def crossesThreshold(start_date, end_date, mahal_timeseries, threshold): for key in [ keyFromDatetime(d) for d in dateRange(start_date, end_date, timedelta(hours=1)) ]: if (key in mahal_timeseries and mahal_timeseries[key] > threshold): return True
def detectWindowedEvents(mahal_timeseries, zscore_timeseries, global_pace_timeseries, out_file, window_size=6, threshold_quant=.95): logMsg("Detecting events at %d%% bound" % int(threshold_quant*100)) #Sort the keys of the timeseries chronologically sorted_dates = sorted(mahal_timeseries) #Generate the list of values of R(t) mahal_list = [mahal_timeseries[d] for d in sorted_dates] #Use the quantile to determine the threshold sorted_mahal = sorted(mahal_list) threshold = getQuantile(sorted_mahal, threshold_quant) # Get the expected global pace (expected_pace_timeseries, sd_pace_timeseries) = getExpectedPace(global_pace_timeseries) start_date = datetime(2010,1,1) end_date = datetime(2014,1,1) shift = timedelta(hours=window_size) prev_above_threshold = False current_event_start = None current_event_end = None eventList = [] for date in dateRange(start_date, end_date, shift): #print #print(str(date)) #print(prev_above_threshold) if(crossesThreshold(date, date+shift, mahal_timeseries, threshold)): #print("CROSS") if(not prev_above_threshold): #print("RESET") current_event_start = date current_event_end = date+shift prev_above_threshold=True else: if(prev_above_threshold): #print("*************OUTPUTTING************") #print("%s -> %s" % (current_event_start, current_event_end)) start_key = keyFromDatetime(current_event_start) end_key = keyFromDatetime(current_event_end) event = computeEventProperties(start_key, end_key, mahal_timeseries, global_pace_timeseries, expected_pace_timeseries, zscore_timeseries, sorted_mahal=sorted_mahal, mahal_threshold=threshold) #Add to list eventList.append(event) prev_above_threshold =False #Sort events by duration, in descending order eventList.sort(key = lambda x: x[5], reverse=True) #Write events to a CSV file w = csv.writer(open(out_file, "w")) w.writerow(["start_date", "end_date", "max_mahal", "mahal_quant", "duration", "hours_above_thresh", "max_pace_dev", "min_pace_dev", "worst_trip"]) for event in eventList: [start_date, end_date, max_mahal, mahal_quant, duration, hours_above_thresh, max_pace_dev, min_pace_dev, worst_trip] = event formattedEvent = [start_date, end_date, "%.2f" % max_mahal, "%.3f" % mahal_quant, duration, hours_above_thresh, "%.2f" % max_pace_dev, "%.2f" % min_pace_dev, worst_trip] w.writerow(formattedEvent) return eventList
def crossesThreshold(start_date, end_date, mahal_timeseries, threshold): for key in [keyFromDatetime(d) for d in dateRange(start_date, end_date, timedelta(hours=1))]: if(key in mahal_timeseries and mahal_timeseries[key] > threshold): return True
def detectWindowedEvents(mahal_timeseries, zscore_timeseries, global_pace_timeseries, out_file, window_size=6, threshold_quant=.95): logMsg("Detecting events at %d%% bound" % int(threshold_quant * 100)) #Sort the keys of the timeseries chronologically sorted_dates = sorted(mahal_timeseries) #Generate the list of values of R(t) mahal_list = [mahal_timeseries[d] for d in sorted_dates] #Use the quantile to determine the threshold sorted_mahal = sorted(mahal_list) threshold = getQuantile(sorted_mahal, threshold_quant) # Get the expected global pace (expected_pace_timeseries, sd_pace_timeseries) = getExpectedPace(global_pace_timeseries) start_date = datetime(2010, 1, 1) end_date = datetime(2014, 1, 1) shift = timedelta(hours=window_size) prev_above_threshold = False current_event_start = None current_event_end = None eventList = [] for date in dateRange(start_date, end_date, shift): #print #print(str(date)) #print(prev_above_threshold) if (crossesThreshold(date, date + shift, mahal_timeseries, threshold)): #print("CROSS") if (not prev_above_threshold): #print("RESET") current_event_start = date current_event_end = date + shift prev_above_threshold = True else: if (prev_above_threshold): #print("*************OUTPUTTING************") #print("%s -> %s" % (current_event_start, current_event_end)) start_key = keyFromDatetime(current_event_start) end_key = keyFromDatetime(current_event_end) event = computeEventProperties(start_key, end_key, mahal_timeseries, global_pace_timeseries, expected_pace_timeseries, zscore_timeseries, sorted_mahal=sorted_mahal, mahal_threshold=threshold) #Add to list eventList.append(event) prev_above_threshold = False #Sort events by duration, in descending order eventList.sort(key=lambda x: x[5], reverse=True) #Write events to a CSV file w = csv.writer(open(out_file, "w")) w.writerow([ "start_date", "end_date", "max_mahal", "mahal_quant", "duration", "hours_above_thresh", "max_pace_dev", "min_pace_dev", "worst_trip" ]) for event in eventList: [ start_date, end_date, max_mahal, mahal_quant, duration, hours_above_thresh, max_pace_dev, min_pace_dev, worst_trip ] = event formattedEvent = [ start_date, end_date, "%.2f" % max_mahal, "%.3f" % mahal_quant, duration, hours_above_thresh, "%.2f" % max_pace_dev, "%.2f" % min_pace_dev, worst_trip ] w.writerow(formattedEvent) return eventList