from Spark import *

def subwayWaitingTime():
    subway = SubwaySpark()
    test_file = [('a',44),('a',10),('a',11),('a',12),('a',5),('c',3),('b',2),('a',1),('a',6),('a',3)]
    subway.setLocalInputFile(test_file)
    subway.buildRecordList()

def groupTripByList():
    subway = SubwaySpark()
    subway.setHDFSFilePath('/zf72/transportation_data/subway_bus/P_GJGD_SZT_20160601')
    #subway.setLocalFilePath("/home/zf72/Dropbox/projects/off-peak-trans/data/SZT/P_GJGD_SZT_20160601")
    #subway.setLocalFilePath("/home/zf72/Dropbox/projects/off-peak-trans/data/sample/public_sample.txt")
    subway.buildRecordList()
    subway.buildTripList()
    # subway.buildTripTimeMatrix()
    subway.buildInVehicleTime()
    subway.buildWaitingTime()
    #subway.saveAverageTripTime('/zf72/transportation_data/result/P_GJGD_SZT_20160601',local=False)
    #subway.saveAverageTripTime("file:/home/zf72/Dropbox/projects/off-peak-trans/data/SZT_RESULT/P_GJGD_SZT_20160601",local=True)

if __name__ == "__main__":
    groupTripByList()