atlas-ftag-tools 0.2.0__py3-none-any.whl → 0.2.2__py3-none-any.whl

{atlas_ftag_tools-0.2.0.dist-info → atlas_ftag_tools-0.2.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: atlas-ftag-tools
-Version: 0.2.0
+Version: 0.2.2
 Summary: ATLAS Flavour Tagging Tools
 Author: Sam Van Stroud, Philipp Gadow
 License: MIT
@@ -11,8 +11,8 @@ Requires-Dist: h5py >=3.0
 Requires-Dist: numpy
 Requires-Dist: PyYAML >=5.1
 Provides-Extra: dev
-Requires-Dist: ruff ==0.2.2 ; extra == 'dev'
-Requires-Dist: mypy ==1.5.1 ; extra == 'dev'
+Requires-Dist: ruff ==0.6.2 ; extra == 'dev'
+Requires-Dist: mypy ==1.11.2 ; extra == 'dev'
 Requires-Dist: pre-commit ==3.1.1 ; extra == 'dev'
 Requires-Dist: pytest ==7.2.2 ; extra == 'dev'
 Requires-Dist: pytest-cov ==4.0.0 ; extra == 'dev'

{atlas_ftag_tools-0.2.0.dist-info → atlas_ftag_tools-0.2.2.dist-info}/RECORD

@@ -1,10 +1,10 @@
-ftag/__init__.py,sha256=w5AN4J84WCX5o22f3aAcidCQISyQgYqeyfWQlMJCzfU,629
+ftag/__init__.py,sha256=7IKOa65yKaQWsx6-s7VVQs4t1NQ9hyVAOlj-U5m-VBk,629
 ftag/cli_utils.py,sha256=w3TtQmUHSyAKChS3ewvOtcSDAUJAZGIIomaNi8f446U,298
 ftag/cuts.py,sha256=a0BJj4cVRunc-hFLPloGvNoSFvRmZg2kVLv7sA0iAaI,2817
 ftag/flavour.py,sha256=qvgp4DarOdcQgjae_NWnd81k_YqdmFY74lOKky2lpb8,3568
-ftag/flavours.yaml,sha256=9ifKyz1_VoHlOaWuf3JEqMLSYyLFedYJf9x1D6dCTnM,5335
+ftag/flavours.yaml,sha256=lFnVwjh_DwLhOc3mr5n6bSIWyHgxQvAXas4lEmEDncU,7520
 ftag/git_check.py,sha256=Y-XqM80CVXZ5ZKrDdZcYOJt3X64uU6W3OP6Z0D7AZU0,1663
-ftag/mock.py,sha256=9V6sAT4_t-rhR67q9KHaj1NKAeqU7lQjWxiOxEzk8Sw,4338
+ftag/mock.py,sha256=QAm0ti6FWDCRtIyay4yozbGNNATDQbq5b1uc8uVhi2s,4275
 ftag/region.py,sha256=ANv0dGI2W6NJqD9fp7EfqAUReH4FOjc1gwl_Qn8llcM,360
 ftag/sample.py,sha256=TFXMhDkbPmjkms9-b-bINJ32T3bO86JcU70C0nY7wa8,2500
 ftag/test_cli_utils.py,sha256=xa08vf6SEOow58SSFagYdAselb-dkNOVvWsWheMnW-g,1001
@@ -12,15 +12,15 @@ ftag/transform.py,sha256=uEGGJSnqoKOzLYQv650XdK_kDNw4Aw-5dc60z9Dp_y0,3963
 ftag/vds.py,sha256=nRViQZQIORB95nC7NZsW3KsSoGkLzEdOsuCViH5h8-U,3296
 ftag/hdf5/__init__.py,sha256=LFDNxVOCp58SvLHwQhdT68Q-KBMS_i6jBrbXoRpHzbM,354
 ftag/hdf5/h5move.py,sha256=oYpRu0IDCIJIQ2ML52HBAdoyDxmKkHTeM9JdbPEgKfI,947
-ftag/hdf5/h5reader.py,sha256=et-_LXt942xegqc14bPapUgIO7MUfC2m04uJslLkXxI,13579
+ftag/hdf5/h5reader.py,sha256=H_5Aw0lOyEzK_phMRhD-jR_OSCsXnCA3qJZnRvPqaRU,13569
 ftag/hdf5/h5split.py,sha256=4Wy6Xc3J58MdD9aBaSZHf5ZcVFnJSkWsm42R5Pgo-R4,2448
 ftag/hdf5/h5utils.py,sha256=-4zKTMtNCrDZr_9Ww7uzfsB7M7muBKpmm_1IkKJnHOI,3222
