Merge branch 'master' into remove_cmt_urls

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 3.0.0
+current_version = 3.0.1
 files = straxen/__init__.py
 commit = True
 tag = True

.gitignore

@@ -74,3 +74,6 @@ docs/source/reference/data_kinds*
 docs/source/reference/release_notes.rst
 
 test_dict.json
+
+*.pkl
+*.pkl.gz

HISTORY.md

@@ -1,3 +1,42 @@
+3.0.1 / 2024-12-27
+-------------------
+* Fix run_doc for led plugin by @GiovanniVolta in https://github.com/XENONnT/straxen/pull/1462
+* Check RSE in `_find` method of `RucioRemoteFrontend` by @dachengx in https://github.com/XENONnT/straxen/pull/1464
+* Garbage collection after calculated each chunk in `peak_positions_mlp` by @dachengx in https://github.com/XENONnT/straxen/pull/1467
+* Enforce stable sorting in `np.sort` and `np.argsort` by @dachengx in https://github.com/XENONnT/straxen/pull/1468
+* Clean `deprecate_kwarg` by @dachengx in https://github.com/XENONnT/straxen/pull/1470
+* Update strax version to v2.0.1 by @dachengx in https://github.com/XENONnT/straxen/pull/1473
+* Remove expedients plugins because SOM will be default by @dachengx in https://github.com/XENONnT/straxen/pull/1472
+* Remove 1T related codes by @dachengx in https://github.com/XENONnT/straxen/pull/1476
+* Use SOM peaklets classification by default by @dachengx in https://github.com/XENONnT/straxen/pull/1471
+* Fix theta uncertainty bug by @napoliion in https://github.com/XENONnT/straxen/pull/1466
+* Remove URLConfig warning about sorting by @dachengx in https://github.com/XENONnT/straxen/pull/1477
+* Merge branch 'sr1_leftovers' into master by @dachengx in https://github.com/XENONnT/straxen/pull/1478
+* Fix small bug in CNF by @dachengx in https://github.com/XENONnT/straxen/pull/1479
+* Remove GCN & CNN S2 pos-rec by @dachengx in https://github.com/XENONnT/straxen/pull/1484
+* Set CNF as the default S2 (x, y) position-reconstruction by @dachengx in https://github.com/XENONnT/straxen/pull/1486
+* Prototype of peaklets-level (x, y) S2 position reconstruction by @dachengx in https://github.com/XENONnT/straxen/pull/1482
+* Rename old `PeakletClassification` as `PeakletClassificationVanilla` by @dachengx in https://github.com/XENONnT/straxen/pull/1487
+* Remove Bayes models by @dachengx in https://github.com/XENONnT/straxen/pull/1488
+* Rename `defualt_run_comments` -> `default_run_comments` by @dachengx in https://github.com/XENONnT/straxen/pull/1489
+* Accelerate Euclidean distance by numba by @dachengx in https://github.com/XENONnT/straxen/pull/1493
+* Move `set_nan_defaults` to be a stand-alone function by @dachengx in https://github.com/XENONnT/straxen/pull/1497
+* Set CNF as the default S2 (x, y) position-reconstruction by @dachengx in https://github.com/XENONnT/straxen/pull/1494
+* Back to fixed window in LED calibration by @GiovanniVolta in https://github.com/XENONnT/straxen/pull/1499
+* Move `compute_center_times` from straxen to strax by @dachengx in https://github.com/XENONnT/straxen/pull/1501
+* Use numpy and strax native dtypes, not `"<i8"` or `"<f4"` by @dachengx in https://github.com/XENONnT/straxen/pull/1502
+* Inherit `area_fraction_top`, `center_time` and `median_time` from peaklets by @dachengx in https://github.com/XENONnT/straxen/pull/1503
+* Bump version of changed plugins in #1503 by @dachengx in https://github.com/XENONnT/straxen/pull/1504
+* Clean unnecessary codes by @dachengx in https://github.com/XENONnT/straxen/pull/1507
+* Clean chunk after computing `records` by @dachengx in https://github.com/XENONnT/straxen/pull/1508
+* Add a line of comment about memory optimization by @dachengx in https://github.com/XENONnT/straxen/pull/1509
+
+New Contributors
+* @napoliion made their first contribution in https://github.com/XENONnT/straxen/pull/1466
+
+**Full Changelog**: https://github.com/XENONnT/straxen/compare/v3.0.0...v3.0.1
+
+
 3.0.0 / 2024-10-24
 -------------------
 * Inherit `DEFAULT_CHUNK_SPLIT_NS` from strax by @dachengx in https://github.com/XENONnT/straxen/pull/1405

pyproject.toml

@@ -1,7 +1,7 @@
 [tool]
 [tool.poetry]
 name = "straxen"
-version = "3.0.0"
+version = "3.0.1"
 description = "Streaming analysis for XENON"
 readme = "README.md"
 authors = [
@@ -30,7 +30,7 @@ straxer = "straxen.scripts.straxer:main"
 
