Mercurial Hosting > traffic-intelligence

comparison scripts/process.py @ 1084:1a7e0b2c858b

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
remove debugging
author Nicolas Saunier <nicolas.saunier@polymtl.ca>
date Tue, 24 Jul 2018 01:24:42 -0400
parents 5b597b021aed
children 8734742c08c0
comparison
equal deleted inserted replaced
1083:5b597b021aed 1084:1a7e0b2c858b
334 # plt.close() 334 # plt.close()
335 elif args.output == 'event': 335 elif args.output == 'event':
336 data.to_csv(args.eventFilename, index = False) 336 data.to_csv(args.eventFilename, index = False)
337 337
338 if args.analyze == 'event-speed': # aggregate event data by 15 min interval (args.intervalDuration), count events with thresholds 338 if args.analyze == 'event-speed': # aggregate event data by 15 min interval (args.intervalDuration), count events with thresholds
339 data = pd.read_csv(args.eventFilename, parse_dates = [2], nrows = 10000) 339 data = pd.read_csv(args.eventFilename, parse_dates = [2])
340 #data = pd.read_csv('./speeds.csv', converters = {'time': lambda s: datetime.datetime.strptime(s, "%H:%M:%S").time()}, nrows = 5000) 340 #data = pd.read_csv('./speeds.csv', converters = {'time': lambda s: datetime.datetime.strptime(s, "%H:%M:%S").time()}, nrows = 5000)
341 # create time for end of each 15 min, then group by, using the agg method for each data column 341 # create time for end of each 15 min, then group by, using the agg method for each data column
342 headers = ['site', 'date', 'intervalend15', 'duration', 'count'] 342 headers = ['site', 'date', 'intervalend15', 'duration', 'count']
343 aggFunctions, tmpheaders = utils.aggregationMethods(args.aggMethods, args.aggCentiles) 343 aggFunctions, tmpheaders = utils.aggregationMethods(args.aggMethods, args.aggCentiles)
344 dataColumns = list(data.columns[4:]) 344 dataColumns = list(data.columns[4:])
371 row.append((group[h] > t).sum()) 371 row.append((group[h] > t).sum())
372 outputData.append(row) 372 outputData.append(row)
373 pd.DataFrame(outputData, columns = headers).to_csv(utils.removeExtension(args.eventFilename)+'-aggregated.csv', index = False) 373 pd.DataFrame(outputData, columns = headers).to_csv(utils.removeExtension(args.eventFilename)+'-aggregated.csv', index = False)
374 374
375 elif args.analyze == 'event-interaction': # aggregate event data by 15 min interval (args.intervalDuration), count events with thresholds 375 elif args.analyze == 'event-interaction': # aggregate event data by 15 min interval (args.intervalDuration), count events with thresholds
376 data = pd.read_csv(args.eventFilename, parse_dates = [2], nrows = 20000) 376 data = pd.read_csv(args.eventFilename, parse_dates = [2])
377 headers = ['site', 'date', 'intervalend15', 'duration', 'count'] 377 headers = ['site', 'date', 'intervalend15', 'duration', 'count']
378 aggFunctions, tmpheaders = utils.aggregationMethods(args.aggMethods, args.aggCentiles) 378 aggFunctions, tmpheaders = utils.aggregationMethods(args.aggMethods, args.aggCentiles)
379 dataColumns = list(data.columns[3:]) 379 dataColumns = list(data.columns[3:])
380 for h in dataColumns: 380 for h in dataColumns:
381 if not 'speed' in h.lower(): # proximity indicators are reversed, taking 85th centile of this column will yield the 15th centile (which we have to take the opposite again) 381 if not 'speed' in h.lower(): # proximity indicators are reversed, taking 85th centile of this column will yield the 15th centile (which we have to take the opposite again)