dcnum 0.25.10__py3-none-any.whl → 0.25.11__py3-none-any.whl

dcnum/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.25.10'
-__version_tuple__ = version_tuple = (0, 25, 10)
+__version__ = version = '0.25.11'
+__version_tuple__ = version_tuple = (0, 25, 11)

dcnum/logic/ctrl.py

@@ -1,6 +1,5 @@
 import collections
 import datetime
-import hashlib
 import importlib
 import json
 import logging
@@ -24,7 +23,7 @@ from ..feat import gate
 from ..feat import EventExtractorManagerThread
 from ..segm import SegmenterManagerThread, get_available_segmenters
 from ..meta import ppid
-from ..read import HDF5Data, get_mapping_indices
+from ..read import HDF5Data, get_measurement_identifier, get_mapping_indices
 from .._version import version, version_tuple
 from ..write import (
     DequeWriterThread, HDF5Writer, QueueCollectorThread, copy_features,
@@ -453,15 +452,7 @@ class DCNumJobRunner(threading.Thread):
                 # segmentation did actually take place.
                 mid_ap = f"dcn-{self.pphash[:7]}"
                 # This is the current measurement identifier
-                mid_cur = hw.h5.attrs.get("experiment:run identifier")
-                if not mid_cur:
-                    # Compute a measurement identifier from the metadata
-                    m_time = hw.h5.attrs.get("experiment:time", "none")
-                    m_date = hw.h5.attrs.get("experiment:date", "none")
-                    m_sid = hw.h5.attrs.get("setup:identifier", "none")
-                    hasher = hashlib.md5(
-                        f"{m_time}_{m_date}_{m_sid}".encode("utf-8"))
-                    mid_cur = str(uuid.UUID(hex=hasher.hexdigest()))
+                mid_cur = get_measurement_identifier(hw.h5)
                 # The new measurement identifier is a combination of both.
                 mid_new = f"{mid_cur}_{mid_ap}" if mid_cur else mid_ap
                 hw.h5.attrs["experiment:run identifier"] = mid_new
@@ -666,6 +657,7 @@ class DCNumJobRunner(threading.Thread):
                                    mapping=basinmap0,
                                    paths=paths,
                                    description=f"Created with dcnum {version}",
+                                   identifier=get_measurement_identifier(hin),
                                    )
                 self._progress_bn += 1 / len(feats_raw)
         t_tot = time.perf_counter() - t0

dcnum/read/__init__.py

@@ -2,6 +2,9 @@
 from .cache import md5sum
 from .const import PROTECTED_FEATURES
 from .detect_flicker import detect_flickering
-from .hdf5_data import HDF5Data, HDF5ImageCache
+from .hdf5_data import (
+    HDF5Data, HDF5ImageCache, get_measurement_identifier,
+    BasinIdentifierMismatchError
+)
 from .hdf5_concat import concatenated_hdf5_data
 from .mapped import get_mapping_indices, get_mapped_object

dcnum/read/hdf5_data.py

@@ -16,6 +16,10 @@ from .const import PROTECTED_FEATURES
 from .mapped import get_mapped_object, get_mapping_indices
 