-ftag/hdf5/h5writer.py,sha256=wVyurIgfSBtvZTX-v0v3R5-8JOwWK_yF1rUX-RewXzY,4826
+ftag/hdf5/h5writer.py,sha256=j3Fy8snkiVVfimiUz3rrZOhSV8OF27978Y9pk0QcTGM,5277
 ftag/wps/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ftag/wps/discriminant.py,sha256=J2Cst9slZCLoHZYTeltQSmN1Uoa8GUX529rwNlHmyfI,3519
+ftag/wps/discriminant.py,sha256=kJFekUTPNIvCabJCon6OqOAQEzz5hj3XrWFFRLOgGOs,3836
 ftag/wps/working_points.py,sha256=VTU6OD40ULAJQD0MlD1EZd33q8ociUvFX1YrhgJFvXc,9722
-atlas_ftag_tools-0.2.0.dist-info/METADATA,sha256=MRi8CwbXm8vSXlwSFUM99Ec5ZibMtVXdJVqdb0gAv94,5168
-atlas_ftag_tools-0.2.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-atlas_ftag_tools-0.2.0.dist-info/entry_points.txt,sha256=LfVLsZHQolqbPnwPgtmc5IQTh527BKkN2v-IpXWTNHw,137
-atlas_ftag_tools-0.2.0.dist-info/top_level.txt,sha256=qiYQuKcAvMim-31FwkT3MTQu7WQm0s58tPAia5KKWqs,5
-atlas_ftag_tools-0.2.0.dist-info/RECORD,,
+atlas_ftag_tools-0.2.2.dist-info/METADATA,sha256=y2fq23cqtkaoUQxEiCrdoTVuBcG154yjo4k4cwf8P-A,5169
+atlas_ftag_tools-0.2.2.dist-info/WHEEL,sha256=UvcQYKBHoFqaQd6LKyqHw9fxEolWLQnlzP0h_LgJAfI,91
+atlas_ftag_tools-0.2.2.dist-info/entry_points.txt,sha256=LfVLsZHQolqbPnwPgtmc5IQTh527BKkN2v-IpXWTNHw,137
+atlas_ftag_tools-0.2.2.dist-info/top_level.txt,sha256=qiYQuKcAvMim-31FwkT3MTQu7WQm0s58tPAia5KKWqs,5
+atlas_ftag_tools-0.2.2.dist-info/RECORD,,

{atlas_ftag_tools-0.2.0.dist-info → atlas_ftag_tools-0.2.2.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.42.0)
+Generator: setuptools (74.0.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

ftag/__init__.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-__version__ = "v0.2.0"
+__version__ = "v0.2.2"
 
 
 from ftag import hdf5

ftag/flavours.yaml

@@ -47,6 +47,28 @@
   colour: gold
   category: single-btag-extended
 
+# single b-tagging (ghost association)
+- name: ghostbjets
+  label: $b$-jets
+  cuts: ["HadronGhostTruthLabelID == 5"]
+  colour: tab:blue
+  category: single-btag-ghost
+- name: ghostcjets
+  label: $c$-jets
+  cuts: ["HadronGhostTruthLabelID == 4"]
+  colour: tab:orange
+  category: single-btag-ghost
+- name: ghostujets
+  label: Light-jets
+  cuts: ["HadronGhostTruthLabelID == 0"]
+  colour: tab:green
+  category: single-btag-ghost
+- name: ghosttaujets
+  label: $\tau$-jets
+  cuts: ["HadronGhostTruthLabelID == 15"]
+  colour: tab:purple
+  category: single-btag-ghost
+
 # Xbb tagging
 - name: hbb
   label: $H \rightarrow b\bar{b}$
@@ -140,37 +162,84 @@
   colour: "#e76f51"
   category: lepton-decay
 
