legend-dataflow-scripts 0.1.3__tar.gz → 0.1.5__tar.gz

{legend_dataflow_scripts-0.1.3/src/legend_dataflow_scripts.egg-info → legend_dataflow_scripts-0.1.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: legend-dataflow-scripts
-Version: 0.1.3
+Version: 0.1.5
 Summary: Python package for the processing scripts for LEGEND-200 data
 Author-email: George Marshall <ggmarsh@uw.edu>, Luigi Pertoldi <gipert@pm.me>
 Maintainer: The LEGEND Collaboration

{legend_dataflow_scripts-0.1.3 → legend_dataflow_scripts-0.1.5/src/legend_dataflow_scripts.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: legend-dataflow-scripts
-Version: 0.1.3
+Version: 0.1.5
 Summary: Python package for the processing scripts for LEGEND-200 data
 Author-email: George Marshall <ggmarsh@uw.edu>, Luigi Pertoldi <gipert@pm.me>
 Maintainer: The LEGEND Collaboration

{legend_dataflow_scripts-0.1.3 → legend_dataflow_scripts-0.1.5}/src/legenddataflowscripts/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.1.3'
-__version_tuple__ = version_tuple = (0, 1, 3)
+__version__ = version = '0.1.5'
+__version_tuple__ = version_tuple = (0, 1, 5)

{legend_dataflow_scripts-0.1.3 → legend_dataflow_scripts-0.1.5}/src/legenddataflowscripts/par/geds/dsp/eopt.py

@@ -23,7 +23,10 @@ from pygama.pargen.dsp_optimize import (
 from ....utils import build_log
 
 warnings.filterwarnings(action="ignore", category=RuntimeWarning)
-warnings.filterwarnings(action="ignore", category=np.exceptions.RankWarning)
+try:
+    warnings.filterwarnings(action="ignore", category=np.exceptions.RankWarning)
+except AttributeError:  # np < 2
+    warnings.filterwarnings(action="ignore", category=np.RankWarning)
 
 
 def par_geds_dsp_eopt() -> None:

{legend_dataflow_scripts-0.1.3 → legend_dataflow_scripts-0.1.5}/src/legenddataflowscripts/par/geds/hit/aoe.py

@@ -297,6 +297,7 @@ def par_geds_hit_aoe() -> None:
     else:
         aoe = None
         plot_dict = out_plot_dict
+        results_dict = {}
 
     if args.plot_file:
         common_dict = plot_dict.pop("common") if "common" in list(plot_dict) else None

{legend_dataflow_scripts-0.1.3 → legend_dataflow_scripts-0.1.5}/src/legenddataflowscripts/par/geds/hit/ecal.py

@@ -33,7 +33,10 @@ mpl.use("agg")
 sto = lh5.LH5Store()
 
 warnings.filterwarnings(action="ignore", category=RuntimeWarning)
-warnings.filterwarnings(action="ignore", category=np.exceptions.RankWarning)
+try:
+    warnings.filterwarnings(action="ignore", category=np.exceptions.RankWarning)
+except AttributeError:  # np < 2
+    warnings.filterwarnings(action="ignore", category=np.RankWarning)
 
 
 def plot_2614_timemap(
@@ -485,7 +488,7 @@ def par_geds_hit_ecal() -> None:
         msg = "invalid tier"
         raise ValueError(msg)
 
-    build_log(config_dict, args.log)
+    log = build_log(config_dict, args.log)
 
     chmap = LegendMetadata(args.metadata).channelmap(
         args.timestamp, system=args.datatype
@@ -575,14 +578,23 @@ def par_geds_hit_ecal() -> None:
     ):
         e_uncal = data.query(selection_string)[energy_param].to_numpy()
 