 
+class BasinIdentifierMismatchError(BaseException):
+    """Used when basin identifiers do not match"""
+
+
 class HDF5Data:
     """HDF5 (.rtdc) input file data instance"""
     def __init__(self,
@@ -473,6 +477,12 @@ class HDF5Data:
             features = []
         else:
             h5 = h5py.File(path, "r")
+            # verify that the basin was identified correctly
+            if ((id_exp := bn_dict.get("identifier")) is not None
+                    and (id_act := get_measurement_identifier(h5)) != id_exp):
+                raise BasinIdentifierMismatchError(
+                    f"The basin '{path}' with identifier '{id_act}' "
+                    f"does not match the expected identifier '{id_exp}'")
             h5group = h5["events"]
             # features defined in the basin
             features = bn_dict.get("features")
@@ -560,3 +570,30 @@ def concatenated_hdf5_data(*args, **kwargs):
         DeprecationWarning)
     from . import hdf5_concat
     return hdf5_concat.concatenated_hdf5_data(*args, **kwargs)
+
+
+def get_measurement_identifier(h5: h5py.Group) -> str | None:
+    """Return the measurement identifier for the given H5File object
+
+    The basin identifier is taken from the HDF5 attributes. If the
+    "experiment:run identifier" attribute is not set, it is
+    computed from the HDF5 attributes "experiment:time",
+    "experiment:date", and "setup:identifier".
+
+    If the measurement identifier cannot be found or computed,
+    return None.
+    """
+    # This is the current measurement identifier
+    mid = h5.attrs.get("experiment:run identifier")
+    if not mid:
+        # Compute a measurement identifier from the metadata
+        m_time = h5.attrs.get("experiment:time", None) or None
+        m_date = h5.attrs.get("experiment:date", None) or None
+        m_sid = h5.attrs.get("setup:identifier", None) or None
+        if None not in [m_time, m_date, m_sid]:
+            # Only compute an identifier if all of the above
+            # are defined.
+            hasher = hashlib.md5(
+                f"{m_time}_{m_date}_{m_sid}".encode("utf-8"))
+            mid = str(uuid.UUID(hex=hasher.hexdigest()))
+    return mid

dcnum/write/writer.py

@@ -8,7 +8,7 @@ import h5py
 import hdf5plugin
 import numpy as np
 
-from ..read import HDF5Data
+from ..read import HDF5Data, get_measurement_identifier
 from .._version import version
 
 
@@ -157,6 +157,7 @@ class HDF5Writer:
                     description: str | None = None,
                     mapping: np.ndarray = None,
                     internal_data: Dict | None = None,
+                    identifier: str | None = None,
                     ):
         """Write an HDF5-based file basin
 
@@ -177,6 +178,10 @@ class HDF5Writer:
         internal_data: dict of ndarrays
             internal basin data to store; If this is set, then `features`
             and `paths` must be set to `None`.
+        identifier: str
+            the measurement identifier of the basin as computed by
+            the :func:`~dcnum.read.hdf5_data.get_measurement_identifier`
+            function.
         """
         bdat = {
             "description": description,
@@ -190,6 +195,9 @@ class HDF5Writer:
             if paths is not None:
                 raise ValueError("`paths` must be set to None when storing "
                                  "internal basin features")
+            if identifier is not None:
+                warnings.warn(f"Not storing identifier for internal "
+                              f"basin '{name}' (got '{identifier}')")
             # store the internal basin information
             for feat in internal_data:
                 if feat in self.h5.require_group("basin_events"):
@@ -206,6 +214,8 @@ class HDF5Writer:
             bdat["format"] = "hdf5"
             bdat["paths"] = [str(pp) for pp in paths]
             bdat["type"] = "file"
+            # identifier only makes sense here (not for internal basins)
+            bdat["identifier"] = identifier
 
         # Explicit features stored in basin file
         if features is not None and len(features):
@@ -322,6 +332,7 @@ def create_with_basins(
         warnings.warn(f"Creating basin-based file '{path_out}' without any "
                       f"basins, since the list `basin_paths' is empty!",
                       CreatingFileWithoutBasinWarning)
+        basin_paths = []
     with HDF5Writer(path_out, mode="w") as hw:
         # Get the metadata from the first available basin path
 
@@ -359,16 +370,19 @@ def create_with_basins(
                     features = sorted(h5["events"].keys())
                     features = [f for f in features if
                                 not f.startswith("basinmap")]
+                    basin_identifier = get_measurement_identifier(h5)
                 name = prep.name
             else:
                 features = None
                 name = bps[0]
+                basin_identifier = None
 
             # Write the basin data
             hw.store_basin(name=name,
                            paths=bps,
                            features=features,
                            description=f"Created by dcnum {version}",
+                           identifier=basin_identifier,
                            )
 
 
@@ -404,6 +418,7 @@ def copy_basins(h5_src: h5py.File,
                            paths=bn_dict["paths"],
                            features=bn_dict["features"],
                            mapping=mapping,
+                           identifier=bn_dict.get("identifier"),
                            )
         else:
             warnings.warn(f"Ignored basin of type '{bn_dict['type']}'",

