dkist-processing-common 14.3.0__tar.gz → 14.3.1__tar.gz

{dkist_processing_common-14.3.0 → dkist_processing_common-14.3.1}/CHANGELOG.rst

@@ -1,3 +1,14 @@
+v14.3.1 (2026-05-19)
+====================
+
+Misc
+----
+
+- Migrate `_find_iqr_outliers` from the quality mixin to the `QualityL0Metrics` workflow task. (`#340 <https://bitbucket.org/dkistdc/dkist-processing-common/pull-requests/340>`__)
+- Migrate `quality_task_types` from the quality mixin to the `QualityL0Metrics` workflow task. (`#341 <https://bitbucket.org/dkistdc/dkist-processing-common/pull-requests/341>`__)
+- Migrate `_format_facet` from the quality mixin to the `QualityMetric` `BaseModel`. (`#342 <https://bitbucket.org/dkistdc/dkist-processing-common/pull-requests/342>`__)
+
+
 v14.3.0 (2026-05-19)
 ====================
 

{dkist_processing_common-14.3.0 → dkist_processing_common-14.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dkist-processing-common
-Version: 14.3.0
+Version: 14.3.1
 Summary: Common task classes used by the DKIST science data processing pipelines
 Author-email: NSO / AURA <dkistdc@nso.edu>
 License: BSD-3-Clause

{dkist_processing_common-14.3.0 → dkist_processing_common-14.3.1}/dkist_processing_common/models/quality.py

@@ -333,13 +333,28 @@ class EfficiencyData(QualityModel):
     pass
 
 
+def format_facet(v: Any) -> Any:
+    """Format the string input as a typical key.  For example, `Beam 1` becomes `BEAM_1`."""
+    if v is None:
+        return None
+    if isinstance(v, str) and v.strip() == "":
+        return None
+    return str(v).replace(" ", "_").upper()
+
+
+QualityFacet = Annotated[
+    str | None,
+    BeforeValidator(format_facet),
+]
+
+
 class QualityMetric(QualityModel):
     """Quality Metric."""
 
     name: str
     description: str
     metric_code: str
-    facet: str | None = None
+    facet: QualityFacet = None
     statement: list[str] | None = None
     plot_data: list[XYData] | None = None
     multi_plot_data: list[MultiPlotData] | None = None

{dkist_processing_common-14.3.0 → dkist_processing_common-14.3.1}/dkist_processing_common/tasks/l1_output_data.py

@@ -158,12 +158,7 @@ class TransferL1Data(TransferDataBase, GlobusMixin):
 
 
 class AssembleQualityData(L1OutputDataBase, QualityMixin):
-    """
-    Assemble quality data from the various quality metrics.
-
-    **NOTE:** Please set `~dkist_processing_common.tasks.mixin.quality.QualityMixin.quality_task_types` in any subclass
-    to the same value that was used in a subclass of `~dkist_processing_common.tasks.quality_metrics.QualityL0Metrics`.
-    """
+    """Assemble quality data from the various quality metrics."""
 
     @property
     def polcal_label_list(self) -> list[str] | None:

{dkist_processing_common-14.3.0 → dkist_processing_common-14.3.1}/dkist_processing_common/tasks/mixin/quality/_base.py

@@ -5,14 +5,11 @@ from typing import Iterable
 from dkist_processing_common.codecs.json import json_encoder
 from dkist_processing_common.codecs.quality import QualityValueEncoder
 from dkist_processing_common.models.tags import Tag
-from dkist_processing_common.models.task_name import TaskName
 from dkist_processing_common.tasks.mixin.quality._metrics import _PolcalQualityMixin
-from dkist_processing_common.tasks.mixin.quality._metrics import _SimplePlotQualityMixin
 from dkist_processing_common.tasks.mixin.quality._metrics import _WavecalQualityMixin
 
 
 class QualityMixin(
-    _SimplePlotQualityMixin,
     _PolcalQualityMixin,
     _WavecalQualityMixin,
 ):
@@ -46,16 +43,6 @@ class QualityMixin(
 
         return result
 
-    @property
-    def quality_task_types(self) -> list[str]:
-        """Task types to use in generating metrics that work on several task types."""
-        return [
-            TaskName.dark.value,
-            TaskName.gain.value,
-            TaskName.lamp_gain.value,
-            TaskName.solar_gain.value,
-        ]
-
     @property
     def quality_metrics_no_task_dependence(self) -> dict:
         """Return a dict of the quality metrics with no task dependence."""

