Python JobManager.runQueue方法代码示例

# 需要导入模块: import JobManager [as 别名]
# 或者: from JobManager import runQueue [as 别名]
    def run(self, name, datafiles, goldnet_file):
        import numpy

        os.chdir(os.environ["gene_path"])

        datastore = ReadData(datafiles[0], "steadystate")
        for file in datafiles[1:]:
            datastore.combine(ReadData(file, "steadystate"))
        datastore.normalize()

        settings = {}
        settings = ReadConfig(settings)
        # TODO: CHANGE ME
        settings["global"]["working_dir"] = os.getcwd() + '/'

        # Setup job manager
        print "Starting new job manager"
        jobman = JobManager(settings)

        # Make GENIE3 jobs
        genie3 = GENIE3()
        genie3.setup(datastore, settings, name)

        print "Queuing job..."
        jobman.queueJob(genie3)

        print jobman.queue
        print "Running queue..."
        jobman.runQueue()
        jobman.waitToClear()

        print "Queue finished"
        job = jobman.finished[0]
        print job.alg.gene_list
        print job.alg.read_output(settings)
        jobnet = job.alg.network
        print "PREDICTED NETWORK:"
        print job.alg.network.network
        print jobnet.original_network

        if goldnet_file != None:
            goldnet = Network()
            goldnet.read_goldstd(goldnet_file)
            print "GOLD NETWORK:"
            print goldnet.network
            print jobnet.analyzeMotifs(goldnet).ToString()
            print jobnet.calculateAccuracy(goldnet)

        return jobnet.original_network

# 需要导入模块: import JobManager [as 别名]
# 或者: from JobManager import runQueue [as 别名]
    def run(self, ts_file, name=None, delta_t=30):

        os.chdir(os.environ["gene_path"])

        print "Reading in knockout data"
        timeseries_storage = ReadData(ts_file, "timeseries")

        settings = {}
        settings = ReadConfig(settings)
        # TODO: CHANGE ME
        settings["global"]["working_dir"] = os.getcwd() + "/"

        # Setup job manager
        print "Starting new job manager"
        jobman = JobManager(settings)

        # Make Banjo jobs
        banjojob = Banjo()
        if delta_t != None:
            settings["global"]["time_series_delta_t"] = int(delta_t)
        else:
            settings["global"]["time_series_delta_t"] = 30
        if name != None:
            banjojob.setup(timeseries_storage, settings, name)
        else:
            banjojob.setup(timeseries_storage, settings)

        print "Queuing job..."
        jobman.queueJob(banjojob)

        print jobman.queue
        print "Running queue..."
        jobman.runQueue()
        jobman.waitToClear()

        print "Queue finished"
        job = jobman.finished[0]
        print job.alg.gene_list
        print job.alg.read_output(settings)
        jobnet = job.alg.network
        print "PREDICTED NETWORK:"
        # print job.alg.network.network
        # print jobnet.original_network

        return jobnet.original_network

# 需要导入模块: import JobManager [as 别名]
# 或者: from JobManager import runQueue [as 别名]
        settings["global"]["time_series_delta_t"] = (1008.0 / (len(ts_storage[0].experiments)-1))
        combined = ReadData(exp_data_directory + '/' + name + '/' + timeseries_filename, "timeseries")[0]

        for ts in timeseries_as_steady_state[name][1:11]:
            combined.combine(ts)
        #combined.combine(knockouts[name])
        combined.combine(multifactorials[name])

        genie3job = GENIE3()
        genie3job.setup(combined, settings, "Genie3_TimeSeries_{0}_{1}".format(name, i))
        jobman.queueJob(genie3job)
        genie3nets[name] = genie3job
        genie3job.goldnet = goldnets[name]


jobman.runQueue()
jobman.waitToClear()


for job in jobman.finished:
    job.alg.network.normalize()

#tprs, fprs, rocs = GenerateMultiROC(jobman.finished, goldnet, False, settings["global"]["output_dir"] + "/OverallROC.pdf")
#ps, rs, precs = GenerateMultiPR(jobman.finished, goldnet, False, settings["global"]["output_dir"] + "/OverallPR.pdf")

#for job in jobman.finished:
    #tprs, fprs, rocs = GenerateMultiROC([job], job.alg.goldnet, False, settings["global"]["output_dir"] + "/" + job.alg.name + ".pdf")
    #ps, rs, precs = GenerateMultiPR([job], job.alg.goldnet, False, settings["global"]["output_dir"] + "/" + job.alg.name + ".pdf")

accs, precs, rocs = SaveResults(jobman.finished, goldnet, settings)

# 需要导入模块: import JobManager [as 别名]
# 或者: from JobManager import runQueue [as 别名]
def get_network_results(name, settings, cache):
  print "STARTING", name

  if name in cache.keys():
    print "CACHE HIT"
    return cache[name]

  ko_file, kd_file, ts_file, wt_file, mf_file, goldnet = get_example_data_files(name, settings)

  # Create date string to append to output_dir
  t = datetime.now().strftime("%Y-%m-%d_%H.%M.%S")
  settings["global"]["output_dir"] = settings["global"]["output_dir_save"] + "/" + \
      settings["global"]["experiment_name"] + "-" + t + "-" + name + "/"
  os.mkdir(settings["global"]["output_dir"])

