Merge pull request #17 from etive-io/fix-interest-dict

Temporarily remove interest code from monitor loop

Author: transientlunatic

.github/workflows/htcondor-tests.yml

@@ -50,7 +50,7 @@ jobs:
         with:
           miniconda-version: "latest"
           auto-activate-base: false
-          python-version: "3.9"
+          python-version: "3.10"
           activate-environment: asimov
           channels: conda-forge
           conda-remove-defaults: "true"
@@ -59,7 +59,7 @@ jobs:
         uses: actions/cache@v4
         with:
           path: /usr/share/miniconda/envs/asimov
-          key: conda-env-asimov-${{ runner.os }}-py39-${{ hashFiles('conda/environment.yaml') }}
+          key: conda-env-asimov-${{ runner.os }}-py310-${{ hashFiles('conda/environment.yaml') }}
           restore-keys: |
             conda-env-asimov-${{ runner.os }}-
 
@@ -68,6 +68,7 @@ jobs:
           conda install -y -n asimov --file conda/environment.yaml
           conda install -y -n asimov conda-build
           pip install .
+          pip install -U bilby bilby_pipe
           # Temporarily use the asimov-gwdata branch
           pip install git+https://git.ligo.org/asimov/pipelines/gwdata.git@update-htcondor
 
@@ -209,16 +210,16 @@ jobs:
           $ASIMOV_CMD asimov manage build
           $ASIMOV_CMD asimov manage submit
           sleep 10
-          sleep 60
 
           condor_q || true
-          echo 'Waiting for PSD files to appear...'
-          TIMEOUT=1200; ELAPSED=0; INTERVAL=30
+          echo 'Waiting for result file to appear...'
+          TIMEOUT=2400; ELAPSED=0; INTERVAL=30
           while [ \$ELAPSED -lt \$TIMEOUT ]; do
             condor_q || true
             RESULT_COUNT=0
-            tail -n 20 working/GW150914_095045/bilby-IMRPhenomXPHM/log_*/*.err || true
-            for f in working/GW150914_095045/bilby-IMRPhenomXPHM/*merge*_result.hdf5; do
+            tail -n 1 working/GW150914_095045/bilby-IMRPhenomXPHM/log_data_analysis/*.out || true
+            ls -lh working/GW150914_095045/bilby-IMRPhenomXPHM/result/ || true
+            for f in working/GW150914_095045/bilby-IMRPhenomXPHM/final_result/*.hdf5; do
               [ -e "\$f" ] && RESULT_COUNT=\$((RESULT_COUNT + 1))
             done
             if [ \$RESULT_COUNT -gt 0 ]; then
@@ -236,4 +237,4 @@ jobs:
             exit 1
           fi
           $ASIMOV_CMD asimov monitor
-          EOF          
+          EOF