+# PDGID labelling: taken from https://pdg.lbl.gov/2023/reviews/rpp2023-rev-monte-carlo-numbering.pdf
+- name: D0meson
+  label: $D^0$ in $c$-jet
+  cuts: ["HadronConeExclTruthLabelID == 4", "HadronConeExclTruthLabelPdgId in (421,-421)"]
+  colour: "#FFA500"
+  category: PDGID
+- name: nonD0meson
+  label: $D^+$, $Ds^+$ or baryon in $c$-jet
+  cuts: ["HadronConeExclTruthLabelID == 4", "HadronConeExclTruthLabelPdgId notin (421,-421)"]
+  colour: "#800080"
+  category: PDGID
+- name: Dplusmeson
+  label: $D^+$ in $c$-jet
+  cuts: ["HadronConeExclTruthLabelID == 4", "HadronConeExclTruthLabelPdgId in (411,-411)"]
+  colour: "#00FFFF"
+  category: PDGID
+- name: Dsplusmeson
+  label: $Ds^+$ in $c$-jet
+  cuts: ["HadronConeExclTruthLabelID == 4", "HadronConeExclTruthLabelPdgId in (431,-431)"]
+  colour: "#781DC8"
+  category: PDGID
+- name: B0meson
+  label: $B^0$ in $b$-jet
+  cuts: ["HadronConeExclTruthLabelID == 5", "HadronConeExclTruthLabelPdgId in (511,-511)"]
+  colour: "#702B1C"
+  category: PDGID
+- name: Bplusmeson
+  label: $B^0$ in $b$-jet
+  cuts: ["HadronConeExclTruthLabelID == 5", "HadronConeExclTruthLabelPdgId in (521,-521)"]
+  colour: "#C81D4A"
+  category: PDGID
+- name: Bs0meson
+  label: $Bs^0$ in $b$-jet
+  cuts: ["HadronConeExclTruthLabelID == 5", "HadronConeExclTruthLabelPdgId in (531,-531)"]
+  colour: "#1D62C8"
+  category: PDGID
+
 # lepton isolation
 ## taken from https://gitlab.cern.ch/atlas/athena/-/blob/main/PhysicsAnalysis/AnalysisCommon/TruthClassification/README.md#4-details-about-the-lepton-categories
 - name: elxprompt
   label: prompt electrons
-  cuts: ["iffClass == 2"]
+  cuts: ["iffClass in (2,3)"]
   colour: tab:red
   category: isolation
+- name: elxnoflip
+  label: prompt electrons with no charge-flip
+  cuts: ["iffClass == 2"]
+  colour: darkorange
+  category: isolation
 - name: elxflip
   label: prompt electrons with charge-flip
   cuts: ["iffClass == 3"]
   colour: tab:orange
   category: isolation
+- name: elxphconv
+  label: electrons from prompt photon-conversions
+  cuts: ["iffClass == 5"]
+  colour: tab:purple
+  category: isolation
+- name: elxnonprompt
+  label: non-prompt electrons
+  cuts: ["iffClass notin (2,3,5)"]
+  colour: "#264653"
+  category: isolation
 - name: muxprompt
   label: prompt muons
-  cuts: ["iffClass == 4"]
+  cuts: ["iffClass in (4,11)"]
   colour: tab:blue
   category: isolation
+- name: muxnoflip
+  label: prompt muons with no charge-flip
+  cuts: ["iffClass == 4"]
+  colour: aqua
+  category: isolation
 - name: muxflip
   label: prompt muons with charge-flip
   cuts: ["iffClass == 11"]
-  colour: aqua
-  category: isolation
-- name: elxphconv
-  label: electrons from prompt photon-conversions
-  cuts: ["iffClass == 5"]
-  colour: tab:purple
-  category: isolation
-- name: elxfrommu
-  label: electrons from muons
-  cuts: ["iffClass == 6"]
-  colour: salmon
+  colour: midnightblue
   category: isolation
 - name: npxall
   label: non-prompt lepton

