def make_singles_plot(workflow, trig_files, bank_file, veto_file, veto_name, out_dir, exclude=None, require=None, tags=None): tags = [] if tags is None else tags makedir(out_dir) secs = requirestr(workflow.cp.get_subsections('plot_singles'), require) secs = excludestr(secs, exclude) files = FileList([]) for tag in secs: for trig_file in trig_files: node = PlotExecutable(workflow.cp, 'plot_singles', ifos=trig_file.ifo, out_dir=out_dir, tags=[tag] + tags).create_node() node.add_input_opt('--bank-file', bank_file) if veto_file is not None: node.add_input_opt('--veto-file', veto_file) node.add_opt('--segment-name', veto_name) node.add_opt('--detector', trig_file.ifo) node.add_input_opt('--single-trig-file', trig_file) node.new_output_file_opt(trig_file.segment, '.png', '--output-file') workflow += node files += node.output_files return files
def setup_postprocprep_pipedown_workflow(workflow, coincFiles, output_dir, tags=[], do_repop=False, injectionFiles=None, vetoFiles=None, injLessTag=None, injectionTags=[], veto_cats=[]): """ Parameters ----------- workflow : pycbc.workflow.core.Workflow The Workflow instance that the coincidence jobs will be added to. coincFiles : pycbc.workflow.core.FileList An FileList of the coincident trigger files that are used as input at this stage. output_dir : path The directory in which output files will be stored. tags : list of strings (optional, default = []) A list of the tagging strings that will be used for all jobs created by this call to the workflow. An example might be ['POSTPROC1'] or ['DENTYSNEWPOSTPROC']. This will be used in output names. do_repop : Boolean If False, use the 'coinc_inspiral.snr' column from the coincident trigger files as clustering and ranking statistic; if True, use a repop_coinc job before clustering to calculate a different ranking statistic and store in the coinc_inspiral table for later use. injectionFiles : pycbc.workflow.core.FileList (optional, default=None) The injection files to be used in this stage. An empty list (or any other input that evaluates as false) is valid and will imply that no injections are being done. vetoFiles : pycbc.workflow.core.FileList (required) The data quality files to be used in this stage. This is required and will be used to determine the analysed times when doing post-processing. injLessTag : string (required) The tag that identifies files that do not have simulations in them. Ie. the primary search results. injectionTags : list of strings (optional, default = []) Each injection file has a unique tag. If used in the method, this tells the post-processing preparation code which injection tags it should include when creating the combined output. veto_cats : list of integers (optional, default = []) Decide which set of veto files should be used in the post-processing preparation. For example tell the workflow to only generate results at cumulative categories 2, 3 and 4 by supplying [2,3,4] here. Returns -------- finalFiles : pycbc.workflow.core.FileList A list of the single SQL database storing the clustered, injection found, triggers for all injections, time slid and zero lag analyses. initialSqlFiles : pycbc.workflow.core.FileList The SQL files before clustering is applied and injection finding performed. clusteredSqlFiles : pycbc.workflow.core.FileList The clustered SQL files before injection finding performed. combinedSqlFiles : pycbc.workflow.core.FileList A combined file containing all triggers after clustering, including the injection and veto tables, but before injection finding performed. Probably there is no need to ever keep this file and it will be a temporary file in most cases. """ if not veto_cats: raise ValueError("A non-empty list of veto categories is required.") # Setup needed exe classes sqliteCombine1ExeTag = workflow.cp.get_opt_tags("workflow-postprocprep", "postprocprep-combiner1-exe", tags) sqliteCombine1Exe = select_generic_executable(workflow, sqliteCombine1ExeTag) sqliteCombine2ExeTag = workflow.cp.get_opt_tags("workflow-postprocprep", "postprocprep-combiner2-exe", tags) sqliteCombine2Exe = select_generic_executable(workflow, sqliteCombine2ExeTag) clusterCoincsExeTag = workflow.cp.get_opt_tags("workflow-postprocprep", "postprocprep-cluster-exe", tags) clusterCoincsExe = select_generic_executable(workflow, clusterCoincsExeTag) injFindExeTag = workflow.cp.get_opt_tags("workflow-postprocprep", "postprocprep-injfind-exe", tags) injFindExe = select_generic_executable(workflow, injFindExeTag) sqliteCombine1Outs = FileList([]) clusterCoincsOuts = FileList([]) injFindOuts = FileList([]) sqliteCombine2Outs = FileList([]) if do_repop: repopCoincExeTag = workflow.cp.get_opt_tags("workflow-postprocprep", "postprocprep-repop-exe", tags) repopCoincExe = select_generic_executable(workflow, repopCoincExeTag) repopCoincOuts = FileList([]) for cat in veto_cats: # FIXME: Some hacking is still needed while we support pipedown # FIXME: There are currently 3 names to say cumulative cat_3 vetoTag = 'CUMULATIVE_CAT_%d' %(cat) dqSegFile = vetoFiles.find_output_with_tag(vetoTag) if not len(dqSegFile) == 1: errMsg = "Did not find exactly 1 data quality file." raise ValueError(errMsg) # Don't think this is used here, this is the tag *in* the file dqVetoName = 'VETO_CAT%d_CUMULATIVE' %(cat) # FIXME: Here we set the dqVetoName to be compatible with pipedown pipedownDQVetoName = 'CAT_%d_VETO' %(cat) sqliteCombine2Inputs = FileList([]) # Do injection-less jobs first. # Choose a label for clustering the jobs job_label = get_random_label() # Combine trig files first currTags = tags + [injLessTag, vetoTag] trigVetoInpFiles = coincFiles.find_output_with_tag(pipedownDQVetoName) trigInpFiles = trigVetoInpFiles.find_output_with_tag(injLessTag) if len(trigInpFiles) == 0: err_msg = "No input files found. Workflow would fail." raise ValueError(err_msg) trigInpFiles.append(dqSegFile[0]) sqliteCombine1Job = sqliteCombine1Exe(workflow.cp, sqliteCombine1ExeTag, ifo=workflow.ifo_string, out_dir=output_dir, tags=currTags) sqliteCombine1Node = sqliteCombine1Job.create_node( workflow.analysis_time, trigInpFiles, workflow=workflow) sqliteCombine1Node.add_profile('pegasus', 'label', job_label) workflow.add_node(sqliteCombine1Node) # Node has only one output file sqliteCombine1Out = sqliteCombine1Node.output_files[0] sqliteCombine1Outs.append(sqliteCombine1Out) if do_repop: repopCoincJob = repopCoincExe(workflow.cp, repopCoincExeTag, ifo=workflow.ifo_string, out_dir=output_dir, tags=currTags) repopCoincNode = repopCoincJob.create_node(workflow.analysis_time, sqliteCombine1Out) repopCoincNode.add_profile('pegasus', 'label', job_label) workflow.add_node(repopCoincNode) # Node has only one output file repopCoincOut = repopCoincNode.output_files[0] repopCoincOuts.append(repopCoincOut) # Input file plumbing allowing for possible repop_coinc job clusterCoincsIn = repopCoincOut if do_repop else sqliteCombine1Out # Cluster coincidences clusterCoincsJob = clusterCoincsExe(workflow.cp, clusterCoincsExeTag, ifo=workflow.ifo_string, out_dir=output_dir, tags=currTags) clusterCoincsNode = clusterCoincsJob.create_node( workflow.analysis_time, clusterCoincsIn) clusterCoincsNode.add_profile('pegasus', 'label', job_label) workflow.add_node(clusterCoincsNode) # Node has only one output file clusterCoincsOut = clusterCoincsNode.output_files[0] clusterCoincsOuts.append(clusterCoincsOut) sqliteCombine2Inputs.append(clusterCoincsOut) # Do injection jobs for injTag in injectionTags: # Choose a label for clustering the jobs job_label = get_random_label() # Combine trig files first currTags = tags + [injTag, vetoTag] trigInpFiles = trigVetoInpFiles.find_output_with_tag(injTag) trigInpFiles.append(dqSegFile[0]) injFile = injectionFiles.find_output_with_tag(injTag) assert (len(injFile) == 1) sqliteCombine1Job = sqliteCombine1Exe(workflow.cp, sqliteCombine1ExeTag, ifo=workflow.ifo_string, out_dir=output_dir, tags=currTags) sqliteCombine1Node = sqliteCombine1Job.create_node( workflow.analysis_time, trigInpFiles, injFile=injFile[0], injString=injTag, workflow=workflow) sqliteCombine1Node.add_profile('pegasus', 'label', job_label) workflow.add_node(sqliteCombine1Node) # Node has only one output file sqliteCombine1Out = sqliteCombine1Node.output_files[0] sqliteCombine1Outs.append(sqliteCombine1Out) if do_repop: repopCoincJob = repopCoincExe(workflow.cp, repopCoincExeTag, ifo=workflow.ifo_string, out_dir=output_dir, tags=currTags) repopCoincNode = repopCoincJob.create_node( workflow.analysis_time, sqliteCombine1Out) repopCoincNode.add_profile('pegasus', 'label', job_label) workflow.add_node(repopCoincNode) # Node has only one output file repopCoincOut = repopCoincNode.output_files[0] repopCoincOuts.append(repopCoincOut) # Input file plumbing allowing for possible repop_coinc job clusterCoincsIn = repopCoincOut if do_repop else sqliteCombine1Out # Cluster coincidences clusterCoincsJob = clusterCoincsExe(workflow.cp, clusterCoincsExeTag, ifo=workflow.ifo_string, out_dir=output_dir, tags=currTags) clusterCoincsNode = clusterCoincsJob.create_node( workflow.analysis_time, clusterCoincsIn) clusterCoincsNode.add_profile('pegasus', 'label', job_label) workflow.add_node(clusterCoincsNode) # Node has only one output file clusterCoincsOut = clusterCoincsNode.output_files[0] clusterCoincsOuts.append(clusterCoincsOut) sqliteCombine2Inputs.append(clusterCoincsOut) # Choose a new label for pegasus-clustering the jobs job_label = get_random_label() # Combine everything together and add veto file currTags = tags + [vetoTag] sqliteCombine2Job = sqliteCombine2Exe(workflow.cp, sqliteCombine2ExeTag, ifo=workflow.ifo_string, out_dir=output_dir, tags=currTags) sqliteCombine2Node = sqliteCombine2Job.create_node( workflow.analysis_time, sqliteCombine2Inputs) sqliteCombine2Node.add_profile('pegasus', 'label', job_label) workflow.add_node(sqliteCombine2Node) sqliteCombine2Out = sqliteCombine2Node.output_files[0] sqliteCombine2Outs.append(sqliteCombine2Out) # Inj finding injFindJob = injFindExe(workflow.cp, injFindExeTag, ifo=workflow.ifo_string, out_dir=output_dir,tags=currTags) injFindNode = injFindJob.create_node(workflow.analysis_time, sqliteCombine2Out) injFindNode.add_profile('pegasus', 'label', job_label) workflow.add_node(injFindNode) injFindOut = injFindNode.output_files[0] injFindOuts.append(injFindOut) return injFindOuts, sqliteCombine1Outs, clusterCoincsOuts,\ sqliteCombine2Outs
def get_coh_PTF_files(cp, ifos, run_dir, bank_veto=False, summary_files=False): """ Retrieve files needed to run coh_PTF jobs within a PyGRB workflow Parameters ---------- cp : pycbc.workflow.configuration.WorkflowConfigParser object The parsed configuration options of a pycbc.workflow.core.Workflow. ifos : str String containing the analysis interferometer IDs. run_dir : str The run directory, destination for retrieved files. bank_veto : Boolean If true, will retrieve the bank_veto_bank.xml file. summary_files : Boolean If true, will retrieve the summary page style files. Returns ------- file_list : pycbc.workflow.FileList object A FileList containing the retrieved files. """ if os.getenv("LAL_SRC") is None: raise ValueError("The environment variable LAL_SRC must be set to a " "location containing the file lalsuite.git") else: lalDir = os.getenv("LAL_SRC") sci_seg = segments.segment(int(cp.get("workflow", "start-time")), int(cp.get("workflow", "end-time"))) file_list = FileList([]) # Bank veto if bank_veto: shutil.copy("%s/lalapps/src/ring/coh_PTF_config_files/" \ "bank_veto_bank.xml" % lalDir, "%s" % run_dir) bank_veto_url = "file://localhost%s/bank_veto_bank.xml" % run_dir bank_veto = File(ifos, "bank_veto_bank", sci_seg, file_url=bank_veto_url) bank_veto.PFN(bank_veto.cache_entry.path, site="local") file_list.extend(FileList([bank_veto])) if summary_files: # summary.js file shutil.copy("%s/lalapps/src/ring/coh_PTF_config_files/" \ "coh_PTF_html_summary.js" % lalDir, "%s" % run_dir) summary_js_url = "file://localhost%s/coh_PTF_html_summary.js" \ % run_dir summary_js = File(ifos, "coh_PTF_html_summary_js", sci_seg, file_url=summary_js_url) summary_js.PFN(summary_js.cache_entry.path, site="local") file_list.extend(FileList([summary_js])) # summary.css file shutil.copy("%s/lalapps/src/ring/coh_PTF_config_files/" \ "coh_PTF_html_summary.css" % lalDir, "%s" % run_dir) summary_css_url = "file://localhost%s/coh_PTF_html_summary.css" \ % run_dir summary_css = File(ifos, "coh_PTF_html_summary_css", sci_seg, file_url=summary_css_url) summary_css.PFN(summary_css.cache_entry.path, site="local") file_list.extend(FileList([summary_css])) return file_list
def setup_interval_coinc(workflow, hdfbank, trig_files, veto_files, veto_names, out_dir, tags=None): """ This function sets up exact match coincidence and background estimation using a folded interval technique. """ if tags is None: tags = [] make_analysis_dir(out_dir) logging.info('Setting up coincidence') if len(hdfbank) > 1: raise ValueError('This coincidence method only supports a ' 'pregenerated template bank') hdfbank = hdfbank[0] if len(workflow.ifos) > 2: raise ValueError( 'This coincidence method only supports two ifo searches') findcoinc_exe = PyCBCFindCoincExecutable(workflow.cp, 'coinc', ifos=workflow.ifos, tags=tags, out_dir=out_dir) # Wall time knob and memory knob factor = int( workflow.cp.get_opt_tags('workflow-coincidence', 'parallelization-factor', tags)) stat_files = [] for veto_file, veto_name in zip(veto_files, veto_names): bg_files = FileList() for i in range(factor): group_str = '%s/%s' % (i, factor) coinc_node = findcoinc_exe.create_node(trig_files, hdfbank, veto_file, veto_name, group_str, tags=[veto_name, str(i)]) bg_files += coinc_node.output_files workflow.add_node(coinc_node) stat_files += [ setup_statmap(workflow, bg_files, hdfbank, out_dir, tags=tags + [veto_name]) ] logging.info('...leaving coincidence ') return stat_files