{dkist_processing_common-14.3.0 → dkist_processing_common-14.3.1}/dkist_processing_common/tasks/mixin/quality/_metrics.py

@@ -6,8 +6,6 @@ These classes should not be directly mixed in to anything. They are pre-mixed in
 import copy
 import json
 import logging
-from datetime import datetime
-from typing import Sequence
 
 import astropy.units as u
 import numpy as np
@@ -29,39 +27,12 @@ from dkist_processing_common.models.quality import PlotRaincloud
 from dkist_processing_common.models.quality import ReportMetric
 from dkist_processing_common.models.quality import SimpleTable
 from dkist_processing_common.models.quality import VerticalMultiPanePlot2D
+from dkist_processing_common.models.quality import format_facet
 from dkist_processing_common.models.tags import Tag
 
 logger = logging.getLogger(__name__)
 
 
-class _SimplePlotQualityMixin:
-    """Mixin containing metrics that present as simple x/y plots."""
-
-    @staticmethod
-    def _find_iqr_outliers(datetimes: Sequence[datetime], values: Sequence[float]) -> list[str]:
-        """
-        Given a list of values, find values that fall more than (1.5 * iqr) outside the quartiles of the data.
-
-        Parameters
-        ----------
-        datetimes: list of datetime strings used to reference the files that are outliers
-        values: values to use to determine outliers from the iqr
-        """
-        if len(values) == 0:
-            raise ValueError("No values provided.")
-        warnings = []
-        q1 = np.quantile(values, 0.25)
-        q3 = np.quantile(values, 0.75)
-        iqr = q3 - q1
-        for i, val in enumerate(values):
-            if val < q1 - (iqr * 1.5) or val > q3 + (iqr * 1.5):
-                warnings.append(
-                    f"File with datetime {datetimes[i]} has a value considered to be an outlier "
-                    f"for this metric"
-                )
-        return warnings
-
-
 class _PolcalQualityMixin:
     """Mixin Class supporting the building of polcal-specific metrics."""
 
@@ -112,13 +83,6 @@ class _PolcalQualityMixin:
             thinning_stride=thinning_stride,
         )
 
-    @staticmethod
-    def _format_facet(label: str | None) -> str | None:
-        """Format the label as a typical key.  For example, `Beam 1` becomes `BEAM_1`."""
-        if label is None or label == "":
-            return None
-        return str(label).replace(" ", "_").upper()
-
     @staticmethod
     def _compute_thinning_stride(
         polcal_fitter: PolcalFitter, num_points_to_sample: int
@@ -340,7 +304,7 @@ class _PolcalQualityMixin:
             description="The deviation from database metrology values for Calibration Unit parameters used to compute "
             f"demodulation matrices. These parameters are fit the same across all polcal bins.",
             metric_code=MetricCode.polcal_global_par_vals,
-            facet=self._format_facet(label),
+            facet=format_facet(label),
             table_data=SimpleTable(rows=table_data),
             warnings=self._format_warnings(data["warnings"]),
         )
@@ -481,7 +445,7 @@ class _PolcalQualityMixin:
             name=f"PolCal Local Bin Fits - {label}",
             description=description,
             metric_code=MetricCode.polcal_local_par_vals,
-            facet=self._format_facet(label),
+            facet=format_facet(label),
             modmat_data=modmat_hist,
             histogram_data=param_histograms,
         )
@@ -601,7 +565,7 @@ class _PolcalQualityMixin:
             name=f"PolCal Fit Residuals - {label}",
             description=description,
             metric_code=MetricCode.polcal_fit_residuals,
-            facet=self._format_facet(label),
+            facet=format_facet(label),
             histogram_data=chisq_hist,
             raincloud_data=residual_series,
         )
@@ -675,7 +639,7 @@ class _PolcalQualityMixin:
             name=f"PolCal Modulation Efficiency - {label}",
             description=description,
             metric_code=MetricCode.polcal_efficiency,
-            facet=self._format_facet(label),
+            facet=format_facet(label),
             efficiency_data=EfficiencyHistograms(efficiency_list=data["efficiency_list"]),
             warnings=self._format_warnings(data["warnings"]),
         )

