updates to datasets and defaults

Author: mafrahm

hbw/config/datasets.py

@@ -52,6 +52,9 @@
         "data_e_e",
         "data_e_f",
     ],
+}
+
+data_egamma = {
     "2022preEE": [
         "data_egamma_c",
         "data_egamma_d",
@@ -211,16 +214,16 @@
         "qcd_em_pt300toInf_pythia",
     ],
     "2022postEE": [
-        "qcd_em_pt10to30_pythia",  # missing process + probably empty anyways
-        "qcd_em_pt30to50_pythia",
+        # "qcd_em_pt10to30_pythia",  # missing process + probably empty anyways
+        # "qcd_em_pt30to50_pythia",  # empty after selection
         "qcd_em_pt50to80_pythia",
         "qcd_em_pt80to120_pythia",
         "qcd_em_pt120to170_pythia",
         "qcd_em_pt170to300_pythia",
         "qcd_em_pt300toInf_pythia",
     ],
     "2022preEE": [
-        "qcd_em_pt10to30_pythia",  # missing process + probably empty anyways
+        # "qcd_em_pt10to30_pythia",  # missing process + probably empty anyways
         "qcd_em_pt30to50_pythia",
         "qcd_em_pt50to80_pythia",
         "qcd_em_pt80to120_pythia",
@@ -301,8 +304,11 @@
         "ggHH_kl_2p45_kt_1_dl_hbbhww_powheg",
         "ggHH_kl_5_kt_1_dl_hbbhww_powheg",
     ],
+    "2022preEE": [
+        "ggHH_kl_1_kt_1_dl_hbbhww_powheg",
+    ],
     "2022postEE": [
-        # empty for now
+        "ggHH_kl_1_kt_1_dl_hbbhww_powheg",
     ],
 }
 
@@ -378,6 +384,7 @@ def get_dataset_names(cpn_tag: int | str, as_list: bool = False) -> DotDict[str:
     dataset_names = DotDict.wrap(
         data_mu=data_mu.get(cpn_tag, []),
         data_e=data_e.get(cpn_tag, []),
+        data_egamma=data_egamma.get(cpn_tag, []),
         tt=tt.get(cpn_tag, []),
         st=st.get(cpn_tag, []),
         w_lnu=w_lnu.get(cpn_tag, []),

hbw/config/defaults_and_groups.py

@@ -142,7 +142,7 @@ def set_config_defaults_and_groups(config_inst):
         "signal": ["ggHH_*", "qqHH_*"], "gghh": ["ggHH_*"], "qqhh": ["qqHH_*"],
     }
     config_inst.x.process_groups["dmuch"] = ["data_mu"] + config_inst.x.process_groups["much"]
-    config_inst.x.process_groups["dech"] = ["data_e"] + config_inst.x.process_groups["ech"]
+    config_inst.x.process_groups["dech"] = ["data_e", "data_egamma"] + config_inst.x.process_groups["ech"]
 
     # dataset groups for conveniently looping over certain datasets
     # (used in wrapper_factory and during plotting)
@@ -167,8 +167,8 @@ def set_config_defaults_and_groups(config_inst):
         "sl_ech": ["1e", "1e__resolved", "1e__boosted"],
         "sl_much_resolved": ["1mu__resolved", "1mu__resolved__1b", "1mu__resolved__2b"],
         "sl_ech_resolved": ["1e__resolved", "1e__resolved__1b", "1e__resolved__2b"],
-        "sl_much_boosted": ["1mu__boosted", "1mu_boosted__1b", "1mu_boosted__2b"],
-        "sl_ech_boosted": ["1e__boosted", "1e__boosted__1b", "1e__boosted__2b"],
+        "sl_much_boosted": ["1mu__boosted"],
+        "sl_ech_boosted": ["1e__boosted"],
         "default": ["incl", "1e", "1mu"],
         "test": ["incl", "1e"],
         "dilep": ["incl", "2e", "2mu", "emu"],
@@ -240,7 +240,7 @@ def set_config_defaults_and_groups(config_inst):
         "unstack_signal": {proc.name: {"unstack": True} for proc in config_inst.processes if "HH" in proc.name},
         "scale_signal": {
             proc.name: {"unstack": True, "scale": 10000}
-            for proc in config_inst.processes if "HH" in proc.name
+            for proc, _, _ in config_inst.walk_processes() if proc.has_tag("is_signal")
         },
         "dilep": {
             "ggHH_kl_0_kt_1_dl_hbbhww": {"scale": 10000, "unstack": True},

hbw/tasks/wrapper.py

@@ -34,7 +34,7 @@ def requires(self):
             for j_channel in ("resolved", "boosted"):
                 reqs[f"control_plots_{l_channel}_{j_channel}"] = PlotVariables1D.req(
                     self,
-                    processes=(f"{l_channel}ch",),
+                    processes=(f"d{l_channel}ch",),
                     # processes=("ggHH_kl_1_kt_1_sl_hbbhww",),
                     process_settings=[["scale_signal"]],
                     variables=[f"sl_{j_channel}"],
@@ -150,7 +150,6 @@ def requires(self):
         return reqs
 
     def output(self):
-
         # use the input also as output
         # (makes it easier to fetch and delete outputs)
         return self.requires()