{dcnum-0.25.10.dist-info → dcnum-0.25.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dcnum
-Version: 0.25.10
+Version: 0.25.11
 Summary: numerics toolbox for imaging deformability cytometry
 Author: Maximilian Schlögel, Paul Müller, Raghava Alajangi
 Maintainer-email: Paul Müller <dev@craban.de>
@@ -55,12 +55,12 @@ For more options, please check out the `documentation
 
 
 
-.. |dcnum| image:: https://raw.github.com/DC-analysis/dcnum/master/docs/logo/dcnum.png
+.. |dcnum| image:: https://raw.github.com/DC-analysis/dcnum/main/docs/logo/dcnum.png
 .. |PyPI Version| image:: https://img.shields.io/pypi/v/dcnum.svg
    :target: https://pypi.python.org/pypi/dcnum
 .. |Build Status| image:: https://img.shields.io/github/actions/workflow/status/DC-analysis/dcnum/check.yml
    :target: https://github.com/DC-analysis/dcnum/actions?query=workflow%3AChecks
-.. |Coverage Status| image:: https://img.shields.io/codecov/c/github/DC-analysis/dcnum/master.svg
+.. |Coverage Status| image:: https://img.shields.io/codecov/c/github/DC-analysis/dcnum
    :target: https://codecov.io/gh/DC-analysis/dcnum
 .. |Docs Status| image:: https://readthedocs.org/projects/dcnum/badge/?version=latest
    :target: https://readthedocs.org/projects/dcnum/builds/