def make_single_template_plots(workflow, segs, seg_name, params, out_dir, inj_file=None, exclude=None, require=None, tags=None, params_str=None, use_exact_inj_params=False): tags = [] if tags is None else tags makedir(out_dir) name = 'single_template_plot' secs = requirestr(workflow.cp.get_subsections(name), require) secs = excludestr(secs, exclude) files = FileList([]) for tag in secs: for ifo in workflow.ifos: # Reanalyze the time around the trigger in each detector node = PlotExecutable(workflow.cp, 'single_template', ifos=[ifo], out_dir=out_dir, tags=[tag] + tags).create_node() if use_exact_inj_params: node.add_opt('--use-params-of-closest-injection') else: node.add_opt('--mass1', "%.6f" % params['mass1']) node.add_opt('--mass2', "%.6f" % params['mass2']) node.add_opt('--spin1z', "%.6f" % params['spin1z']) node.add_opt('--spin2z', "%.6f" % params['spin2z']) # str(numpy.float64) restricts to 2d.p. BE CAREFUL WITH THIS!!! str_trig_time = '%.6f' % (params[ifo + '_end_time']) node.add_opt('--trigger-time', str_trig_time) node.add_input_opt('--inspiral-segments', segs[ifo]) if inj_file is not None: node.add_input_opt('--injection-file', inj_file) node.add_opt('--segment-name', seg_name) node.new_output_file_opt(workflow.analysis_time, '.hdf', '--output-file', store_file=False) data = node.output_files[0] workflow += node # Make the plot for this trigger and detector node = PlotExecutable(workflow.cp, name, ifos=[ifo], out_dir=out_dir, tags=[tag] + tags).create_node() node.add_input_opt('--single-template-file', data) node.new_output_file_opt(workflow.analysis_time, '.png', '--output-file') title = "'%s SNR and chi^2 timeseries" % (ifo) if params_str is not None: title += " using %s" % (params_str) title += "'" node.add_opt('--plot-title', title) caption = "'The SNR and chi^2 timeseries around the injection" if params_str is not None: caption += " using %s" % (params_str) if use_exact_inj_params: caption += ". The injection itself was used as the template.'" else: caption += ". The template used has the following parameters: " caption += "mass1=%s, mass2=%s, spin1z=%s, spin2z=%s'"\ %(params['mass1'], params['mass2'], params['spin1z'], params['spin2z']) node.add_opt('--plot-caption', caption) workflow += node files += node.output_files return files
def setup_matchedfltr_dax_generated_multi(workflow, science_segs, datafind_outs, tmplt_banks, output_dir, injection_file=None, tags=None, link_to_tmpltbank=False, compatibility_mode=False): ''' Setup matched-filter jobs that are generated as part of the workflow in which a single job reads in and generates triggers over multiple ifos. This module can support any matched-filter code that is similar in principle to pycbc_multi_inspiral or lalapps_coh_PTF_inspiral, but for new codes some additions are needed to define Executable and Job sub-classes (see jobutils.py). Parameters ----------- workflow : pycbc.workflow.core.Workflow The Workflow instance that the coincidence jobs will be added to. science_segs : ifo-keyed dictionary of glue.segments.segmentlist instances The list of times that are being analysed in this workflow. datafind_outs : pycbc.workflow.core.FileList An FileList of the datafind files that are needed to obtain the data used in the analysis. tmplt_banks : pycbc.workflow.core.FileList An FileList of the template bank files that will serve as input in this stage. output_dir : path The directory in which output will be stored. injection_file : pycbc.workflow.core.File, optional (default=None) If given the file containing the simulation file to be sent to these jobs on the command line. If not given no file will be sent. tags : list of strings (optional, default = []) A list of the tagging strings that will be used for all jobs created by this call to the workflow. An example might be ['BNSINJECTIONS'] or ['NOINJECTIONANALYSIS']. This will be used in output names. Returns ------- inspiral_outs : pycbc.workflow.core.FileList A list of output files written by this stage. This *will not* contain any intermediate products produced within this stage of the workflow. If you require access to any intermediate products produced at this stage you can call the various sub-functions directly. ''' if tags is None: tags = [] # Need to get the exe to figure out what sections are analysed, what is # discarded etc. This should *not* be hardcoded, so using a new executable # will require a bit of effort here .... cp = workflow.cp ifos = science_segs.keys() match_fltr_exe = os.path.basename(cp.get('executables', 'inspiral')) # List for holding the output inspiral_outs = FileList([]) logging.info("Setting up matched-filtering for %s." % (' '.join(ifos), )) if match_fltr_exe == 'lalapps_coh_PTF_inspiral': from pylal.legacy_ihope import select_legacy_matchedfilter_class exe_class = select_legacy_matchedfilter_class(match_fltr_exe) cp.set('inspiral', 'right-ascension', cp.get('workflow', 'ra')) cp.set('inspiral', 'declination', cp.get('workflow', 'dec')) cp.set('inspiral', 'sky-error', cp.get('workflow', 'sky-error')) cp.set('inspiral', 'trigger-time', cp.get('workflow', 'trigger-time')) cp.set('inspiral', 'block-duration', str(abs(science_segs[ifos[0]][0]) - \ 2 * int(cp.get('inspiral', 'pad-data')))) job_instance = exe_class(workflow.cp, 'inspiral', ifo=ifos, out_dir=output_dir, injection_file=injection_file, tags=tags) multi_ifo_coherent_job_setup(workflow, inspiral_outs, job_instance, science_segs, datafind_outs, output_dir, parents=tmplt_banks) else: # Select the appropriate class raise ValueError("Not currently supported.") return inspiral_outs
def setup_tmpltbank_pregenerated(workflow, tags=None): ''' Setup CBC workflow to use a pregenerated template bank. The bank given in cp.get('workflow','pregenerated-template-bank') will be used as the input file for all matched-filtering jobs. If this option is present, workflow will assume that it should be used and not generate template banks within the workflow. Parameters ---------- workflow: pycbc.workflow.core.Workflow An instanced class that manages the constructed workflow. tags : list of strings If given these tags are used to uniquely name and identify output files that would be produced in multiple calls to this function. Returns -------- tmplt_banks : pycbc.workflow.core.FileList The FileList holding the details of the template bank. ''' if tags is None: tags = [] # Currently this uses the *same* fixed bank for all ifos. # Maybe we want to add capability to analyse separate banks in all ifos? # Set up class for holding the banks tmplt_banks = FileList([]) cp = workflow.cp global_seg = workflow.analysis_time user_tag = "PREGEN_TMPLTBANK" try: # First check if we have a bank for all ifos pre_gen_bank = cp.get_opt_tags('workflow-tmpltbank', 'tmpltbank-pregenerated-bank', tags) pre_gen_bank = resolve_url(pre_gen_bank) file_url = urlparse.urljoin('file:', urllib.pathname2url(pre_gen_bank)) curr_file = File(workflow.ifos, user_tag, global_seg, file_url, tags=tags) curr_file.PFN(file_url, site='local') tmplt_banks.append(curr_file) except ConfigParser.Error: # Okay then I must have banks for each ifo for ifo in workflow.ifos: try: pre_gen_bank = cp.get_opt_tags( 'workflow-tmpltbank', 'tmpltbank-pregenerated-bank-%s' % ifo.lower(), tags) pre_gen_bank = resolve_url(pre_gen_bank) file_url = urlparse.urljoin('file:', urllib.pathname2url(pre_gen_bank)) curr_file = File(ifo, user_tag, global_seg, file_url, tags=tags) curr_file.PFN(file_url, site='local') tmplt_banks.append(curr_file) except ConfigParser.Error: err_msg = "Cannot find pregerated template bank in section " err_msg += "[workflow-tmpltbank] or any tagged sections. " if tags: tagged_secs = " ".join("[workflow-tmpltbank-%s]" \ %(ifo,) for ifo in workflow.ifos) err_msg += "Tagged sections are %s. " % (tagged_secs, ) err_msg += "I looked for 'tmpltbank-pregenerated-bank' option " err_msg += "and 'tmpltbank-pregenerated-bank-%s'." % (ifo, ) raise ConfigParser.Error(err_msg) return tmplt_banks
def setup_tmpltbank_dax_generated(workflow, science_segs, datafind_outs, output_dir, tags=None, link_to_matchedfltr=True, compatibility_mode=False, psd_files=None): ''' Setup template bank jobs that are generated as part of the CBC workflow. This function will add numerous jobs to the CBC workflow using configuration options from the .ini file. The following executables are currently supported: * lalapps_tmpltbank * pycbc_geom_nonspin_bank Parameters ---------- workflow: pycbc.workflow.core.Workflow An instanced class that manages the constructed workflow. science_segs : Keyed dictionary of glue.segmentlist objects scienceSegs[ifo] holds the science segments to be analysed for each ifo. datafind_outs : pycbc.workflow.core.FileList The file list containing the datafind files. output_dir : path string The directory where data products will be placed. tags : list of strings If given these tags are used to uniquely name and identify output files that would be produced in multiple calls to this function. link_to_matchedfltr : boolean, optional (default=True) If this option is given, the job valid_times will be altered so that there will be one inspiral file for every template bank and they will cover the same time span. Note that this option must also be given during matched-filter generation to be meaningful. psd_file : pycbc.workflow.core.FileList The file list containing predefined PSDs, if provided. Returns -------- tmplt_banks : pycbc.workflow.core.FileList The FileList holding the details of all the template bank jobs. ''' if tags is None: tags = [] cp = workflow.cp # Need to get the exe to figure out what sections are analysed, what is # discarded etc. This should *not* be hardcoded, so using a new executable # will require a bit of effort here .... ifos = science_segs.keys() tmplt_bank_exe = os.path.basename(cp.get('executables', 'tmpltbank')) # Select the appropriate class exe_class = select_tmpltbank_class(tmplt_bank_exe) # The exe instance needs to know what data segments are analysed, what is # discarded etc. This should *not* be hardcoded, so using a new executable # will require a bit of effort here .... if link_to_matchedfltr: # Use this to ensure that inspiral and tmpltbank jobs overlap. This # means that there will be 1 inspiral job for every 1 tmpltbank and # the data read in by both will overlap as much as possible. (If you # ask the template bank jobs to use 2000s of data for PSD estimation # and the matched-filter jobs to use 4000s, you will end up with # twice as many matched-filter jobs that still use 4000s to estimate a # PSD but then only generate triggers in the 2000s of data that the # template bank jobs ran on. tmpltbank_exe = os.path.basename(cp.get('executables', 'inspiral')) link_exe_instance = select_matchedfilter_class(tmpltbank_exe) else: link_exe_instance = None # Set up class for holding the banks tmplt_banks = FileList([]) # Template banks are independent for different ifos, but might not be! # Begin with independent case and add after FIXME for ifo in ifos: job_instance = exe_class(workflow.cp, 'tmpltbank', ifo=ifo, out_dir=output_dir, tags=tags) # Check for the write_psd flag if cp.has_option_tags("workflow-tmpltbank", "tmpltbank-write-psd-file", tags): job_instance.write_psd = True else: job_instance.write_psd = False if link_exe_instance: link_job_instance = link_exe_instance(cp, 'inspiral', ifo=ifo, out_dir=output_dir, tags=tags) else: link_job_instance = None sngl_ifo_job_setup(workflow, ifo, tmplt_banks, job_instance, science_segs[ifo], datafind_outs, link_job_instance=link_job_instance, allow_overlap=True, compatibility_mode=compatibility_mode) return tmplt_banks
def convert_cachelist_to_filelist(datafindcache_list): """ Take as input a list of glue.lal.Cache objects and return a pycbc FileList containing all frames within those caches. Parameters ----------- datafindcache_list : list of glue.lal.Cache objects The list of cache files to convert. Returns -------- datafind_filelist : FileList of frame File objects The list of frame files. """ datafind_filelist = FileList([]) prev_file = None for cache in datafindcache_list: curr_ifo = cache.ifo for frame in cache: # Don't add a new workflow file entry for this frame if # if is a duplicate. These are assumed to be returned in time # order if prev_file: prev_name = prev_file.cache_entry.url.split('/')[-1] this_name = frame.url.split('/')[-1] if prev_name == this_name: continue # Pegasus doesn't like "localhost" in URLs. frame.url = frame.url.replace('file://localhost', 'file://') currFile = File(curr_ifo, frame.description, frame.segment, file_url=frame.url, use_tmp_subdirs=True) if frame.url.startswith('file://'): currFile.PFN(frame.url, site='local') if frame.url.startswith( 'file:///cvmfs/oasis.opensciencegrid.org/'): # Datafind returned a URL valid on the osg as well # so add the additional PFNs to allow OSG access. currFile.PFN(frame.url, site='osg') currFile.PFN(frame.url.replace( 'file:///cvmfs/oasis.opensciencegrid.org/', 'root://xrootd-local.unl.edu/user/'), site='osg') currFile.PFN(frame.url.replace( 'file:///cvmfs/oasis.opensciencegrid.org/', 'gsiftp://red-gridftp.unl.edu/user/'), site='osg') currFile.PFN(frame.url.replace( 'file:///cvmfs/oasis.opensciencegrid.org/', 'gsiftp://ldas-grid.ligo.caltech.edu/hdfs/'), site='osg') else: currFile.PFN(frame.url, site='notlocal') datafind_filelist.append(currFile) prev_file = currFile return datafind_filelist
def make_inference_single_parameter_plots(workflow, inference_file, output_dir, variable_args=None, samples_name="inference_samples", acf_name="inference_acf", acl_name="inference_acl", analysis_seg=None, tags=None): """ Sets up single-parameter plots for inference workflow. Parameters ---------- workflow: pycbc.workflow.Workflow The core workflow instance we are populating inference_file: pycbc.workflow.File The file with posterior samples. output_dir: str The directory to store result plots and files. variable_args : list A list of parameters to use instead of [variable_args]. samples_name: str The name in the [executables] section of the configuration file to use for the plot that shows all samples. acf_name: str The name in the [executables] section of the configuration file to use for the autocorrelation function plot. acl_name: str The name in the [executables] section of the configuration file to use for the autocorrelation length histogram. analysis_segs: {None, glue.segments.Segment} The segment this job encompasses. If None then use the total analysis time from the workflow. tags: {None, optional} Tags to add to the inference executables. Returns ------- files: pycbc.workflow.FileList A list of result and output files. """ # default values tags = [] if tags is None else tags analysis_seg = workflow.analysis_time \ if analysis_seg is None else analysis_seg # make the directory that will contain the output files makedir(output_dir) # list of all output files files = FileList() # make a set of plots for each parameter for arg in variable_args: # plot posterior distribution corner_files = make_inference_posterior_plot(workflow, inference_file, output_dir, variable_args=[arg], analysis_seg=analysis_seg, tags=tags + [arg]) # make a node for plotting all the samples for each walker samples_node = PlotExecutable(workflow.cp, samples_name, ifos=workflow.ifos, out_dir=output_dir, tags=tags + [arg]).create_node() samples_node.add_input_opt("--input-file", inference_file) samples_node.new_output_file_opt(analysis_seg, ".png", "--output-file") samples_node.add_opt("--parameters", arg) # make node for plotting the autocorrelation function for each walker acf_node = PlotExecutable(workflow.cp, acf_name, ifos=workflow.ifos, out_dir=output_dir, tags=tags + [arg]).create_node() acf_node.add_input_opt("--input-file", inference_file) acf_node.new_output_file_opt(analysis_seg, ".png", "--output-file") acf_node.add_opt("--parameters", arg) # make node for plotting the autocorrelation function for each walker acl_node = PlotExecutable(workflow.cp, acl_name, ifos=workflow.ifos, out_dir=output_dir, tags=tags + [arg]).create_node() acl_node.add_input_opt("--input-file", inference_file) acl_node.new_output_file_opt(analysis_seg, ".png", "--output-file") acl_node.add_opt("--parameters", arg) # add nodes to workflow workflow += samples_node workflow += acf_node workflow += acl_node # add files to output files list files += corner_files files += samples_node.output_files files += acf_node.output_files files += acl_node.output_files return files
