reboost 0.5.0__tar.gz → 0.5.2__tar.gz

{reboost-0.5.0 → reboost-0.5.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: reboost
-Version: 0.5.0
+Version: 0.5.2
 Summary: New LEGEND Monte-Carlo simulation post-processing
 Author-email: Manuel Huber <info@manuelhu.de>, Toby Dixon <toby.dixon.23@ucl.ac.uk>, Luigi Pertoldi <gipert@pm.me>
 Maintainer: The LEGEND Collaboration
@@ -701,7 +701,7 @@ Requires-Dist: numpy
 Requires-Dist: scipy
 Requires-Dist: numba
 Requires-Dist: legend-pydataobj>=1.12.0
-Requires-Dist: legend-pygeom-optics>=0.6.5
+Requires-Dist: legend-pygeom-optics>=0.9.2
 Requires-Dist: hist
 Requires-Dist: dbetto
 Requires-Dist: particle

{reboost-0.5.0 → reboost-0.5.2}/pyproject.toml

@@ -37,7 +37,7 @@ dependencies = [
     "scipy",
     "numba",
     "legend-pydataobj>=1.12.0",
-    "legend-pygeom-optics>=0.6.5",
+    "legend-pygeom-optics>=0.9.2",
     "hist",
     "dbetto",
     "particle",

{reboost-0.5.0 → reboost-0.5.2}/src/reboost/__init__.py

@@ -2,20 +2,12 @@ from __future__ import annotations
 
 from lgdo import lh5
 
-from . import build_hit, core, iterator, math, shape
 from ._version import version as __version__
+from .build_hit import build_hit
 
 __all__ = [
     "__version__",
-    "build_glm",
     "build_hit",
-    "build_hit",
-    "build_tcm",
-    "core",
-    "iterator",
-    "math",
-    "optmap",
-    "shape",
 ]
 
 lh5.settings.DEFAULT_HDF5_SETTINGS = {"shuffle": True, "compression": "lzf"}

{reboost-0.5.0 → reboost-0.5.2}/src/reboost/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.5.0'
-__version_tuple__ = version_tuple = (0, 5, 0)
+__version__ = version = '0.5.2'
+__version_tuple__ = version_tuple = (0, 5, 2)

{reboost-0.5.0 → reboost-0.5.2}/src/reboost/build_evt.py

@@ -78,9 +78,6 @@ def build_evt(
     -------
     ak.Array of the evt tier data (if the data is not saved to disk)
     """
-    msg = "... beginning the evt tier processing"
-    log.info(msg)
-
     # create the objects needed for evaluate expression
 
     file_info = {

{reboost-0.5.0 → reboost-0.5.2}/src/reboost/build_glm.py

@@ -224,8 +224,8 @@ def build_glm(
     glm_sum = {}
 
     for file_idx, stp_file in enumerate(files.stp):
-        msg = f"Start generating glm for {stp_file} "
-        log.info(msg)
+        msg = f"start generating glm for {stp_file} "
+        log.debug(msg)
 
         # loop over the lh5_tables
         lh5_table_list = [
@@ -298,8 +298,6 @@ def build_glm(
                         if glm_sum[lh5_subgroup] is None
                         else ak.concatenate((glm_sum[lh5_subgroup], glm))
                     )
-        msg = f"Finished generating glm for {stp_file} "
-        log.info(msg)
 
     # return if it was requested to keep glm in memory
     if glm_sum is not None:

{reboost-0.5.0 → reboost-0.5.2}/src/reboost/build_hit.py

@@ -239,17 +239,17 @@ def build_hit(
     # iterate over files
     for file_idx, (stp_file, glm_file) in enumerate(zip(files.stp, files.glm)):
         msg = (
-            f"... starting post processing of {stp_file} to {files.hit[file_idx]} "
+            f"starting processing of {stp_file} to {files.hit[file_idx]} "
             if files.hit[file_idx] is not None
-            else f"... starting post processing of {stp_file}"
+            else f"starting processing of {stp_file}"
         )
         log.info(msg)
 