-        hist, bins, bar = pgh.get_hist(
-            e_uncal[
-                (e_uncal > np.nanpercentile(e_uncal, 95))
-                & (e_uncal < np.nanpercentile(e_uncal, 99.9))
-            ],
-            dx=1,
-            range=[np.nanpercentile(e_uncal, 95), np.nanpercentile(e_uncal, 99.9)],
-        )
+        if len(e_uncal) > 0:
+            if isinstance(e_uncal[0], np.ndarray | list):
+                e_uncal = np.concatenate([arr for arr in e_uncal if len(arr) > 0])
+            hist, bins, _ = pgh.get_hist(
+                e_uncal[
+                    (e_uncal > np.nanpercentile(e_uncal, 95))
+                    & (e_uncal < np.nanpercentile(e_uncal, 99.9))
+                ],
+                dx=1,
+                range=[
+                    np.nanpercentile(e_uncal, 95),
+                    np.nanpercentile(e_uncal, 99.9),
+                ],
+            )
+        else:
+            msg = f"e_uncal should not be empty! energy_param: {energy_param}"
+            raise ValueError(msg)
 
         guess = 2614.511 / bins[np.nanargmax(hist)]
         full_object_dict[cal_energy_param] = HPGeCalibration(
@@ -644,8 +656,21 @@ def par_geds_hit_ecal() -> None:
             interp_energy_kev={"Qbb": 2039.0},
         )
 
+        energy = data[energy_param].to_numpy()
+        if isinstance(energy[0], np.ndarray | list):
+            energy = np.concatenate(energy)
+
+        if len(energy) < len(data):
+            log.warning("len(energy) and len(data) are not the same")
+            energy = np.pad(
+                energy, (0, len(data) - len(energy)), constant_values=np.nan
+            )
+
+        if len(data) < len(energy):
+            energy = energy[: len(data)]
+
         data[cal_energy_param] = nb_poly(
-            data[energy_param].to_numpy(), full_object_dict[cal_energy_param].pars
+            energy, full_object_dict[cal_energy_param].pars
         )
 
         results_dict[cal_energy_param] = get_results_dict(

{legend_dataflow_scripts-0.1.3 → legend_dataflow_scripts-0.1.5}/src/legenddataflowscripts/par/geds/hit/lq.py

@@ -295,7 +295,7 @@ def par_geds_hit_lq() -> None:
 
         data["run_timestamp"] = args.timestamp
 
-        out_dicts, eres_dicts, plot_dicts, lq_dict = run_lq_calibration(
+        out_dicts, results_dicts, plot_dicts, lq_dict = run_lq_calibration(
             data,
             cal_dicts={args.timestamp: cal_dict},
             results_dicts={args.timestamp: eres_dict},
@@ -305,12 +305,13 @@ def par_geds_hit_lq() -> None:
             debug_mode=args.debug,
         )
         cal_dict = out_dicts[args.timestamp]
-        eres_dict = eres_dicts[args.timestamp]
+        results_dict = results_dicts[args.timestamp]
         plot_dict = plot_dicts[args.timestamp]
         lq = lq_dict[args.timestamp]
 
     else:
         lq = None
+        results_dict = {}
 
     if args.plot_file:
         Path(args.plot_file).parent.mkdir(parents=True, exist_ok=True)
@@ -320,7 +321,7 @@ def par_geds_hit_lq() -> None:
     final_hit_dict = convert_dict_np_to_float(
         {
             "pars": {"operations": cal_dict},
-            "results": dict(**ecal_dict["results"], lq=eres_dict),
+            "results": dict(**ecal_dict["results"], lq=results_dict),
         }
     )
     Path(args.hit_pars).parent.mkdir(parents=True, exist_ok=True)

{legend_dataflow_scripts-0.1.3 → legend_dataflow_scripts-0.1.5}/src/legenddataflowscripts/par/geds/hit/qc.py

@@ -129,6 +129,7 @@ def build_qc(
     else:
         hit_dict_fft = {}
         plot_dict_fft = {}
+        fft_data = None
 