def setup_coincidence_workflow_ligolw_thinca(workflow, segsList, timeSlideFiles, inspiral_outs, output_dir, veto_cats=[2, 3, 4], tags=[], timeSlideTags=None, parallelize_split_input=False): """ This function is used to setup a single-stage ihope style coincidence stage of the workflow using ligolw_sstinca (or compatible code!). Parameters ----------- workflow : pycbc.workflow.core.Workflow The workflow instance that the coincidence jobs will be added to. segsList : pycbc.workflow.core.FileList The list of files returned by workflow's segment module that contains pointers to all the segment files generated in the workflow. If the coincidence code will be applying the data quality vetoes, then this will be used to ensure that the codes get the necessary input to do this. timeSlideFiles : pycbc.workflow.core.FileList An FileList of the timeSlide input files that are needed to determine what time sliding needs to be done. One of the timeSlideFiles will normally be "zero-lag only", the others containing time slides used to facilitate background computations later in the workflow. inspiral_outs : pycbc.workflow.core.FileList An FileList of the matched-filter module output that is used as input to the coincidence codes running at this stage. output_dir : path The directory in which coincidence output will be stored. veto_cats : list of ints (optional, default = [2,3,4]) Veto categories that will be applied in the coincidence jobs. If this takes the default value the code will run data quality at cumulative categories 2, 3 and 4. Note that if we change the flag definitions to be non-cumulative then this option will need to be revisited. tags : list of strings (optional, default = []) A list of the tagging strings that will be used for all jobs created by this call to the workflow. An example might be ['BNSINJECTIONS'] or ['NOINJECTIONANALYSIS']. This will be used in output names. timeSlideTags : list of strings (optional, default = []) A list of the tags corresponding to the timeSlideFiles that are to be used in this call to the module. This can be used to ensure that the injection runs do no time sliding, but the no-injection runs do perform time slides (or vice-versa if you prefer!) Returns -------- ligolwThincaOuts : pycbc.workflow.core.FileList A list of the output files generated from ligolw_sstinca. ligolwAddOuts : pycbc.workflow.core.FileList A list of the output files generated from ligolw_add. """ from pylal import ligolw_cafe logging.debug("Entering coincidence module.") cp = workflow.cp ifoString = workflow.ifo_string # setup code for each veto_category coinc_outs = FileList([]) other_outs = {} if not timeSlideTags: # Get all sections by looking in ini file, use all time slide files. timeSlideTags = [(sec.split('-')[-1]).upper() for sec in workflow.cp.sections() if sec.startswith('tisi-')] if parallelize_split_input: # Want to split all input jobs according to their JOB%d tag. # This matches any string that is the letters JOB followed by some # numbers and nothing else. inspiral_outs_dict = {} regex_match = re.compile('JOB([0-9]+)\Z') for file in inspiral_outs: matches = [regex_match.match(tag) for tag in file.tags] # Remove non matching entries matches = [i for i in matches if i is not None] # Must have one entry if len(matches) == 0: warn_msg = "I was asked to parallelize over split inspiral " warn_msg += "files at the coincidence stage, but at least one " warn_msg += "input file does not have a JOB\%d tag indicating " warn_msg += "that it was split. Assuming that I do not have " warn_msg += "split input files and turning " warn_msg += "parallelize_split_input off." logging.warn(warn_msg) parallelize_split_input = False break if len(matches) > 1: err_msg = "One of my input files has two tags fitting JOB\%d " err_msg += "this means I cannot tell which split job this " err_msg += "file is from." raise ValueError(err_msg) # Extract the job ID id = int(matches[0].string[3:]) if not inspiral_outs_dict.has_key(id): inspiral_outs_dict[id] = FileList([]) inspiral_outs_dict[id].append(file) else: # If I got through all the files I want to sort the dictionaries so # that file with key a and index 3 is the same file as key b and # index 3 other than the tag is JOBA -> JOBB ... ie. it has used # a different part of the template bank. sort_lambda = lambda x: (x.ifo_string, x.segment, x. tagged_description) for key in inspiral_outs_dict.keys(): inspiral_outs_dict[id].sort(key=sort_lambda) # These should be in ascending order, so I can assume the existence # of a JOB0 tag inspiral_outs = inspiral_outs_dict[0] for index, file in enumerate(inspiral_outs): # Store the index in the file for quicker mapping later file.thinca_index = index else: inspiral_outs_dict = None for timeSlideTag in timeSlideTags: # Get the time slide file from the inputs tisiOutFile = timeSlideFiles.find_output_with_tag(timeSlideTag) if not len(tisiOutFile) == 1: errMsg = "If you are seeing this, something batshit is going on!" if len(tisiOutFile) == 0: errMsg = "No time slide files found matching %s." \ %(timeSlideTag) if len(tisiOutFile) > 1: errMsg = "More than one time slide files match %s." \ %(timeSlideTag) raise ValueError(errMsg) tisiOutFile = tisiOutFile[0] # Next we run ligolw_cafe. This is responsible for # identifying what times will be used for the ligolw_thinca jobs and # what files are needed for each. If doing time sliding there # will be some triggers read into multiple jobs cacheInspOuts = inspiral_outs.convert_to_lal_cache() if workflow.cp.has_option_tags("workflow-coincidence", "maximum-extent", tags): max_extent = float( workflow.cp.get_opt_tags("workflow-coincidence", "maximum-extent", tags)) else: # hard-coded default value for extent of time in a single job max_extent = 3600 logging.debug("Calling into cafe.") time_slide_table = lsctables.TimeSlideTable.get_table(\ ligolw_utils.load_filename(tisiOutFile.storage_path, gz=tisiOutFile.storage_path.endswith(".gz"), contenthandler=ContentHandler, verbose=False)) time_slide_table.sync_next_id() time_slide_dict = time_slide_table.as_dict() cafe_seglists, cafe_caches = ligolw_cafe.ligolw_cafe( cacheInspOuts, time_slide_dict.values(), extentlimit=max_extent, verbose=False) logging.debug("Done with cafe.") # Take the combined seglist file dqSegFile = segsList.find_output_with_tag( 'COMBINED_CUMULATIVE_SEGMENTS') if not len(dqSegFile) == 1: errMsg = "Did not find exactly 1 data quality file." print len(dqSegFile), dqSegFile raise ValueError(errMsg) dqSegFile = dqSegFile[0] # Set up llwadd job llwadd_tags = [timeSlideTag] + tags ligolwadd_job = LigolwAddExecutable(cp, 'llwadd', ifo=ifoString, out_dir=output_dir, tags=llwadd_tags) ligolwAddOuts = FileList([]) # Go global setup at each category # This flag will add a clustering job after ligolw_thinca if workflow.cp.has_option_tags("workflow-coincidence", "coincidence-post-cluster", llwadd_tags): coinc_post_cluster = True else: coinc_post_cluster = False # Go global setup at each category ligolwthinca_job = {} cluster_job = {} thinca_tags = {} for category in veto_cats: logging.debug("Preparing %s %s" % (timeSlideTag, category)) dqVetoName = 'VETO_CAT%d_CUMULATIVE' % (category) # FIXME: Should we resolve this now? # FIXME: Here we set the dqVetoName to be compatible with pipedown # For pipedown must put the slide identifier first and # dqVetoName last. pipedownDQVetoName = 'CAT_%d_VETO' % (category) curr_thinca_job_tags = [timeSlideTag] + tags + [pipedownDQVetoName] thinca_tags[category] = curr_thinca_job_tags # Set up jobs for ligolw_thinca ligolwthinca_job[category] = LigolwSSthincaExecutable( cp, 'thinca', ifo=ifoString, out_dir=output_dir, dqVetoName=dqVetoName, tags=curr_thinca_job_tags) if coinc_post_cluster: cluster_job[category] = SQLInOutExecutable( cp, 'pycbccluster', ifo=ifoString, out_dir=output_dir, tags=curr_thinca_job_tags) for idx, cafe_cache in enumerate(cafe_caches): ligolwAddOuts = FileList([]) ligolwThincaOuts = FileList([]) ligolwThincaLikelihoodOuts = FileList([]) ligolwClusterOuts = FileList([]) if not len(cafe_cache.objects): raise ValueError("One of the cache objects contains no files!") # Determine segments to accept coincidences. # If cache is not the first or last in the timeseries, check if the # two closes caches in the timeseries and see if their extent # match. If they match, they're adjacent and use the time where # they meet as a bound for accepting coincidences. If they're not # adjacent, then there is no bound for accepting coincidences. coincStart, coincEnd = None, None if idx and (cafe_cache.extent[0] == cafe_caches[idx - 1].extent[1]): coincStart = cafe_cache.extent[0] if idx + 1 - len(cafe_caches) and \ (cafe_cache.extent[1] == cafe_caches[idx+1].extent[0]): coincEnd = cafe_cache.extent[1] coincSegment = (coincStart, coincEnd) # Need to create a list of the File(s) contained in the cache. # Assume that if we have partitioned input then if *one* job in the # partitioned input is an input then *all* jobs will be. if not parallelize_split_input: inputTrigFiles = FileList([]) for object in cafe_cache.objects: inputTrigFiles.append(object.workflow_file) llw_files = inputTrigFiles + [dqSegFile] + [tisiOutFile] # Now we can create the nodes node = ligolwadd_job.create_node(cafe_cache.extent, llw_files) ligolwAddFile = node.output_files[0] ligolwAddOuts.append(ligolwAddFile) workflow.add_node(node) for category in veto_cats: node = ligolwthinca_job[category].create_node(\ cafe_cache.extent, coincSegment, ligolwAddFile) ligolwThincaOuts += \ node.output_files.find_output_without_tag('DIST_STATS') ligolwThincaLikelihoodOuts += \ node.output_files.find_output_with_tag('DIST_STATS') workflow.add_node(node) if coinc_post_cluster: node = cluster_job[category].create_node(\ cafe_cache.extent, ligolwThincaOuts[-1]) ligolwClusterOuts += node.output_files workflow.add_node(node) else: for key in inspiral_outs_dict.keys(): curr_tags = ["JOB%d" % (key)] curr_list = inspiral_outs_dict[key] inputTrigFiles = FileList([]) for object in cafe_cache.objects: inputTrigFiles.append( curr_list[object.workflow_file.thinca_index]) llw_files = inputTrigFiles + [dqSegFile] + [tisiOutFile] # Now we can create the nodes node = ligolwadd_job.create_node(cafe_cache.extent, llw_files, tags=curr_tags) ligolwAddFile = node.output_files[0] ligolwAddOuts.append(ligolwAddFile) workflow.add_node(node) if workflow.cp.has_option_tags( "workflow-coincidence", "coincidence-write-likelihood", curr_thinca_job_tags): write_likelihood = True else: write_likelihood = False for category in veto_cats: node = ligolwthinca_job[category].create_node(\ cafe_cache.extent, coincSegment, ligolwAddFile, tags=curr_tags, write_likelihood=write_likelihood) ligolwThincaOuts += \ node.output_files.find_output_without_tag(\ 'DIST_STATS') ligolwThincaLikelihoodOuts += \ node.output_files.find_output_with_tag(\ 'DIST_STATS') workflow.add_node(node) if coinc_post_cluster: node = cluster_job[category].create_node(\ cafe_cache.extent, ligolwThincaOuts[-1]) ligolwClusterOuts += node.output_files workflow.add_node(node) other_returns = {} other_returns['LIGOLW_ADD'] = ligolwAddOuts other_returns['DIST_STATS'] = ligolwThincaLikelihoodOuts if coinc_post_cluster: main_return = ligolwClusterOuts other_returns['THINCA'] = ligolwThincaOuts else: main_return = ligolwThincaOuts logging.debug("Done") coinc_outs.extend(main_return) for key, file_list in other_returns.items(): if other_outs.has_key(key): other_outs[key].extend(other_returns[key]) else: other_outs[key] = other_returns[key] return coinc_outs, other_outs
