merge master branch into v12_2016_post

.github/workflows/lint_and_test.yaml

@@ -56,6 +56,7 @@ jobs:
           python -c "from cmsdb.campaigns.run2_2017_nano_uhh_v11 import *"
           python -c "from cmsdb.campaigns.run2_2018_nano_uhh_v11 import *"
           python -c "from cmsdb.campaigns.run2_2016_nano_uhh_v12 import *"
+          python -c "from cmsdb.campaigns.run2_2017_JMEnano_v9 import *"
           python -c "from cmsdb.campaigns.run2_2018_JMEnano_v9 import *"
           python -c "from cmsdb.campaigns.run3_2022_preEE_nano_v11 import *"
           python -c "from cmsdb.campaigns.run3_2022_postEE_nano_v11 import *"

cmsdb/campaigns/run2_2017_JMEnano_v9/__init__.py

@@ -0,0 +1,32 @@
+# coding: utf-8
+
+"""
+Common, analysis independent definition of the 2017 data-taking campaign
+with datasets at NanoAOD tier in version 9.
+See https://python-order.readthedocs.io/en/latest/quickstart.html#analysis-campaign-and-config.
+
+Dataset ids are identical to those in DAS (https://cmsweb.cern.ch/das).
+"""
+
+from order import Campaign
+
+
+#
+# campaign
+#
+
+campaign_run2_2017_JMEnano_v9 = Campaign(
+    name="run2_2017_JMEnano_v9",
+    id=220201,
+    ecm=13,
+    bx=25,
+    aux={
+        "year": 2017,
+        "tier": "NanoAOD",
+        "version": "9",
+    },
+)
+
+# trailing imports to load datasets
+import cmsdb.campaigns.run2_2017_JMEnano_v9.data  # noqa
+import cmsdb.campaigns.run2_2017_JMEnano_v9.qcd  # noqa

cmsdb/campaigns/run2_2017_JMEnano_v9/data.py

@@ -0,0 +1,88 @@
+# coding: utf-8
+
+"""
+CMS datasets from the 2017 data-taking campaign
+"""
+
+import cmsdb.processes as procs
+from cmsdb.campaigns.run2_2017_JMEnano_v9 import campaign_run2_2017_JMEnano_v9 as cpn
+
+
+#
+# DiJet
+#
+
+cpn.add_dataset(
+    name="data_jetht_b",
+    id=14260759,  # from das
+    is_data=True,
+    processes=[procs.data_jetht],
+    keys=[
+        "/JetHT/Run2017B-UL2017_MiniAODv2_JMENanoAODv9-v1/NANOAOD",
+    ],
+    n_files=96,
+    n_events=63043590,
+    aux={
+        "era": "B",
+    },
+)
+
+cpn.add_dataset(
+    name="data_jetht_c",
+    id=14260769,
+    is_data=True,
+    processes=[procs.data_jetht],
+    keys=[
+        "/JetHT/Run2017C-UL2017_MiniAODv2_JMENanoAODv9-v1/NANOAOD",
+    ],
+    n_files=158,
+    n_events=96264601,
+    aux={
+        "era": "C",
+    },
+)
+
+cpn.add_dataset(
+    name="data_jetht_d",
+    id=14260518,
+    is_data=True,
+    processes=[procs.data_jetht],
+    keys=[
+        "/JetHT/Run2017D-UL2017_MiniAODv2_JMENanoAODv9-v1/NANOAOD",
+    ],
+    n_files=89,
+    n_events=46145204,
+    aux={
+        "era": "D",
+    },
+)
+
+cpn.add_dataset(
+    name="data_jetht_e",
+    id=14260363,
+    is_data=True,
+    processes=[procs.data_jetht],
+    keys=[
+        "/JetHT/Run2017E-UL2017_MiniAODv2_JMENanoAODv9-v1/NANOAOD",
+    ],
+    n_files=148,
+    n_events=89630771,
+    aux={
+        "era": "E",
+    },
+)
+
+cpn.add_dataset(
+    name="data_jetht_f",
+    id=14260621,
+    is_data=True,
+    processes=[procs.data_jetht],
+    keys=[
+        "/JetHT/Run2017F-UL2017_MiniAODv2_JMENanoAODv9-v1/NANOAOD",
+    ],
+    n_files=228,
+    n_events=115429972,
+    aux={
+        "era": "F",
+    },
+)

