+[docs]
+ defcompute_pattern_support(self)->np.array:''' Computes the pattern support for each of the rules for the given X. Each pattern support firing strength is the result of the tnorm for all the antecedent memeberships,
@@ -162,7 +166,10 @@
+[docs]
+ defcompute_aux_pattern_support(self)->np.array:''' Computes the pattern support for each of the rules for each of the classes for the given X. Each pattern support firing strength is the result of the tnorm for all the antecedent memeberships,
@@ -201,6 +208,7 @@
Source code for ex_fuzzy.eval_rules
returnres
+
def_get_all_rules(self)->list[rules.RuleSimple]:''' Returns a list of all the rules in the master rule base.
@@ -214,7 +222,9 @@
+[docs]
+ defcompute_pattern_confidence(self)->np.array:''' Computes the pattern confidence for each of the rules for the given X. Each pattern confidence is the normalized firing strength.
@@ -250,7 +260,10 @@
+[docs]
+ defcompute_aux_pattern_confidence(self)->np.array:''' Computes the pattern confidence for each of the rules for the given X. Each pattern confidence is the normalized firing strength.
@@ -287,7 +300,10 @@
+[docs]
+ defadd_auxiliary_rule_weights(self)->None:''' Add dominance score field to each of the rules present in the master Rule Base for each consequent. They are labeled as aux_score, aux_support and aux_confidence. (Because they are not the main rule weights)
@@ -357,7 +385,10 @@
+[docs]
+ defadd_classification_metrics(self,X:np.array=None,y:np.array=None)->None:''' Adds the accuracy of each rule in the master rule base. It also adds the f1, precision and recall scores. If X and y are None uses the train set.
@@ -403,9 +434,12 @@
+[docs]
+ defclassification_eval(self)->float:''' Returns the matthews correlation coefficient for a classification task using the rules evaluated.
@@ -416,10 +450,16 @@
+[docs]
+ defsize_antecedents_eval(self,tolerance=0.1)->float:''' Returns a score between 0 and 1, where 1 means that the rule base only contains almost no antecedents.
@@ -454,9 +494,12 @@
+[docs]
+ defeffective_rulesize_eval(self,tolerance=0.1)->float:''' Returns a score between 0 and 1, where 1 means that the rule base only contains almost no antecedents.
@@ -489,12 +532,51 @@
+[docs]
+ defp_permutation_classifier_validation(self,n=100,r=10)->float:
+'''
+ Performs a boostrap test to evaluate the performance of the rule base.
+ Returns the p-valuefor the label permutation test and the feature coalition test.
+
+ :param n: int. Number of boostrap samples.
+ :param r: int. Number of repetitions to estimate the original error rate.
+ :return: p-value of the permutation test.
+ '''
+ test1=bt.permutation_labels_test(self.mrule_base,self.X,self.y,k=n,r=r)
+ test2=bt.permute_columns_class_test(self.mrule_base,self.X,self.y,k=n,r=r)
+
+ bt.rulewise_label_permutation_test(self.mrule_base,self.X,self.y,k=n,r=r)
+ bt.rulewise_column_permutation_test(self.mrule_base,self.X,self.y,k=n,r=r)
+
+ self.mrule_base.p_value_class_structure=test1
+ self.mrule_base.p_value_feature_coalition=test2
+
+ returntest1,test2
+[docs]
+ defadd_full_evaluation(self):''' Adds classification scores, both Dominance Scores and accuracy metrics, for each individual rule. '''self.add_rule_weights()
- self.add_classification_metrics()
+[docs]
+classFuzzyEvaluator():'''
- Function that evaluates a fuzzy rule based model. It also plots the rules and the fuzzy partitions.
-
- :param fl_classifier: Fuzzy rule based model.
- :param X_train: Training data.
- :param y_train: Training labels.
- :param X_test: Test data.
- :param y_test: Test labels.
- :param plot_rules: If True, it plots the rules.