def setup_postproc_pipedown_workflow(workflow, trigger_files, summary_xml_files, output_dir, tags=[], veto_cats=[]): """ This module sets up the post-processing stage in the workflow, using a pipedown style set up. This consists of running compute_durations to determine and store the analaysis time (foreground and background). It then runs cfar jobs to determine the false alarm rate for all triggers (simulations or otherwise) in the input database. Pipedown expects to take as input (at this stage) a single database containing all triggers. This sub-module follows that same idea, so len(triggerFiles) must equal 1 (for every DQ category that we will run). Parameters ---------- workflow : pycbc.workflow.core.Workflow The Workflow instance that the coincidence jobs will be added to. trigger_files : pycbc.workflow.core.FileList An FileList containing the combined databases at CAT_1,2,3... that will be used to calculate FARs summary_xml_files : pycbc.workflow.core.FileList (required) A FileList of the output of the analysislogging_utils module. For pipedown-style post-processing this should be one file containing a segment table holding the single detector analysed times. output_dir : path The directory in which output files will be stored. tags : list of strings (optional, default = []) A list of the tagging strings that will be used for all jobs created by this call to the workflow. An example might be ['POSTPROC1'] or ['DENTYSNEWPOSTPROC']. This will be used in output names. veto_cats : list of integers (default = [], non-empty list required) Decide which veto category levels should be used in post-processing. For example tell the workflow to only generate results at cumulative categories 2, 3 and 4 by supplying [2,3,4] here. Returns -------- final_files : pycbc.workflow.core.FileList A list of the final SQL databases containing computed FARs. """ if not veto_cats: raise ValueError("A non-empty list of veto categories is required.") if not len(summary_xml_files) == 1: errMsg = "I need exactly one summaryXML file, got %d." \ %(len(summary_xml_files),) raise ValueError(errMsg) # Setup needed exe classes compute_durations_exe_tag = workflow.cp.get_opt_tags( "workflow-postproc", "postproc-computedurations-exe", tags) compute_durations_exe = select_generic_executable( workflow, compute_durations_exe_tag) cfar_exe_tag = workflow.cp.get_opt_tags("workflow-postproc", "postproc-cfar-exe", tags) cfar_exe = select_generic_executable(workflow, cfar_exe_tag) comp_durations_outs = FileList([]) cfar_outs = FileList([]) for cat in veto_cats: veto_tag = 'CUMULATIVE_CAT_%d' % (cat) trig_input_files = trigger_files.find_output_with_tag(veto_tag) if not len(trig_input_files) == 1: err_msg = "Did not find exactly 1 database input file." raise ValueError(err_msg) curr_tags = tags + [veto_tag] # Choose a label for clustering the jobs job_label = get_random_label() # Start with compute durations computeDurationsJob = compute_durations_exe(workflow.cp, compute_durations_exe_tag, ifo=workflow.ifo_string, out_dir=output_dir, tags=curr_tags) compute_durations_node = computeDurationsJob.create_node( workflow.analysis_time, trig_input_files[0], summary_xml_files[0]) compute_durations_node.add_profile('pegasus', 'label', job_label) workflow.add_node(compute_durations_node) # Node has only one output file compute_durations_out = compute_durations_node.output_files[0] comp_durations_outs.append(compute_durations_out) # Add the calculate FAR (cfar) job cfar_job = cfar_exe(workflow.cp, cfar_exe_tag, ifo=workflow.ifo_string, out_dir=output_dir, tags=curr_tags) cfar_node = cfar_job.create_node(workflow.analysis_time, compute_durations_out) cfar_node.add_profile('pegasus', 'label', job_label) workflow.add_node(cfar_node) # Node has only one output file cfar_out = cfar_node.output_files[0] cfar_outs.append(cfar_out) return cfar_outs
def create_node(self, trig_files=None, segment_dir=None, out_tags=[], tags=[]): node = Node(self) if not trig_files: raise ValueError("%s must be supplied with trigger files" % self.name) # Data options pad_data = self.cp.get('inspiral', 'pad-data') if pad_data is None: raise ValueError("The option pad-data is a required option of " "%s. Please check the ini file." % self.name) num_trials = int(self.cp.get("trig_combiner", "num-trials")) trig_name = self.cp.get('workflow', 'trigger-name') if all("COHERENT_NO_INJECTIONS" in t.name for t in trig_files) and \ self.cp.has_option_tag('inspiral', 'do-short-slides', 'coherent_no_injections'): node.add_opt('--short-slides') node.add_opt('--grb-name', trig_name) node.add_opt('--pad-data', pad_data) node.add_opt('--segment-length', self.cp.get('inspiral', 'segment-duration')) node.add_opt('--ifo-tag', self.ifos) node.add_opt('--user-tag', 'INSPIRAL') # Set input / output options node.add_input_list_opt('--input-files', trig_files) node.add_opt('--segment-dir', segment_dir) node.add_opt('--output-dir', self.out_dir) out_files = FileList([]) for out_tag in out_tags: out_file = File(self.ifos, 'INSPIRAL', trig_files[0].segment, directory=self.out_dir, extension='xml.gz', tags=["GRB%s" % trig_name, out_tag], store_file=self.retain_files) out_files.append(out_file) for trial in range(1, num_trials + 1): out_file = File(self.ifos, 'INSPIRAL', trig_files[0].segment, directory=self.out_dir, extension='xml.gz', tags=["GRB%s" % trig_name, "OFFTRIAL_%d" % trial], store_file=self.retain_files) out_files.append(out_file) node.add_profile('condor', 'request_cpus', self.num_threads) return node, out_files
def convert_cachelist_to_filelist(datafindcache_list): """ Take as input a list of glue.lal.Cache objects and return a pycbc FileList containing all frames within those caches. Parameters ----------- datafindcache_list : list of glue.lal.Cache objects The list of cache files to convert. Returns -------- datafind_filelist : FileList of frame File objects The list of frame files. """ prev_file = None prev_name = None this_name = None datafind_filelist = FileList([]) for cache in datafindcache_list: # sort the cache into time sequential order cache.sort() curr_ifo = cache.ifo for frame in cache: # Pegasus doesn't like "localhost" in URLs. frame.url = frame.url.replace('file://localhost','file://') # Create one File() object for each unique frame file that we # get back in the cache. if prev_file: prev_name = os.path.basename(prev_file.cache_entry.url) this_name = os.path.basename(frame.url) if (prev_file is None) or (prev_name != this_name): currFile = File(curr_ifo, frame.description, frame.segment, file_url=frame.url, use_tmp_subdirs=True) datafind_filelist.append(currFile) prev_file = currFile # Populate the PFNs for the File() we just created if frame.url.startswith('file://'): currFile.add_pfn(frame.url, site='local') if frame.url.startswith( 'file:///cvmfs/oasis.opensciencegrid.org/ligo/frames'): # Datafind returned a URL valid on the osg as well # so add the additional PFNs to allow OSG access. currFile.add_pfn(frame.url, site='osg') currFile.add_pfn(frame.url.replace( 'file:///cvmfs/oasis.opensciencegrid.org/', 'root://xrootd-local.unl.edu/user/'), site='osg') currFile.add_pfn(frame.url.replace( 'file:///cvmfs/oasis.opensciencegrid.org/', 'gsiftp://red-gridftp.unl.edu/user/'), site='osg') currFile.add_pfn(frame.url.replace( 'file:///cvmfs/oasis.opensciencegrid.org/', 'gsiftp://ldas-grid.ligo.caltech.edu/hdfs/'), site='osg') elif frame.url.startswith( 'file:///cvmfs/gwosc.osgstorage.org/'): # Datafind returned a URL valid on the osg as well # so add the additional PFNs to allow OSG access. for s in ['osg', 'orangegrid', 'osgconnect']: currFile.add_pfn(frame.url, site=s) currFile.add_pfn(frame.url, site="{}-scratch".format(s)) else: currFile.add_pfn(frame.url, site='notlocal') return datafind_filelist
def setup_analysislogging(workflow, segs_list, insps, args, output_dir, program_name="workflow", tags=[]): """ This module sets up the analysis logging xml file that contains the following information: * Command line arguments that the code was run with * Segment list of times marked as SCIENCE * Segment list of times marked as SCIENCE and "OK" ie. not CAT_1 vetoed * Segment list of times marked as SCIENCE_OK and present on the cluster * The times that will be analysed by the matched-filter jobs Parameters ----------- workflow : pycbc.workflow.core.Workflow The Workflow instance. segs_list : pycbc.workflow.core.FileList A list of Files containing the information needed to generate the segments above. For segments generated at run time the associated segmentlist is a property of this object. insps : pycbc.workflow.core.FileList The output files from the matched-filtering module. Used to identify what times have been analysed in this workflow. output_dir : path Directory to output any files to. program_name : string (optional, default = "workflow") The program name to stick in the process/process_params tables. tags : list (optional, default = []) If given restrict to considering inspiral and segment files that are tagged with all tags in this list. """ logging.info("Entering analysis logging module.") make_analysis_dir(output_dir) # Construct the summary XML file outdoc = ligolw.Document() outdoc.appendChild(ligolw.LIGO_LW()) # Add process and process_params tables proc_id = process.register_to_xmldoc(outdoc, program_name, vars(args) ).process_id # Now add the various segment lists to this file summ_segs = segmentlist([workflow.analysis_time]) # If tags is given filter by tags if tags: for tag in tags: segs_list = segs_list.find_output_with_tag(tag) insps = insps.find_output_with_tag(tag) for ifo in workflow.ifos: # Lets get the segment lists we need seg_ifo_files = segs_list.find_output_with_ifo(ifo) # SCIENCE sci_seg_file = seg_ifo_files.find_output_with_tag('SCIENCE') if len(sci_seg_file) == 1: sci_seg_file = sci_seg_file[0] sci_segs = sci_seg_file.segmentList sci_def_id = segmentdb_utils.add_to_segment_definer(outdoc, proc_id, ifo, "CBC_WORKFLOW_SCIENCE", 0) segmentdb_utils.add_to_segment(outdoc, proc_id, sci_def_id, sci_segs) segmentdb_utils.add_to_segment_summary(outdoc, proc_id, sci_def_id, summ_segs, comment='') elif sci_seg_file: # FIXME: While the segment module is still fractured (#127) this # may not work. Please update when #127 is resolved pass #err_msg = "Got %d files matching %s and %s. Expected 1 or 0." \ # %(len(sci_seg_file), ifo, 'SCIENCE') #raise ValueError(err_msg) # SCIENCE_OK sci_ok_seg_file = seg_ifo_files.find_output_with_tag('SCIENCE_OK') if len(sci_ok_seg_file) == 1: sci_ok_seg_file = sci_ok_seg_file[0] sci_ok_segs = sci_ok_seg_file.segmentList sci_ok_def_id = segmentdb_utils.add_to_segment_definer(outdoc, proc_id, ifo, "CBC_WORKFLOW_SCIENCE_OK", 0) segmentdb_utils.add_to_segment(outdoc, proc_id, sci_ok_def_id, sci_ok_segs) segmentdb_utils.add_to_segment_summary(outdoc, proc_id, sci_ok_def_id, summ_segs, comment='') elif sci_ok_seg_file: # FIXME: While the segment module is still fractured (#127) this # may not work. Please update when #127 is resolved pass #err_msg = "Got %d files matching %s and %s. Expected 1 or 0." \ # %(len(sci_ok_seg_file), ifo, 'SCIENCE_OK') #raise ValueError(err_msg) # SCIENCE_AVAILABLE sci_available_seg_file = seg_ifo_files.find_output_with_tag(\ 'SCIENCE_AVAILABLE') if len(sci_available_seg_file) == 1: sci_available_seg_file = sci_available_seg_file[0] sci_available_segs = sci_available_seg_file.segmentList sci_available_def_id = segmentdb_utils.add_to_segment_definer(\ outdoc, proc_id, ifo, "CBC_WORKFLOW_SCIENCE_AVAILABLE", 0) segmentdb_utils.add_to_segment(outdoc, proc_id, sci_available_def_id, sci_available_segs) segmentdb_utils.add_to_segment_summary(outdoc, proc_id, sci_available_def_id, summ_segs, comment='') elif sci_available_seg_file: # FIXME: While the segment module is still fractured (#127) this # may not work. Please update when #127 is resolved pass #err_msg = "Got %d files matching %s and %s. Expected 1 or 0." \ # %(len(sci_available_seg_file), ifo, 'SCIENCE_AVAILABLE') #raise ValueError(err_msg) # ANALYSABLE - This one needs to come from inspiral outs ifo_insps = insps.find_output_with_ifo(ifo) analysable_segs = ifo_insps.get_times_covered_by_files() analysable_def_id = segmentdb_utils.add_to_segment_definer(outdoc, proc_id, ifo, "CBC_WORKFLOW_ANALYSABLE", 0) segmentdb_utils.add_to_segment(outdoc, proc_id, analysable_def_id, analysable_segs) segmentdb_utils.add_to_segment_summary(outdoc, proc_id, analysable_def_id, summ_segs, comment='') summ_file = File(workflow.ifos, "WORKFLOW_SUMMARY", workflow.analysis_time, extension=".xml", directory=output_dir) summ_file.PFN(summ_file.storage_path, site='local') utils.write_filename(outdoc, summ_file.storage_path) return FileList([summ_file])
def setup_postproc_coh_PTF_workflow(workflow, trig_files, trig_cache, inj_trig_files, inj_files, inj_trig_caches, inj_caches, config_file, output_dir, html_dir, segment_dir, ifos, inj_tags=[], tags=[]): """ This module sets up the post-processing stage in the workflow, using a coh_PTF style set up. This consists of running trig_combiner to find coherent triggers, and injfinder to look for injections. It then runs a horizon_dist job, trig_cluster to cluster triggers, and injcombiner to calculate injection statistics. Finally, efficiency and sbv_plotter jobs calculate efficiency and signal based veto statistics and make plots. workflow : pycbc.workflow.core.Workflow The Workflow instance that the jobs will be added to. trig_files : pycbc.workflow.core.FileList A FileList containing the combined databases. Returns -------- """ cp = workflow.cp full_segment = trig_files[0].segment trig_name = cp.get("workflow", "trigger-name") grb_string = "GRB" + trig_name num_trials = int(cp.get("trig_combiner", "num-trials")) pp_outs = FileList([]) pp_nodes = [] # Set up needed exe classes trig_combiner_exe = os.path.basename(cp.get("executables", "trig_combiner")) trig_combiner_class = select_generic_executable(workflow, "trig_combiner") trig_cluster_exe = os.path.basename(cp.get("executables", "trig_cluster")) trig_cluster_class = select_generic_executable(workflow, "trig_cluster") sbv_plotter_exe = os.path.basename(cp.get("executables", "sbv_plotter")) sbv_plotter_class = select_generic_executable(workflow, "sbv_plotter") efficiency_exe = os.path.basename(cp.get("executables", "efficiency")) efficiency_class = select_generic_executable(workflow, "efficiency") """ horizon_dist_exe = os.path.basename(cp.get("executables", "horizon_dist")) horizon_dist_class = select_generic_executable(workflow, "horizon_dist") """ html_summary_exe = os.path.basename(cp.get("executables", "html_summary")) html_summary_class = select_generic_executable(workflow, "html_summary") # Set up trig_combiner job trig_combiner_out_tags = ["OFFSOURCE", "ONSOURCE", "ALL_TIMES"] trig_combiner_jobs = trig_combiner_class(cp, "trig_combiner", ifo=ifos, out_dir=output_dir, tags=tags) trig_combiner_node, trig_combiner_outs = trig_combiner_jobs.create_node(\ trig_files, segment_dir, out_tags=trig_combiner_out_tags, tags=tags) pp_nodes.append(trig_combiner_node) workflow.add_node(trig_combiner_node) pp_outs.extend(trig_combiner_outs) # Initialise trig_cluster class trig_cluster_outs = FileList([]) trig_cluster_jobs = trig_cluster_class(cp, "trig_cluster", ifo=ifos, out_dir=output_dir, tags=tags) # Set up injfinder jobs if cp.has_section("workflow-injections"): injfinder_nodes = [] injcombiner_parent_nodes = [] inj_sbv_plotter_parent_nodes = [] injfinder_exe = os.path.basename(cp.get("executables", "injfinder")) injfinder_class = select_generic_executable(workflow, "injfinder") injfinder_jobs = injfinder_class(cp, "injfinder", ifo=ifos, out_dir=output_dir, tags=tags) injcombiner_exe = os.path.basename(cp.get("executables", "injcombiner")) injcombiner_class = select_generic_executable(workflow, "injcombiner") injcombiner_jobs = injcombiner_class(cp, "injcombiner", ifo=ifos, out_dir=output_dir, tags=tags) injfinder_outs = FileList([]) for inj_tag in inj_tags: triggers = FileList([file for file in inj_trig_files \ if inj_tag in file.tag_str]) injections = FileList([file for file in inj_files \ if inj_tag in file.tag_str]) trig_cache = [file for file in inj_trig_caches \ if inj_tag in file.tag_str][0] inj_cache = [file for file in inj_caches \ if inj_tag in file.tag_str][0] injfinder_node, curr_outs = injfinder_jobs.create_node(\ triggers, injections, segment_dir, tags=[inj_tag]) injfinder_nodes.append(injfinder_node) pp_nodes.append(injfinder_node) workflow.add_node(injfinder_node) injfinder_outs.extend(curr_outs) if "DETECTION" not in curr_outs[0].tagged_description: injcombiner_parent_nodes.append(injfinder_node) else: inj_sbv_plotter_parent_nodes.append(injfinder_node) pp_outs.extend(injfinder_outs) # Make injfinder output cache fm_cache = File(ifos, "foundmissed", full_segment, extension="lcf", directory=output_dir) fm_cache.PFN(fm_cache.cache_entry.path, site="local") injfinder_outs.convert_to_lal_cache().tofile(\ open(fm_cache.storage_path, "w")) pp_outs.extend(FileList([fm_cache])) # Set up injcombiner jobs injcombiner_outs = FileList([file for file in injfinder_outs \ if "DETECTION" in file.tag_str]) injcombiner_tags = [inj_tag for inj_tag in inj_tags \ if "DETECTION" not in inj_tag] injcombiner_out_tags = [injcombiner_outs[0].tag_str.rsplit('_', 1)[0]] injcombiner_nodes = [] for injcombiner_tag in injcombiner_tags: max_inc = cp.get_opt_tags("injections", "max-inc", [injcombiner_tag]) inj_str = injcombiner_tag[:4] inputs = FileList([file for file in injfinder_outs \ if injcombiner_tag in file.tagged_description]) # if any(tag in file.tagged_description \ # for tag in injcombiner_tags)]) injcombiner_node, curr_outs = injcombiner_jobs.create_node(\ fm_cache, inputs, inj_str, max_inc, workflow.analysis_time) injcombiner_nodes.append(injcombiner_node) injcombiner_out_tags.append("%s_FILTERED_%s" % (inj_str, max_inc)) injcombiner_outs.extend(curr_outs) pp_outs.extend(curr_outs) pp_nodes.append(injcombiner_node) workflow.add_node(injcombiner_node) for parent_node in injcombiner_parent_nodes: dep = dax.Dependency(parent=parent_node._dax_node, child=injcombiner_node._dax_node) workflow._adag.addDependency(dep) # Initialise injection_efficiency class inj_efficiency_jobs = efficiency_class(cp, "inj_efficiency", ifo=ifos, out_dir=output_dir, tags=tags) # Initialise sbv_plotter class sbv_plotter_outs = FileList([]) sbv_plotter_jobs = sbv_plotter_class(cp, "sbv_plotter", ifo=ifos, out_dir=output_dir, tags=tags) # Initialise efficiency class efficiency_outs = FileList([]) efficiency_jobs = efficiency_class(cp, "efficiency", ifo=ifos, out_dir=output_dir, tags=tags) # Add trig_cluster jobs and their corresponding plotting jobs for out_tag in trig_combiner_out_tags: unclust_file = [file for file in trig_combiner_outs \ if out_tag in file.tag_str][0] trig_cluster_node, curr_outs = trig_cluster_jobs.create_node(\ unclust_file) trig_cluster_outs.extend(curr_outs) clust_file = curr_outs[0] if out_tag != "ONSOURCE": # Add memory requirememnt for jobs with potentially large files trig_cluster_node.set_memory(1300) pp_nodes.append(trig_cluster_node) workflow.add_node(trig_cluster_node) dep = dax.Dependency(parent=trig_combiner_node._dax_node, child=trig_cluster_node._dax_node) workflow._adag.addDependency(dep) # Add sbv_plotter job sbv_out_tags = [out_tag, "_clustered"] sbv_plotter_node = sbv_plotter_jobs.create_node(clust_file, segment_dir, tags=sbv_out_tags) pp_nodes.append(sbv_plotter_node) workflow.add_node(sbv_plotter_node) dep = dax.Dependency(parent=trig_cluster_node._dax_node, child=sbv_plotter_node._dax_node) workflow._adag.addDependency(dep) # Add injection sbv_plotter nodes if appropriate if out_tag == "OFFSOURCE" and \ cp.has_section("workflow-injections"): offsource_clustered = clust_file off_node = sbv_plotter_node found_inj_files = FileList([file for file in injcombiner_outs \ if "FOUND" in file.tag_str]) for curr_injs in found_inj_files: curr_tags = [tag for tag in injcombiner_out_tags \ if tag in curr_injs.name] curr_tags.append("_clustered") sbv_plotter_node = sbv_plotter_jobs.create_node( clust_file, segment_dir, inj_file=curr_injs, tags=curr_tags) pp_nodes.append(sbv_plotter_node) workflow.add_node(sbv_plotter_node) dep = dax.Dependency(parent=trig_cluster_node._dax_node, child=sbv_plotter_node._dax_node) workflow._adag.addDependency(dep) if "DETECTION" in curr_injs.tagged_description: for parent_node in inj_sbv_plotter_parent_nodes: dep = dax.Dependency( parent=parent_node._dax_node, child=sbv_plotter_node._dax_node) workflow._adag.addDependency(dep) else: for parent_node in injcombiner_nodes: dep = dax.Dependency( parent=parent_node._dax_node, child=sbv_plotter_node._dax_node) workflow._adag.addDependency(dep) # Also add sbv_plotter job for unclustered triggers sbv_plotter_node = sbv_plotter_jobs.create_node( unclust_file, segment_dir, tags=[out_tag, "_unclustered"]) sbv_plotter_node.set_memory(1300) pp_nodes.append(sbv_plotter_node) workflow.add_node(sbv_plotter_node) dep = dax.Dependency(parent=trig_combiner_node._dax_node, child=sbv_plotter_node._dax_node) workflow._adag.addDependency(dep) else: pp_nodes.append(trig_cluster_node) workflow.add_node(trig_cluster_node) dep = dax.Dependency(parent=trig_combiner_node._dax_node, child=trig_cluster_node._dax_node) workflow._adag.addDependency(dep) # Add efficiency job for on/off efficiency_node = efficiency_jobs.create_node(clust_file, offsource_clustered, segment_dir, tags=[out_tag]) pp_nodes.append(efficiency_node) workflow.add_node(efficiency_node) dep = dax.Dependency(parent=off_node._dax_node, child=efficiency_node._dax_node) workflow._adag.addDependency(dep) if cp.has_section("workflow-injections"): for tag in injcombiner_out_tags: if "_FILTERED_" in tag: inj_set_tag = [t for t in inj_tags if \ str(tag).replace("_FILTERED_", "") \ in t][0] else: inj_set_tag = str(tag) found_file = [file for file in injcombiner_outs \ if tag + "_FOUND" in file.tag_str][0] missed_file = [file for file in injcombiner_outs \ if tag + "_MISSED" in file.tag_str][0] inj_efficiency_node = inj_efficiency_jobs.create_node(\ clust_file, offsource_clustered, segment_dir, found_file, missed_file, tags=[out_tag, tag, inj_set_tag]) pp_nodes.append(inj_efficiency_node) workflow.add_node(inj_efficiency_node) dep = dax.Dependency(parent=off_node._dax_node, child=inj_efficiency_node._dax_node) workflow._adag.addDependency(dep) for injcombiner_node in injcombiner_nodes: dep = dax.Dependency( parent=injcombiner_node._dax_node, child=inj_efficiency_node._dax_node) workflow._adag.addDependency(dep) for injfinder_node in injfinder_nodes: dep = dax.Dependency( parent=injfinder_node._dax_node, child=inj_efficiency_node._dax_node) workflow._adag.addDependency(dep) # Add further trig_cluster jobs for trials trial = 1 while trial <= num_trials: trial_tag = "OFFTRIAL_%d" % trial unclust_file = [file for file in trig_combiner_outs \ if trial_tag in file.tag_str][0] trig_cluster_node, clust_outs = trig_cluster_jobs.create_node(\ unclust_file) clust_file = clust_outs[0] trig_cluster_outs.extend(clust_outs) pp_nodes.append(trig_cluster_node) workflow.add_node(trig_cluster_node) dep = dax.Dependency(parent=trig_combiner_node._dax_node, child=trig_cluster_node._dax_node) workflow._adag.addDependency(dep) # Add efficiency job efficiency_node = efficiency_jobs.create_node(clust_file, offsource_clustered, segment_dir, tags=[trial_tag]) pp_nodes.append(efficiency_node) workflow.add_node(efficiency_node) dep = dax.Dependency(parent=off_node._dax_node, child=efficiency_node._dax_node) workflow._adag.addDependency(dep) dep = dax.Dependency(parent=trig_cluster_node._dax_node, child=efficiency_node._dax_node) workflow._adag.addDependency(dep) # Adding inj_efficiency job if cp.has_section("workflow-injections"): for tag in injcombiner_out_tags: if "_FILTERED_" in tag: inj_set_tag = [t for t in inj_tags if \ str(tag).replace("_FILTERED_", "") in t][0] else: inj_set_tag = str(tag) found_file = [file for file in injcombiner_outs \ if tag + "_FOUND" in file.tag_str][0] missed_file = [file for file in injcombiner_outs \ if tag + "_MISSED" in file.tag_str][0] inj_efficiency_node = inj_efficiency_jobs.create_node(\ clust_file, offsource_clustered, segment_dir, found_file, missed_file, tags=[trial_tag, tag, inj_set_tag]) pp_nodes.append(inj_efficiency_node) workflow.add_node(inj_efficiency_node) dep = dax.Dependency(parent=off_node._dax_node, child=inj_efficiency_node._dax_node) workflow._adag.addDependency(dep) for injcombiner_node in injcombiner_nodes: dep = dax.Dependency(parent=injcombiner_node._dax_node, child=inj_efficiency_node._dax_node) workflow._adag.addDependency(dep) for injfinder_node in injfinder_nodes: dep = dax.Dependency(parent=injfinder_node._dax_node, child=inj_efficiency_node._dax_node) workflow._adag.addDependency(dep) trial += 1 # Initialise html_summary class and set up job #FIXME: We may want this job to run even if some jobs fail html_summary_jobs = html_summary_class(cp, "html_summary", ifo=ifos, out_dir=output_dir, tags=tags) if cp.has_section("workflow-injections"): tuning_tags = [inj_tag for inj_tag in injcombiner_out_tags \ if "DETECTION" in inj_tag] exclusion_tags = [inj_tag for inj_tag in injcombiner_out_tags \ if "DETECTION" not in inj_tag] html_summary_node = html_summary_jobs.create_node( c_file=config_file, tuning_tags=tuning_tags, exclusion_tags=exclusion_tags, html_dir=html_dir) else: html_summary_node = html_summary_jobs.create_node(c_file=config_file, html_dir=html_dir) workflow.add_node(html_summary_node) for pp_node in pp_nodes: dep = dax.Dependency(parent=pp_node._dax_node, child=html_summary_node._dax_node) workflow._adag.addDependency(dep) # Make the open box shell script open_box_cmd = html_summary_node.executable.get_pfn() + " " open_box_cmd += ' '.join(html_summary_node._args + \ html_summary_node._options) open_box_cmd += " --open-box" open_box_path = "%s/open_the_box.sh" % output_dir f = open(open_box_path, "w") f.write("#!/bin/sh\n%s" % open_box_cmd) f.close() os.chmod(open_box_path, 0500) pp_outs.extend(trig_cluster_outs) return pp_outs
def setup_timeslides_workflow(workflow, output_dir=None, tags=[], timeSlideSectionName='ligolw_tisi'): ''' Setup generation of time_slide input files in the workflow. Currently used only with ligolw_tisi to generate files containing the list of slides to be performed in each time slide job. Parameters ----------- workflow : pycbc.workflow.core.Workflow The Workflow instance that the coincidence jobs will be added to. output_dir : path The directory in which output files will be stored. tags : list of strings (optional, default = []) A list of the tagging strings that will be used for all jobs created by this call to the workflow. This will be used in output names. timeSlideSectionName : string (optional, default='injections') The string that corresponds to the option describing the exe location in the [executables] section of the .ini file and that corresponds to the section (and sub-sections) giving the options that will be given to the code at run time. Returns -------- timeSlideOuts : pycbc.workflow.core.FileList The list of time slide files created by this call. ''' logging.info("Entering time slides setup module.") make_analysis_dir(output_dir) # Get ifo list and full analysis segment for output file naming ifoList = workflow.ifos ifo_string = workflow.ifo_string fullSegment = workflow.analysis_time # Identify which time-slides to do by presence of sub-sections in the # configuration file all_sec = workflow.cp.sections() timeSlideSections = [sec for sec in all_sec if sec.startswith('tisi-')] timeSlideTags = [(sec.split('-')[-1]).upper() for sec in timeSlideSections] timeSlideOuts = FileList([]) # FIXME: Add ability to specify different exes # Make the timeSlideFiles for timeSlideTag in timeSlideTags: currTags = tags + [timeSlideTag] timeSlideMethod = workflow.cp.get_opt_tags("workflow-timeslides", "timeslides-method", currTags) if timeSlideMethod in ["IN_WORKFLOW", "AT_RUNTIME"]: timeSlideExeTag = workflow.cp.get_opt_tags("workflow-timeslides", "timeslides-exe", currTags) timeSlideExe = select_generic_executable(workflow, timeSlideExeTag) timeSlideJob = timeSlideExe(workflow.cp, timeSlideExeTag, ifos=ifo_string, tags=currTags, out_dir=output_dir) timeSlideNode = timeSlideJob.create_node(fullSegment) if timeSlideMethod == "AT_RUNTIME": workflow.execute_node(timeSlideNode) else: workflow.add_node(timeSlideNode) tisiOutFile = timeSlideNode.output_files[0] elif timeSlideMethod == "PREGENERATED": timeSlideFilePath = workflow.cp.get_opt_tags("workflow-timeslides", "timeslides-pregenerated-file", currTags) file_url = urlparse.urljoin('file:', urllib.pathname2url(\ timeSlideFilePath)) tisiOutFile = File(ifoString, 'PREGEN_TIMESLIDES', fullSegment, file_url, tags=currTags) timeSlideOuts.append(tisiOutFile) return timeSlideOuts
def setup_tmpltbank_dax_generated(workflow, science_segs, datafind_outs, output_dir, tags=None, psd_files=None): ''' Setup template bank jobs that are generated as part of the CBC workflow. This function will add numerous jobs to the CBC workflow using configuration options from the .ini file. The following executables are currently supported: * lalapps_tmpltbank * pycbc_geom_nonspin_bank Parameters ---------- workflow: pycbc.workflow.core.Workflow An instanced class that manages the constructed workflow. science_segs : Keyed dictionary of ligo.segments.segmentlist objects scienceSegs[ifo] holds the science segments to be analysed for each ifo. datafind_outs : pycbc.workflow.core.FileList The file list containing the datafind files. output_dir : path string The directory where data products will be placed. tags : list of strings If given these tags are used to uniquely name and identify output files that would be produced in multiple calls to this function. psd_file : pycbc.workflow.core.FileList The file list containing predefined PSDs, if provided. Returns -------- tmplt_banks : pycbc.workflow.core.FileList The FileList holding the details of all the template bank jobs. ''' if tags is None: tags = [] cp = workflow.cp # Need to get the exe to figure out what sections are analysed, what is # discarded etc. This should *not* be hardcoded, so using a new executable # will require a bit of effort here .... ifos = science_segs.keys() tmplt_bank_exe = os.path.basename(cp.get('executables', 'tmpltbank')) # Select the appropriate class exe_class = select_tmpltbank_class(tmplt_bank_exe) # Set up class for holding the banks tmplt_banks = FileList([]) for ifo in ifos: job_instance = exe_class(workflow.cp, 'tmpltbank', ifo=ifo, out_dir=output_dir, tags=tags) # Check for the write_psd flag if cp.has_option_tags("workflow-tmpltbank", "tmpltbank-write-psd-file", tags): job_instance.write_psd = True else: job_instance.write_psd = False sngl_ifo_job_setup(workflow, ifo, tmplt_banks, job_instance, science_segs[ifo], datafind_outs, allow_overlap=True) return tmplt_banks
