Merging full workflow into Tanay's HiggsDNA

Don't merge this yet! Let's do some testing first before we merge to master

This should work out of the box (fingers crossed). This will have the full h->aa->4gamma workflow included in the base class. This should also not affect any corrections that you are using currently. That still needs to be tested. There may be bugs that I haven't caught yet, so I need to do some testing... I also included some nice helper scripts for you in the scripts folder.

higgs_dna/utils/dumping_utils.py

@@ -17,18 +17,29 @@ def diphoton_list_to_pandas(self, diphotons: awkward.Array) -> pandas.DataFrame:
     The observables related to the diphoton pair are stored with no prefix.
     To change the behavior, you can redefine the `diphoton_list_to_pandas` method in the
     derived class.
+
+    Note: Sergi edited this to be more efficient and to suppress the annoying warnings about fragmented DataFrames.
     """
     output = pandas.DataFrame()
+    results = []
     for field in awkward.fields(diphotons):
         prefix = self.prefixes.get(field, "")
         if len(prefix) > 0:
             for subfield in awkward.fields(diphotons[field]):
                 if subfield != "__systematics__":
-                    output[f"{prefix}_{subfield}"] = awkward.to_numpy(
-                        diphotons[field][subfield]
+                    sub = f"{prefix}_{subfield}"
+                    results.append(
+                        pandas.Series(awkward.to_numpy(diphotons[field][subfield]), name=sub)
                     )
         else:
-            output[field] = awkward.to_numpy(diphotons[field])
+            sub = field
+            if sub in ["pt", "eta", "phi", "mass", "charge"]:
+                sub = f"dipho_{sub}"
+            results.append(
+                pandas.Series(awkward.to_numpy(diphotons[field]), name=sub)
+            )
+
+    output = pandas.concat(results, axis=1)
     return output
 
 
@@ -283,3 +294,57 @@ def get_obj_syst_dict(obj_ak: awkward.Array, var_new: Optional[List[str]] = ["pt
                 obj_tmp[ivariable] = obj_ak[replace_dict[isyst][ivariation][ivariable]]
             obj_syst_dict.update({f"{isyst}_{ivariation}": obj_tmp})
     return syst_list, obj_syst_dict
+
+
+# Convert pseudos array to pandas DataFrame
+def ps_list_to_pandas(pseudos: awkward.Array) -> pandas.DataFrame:
+    results = []
+    for field in awkward.fields(pseudos):
+        if field not in [
+                "mass_gggg",
+                "pT1_ma1",
+                "pT2_ma1",
+                "pT1_ma2",
+                "pT2_ma2",
+                "sumPt_gggg",
+                "dM",
+                "dR_aa",
+                "dR_aa_mass_gggg",
+                "cos_ag",
+                "LeadPs_interMass",
+                "SubleadPs_interMass",
+                "Ps_massDiff",
+                "m_hyp",
+                "genWeight"]:
+            for subfield in awkward.fields(pseudos[field]):
+                try:
+                    if subfield != "__systematics__":
+                        try:
+                            if field == "LeadPs" or field == "SubleadPs" and (subfield == "leading_pho" or subfield == "subleading_pho"):
+                                for subsubfield in awkward.fields(pseudos[field][subfield]):
+                                    if subsubfield != "__systematics__":
+                                        sub = f"{field}_{subfield}_{subsubfield}"
+                                        results.append(
+                                            pandas.Series(awkward.to_numpy(pseudos[field][subfield][subsubfield][:,0]), name=sub)
+                                        )
+
+                            if subfield != "leading_pho" and subfield != "subleading_pho":
+                                sub = f"{field}_{subfield}"
+                                results.append(
+                                    pandas.Series(awkward.to_numpy(pseudos[field][subfield][:,0]), name=sub)
+                                )
+                        except:
+                            print(f"Failed to convert {sub}!")                
+                except:
+                    print(f"Failed to convert {sub}!")
+        else:
+            try:
+                results.append(
+                    pandas.Series(awkward.to_numpy(pseudos[field][:,0]), name=field.replace("/","_"))
+                )
+            except:
+                print(f"Failed to convert {field}!")
+
+    assert len(results) > 0
+    output = pandas.concat(results, axis=1)
+    return output