Updated on Fake Factor method

columnflow/calibration/cms/met.py

@@ -13,9 +13,8 @@
 
 
 @calibrator(
-    uses={"run", "PV.npvs"},
-    # name of the MET collection to calibrate
-    met_name="MET",
+    uses={"run", "PV.npvs", "PuppiMET.pt", "PuppiMET.phi"},
+    produces={"PuppiMET.pt", "PuppiMET.phi"},
 
     # function to determine the correction file
     get_met_file=(lambda self, external_files: external_files.met_phi_corr),
@@ -55,17 +54,17 @@ def met_phi(self: Calibrator, events: ak.Array, **kwargs) -> ak.Array:
     met = events[self.met_name]
 
     # copy the intial pt and phi values
+    corr_pt = np.array(events.PuppiMET.pt, dtype=np.float32)
+    corr_phi = np.array(events.PuppiMET.phi, dtype=np.float32)
 
-    corr_pt = np.array(met.pt, dtype=np.float32)
-    corr_phi = np.array(met.phi, dtype=np.float32)
 
-    # select only events where MET pt is below the expected beam energy
-    mask = met.pt < (0.5 * self.config_inst.campaign.ecm)
+    # select only events where PuppiMET pt is below the expected beam energy
+    mask = events.PuppiMET.pt < (0.5 * self.config_inst.campaign.ecm)
 
     # arguments for evaluation
     args = (
-        met.pt[mask],
-        met.phi[mask],
+        events.PuppiMET.pt[mask],
+        events.PuppiMET.phi[mask],
         ak.values_astype(events.PV.npvs[mask], np.float32),
         ak.values_astype(events.run[mask], np.float32),
     )
@@ -75,8 +74,8 @@ def met_phi(self: Calibrator, events: ak.Array, **kwargs) -> ak.Array:
     corr_phi[mask] = self.met_phi_corrector.evaluate(*args)
 
     # save the corrected values
-    events = set_ak_column(events, f"{self.met_name}.pt", corr_pt, value_type=np.float32)
-    events = set_ak_column(events, f"{self.met_name}.phi", corr_phi, value_type=np.float32)
+    events = set_ak_column(events, "PuppiMET.pt", corr_pt, value_type=np.float32)
+    events = set_ak_column(events, "PuppiMET.phi", corr_phi, value_type=np.float32)
 
 
     return events

columnflow/columnar_util.py

@@ -14,6 +14,7 @@
 import math
 import time
 import enum
+
 import inspect
 import threading
 import multiprocessing
@@ -40,6 +41,7 @@
 maybe_import("coffea.nanoevents.methods.base")
 maybe_import("coffea.nanoevents.methods.nanoaod")
 pq = maybe_import("pyarrow.parquet")
+hist = maybe_import("hist")
 
 
 # loggers
@@ -1405,18 +1407,15 @@ def allows_shift(ax) -> bool:
             data[ax.name] = ak.copy(data[ax.name])
             flat_np_view(data[ax.name])[right_egde_mask] -= ax.widths[-1] * 1e-5
 
-    print("CreateHistograms /afs/cern.ch/user/j/jmalvaso/CPinHToTauTau/modules/columnflow/columnflow/columnar_util.py needs to be fixed")
-    print("Comment until else to run plotvariables")
-    #fill
-    # if 'event' in data.keys():
-    #     arrays = {}
-    #     for ax_name in axis_names:
-    #         if ax_name in data.keys():
-    #             arrays[ax_name] = data[ax_name]
-    #     h.fill(**fill_kwargs, **arrays)
-    # else:
-    arrays = ak.flatten(ak.cartesian(data))
-    h.fill(**fill_kwargs, **{field: arrays[field] for field in arrays.fields})
+    if 'event' in data.keys():
+        arrays = {}
+        for ax_name in axis_names:
+            if ax_name in data.keys():
+                arrays[ax_name] = data[ax_name]
+        h.fill(**fill_kwargs, **arrays)
+    else:
+        arrays = ak.flatten(ak.cartesian(data))
+        h.fill(**fill_kwargs, **{field: arrays[field] for field in arrays.fields})
 