{dkist_processing_common-14.3.0 → dkist_processing_common-14.3.1}/dkist_processing_common/tasks/quality_metrics.py

@@ -5,6 +5,7 @@ from collections import defaultdict
 from datetime import datetime
 from itertools import chain
 from typing import Iterable
+from typing import Sequence
 from typing import Type
 
 import numpy as np
@@ -23,6 +24,7 @@ from dkist_processing_common.models.quality import TableData
 from dkist_processing_common.models.quality import TimeSeriesData
 from dkist_processing_common.models.quality import XYData
 from dkist_processing_common.models.tags import Tag
+from dkist_processing_common.models.task_name import TaskName
 from dkist_processing_common.parsers.l0_fits_access import L0FitsAccess
 from dkist_processing_common.parsers.quality import L1QualityFitsAccess
 from dkist_processing_common.tasks.base import WorkflowTaskBase
@@ -76,20 +78,14 @@ class QualityL0Metrics(WorkflowTaskBase, QualityMixin):
         instruments this can be left as the default `Tag.input()`, but IR cameras will probably want to set this to
         `Tag.linearized()` or similar.
 
-    `~dkist_processing_common.tasks.mixin.quality.QualityMixin.quality_task_types` (`list[str]`)
+    `quality_task_types` (`list[str]`)
         A list of IPTASK types. A separate set of L0 metrics will be reported for each task type listed here.
-        See the definition of `~dkist_processing_common.tasks.mixin.quality.QualityMixin.quality_task_types` for the
-        sensible defaults. If overloading, please use controlled `~dkist_processing_common.models.task_name.TaskName`
-        values, if possible.
+        If overloading, please use controlled `~dkist_processing_common.models.task_name.TaskName` values, if possible.
 
     `modstate_list` (`list[int] | None`)
         A list of modstates over which to separate each metric. Adding modstates does not create new metric entries, but
         does sub-divide each TASK's metric into modstate bins. If you want *all* files of a single TASK to be considered
         together return ``None`` here.
-
-    **NOTE:** The `~dkist_processing_common.tasks.mixin.quality.QualityMixin.quality_task_types` on an instrument
-    subclass of `~dkist_processing_common.tasks.l1_output_data.AssembleQualityData` should match whatever is set here
-    (although in both cases the default is probably fine).
     """
 
     @property
@@ -115,6 +111,40 @@ class QualityL0Metrics(WorkflowTaskBase, QualityMixin):
         """Define the `FitsAccess`-type class used to parse the headers of L0 frames."""
         return L0FitsAccess
 
+    @property
+    def quality_task_types(self) -> list[str]:
+        """Task types to use in generating metrics that work on several task types."""
+        return [
+            TaskName.dark.value,
+            TaskName.gain.value,
+            TaskName.lamp_gain.value,
+            TaskName.solar_gain.value,
+        ]
+
+    @staticmethod
+    def _find_iqr_outliers(datetimes: Sequence[datetime], values: Sequence[float]) -> list[str]:
+        """
+        Given a list of values, find values that fall more than (1.5 * iqr) outside the quartiles of the data.
+
+        Parameters
+        ----------
+        datetimes: list of datetime strings used to reference the files that are outliers
+        values: values to use to determine outliers from the iqr
+        """
+        if len(values) == 0:
+            raise ValueError("No values provided.")
+        warnings = []
+        q1 = np.quantile(values, 0.25)
+        q3 = np.quantile(values, 0.75)
+        iqr = q3 - q1
+        for i, val in enumerate(values):
+            if val < q1 - (iqr * 1.5) or val > q3 + (iqr * 1.5):
+                warnings.append(
+                    f"File with datetime {datetimes[i]} has a value considered to be an outlier "
+                    f"for this metric"
+                )
+        return warnings
+
     def run(self) -> None:
         """
         Calculate L0 quality metrics for all TASK/MODSTATE combinations.
@@ -316,7 +346,7 @@ class QualityL0Metrics(WorkflowTaskBase, QualityMixin):
                 name=f"Average Across Frame - {task_type.upper()}",
                 description=f"Average intensity value across frames of task type {task_type}. One measurement is taken per frame in each task type.",
                 metric_code=MetricCode.frame_average,
-                facet=task_type.upper(),
+                facet=task_type,
                 plot_data=[xy_data],
                 warnings=warnings,
             )
@@ -361,7 +391,7 @@ class QualityL0Metrics(WorkflowTaskBase, QualityMixin):
                 name=f"Root Mean Square (RMS) Across Frame - {task_type.upper()}",
                 description=f"RMS value across frames of task type {task_type}. One measurement is taken per frame in each task type.",
                 metric_code=MetricCode.frame_rms,
-                facet=task_type.upper(),
+                facet=task_type,
                 plot_data=[xy_data],
                 warnings=warnings,
             )