cmsdb/campaigns/run2_2017_JMEnano_v9/qcd.py

@@ -0,0 +1,117 @@
+# coding: utf-8
+
+"""
+QCD datasets for the 2017 data-taking campaign
+"""
+
+import cmsdb.processes as procs
+from cmsdb.campaigns.run2_2017_JMEnano_v9 import campaign_run2_2017_JMEnano_v9 as cpn
+
+
+#
+# QCD HT-binned
+#
+
+# HT-binned samples
+
+generator = "TuneCP5_PSWeights_13TeV-madgraph-pythia8"
+cmssw = "106X_mc2017_realistic_v9-v1"
+
+cpn.add_dataset(
+    name="qcd_ht50to100_madgraph",
+    id=14281497,
+    processes=[procs.qcd_ht50to100],
+    keys=[
+        f"/QCD_HT50to100_{generator}/RunIISummer20UL17NanoAODv9-20UL17JMENano_{cmssw}/NANOAODSIM",
+    ],
+    n_files=52,
+    n_events=26129826,
+)
+
+cpn.add_dataset(
+    name="qcd_ht100to200_madgraph",
+    id=14300506,
+    processes=[procs.qcd_ht100to200],
+    keys=[
+        f"/QCD_HT100to200_{generator}/RunIISummer20UL17NanoAODv9-20UL17JMENano_{cmssw}/NANOAODSIM",
+    ],
+    n_files=99,
+    n_events=54705747,
+)
+
+cpn.add_dataset(
+    name="qcd_ht200to300_madgraph",
+    id=14289012,
+    processes=[procs.qcd_ht200to300],
+    keys=[
+        f"/QCD_HT200to300_{generator}/RunIISummer20UL17NanoAODv9-20UL17JMENano_{cmssw}/NANOAODSIM",
+    ],
+    n_files=85,
+    n_events=42679193,
+)
+
+cpn.add_dataset(
+    name="qcd_ht300to500_madgraph",
+    id=14288347,
+    processes=[procs.qcd_ht300to500],
+    keys=[
+        f"/QCD_HT300to500_{generator}/RunIISummer20UL17NanoAODv9-20UL17JMENano_{cmssw}/NANOAODSIM",
+    ],
+    n_files=94,
+    n_events=43589739,
+)
+
+cpn.add_dataset(
+    name="qcd_ht500to700_madgraph",
+    id=14279003,
+    processes=[procs.qcd_ht500to700],
+    keys=[
+        f"/QCD_HT500to700_{generator}/RunIISummer20UL17NanoAODv9-20UL17JMENano_{cmssw}/NANOAODSIM",
+    ],
+    n_files=85,
+    n_events=36082941,
+)
+
+cpn.add_dataset(
+    name="qcd_ht700to1000_madgraph",
+    id=14281356,
+    processes=[procs.qcd_ht700to1000],
+    keys=[
+        f"/QCD_HT700to1000_{generator}/RunIISummer20UL17NanoAODv9-20UL17JMENano_{cmssw}/NANOAODSIM",
+    ],
+    n_files=84,
+    n_events=32788396,
+)
+
+cpn.add_dataset(
+    name="qcd_ht1000to1500_madgraph",
+    id=14296775,
+    processes=[procs.qcd_ht1000to1500],
+    keys=[
+        f"/QCD_HT1000to1500_{generator}/RunIISummer20UL17NanoAODv9-20UL17JMENano_{cmssw}/NANOAODSIM",
+    ],
+    n_files=65,
+    n_events=10256089,
+)
+
+cpn.add_dataset(
+    name="qcd_ht1500to2000_madgraph",
+    id=14270490,
+    processes=[procs.qcd_ht1500to2000],
+    keys=[
+        f"/QCD_HT1500to2000_{generator}/RunIISummer20UL17NanoAODv9-20UL17JMENano_{cmssw}/NANOAODSIM",
+    ],
+    n_files=43,
+    n_events=7540039,
+)
+
+cpn.add_dataset(
+    name="qcd_ht2000_madgraph",
+    id=14296752,
+    processes=[procs.qcd_ht2000],
+    keys=[
+        f"/QCD_HT2000toInf_{generator}/RunIISummer20UL17NanoAODv9-20UL17JMENano_{cmssw}/NANOAODSIM",
+    ],
+    n_files=38,
+    n_events=4055223,
+)

