kt reclustering

rkansal47 · Dec 15, 2024 · 2af62e4 · 2af62e4
1 parent 762c679
commit 2af62e4
Show file tree

Hide file tree

Showing 4 changed files with 93 additions and 1,235 deletions.
diff --git a/src/HHbbVV/postprocessing/TopAnalysis.ipynb b/src/HHbbVV/postprocessing/TopAnalysis.ipynb
diff --git a/src/HHbbVV/processors/corrections.py b/src/HHbbVV/processors/corrections.py
@@ -844,6 +844,7 @@ def _get_lund_arrays(
     fatjet_idx: int | ak.Array,
     num_prongs: int,
     min_pt: float = 1.0,
+    ca_recluster: bool = False,
 ):
     """
     Gets the ``num_prongs`` subjet pTs and Delta and kT per primary LP splitting of fatjets at
@@ -854,6 +855,8 @@ def _get_lund_arrays(
         jec_fatjets (FatJetArray): post-JEC fatjets, used to update subjet pTs.
         fatjet_idx (int | ak.Array): fatjet index
         num_prongs (int): number of prongs / subjets per jet to reweight
+        min_pt (float): minimum pT for pf candidates considered for LP declustering
+        ca_recluster (bool): whether to recluster subjets with CA after kT
 
     Returns:
         lds, kt_subjets_vec, kt_subjets_pt: lund declusterings, subjet 4-vectors, JEC-corrected subjet pTs
@@ -870,6 +873,8 @@ def _get_lund_arrays(
     cadef = fastjet.JetDefinition(fastjet.cambridge_algorithm, dR)
     ktdef = fastjet.JetDefinition(fastjet.kt_algorithm, dR)
 
+    recluster_def = cadef if ca_recluster else ktdef
+
     # get pfcands of the top-matched jets
     ak8_pfcands = events.FatJetPFCands
     ak8_pfcands = ak8_pfcands[ak8_pfcands.jetIdx == fatjet_idx]
@@ -911,8 +916,8 @@ def _get_lund_arrays(
 
     # then re-cluster with CA
     # won't need to flatten once https://github.com/scikit-hep/fastjet/pull/145 is released
-    ca_clustering = fastjet.ClusterSequence(kt_subjet_consts, cadef)
-    lds = ca_clustering.exclusive_jets_lund_declusterings(1)
+    reclustering = fastjet.ClusterSequence(kt_subjet_consts, recluster_def)
+    lds = reclustering.exclusive_jets_lund_declusterings(1)
 
     return lds, kt_subjets_vec, kt_subjets_pt
 

diff --git a/src/HHbbVV/scale_factors/top_reweighting.ipynb b/src/HHbbVV/scale_factors/top_reweighting.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -41,7 +41,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -132,7 +132,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -150,7 +150,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -196,7 +196,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -228,7 +228,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -252,7 +252,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -498,7 +498,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -523,7 +523,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -538,7 +538,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -561,7 +561,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -604,7 +604,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -649,7 +649,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -658,7 +658,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -677,7 +677,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -692,7 +692,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -725,7 +725,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -741,7 +741,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -763,7 +763,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -790,7 +790,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -805,7 +805,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 27,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -836,11 +836,38 @@
     "# then re-cluster with CA\n",
     "# won't need to flatten once https://github.com/scikit-hep/fastjet/pull/145 is released\n",
     "# ca_clustering = fastjet.ClusterSequence(ak.flatten(kt_subjet_consts, axis=1), cadef)\n",
-    "ca_clustering = fastjet.ClusterSequence(filled_consts, cadef)\n",
+    "ca_clustering = fastjet.ClusterSequence(filled_consts, ktdef)\n",
     "lds = ca_clustering.exclusive_jets_lund_declusterings(1)\n",
     "lds_flat = ak.flatten(lds, axis=1)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lds"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "merged_top_events"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "kt_subjet_consts"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -1432,7 +1459,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "python310",
+   "display_name": "python39",
    "language": "python",
    "name": "python3"
   },
@@ -1448,12 +1475,7 @@
    "pygments_lexer": "ipython3",
    "version": "3.9.15"
   },
-  "orig_nbformat": 4,
-  "vscode": {
-   "interpreter": {
-    "hash": "15adc7883e707560d0d9727709639b8fe3f3cff1f197d2d643742923ff23a29c"
-   }
-  }
+  "orig_nbformat": 4
  },
  "nbformat": 4,
  "nbformat_minor": 2

diff --git a/src/condor/submit_configs/ttsfs_24_12_15_lp.yaml b/src/condor/submit_configs/ttsfs_24_12_15_lp.yaml
@@ -0,0 +1,26 @@
+{
+  "TTbarScaleFactors":
+    {
+      "TTbar":
+        {
+          "files_per_job": 10,
+          "max_files": 80,
+          "chunksize": 80000,
+          "subsamples": ["TTToSemiLeptonic"],
+        },
+      "SingleTop":
+        {
+          "files_per_job": 10,
+          "max_files": 80,
+          "chunksize": 80000,
+          "subsamples":
+            [
+              "ST_tW_antitop_5f_NoFullyHadronicDecays",
+              "ST_tW_top_5f_NoFullyHadronicDecays",
+              "ST_s-channel_4f_leptonDecays",
+              "ST_t-channel_antitop_4f_InclusiveDecays",
+              "ST_t-channel_top_4f_InclusiveDecays",
+            ],
+        },
+    },
+}