{dkist_processing_common-14.3.0 → dkist_processing_common-14.3.1}/dkist_processing_common/tests/test_quality.py

@@ -3,6 +3,7 @@
 from datetime import datetime
 from datetime import timedelta
 from pathlib import Path
+from typing import Any
 from typing import Sequence
 
 import numpy as np
@@ -18,6 +19,7 @@ from dkist_processing_common.codecs.fits import fits_hdulist_encoder
 from dkist_processing_common.models.quality import QualityMetric
 from dkist_processing_common.models.quality import TableData
 from dkist_processing_common.models.quality import XYData
+from dkist_processing_common.models.quality import format_facet
 from dkist_processing_common.models.tags import Tag
 from dkist_processing_common.models.task_name import TaskName
 from dkist_processing_common.tasks.quality_metrics import L0QualityData
@@ -1126,3 +1128,43 @@ def test_no_calibration_frames_no_l1_metrics(quality_l1_task_no_scratch_data: Qu
         task.read(tags=tags, decoder=basemodel_decoder, model=QualityMetric)
     )
     assert len(metrics) == 0
+
+
+def test_find_iqr_outliers(quality_l0_task):
+    """
+    Given: a list of float values
+    When: checking data for outliers
+    Then: the correct outliers are found
+    """
+    task = quality_l0_task
+    start = datetime.now()
+    datetimes = tuple([start + timedelta(milliseconds=i) for i in range(5)])
+    values = [5.1, 4.9, 9.3, 5.3, 4.9]
+    warnings = task._find_iqr_outliers(datetimes=datetimes, values=values)
+    assert warnings == [
+        f"File with datetime {datetimes[2]} has a value considered to be an outlier for this metric"
+    ]
+
+
+@pytest.mark.parametrize(
+    "label, expected_result",
+    [
+        pytest.param(None, None, id="none"),
+        pytest.param("", None, id="empty"),
+        pytest.param("abc", "ABC", id="lower"),
+        pytest.param("XYZ", "XYZ", id="upper"),
+        pytest.param("lMn", "LMN", id="mixed"),
+        pytest.param("heLLo 1  abc", "HELLO_1__ABC", id="spaces"),
+        pytest.param(0, "0", id="zero"),
+        pytest.param(1, "1", id="one"),
+        pytest.param(False, "FALSE", id="false"),
+        pytest.param("@,$#", "@,$#", id="random"),
+    ],
+)
+def test_format_facet(label: str | Any, expected_result: str):
+    """
+    Given: A label
+    When: formatting the label as a key
+    Then: the label is properly formatted
+    """
+    assert format_facet(label) == expected_result

{dkist_processing_common-14.3.0 → dkist_processing_common-14.3.1}/dkist_processing_common/tests/test_quality_mixin.py

@@ -1,6 +1,4 @@
 import json
-from datetime import datetime
-from datetime import timedelta
 from io import StringIO
 from typing import Any
 
@@ -19,6 +17,7 @@ from dkist_processing_common.codecs.quality import QualityValueEncoder
 from dkist_processing_common.models.metric_code import MetricCode
 from dkist_processing_common.models.quality import Plot2D
 from dkist_processing_common.models.quality import VerticalMultiPanePlot2D
+from dkist_processing_common.models.quality import format_facet
 from dkist_processing_common.models.tags import Tag
 from dkist_processing_common.tasks import WorkflowTaskBase
 from dkist_processing_common.tasks.mixin.quality import QualityMixin
@@ -81,22 +80,6 @@ def test_format_warnings(quality_mixin_task):
     assert warnings is None
 