 [tool.poetry.dependencies]
 python = ">=3.9,<3.13"
-strax = ">=2.0.1"
+strax = ">=2.0.3"
 bokeh = "*"
 commentjson = "*"
 gitpython = "*"

straxen/__init__.py

@@ -1,5 +1,5 @@
 # mypy: disable-error-code="no-redef"
-__version__ = "3.0.0"
+__version__ = "3.0.1"
 
 from utilix import uconfig
 from .common import *

straxen/analyses/bokeh_waveform_plot.py

@@ -101,7 +101,7 @@ def event_display_interactive(
         raise ValueError("Found an event without peaks this should not had have happened.")
 
     # Select main/alt S1/S2s based on time and endtime in event:
-    m_other_peaks = np.ones(len(peaks), dtype=np.bool_)  # To select non-event peaks
+    m_other_peaks = np.ones(len(peaks), dtype=bool)  # To select non-event peaks
     endtime = strax.endtime(peaks)
 
     signal = {}
@@ -570,7 +570,7 @@ def plot_pmt_array(
     # Plotting PMTs:
     pmts = straxen.pmt_positions()
     if plot_all_pmts:
-        mask_pmts = np.zeros(len(pmts), dtype=np.bool_)
+        mask_pmts = np.zeros(len(pmts), dtype=bool)
     else:
         mask_pmts = to_pe == 0
     pmts_on = pmts[~mask_pmts]

straxen/analyses/waveform_plot.py

@@ -191,7 +191,7 @@ def plot_records_matrix(
         # labels in the case of strings.
         # Make a dict that converts the label to an int
         int_labels = {h: i for i, h in enumerate(set(ylabs))}
-        mask = np.ones(len(ylabs), dtype=np.bool_)
+        mask = np.ones(len(ylabs), dtype=bool)
         # If the label (int) is different wrt. its neighbour, show it
         mask[1:] = np.abs(np.diff([int_labels[y] for y in ylabs])) > 0
         # Only label the selection

straxen/config/protocols.py

@@ -65,6 +65,8 @@ def read_json(content: str, **kwargs):
 @URLConfig.register("take")
 def get_key(container: Container, take=None, **kwargs):
     """Return a single element of a container."""
+    if not isinstance(container, dict):
+        raise ValueError(f"Container is not a dict but a {type(container)}")
     if take is None:
         return container
     if not isinstance(take, list):

straxen/plugins/afterpulses/afterpulse_processing.py

@@ -421,45 +421,41 @@ def dtype_afterpulses():
     - The afterpulse datatype
 
     """
-    dtype_ap = [
-        (("Channel/PMT number", "channel"), "<i2"),
-        (("Time resolution in ns", "dt"), "<i2"),
-        (("Start time of the interval (ns since unix epoch)", "time"), "<i8"),
-        (("Length of the interval in samples", "length"), "<i4"),
-        (("Integral in ADC x samples", "area"), "<i4"),
-        (("Pulse area in PE", "area_pe"), "<f4"),
-        (("Sample index in which hit starts", "left"), "<i2"),
+    dtype_ap = strax.interval_dtype + [
+        (("Integral in ADC x samples", "area"), np.int32),
+        (("Pulse area in PE", "area_pe"), np.float32),
+        (("Sample index in which hit starts", "left"), np.int16),
         (
             (
                 "Sample index in which hit area succeeds 10% of total area",
                 "sample_10pc_area",
             ),
-            "<i2",
+            np.int16,
         ),
         (
             (
                 "Sample index in which hit area succeeds 50% of total area",
                 "sample_50pc_area",
             ),
-            "<i2",
+            np.int16,
         ),
-        (("Sample index of hit maximum", "max"), "<i2"),
+        (("Sample index of hit maximum", "max"), np.int16),
         (
             (
                 "Index of first sample in record just beyond hit (exclusive bound)",
                 "right",
             ),
-            "<i2",
+            np.int16,
         ),
-        (("Height of hit in ADC counts", "height"), "<i4"),
-        (("Height of hit in PE", "height_pe"), "<f4"),
-        (("Delay of hit w.r.t. LED hit in same WF, in samples", "tdelay"), "<i2"),
+        (("Height of hit in ADC counts", "height"), np.int32),
+        (("Height of hit in PE", "height_pe"), np.float32),
+        (("Delay of hit w.r.t. LED hit in same WF, in samples", "tdelay"), np.int16),
         (
             (
                 "Internal (temporary) index of fragment in which hit was found",
                 "record_i",
             ),
-            "<i4",
+            np.int32,
         ),
         (
             ("Index of sample in record where integration starts", "left_integration"),

straxen/plugins/events/event_basics_som.py

@@ -1,7 +1,6 @@
 import strax
-import numpy as np
-
 from straxen.plugins.events.event_basics_vanilla import EventBasicsVanilla
+from straxen.plugins.peaklets.peaklet_classification_som import som_additional_fields
 
 export, __all__ = strax.exporter()
 