{dcnum-0.25.10.dist-info → dcnum-0.25.11.dist-info}/RECORD

@@ -1,5 +1,5 @@
 dcnum/__init__.py,sha256=p0mYg01FQ6nsERYmx_FfVxqqHvYcSMEyIAMBIivAmO8,1206
-dcnum/_version.py,sha256=2u4bWaMdcZXyf4_yxgykEAXNXcEaVQumowHKcuxLJUI,515
+dcnum/_version.py,sha256=G2RU878iZqAjfDOQZYI6kgCV8us1Ipc26TtDUjv56s0,515
 dcnum/os_env_st.py,sha256=4psq-gPuWTTQ118kCiTx0Mhoyads4Irn6JSUzZk8gyc,3052
 dcnum/feat/__init__.py,sha256=jUJYWTD3VIoDNKrmryXbjHb1rGwYtK4b7VPWihYgUoo,325
 dcnum/feat/event_extractor_manager_thread.py,sha256=6D3RVYBuH7gOoGZ4Kz74n6fhq7MtlTY26kpSwZRqg3M,7972
@@ -21,18 +21,18 @@ dcnum/feat/feat_texture/__init__.py,sha256=6StM9S540UVtdFFR3bHa7nfCTomeVdoo7Uy9C
 dcnum/feat/feat_texture/common.py,sha256=COXHpXS-7DMouGu3WF83I76L02Sr7P9re4lxajh6g0E,439
 dcnum/feat/feat_texture/tex_all.py,sha256=_5H3sXYRN0Uq2eUHn3XUyEHkU_tncEqbqJTC-HZcnGY,5198
 dcnum/logic/__init__.py,sha256=7J3GrwJInNQbrLk61HRIV7X7p69TAIbMYpR34hh6u14,177
-dcnum/logic/ctrl.py,sha256=c06ZOUD0T4_FdQDHbigkLAPQTyoeFxhETg-K3W1UyeM,37520
+dcnum/logic/ctrl.py,sha256=4r5N4WlqJW1f61zpaWFBJofEgMsD7H2APeiqOu9Li08,37099
 dcnum/logic/job.py,sha256=MprDL6DwXWmvtGgy7W9A7s2rVRx68ObdJB8mvGFwVcw,7718
 dcnum/logic/json_encoder.py,sha256=wb6uk6EeTkXyrvwtLm9uWe0cfmiBannzcsKLsDLHuQo,843
 dcnum/meta/__init__.py,sha256=AVqRgyKXO1orKnE305h88IBvoZ1oz6X11HN1WP5nGvg,60
 dcnum/meta/paths.py,sha256=aIG39JYbZpOlCbPQIlp0SqGumjbGINYhL2AAoznJt5o,1113
 dcnum/meta/ppid.py,sha256=JInGtwSCsO9nr1E1aishm0k9iQIFB-essBKvv5aBE98,8510
-dcnum/read/__init__.py,sha256=vhriJFlJ3DlqkAnRPQsOfUQWKYSzLNNp_NZeZ5eBvmo,286
+dcnum/read/__init__.py,sha256=EzH-a_RHnUdG32ws-UgU5tc_je972G3pYgn48ai8PFc,356
 dcnum/read/cache.py,sha256=ChxokVuMaTfi6N6ZbOTWpNYkPgAAYi1lR8nD7JbzjPQ,6497
 dcnum/read/const.py,sha256=x6LfRwWvIxm6nDWlSADVWqDuzMX6bLzy5kQprwLPzA4,496
 dcnum/read/detect_flicker.py,sha256=XVf7nqaHx6weRTtS7KPa5_WRU2flDQIZTbKspeguqdU,1829
 dcnum/read/hdf5_concat.py,sha256=A4Ah_NLxa1ESapEWJcUhdglzi7_E3qKNd81ES7A-_2o,5589
-dcnum/read/hdf5_data.py,sha256=KGMQJYtirBSjnen7FWwfMJB4sr_eOuT8qPGkLZwuMN0,21293
+dcnum/read/hdf5_data.py,sha256=Hp1nzEe4EYaIFw22-VLFYbzvwFzctMYrtjoHAwdhDI8,22924
 dcnum/read/mapped.py,sha256=zU2fYdZfLNHn0rKHxDzBhNFMu4--WWa8nSeE2likyZA,3637
 dcnum/segm/__init__.py,sha256=9cLEAd3JWE8IGqDHV-eSDIYOGBfOepd8OcebtNs8Omk,309
 dcnum/segm/segm_thresh.py,sha256=iVhvIhzO0Gw0t3rXOgH71rOI0CNjJJQq4Gg6BulUhK8,948
@@ -50,9 +50,9 @@ dcnum/segm/segm_torch/torch_preproc.py,sha256=m4Dd2URdvS7ifA1MkbEkc9d9T30lA_1qbE
 dcnum/write/__init__.py,sha256=sK79IlvCFIqf2oFABVeyYedMnHOsEIQpxAauEeNO-Tw,273
 dcnum/write/deque_writer_thread.py,sha256=ao7F1yrVKyufgC4rC0Y2_Vt7snuT6KpI7W2qVxcjdhk,1994
 dcnum/write/queue_collector_thread.py,sha256=-p5vrk9cDhtaIMFIu_cCmvlZJafrFkW68uONonMURYo,11617
-dcnum/write/writer.py,sha256=JkVb4KDBV3oo9r3p2yy9wECO1REx7FG0PRBmVWTxJdk,20577
-dcnum-0.25.10.dist-info/licenses/LICENSE,sha256=rX7tNSxP-EhLz-yYUyoBGwjJheA2fiZpT1Iw0LXnJ2M,1069
-dcnum-0.25.10.dist-info/METADATA,sha256=twT_YXAb4Xxt24EKrjxEg8-4UgkHDHYOfzS-prFCXTM,2355
-dcnum-0.25.10.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dcnum-0.25.10.dist-info/top_level.txt,sha256=Hmh38rgG_MFTVDpUDGuO2HWTSq80P585Het4COQzFTg,6
-dcnum-0.25.10.dist-info/RECORD,,
+dcnum/write/writer.py,sha256=WZLuetH7ZIvK-lhXjmyskHczAWFa9EfHXZWBUf9w1UE,21394
+dcnum-0.25.11.dist-info/licenses/LICENSE,sha256=rX7tNSxP-EhLz-yYUyoBGwjJheA2fiZpT1Iw0LXnJ2M,1069
+dcnum-0.25.11.dist-info/METADATA,sha256=N1T08nz_vUPVx7WzJ6aT45yfVfLu4VdM5EcUm7CfROY,2342
+dcnum-0.25.11.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dcnum-0.25.11.dist-info/top_level.txt,sha256=Hmh38rgG_MFTVDpUDGuO2HWTSq80P585Het4COQzFTg,6
+dcnum-0.25.11.dist-info/RECORD,,