  # Get a list of the multifactorial files

  # Read data into program
  # Where the format is "FILENAME" "DATATYPE"
  mf_storage = ReadData(mf_file[0], "multifactorial")
  knockout_storage = ReadData(ko_file[0], "knockout")
  knockdown_storage = ReadData(kd_file[0], "knockdown")
  wildtype_storage = ReadData(wt_file[0], "wildtype")
  timeseries_storage = ReadData(ts_file[0], "timeseries")
  gene_list = knockout_storage.gene_list

  # Setup job manager
  jobman = JobManager(settings)

  # MCZ
  mczjob = MCZ()
  mczjob.setup(knockout_storage, wildtype_storage, settings, timeseries_storage, knockdown_storage, "MCZ")
  jobman.queueJob(mczjob)

  # CLR
  clrjob = CLR()
  clrjob.setup(knockout_storage, settings, "CLR", "plos", 6)
  jobman.queueJob(clrjob)

  # GENIE3
  mf_storage.combine(knockout_storage)
  mf_storage.combine(wildtype_storage)
  mf_storage.combine(knockdown_storage)
  genie3job = GENIE3()
  genie3job.setup(mf_storage, settings, "GENIE3")
  jobman.queueJob(genie3job)

  ## TLCLR
  tlclrjob = TLCLR()
  tlclrjob.setup(knockout_storage, wildtype_storage, settings, timeseries_storage, knockdown_storage, "TLCLR")
  jobman.queueJob(tlclrjob)

  #if sys.argv[1] != "dream4100":
      #cojob = ConvexOptimization()
      #cojob.setup(knockout_storage, settings, "ConvOpt_T-"+ str(0.01),None, None, 0.01)
      #jobman.queueJob(cojob)

  ### DFG4GRN
  dfg = DFG4GRN()
  settings["dfg4grn"]["eta_z"] = 0.01
  settings["dfg4grn"]["lambda_w"] = 0.001
  settings["dfg4grn"]["tau"] = 3
  dfg.setup(timeseries_storage, TFList(timeseries_storage[0].gene_list), settings, "DFG", 20)
  jobman.queueJob(dfg)

  ### Inferelator

  ### NIR
  nirjob = NIR()
  nirjob.setup(knockout_storage, settings, "NIR", 5, 5)
  jobman.queueJob(nirjob)

  #### TDARACNE
  settings = ReadConfig(settings, "./config/default_values/tdaracne.cfg")
  bjob = tdaracne()
  settings["tdaracne"]["num_bins"] = 4
  bjob.setup(timeseries_storage, settings, "TDARACNE")
  jobman.queueJob(bjob)


  print jobman.queue
  jobman.runQueue()
  jobman.waitToClear(name)
  SaveResults(jobman.finished, goldnet, settings, name)

  cache[name] = jobman.finished[:]

  return cache[name]

# 需要导入模块: import JobManager [as 别名]
# 或者: from JobManager import runQueue [as 别名]
    def run(self, kofile, tsfile, wtfile, datafiles, name, goldnet_file, normalize=False):
        os.chdir(os.environ["gene_path"])
        knockout_storage = ReadData(kofile, "knockout")
        print "Reading in knockout data"
        wildtype_storage = ReadData(wtfile, "steadystate")

        if datafiles == []:
          other_storage = None
        else:
          other_storage = ReadData(datafiles[0], "steadystate")
          for file in datafiles[1:]:
              other_storage.combine(ReadData(file, "steadystate"))

        timeseries_storage = None
        if tsfile != None:
            timeseries_storage = ReadData(tsfile, "timeseries")
            #for ts in timeseries_storage:
                #ts.normalize()

        #if normalize:
            #knockout_storage.normalize()
            #wildtype_storage.normalize()
            #other_storage.normalize()


        settings = {}
        settings = ReadConfig(settings)
        # TODO: CHANGE ME
        settings["global"]["working_dir"] = os.getcwd() + '/'

        # Setup job manager
        print "Starting new job manager"
        jobman = JobManager(settings)

        # Make inferelator jobs
        inferelatorjob = inferelator()
        inferelatorjob.setup(knockout_storage, wildtype_storage, settings, timeseries_storage, other_storage, name)

        print "Queuing job..."
        jobman.queueJob(inferelatorjob)

        print jobman.queue
        print "Running queue..."
        jobman.runQueue()
        jobman.waitToClear()

        print "Queue finished"
        job = jobman.finished[0]
        #print job.alg.gene_list
        #print job.alg.read_output(settings)
        jobnet = job.alg.network
        #print "PREDICTED NETWORK:"
        #print job.alg.network.network
        print jobnet.original_network

        if goldnet_file != None:
            goldnet = Network()
            goldnet.read_goldstd(goldnet_file)
            #print "GOLD NETWORK:"
            #print goldnet.network
            #print jobnet.analyzeMotifs(goldnet).ToString()
            print jobnet.calculateAccuracy(goldnet)
            import AnalyzeResults
            tprs, fprs, rocs = AnalyzeResults.GenerateMultiROC(jobman.finished, goldnet )
            ps, rs, precs = AnalyzeResults.GenerateMultiPR(jobman.finished, goldnet)
            print "Area Under ROC"
            print rocs

            print "Area Under PR"
            print precs

        return jobnet.original_network