@@ -17,15 +16,4 @@ def _set_dtype_requirements(self):
         # Properties to store for each peak (main and alternate S1 and S2)
         # Add here SOM types:
         super()._set_dtype_requirements()
-        self.peak_properties = list(self.peak_properties)
-        self.peak_properties += [
-            ("som_sub_type", np.int32, "SOM subtype of the peak(let)"),
-            ("old_type", np.int8, "Old type of the peak(let)"),
-            ("loc_x_som", np.int16, "x location of the peak(let) in the SOM"),
-            ("loc_y_som", np.int16, "y location of the peak(let) in the SOM"),
-        ]
-        self.peak_properties = tuple(self.peak_properties)
-
-    def compute(self, events, peaks):
-        result = super().compute(events, peaks)
-        return result
+        self.peak_properties += tuple(som_additional_fields)

straxen/plugins/events/event_basics_vanilla.py

@@ -17,7 +17,7 @@ class EventBasicsVanilla(strax.Plugin):
 
     """
 
-    __version__ = "1.3.3"
+    __version__ = "1.3.4"
 
     depends_on = ("events", "peak_basics", "peak_positions", "peak_proximity")
     provides = "event_basics"
@@ -66,9 +66,7 @@ def infer_dtype(self):
         # Basic event properties
         self._set_posrec_save()
         self._set_dtype_requirements()
-        dtype = []
-        dtype += strax.time_fields
-        dtype += [
+        dtype = strax.time_fields + [
             ("n_peaks", np.int32, "Number of peaks in the event"),
             ("drift_time", np.float32, "Drift time between main S1 and S2 in ns"),
             ("event_number", np.int64, "Event number in this dataset"),
@@ -116,7 +114,8 @@ def _set_dtype_requirements(self):
         # Properties to store for each peak (main and alternate S1 and S2)
         self.peak_properties = (
             ("time", np.int64, "start time since unix epoch [ns]"),
-            ("center_time", np.int64, "weighted center time since unix epoch [ns]"),
+            ("center_time", np.int64, "weighted average center time since unix epoch [ns]"),
+            ("median_time", np.float32, "weighted relative median time of the peak [ns]"),
             ("endtime", np.int64, "end time since unix epoch [ns]"),
             ("area", np.float32, "area, uncorrected [PE]"),
             ("n_channels", np.int16, "count of contributing PMTs"),
@@ -128,8 +127,8 @@ def _set_dtype_requirements(self):
             ("range_90p_area", np.float32, "width, 90% area [ns]"),
             ("rise_time", np.float32, "time between 10% and 50% area quantiles [ns]"),
             ("area_fraction_top", np.float32, "fraction of area seen by the top PMT array"),
-            ("tight_coincidence", np.int16, "Channel within tight range of mean"),
-            ("n_saturated_channels", np.int16, "Total number of saturated channels"),
+            ("tight_coincidence", np.int16, "channel within tight range of mean"),
+            ("n_saturated_channels", np.int16, "total number of saturated channels"),
         )
 
     def setup(self):
@@ -217,19 +216,18 @@ def compute(self, events, peaks):
         result["endtime"] = events["endtime"]
         result["event_number"] = events["event_number"]
 
-        self.fill_events(result, events, split_peaks)
+        self.fill_events(result, split_peaks)
         return result
 
     # If copy_largest_peaks_into_event is ever numbafied, also numbafy this function
-    def fill_events(self, result_buffer, events, split_peaks):
+    def fill_events(self, result_buffer, split_peaks):
         """Loop over the events and peaks within that event."""
-        for event_i, _ in enumerate(events):
-            peaks_in_event_i = split_peaks[event_i]
+        for event_i, peaks_in_event_i in enumerate(split_peaks):
             n_peaks = len(peaks_in_event_i)
             result_buffer[event_i]["n_peaks"] = n_peaks
 
             if not n_peaks:
-                raise ValueError(f"No peaks within event?\n{events[event_i]}")
+                raise ValueError(f"No peaks within event {event_i}?")
 
