Update of the xsections and of the 2022preEE campaign for 2025_v1 samples

cmsdb/campaigns/run3_2022_postEE_nano_tau_skim_2025_v1/__init__.py

@@ -25,4 +25,4 @@
 import cmsdb.campaigns.run3_2022_postEE_nano_tau_skim_2025_v1.bkgs
 import cmsdb.campaigns.run3_2022_postEE_nano_tau_skim_2025_v1.data
 import cmsdb.campaigns.run3_2022_postEE_nano_tau_skim_2025_v1.signal
-
+import cmsdb.campaigns.run3_2022_postEE_nano_tau_skim_2025_v1.cp_signal

cmsdb/campaigns/run3_2022_postEE_nano_tau_skim_2025_v1/cp_signal.py

@@ -0,0 +1,99 @@
+# coding: utf-8
+
+"""
+signals for CP analysis from the 2022 post-EE campaign
+"""
+
+import cmsdb.processes as procs
+from cmsdb.campaigns.run3_2022_postEE_nano_tau_skim_2025_v1 import campaign_run3_2022_postEE_nano_tau_skim_2025_v1 as cpn  # TODO: adjust if needed
+
+import re
+from collections import OrderedDict
+
+def _base_name(name: str) -> str:
+  m = re.match(r'^(.*)_ext\d+$', name)
+  return m.group(1) if m else name
+
+def _ext_number(s: str) -> int:
+  m = re.search(r'_ext(\d+)$', s)
+  return int(m.group(1)) if m else 0
+
+def _key_sort_key(key: str):
+  n = _ext_number(key)
+  # base (no ext) first, then _ext1, _ext2, ...
+  return (0, 0) if n == 0 else (1, n)
+
+def add_merged_datasets(dataset_rows, cpn, procs):
+  """
+  dataset_rows: iterable of (name, key_or_keys, n_evt, n_files, pid, proc)
+  Groups *_extX with their base sample, then calls cpn.add_dataset once per base.
+  """
+  groups = {}  # base_name -> accumulator
+  for name, key, n_evt, n_files, pid, proc in dataset_rows:
+    base = _base_name(name)
+    g = groups.get(base)
+    if g is None:
+      g = {
+        "name": base,
+        "proc": proc,
+        "id": None,            # prefer non-ext id; fallback to first seen
+        "keys": OrderedDict(), # preserve insertion order, avoid dups
+        "n_events": 0,
+        "n_files": 0,
+      }
+      groups[base] = g
+
+    if g["proc"] != proc:
+      raise ValueError(f"Process mismatch for {base}: {g['proc']} vs {proc}")
+
+    if not re.search(r'_ext\d+$', name):
+      g["id"] = pid
+    elif g["id"] is None:
+      g["id"] = pid
+
+    # --- FIX: accept string OR list of strings for 'key' ---
+    keys_in = key if isinstance(key, (list, tuple)) else [key]
+    for k in keys_in:
+      if not isinstance(k, str):
+        raise TypeError(f"key must be a string, got {type(k).__name__}: {k}")
+      g["keys"][k] = True
+
+    g["n_events"] += int(n_evt)
+    g["n_files"]  += int(n_files)
+
+  # emit one add per base sample with sorted keys (base first, then ext1, ext2, ...)
+  for base, g in groups.items():
+    keys = list(g["keys"].keys())
+    keys.sort(key=_key_sort_key)
+    cpn.add_dataset(
+      name=g["name"],
+      id=g["id"],
+      is_data=False,
+      processes=[getattr(procs, g["proc"])],
+      keys=keys,
+      n_files=g["n_files"],
+      n_events=g["n_events"],
+    )
+
+# ---- your datasets (name, key, n_evt, n_files, pid, proc) ----
+
+dataset_rows = [
+    #ggH SM production
+    ("h_ggf_htt_sm_prod_sm_filtered",  ["/GluGluHto2Tau_UncorrelatedDecay_SM_Filtered_ProdAndDecay"],    19599725,  49,  22100000, "h_ggf_htt_sm_prod_sm"),
+    ("h_ggf_htt_sm_prod_cpo_filtered", ["/GluGluHto2Tau_UncorrelatedDecay_CPodd_Filtered_ProdAndDecay"], 21495773,  54,  22100010, "h_ggf_htt_sm_prod_cpo"),
+    ("h_ggf_htt_sm_prod_mm_filtered",  ["/GluGluHto2Tau_UncorrelatedDecay_MM_Filtered_ProdAndDecay"],    20689379,  52,  22100020, "h_ggf_htt_sm_prod_mm"),
+    ("h_vbf_htt_sm_filtered",          ["/VBFHto2Tau_UncorrelatedDecay_Filtered"],                       14552639,  35,  22100030, "h_vbf_htt_sm"),
+    ("zh_htt_sm_filtered",             ["/ZHto2Tau_UncorrelatedDecay_Filtered"],                         1863291,   6,   22100040, "zh_htt_sm"),
+    ("wph_htt_sm_filtered",            ["/WplusHto2Tau_UncorrelatedDecay_Filtered"],                     2025321,   6,   22100050, "wph_htt_sm"),
+    ("wmh_htt_sm_filtered",            ["/WminusHto2Tau_UncorrelatedDecay_Filtered"],                    1480135,   4,   22100060, "wmh_htt_sm"),
+]
+
+dataset_rows_cp = []
+for name, key, n_evt, n_files, pid, proc in dataset_rows:
+    dataset_rows_cp.append((name, key, n_evt, n_files, pid, proc))
+    for idx, the_cp_var in enumerate(['htt_mm','htt_cpo','htt_flat']):
+        cp_name = name.replace('htt_sm', the_cp_var)
+        cp_proc = proc.replace('htt_sm', the_cp_var)
+        cp_pid=pid+idx+1
+        dataset_rows_cp.append((cp_name, key, n_evt, n_files, cp_pid, cp_proc))
+add_merged_datasets(dataset_rows_cp, cpn, procs)

cmsdb/campaigns/run3_2022_postEE_v2_nano_tau_v14/__init__.py

@@ -14,6 +14,7 @@
         "year": 2022,
         "version": 14,
         "tag": "postEE",
+        "postfix" : "EE",
         "custom": {
             "name": "run3_2022_postEE_v2_nano_tau_v14",
             "creator": "desy",

cmsdb/campaigns/run3_2022_postEE_v2_nano_tau_v14/ewk.py

@@ -18,7 +18,7 @@
         name="dy_lep_madgraph",
         id=220154049,
 #        is_mc=True,
-        processes=[procs.dy_lep], #,procs.dy_z2ee,procs.dy_z2mumu,procs.dy_z2tautau],
+        processes=[procs.dy_lep],
         keys=["/DYto2L_M_50_madgraphMLM","/DYto2L_M_50_madgraphMLM_ext1",],
         n_files=464,
         n_events=494841164,

cmsdb/campaigns/run3_2022_preEE_nano_tau_skim_2025_v1/__init__.py

@@ -25,4 +25,5 @@
 import cmsdb.campaigns.run3_2022_preEE_nano_tau_skim_2025_v1.data
 import cmsdb.campaigns.run3_2022_preEE_nano_tau_skim_2025_v1.bkgs
 import cmsdb.campaigns.run3_2022_preEE_nano_tau_skim_2025_v1.signal
+import cmsdb.campaigns.run3_2022_preEE_nano_tau_skim_2025_v1.cp_signal