 
 

columnflow/hist_util.py

@@ -74,8 +74,12 @@ def allows_shift(ax) -> bool:
             flat_np_view(data[ax.name])[right_egde_mask] -= ax.widths[-1] * 1e-5
 
     # fill
-    arrays = ak.flatten(ak.cartesian(data))
-    h.fill(**fill_kwargs, **{field: arrays[field] for field in arrays.fields})
+    flat_data = {}
+    for key, arr in data.items():
+        if arr.ndim != 1: flat_data[key] = ak.flatten(arr)
+        else: flat_data[key] = arr
+    h.fill(**fill_kwargs, **flat_data)
+
 
 
 def add_hist_axis(histogram: hist.Hist, variable_inst: od.Variable) -> hist.Hist:

columnflow/plotting/plot_all.py

@@ -276,7 +276,8 @@ def plot_all(
         legend_kwargs = {
             "ncol": 2,
             "loc": "center left",
-            "bbox_to_anchor": (0.25, 0.8),  # Position the legend outside the plot
+
+            "bbox_to_anchor": (0.35, 0.8),  # Position the legend outside the plot
                                          # Moves the legend to the right side of the plot.
                                          # The first value (1) controls the horizontal position,
                                          # and the second value (0.95) controls the vertical position.

columnflow/plotting/plot_functions_1d.py

@@ -56,6 +56,7 @@ def plot_variable_per_process(
     and the process with the second highest number of events last.
     Handles cases with only one or two processes.
     """ 
+
     remove_residual_axis(hists, "shift")
     # Define the color maps
     color_maps = {
@@ -94,7 +95,6 @@ def plot_variable_per_process(
         custom_order = sorted_keys 
     # Reorder histograms based on custom order
     sorted_hists = OrderedDict((key, sorted_hists_desc[key]) for key in custom_order)
-
     variable_inst = variable_insts[0]
     sorted_hists = apply_variable_settings(sorted_hists, variable_insts, variable_settings)
     sorted_hists = apply_process_settings(sorted_hists, process_settings)
@@ -276,7 +276,7 @@ def plot_shifted_variable(
     default_style_config = prepare_style_config(
         config_inst, category_inst, variable_inst, density, shape_norm, yscale,
     )
-    default_style_config["rax_cfg"]["ylim"] = (0.25, 1.75)
+    default_style_config["rax_cfg"]["ylim"] = (0.75, 1.25)
     default_style_config["rax_cfg"]["ylabel"] = "Ratio"
     default_style_config["legend_cfg"]["title"] = legend_title
 

columnflow/production/normalization.py

@@ -339,21 +339,20 @@ def normalization_weights_setup(
         )
 
         for process_id, br in branching_ratios.items():
-
             #sum_weights = merged_selection_stats["sum_mc_weight_per_process"][str(process_id)]
             sum_weights = self.dataset_inst.n_events
             process_weight_table[0, process_id] = lumi * inclusive_xsec * br / sum_weights
-
     else:
         # fill the process weight table with per-process cross sections
         for process_inst in process_insts:
             if self.config_inst.campaign.ecm not in process_inst.xsecs.keys():
-
-                continue
+                raise KeyError(
+                    f"no cross section registered for process {process_inst} for center-of-mass "
+                    f"energy of {self.config_inst.campaign.ecm}",
+                )
             #sum_weights = merged_selection_stats["sum_mc_weight_per_process"][str(process_inst.id)]
             #quick fix that need to be fixed
             ################################
-            #n_evt_per_file = /self.dataset_inst.n_files
             sum_weights = self.dataset_inst.n_events
             ################################
             xsec = process_inst.get_xsec(self.config_inst.campaign.ecm).nominal
@@ -402,3 +401,5 @@ def normalization_weights_init(self: Producer) -> None:
         "get_xsecs_from_inclusive_dataset": False,
     },
 )
+
+

columnflow/selection/cms/jets.py

@@ -22,7 +22,7 @@
 
 @selector(
     uses={
-        "Jet.{pt,eta,phi,mass,jetId,chEmEF}", optional("Jet.puId"),
+        "Jet.{pt,eta,phi,mass,jetId,chEmEF}", 
         "Muon.{pt,eta,phi,mass,isPFcand}",
     },
     produces={"Jet.veto_map_mask"},