 
-def test_find_iqr_outliers(quality_mixin_task):
-    """
-    Given: a task with the QualityMixin
-    When: checking data for outliers
-    Then: the correct outliers are found
-    """
-    task = quality_mixin_task
-    start = datetime.now()
-    datetimes = tuple([start + timedelta(milliseconds=i) for i in range(5)])
-    values = [5.1, 4.9, 9.3, 5.3, 4.9]
-    warnings = task._find_iqr_outliers(datetimes=datetimes, values=values)
-    assert warnings == [
-        f"File with datetime {datetimes[2]} has a value considered to be an outlier for this metric"
-    ]
-
-
 @pytest.mark.parametrize(
     "thin, samples_larger_than_total",
     [
@@ -362,7 +345,7 @@ def test_polcal_build_global_parameter_values(quality_mixin_task, polcal_global_
 
     assert metric["name"] == f"PolCal Global Calibration Unit Fit - {label}"
     assert metric["metric_code"] == "POLCAL_GLOBAL_PAR_VALS"
-    assert metric["facet"] == quality_mixin_task._format_facet(label)
+    assert metric["facet"] == format_facet(label)
     assert metric["warnings"] == ["A thing is bad"]
     metric_table = metric["table_data"]["rows"]
     assert len(metric_table) == 4  # 3 rows + one for header
@@ -416,7 +399,7 @@ def test_polcal_build_local_parameter_values(quality_mixin_task, polcal_local_pa
 
     assert metric["name"] == f"PolCal Local Bin Fits - {label}"
     assert metric["metric_code"] == "POLCAL_LOCAL_PAR_VALS"
-    assert metric["facet"] == quality_mixin_task._format_facet(label)
+    assert metric["facet"] == format_facet(label)
     assert metric["description"].endswith(
         "Data show 3 uniformly sampled points from 6 total points spanning 2 spatial and 3 radical bins."
     )
@@ -468,7 +451,7 @@ def test_polcal_build_fit_residuals(quality_mixin_task, polcal_fit_residuals_jso
 
     assert metric["name"] == f"PolCal Fit Residuals - {label}"
     assert metric["metric_code"] == "POLCAL_FIT_RESIDUALS"
-    assert metric["facet"] == quality_mixin_task._format_facet(label)
+    assert metric["facet"] == format_facet(label)
 
     assert metric["description"].endswith(
         "Data show 3 uniformly sampled points from 6 total points spanning 21 financial bins."
@@ -521,7 +504,7 @@ def test_polcal_build_efficiency(quality_mixin_task, polcal_efficiency_json):
         "Data show 33 uniformly sampled points from 99 total points spanning 2 spatial, 4 forever, and 6 smelly bins."
     )
     assert metric["metric_code"] == "POLCAL_EFFICIENCY"
-    assert metric["facet"] == quality_mixin_task._format_facet(label)
+    assert metric["facet"] == format_facet(label)
     efficiency_data = metric["efficiency_data"]
     assert efficiency_data["efficiency_list"] == [[1.0, 2.0], [2.0, 3.0]]
 
@@ -759,30 +742,6 @@ def test_compute_bin_description(
     assert result == expected_full
 
 
-@pytest.mark.parametrize(
-    "label, expected_result",
-    [
-        pytest.param(None, None, id="none"),
-        pytest.param("", None, id="empty"),
-        pytest.param("abc", "ABC", id="lower"),
-        pytest.param("XYZ", "XYZ", id="upper"),
-        pytest.param("lMn", "LMN", id="mixed"),
-        pytest.param("heLLo 1  abc", "HELLO_1__ABC", id="spaces"),
-        pytest.param(0, "0", id="zero"),
-        pytest.param(1, "1", id="one"),
-        pytest.param(False, "FALSE", id="false"),
-        pytest.param("@,$#", "@,$#", id="random"),
-    ],
-)
-def test_format_facet(label: str | Any, expected_result: str):
-    """
-    Given: A label
-    When: formatting the label as a key
-    Then: the label is properly formatted
-    """
-    assert QualityMixin._format_facet(label) == expected_result
-
-
 def test_validate_vertical_multi_pane_plot_model():
     """
     Given: A `VerticalMultiPanePlot2D` model and some `Plot2D` models

{dkist_processing_common-14.3.0 → dkist_processing_common-14.3.1}/dkist_processing_common.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dkist-processing-common
-Version: 14.3.0
+Version: 14.3.1
 Summary: Common task classes used by the DKIST science data processing pipelines
 Author-email: NSO / AURA <dkistdc@nso.edu>
 License: BSD-3-Clause