dmonscilearncluster.py 文件源码

def detect(self, method, model, data):
        '''
        :param method: -> method name
        :param model: -> trained clusterer
        :param data: -> dataframe with data
        :return: -> dictionary that contains the list of anomalous timestamps
        '''
        smodel = self.__loadClusterModel(method, model)
        anomalieslist = []
        if not smodel:
            dpredict = 0
        else:
            if data.shape[0]:
                if isinstance(smodel, IsolationForest):
                    print "Detected IsolationForest model"
                    print "Contamination -> %s" % smodel.contamination
                    print "Max_Features -> %s" % smodel.max_features
                    print "Max_Samples -> %s" % smodel.max_samples_
                    print "Threashold -> %s " % smodel.threshold_
                    try:
                        dpredict = smodel.predict(data)
                        print "IsolationForest Prediction Array -> %s" %str(dpredict)
                    except Exception as inst:
                        logger.error('[%s] : [ERROR] Error while fitting isolationforest model to event with %s and %s',
                             datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H:%M:%S'), type(inst), inst.args)
                        dpredict = 0

                elif isinstance(smodel, DBSCAN):
                    print "Detected DBSCAN model"
                    print "Leaf_zise -> %s" % smodel.leaf_size
                    print "Algorithm -> %s" % smodel.algorithm
                    print "EPS -> %s" % smodel.eps
                    print "Min_Samples -> %s" % smodel.min_samples
                    print "N_jobs -> %s" % smodel.n_jobs
                    try:
                        dpredict = smodel.fit_predict(data)
                    except Exception as inst:
                        logger.error('[%s] : [ERROR] Error while fitting sDBSCAN model to event with %s and %s',
                                     datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H:%M:%S'), type(inst),
                                     inst.args)
                        dpredict = 0
            else:
                dpredict = 0
                logger.warning('[%s] : [WARN] Dataframe empty with shape (%s,%s)',
                             datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H:%M:%S'), str(data.shape[0]),
                             str(data.shape[1]))
                print "Empty dataframe received with shape (%s,%s)" % (str(data.shape[0]),
                             str(data.shape[1]))
            print "dpredict type is %s" % (type(dpredict))
            if type(dpredict) is not int:
                anomalyarray = np.argwhere(dpredict == -1)
                for an in anomalyarray:
                    anomalies = {}
                    anomalies['utc'] = int(data.iloc[an[0]]['key'])
                    anomalies['hutc'] = ut2hum(int(data.iloc[an[0]]['key']))
                    anomalieslist.append(anomalies)
        anomaliesDict = {}
        anomaliesDict['anomalies'] = anomalieslist
        logger.info('[%s] : [INFO] Detected anomalies with model %s using method %s are -> %s',
                         datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H:%M:%S'), model, method, str(anomaliesDict))
        return anomaliesDict