legend-dataflow-scripts 0.2.4__py3-none-any.whl → 0.3.0a2__py3-none-any.whl

{legend_dataflow_scripts-0.2.4.dist-info → legend_dataflow_scripts-0.3.0a2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: legend-dataflow-scripts
-Version: 0.2.4
+Version: 0.3.0a2
 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-0.2.4.dist-info → legend_dataflow_scripts-0.3.0a2.dist-info}/RECORD

@@ -1,13 +1,13 @@
 legenddataflowscripts/__init__.py,sha256=hlpvTxSBjOyXlZUyOyYx3VwT5LS6zNzhAZnTmfT3NjU,303
-legenddataflowscripts/_version.py,sha256=NRw4Jle4n9v_DD2wtplRqflGCvX8OU5eAjycYY0vY3Y,704
+legenddataflowscripts/_version.py,sha256=pJ82jXLrlPbvRihDFN5QbVZSY5eoLHiYmzrB4vIro6o,712
 legenddataflowscripts/par/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 legenddataflowscripts/par/geds/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 legenddataflowscripts/par/geds/dsp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 legenddataflowscripts/par/geds/dsp/dplms.py,sha256=GIMQo_qiI-ga5zsdf3oDnxjDzw5T6gqVCQob-Mf2Pvw,5376
-legenddataflowscripts/par/geds/dsp/eopt.py,sha256=epnkSddyzI0sXwPyA8gJxoRumGubv3tQpa2J_uRusV8,13615
-legenddataflowscripts/par/geds/dsp/evtsel.py,sha256=tyF5sCovm22w0Rdd9vD8NyzM2ym8AGO8IR9oKQFYAWA,17296
-legenddataflowscripts/par/geds/dsp/nopt.py,sha256=l3Z5RqPM4my6xSTG78zmjQIorCwGLMP-ipTbNOauWFY,3977
-legenddataflowscripts/par/geds/dsp/pz.py,sha256=l9nc3MmSjghmYOR3LBbbGZMnHc52MFy5F7EOnYAPqvc,8062
+legenddataflowscripts/par/geds/dsp/eopt.py,sha256=yTxzt7gNNRxYz8OvULaLPx59UgTV3NTCiGgstF3myes,13635
+legenddataflowscripts/par/geds/dsp/evtsel.py,sha256=VLkrLGedQUSjFptred7cWZ9L_qNdIU5V4BXF_uA37Gs,17658
+legenddataflowscripts/par/geds/dsp/nopt.py,sha256=uJlQreX7F6vHH69GCMQL_mGyGd-BL376UknX83X8_8M,3971
+legenddataflowscripts/par/geds/dsp/pz.py,sha256=PrXrYv5OO-CMrm6Np9Y-jrXaIIZoiKWvGPqsEgGSTSc,8056
 legenddataflowscripts/par/geds/dsp/svm.py,sha256=eDneRB_PQZp8Q4n2VheTX3kbu4ufZQ-jnuCCjvtwFpk,826
 legenddataflowscripts/par/geds/dsp/svm_build.py,sha256=w5-vT6rXmpl7V9rdkfc7_g6GTzn86i41tHkIT-3f5YI,1931
 legenddataflowscripts/par/geds/hit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -16,13 +16,13 @@ legenddataflowscripts/par/geds/hit/ecal.py,sha256=Ki1YGzFYMcQhh2S2VgNs1ApkMjJjGV
 legenddataflowscripts/par/geds/hit/lq.py,sha256=aY2tRwbTI9U7b5bxwDohQitY-Tuhe1tXdAA5dqeaznc,11264
 legenddataflowscripts/par/geds/hit/qc.py,sha256=j3oWN28zfGrR_WMMZMGWJ46dpegKf38Fq8J3zH815sU,12606
 legenddataflowscripts/tier/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-legenddataflowscripts/tier/dsp.py,sha256=J_ABEqbQurZHJOg8LV2aporNjZQpPg2bDZG6DkmuAL4,8633
+legenddataflowscripts/tier/dsp.py,sha256=SM5OVYunITFWQSkMGp5ydDnQhDtCBVTQp7jRN9gjXjY,8910
 legenddataflowscripts/tier/hit.py,sha256=-LCfsqYAYPAuN2OKbPuh4G2P5B4uA4YmQGcqUtbZxis,4989
 legenddataflowscripts/utils/__init__.py,sha256=NPpxqapio8CeQIbG8gYnz-OPoUbOlDT6tjXV-lJrKWc,426
 legenddataflowscripts/utils/alias_table.py,sha256=Im1jYnyt5pWEh8jvF_PxSi6Ur3c0E7nM62MMC-c01zE,1620
 legenddataflowscripts/utils/cfgtools.py,sha256=_1yxw_eJ08AihONhJ9sWet5HQZpOagj8Yg8y9LS3zX4,381
 legenddataflowscripts/utils/convert_np.py,sha256=qw-pX9345lhzLAwERLjEJtnikzAWWIeD9lyDre2n9P0,853
-legenddataflowscripts/utils/log.py,sha256=RnwUSgSxH7uK_I26rARwnIE_2R0vEvix8Nv_WjmxOGA,2437
+legenddataflowscripts/utils/log.py,sha256=gHG-0K0I1p-5iB6JSvCkvM8_M0a91GsKW7XfSy4bmho,4028
 legenddataflowscripts/utils/plot_dict.py,sha256=6f2ZB8J1GNAGfldQjgl1gkKMDcqPo1W7Y2Zhxm9NaGI,472
 legenddataflowscripts/utils/pulser_removal.py,sha256=kuARdp1jf-lsUWcb0_KRDp-ZXzkHNrDCXUc3h7TJm7Q,424
 legenddataflowscripts/workflow/__init__.py,sha256=JhudKYhBT8bXtX4LCqxQCHzUiITpugAtFxePWEtphC4,474
@@ -30,8 +30,8 @@ legenddataflowscripts/workflow/execenv.py,sha256=qTG4N9ovEPxA0QtqG0wWUIuK50BZIcY
 legenddataflowscripts/workflow/filedb.py,sha256=6scz8DjdvbXs8OXOy2-6BJWVSALQzmy5cLLn-OsdXsU,3656
 legenddataflowscripts/workflow/pre_compile_catalog.py,sha256=cEK0KXh-ClSE2Bo9MK471o79XG22bMY5r-2tIihtCfk,790
 legenddataflowscripts/workflow/utils.py,sha256=VVCsj7wNaqV6sw2Xnk_xykhVv3BKTX4hqQtKE4UUayg,3170
-legend_dataflow_scripts-0.2.4.dist-info/METADATA,sha256=vQ9uxbFCQUTNbkVqZlpOVWKOnKxnKj8Ew-b8e6Zr4O0,3085
-legend_dataflow_scripts-0.2.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-legend_dataflow_scripts-0.2.4.dist-info/entry_points.txt,sha256=B197waSm-orA_ZS-9rkxNDsmOHdCn8CbWodnlqXQKRg,1313
-legend_dataflow_scripts-0.2.4.dist-info/top_level.txt,sha256=s8E2chjJNYUbrN6whFG_VCsJKySFp1IOXLcUefA7DB0,22
-legend_dataflow_scripts-0.2.4.dist-info/RECORD,,
+legend_dataflow_scripts-0.3.0a2.dist-info/METADATA,sha256=JsHhX3p6jO9vLRUTG-4v4tXtYrxRljBTH2LHVCjrZjc,3091
+legend_dataflow_scripts-0.3.0a2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+legend_dataflow_scripts-0.3.0a2.dist-info/entry_points.txt,sha256=B197waSm-orA_ZS-9rkxNDsmOHdCn8CbWodnlqXQKRg,1313
+legend_dataflow_scripts-0.3.0a2.dist-info/top_level.txt,sha256=s8E2chjJNYUbrN6whFG_VCsJKySFp1IOXLcUefA7DB0,22
+legend_dataflow_scripts-0.3.0a2.dist-info/RECORD,,