- :param print_rules: If True, it prints the rules.
- :param plot_partitions: If True, it plots the fuzzy partitions.
- :return: None
+ Takes a model and associated data and permits rule evaluation '''
- # Get the unique classes from the classifier
- unique_classes=fl_classifier.classes_names
+ def__init__(self,fl_classifier:evf.BaseFuzzyRulesClassifier):
+'''
+ :param fl_classifier: Fuzzy rule based model
+ '''
+ self.fl_classifier=fl_classifier
+
- # Convert the names from the labels to the corresponding class if necessary
- ifisinstance(y_train[0],str):
- y_train=np.array([list(unique_classes).index(str(y))foryiny_train])
- y_test=np.array([list(unique_classes).index(str(y))foryiny_test])
-
- ifprint_accuracy:
- print('------------')
- print('ACCURACY')
- print('Train performance: '+
- str(np.mean(np.equal(y_train,fl_classifier.predict(X_train,out_class_names=isinstance(y_train[0],str))))))
- print('Test performance: '+
- str(np.mean(np.equal(y_test,fl_classifier.predict(X_test,out_class_names=isinstance(y_train[0],str))))))
- print('------------')
- ifprint_matthew:
- print('MATTHEW CORRCOEF')
- print('Train performance: '+
- str(matthews_corrcoef(y_train,fl_classifier.predict(X_train,out_class_names=isinstance(y_train[0],str))))
- )
- print('Test performance: '+
- str(matthews_corrcoef(y_test,fl_classifier.predict(X_test,out_class_names=isinstance(y_train[0],str))))
- )
- print('------------')
-
-
- ifprint_rulesorreturn_rules:
- res=fl_classifier.print_rules(True)
-
- ifprint_rules:
- print(res)
-
- ifplot_partitions:
- fl_classifier.plot_fuzzy_variables()
-
- ifplot_rules:
- vis_rules.visualize_rulebase(fl_classifier.rule_base,export_path=export_path)
-
- ifreturn_rules:
- returnres
-
+ defpredict(self,X:np.array)->np.array:
+ # Predict y for given X for use in metric evaluation
+ returnself.fl_classifier.predict(X)
+
+
+[docs]
+ defget_metric(self,metric:str,X_true:np.array,y_true:np.array,**kwargs)->float:
+'''
+ :param metric: named metric in string format available in sklearn library for evaluation
+ :param X_true: np.array of X values for prediction
+ :param y_true: np.array of true class outcomes for X values
+ :param **kwargs: additional arguments for different sklearn.metrics functions
+ '''
+ #Get y predictions
+ y_pred=self.predict(X_true)
+ y_true=np.array(y_true)
+ #Convert str classes to numbers in corresponding class if necessary
+ unique_classes=self.fl_classifier.classes_names
+
+ ifisinstance(y_true[0],str):
+ y_true=np.array([list[unique_classes].index(str(y))foryiny_true])
+
+ #Find metrics requested in sklearn library, if not found
+ try:
+ # Get the metric function dynamically from sklearn.metrics
+ metric_function=getattr(metrics,metric)
+ # Call the metric function with y_true, y_pred, and any additional keyword arguments
+ returnmetric_function(y_true,y_pred,**kwargs)
+ exceptAttributeError:
+ returnf"Metric '{metric}' not found in sklearn.metrics."
+ exceptTypeError:
+ returnf"Invalid arguments passed for the metric '{metric}'."
+
+
+
+
+[docs]
+ defeval_fuzzy_model(self,X_train:np.array,y_train:np.array,X_test:np.array,y_test:np.array,
+ plot_rules=True,print_rules=True,plot_partitions=True,
+ return_rules=False,print_accuracy=True,print_matthew=True,export_path:str=None)->None:
+'''
+ Function that evaluates a fuzzy rule based model. It also plots the rules and the fuzzy partitions.
+
+ :param X_train: Training data.