         # loop over processing groups
         for group_idx, proc_group in enumerate(config["processing_groups"]):
             proc_name = proc_group.get("name", "default")
-            msg = f"... starting group {proc_name}"
-            log.info(msg)
+            msg = f"starting group {proc_name}"
+            log.debug(msg)
 
             if proc_name not in time_dict:
                 time_dict[proc_name] = ProfileDict()
@@ -261,7 +261,7 @@ def build_hit(
 
             # loop over detectors
             for in_det_idx, (in_detector, out_detectors) in enumerate(detectors_mapping.items()):
-                msg = f"... processing {in_detector} (to {out_detectors})"
+                msg = f"processing {in_detector} (to {out_detectors})"
                 log.debug(msg)
 
                 # get detector objects
@@ -328,7 +328,14 @@ def build_hit(
                             "DETECTOR": out_detector,
                         }
                         # add fields
-                        for field, expression in proc_group.get("operations", {}).items():
+                        for field, info in proc_group.get("operations", {}).items():
+                            if isinstance(info, str):
+                                expression = info
+                                units = None
+                            else:
+                                expression = info["expression"]
+                                units = info.get("units", None)
+
                             # evaluate the expression
                             col = core.evaluate_output_column(
                                 hit_table,
@@ -338,6 +345,10 @@ def build_hit(
                                 time_dict=time_dict[proc_name],
                                 name=field,
                             )
+
+                            if units is not None:
+                                col.attrs["units"] = units
+
                             core.add_field_with_nesting(hit_table, field, col)
 
                         # remove unwanted fields
@@ -393,14 +404,14 @@ def build_hit(
                         lh5.read(obj, stp_file),
                         obj,
                         files.hit[file_idx],
-                        wo_mode="write_safe",
+                        wo_mode="write_safe" if file_idx == 0 else "append",
                     )
                 except LH5EncodeError as e:
                     msg = f"cannot forward object {obj} as it has been already processed by reboost"
                     raise RuntimeError(msg) from e
 
     # return output table or nothing
-    log.info(time_dict)
+    log.debug(time_dict)
 
     if output_tables == {}:
         output_tables = None

{reboost-0.5.0 → reboost-0.5.2}/src/reboost/core.py

@@ -139,7 +139,7 @@ def get_global_objects(
         time_start = time.time()
 
     msg = f"Getting global objects with {expressions.keys()} and {local_dict}"
-    log.info(msg)
+    log.debug(msg)
     res = {}
 
     for obj_name, expression in expressions.items():

{reboost-0.5.0 → reboost-0.5.2}/src/reboost/iterator.py

@@ -113,7 +113,7 @@ class GLMIterator:
         if self.use_glm:
             self.buffer = int(buffer * glm_n_rows / stp_n_rows)
             msg = f"Number of stp rows {stp_n_rows}, number of glm rows {glm_n_rows} changing buffer from {buffer} to {self.buffer}"
-            log.info(msg)
+            log.debug(msg)
 
     def __iter__(self) -> typing.Iterator:
         self.current_i_entry = 0

{reboost-0.5.0 → reboost-0.5.2}/src/reboost/optmap/convolve.py

@@ -75,8 +75,14 @@ def iterate_stepwise_depositions(
     mode: str = "no-fano",
 ):
     # those np functions are not supported by numba, but needed for efficient array access below.
-    x0 = structured_to_unstructured(edep_df[["xloc_pre", "yloc_pre", "zloc_pre"]], np.float64)
-    x1 = structured_to_unstructured(edep_df[["xloc_post", "yloc_post", "zloc_post"]], np.float64)
+    if "xloc_pre" in edep_df.dtype.names:
+        x0 = structured_to_unstructured(edep_df[["xloc_pre", "yloc_pre", "zloc_pre"]], np.float64)
+        x1 = structured_to_unstructured(
+            edep_df[["xloc_post", "yloc_post", "zloc_post"]], np.float64
+        )
+    else:
+        x0 = structured_to_unstructured(edep_df[["xloc", "yloc", "zloc"]], np.float64)
+        x1 = None
 
     rng = np.random.default_rng() if rng is None else rng
     output_map, res = _iterate_stepwise_depositions(
@@ -157,12 +163,16 @@ def _iterate_stepwise_depositions(
 