def setup_tmpltbank_without_frames(workflow, output_dir, tags=None, independent_ifos=False, psd_files=None): ''' Setup CBC workflow to use a template bank (or banks) that are generated in the workflow, but do not use the data to estimate a PSD, and therefore do not vary over the duration of the workflow. This can either generate one bank that is valid for all ifos at all times, or multiple banks that are valid only for a single ifo at all times (one bank per ifo). Parameters ---------- workflow: pycbc.workflow.core.Workflow An instanced class that manages the constructed workflow. output_dir : path string The directory where the template bank outputs will be placed. tags : list of strings If given these tags are used to uniquely name and identify output files that would be produced in multiple calls to this function. independent_ifos : Boolean, optional (default=False) If given this will produce one template bank per ifo. If not given there will be on template bank to cover all ifos. psd_file : pycbc.workflow.core.FileList The file list containing predefined PSDs, if provided. Returns -------- tmplt_banks : pycbc.workflow.core.FileList The FileList holding the details of the template bank(s). ''' if tags is None: tags = [] cp = workflow.cp # Need to get the exe to figure out what sections are analysed, what is # discarded etc. This should *not* be hardcoded, so using a new executable # will require a bit of effort here .... ifos = workflow.ifos fullSegment = workflow.analysis_time tmplt_bank_exe = os.path.basename(cp.get('executables', 'tmpltbank')) # Can not use lalapps_template bank with this if tmplt_bank_exe == 'lalapps_tmpltbank': errMsg = "Lalapps_tmpltbank cannot be used to generate template banks " errMsg += "without using frames. Try another code." raise ValueError(errMsg) # Select the appropriate class exe_instance = select_tmpltbank_class(tmplt_bank_exe) tmplt_banks = FileList([]) # Make the distinction between one bank for all ifos and one bank per ifo if independent_ifos: ifoList = [ifo for ifo in ifos] else: ifoList = [[ifo for ifo in ifos]] # Check for the write_psd flag if cp.has_option_tags("workflow-tmpltbank", "tmpltbank-write-psd-file", tags): exe_instance.write_psd = True else: exe_instance.write_psd = False for ifo in ifoList: job_instance = exe_instance(workflow.cp, 'tmpltbank', ifo=ifo, out_dir=output_dir, tags=tags, psd_files=psd_files) node = job_instance.create_nodata_node(fullSegment) workflow.add_node(node) tmplt_banks += node.output_files return tmplt_banks
def setup_plotthinca(workflow, input_files, cache_filename, coinc_cachepattern, slide_cachepattern, output_dir, tags=[], **kwargs): """ This function sets up the nodes that will generate summary from a list of thinca files. Parameters ----------- Workflow : ahope.Workflow The ahope workflow instance that the coincidence jobs will be added to. input_files : ahope.FileList An FileList of files that are used as input at this stage. cache_filename : str Filename of the ihope cache. coinc_cachepattern : str The pattern that will be used to find zero-lag coincidence filenames in the cache. slide_cachepattern : str The pattern that will be used to find time slide filenames in the cache. output_dir : path The directory in which output files will be stored. tags : list of strings (optional, default = []) A list of the tagging strings that will be used for all jobs created by this call to the workflow. An example might be ['full_data']. This will be used in output names and directories. Returns -------- plot_files : ahope.FileList A list of the output files from this stage. """ plot_files = FileList([]) # create executable plotthinca_job = Executable(workflow.cp, 'plotthinca', 'vanilla', workflow.ifos, output_dir, tags) # get all ifo combinations of at least 2 coincident ifos ifo_combos = [] for n in xrange(len(plotthinca_job.ifo_list) + 1): for ifo_list in itertools.combinations(plotthinca_job.ifo_list, n + 2): ifo_combos.append(ifo_list) for tag in tags: for ifo_list in ifo_combos: ifo_string = ''.join(ifo_list) # create node node = Node(plotthinca_job) node.add_opt('--gps-start-time', workflow.analysis_time[0]) node.add_opt('--gps-end-time', workflow.analysis_time[1]) node.add_opt('--cache-file', cache_filename) node.add_opt('--ifo-times', ifo_string) node.add_opt('--ifo-tag', 'SECOND_' + ifo_string) for ifo in ifo_list: node.add_opt('--%s-triggers' % ifo.lower(), '') node.add_opt('--user-tag', tag.upper() + '_SUMMARY_PLOTS') node.add_opt('--output-path', output_dir) node.add_opt('--coinc-pattern', coinc_cachepattern) node.add_opt('--slide-pattern', slide_cachepattern) node.add_opt('--enable-output') # add node to workflow workflow.add_node(node) # make all input_files parents #for f in input_files: # dep = dax.Dependency(parent=f.node._dax_node, child=node._dax_node) # workflow._adag.addDependency(dep) return plot_files
def setup_matchedfltr_dax_generated(workflow, science_segs, datafind_outs, tmplt_banks, output_dir, injection_file=None, tags=None, link_to_tmpltbank=False, compatibility_mode=False): ''' Setup matched-filter jobs that are generated as part of the workflow. This module can support any matched-filter code that is similar in principle to lalapps_inspiral, but for new codes some additions are needed to define Executable and Job sub-classes (see jobutils.py). Parameters ----------- workflow : pycbc.workflow.core.Workflow The Workflow instance that the coincidence jobs will be added to. science_segs : ifo-keyed dictionary of glue.segments.segmentlist instances The list of times that are being analysed in this workflow. datafind_outs : pycbc.workflow.core.FileList An FileList of the datafind files that are needed to obtain the data used in the analysis. tmplt_banks : pycbc.workflow.core.FileList An FileList of the template bank files that will serve as input in this stage. output_dir : path The directory in which output will be stored. injection_file : pycbc.workflow.core.File, optional (default=None) If given the file containing the simulation file to be sent to these jobs on the command line. If not given no file will be sent. tags : list of strings (optional, default = []) A list of the tagging strings that will be used for all jobs created by this call to the workflow. An example might be ['BNSINJECTIONS'] or ['NOINJECTIONANALYSIS']. This will be used in output names. link_to_tmpltbank : boolean, optional (default=True) If this option is given, the job valid_times will be altered so that there will be one inspiral file for every template bank and they will cover the same time span. Note that this option must also be given during template bank generation to be meaningful. Returns ------- inspiral_outs : pycbc.workflow.core.FileList A list of output files written by this stage. This *will not* contain any intermediate products produced within this stage of the workflow. If you require access to any intermediate products produced at this stage you can call the various sub-functions directly. ''' if tags is None: tags = [] # Need to get the exe to figure out what sections are analysed, what is # discarded etc. This should *not* be hardcoded, so using a new executable # will require a bit of effort here .... cp = workflow.cp ifos = science_segs.keys() match_fltr_exe = os.path.basename(cp.get('executables', 'inspiral')) # Select the appropriate class exe_class = select_matchedfilter_class(match_fltr_exe) if link_to_tmpltbank: # Use this to ensure that inspiral and tmpltbank jobs overlap. This # means that there will be 1 inspiral job for every 1 tmpltbank and # the data read in by both will overlap as much as possible. (If you # ask the template bank jobs to use 2000s of data for PSD estimation # and the matched-filter jobs to use 4000s, you will end up with # twice as many matched-filter jobs that still use 4000s to estimate a # PSD but then only generate triggers in the 2000s of data that the # template bank jobs ran on. tmpltbank_exe = os.path.basename(cp.get('executables', 'tmpltbank')) link_exe_instance = select_tmpltbank_class(tmpltbank_exe) else: link_exe_instance = None # Set up class for holding the banks inspiral_outs = FileList([]) # Matched-filtering is done independently for different ifos, but might not be! # If we want to use multi-detector matched-filtering or something similar to this # it would probably require a new module for ifo in ifos: logging.info("Setting up matched-filtering for %s." % (ifo)) job_instance = exe_class(workflow.cp, 'inspiral', ifo=ifo, out_dir=output_dir, injection_file=injection_file, tags=tags) if link_exe_instance: link_job_instance = link_exe_instance(cp, 'tmpltbank', ifo=ifo, out_dir=output_dir, tags=tags) else: link_job_instance = None sngl_ifo_job_setup(workflow, ifo, inspiral_outs, job_instance, science_segs[ifo], datafind_outs, parents=tmplt_banks, allow_overlap=False, link_job_instance=link_job_instance, compatibility_mode=compatibility_mode) return inspiral_outs
def setup_summary_plots( workflow, input_files, cache_filename, tmpltbank_cachepattern, inspiral_cachepattern, #coinc_cachepattern, slide_cachepattern, output_dir, tags=[], **kwargs): """ This function sets up the summary plots jobs. Parameters ----------- Workflow : ahope.Workflow The ahope workflow instance that the coincidence jobs will be added to. input_files : ahope.FileList An FileList of files that are used as input at this stage. cache_filename : str Filename of the ihope cache. tmpltbank_cachepattern : str The pattern that will be used to find template_bank filenames in the cache. inspiral_cachepattern : str The pattern that will be used to find inspiral filenames in the cache. coinc_cachepattern : str (currently not implemented) The pattern that will be used to find zero-lag coincidence filenames in the cache. slide_cachepattern : str (currently not implemented) The pattern that will be used to find time slide filenames in the cache. output_dir : path The directory in which output files will be stored. tags : list of strings (optional, default = []) A list of the tagging strings that will be used for all jobs created by this call to the workflow. An example might be ['full_data']. This will be used in output names and directories. Returns -------- plot_files : ahope.FileList A list of the output files from this stage. """ plot_files = FileList([]) # make summary plot dir if not os.path.exists(output_dir): os.makedirs(output_dir) # setup summary plot jobs plotinspiral_files = setup_plotinspiral(workflow, input_files, cache_filename, inspiral_cachepattern, output_dir, tags) plotinspiralrange_files = setup_plotinspiralrange(workflow, input_files, cache_filename, tmpltbank_cachepattern, inspiral_cachepattern, output_dir, tags) plotnumtemplates_files = setup_plotnumtemplates(workflow, input_files, cache_filename, tmpltbank_cachepattern, output_dir, tags) #plotthinca_files = setup_plotthinca(workflow, input_files, cache_filename, # coinc_cachepattern, slide_cachepattern, # output_dir, tags) # concatenate plot files plot_files += plotinspiral_files plot_files += plotinspiralrange_files plot_files += plotnumtemplates_files #plot_files += plotthinca_files return plot_files
def setup_injection_workflow(workflow, output_dir=None, inj_section_name='injections', exttrig_file=None, tags=None): """ This function is the gateway for setting up injection-generation jobs in a workflow. It should be possible for this function to support a number of different ways/codes that could be used for doing this, however as this will presumably stay as a single call to a single code (which need not be inspinj) there are currently no subfunctions in this moudle. Parameters ----------- workflow : pycbc.workflow.core.Workflow The Workflow instance that the coincidence jobs will be added to. output_dir : path The directory in which injection files will be stored. inj_section_name : string (optional, default='injections') The string that corresponds to the option describing the exe location in the [executables] section of the .ini file and that corresponds to the section (and sub-sections) giving the options that will be given to the code at run time. tags : list of strings (optional, default = []) A list of the tagging strings that will be used for all jobs created by this call to the workflow. This will be used in output names. Returns -------- inj_files : pycbc.workflow.core.FileList The list of injection files created by this call. inj_tags : list of strings The tag corresponding to each injection file and used to uniquely identify them. The FileList class contains functions to search based on tags. """ if tags is None: tags = [] logging.info("Entering injection module.") make_analysis_dir(output_dir) # Get full analysis segment for output file naming full_segment = workflow.analysis_time ifos = workflow.ifos # Identify which injections to do by presence of sub-sections in # the configuration file inj_tags = [] inj_files = FileList([]) for section in workflow.cp.get_subsections(inj_section_name): inj_tag = section.upper() curr_tags = tags + [inj_tag] # Parse for options in ini file injection_method = workflow.cp.get_opt_tags("workflow-injections", "injections-method", curr_tags) if injection_method in ["IN_WORKFLOW", "AT_RUNTIME"]: # FIXME: Add ability to specify different exes inj_job = LalappsInspinjExecutable(workflow.cp, inj_section_name, out_dir=output_dir, ifos='HL', tags=curr_tags) node = inj_job.create_node(full_segment) if injection_method == "AT_RUNTIME": workflow.execute_node(node) else: workflow.add_node(node) inj_file = node.output_files[0] inj_files.append(inj_file) elif injection_method == "PREGENERATED": file_attrs = { 'ifos': ['HL'], 'segs': full_segment, 'tags': curr_tags } injection_path = workflow.cp.get_opt_tags( "workflow-injections", "injections-pregenerated-file", curr_tags) curr_file = resolve_url_to_file(injection_path, attrs=file_attrs) inj_files.append(curr_file) elif injection_method in ["IN_COH_PTF_WORKFLOW", "AT_COH_PTF_RUNTIME"]: inj_job = LalappsInspinjExecutable(workflow.cp, inj_section_name, out_dir=output_dir, ifos=ifos, tags=curr_tags) node = inj_job.create_node(full_segment, exttrig_file) if injection_method == "AT_COH_PTF_RUNTIME": workflow.execute_node(node) else: workflow.add_node(node) inj_file = node.output_files[0] if workflow.cp.has_option("workflow-injections", "em-bright-only"): em_filter_job = PycbcDarkVsBrightInjectionsExecutable( workflow.cp, 'em_bright_filter', tags=curr_tags, out_dir=output_dir, ifos=ifos) node = em_filter_job.create_node(inj_file, full_segment, curr_tags) if injection_method == "AT_COH_PTF_RUNTIME": workflow.execute_node(node) else: workflow.add_node(node) inj_file = node.output_files[0] if workflow.cp.has_option("workflow-injections", "do-jitter-skyloc"): jitter_job = LigolwCBCJitterSkylocExecutable( workflow.cp, 'jitter_skyloc', tags=curr_tags, out_dir=output_dir, ifos=ifos) node = jitter_job.create_node(inj_file, full_segment, curr_tags) if injection_method == "AT_COH_PTF_RUNTIME": workflow.execute_node(node) else: workflow.add_node(node) inj_file = node.output_files[0] if workflow.cp.has_option("workflow-injections", "do-align-total-spin"): align_job = LigolwCBCAlignTotalSpinExecutable( workflow.cp, 'align_total_spin', tags=curr_tags, out_dir=output_dir, ifos=ifos) node = align_job.create_node(inj_file, full_segment, curr_tags) if injection_method == "AT_COH_PTF_RUNTIME": workflow.execute_node(node) else: workflow.add_node(node) inj_file = node.output_files[0] inj_files.append(inj_file) else: err = "Injection method must be one of IN_WORKFLOW, " err += "AT_RUNTIME or PREGENERATED. Got %s." % (injection_method) raise ValueError(err) inj_tags.append(inj_tag) logging.info("Leaving injection module.") return inj_files, inj_tags
