From 3bd18687d07bddbffa35fe6bf82f9515f80c4187 Mon Sep 17 00:00:00 2001
From: Billy Li <li000400@umn.edu>
Date: Thu, 18 Jul 2024 13:51:41 -0700
Subject: [PATCH] dev: mix baseline with bdt for boosted prediction

---
 notebooks/dev/mix_basline_bdt.ipynb | 86 ++++++++++++++++++-----------
 1 file changed, 54 insertions(+), 32 deletions(-)

diff --git a/notebooks/dev/mix_basline_bdt.ipynb b/notebooks/dev/mix_basline_bdt.ipynb
index ea7bb36..6fdce27 100644
--- a/notebooks/dev/mix_basline_bdt.ipynb
+++ b/notebooks/dev/mix_basline_bdt.ipynb
@@ -130,30 +130,55 @@
     "    return ak.fill_none(ak.pad_none(ak_array, max_n, clip=True, axis=axis), pad, axis=axis).to_numpy()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "42e8de48",
+   "metadata": {},
+   "source": [
+    "### BDT WP by background misidentification rate\n",
+    "Tight: 0.3%\n",
+    "\n",
+    "Medium: 1%\n",
+    "\n",
+    "Loose: 2%"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 7,
-   "id": "d7cceadc",
+   "id": "f2ad1605",
    "metadata": {},
    "outputs": [],
    "source": [
-    "WP = 0.911"
+    "WP_tight = 0.95626426\n",
+    "WP_medium = 0.93498826\n",
+    "WP_loose = 0.911348"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 8,
+   "id": "d7cceadc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "WP = WP_loose\n",
+    "pred_file = \"//Users/billyli/UCSD/hhh/reports/bv2/pred_baseline_bdt_loose.h5\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
    "id": "6d2502b7",
    "metadata": {},
    "outputs": [],
    "source": [
-    "pred_file = \"//Users/billyli/UCSD/hhh/reports/bv2/pred_baseline_bdt_loose.h5\"\n",
     "test_file = \"//Users/billyli/UCSD/hhh/reports/bv2/hhh_test.h5\""
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "id": "ea6b8317",
    "metadata": {},
    "outputs": [],
@@ -163,7 +188,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "id": "401061e3",
    "metadata": {},
    "outputs": [
@@ -173,7 +198,7 @@
        "<KeysViewHDF5 ['MASK', 'fj_charge', 'fj_chargedenergyfrac', 'fj_cosphi', 'fj_ehadovereem', 'fj_eta', 'fj_mass', 'fj_ncharged', 'fj_neutralenergyfrac', 'fj_nneutral', 'fj_phi', 'fj_pt', 'fj_sdmass', 'fj_sinphi', 'fj_tau21', 'fj_tau32']>"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -184,7 +209,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 12,
    "id": "1632da1f",
    "metadata": {},
    "outputs": [],
@@ -204,7 +229,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 13,
    "id": "1820e38a",
    "metadata": {},
    "outputs": [],
@@ -261,7 +286,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 14,
    "id": "ad91ad5a",
    "metadata": {},
    "outputs": [
@@ -280,7 +305,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 15,
    "id": "30133d49",
    "metadata": {},
    "outputs": [],
@@ -305,7 +330,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 16,
    "id": "9133ec8b",
    "metadata": {},
    "outputs": [],
@@ -335,7 +360,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 17,
    "id": "60993088",
    "metadata": {},
    "outputs": [
@@ -355,7 +380,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 18,
    "id": "118d59dc",
    "metadata": {},
    "outputs": [],
@@ -388,23 +413,19 @@
    "id": "9f12c161",
    "metadata": {},
    "source": [
-    "### Remove overlapped jets"
+    "### Select un_padded jets"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 19,
    "id": "e3d30de8",
    "metadata": {},
    "outputs": [],
    "source": [
     "# find ak4jets that matched to selected ak8jets (dR check)\n",
-    "matched_fj_idx = match_fjet_to_jet(fjs_selected, js, ak.ArrayBuilder()).snapshot()\n",
-    "\n",
-    "# remove overlapped ak4jets and padded jets\n",
-    "unoverlapped = matched_fj_idx==-1\n",
     "not_padded = js['mask']\n",
-    "j_cond = unoverlapped & not_padded\n",
+    "j_cond = not_padded\n",
     "js_selected = js[j_cond]"
    ]
   },
@@ -418,7 +439,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 20,
    "id": "8eda8e8b",
    "metadata": {},
    "outputs": [],
@@ -428,12 +449,13 @@
     "# and how many boosted Higgs that you have reconstructed\n",
     "N_jet = ak.num(js_selected, axis=-1).to_numpy(allow_missing=False)\n",
     "N_bH = ak.num(fjs_selected, axis=-1).to_numpy(allow_missing=False)\n",
-    "N_rH = np.minimum(np.floor(N_jet/2), 3-N_bH)"
+    "# N_rH = np.minimum(np.floor(N_jet/2), 3-N_bH)\n",
+    "N_rH = np.minimum(np.floor(N_jet/2), 3)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 21,
    "id": "b4f5933a",
    "metadata": {},
    "outputs": [],
@@ -454,7 +476,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 22,
    "id": "3b38686d",
    "metadata": {},
    "outputs": [],
@@ -492,7 +514,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 23,
    "id": "1662a585",
    "metadata": {},
    "outputs": [],
@@ -523,7 +545,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 24,
    "id": "b6b04fe7",
    "metadata": {},
    "outputs": [],
@@ -537,7 +559,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 25,
    "id": "d7607a1b",
    "metadata": {},
    "outputs": [],
@@ -555,7 +577,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 26,
    "id": "f620bdfc",
    "metadata": {},
    "outputs": [],
@@ -565,7 +587,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 27,
    "id": "d91e4dc0",
    "metadata": {},
    "outputs": [
@@ -575,7 +597,7 @@
        "<KeysViewHDF5 ['assignment_probability', 'b1', 'b2', 'detection_probability']>"
       ]
      },
-     "execution_count": 26,
+     "execution_count": 27,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -586,7 +608,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 28,
    "id": "17aa80d9",
    "metadata": {},
    "outputs": [
@@ -596,7 +618,7 @@
        "<KeysViewHDF5 ['INPUTS', 'TARGETS']>"
       ]
      },
-     "execution_count": 27,
+     "execution_count": 28,
      "metadata": {},
      "output_type": "execute_result"
     }