cmsdb/campaigns/run2_2018_JMEnano_v9/__init__.py

@@ -17,7 +17,7 @@
 
 campaign_run2_2018_JMEnano_v9 = Campaign(
     name="run2_2018_JMEnano_v9",
-    id=220181,
+    id=220191,
     ecm=13,
     bx=25,
     aux={

cmsdb/campaigns/run2_2018_JMEnano_v9/qcd.py

@@ -1,7 +1,7 @@
 # coding: utf-8
 
 """
-QCD datasets for the 2017 data-taking campaign
+QCD datasets for the 2018 data-taking campaign
 """
 
 import cmsdb.processes as procs

cmsdb/processes/hh2bbtautau.py

@@ -481,7 +481,7 @@
 )
 
 graviton_hh_ggf_bbtautau_m3000 = graviton_hh_ggf_bbtautau.add_process(
-    name="hh_ggf_graviton_bbtautau_m3000",
+    name="graviton_hh_ggf_bbtautau_m3000",
     id=24125,
     xsecs={13: Number(0.1)},  # TODO
 )

cmsdb/processes/hh2bbww.py

@@ -632,7 +632,7 @@
 )
 
 graviton_hh_ggf_bbww_m3000 = graviton_hh_ggf_bbww.add_process(
-    name="hh_ggf_graviton_bbww_m3000",
+    name="graviton_hh_ggf_bbww_m3000",
     id=24225,
     xsecs={13: Number(0.1)},  # TODO
 )

requirements.txt

@@ -1,2 +1,2 @@
-scinum>=1.4.6
+scinum~=2.0.2
 order>=2.1.4

scripts/get_das_info.py

@@ -12,6 +12,19 @@
 import law
 
 
+def convert_to_desired_structure(data: dict) -> str:
+    return f"""cpn.add_dataset(
+    name="PLACEHOLDER",
+    id={data['dataset_id']}
+    processes=[procs.PLACEHOLDER],
+    keys=[
+        {data['name']},  # noqa
+    ],
+    n_files={data['nfiles']},
+    n_events={data['nevents']},
+)"""
+
+
 def print_das_info(das_strings: list[str], keys_of_interest: tuple | None = None):
     for das_string in das_strings:
         # set default keys of interest
@@ -38,7 +51,6 @@ def print_das_info(das_strings: list[str], keys_of_interest: tuple | None = None
             infos = json.loads(out)
             for info in infos:
                 dataset_name = info.get("dataset", [])[0].get("name", "")
-                # print(dataset_name) # keep for debugging purpose
                 datasets.append(dataset_name)
 
         for dataset in datasets:
@@ -63,7 +75,10 @@ def print_das_info(das_strings: list[str], keys_of_interest: tuple | None = None
                 elif "filesummaries" in info["das"]["services"][0]:
                     info_of_interest["nfiles"] = dataset_info.get("nfiles", "")
                     info_of_interest["nevents"] = dataset_info.get("nevents", "")
-            print(json.dumps(info_of_interest, indent=4))
+
+            desired_output = convert_to_desired_structure(info_of_interest)
+            print(desired_output)
+            print()
 
 
 if __name__ == "__main__":