def setup_hardware_injection_page(workflow, input_files, cache_filename, inspiral_cachepattern, output_dir, tags=[], **kwargs): """ This function sets up the nodes that will create the hardware injection page. Parameters ----------- Workflow : ahope.Workflow The ahope workflow instance that the coincidence jobs will be added to. input_files : ahope.FileList An FileList of files that are used as input at this stage. cache_filename : str Filename of the ihope cache. inspiral_cachepattern : str The pattern that will be used to find inspiral filenames in the cache. output_dir : path The directory in which output files will be stored. tags : list of strings (optional, default = []) A list of the tagging strings that will be used for all jobs created by this call to the workflow. An example might be ['full_data']. This will be used to search the cache. Returns -------- plot_files : ahope.FileList A list of the output files from this stage. """ logging.info("Entering hardware injection page setup.") out_files = FileList([]) # check if hardware injection section exists # if not then do not do add hardware injection job to the workflow if not workflow.cp.has_section('workflow-hardware-injections'): msg = "There is no workflow-hardware-injections section. " msg += "The hardware injection page will not be added to the workflow." logging.info(msg) logging.info("Leaving hardware injection page setup.") return out_files # make the output dir if not os.path.exists(output_dir): os.makedirs(output_dir) # create executable hwinjpage_job = Executable(workflow.cp, 'hardware_injection_page', 'vanilla', workflow.ifos, output_dir, tags) # retrieve hardware injection file hwinjDefUrl = workflow.cp.get_opt_tags('workflow-hardware-injections', 'hwinj-definer-url', tags) hwinjDefBaseName = os.path.basename(hwinjDefUrl) hwinjDefNewPath = os.path.join(output_dir, hwinjDefBaseName) urllib.urlretrieve(hwinjDefUrl, hwinjDefNewPath) # update hwinj definer file location workflow.cp.set("workflow-hardware-injections", "hwinj-definer-file", hwinjDefNewPath) # query for the hardware injection segments get_hardware_injection_segment_files(workflow, output_dir, hwinjDefNewPath) # create node node = Node(hwinjpage_job) node.add_opt('--gps-start-time', workflow.analysis_time[0]) node.add_opt('--gps-end-time', workflow.analysis_time[1]) node.add_opt('--source-xml', hwinjDefNewPath) node.add_opt('--segment-dir', output_dir) node.add_opt('--cache-file', cache_filename) node.add_opt('--cache-pattern', inspiral_cachepattern) node.add_opt('--analyze-injections', '') for ifo in workflow.ifos: node.add_opt('--%s-injections' % ifo.lower(), '') outfile = File(node.executable.ifo_string, 'HWINJ_SUMMARY', workflow.analysis_time, extension='html', directory=output_dir) node.add_opt('--outfile', outfile.storage_path) # add node to workflow workflow.add_node(node) # make all input_files parents #for f in input_files: # dep = dax.Dependency(parent=f.node._dax_node, child=node._dax_node) # workflow._adag.addDependency(dep) out_files += node.output_files logging.info("Leaving hardware injection page setup.") return out_files
def setup_interval_coinc_inj(workflow, hdfbank, full_data_trig_files, inj_trig_files, background_file, veto_file, veto_name, out_dir, tags=None): """ This function sets up exact match coincidence and background estimation using a folded interval technique. """ if tags is None: tags = [] make_analysis_dir(out_dir) logging.info('Setting up coincidence for injection') if len(hdfbank) > 1: raise ValueError('This coincidence method only supports a ' 'pregenerated template bank') hdfbank = hdfbank[0] if len(workflow.ifos) > 2: raise ValueError( 'This coincidence method only supports two ifo searches') # Wall time knob and memory knob factor = int( workflow.cp.get_opt_tags('workflow-coincidence', 'parallelization-factor', tags)) ffiles = {} ifiles = {} ifos, files = full_data_trig_files.categorize_by_attr('ifo') for ifo, file in zip(ifos, files): ffiles[ifo] = file[0] ifos, files = inj_trig_files.categorize_by_attr('ifo') for ifo, file in zip(ifos, files): ifiles[ifo] = file[0] ifo0, ifo1 = ifos[0], ifos[1] combo = [ (FileList([ifiles[ifo0], ifiles[ifo1]]), "injinj"), (FileList([ifiles[ifo0], ffiles[ifo1]]), "injfull"), (FileList([ifiles[ifo1], ffiles[ifo0]]), "fullinj"), ] bg_files = {'injinj': [], 'injfull': [], 'fullinj': []} for trig_files, ctag in combo: findcoinc_exe = PyCBCFindCoincExecutable(workflow.cp, 'coinc', ifos=workflow.ifos, tags=tags + [ctag], out_dir=out_dir) for i in range(factor): group_str = '%s/%s' % (i, factor) coinc_node = findcoinc_exe.create_node(trig_files, hdfbank, veto_file, veto_name, group_str, tags=([str(i)])) bg_files[ctag] += coinc_node.output_files workflow.add_node(coinc_node) return setup_statmap_inj(workflow, bg_files, background_file, hdfbank, out_dir, tags=tags)
def setup_plotnumtemplates(workflow, input_files, cache_filename, tmpltbank_cachepattern, output_dir, tags=[], **kwargs): """ This function sets up the nodes that will generate a plot of the number of templates against time. Parameters ----------- Workflow : ahope.Workflow The ahope workflow instance that the coincidence jobs will be added to. input_files : ahope.FileList An FileList of files that are used as input at this stage. cache_filename : str Filename of the ihope cache. tmpltbank_cachepattern : str The pattern that will be used to find template_bank filenames in the cache. output_dir : path The directory in which output files will be stored. tags : list of strings (optional, default = []) A list of the tagging strings that will be used for all jobs created by this call to the workflow. An example might be ['full_data']. This will be used in output names and directories. Returns -------- plot_files : ahope.FileList A list of the output files from this stage. """ plot_files = FileList([]) # create executable plotnumtemplates_job = Executable(workflow.cp, 'plotnumtemplates', 'vanilla', workflow.ifos, output_dir, tags) for tag in tags: # create node node = Node(plotnumtemplates_job) node.add_opt('--gps-start-time', workflow.analysis_time[0]) node.add_opt('--gps-end-time', workflow.analysis_time[1]) node.add_opt('--cache-file', cache_filename) node.add_opt('--ifo-times', node.executable.ifo_string) node.add_opt('--user-tag', tag.upper() + '_SUMMARY_PLOTS') node.add_opt('--output-path', output_dir) node.add_opt('--bank-pattern', tmpltbank_cachepattern) node.add_opt('--enable-output') # add node to workflow workflow.add_node(node) # make all input_files parents #for f in input_files: # dep = dax.Dependency(parent=f.node._dax_node, child=node._dax_node) # workflow._adag.addDependency(dep) return plot_files
def setup_datafind_workflow(workflow, scienceSegs, outputDir, seg_file=None, tags=None): """ Setup datafind section of the workflow. This section is responsible for generating, or setting up the workflow to generate, a list of files that record the location of the frame files needed to perform the analysis. There could be multiple options here, the datafind jobs could be done at run time or could be put into a dag. The subsequent jobs will know what was done here from the OutFileList containing the datafind jobs (and the Dagman nodes if appropriate. For now the only implemented option is to generate the datafind files at runtime. This module can also check if the frameFiles actually exist, check whether the obtained segments line up with the original ones and update the science segments to reflect missing data files. Parameters ---------- workflow: pycbc.workflow.core.Workflow The workflow class that stores the jobs that will be run. scienceSegs : Dictionary of ifo keyed glue.segment.segmentlist instances This contains the times that the workflow is expected to analyse. outputDir : path All output files written by datafind processes will be written to this directory. seg_file : SegFile, optional (default=None) The file returned by get_science_segments containing the science segments and the associated segment_summary. This will be used for the segment_summary test and is required if, and only if, performing that test. tags : list of string, optional (default=None) Use this to specify tags. This can be used if this module is being called more than once to give call specific configuration (by setting options in [workflow-datafind-${TAG}] rather than [workflow-datafind]). This is also used to tag the Files returned by the class to uniqueify the Files and uniqueify the actual filename. FIXME: Filenames may not be unique with current codes! Returns -------- datafindOuts : OutGroupList List of all the datafind output files for use later in the pipeline. sci_avlble_file : SegFile SegFile containing the analysable time after checks in the datafind module are applied to the input segment list. For production runs this is expected to be equal to the input segment list. scienceSegs : Dictionary of ifo keyed glue.segment.segmentlist instances This contains the times that the workflow is expected to analyse. If the updateSegmentTimes kwarg is given this will be updated to reflect any instances of missing data. sci_avlble_name : string The name with which the analysable time is stored in the sci_avlble_file. """ if tags is None: tags = [] logging.info("Entering datafind module") make_analysis_dir(outputDir) cp = workflow.cp # Parse for options in ini file datafindMethod = cp.get_opt_tags("workflow-datafind", "datafind-method", tags) if cp.has_option_tags("workflow-datafind", "datafind-check-segment-gaps", tags): checkSegmentGaps = cp.get_opt_tags("workflow-datafind", "datafind-check-segment-gaps", tags) else: checkSegmentGaps = "no_test" if cp.has_option_tags("workflow-datafind", "datafind-check-frames-exist", tags): checkFramesExist = cp.get_opt_tags("workflow-datafind", "datafind-check-frames-exist", tags) else: checkFramesExist = "no_test" if cp.has_option_tags("workflow-datafind", "datafind-check-segment-summary", tags): checkSegmentSummary = cp.get_opt_tags("workflow-datafind", "datafind-check-segment-summary", tags) else: checkSegmentSummary = "no_test" logging.info("Starting datafind with setup_datafind_runtime_generated") if datafindMethod == "AT_RUNTIME_MULTIPLE_CACHES": datafindcaches, datafindouts = \ setup_datafind_runtime_cache_multi_calls_perifo(cp, scienceSegs, outputDir, tags=tags) elif datafindMethod == "AT_RUNTIME_SINGLE_CACHES": datafindcaches, datafindouts = \ setup_datafind_runtime_cache_single_call_perifo(cp, scienceSegs, outputDir, tags=tags) elif datafindMethod == "AT_RUNTIME_MULTIPLE_FRAMES": datafindcaches, datafindouts = \ setup_datafind_runtime_frames_multi_calls_perifo(cp, scienceSegs, outputDir, tags=tags) elif datafindMethod == "AT_RUNTIME_SINGLE_FRAMES": datafindcaches, datafindouts = \ setup_datafind_runtime_frames_single_call_perifo(cp, scienceSegs, outputDir, tags=tags) elif datafindMethod == "FROM_PREGENERATED_LCF_FILES": ifos = scienceSegs.keys() datafindcaches, datafindouts = \ setup_datafind_from_pregenerated_lcf_files(cp, ifos, outputDir, tags=tags) else: msg = "Entry datafind-method in [workflow-datafind] does not have " msg += "expected value. Valid values are " msg += "AT_RUNTIME_MULTIPLE_FRAMES, AT_RUNTIME_SINGLE_FRAMES " msg += "AT_RUNTIME_MULTIPLE_CACHES or AT_RUNTIME_SINGLE_CACHES. " msg += "Consult the documentation for more info." raise ValueError(msg) using_backup_server = False if datafindMethod == "AT_RUNTIME_MULTIPLE_FRAMES" or \ datafindMethod == "AT_RUNTIME_SINGLE_FRAMES": if cp.has_option_tags("workflow-datafind", "datafind-backup-datafind-server", tags): using_backup_server = True backup_server = cp.get_opt_tags("workflow-datafind", "datafind-backup-datafind-server", tags) cp_new = copy.deepcopy(cp) cp_new.set("workflow-datafind", "datafind-ligo-datafind-server", backup_server) cp_new.set('datafind', 'urltype', 'gsiftp') backup_datafindcaches, backup_datafindouts =\ setup_datafind_runtime_frames_single_call_perifo(cp_new, scienceSegs, outputDir, tags=tags) backup_datafindouts = datafind_keep_unique_backups(\ backup_datafindouts, datafindouts) datafindcaches.extend(backup_datafindcaches) datafindouts.extend(backup_datafindouts) logging.info("setup_datafind_runtime_generated completed") # If we don't have frame files covering all times we can update the science # segments. if checkSegmentGaps in ['warn','update_times','raise_error']: logging.info("Checking science segments against datafind output....") newScienceSegs = get_science_segs_from_datafind_outs(datafindcaches) logging.info("New segments calculated from data find output.....") missingData = False for ifo in scienceSegs.keys(): # If no science segments in input then do nothing if not scienceSegs[ifo]: msg = "No science segments are present for ifo %s, " %(ifo) msg += "the segment metadata indicates there is no analyzable" msg += " strain data between the selected GPS start and end " msg += "times." logging.warning(msg) continue if not newScienceSegs.has_key(ifo): msg = "No data frames were found corresponding to the science " msg += "segments for ifo %s" %(ifo) logging.error(msg) missingData = True if checkSegmentGaps == 'update_times': scienceSegs[ifo] = segments.segmentlist() continue missing = scienceSegs[ifo] - newScienceSegs[ifo] if abs(missing): msg = "From ifo %s we are missing frames covering:" %(ifo) msg += "\n%s" % "\n".join(map(str, missing)) missingData = True logging.error(msg) if checkSegmentGaps == 'update_times': # Remove missing time, so that we can carry on if desired logging.info("Updating science segments for