             self.fill_result_i(result_buffer[event_i], peaks_in_event_i)
 

straxen/plugins/events/event_top_bottom_params.py

@@ -12,7 +12,7 @@ class EventTopBottomParams(strax.Plugin):
 
     depends_on = ("event_info", "event_waveform")
     provides = "event_top_bottom_params"
-    __version__ = "0.0.0"
+    __version__ = "0.0.1"
 
     def infer_dtype(self):
         # Populating data type information
@@ -91,6 +91,9 @@ def infer_dtype(self):
 
     def compute(self, events):
         result = np.zeros(events.shape, dtype=self.dtype)
+        if not len(events):
+            return result
+
         result["time"], result["endtime"] = events["time"], strax.endtime(events)
         peak_dtype = strax.peak_dtype(n_channels=straxen.n_tpc_pmts, store_data_top=False)
         for type_ in self.ptypes:
@@ -129,15 +132,13 @@ def compute(self, events):
                 result[f"{type_}_center_time_{arr_}"][mask] += recalc_ctime[mask].astype(int)
                 # computing widths ##
                 # zero or undefined area peaks should have nans
-                strax.compute_widths(fpeaks_)
+                _, width, area_decile_from_midpoint = strax.compute_widths(fpeaks_)
                 result[f"{type_}_rise_time_{arr_}"][:] = np.nan
-                result[f"{type_}_rise_time_{arr_}"][mask] = -fpeaks_["area_decile_from_midpoint"][
-                    mask
-                ][:, 1]
+                result[f"{type_}_rise_time_{arr_}"][mask] = -area_decile_from_midpoint[mask][:, 1]
                 result[f"{type_}_range_50p_area_{arr_}"][:] = np.nan
-                result[f"{type_}_range_50p_area_{arr_}"][mask] = fpeaks_["width"][mask][:, 5]
+                result[f"{type_}_range_50p_area_{arr_}"][mask] = width[mask][:, 5]
                 result[f"{type_}_range_90p_area_{arr_}"][:] = np.nan
-                result[f"{type_}_range_90p_area_{arr_}"][mask] = fpeaks_["width"][mask][:, 9]
+                result[f"{type_}_range_90p_area_{arr_}"][mask] = width[mask][:, 9]
             # Difference between center times of top and bottom arrays
             result[f"{type_}_center_time_diff_top_bot"] = (
                 result[f"{type_}_center_time_top"] - result[f"{type_}_center_time_bot"]

straxen/plugins/events_nv/event_waveform_nv.py

@@ -11,7 +11,7 @@ class nVETOEventWaveform(strax.Plugin):
     """Plugin which computes the summed waveform as well as some shape properties of the NV
     events."""
 
-    __version__ = "0.0.1"
+    __version__ = "0.0.2"
 
     depends_on = "events_nv", "records_nv"
     provides = "event_waveform_nv"
@@ -61,7 +61,7 @@ def compute(self, events_nv, records_nv, start, end):
         _tmp_events["length"] = (events_nv["endtime"] - events_nv["time"]) // 2
         _tmp_events["dt"] = 2
         strax.simple_summed_waveform(records_nv, _tmp_events, self.to_pe)
-        strax.compute_widths(_tmp_events)
+        strax.compute_properties(_tmp_events)
 
         strax.copy_to_buffer(_tmp_events, events_waveform, "_temp_nv_evts_cpy")
         events_waveform["range_50p_area"] = _tmp_events["width"][:, 5]
@@ -75,9 +75,7 @@ def compute(self, events_nv, records_nv, start, end):
 def veto_event_waveform_dtype(
     n_samples_wf: int = 200,
 ) -> list:
-    dtype = []
-    dtype += strax.time_dt_fields  # because mutable
-    dtype += [
+    dtype = strax.time_dt_fields + [
         (("Waveform data in PE/sample (not PE/ns!)", "data"), np.float32, n_samples_wf),
         (("Width (in ns) of the central 50% area of the peak", "range_50p_area"), np.float32),
         (("Width (in ns) of the central 90% area of the peak", "range_90p_area"), np.float32),
@@ -109,6 +107,8 @@ def _temp_event_data_type(n_samples_wf: int = 150, n_widths: int = 11) -> list:
             np.float32,
             n_samples_wf,
         ),
+        (("Weighted average center time of the peak [ns]", "center_time"), np.int64),
+        (("Weighted relative median time of the peak [ns]", "median_time"), np.float32),
         (("Peak widths in range of central area fraction [ns]", "width"), np.float32, n_widths),
         (
             ("Peak widths: time between nth and 5th area decile [ns]", "area_decile_from_midpoint"),