asimov/cli/manage.py

@@ -455,84 +455,51 @@ def submit(event, update, dryrun):
                 production.status = "running"
             else:
                 pipe = production.pipeline
-                # check the priority status to see if we need to start 
-                # the analysis
-                to_analyse = True
-                if production.status not in {"ready"}:
-                    to_analyse = False
-                else:
-                    # verify priority method to be used 
-                    priority_method = check_priority_method(production)
-                    if priority_method == "vanilla":
-                        N_ok = 0
-                        for prod in production._needs:
-                            if interest_dict_single_analysis[production.event.name][prod]['done']:
-                                N_ok += 1
-                        if N_ok < len(production._needs):
-                            to_analyse = False
-                    elif priority_method == "is_interesting":
-                        if "minimum" in production.meat["needs settings"].keys():
-                            N_target = int(production.meta["needs settings"]["minimum"])
-                        else:
-                            # all pipelines should indicate the run as interesting
-                            N_target = len(production._needs)
-                        for prod in production._needs:
-                            if interest_dict_single_analysis[production.event.name][prod]['interest status']:
-                                N_ok += 1
-                        if N_ok < N_target:
-                            to_analyse = False
-                    else:
-                        raise ValueError(f"Priority method {priority_method} not recognized")
-                if to_analyse:
-                    try:
-                        pipe.build_dag(dryrun=dryrun)
-                    except PipelineException as e:
-                        logger.error(
-                            "failed to build a DAG file.",
-                        )
-                        logger.exception(e)
-                        click.echo(
-                            click.style("●", fg="red")
-                            + f" Unable to submit {production.name}"
-                        )
-                    except ValueError:
-                        logger.info("Unable to submit an unbuilt production")
+                
+                try:
+                    pipe.build_dag(dryrun=dryrun)
+                except PipelineException as e:
+                    logger.error(
+                        "failed to build a DAG file.",
+                    )
+                    logger.exception(e)
+                    click.echo(
+                        click.style("●", fg="red")
+                        + f" Unable to submit {production.name}"
+                    )
+                except ValueError:
+                    logger.info("Unable to submit an unbuilt production")
+                    click.echo(
+                        click.style("●", fg="red")
+                        + f" Unable to submit {production.name} as it hasn't been built yet."
+                    )
+                    click.echo("Try running `asimov manage build` first.")
+                try:
+                    pipe.submit_dag(dryrun=dryrun)
+                    if not dryrun:
                         click.echo(
-                            click.style("●", fg="red")
-                            + f" Unable to submit {production.name} as it hasn't been built yet."
+                            click.style("●", fg="green")
+                            + f" Submitted {production.event.name}/{production.name}"
                         )
-                        click.echo("Try running `asimov manage build` first.")
-                    try:
-                        pipe.submit_dag(dryrun=dryrun)
-                        if not dryrun:
-                            click.echo(
-                                click.style("●", fg="green")
-                                + f" Submitted {production.event.name}/{production.name}"
-                            )
-                            production.status = "running"
+                        production.status = "running"
 
-                    except PipelineException as e:
-                        production.status = "stuck"
-                        click.echo(
-                            click.style("●", fg="red")
-                            + f" Unable to submit {production.name}"
-                        )
-                        logger.exception(e)
-                        ledger.update_event(event)
-                        logger.error(
-                            f"The pipeline failed to submit the DAG file to the cluster. {e}",
-                        )
-                    if not dryrun:
-                        # Refresh the job list
-                        job_list = condor.CondorJobList()
-                        job_list.refresh()
-                        # Update the ledger
-                        ledger.update_event(event)
-                else:
+                except PipelineException as e:
+                    production.status = "stuck"
                     click.echo(
-                        click.style("●", fg="yellow")
-                        + f"Production {production.name} not ready to submit"
+                        click.style("●", fg="red")
+                        + f" Unable to submit {production.name}"
                     )
+                    logger.exception(e)
+                    ledger.update_event(event)
+                    logger.error(
+                        f"The pipeline failed to submit the DAG file to the cluster. {e}",
+                    )
+                if not dryrun:
+                    # Refresh the job list
+                    job_list = condor.CondorJobList()
+                    job_list.refresh()
+                    # Update the ledger
+                    ledger.update_event(event)
 
 @click.option(
     "--event",

tests/test_blueprints/gwosc_quick_test.yaml

@@ -18,12 +18,13 @@ pipelines:
         V1: V1:DQ_ANALYSIS_STATE_VECTOR
     sampler:
       sampler: dynesty
-      parallel jobs: 2
-      sampler kwargs: "{nlive: 100, dlogz: 1, nact: 5}"
+      parallel jobs: 1
+      sampler kwargs: "{nlive: 50, dlogz: 1, naccept: 5, check_point_delta_t: 1800, 'print_method': 'interval-10', 'sample': 'acceptance-walk'}"
     scheduler:
       accounting group: ligo.dev.o4.cbc.pe.bilby
       request cpus: 4
       request memory: 2.0
+    cosmology: Planck15_lal
   bayeswave:
     quality:
       state vector: