legend-dataflow-scripts 0.2.3__tar.gz → 0.3.0a1__tar.gz

{legend_dataflow_scripts-0.2.3/src/legend_dataflow_scripts.egg-info → legend_dataflow_scripts-0.3.0a1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: legend-dataflow-scripts
-Version: 0.2.3
+Version: 0.3.0a1
 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
@@ -19,10 +19,10 @@ Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 Requires-Dist: colorlog
 Requires-Dist: dbetto>=1.2.3
-Requires-Dist: pygama>=2.1
-Requires-Dist: dspeed>=1.6
+Requires-Dist: pygama>=2.3.0a1
+Requires-Dist: dspeed>=2.0
 Requires-Dist: pylegendmeta>=1.2.5
-Requires-Dist: legend-pydataobj>=1.11
+Requires-Dist: legend-pydataobj>=1.16
 Requires-Dist: pip
 Provides-Extra: test
 Requires-Dist: legend-dataflow-scripts; extra == "test"

{legend_dataflow_scripts-0.2.3 → legend_dataflow_scripts-0.3.0a1}/pyproject.toml

@@ -52,10 +52,10 @@ dynamic = ["version"]
 dependencies = [
     "colorlog",
     "dbetto>=1.2.3",
-    "pygama>=2.1",
-    "dspeed>=1.6",
+    "pygama>=2.3.0a1",
+    "dspeed>=2.0",
     "pylegendmeta>=1.2.5",
-    "legend-pydataobj>=1.11",
+    "legend-pydataobj>=1.16",
     "pip",
 ]
 # "legend-daq2lh5 @  file:///${PROJECT_ROOT}/software/python/src/legend-daq2lh5

{legend_dataflow_scripts-0.2.3 → legend_dataflow_scripts-0.3.0a1/src/legend_dataflow_scripts.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: legend-dataflow-scripts
-Version: 0.2.3
+Version: 0.3.0a1
 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
@@ -19,10 +19,10 @@ Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 Requires-Dist: colorlog
 Requires-Dist: dbetto>=1.2.3
-Requires-Dist: pygama>=2.1
-Requires-Dist: dspeed>=1.6
+Requires-Dist: pygama>=2.3.0a1
+Requires-Dist: dspeed>=2.0
 Requires-Dist: pylegendmeta>=1.2.5
-Requires-Dist: legend-pydataobj>=1.11
+Requires-Dist: legend-pydataobj>=1.16
 Requires-Dist: pip
 Provides-Extra: test
 Requires-Dist: legend-dataflow-scripts; extra == "test"

{legend_dataflow_scripts-0.2.3 → legend_dataflow_scripts-0.3.0a1}/src/legend_dataflow_scripts.egg-info/requires.txt

@@ -1,9 +1,9 @@
 colorlog
 dbetto>=1.2.3
-pygama>=2.1
-dspeed>=1.6
+pygama>=2.3.0a1
+dspeed>=2.0
 pylegendmeta>=1.2.5
-legend-pydataobj>=1.11
+legend-pydataobj>=1.16
 pip
 
 [dev]

{legend_dataflow_scripts-0.2.3 → legend_dataflow_scripts-0.3.0a1}/src/legenddataflowscripts/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.2.3'
-__version_tuple__ = version_tuple = (0, 2, 3)
+__version__ = version = '0.3.0a1'
+__version_tuple__ = version_tuple = (0, 3, 0, 'a1')
 
-__commit_id__ = commit_id = 'g43d598320'
+__commit_id__ = commit_id = 'gc8848acbc'

{legend_dataflow_scripts-0.2.3 → legend_dataflow_scripts-0.3.0a1}/src/legenddataflowscripts/par/geds/dsp/eopt.py

@@ -10,13 +10,13 @@ import numpy as np
 import pygama.pargen.energy_optimisation as om  # noqa: F401
 import sklearn.gaussian_process.kernels as ker
 from dbetto.catalog import Props
+from dspeed import build_dsp
 from dspeed.units import unit_registry as ureg
 from lgdo import lh5
 from pygama.math.distributions import hpge_peak
 from pygama.pargen.dsp_optimize import (
     BayesianOptimizer,
     run_bayesian_optimisation,
-    run_one_dsp,
 )
 
 from ....utils import build_log
@@ -127,7 +127,7 @@ def par_geds_dsp_eopt() -> None:
 
         dsp_config["outputs"] = ["tp_99", "tp_0_est", "dt_eff"]
 
-        init_data = run_one_dsp(tb_data, dsp_config, db_dict=db_dict, verbosity=0)
+        init_data = build_dsp(raw_in=tb_data, dsp_config=dsp_config, database=db_dict)
         full_dt = (init_data["tp_99"].nda - init_data["tp_0_est"].nda)[idx_list[-1]]
         flat_val = np.ceil(1.1 * np.nanpercentile(full_dt, 99) / 100) / 10
 
@@ -193,7 +193,7 @@ def par_geds_dsp_eopt() -> None:
             msg = f"Initialising values {i + 1} : {db_dict}"
             log.info(msg)
 
-            tb_out = run_one_dsp(tb_data, dsp_config, db_dict=db_dict, verbosity=0)
+            tb_out = build_dsp(raw_in=tb_data, dsp_config=dsp_config, database=db_dict)
 
             res = fom(tb_out, kwarg_dict[0])
             results_cusp.append(res)

{legend_dataflow_scripts-0.2.3 → legend_dataflow_scripts-0.3.0a1}/src/legenddataflowscripts/par/geds/dsp/evtsel.py

@@ -12,9 +12,9 @@ import numpy as np
 import pygama.math.histogram as pgh
 import pygama.pargen.energy_cal as pgc
 from dbetto.catalog import Props
+from dspeed import build_dsp
 from lgdo import lh5
 from pygama.pargen.data_cleaning import generate_cuts, get_keys
-from pygama.pargen.dsp_optimize import run_one_dsp
 
 from ....utils import build_log, get_pulser_mask
 
@@ -247,7 +247,7 @@ def par_geds_dsp_evtsel() -> None:
         ]
 
         log.debug("Processing data")
-        tb_data = run_one_dsp(input_data, dsp_config, db_dict=db_dict)
+        tb_data = build_dsp(raw_in=input_data, dsp_config=dsp_config, database=db_dict)
 
         if cut_parameters is not None:
             cut_dict = generate_cuts(tb_data, cut_parameters)
@@ -297,8 +297,10 @@ def par_geds_dsp_evtsel() -> None:
                         peak_dict["obj_buf_start"] += n_rows_read_i
                     if peak_dict["n_rows_read"] >= 10000 or file == raw_files[-1]:
                         if "e_lower_lim" not in peak_dict:
-                            tb_out = run_one_dsp(
-                                peak_dict["obj_buf"], dsp_config, db_dict=db_dict
+                            tb_out = build_dsp(
+                                raw_in=peak_dict["obj_buf"],
+                                dsp_config=dsp_config,
+                                database=db_dict,
                             )
                             energy = tb_out[energy_parameter].nda
 
@@ -396,8 +398,10 @@ def par_geds_dsp_evtsel() -> None:
                             peak_dict["obj_buf"] is not None
                             and len(peak_dict["obj_buf"]) > 0
                         ):
-                            tb_out = run_one_dsp(
-                                peak_dict["obj_buf"], dsp_config, db_dict=db_dict
+                            tb_out = build_dsp(
+                                raw_in=peak_dict["obj_buf"],
+                                dsp_config=dsp_config,
+                                database=db_dict,
                             )
                             out_tbl, n_wfs = get_out_data(
                                 peak_dict["obj_buf"],

{legend_dataflow_scripts-0.2.3 → legend_dataflow_scripts-0.3.0a1}/src/legenddataflowscripts/par/geds/dsp/nopt.py