ifo %s." %(ifo)) scienceSegs[ifo] = scienceSegs[ifo] - missing if checkSegmentGaps == 'raise_error' and missingData: raise ValueError("Workflow cannot find needed data, exiting.") logging.info("Done checking, any discrepancies are reported above.") elif checkSegmentGaps == 'no_test': pass else: errMsg = "checkSegmentGaps kwarg must take a value from 'no_test', " errMsg += "'warn', 'update_times' or 'raise_error'." raise ValueError(errMsg) # Do all of the frame files that were returned actually exist? if checkFramesExist in ['warn','update_times','raise_error']: logging.info("Verifying that all frames exist on disk.") missingFrSegs, missingFrames = \ get_missing_segs_from_frame_file_cache(datafindcaches) missingFlag = False for ifo in missingFrames.keys(): # If no data in the input then do nothing if not scienceSegs[ifo]: continue # If using a backup server, does the frame exist remotely? if using_backup_server: # WARNING: This will be slow, but hopefully it will not occur # for too many frames. This could be optimized if # it becomes necessary. new_list = [] for frame in missingFrames[ifo]: for dfout in datafindouts: dfout_pfns = list(dfout.pfns) dfout_urls = [a.url for a in dfout_pfns] if frame.url in dfout_urls: pfn = dfout_pfns[dfout_urls.index(frame.url)] dfout.removePFN(pfn) if len(dfout.pfns) == 0: new_list.append(frame) else: msg = "Frame %s not found locally. "\ %(frame.url,) msg += "Replacing with remote url(s) %s." \ %(str([a.url for a in dfout.pfns]),) logging.info(msg) break else: new_list.append(frame) missingFrames[ifo] = new_list if missingFrames[ifo]: msg = "From ifo %s we are missing the following frames:" %(ifo) msg +='\n'.join([a.url for a in missingFrames[ifo]]) missingFlag = True logging.error(msg) if checkFramesExist == 'update_times': # Remove missing times, so that we can carry on if desired logging.info("Updating science times for ifo %s." %(ifo)) scienceSegs[ifo] = scienceSegs[ifo] - missingFrSegs[ifo] if checkFramesExist == 'raise_error' and missingFlag: raise ValueError("Workflow cannot find all frames, exiting.") logging.info("Finished checking frames.") elif checkFramesExist == 'no_test': pass else: errMsg = "checkFramesExist kwarg must take a value from 'no_test', " errMsg += "'warn', 'update_times' or 'raise_error'." raise ValueError(errMsg) # Check if there are cases where frames exist, but no entry in the segment # summary table are present. if checkSegmentSummary in ['warn', 'raise_error']: logging.info("Checking the segment summary table against frames.") dfScienceSegs = get_science_segs_from_datafind_outs(datafindcaches) missingFlag = False # NOTE: Should this be overrideable in the config file? sci_seg_name = "SCIENCE" if seg_file is None: err_msg = "You must provide the science segments SegFile object " err_msg += "if using the datafind-check-segment-summary option." raise ValueError(err_msg) if seg_file.seg_summ_dict is None: err_msg = "The provided science segments SegFile object must " err_msg += "contain a valid segment_summary table if using the " err_msg += "datafind-check-segment-summary option." raise ValueError(err_msg) seg_summary_times = seg_file.seg_summ_dict for ifo in dfScienceSegs.keys(): curr_seg_summ_times = seg_summary_times[ifo + ":" + sci_seg_name] missing = (dfScienceSegs[ifo] & seg_file.valid_segments) missing.coalesce() missing = missing - curr_seg_summ_times missing.coalesce() scienceButNotFrame = scienceSegs[ifo] - dfScienceSegs[ifo] scienceButNotFrame.coalesce() missing2 = scienceSegs[ifo] - scienceButNotFrame missing2.coalesce() missing2 = missing2 - curr_seg_summ_times missing2.coalesce() if abs(missing): msg = "From ifo %s the following times have frames, " %(ifo) msg += "but are not covered in the segment summary table." msg += "\n%s" % "\n".join(map(str, missing)) logging.error(msg) missingFlag = True if abs(missing2): msg = "From ifo %s the following times have frames, " %(ifo) msg += "are science, and are not covered in the segment " msg += "summary table." msg += "\n%s" % "\n".join(map(str, missing2)) logging.error(msg) missingFlag = True if checkSegmentSummary == 'raise_error' and missingFlag: errMsg = "Segment_summary discrepancy detected, exiting." raise ValueError(errMsg) elif checkSegmentSummary == 'no_test': pass else: errMsg = "checkSegmentSummary kwarg must take a value from 'no_test', " errMsg += "'warn', or 'raise_error'." raise ValueError(errMsg) # Now need to create the file for SCIENCE_AVAILABLE sci_avlble_dict = segments.segmentlistdict() # NOTE: Should this be overrideable in the config file? sci_avlble_name = "SCIENCE_AVAILABLE" for ifo in scienceSegs.keys(): sci_avlble_dict[ifo + ':' + sci_avlble_name] = scienceSegs[ifo] sci_avlble_file = SegFile.from_segment_list_dict('SCIENCE_AVAILABLE', sci_avlble_dict, ifo_list = scienceSegs.keys(), valid_segment=workflow.analysis_time, extension='.xml', tags=tags, directory=outputDir) logging.info("Leaving datafind module") return FileList(datafindouts), sci_avlble_file, scienceSegs, sci_avlble_name
def create_node(self, trig_files=None, segment_dir=None, analysis_seg=None, slide_tag=None, out_tags=None, tags=None): import Pegasus.DAX3 as dax if out_tags is None: out_tags = [] if tags is None: tags = [] node = Node(self) if not trig_files: raise ValueError("%s must be supplied with trigger files" % self.name) # Data options num_trials = int(self.cp.get("trig_combiner", "num-trials")) trig_name = self.cp.get('workflow', 'trigger-name') if all("COHERENT_NO_INJECTIONS" in t.name for t in trig_files) and \ self.cp.has_option_tag('inspiral', 'do-short-slides', 'coherent_no_injections'): node.add_opt('--short-slides') node.add_opt('--grb-name', trig_name) node.add_opt('--trig-start-time', analysis_seg[0]) node.add_opt('--ifo-tag', self.ifos) node.add_opt('--user-tag', 'INSPIRAL') if tags: node.add_opt('--job-tag', '_'.join(tags)) if slide_tag is not None: node.add_opt('--slide-tag', slide_tag) node.add_opt('--long-slides') tag_start=["TIMESLIDES_GRB%s_%s" % (trig_name, slide_tag)]+tags else: tag_start=["GRB%s" % trig_name]+tags # Set input / output options if all(hasattr(t.node, "executable") for t in trig_files): if all(t.node.executable.name == "trig_cluster" for t in trig_files): node.add_opt('--input-files', " ".join([t.storage_path for t in trig_files])) if self.cp.has_option_tag('inspiral', 'do-short-slides', 'coherent_no_injections'): node.add_opt('--short-slides') else: node.add_input_list_opt('--input-files', trig_files) else: node.add_opt('--input-files', " ".join([t.storage_path for t in trig_files])) node.add_opt('--segment-dir', segment_dir) node.add_opt('--output-dir', self.out_dir) out_files = FileList([]) for out_tag in out_tags: out_file = File(self.ifos, 'INSPIRAL', trig_files[0].segment, directory=self.out_dir, extension='xml.gz', tags=tag_start+[out_tag], store_file=self.retain_files) out_files.append(out_file) #node._dax_node.uses(out_file, link=dax.Link.OUTPUT, register=False, # transfer=False) #node._outputs += [out_file] #out_file.node = node #node._add_output(out_file) for trial in range(1, num_trials + 1): out_file = File(self.ifos, 'INSPIRAL', trig_files[0].segment, directory=self.out_dir, extension='xml.gz', tags=tag_start+["OFFTRIAL_%d" % trial], store_file=self.retain_files) out_files.append(out_file) #node._dax_node.uses(out_file, link=dax.Link.OUTPUT, register=False, # transfer=False) #node._outputs += [out_file] #out_file.node = node #node._add_output(out_file) node.add_profile('condor', 'request_cpus', self.num_threads) return node, out_files
def make_single_template_plots(workflow, segs, data_read_name, analyzed_name, params, out_dir, inj_file=None, exclude=None, require=None, tags=None, params_str=None, use_exact_inj_params=False): """Function for creating jobs to run the pycbc_single_template code and to run the associated plotting code pycbc_single_template_plots and add these jobs to the workflow. Parameters ----------- workflow : workflow.Workflow instance The pycbc.workflow.Workflow instance to add these jobs to. segs : workflow.File instance The pycbc.workflow.File instance that points to the XML file containing the segment lists of data read in and data analyzed. data_read_name : str The name of the segmentlist containing the data read in by each inspiral job in the segs file. analyzed_name : str The name of the segmentlist containing the data analyzed by each inspiral job in the segs file. params : dictionary A dictionary containing the parameters of the template to be used. params[ifo+'end_time'] is required for all ifos in workflow.ifos. If use_exact_inj_params is False then also need to supply values for [mass1, mass2, spin1z, spin2x]. For precessing templates one also needs to supply [spin1y, spin1x, spin2x, spin2y, inclination] additionally for precession one must supply u_vals or u_vals_+ifo for all ifos. u_vals is the ratio between h_+ and h_x to use when constructing h(t). h(t) = (h_+ * u_vals) + h_x. out_dir : str Directory in which to store the output files. inj_file : workflow.File (optional, default=None) If given send this injection file to the job so that injections are made into the data. exclude : list (optional, default=None) If given, then when considering which subsections in the ini file to parse for options to add to single_template_plot, only use subsections that *do not* match strings in this list. require : list (optional, default=None) If given, then when considering which subsections in the ini file to parse for options to add to single_template_plot, only use subsections matching strings in this list. tags : list (optional, default=None) Add this list of tags to all jobs. params_str : str (optional, default=None) If given add this string to plot title and caption to describe the template that was used. use_exact_inj_params : boolean (optional, default=False) If True do not use masses and spins listed in the params dictionary but instead use the injection closest to the filter time as a template. Returns -------- output_files : workflow.FileList The list of workflow.Files created in this function. """ tags = [] if tags is None else tags makedir(out_dir) name = 'single_template_plot' secs = requirestr(workflow.cp.get_subsections(name), require) secs = excludestr(secs, exclude) files = FileList([]) for tag in secs: for ifo in workflow.ifos: if params['%s_end_time' % ifo] == -1.0: continue # Reanalyze the time around the trigger in each detector node = SingleTemplateExecutable(workflow.cp, 'single_template', ifos=[ifo], out_dir=out_dir, tags=[tag] + tags).create_node() if use_exact_inj_params: node.add_opt('--use-params-of-closest-injection') else: node.add_opt('--mass1', "%.6f" % params['mass1']) node.add_opt('--mass2', "%.6f" % params['mass2']) node.add_opt('--spin1z',"%.6f" % params['spin1z']) node.add_opt('--spin2z',"%.6f" % params['spin2z']) node.add_opt('--template-start-frequency', "%.6f" % params['f_lower']) # Is this precessing? if 'u_vals' in params or 'u_vals_%s' % ifo in params: node.add_opt('--spin1x',"%.6f" % params['spin1x']) node.add_opt('--spin1y',"%.6f" % params['spin1y']) node.add_opt('--spin2x',"%.6f" % params['spin2x']) node.add_opt('--spin2y',"%.6f" % params['spin2y']) node.add_opt('--inclination',"%.6f" % params['inclination']) try: node.add_opt('--u-val',"%.6f" % params['u_vals']) except: node.add_opt('--u-val', "%.6f" % params['u_vals_%s' % ifo]) # str(numpy.float64) restricts to 2d.p. BE CAREFUL WITH THIS!!! str_trig_time = '%.6f' %(params[ifo + '_end_time']) node.add_opt('--trigger-time', str_trig_time) node.add_input_opt('--inspiral-segments', segs) if inj_file is not None: node.add_input_opt('--injection-file', inj_file) node.add_opt('--data-read-name', data_read_name) node.add_opt('--data-analyzed-name', analyzed_name) node.new_output_file_opt(workflow.analysis_time, '.hdf', '--output-file', store_file=False) data = node.output_files[0] workflow += node # Make the plot for this trigger and detector node = PlotExecutable(workflow.cp, name, ifos=[ifo], out_dir=out_dir, tags=[tag] + tags).create_node() node.add_input_opt('--single-template-file', data) node.new_output_file_opt(workflow.analysis_time, '.png', '--output-file') title="'%s SNR and chi^2 timeseries" %(ifo) if params_str is not None: title+= " using %s" %(params_str) title+="'" node.add_opt('--plot-title', title) caption = "'The SNR and chi^2 timeseries around the injection" if params_str is not None: caption += " using %s" %(params_str) if use_exact_inj_params: caption += ". The injection itself was used as the template.'" else: caption += ". The template used has the following parameters: " caption += "mass1=%s, mass2=%s, spin1z=%s, spin2z=%s'"\ %(params['mass1'], params['mass2'], params['spin1z'], params['spin2z']) node.add_opt('--plot-caption', caption) workflow += node files += node.output_files return files
def setup_psd_pregenerated(workflow, tags=None): ''' Setup CBC workflow to use pregenerated psd files. The file given in cp.get('workflow','pregenerated-psd-file-(ifo)') will be used as the --psd-file argument to geom_nonspinbank, geom_aligned_bank and pycbc_plot_psd_file. Parameters ---------- workflow: pycbc.workflow.core.Workflow An instanced class that manages the constructed workflow. tags : list of strings If given these tags are used to uniquely name and identify output files that would be produced in multiple calls to this function. Returns -------- psd_files : pycbc.workflow.core.FileList The FileList holding the gating files ''' if tags is None: tags = [] psd_files = FileList([]) cp = workflow.cp global_seg = workflow.analysis_time user_tag = "PREGEN_PSD" # Check for one psd for all ifos try: pre_gen_file = cp.get_opt_tags('workflow-psd', 'psd-pregenerated-file', tags) pre_gen_file = resolve_url(pre_gen_file) file_url = urlparse.urljoin('file:', urllib.pathname2url(pre_gen_file)) curr_file = File(workflow.ifos, user_tag, global_seg, file_url, tags=tags) curr_file.PFN(file_url, site='local') psd_files.append(curr_file) except ConfigParser.Error: # Check for one psd per ifo for ifo in workflow.ifos: try: pre_gen_file = cp.get_opt_tags('workflow-psd', 'psd-pregenerated-file-%s' % ifo.lower(), tags) pre_gen_file = resolve_url(pre_gen_file) file_url = urlparse.urljoin('file:', urllib.pathname2url(pre_gen_file)) curr_file = File(ifo, user_tag, global_seg, file_url, tags=tags) curr_file.PFN(file_url, site='local') psd_files.append(curr_file) except ConfigParser.Error: # It's unlikely, but not impossible, that only some ifos # will have pregenerated PSDs logging.warn("No psd file specified for IFO %s." % (ifo,)) pass return psd_files