         # do the scintillation.
         part, charge = pdgid_map[t.particle]
+
+        # if we have both pre and post step points use them
+        # else pass as None
+
         scint_times = sc.scintillate(
             scint_mat_params,
             x0[rowid],
-            x1[rowid],
-            t.v_pre,
-            t.v_post,
+            x1[rowid] if x1 is not None else None,
+            t.v_pre if x1 is not None else None,
+            t.v_post if x1 is not None else None,
             t.time,
             part,
             charge,
@@ -358,7 +368,7 @@ def convolve(
     it = LH5Iterator(edep_file, edep_path, buffer_len=buffer_len)
 
     for it_count, edep_lgdo in enumerate(it):
-        edep_df = edep_lgdo.view_as("pd").iloc.to_records()
+        edep_df = edep_lgdo.view_as("pd").to_records()
 
         log.info("start event processing (%d)", it_count)
         output_map = iterate_stepwise_depositions(

{reboost-0.5.0 → reboost-0.5.2}/src/reboost/optmap/create.py

@@ -131,7 +131,7 @@ def _create_optical_maps_chunk(
     hits_per_primary = np.zeros(10, dtype=np.int64)
     hits_per_primary_len = 0
     for it_count, events_lgdo in enumerate(optmap_events_it):
-        optmap_events = events_lgdo.view_as("pd").iloc
+        optmap_events = events_lgdo.view_as("pd")
         hitcounts = optmap_events[all_det_ids].to_numpy()
         loc = optmap_events[["xloc", "yloc", "zloc"]].to_numpy()
 

{reboost-0.5.0 → reboost-0.5.2}/src/reboost/optmap/evt.py

@@ -25,7 +25,6 @@ def build_optmap_evt(
     if lh5_out_file_tmp.exists():
         msg = f"temporary output file {lh5_out_file_tmp} already exists"
         raise RuntimeError(msg)
-
     vert_it = LH5Iterator(lh5_in_file, "vtx", buffer_len=buffer_len)
     opti_it = LH5Iterator(lh5_in_file, "stp/optical", buffer_len=buffer_len)
 
@@ -80,8 +79,7 @@ def build_optmap_evt(
             _store_vert_df()
 
             # read the next vertex chunk into memory.
-            (vert_lgdo, vert_entry) = next(vert_it)
-            vert_df = vert_lgdo.view_as("pd").iloc
+            vert_df = next(vert_it).view_as("pd")
 
             # prepare vertex coordinates.
             vert_df = vert_df.set_index("evtid", drop=True).drop(["n_part", "time"], axis=1)
@@ -95,9 +93,10 @@ def build_optmap_evt(
     # use smaller integer type uint8 to spare RAM when storing types.
     hit_count_type = np.uint8
     for opti_it_count, opti_lgdo in enumerate(opti_it):
-        opti_df = opti_lgdo.view_as("pd").iloc
+        opti_df = opti_lgdo.view_as("pd")
 
         log.info("build evt table (%d)", opti_it_count)
+
         for t in opti_df[["evtid", "det_uid"]].itertuples(name=None, index=False):
             _ensure_vert_df(vert_it, t[0])
             vert_df.loc[t[0], str(t[1])] += 1

{reboost-0.5.0 → reboost-0.5.2}/src/reboost.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: reboost
-Version: 0.5.0
+Version: 0.5.2
 Summary: New LEGEND Monte-Carlo simulation post-processing
 Author-email: Manuel Huber <info@manuelhu.de>, Toby Dixon <toby.dixon.23@ucl.ac.uk>, Luigi Pertoldi <gipert@pm.me>
 Maintainer: The LEGEND Collaboration
@@ -701,7 +701,7 @@ Requires-Dist: numpy
 Requires-Dist: scipy
 Requires-Dist: numba
 Requires-Dist: legend-pydataobj>=1.12.0
-Requires-Dist: legend-pygeom-optics>=0.6.5
+Requires-Dist: legend-pygeom-optics>=0.9.2
 Requires-Dist: hist
 Requires-Dist: dbetto
 Requires-Dist: particle