     if overwrite is not None:
         for name in kwarg_dict_fft["cut_parameters"]:
@@ -234,7 +235,7 @@ def build_qc(
         exp = info["expression"]
         for key in info.get("parameters", None):
             exp = re.sub(f"(?<![a-zA-Z0-9]){key}(?![a-zA-Z0-9])", f"@{key}", exp)
-        if outname not in fft_data:
+        if fft_data is not None and outname not in fft_data:
             fft_data[outname] = fft_data.eval(
                 exp, local_dict=info.get("parameters", None)
             )
@@ -251,24 +252,34 @@ def build_qc(
                 ((sf_cal) * (1 - sf_cal))
                 / len(data.query("~is_pulser & ~is_recovering"))
             )
-            sf_fft = len(fft_data.query(f"{entry} & ~is_recovering")) / len(
-                fft_data.query("~is_recovering")
-            )
-            sf_fft_err = 100 * np.sqrt(
-                ((sf_fft) * (1 - sf_fft)) / len(fft_data.query("~is_recovering"))
-            )
             sf_cal *= 100
-            sf_fft *= 100
-
-            msg = f"{entry} cut applied: {sf_cal:.2f}% of events passed the cut for cal data, {sf_fft:.2f}% for fft data"
+            msg = f"{entry} cut applied: {sf_cal:.2f}% of events passed the cut for cal data"
             log.info(msg)
+
             qc_results[entry] = {
                 "sf_cal": sf_cal,
                 "sf_cal_err": sf_cal_err,
-                "sf_fft": sf_fft,
-                "sf_fft_err": sf_fft_err,
             }
 
+            if fft_data is not None:
+                sf_fft = len(fft_data.query(f"{entry} & ~is_recovering")) / len(
+                    fft_data.query("~is_recovering")
+                )
+                sf_fft_err = 100 * np.sqrt(
+                    ((sf_fft) * (1 - sf_fft)) / len(fft_data.query("~is_recovering"))
+                )
+                sf_fft *= 100
+                msg = f"{entry} cut applied: {sf_fft:.2f}% of events passed the cut for fft data"
+
+                log.info(msg)
+
+                qc_results[entry].update(
+                    {
+                        "sf_fft": sf_fft,
+                        "sf_fft_err": sf_fft_err,
+                    }
+                )
+
     out_dict = convert_dict_np_to_float(
         {"operations": hit_dict, "results": {"qc": qc_results}}
     )

{legend_dataflow_scripts-0.1.3 → legend_dataflow_scripts-0.1.5}/src/legenddataflowscripts/utils/alias_table.py

@@ -1,11 +1,12 @@
 from __future__ import annotations
 
 import json
+from pathlib import Path
 
 import h5py
 
 
-def alias_table(file, mapping):
+def alias_table(file: str | Path, mapping: str):
     """
     Create an alias table for the given file and mapping.
 
@@ -13,11 +14,12 @@ def alias_table(file, mapping):
         file (str): Path to the input file.
         mapping (dict): Mapping of current table name and alias table name.
 
-    Returns:
-        dict: A dictionary containing the alias table.
     """
     if isinstance(mapping, str):
         mapping = json.loads(mapping)
+    if isinstance(mapping, list):
+        for m in mapping:
+            alias_table(file, m)
     with h5py.File(file, "a") as f:
         for raw_id, alias in mapping.items():
             if raw_id in f:

{legend_dataflow_scripts-0.1.3 → legend_dataflow_scripts-0.1.5}/src/legenddataflowscripts/utils/convert_np.py

@@ -24,7 +24,7 @@ def convert_dict_np_to_float(dic: dict) -> dict:
             convert_dict_np_to_float(value)
         elif isinstance(value, np.float32 | np.float64):
             dic[key] = float(value)
-        elif isinstance(dic[key], Sequence):
+        elif isinstance(dic[key], Sequence) and not isinstance(dic[key], str):
             dic[key] = [
                 float(x) if isinstance(x, np.float32 | np.float64) else x for x in value
             ]

{legend_dataflow_scripts-0.1.3 → legend_dataflow_scripts-0.1.5}/src/legenddataflowscripts/workflow/__init__.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 from .execenv import execenv_prefix, execenv_pyexe
+from .pre_compile_catalog import pre_compile_catalog
 from .utils import (
     as_ro,
     set_last_rule_name,
@@ -13,6 +14,7 @@ __all__ = [
     "as_ro",
     "execenv_prefix",
     "execenv_pyexe",
+    "pre_compile_catalog",
     "set_last_rule_name",
     "subst_vars",
     "subst_vars_impl",