+ :param y_train: Training labels.
+ :param X_test: Test data.
+ :param y_test: Test labels.
+ :param plot_rules: If True, it plots the rules.
+ :param print_rules: If True, it prints the rules.
+ :param plot_partitions: If True, it plots the fuzzy partitions.
+ :return: None
+ '''
+ # Get the unique classes from the classifier
+ unique_classes=self.fl_classifier.classes_names
+
+ # Convert the names from the labels to the corresponding class if necessary
+ ifisinstance(y_train[0],str):
+ y_train=np.array([list(unique_classes).index(str(y))foryiny_train])
+ y_test=np.array([list(unique_classes).index(str(y))foryiny_test])
+
+ ifprint_accuracy:
+ print('------------')
+ print('ACCURACY')
+ print('Train performance: '+
+ str(self.get_metric('accuracy_score',X_train,y_train)))
+ print('Test performance: '+
+ str(self.get_metric('accuracy_score',X_test,y_test)))
+ print('------------')
+ ifprint_matthew:
+ print('MATTHEW CORRCOEF')
+ print('Train performance: '+
+ str(self.get_metric('matthews_corrcoef',X_train,y_train))
+ )
+ print('Test performance: '+
+ str(self.get_metric('matthews_corrcoef',X_test,y_test))
+ )
+ print('------------')
+
+
+ ifprint_rulesorreturn_rules:
+ res=self.fl_classifier.print_rules(True)
+
+ ifprint_rules:
+ print(res)
+
+ ifplot_partitions:
+ self.fl_classifier.plot_fuzzy_variables()
+
+ ifplot_rules:
+ vis_rules.visualize_rulebase(self.fl_classifier.rule_base,export_path=export_path)
+
+ ifreturn_rules:
+ returnres
+[docs]
+classBaseFuzzyRulesClassifier(ClassifierMixin):''' Class that is used as a classifier for a fuzzy rule based system. Supports precomputed and optimization of the linguistic variables. '''
@@ -207,7 +207,9 @@
+[docs]
+ deffit(self,X:np.array,y:np.array,n_gen:int=70,pop_size:int=30,
+ checkpoints:int=0,candidate_rules:rules.MasterRuleBase=None,initial_rules:rules.MasterRuleBase=None,random_state:int=33,
+ var_prob:float=0.3,sbx_eta:float=3.0,mutation_eta=7.0,tournament_size=3,bootstrap_size=1000)->None:''' Fits a fuzzy rule based classifier using a genetic algorithm to the given data.
@@ -228,6 +234,12 @@
Source code for ex_fuzzy.evolutionary_fit
:param pop_size: integer. Population size for each gneration. :param checkpoints: integer. Number of checkpoints to save the best rulebase found so far. :param candidate_rules: if these rules exist, the optimization process will choose the best rules from this set. If None (default) the rules will be generated from scratch.
+ :param initial_rules: if these rules exist, the optimization process will start from this set. If None (default) the rules will be generated from scratch.
+ :param random_state: integer. Random seed for the optimization process.
+ :param var_prob: float. Probability of crossover for the genetic algorithm.
+ :param sbx_eta: float. Eta parameter for the SBX crossover.
+ :param mutation_eta: float. Eta parameter for the polynomial mutation.
+ :param tournament_size: integer. Size of the tournament for the genetic algorithm. :return: None. The classifier is fitted to the data. '''ifmnt.save_usage_flag:
@@ -287,8 +299,9 @@
+[docs]
+ defload_master_rule_base(self,rule_base:rules.MasterRuleBase)->None:''' Loads a master rule base to be used in the prediction process.
@@ -373,9 +393,12 @@
+[docs]
+ defprint_rules(self,return_rules:bool=False)->None:''' Print the rules contained in the fitted rulebase. '''returnself.rule_base.print_rules(return_rules)
+[docs]
+ defrename_fuzzy_variables(self)->None:''' Renames the linguist labels so that high, low and so on are consistent. It does so usually after an optimization process.