legenddataflowscripts/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.2.4'
-__version_tuple__ = version_tuple = (0, 2, 4)
+__version__ = version = '0.3.0a2'
+__version_tuple__ = version_tuple = (0, 3, 0, 'a2')
 
 __commit_id__ = commit_id = None

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)

legenddataflowscripts/par/geds/dsp/evtsel.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import argparse
 import json
+import sys
 import time
 import warnings
 from bisect import bisect_left
@@ -12,9 +13,9 @@ 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
 
@@ -99,6 +100,12 @@ def par_geds_dsp_evtsel() -> None:
         required=False,
     )
 
+    argparser.add_argument(
+        "--channel",
+        type=str,
+        help="Channel to process; required if --raw-cal-curve is set",
+        required="--raw-cal-curve" in sys.argv,
+    )
     argparser.add_argument("--log", help="log_file", type=str)
 
     argparser.add_argument(
@@ -247,7 +254,7 @@ 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 +304,10 @@ 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 +405,10 @@ 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"],

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(

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:

legenddataflowscripts/tier/dsp.py

@@ -95,6 +95,8 @@ def build_tier_dsp() -> None:
         # check if the raw tables are all existing
         if len(lh5.ls(args.input, input_tbl_name)) > 0:
             dsp_cfg_tbl_dict[input_tbl_name] = Props.read_from(file)
+            msg = f"found table {input_tbl_name} in {args.input}"
+            log.debug(msg)
         else:
             msg = f"table {input_tbl_name} not found in {args.input} skipping"
             log.info(msg)
@@ -145,8 +147,10 @@ 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],
+                "lh5_tables": list(config.keys()),
+                "base_group": "",
                 "chan_config": config,
                 "database": database_dict,
                 "write_mode": "r",
@@ -171,8 +175,10 @@ def build_tier_dsp() -> None:
 
     else:
         build_dsp(
-            args.input,
-            args.output,
+            raw_in=args.input,
+            dsp_out=args.output,
+            lh5_tables=list(dsp_cfg_tbl_dict.keys()),
+            base_group="",
             database=database_dict,
             chan_config=dsp_cfg_tbl_dict,
             write_mode="r",

legenddataflowscripts/utils/log.py

@@ -26,7 +26,7 @@ class StreamToLogger:
 
 
 def build_log(
-    config_dict: dict, log_file: str | None = None, fallback: str = "prod"
+    config_dict: dict | str, log_file: str | None = None, fallback: str = "prod"
 ) -> logging.Logger:
     """Build a logger from a configuration dictionary.
 
@@ -39,10 +39,22 @@ def build_log(
     log_file
         The path to the log file.
     """
-    if isinstance(config_dict, str | dict):
+    # Accept either:
+    # - a str pointing to a logging properties file
+    # - a plain logging dict (handlers/formatters/etc.)
+    # - a dict already containing "options" -> {"logging": ...}
+    # If a dict is provided and it already contains an "options" key, assume
+    # caller set options explicitly (so we must not wrap it).
+    if isinstance(config_dict, str) or (
+        isinstance(config_dict, dict) and "options" not in config_dict
+    ):
         config_dict = {"options": {"logging": config_dict}}
 
-    if "logging" in config_dict["options"]:
+    if (
+        isinstance(config_dict, dict)
+        and "options" in config_dict
+        and "logging" in config_dict["options"]
+    ):
         log_config = config_dict["options"]["logging"]
         # if it's a str, interpret it as a path to a file
         if isinstance(log_config, str):
@@ -50,7 +62,29 @@ def build_log(
 
         if log_file is not None:
             Path(log_file).parent.mkdir(parents=True, exist_ok=True)
-            log_config["handlers"]["dataflow"]["filename"] = log_file
+            # Ensure the logging config has a handlers->dataflow entry; create
+            # minimal structure if needed so we can set the filename.
+            if isinstance(log_config, dict):
+                handlers = log_config.setdefault("handlers", {})
+                dataflow = handlers.setdefault("dataflow", {})
+                # Set the filename for the dataflow handler
+                dataflow["filename"] = log_file
+                dataflow.setdefault("class", "logging.FileHandler")
+                dataflow.setdefault("level", "INFO")
+                log_config.setdefault("version", 1)
+                if (
+                    "handlers" in log_config
+                    and "dataflow" in log_config["handlers"]
+                    and "root" not in log_config
+                    and "loggers" not in log_config
+                ):
+                    dataflow_level = log_config["handlers"]["dataflow"].get(
+                        "level", "INFO"
+                    )
+                    log_config["root"] = {
+                        "level": dataflow_level,
+                        "handlers": ["dataflow"],
+                    }
 
         dictConfig(log_config)
         log = logging.getLogger(config_dict["options"].get("logger", "prod"))