atlas-schema 0.2.4__py3-none-any.whl → 0.3.0__py3-none-any.whl

atlas_schema/_version.py

@@ -1,8 +1,13 @@
-# file generated by setuptools_scm
+# file generated by setuptools-scm
 # don't change, don't track in version control
+
+__all__ = ["__version__", "__version_tuple__", "version", "version_tuple"]
+
 TYPE_CHECKING = False
 if TYPE_CHECKING:
-    from typing import Tuple, Union
+    from typing import Tuple
+    from typing import Union
+
     VERSION_TUPLE = Tuple[Union[int, str], ...]
 else:
     VERSION_TUPLE = object
@@ -12,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.2.4'
-__version_tuple__ = version_tuple = (0, 2, 4)
+__version__ = version = '0.3.0'
+__version_tuple__ = version_tuple = (0, 3, 0)

atlas_schema/methods.py

@@ -8,7 +8,6 @@ from operator import ior
 import awkward
 import particle
 from coffea.nanoevents.methods import base, candidate, vector
-from dask_awkward import dask_method
 
 from atlas_schema.enums import PhotonID
 from atlas_schema.typing_compat import Behavior
@@ -63,22 +62,9 @@ class Particle(vector.PtEtaPhiMLorentzVector):
     - '{obj}_select'
     """
 
-    @property
-    def mass(self):
-        r"""Invariant mass (+, -, -, -)
-
-        :math:`\sqrt{t^2-x^2-y^2-z^2}`
-        """
-        return self["mass"] / 1.0e3
-
-    @dask_method
     def passes(self, name):
         return self[f"select_{name}"] == 1
 
-    @passes.dask
-    def passes(self, dask_array, name):
-        return dask_array[f"select_{name}"] == 1
-
     # NB: fields with the name 'pt' take precedence over this
     # @dask_property
     # def pt(self):
@@ -166,8 +152,8 @@ behavior.update(awkward._util.copy_behaviors("Particle", "Electron", behavior))
 class Electron(Particle, base.NanoCollection, base.Systematic):
     @property
     def mass(self):
-        """Electron mass in GeV"""
-        return particle.literals.e_minus.mass / 1.0e3
+        """Electron mass in MeV"""
+        return awkward.ones_like(self.pt) * particle.literals.e_minus.mass
 
 
 _set_repr_name("Electron")
@@ -184,8 +170,8 @@ behavior.update(awkward._util.copy_behaviors("Particle", "Muon", behavior))
 class Muon(Particle, base.NanoCollection, base.Systematic):
     @property
     def mass(self):
-        """Muon mass in GeV"""
-        return particle.literals.mu_minus.mass / 1.0e3
+        """Muon mass in MeV"""
+        return awkward.ones_like(self.pt) * particle.literals.mu_minus.mass
 
 
 _set_repr_name("Muon")
@@ -202,8 +188,8 @@ behavior.update(awkward._util.copy_behaviors("Particle", "Tau", behavior))
 class Tau(Particle, base.NanoCollection, base.Systematic):
     @property
     def mass(self):
-        """Tau mass in GeV"""
-        return particle.literals.tau_minus.mass / 1.0e3
+        """Tau mass in MeV"""
+        return awkward.ones_like(self.pt) * particle.literals.tau_minus.mass
 
 
 _set_repr_name("Tau")
@@ -218,7 +204,14 @@ behavior.update(awkward._util.copy_behaviors("Particle", "Jet", behavior))
 
 
 @awkward.mixin_class(behavior)
-class Jet(Particle, base.NanoCollection, base.Systematic): ...
+class Jet(Particle, base.NanoCollection, base.Systematic):
+    @property
+    def mass(self):
+        r"""Invariant mass (+, -, -, -)
+
+        :math:`\sqrt{t^2-x^2-y^2-z^2}`
+        """
+        return self["m"]
 
 
 _set_repr_name("Jet")

atlas_schema/schema.py

@@ -7,6 +7,7 @@ from typing import Any, ClassVar
 
 from coffea.nanoevents.schemas.base import BaseSchema, zip_forms
 
+from atlas_schema.methods import behavior as roaster
 from atlas_schema.typing_compat import Behavior, Self
 