@@ -474,16 +512,22 @@
+[docs]
+ defget_rulebase(self)->list[np.array]:''' Get the rulebase obtained after fitting the classifier to the data. :return: a matrix format for the rulebase. '''returnself.rule_base.get_rulebase_matrix()
+[docs]
+classExploreRuleBases(Problem):''' Class to model as pymoo problem the fitting of a rulebase to a set of data given a series of candidate rules for a classification problem using Evolutionary strategies Supports type 1 and t2.
@@ -624,7 +681,9 @@
+[docs]
+classFitRuleBase(Problem):''' Class to model as pymoo problem the fitting of a rulebase for a classification problem using Evolutionary strategies. Supports type 1 and iv fs (iv-type 2)
@@ -850,7 +913,9 @@
+[docs]
+ defencode_rulebase(self,rule_base:rules.MasterRuleBase,optimize_lv:bool,encode_mods:bool=False)->np.array:''' Given a rule base, constructs the corresponding gene associated with that rule base.
@@ -869,10 +934,10 @@
Source code for ex_fuzzy.evolutionary_fit
gene=np.zeros((self.single_gen_size,))n_lv_possible=len(rule_base.rule_bases[0].antecedents[0].linguistic_variables)
- fz_type=rule_base.fuzzy_type()
+ fuzzy_type=rule_base.fuzzy_type()rule_consequents=rule_base.get_consequents()nreal_rules=len(rule_consequents)
- mf_size=4iffz_type==fs.FUZZY_SETS.t1else8
+ mf_size=4iffuzzy_type==fs.FUZZY_SETS.t1else8# Pointer to the fourth section of the gene: consequentsifoptimize_lv:
@@ -939,15 +1004,16 @@
Source code for ex_fuzzy.evolutionary_fit
aux_pointer+=1returnnp.array(list(map(int,gene)))
+
- def_construct_ruleBase(self,x:np.array,fz_type:fs.FUZZY_SETS,**kwargs)->rules.MasterRuleBase:
+ def_construct_ruleBase(self,x:np.array,fuzzy_type:fs.FUZZY_SETS,**kwargs)->rules.MasterRuleBase:''' Given a subject, it creates a rulebase according to its specification. :param x: gen of a rulebase. type: dict.
- :param fz_type: a enum type. Check fuzzy_sets for complete specification (two fields, t1 and t2, to mark which fs you want to use)
+ :param fuzzy_type: a enum type. Check fuzzy_sets for complete specification (two fields, t1 and t2, to mark which fs you want to use) :param kwargs: additional parameters to pass to the rule :return: a rulebase object.
@@ -958,7 +1024,7 @@
+[docs]
+ deftype(self)->FUZZY_SETS:''' Returns the corresponding fuzzy set type according to FUZZY_SETS enum. '''
- returnFUZZY_SETS.t1
+ returnFUZZY_SETS.t1
+
+
+
+ def__str__(self)->str:
+'''
+ Returns the name of the fuzzy set, its type and its parameters.
+
+ :return: string.
+ '''
+ returnf'Categorical set: {self.name}, type 1 output'
+[docs]
+ deftype(self)->FUZZY_SETS:''' Returns the corresponding fuzzy set type according to FUZZY_SETS enum: (t2) '''
- returnFUZZY_SETS.t2
+ returnFUZZY_SETS.t2
+
+
+
+ def__str__(self)->str:
+'''
+ Returns the name of the fuzzy set, its type and its parameters.
+
+ :return: string.
+ '''
+ returnf'{self.name} ({self.type().name}) - {self.secondMF_lower} - {self.secondMF_upper}'
+[docs]
+ deftype(self)->FUZZY_SETS:''' Returns the corresponding fuzzy set type according to FUZZY_SETS enum. '''
- returnFUZZY_SETS.t2
+ returnFUZZY_SETS.t2
+
+
+
+ def__str__(self)->str:
+'''
+ Returns the name of the fuzzy set, its type and its parameters.
+
+ :return: string.
+ '''
+ returnf'Categorical set: {self.name}, type 2 output'
+[docs]
+ defalpha_reduction(self,x)->np.array:''' Computes the type reduction to reduce the alpha cuts to one value. :param x: array with the values of the inputs. :return: array with the memberships of the consequents for each sample. '''
- returnself._alpha_reduction(x)
+[docs]
+classfuzzyVariable():''' Class to implement a fuzzy Variable. Contains a series of fuzzy sets and computes the memberships to all of them. '''
@@ -588,7 +684,21 @@
+[docs]
+ defappend(self,fs:FS)->None:
+'''
+ Appends a fuzzy set to the fuzzy variable.
+
+ :param fs: FS. Fuzzy set to append.
+ '''
+ self.linguistic_variables.append(fs)
+
+
+
+
+[docs]
+ deflinguistic_variable_names(self)->list:''' Returns the name of the linguistic variables.
@@ -597,7 +707,10 @@
+[docs]
+defload_fuzzy_rules(rules_printed:str,fuzzy_variables:list)->rules.MasterRuleBase:''' Load the rules from a string. :param rules_printed: string with the rules. Follows the specification given by the same printing method of rules.MasterRuleBase :param fuzzy_variables: list with the linguistic variables. Objects of FuzzyVariable class.
-
+ :return mrule_base: object of MasterRuleBase class that contains the rules. '''ifmnt.save_usage_flag:mnt.usage_data[mnt.usage_categories.Persistence]['persistence_read']+=1
@@ -146,7 +152,8 @@
+[docs]
+defload_fuzzy_variables(fuzzy_variables_printed:str)->list:''' Load the linguistic variables from a string. :param fuzzy_variables_printed: string with the linguistic variables. Follows the specification given by the same printing method of FuzzyVariable class.
-
+ :return fuzzy_variables: list with the linguistic variables. Objects of FuzzyVariable class. '''ifmnt.save_usage_flag:mnt.usage_data[mnt.usage_categories.Persistence]['persistence_read']+=1
@@ -297,12 +307,15 @@
+[docs]
+defprint_fuzzy_variable(fuzzy_variable:fs.fuzzyVariable)->str:''' Save the linguistic variable to a string. :param fuzzy_variable: linguistic variable. Object of FuzzyVariable class.
-
+ :return fuzzy_variable_printed: string with the linguistic variable. Follows the specification given by the same printing method of FuzzyVariable class. '''ifmnt.save_usage_flag:mnt.usage_data[mnt.usage_categories.Persistence]['persistence_write']+=1
@@ -335,12 +348,15 @@
+[docs]
+defsave_fuzzy_variables(fuzzy_variables:list)->str:''' Save the linguistic variables to a string. :param fuzzy_variables: list with the linguistic variables. Objects of FuzzyVariable class.
-
+ :return fuzzy_variables_printed: string with the linguistic variables. Follows the specification given by the same printing method of FuzzyVariable class. '''ifmnt.save_usage_flag:mnt.usage_data[mnt.usage_categories.Persistence]['persistence_write']+=1
@@ -350,6 +366,7 @@
+[docs]
+defcompute_antecedents_memberships(antecedents:list[fs.fuzzyVariable],x:np.array)->list[dict]:''' Returns a list of of dictionaries that contains the memberships for each x value to the ith antecedents, nth linguistic variable. x must be a vector (only one sample)
@@ -118,9 +118,12 @@
+[docs]
+classRule():''' Class of Rule designed to work with one single rule. It contains the whole inference functionally in itself. '''
@@ -158,7 +164,9 @@
+[docs]
+ defmembership(self,x:np.array,tnorm=_myprod)->np.array:''' Computes the membership of one input to the antecedents of the rule.
@@ -174,7 +182,10 @@
+[docs]
+ defconsequent_centroid(self)->np.array:''' Returns the centroid of the consequent using a Karnik and Mendel algorithm. '''
@@ -190,11 +201,15 @@
+[docs]
+classRuleBase():''' Class optimized to work with multiple rules at the same time. Right now supports only one consequent. (Solution: use one rulebase per consequent to study) '''
@@ -327,14 +356,19 @@
+[docs]
+ defget_scores(self):''' Returns an array with the dominance score for each rule. (Must been already computed by an evalRule object)
@@ -392,9 +441,12 @@
+[docs]
+ defget_weights(self):''' Returns an array with the weights for each rule. (Different from dominance scores: must been already computed by an optimization algorithm)
@@ -407,6 +459,7 @@
Source code for ex_fuzzy.rules
returnres
+
defdelete_rule_duplicates(self,list_rules:list[RuleSimple]):# Delete the rules that are duplicated in the rule listunique={}
@@ -421,7 +474,9 @@
+[docs]
+ defcompute_antecedents_memberships(self,x:np.array)->list[dict]:''' Returns a list of of dictionaries that contains the memberships for each x value to the ith antecedents, nth linguistic variable. x must be a vector (only one sample)
@@ -451,7 +506,10 @@
+[docs]
+ defcompute_rule_antecedent_memberships(self,x:np.array,scaled=False,antecedents_memberships:list[np.array]=None)->np.array:''' Computes the antecedent truth value of an input array.
@@ -544,7 +602,10 @@
+[docs]
+ @abc.abstractmethoddeffuzzy_type(self)->fs.FUZZY_SETS:''' Returns the corresponding type of the RuleBase using the enum type in the fuzzy_sets module.
@@ -600,6 +670,7 @@
Source code for ex_fuzzy.rules
raiseNotImplementedError
+
def__len__(self):''' Returns the number of rules in the rule base.
@@ -607,7 +678,9 @@
+[docs]
+ defprune_bad_rules(self,tolerance=0.01)->None:''' Delete the rules from the rule base that do not have a dominance score superior to the threshold or have 0 accuracy in the training set.
@@ -632,7 +705,10 @@
+[docs]
+ defn_linguistic_variables(self)->int:''' Returns the number of linguistic variables in the rule base. '''
- return[len(amt)foramtinself.antecedents]
+[docs]
+classRuleBaseT2(RuleBase):''' Class optimized to work with multiple rules at the same time. Supports only one consequent. (Use one rulebase per consequent to study classification problems. Check MasterRuleBase class for more documentation)
@@ -755,7 +838,9 @@
+[docs]
+ deffuzzy_type(self)->fs.FUZZY_SETS:''' Returns the correspoing type of the RuleBase using the enum type in the fuzzy_sets module. :return: the corresponding fuzzy set type of the RuleBase. '''
- returnfs.FUZZY_SETS.t2
+[docs]
+classRuleBaseGT2(RuleBase):''' Class optimized to work with multiple rules at the same time. Supports only one consequent. (Use one rulebase per consequent to study classification problems. Check MasterRuleBase class for more documentation)
@@ -826,7 +921,9 @@
+[docs]
+ deffuzzy_type(self)->fs.FUZZY_SETS:''' Returns the correspoing type of the RuleBase using the enum type in the fuzzy_sets module.
@@ -878,7 +981,10 @@
+[docs]
+ defcompute_rule_antecedent_memberships(self,x:np.array,scaled=True,antecedents_memberships=None)->np.array:''' Computes the membership for the antecedents performing the alpha_cut reduction.
@@ -887,11 +993,16 @@
Source code for ex_fuzzy.rules
:param antecedents_memberships: precomputed antecedent memberships. Not supported for GT2. :return: array with the memberships of the antecedents for each sample. '''
- antecedent_membership=super().compute_rule_antecedent_memberships(x,scaled)
- returnself._alpha_reduction(antecedent_membership)
+[docs]
+ defalpha_compute_rule_antecedent_memberships(self,x:np.array,scaled=True,antecedents_memberships=None)->np.array:''' Computes the membership for the antecedents for all the alpha cuts.
@@ -900,11 +1011,15 @@
Source code for ex_fuzzy.rules
:param antecedents_memberships: precomputed antecedent memberships. Not supported for GT2. :return: array with the memberships of the antecedents for each sample. '''
- returnsuper().compute_rule_antecedent_memberships(x,scaled)
+[docs]
+classRuleBaseT1(RuleBase):''' Class optimized to work with multiple rules at the same time. Supports only one consequent. (Use one rulebase per consequent to study classification problems. Check MasterRuleBase class for more documentation)
@@ -947,7 +1062,9 @@
+[docs]
+ deffuzzy_type(self)->fs.FUZZY_SETS:''' Returns the correspoing type of the RuleBase using the enum type in the fuzzy_sets module. :return: the corresponding fuzzy set type of the RuleBase. '''
- returnfs.FUZZY_SETS.t1
+[docs]
+classMasterRuleBase():''' This Class encompasses a list of rule bases where each one corresponds to a different class. '''
@@ -1013,14 +1140,19 @@
+[docs]
+ defrename_cons(self,consequent_names:list[str])->None:''' Renames the consequents of the rule base. '''self.consequent_names=consequent_names
+[docs]
+ defget_consequents_names(self)->list[str]:''' Returns a list with the names of the consequents. :return: list with the names of the consequents. '''returnself.consequent_names
+[docs]
+ defget_rulebase_matrix(self)->list[np.array]:''' Returns a list with the rulebases for each antecedent in matrix format.
@@ -1057,7 +1198,10 @@
+[docs]
+ defcompute_firing_strenghts(self,X,precomputed_truth=None)->np.array:''' Computes the firing strength of each rule for each sample.
@@ -1099,10 +1249,11 @@
Source code for ex_fuzzy.rules
forixinrange(len(self.rule_bases)):aux.append(self[ix].compute_rule_antecedent_memberships(X,antecedents_memberships=precomputed_truth))
- # Firing strengths shape: samples x rules
+ # Firing strengths shape: samples x rules (x 2) (last is iv dimension) or (x alpha_cuts x 2) for gt2returnnp.concatenate(aux,axis=1)
+[docs]
+ defcompute_association_degrees(self,X,precomputed_truth=None):''' Returns the winning rule for each sample. Takes into account dominance scores if already computed. :param X: array with the values of the inputs.
@@ -1145,9 +1298,12 @@
+[docs]
+ defwinning_rule_predict(self,X:np.array,precomputed_truth=None,out_class_names=False)->np.array:''' Returns the winning rule for each sample. Takes into account dominance scores if already computed.
@@ -1188,7 +1344,10 @@
+[docs]
+ deffuzzy_type(self)->fs.FUZZY_SETS:''' Returns the correspoing type of the RuleBase using the enum type in the fuzzy_sets module.
@@ -1238,7 +1406,10 @@
+[docs]
+ defpurge_rules(self,tolerance=0.001)->None:''' Delete the roles with a dominance score lower than the tolerance.
@@ -1248,6 +1419,7 @@
Source code for ex_fuzzy.rules
ruleBase.prune_bad_rules(tolerance)
+
def__getitem__(self,item)->RuleBase:''' Returns the corresponding rulebase.
@@ -1297,9 +1469,24 @@
Source code for ex_fuzzy.rules
# Convert the predictions to the names of the consequents#return np.array(self.consequent_names)[aux]returnaux
+
+
+
+[docs]
+ defpredict(self,X:np.array)->np.array:
+'''
+ Gives the prediction for each sample (same as winning_rule_predict)
+
+ :param X: array of dims: samples x features.
+ :return: vector of predictions, size: samples,
+ '''
+ returnself(X)