@@ -8,9 +8,9 @@ from pathlib import Path
 import numpy as np
 import pygama.pargen.noise_optimization as pno
 from dbetto.catalog import Props
+from dspeed import build_dsp
 from lgdo import lh5
 from pygama.pargen.data_cleaning import generate_cuts, get_cut_indexes
-from pygama.pargen.dsp_optimize import run_one_dsp
 
 from ....utils import build_log
 
@@ -73,7 +73,7 @@ def par_geds_dsp_nopt() -> None:
 
         msg = f"Select baselines {len(tb_data)}"
         log.info(msg)
-        dsp_data = run_one_dsp(tb_data, dsp_config)
+        dsp_data = build_dsp(raw_in=tb_data, dsp_config=dsp_config)
         cut_dict = generate_cuts(dsp_data, cut_dict=opt_dict.pop("cut_pars"))
         cut_idxs = get_cut_indexes(dsp_data, cut_dict)
         tb_data = lh5.read(

{legend_dataflow_scripts-0.2.3 → legend_dataflow_scripts-0.3.0a1}/src/legenddataflowscripts/par/geds/dsp/pz.py

@@ -7,9 +7,9 @@ from pathlib import Path
 
 import numpy as np
 from dbetto.catalog import Props
+from dspeed import build_dsp
 from lgdo import lh5
 from pygama.pargen.data_cleaning import get_cut_indexes
-from pygama.pargen.dsp_optimize import run_one_dsp
 from pygama.pargen.pz_correct import PZCorrect
 
 from ....utils import (
@@ -134,7 +134,7 @@ def par_geds_dsp_pz() -> None:
         if "frac" in dsp_config["outputs"]:
             dsp_config_optimise_removed["outputs"].remove("frac")
 
-        tb_out = run_one_dsp(tb_data, dsp_config_optimise_removed)
+        tb_out = build_dsp(raw_in=tb_data, dsp_config=dsp_config_optimise_removed)
         log.debug("Processed Data")
         cut_parameters = kwarg_dict.get("cut_parameters", None)
         if cut_parameters is not None:

{legend_dataflow_scripts-0.2.3 → legend_dataflow_scripts-0.3.0a1}/src/legenddataflowscripts/par/geds/hit/aoe.py

@@ -251,14 +251,13 @@ def par_geds_hit_aoe() -> None:
         ]
 
         if "dt_param" in kwarg_dict:
-            params += kwarg_dict["dt_param"]
+            params.append(kwarg_dict["dt_param"])
         else:
             params.append("dt_eff")
 
         if "dt_cut" in kwarg_dict and kwarg_dict["dt_cut"] is not None:
             cal_dict.update(kwarg_dict["dt_cut"]["cut"])
             params.append(kwarg_dict["dt_cut"]["out_param"])
-
         # load data in
         data, threshold_mask = load_data(
             files,
@@ -271,9 +270,12 @@ def par_geds_hit_aoe() -> None:
         msg = f"Loaded {len(data)} events"
         log.info(msg)
 
-        mask = get_pulser_mask(
-            pulser_file=args.pulser_file,
-        )
+        if args.pulser_file is not None:
+            mask = get_pulser_mask(
+                pulser_file=args.pulser_file,
+            )
+        else:
+            mask = np.zeros(len(threshold_mask), dtype=bool)
 
         data["is_pulser"] = mask[threshold_mask]
 

{legend_dataflow_scripts-0.2.3 → legend_dataflow_scripts-0.3.0a1}/src/legenddataflowscripts/par/geds/hit/ecal.py

@@ -532,9 +532,12 @@ def par_geds_hit_ecal() -> None:
         cal_energy_param="trapTmax",
     )
 
-    mask = get_pulser_mask(
-        pulser_file=args.pulser_file,
-    )
+    if args.pulser_file is not None:
+        mask = get_pulser_mask(
+            pulser_file=args.pulser_file,
+        )
+    else:
+        mask = np.zeros(len(threshold_mask), dtype=bool)
 
     data["is_pulser"] = mask[threshold_mask]
 