 
@@ -190,7 +191,9 @@ class NtupleSchema(BaseSchema):  # type: ignore[misc]
         branch_forms = dict(zip(field_names, input_contents))
 
         # parse into high-level records (collections, list collections, and singletons)
-        collections = {k.split("_")[0] for k in branch_forms}
+        collections = {
+            k.split("_")[0] for k in branch_forms if k not in self.singletons
+        }
         collections -= self.event_ids
         collections -= set(self.singletons)
 
@@ -227,17 +230,25 @@ class NtupleSchema(BaseSchema):  # type: ignore[misc]
             branch_forms[k.replace("_NOSYS", "") + "_NOSYS"] = branch_forms.pop(k)
 
         # these are collections with systematic variations
-        subcollections = {
-            k.split("__")[0].split("_", 1)[1].replace("_NOSYS", "")
-            for k in branch_forms
-            if "NOSYS" in k
-        }
+        try:
+            subcollections = {
+                k.split("__")[0].split("_", 1)[1].replace("_NOSYS", "")
+                for k in branch_forms
+                if "NOSYS" in k and k not in self.singletons
+            }
+        except IndexError as exc:
+            msg = "One of the branches does not follow the assumed pattern for this schema. [invalid-branch-name]"
+            raise RuntimeError(msg) from exc
 
         # Check the presence of the event_ids
         missing_event_ids = [
             event_id for event_id in self.event_ids if event_id not in branch_forms
         ]
 
+        missing_singletons = [
+            singleton for singleton in self.singletons if singleton not in branch_forms
+        ]
+
         if len(missing_event_ids) > 0:
             if self.error_missing_event_ids:
                 msg = f"There are missing event ID fields: {missing_event_ids} \n\n\
@@ -253,12 +264,25 @@ class NtupleSchema(BaseSchema):  # type: ignore[misc]
                 stacklevel=2,
             )
 
+        if len(missing_singletons) > 0:
+            # These singletons are simply branches we do not parse or handle
+            # explicitly in atlas-schema (e.g. they are copied directly to the
+            # output structure we provide you), however there can be false
+            # positives when you submit multiple files with different branch
+            # structures and this warning could be safely ignored.
+            warnings.warn(
+                f"Missing singletons : {missing_singletons}. [singleton-missing]",
+                RuntimeWarning,
+                stacklevel=2,
+            )
+
         output = {}
 
         # first, register singletons (event-level, others)
         for name in {*self.event_ids, *self.singletons}:
-            if name in missing_event_ids:
+            if name in [*missing_event_ids, *missing_singletons]:
                 continue
+
             output[name] = branch_forms[name]
 
         # next, go through and start grouping up collections
@@ -354,8 +378,6 @@ class NtupleSchema(BaseSchema):  # type: ignore[misc]
         Returns:
             dict[str | tuple['*', str], type[awkward.Record]]: an :data:`awkward.behavior` dictionary
         """
-        from atlas_schema.methods import behavior as roaster
-
         return roaster
 
     @classmethod

atlas_schema/utils.py

@@ -1,16 +1,15 @@
 from __future__ import annotations
 
 from enum import Enum
-from typing import TypeVar, Union, cast
+from typing import TypeVar, cast
 
 import awkward as ak
-import dask_awkward as dak
 
-Array = TypeVar("Array", bound=Union[dak.Array, ak.Array])
+Array = TypeVar("Array", bound=ak.Array)
 _E = TypeVar("_E", bound=Enum)
 
 
-def isin(element: Array, test_elements: dak.Array | ak.Array, axis: int = -1) -> Array:
+def isin(element: Array, test_elements: ak.Array, axis: int = -1) -> Array:
     """
     Find test_elements in element. Similar in API as :func:`numpy.isin`.
 
@@ -21,12 +20,12 @@ def isin(element: Array, test_elements: dak.Array | ak.Array, axis: int = -1) ->
     comparison.
 
