models_classification.py 文件源码

def calc_model_characteristics(self, performCV=True):
        # Determine key metrics to analyze the classification model. These 
        # are stored in the classification_output series object belonginf to 
        # this class.
        for metric in [self.scoring_metric]+self.additional_display_metrics:
            #Determine for both test and train, except predict:
            for key,data in self.dp.items():
                if key!='predict':  
                    name = '%s_%s'%(metric,key)
                    #Case where probabilities to be passed as arguments
                    if base_classification.metrics_map[metric][2]:
                        self.classification_output[name] = \
                            base_classification.metrics_map[metric][0](
                                data[self.datablock.target],
                                self.predictions_probabilities[key])
                    #case where class predictions to be passed  as arguments
                    else:                                                   
                        self.classification_output[name] = \
                            base_classification.metrics_map[metric][0](
                                data[self.datablock.target],
                                self.predictions_class[key])

                #Determine confusion matrix:
                name = 'ConfusionMatrix_%s'%key
                self.classification_output[name] = pd.crosstab(
                        data[self.datablock.target], 
                        self.predictions_class[key]
                    ).to_string()

        if performCV:
            cv_score = self.KFold_CrossValidation(
                        scoring_metric=self.scoring_metric)
        else:
            cv_score = {
                'mean_error': 0.0, 
                'std_error': 0.0
            }

        self.classification_output['CVMethod'] = \
                                        'KFold - ' + str(self.cv_folds)
        self.classification_output['CVScore_mean'] = cv_score['mean_error']
        self.classification_output['CVScore_std'] = cv_score['std_error']
        self.classification_output['Predictors'] = str(self.predictors)