{legend_dataflow_scripts-0.2.3 → legend_dataflow_scripts-0.3.0a1}/src/legenddataflowscripts/par/geds/hit/lq.py

@@ -288,9 +288,12 @@ def par_geds_hit_lq() -> None:
         msg = f"Loaded {len(data)} events"
         log.info(msg)
 
-        mask = get_pulser_mask(
-            pulser_file=args.pulser_file,
-        )
+        if args.pulser_file is not None:
+            mask = get_pulser_mask(
+                pulser_file=args.pulser_file,
+            )
+        else:
+            mask = np.zeros(len(threshold_mask), dtype=bool)
 
         data["is_pulser"] = mask[threshold_mask]
 

{legend_dataflow_scripts-0.2.3 → legend_dataflow_scripts-0.3.0a1}/src/legenddataflowscripts/par/geds/hit/qc.py

@@ -39,17 +39,18 @@ def build_qc(
 ):
     search_name = table_name if table_name[-1] == "/" else table_name + "/"
 
-    kwarg_dict_fft = config["fft_fields"]
+    kwarg_dict_fft = config.get("fft_fields", None)
     kwarg_dict_cal = config["cal_fields"]
 
     cut_fields = get_keys(
         [key.replace(search_name, "") for key in ls(cal_files[0], search_name)],
         kwarg_dict_cal["cut_parameters"],
     )
-    cut_fields += get_keys(
-        [key.replace(search_name, "") for key in ls(cal_files[0], search_name)],
-        kwarg_dict_fft["cut_parameters"],
-    )
+    if kwarg_dict_fft is not None:
+        cut_fields += get_keys(
+            [key.replace(search_name, "") for key in ls(cal_files[0], search_name)],
+            kwarg_dict_fft["cut_parameters"],
+        )
 
     if "initial_cal_cuts" in config:
         init_cal = config["initial_cal_cuts"]
@@ -147,9 +148,12 @@ def build_qc(
         cal_energy_param="trapTmax",
     )
 
-    mask = get_pulser_mask(
-        pulser_file=pulser_file,
-    )
+    if pulser_file is not None:
+        mask = get_pulser_mask(
+            pulser_file=pulser_file,
+        )
+    else:
+        mask = np.zeros(len(threshold_mask), dtype=bool)
 
     data["is_pulser"] = mask[threshold_mask]
 
@@ -289,7 +293,9 @@ def build_qc(
 def par_geds_hit_qc() -> None:
     argparser = argparse.ArgumentParser()
     argparser.add_argument("--cal-files", help="cal_files", nargs="*", type=str)
-    argparser.add_argument("--fft-files", help="fft_files", nargs="*", type=str)
+    argparser.add_argument(
+        "--fft-files", help="fft_files", nargs="*", type=str, default=[]
+    )
 
     argparser.add_argument(
         "--tcm-filelist", help="tcm_filelist", type=str, required=False

{legend_dataflow_scripts-0.2.3 → legend_dataflow_scripts-0.3.0a1}/src/legenddataflowscripts/tier/dsp.py

@@ -145,8 +145,8 @@ def build_tier_dsp() -> None:
         process_kwargs_list = []
         for i, config in enumerate(chan_configs):
             kwargs = {
-                "f_raw": args.input,
-                "f_dsp": dsp_files[i],
+                "raw_in": args.input,
+                "dsp_out": dsp_files[i],
                 "chan_config": config,
                 "database": database_dict,
                 "write_mode": "r",
@@ -171,8 +171,8 @@ def build_tier_dsp() -> None:
 
     else:
         build_dsp(
-            args.input,
-            args.output,
+            raw_in=args.input,
+            dsp_out=args.output,
             database=database_dict,
             chan_config=dsp_cfg_tbl_dict,
             write_mode="r",