     Args:
-        element (dask_awkward.Array or ak.Array): input array of values.
-        test_elements (dask_awkward.Array or ak.Array): one-dimensional set of values against which to test each value of *element*.
+        element (ak.Array): input array of values.
+        test_elements (ak.Array): one-dimensional set of values against which to test each value of *element*.
         axis (int): the axis along which the comparison is performed
 
     Returns:
-        dask_awkward.Array or ak.Array: result of comparison for test_elements in *element*
+        ak.Array: result of comparison for test_elements in *element*
 
     Example:
         >>> import awkward as ak

{atlas_schema-0.2.4.dist-info → atlas_schema-0.3.0.dist-info}/METADATA

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: atlas-schema
-Version: 0.2.4
+Version: 0.3.0
 Summary: Helper python package for ATLAS Common NTuple Analysis work.
 Project-URL: Homepage, https://github.com/scipp-atlas/atlas-schema
 Project-URL: Bug Tracker, https://github.com/scipp-atlas/atlas-schema/issues
 Project-URL: Discussions, https://github.com/scipp-atlas/atlas-schema/discussions
-Project-URL: Documentation, https://atlas-schema.readthedocs.io/en/v0.2.4/
+Project-URL: Documentation, https://atlas-schema.readthedocs.io/en/v0.3.0/
 Project-URL: Releases, https://github.com/scipp-atlas/atlas-schema/releases
 Project-URL: Release Notes, https://atlas-schema.readthedocs.io/en/latest/history.html
 Author-email: Giordon Stark <kratsg@gmail.com>
@@ -227,7 +227,7 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering
 Classifier: Typing :: Typed
 Requires-Python: >=3.9
-Requires-Dist: coffea[dask]>=2024.4.1
+Requires-Dist: coffea[dask]>=2025.7.0
 Requires-Dist: particle>=0.25.0
 Provides-Extra: dev
 Requires-Dist: pytest-cov>=3; extra == 'dev'
@@ -251,7 +251,7 @@ Requires-Dist: tbump>=6.7.0; extra == 'test'
 Requires-Dist: twine; extra == 'test'
 Description-Content-Type: text/markdown
 
