+
+            # check if file exists
+            if not os.path.exists(self._filepath):
+                with open(self._filepath, 'w') as f:
+                    f.write(line)
+            else:
+                with open(self._filepath, 'a') as f:
+                    f.write(line)
+
+    def load(self):
+        """
+        Load nothing there, as we only log surrogate training information
+        """
+        if os.path.exists(self._filepath):
+
+            logging.info('Load best solution from last checkpoint')
+            with open(self._filepath) as f:
+
+                # get last line and read data
+                lastline = f.readlines()[-1]
+                data = lastline.split(';')
+
+                k_indices = data[1:]
+                k_indices_final = []
+
+                for indices in k_indices:
+                    k_indices_final.append(list(map(int, indices.split(' '))))
+
+                # set k_indices into main algorithm
+                self._algo._k_indices = k_indices_final
+
+            print(macop_line())
+            print(macop_text(f' MultiSurrogateCheckpoint found from `{self._filepath}` file.'))
+
+        else:
+            print(macop_text('No backup found... Start running using new `k_indices` values'))
+            logging.info("Can't load MultiSurrogate backup... Backup filepath not valid in  MultiSurrogateCheckpoint")
+
+        print(macop_line())
+

optimization/utils/SurrogateAnalysis.py

@@ -0,0 +1,10 @@
+# quick object for surrogate logging data
+class SurrogateAnalysis():
+
+    def __init__(self, time, every_ls, r2, evaluations, n_local_search):
+        self._time = time
+        self._every_ls = every_ls
+        self._r2 = r2
+        self._evaluations = evaluations
+        self._n_local_search = n_local_search
+