ftag/hdf5/h5reader.py

@@ -60,7 +60,7 @@ class H5SingleReader:
             for var in array.dtype.names:
                 isinf = np.isinf(array[var])
                 isinf = isinf if name == self.jets_name else isinf.any(axis=-1)
-                keep_idx = keep_idx & ~isinf
+                keep_idx &= ~isinf
                 if num_inf := isinf.sum():
                     log.warning(
                         f"{num_inf} inf values detected for variable {var} in"

ftag/hdf5/h5writer.py

@@ -41,7 +41,7 @@ class H5Writer:
     jets_name: str = "jets"
     add_flavour_label: bool = False
     compression: str = "lzf"
-    precision: str | None = None
+    precision: str = "full"
     shuffle: bool = True
 
     def __post_init__(self):
@@ -51,6 +51,13 @@ class H5Writer:
         assert len(set(self.num_jets)) == 1, "Must have same number of jets per group"
         self.num_jets = self.num_jets[0]
 
+        if self.precision == "full":
+            self.fp_dtype = np.float32
+        elif self.precision == "half":
+            self.fp_dtype = np.float16
+        else:
+            raise ValueError(f"Invalid precision: {self.precision}")
+
         self.dst = Path(self.dst)
         self.dst.parent.mkdir(parents=True, exist_ok=True)
         self.file = h5py.File(self.dst, "w")
@@ -77,11 +84,17 @@ class H5Writer:
         if name == self.jets_name and self.add_flavour_label:
             dtype = np.dtype([*dtype.descr, ("flavour_label", "i4")])
 
+        # adjust dtype based on specified precision
+        dtype = np.dtype([
+            (field, self.fp_dtype if np.issubdtype(dt, np.floating) else dt)
+            for field, dt in dtype.descr
+        ])
+
         # optimal chunking is around 100 jets, only aply for track groups
         shape = self.shapes[name]
         chunks = (100,) + shape[1:] if shape[1:] else None
 
-        # note: enabling the hd5 shuffle filter doesn't improve anything
+        # note: enabling the hd5 shuffle filter doesn't improve write performance
         self.file.create_dataset(
             name, dtype=dtype, shape=shape, compression=self.compression, chunks=chunks
         )

ftag/mock.py

@@ -52,7 +52,6 @@ TRACK_VARS = [
 
 
 def softmax(x, axis=None):
-    """Compute softmax values for each sets of scores in x."""
     e_x = np.exp(x - np.max(x, axis=axis, keepdims=True))
     return e_x / e_x.sum(axis=axis, keepdims=True)
 

ftag/wps/discriminant.py

@@ -53,6 +53,11 @@ def discriminant(
     return np.log((jets[f"{tagger}_{signal.px}"] + epsilon) / (denominator + epsilon))
 
 
+def tautag_dicriminant(jets, tagger, fb, fc, epsilon=1e-10):
+    fxs = {"pb": fb, "pc": fc, "pu": 1 - fb - fc}
+    return discriminant(jets, tagger, Flavours.taujets, fxs, epsilon=epsilon)
+
+
 def btag_discriminant(jets, tagger, fc, ftau=0, epsilon=1e-10):
     fxs = {"pc": fc, "ptau": ftau, "pu": 1 - fc - ftau}
     return discriminant(jets, tagger, Flavours.bjets, fxs, epsilon=epsilon)
@@ -95,10 +100,16 @@ def get_discriminant(
     -------
     np.ndarray
         Array of discriminant values.
+
+    Raises
+    ------
+    ValueError
+        If the signal flavour is not recognised.
     """
     tagger_funcs: dict[str, Callable] = {
         "bjets": btag_discriminant,
         "cjets": ctag_discriminant,
+        "taujets": tautag_dicriminant,
         "hbb": hbb_discriminant,
         "hcc": hcc_discriminant,
     }