-# atlas-schema v0.2.4
+# atlas-schema v0.3.0
 
 [![Actions Status][actions-badge]][actions-link]
 [![Documentation Status][rtd-badge]][rtd-link]
@@ -335,11 +335,9 @@ like below:
 
 ```python
 import awkward as ak
-import dask
-import hist.dask as had
+from hist import Hist
 import matplotlib.pyplot as plt
 from coffea import processor
-from coffea.nanoevents import NanoEventsFactory
 from distributed import Client
 
 from atlas_schema.schema import NtupleSchema
@@ -352,7 +350,7 @@ class MyFirstProcessor(processor.ProcessorABC):
     def process(self, events):
         dataset = events.metadata["dataset"]
         h_ph_pt = (
-            had.Hist.new.StrCat(["all", "pass", "fail"], name="isEM")
+            Hist.new.StrCat(["all", "pass", "fail"], name="isEM")
             .Regular(200, 0.0, 2000.0, name="pt", label="$pt_{\gamma}$ [GeV]")
             .Int64()
         )
@@ -376,17 +374,18 @@ class MyFirstProcessor(processor.ProcessorABC):
 if __name__ == "__main__":
     client = Client()
 
-    fname = "ntuple.root"
-    events = NanoEventsFactory.from_root(
-        {fname: "analysis"},
-        schemaclass=NtupleSchema,
-        metadata={"dataset": "700352.Zqqgamma.mc20d.v1"},
-    ).events()
-
-    p = MyFirstProcessor()
-    out = p.process(events)
-    (computed,) = dask.compute(out)
-    print(computed)
+    fileset = {"700352.Zqqgamma.mc20d.v1": {"files": {"ntuple.root": "analysis"}}}
+
+    run = processor.Runner(
+        executor=processor.IterativeExecutor(compression=None),
+        schema=NtupleSchema,
+        savemetrics=True,
+    )
+
+    out, metrics = run(fileset, processor_instance=MyFirstProcessor())
+
+    print(out)
+    print(metrics)
 
     fig, ax = plt.subplots()
     computed["700352.Zqqgamma.mc20d.v1"]["ph_pt"].plot1d(ax=ax)

atlas_schema-0.3.0.dist-info/RECORD

@@ -0,0 +1,13 @@
+atlas_schema/__init__.py,sha256=ebY-rTiwSGnfvt1yWATze2GE7K3fVgJj6fT64Sl4sH8,469
+atlas_schema/_version.py,sha256=AGmG_Lx0-9ztFw_7d9mYbaYuC-2abxE1oXOUNAY29YY,511
+atlas_schema/_version.pyi,sha256=j5kbzfm6lOn8BzASXWjGIA1yT0OlHTWqlbyZ8Si_o0E,118
+atlas_schema/enums.py,sha256=hwgOvFBmITNxL0MQkrNpbiPv9VMezFoE-eyGgjzem8E,3688
+atlas_schema/methods.py,sha256=DPeEFofeD5_bCk7V3KudJaE_sAUMpBIh-gPnM4kWDe8,7124
+atlas_schema/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+atlas_schema/schema.py,sha256=44i7ri-7OP4SK6_D_3JAGvoiIY-IcPBp1p6MlKfWK5I,21675
+atlas_schema/typing_compat.py,sha256=3G8h4WfLoDmrtWZvtYKLCwEpCQ_O4Fwygb2WlDRSE4E,488
+atlas_schema/utils.py,sha256=E3jCka-pf_0h_r3OO0hMLlbF6dQKoxr2T1Gd18-aJ4U,2034
+atlas_schema-0.3.0.dist-info/METADATA,sha256=NCkA4ydLhlTHYJOTipTgZlR7_yhDsDe7zpa0jbnqw00,20069
+atlas_schema-0.3.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+atlas_schema-0.3.0.dist-info/licenses/LICENSE,sha256=snem82NV8fgAi4DKaaUIfReaM5RqIWbH5OOXOvy40_w,11344
+atlas_schema-0.3.0.dist-info/RECORD,,

atlas_schema-0.2.4.dist-info/RECORD

@@ -1,13 +0,0 @@
-atlas_schema/__init__.py,sha256=ebY-rTiwSGnfvt1yWATze2GE7K3fVgJj6fT64Sl4sH8,469
-atlas_schema/_version.py,sha256=4gL0W4-u58XR5lRLpeoIPrGhcewTk0-527de6uTNmkg,411
-atlas_schema/_version.pyi,sha256=j5kbzfm6lOn8BzASXWjGIA1yT0OlHTWqlbyZ8Si_o0E,118
-atlas_schema/enums.py,sha256=hwgOvFBmITNxL0MQkrNpbiPv9VMezFoE-eyGgjzem8E,3688
-atlas_schema/methods.py,sha256=hFdtKXnyCcx4M05WhAM24fKwzEhh_ubA7jNa6_xv67k,7238
-atlas_schema/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-atlas_schema/schema.py,sha256=4OAvuPrOds-taVES32y4K8dvNDf8PKdu83DZqAlTdp8,20621
-atlas_schema/typing_compat.py,sha256=3G8h4WfLoDmrtWZvtYKLCwEpCQ_O4Fwygb2WlDRSE4E,488
-atlas_schema/utils.py,sha256=IqMbWqq0ib_kZdJCaM5ghURZatmb8pKidlewx3dpy0A,2164
-atlas_schema-0.2.4.dist-info/METADATA,sha256=KZDH5fsZon5wFXuU-iSUeqgjoplOwAoqTM1I9LgaTiM,20107
-atlas_schema-0.2.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-atlas_schema-0.2.4.dist-info/licenses/LICENSE,sha256=snem82NV8fgAi4DKaaUIfReaM5RqIWbH5OOXOvy40_w,11344
-atlas_schema-0.2.4.dist-info/RECORD,,