fix: add debug stuff

.gitlab-ci.yml

@@ -0,0 +1,29 @@
+
+# This file is a template, and might need editing before it works on your project.
+# This is a sample GitLab CI/CD configuration file that should run without any modifications.
+# It demonstrates a basic 3 stage CI/CD pipeline. Instead of real tests or scripts,
+# it uses echo commands to simulate the pipeline execution.
+#
+# A pipeline is composed of independent jobs that run scripts, grouped into stages.
+# Stages run in sequential order, but jobs within stages run in parallel.
+#
+# For more information, see: https://docs.gitlab.com/ee/ci/yaml/index.html#stages
+#
+# You can copy and paste this template into a new `.gitlab-ci.yml` file.
+# You should not add this template to an existing `.gitlab-ci.yml` file by using the `include:` keyword.
+#
+# To contribute improvements to CI/CD templates, please follow the Development guide at:
+# https://docs.gitlab.com/ee/development/cicd/templates.html
+# This specific template is located at:
+# https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/ci/templates/Getting-Started.gitlab-ci.yml
+
+stages:          # List of stages for jobs, and their order of execution
+  - deploy
+
+deploy-job:      # This job runs in the deploy stage.
+  stage: deploy  # It only runs when *both* jobs in the test stage complete successfully.
+  script:
+    - 'curl --fail --request POST --form token=$MY_TRIGGER_TOKEN --form ref=master "https://gitlab.cern.ch/cms-analysis/btv/software-and-algorithms/autobtv/trigger/pipeline"'
+  rules:
+    - if: $CI_COMMIT_TAG
+  environment: production

scripts/fetch.py

@@ -197,7 +197,7 @@ def getFilesFromDas(args):
             .read()
             .split("\n")
         )
-
+        print("Number of files: ", len(flist))
         import json
 
         dataset = dataset[:-1] if "\n" in dataset else dataset

scripts/suball.py

@@ -103,8 +103,6 @@ def get_lumi_from_web(year):
             # "QCD_mu_sf"
         ],
     }
-    if args.debug:
-        args.local = True
     if args.scheme in workflows.keys():
         workflow_group["test"] = [args.scheme]
         args.scheme = "test"
@@ -127,7 +125,7 @@ def get_lumi_from_web(year):
 
     for wf in workflow_group[args.scheme]:
         if args.debug:
-            print(f"Start running {wf} workflow!!!")
+            print(f"======{wf} in {args.scheme}=====")
         overwrite = "--overwrite" if args.overwrite else ""
         ## creating dataset
         if (
@@ -136,13 +134,24 @@ def get_lumi_from_web(year):
             )
             or args.overwrite
         ):
+            if args.debug:
+                print(
+                    f"Creating MC dataset: python scripts/fetch.py -c {args.campaign} --from_workflow {wf} --DAS_campaign {args.DAS_campaign} --year {args.year} {overwrite} --skipvalidation"
+                )
             os.system(
                 f"python scripts/fetch.py -c {args.campaign} --from_workflow {wf} --DAS_campaign {args.DAS_campaign} --year {args.year} {overwrite} --skipvalidation"
             )
+            if args.debug:
+                os.system(f"ls metadata/{args.campaign}/*.json are generated")
+
         ## Run the workflows
         for types in predefined_sample[wf].keys():
+
             if (types != "data" or types != "MC") and args.scheme == "Validation":
                 continue
+            print(
+                f"hists_{wf}_{types}_{args.campaign}_{args.year}_{wf}/hists_{wf}_{types}_{args.campaign}_{args.year}_{wf}.coffea"
+            )
             if (
                 not os.path.exists(
                     f"hists_{wf}_{types}_{args.campaign}_{args.year}_{wf}/hists_{wf}_{types}_{args.campaign}_{args.year}_{wf}.coffea"
@@ -181,31 +190,36 @@ def get_lumi_from_web(year):
                             and "limit" not in key
                         ):
                             runner_config += " --limit 50"
-                        elif args.debug:
-                            runner_config += " --limit 1 --executor iterative"
+
                         else:
                             runner_config += f" --{key}={value}"
                 runner_config = runner_config_required + runner_config
-                print(runner_config)
+                if args.debug:
+                    print(f"run the workflow: {runner_config}")
                 with open(
                     f"config_{args.year}_{args.campaign}_{args.scheme}_{args.version}.txt",
                     "w",
                 ) as config_list:
                     config_list.write(runner_config)
 
                 os.system(runner_config)
-
+        if args.debug:
+            print(f"workflow is finished for {wf}!")
         # Get luminosity
         if (
             os.path.exists(
                 f"hists_{wf}_data_{args.campaign}_{args.year}_{wf}/hists_{wf}_data_{args.campaign}_{args.year}_{wf}.coffea"
             )
             or args.overwrite
         ):
+            if args.debug:
+                print(
+                    f"Get the luminosity from hists_{wf}_data_{args.campaign}_{args.year}_{wf}/hists_{wf}_data_{args.campaign}_{args.year}_{wf}.coffea"
+                )
             lumi = os.popen(
                 f"python scripts/dump_processed.py -t all -c hists_{wf}_data_{args.campaign}_{args.year}_{wf}/hists_{wf}_data_{args.campaign}_{args.year}_{wf}.coffea --json metadata/{args.campaign}/data_{args.campaign}_{args.year}_{wf}.json -n {args.campaign}_{args.year}_{wf}"
             ).read()
-
+            print(lumi)
             lumi = int(
                 round(
                     float(
@@ -220,14 +234,20 @@ def get_lumi_from_web(year):
             )
             if os.path.exists(
                 f"hists_{wf}_MC_{args.campaign}_{args.year}_{wf}/hists_{wf}_MC_{args.campaign}_{args.year}_{wf}.coffea"
+            ) and os.path.exists(
+                f"hists_{wf}_data_{args.campaign}_{args.year}_{wf}/hists_{wf}_data_{args.campaign}_{args.year}_{wf}.coffea"
             ):
                 print(lumi)
+                if args.debug:
+                    print(f"Plot the dataMC for {wf}")
                 os.system(
                     f'python scripts/plotdataMC.py -i "hists_{wf}_*_{args.campaign}_{args.year}_{wf}/hists_{wf}_*_{args.campaign}_{args.year}_{wf}.coffea" --lumi {lumi} -p {wf} -v all --ext {args.campaign}_{args.year}{args.version}'
                 )
                 ## Inspired from Uttiya, create remote directory
                 # https://github.com/cms-btv-pog/BTVNanoCommissioning/blob/14e654feeb4b4d738ee43ab913efb343ea65fd1d/scripts/submit/createremotedir.sh
                 # create remote direcotry
+                if args.debug:
+                    print(f"Upload plots&coffea to eos: {wf}")
                 if not args.local:
                     os.system(f"mkdir -p {args.campaign}{args.version}/{wf}")
                     os.system(f"cp scripts/index.php {args.campaign}{args.version}/.")

src/BTVNanoCommissioning/helpers/update_branch.py

@@ -86,7 +86,9 @@ def missing_branch(events):
             events.Jet,
             {"btagPNetCvNotB": jets.btagPNetCvNotB},
         )
-    if not hasattr(events.Jet, "btagRobustParTAK4CvNotB"):
+    if not hasattr(events.Jet, "btagRobustParTAK4CvNotB") and hasattr(
+        events.Jet, "btagRobustParTAK4B"
+    ):
         jets = events.Jet
         jets["btagRobustParTAK4CvNotB"] = (
             jets.btagRobustParTAK4CvB