data_manager.py 文件源码

def getTypeProblem (self, solution_filename):
            ''' Get the type of problem directly from the solution file (in case we do not have an info file)'''
        if 'task' not in self.info.keys():
            solution = np.array(data_converter.file_to_array(solution_filename))
            target_num = solution.shape[1]
            self.info['target_num']=target_num
            if target_num == 1: # if we have only one column
                solution = np.ravel(solution) # flatten
                nbr_unique_values = len(np.unique(solution))
                if nbr_unique_values < len(solution)/8:
                    # Classification
                    self.info['label_num'] = nbr_unique_values
                    if nbr_unique_values == 2:
                        self.info['task'] = 'binary.classification'
                        self.info['target_type'] = 'Binary'
                    else:
                        self.info['task'] = 'multiclass.classification'
                        self.info['target_type'] = 'Categorical'
                else:
                    # Regression
                    self.info['label_num'] = 0
                    self.info['task'] = 'regression'
                    self.info['target_type'] = 'Numerical'     
            else:
                # Multilabel or multiclass       
                self.info['label_num'] = target_num
                self.info['target_type'] = 'Binary' 
                if any(item > 1 for item in map(np.sum,solution.astype(int))):
                    self.info['task'] = 'multilabel.classification'     
                else:
                    self.info['task'] = 'multiclass.classification'        
        return self.info['task']