{reboost-0.5.0 → reboost-0.5.2}/src/reboost.egg-info/requires.txt

@@ -3,7 +3,7 @@ numpy
 scipy
 numba
 legend-pydataobj>=1.12.0
-legend-pygeom-optics>=0.6.5
+legend-pygeom-optics>=0.9.2
 hist
 dbetto
 particle

{reboost-0.5.0 → reboost-0.5.2}/tests/conftest.py

@@ -12,8 +12,6 @@ from legendtestdata import LegendTestData
 
 _tmptestdir = Path(gettempdir()) / f"reboost-tests-{getuser()}-{uuid.uuid4()!s}"
 
-collect_ignore = ["test_optmap.py"]
-
 
 @pytest.fixture(scope="session")
 def tmptestdir_global():

{reboost-0.5.0 → reboost-0.5.2}/tests/hit/test_build_hit.py

@@ -79,7 +79,7 @@ def test_gen_lh5_flat(tmptestdir):
 def test_reshape(test_gen_lh5_flat, tmptestdir):
     outfile = f"{tmptestdir}/basic_hit_reshaped.lh5"
 
-    reboost.build_hit.build_hit(
+    reboost.build_hit(
         f"{Path(__file__).parent}/configs/reshape.yaml",
         args={},
         stp_files=test_gen_lh5_flat,
@@ -110,7 +110,7 @@ def test_reshape(test_gen_lh5_flat, tmptestdir):
 def test_basic(test_gen_lh5, tmptestdir):
     outfile = f"{tmptestdir}/basic_hit.lh5"
 
-    reboost.build_hit.build_hit(
+    reboost.build_hit(
         f"{Path(__file__).parent}/configs/basic.yaml",
         args={},
         stp_files=test_gen_lh5,
@@ -132,9 +132,11 @@ def test_basic(test_gen_lh5, tmptestdir):
     assert ak.all(hits.evtid[0] == [0, 0])
     assert ak.all(hits.evtid[1] == [1, 1, 1])
 
+    assert len(hits) == 2
+
     # test in memory
 
-    hits, time_dict = reboost.build_hit.build_hit(
+    hits, time_dict = reboost.build_hit(
         f"{Path(__file__).parent}/configs/basic.yaml",
         args={},
         stp_files=test_gen_lh5,
@@ -158,6 +160,25 @@ def test_basic(test_gen_lh5, tmptestdir):
     assert set(time_dict["geds"]["expressions"].keys()) == {"t0", "first_evtid", "energy"}
 
 
+def test_file_merging(test_gen_lh5, tmptestdir):
+    outfile = f"{tmptestdir}/basic_hit_merged.lh5"
+
+    reboost.build_hit(
+        f"{Path(__file__).parent}/configs/basic.yaml",
+        args={},
+        stp_files=[test_gen_lh5, test_gen_lh5],
+        glm_files=None,
+        hit_files=outfile,
+        overwrite=True,
+    )
+
+    assert lh5.ls(outfile) == ["hit", "vtx"]
+
+    hits = lh5.read("hit/det1", outfile).view_as("ak")
+
+    assert len(hits) == 4
+
+
 def test_full_chain(test_gen_lh5, tmptestdir):
     args = dbetto.AttrsDict(
         {
@@ -166,7 +187,7 @@ def test_full_chain(test_gen_lh5, tmptestdir):
         }
     )
 
-    _, time_dict = reboost.build_hit.build_hit(
+    _, time_dict = reboost.build_hit(
         f"{Path(__file__).parent}/configs/hit_config.yaml",
         args=args,
         stp_files=test_gen_lh5,