dclab 0.65.0__cp312-cp312-macosx_10_13_x86_64.whl → 0.66.0__cp312-cp312-macosx_10_13_x86_64.whl

dclab/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.65.0'
-__version_tuple__ = version_tuple = (0, 65, 0)
+__version__ = version = '0.66.0'
+__version_tuple__ = version_tuple = (0, 66, 0)

dclab/rtdc_dataset/core.py

@@ -741,7 +741,9 @@ class RTDCBase(abc.ABC):
                 # need the referring dataset.
                 "mapping_referrer": self,
                 # Make sure the measurement identifier is checked.
-                "measurement_identifier": self.get_measurement_identifier(),
+                "referrer_identifier": self.get_measurement_identifier(),
+                # Make sure the basin identifier is checked.
+                "basin_identifier": bdict.get("identifier"),
                 # allow to ignore basins
                 "ignored_basins": bd_keys,
                 # basin key

dclab/rtdc_dataset/export.py

@@ -438,7 +438,6 @@ class Export(object):
                 if progress_callback:
                     progress_callback(1 - 1 / (len(features) or 1),
                                       "writing basins")
-
                 # We have to store basins. There are three options:
                 # - filtering disabled: just copy basins
                 # - filtering enabled
@@ -450,6 +449,8 @@ class Export(object):
                 basin_list = [bn.as_dict() for bn in ds.basins]
                 # In addition to the upstream basins, also store a reference
                 # to the original file from which the export was done.
+                # Get the identifier of the current dataset for the new basins.
+                basin_id = ds.get_measurement_identifier()
                 if ds.format in get_basin_classes():
                     # The dataset has a format that matches a basin format
                     # directly.
@@ -464,6 +465,7 @@ class Export(object):
                         "basin_format": ds.format,
                         "basin_locs": basin_locs,
                         "basin_descr": f"Exported with dclab {version}",
+                        "basin_id": basin_id,
                     })
                 elif (ds.format == "hierarchy"
                       and ds.get_root_parent().format in get_basin_classes()):
@@ -497,6 +499,7 @@ class Export(object):
                             child=ds,
                             child_indices=np.arange(len(ds))
                             ),
+                        "basin_id": basin_id,
                     })
 
                 for bn_dict in basin_list:

dclab/rtdc_dataset/feat_basin.py

@@ -176,7 +176,8 @@ class Basin(abc.ABC):
                  name: str = None,
                  description: str = None,
                  features: List[str] = None,
-                 measurement_identifier: str = None,
+                 referrer_identifier: str = None,
+                 basin_identifier: str = None,
                  mapping: Literal["same",
                                   "basinmap0",
                                   "basinmap1",
@@ -208,10 +209,18 @@ class Basin(abc.ABC):
         features: list of str
             List of features this basin provides; This list is enforced,
             even if the basin actually contains more features.
-        measurement_identifier: str
+        referrer_identifier: str
             A measurement identifier against which to check the basin.
+            If the basin mapping is "same", then this must match the
+            identifier of the basin exactly, otherwise it must start
+            with the basin identifier (e.g. "basin-id_referrer-sub-id").
             If this is set to None (default), there is no certainty
             that the downstream dataset is from the same measurement.
+        basin_identifier: str
+            A measurement identifier that must match the basin exactly.
+            In contrast to `referrer_identifier`, the basin identifier is
+            the identifier of the basin file. If `basin_identifier` is
+            specified, the identifier of the basin must be identical to it.
         mapping: str
             Which type of mapping to use. This can be either "same"
             when the event list of the basin is identical to that
@@ -261,8 +270,9 @@ class Basin(abc.ABC):
         # features this basin provides
         self._features = features
         #: measurement identifier of the referencing dataset
-        self.measurement_identifier = measurement_identifier
-        self._measurement_identifier_verified = False
+        self.referrer_identifier = referrer_identifier
+        self.basin_identifier = basin_identifier or None
+        self._identifiers_verification = None
         #: ignored basins
         self.ignored_basins = ignored_basins or []
         #: additional keyword arguments passed to the basin
@@ -304,13 +314,13 @@ class Basin(abc.ABC):
 
         return f"<{self.__class__.__name__} ({opt_str}) at {hex(id(self))}>"
 
-    def _assert_measurement_identifier(self):
+    def _assert_referrer_identifier(self):
         """Make sure the basin matches the measurement identifier
         """
         if not self.verify_basin(run_identifier=True):
             raise KeyError(f"Measurement identifier of basin {self.ds} "
                            f"({self.get_measurement_identifier()}) does "
-                           f"not match {self.measurement_identifier}!")
+                           f"not match {self.referrer_identifier}!")
 
     @property
     def basinmap(self):
@@ -410,7 +420,7 @@ class Basin(abc.ABC):
 
     def get_feature_data(self, feat):
         """Return an object representing feature data of the basin"""
-        self._assert_measurement_identifier()
+        self._assert_referrer_identifier()
         return self.ds[feat]
 
     def get_measurement_identifier(self):
@@ -455,20 +465,30 @@ class Basin(abc.ABC):
         # Only check for run identifier if requested and if the availability
         # check did not fail.
         if run_identifier and check_avail:
-            if not self._measurement_identifier_verified:
-                if self.measurement_identifier is None:
+            if self._identifiers_verification is None:
+                # This is the measurement identifier of the basin.
+                basin_identifier = self.get_measurement_identifier()
+
+                # Perform a sanity check for the basin identifier.
+                if (self.basin_identifier
+                        and self.basin_identifier != basin_identifier):
+                    # We should not proceed any further with this basin.
+                    self._identifiers_verification = False
+                    warnings.warn(
+                        f"Basin identifier mismatch for {self}. Expected "
+                        f"'{self.basin_identifier}', got '{basin_identifier}'")
+
+                if self.referrer_identifier is None:
                     # No measurement identifier was presented by the
                     # referencing dataset. We are in the dark.
                     # Don't perform any checks.
-                    self._measurement_identifier_verified = True
+                    self._identifiers_verification = True
                 else:
-                    # This is the measurement identifier of the basin.
-                    basin_identifier = self.get_measurement_identifier()
                     if basin_identifier is None:
                         # Again, we are in the dark, because the basin dataset
                         # does not have an identifier. This is an undesirable
                         # situation, but there is nothing we can do about it.
-                        self._measurement_identifier_verified = True
+                        self._identifiers_verification = True
                     else:
                         if self.mapping == "same":
                             # When we have identical mapping, then the
@@ -479,10 +499,10 @@ class Basin(abc.ABC):
                             # data), then the measurement identifier has to
                             # partially match.
                             verifier = str.startswith
-                        self._measurement_identifier_verified = verifier(
-                            self.measurement_identifier, basin_identifier)
+                        self._identifiers_verification = verifier(
+                            self.referrer_identifier, basin_identifier)
 
-            check_rid = self._measurement_identifier_verified
+            check_rid = self._identifiers_verification
         else:
             check_rid = True
 

dclab/rtdc_dataset/writer.py

@@ -207,6 +207,7 @@ class RTDCWriter:
                     basin_descr: str | None = None,
                     basin_feats: List[str] = None,
                     basin_map: np.ndarray | Tuple[str, np.ndarray] = None,
+                    basin_id: str = None,
                     internal_data: Dict | h5py.Group = None,
                     verify: bool = True,
                     perishable: bool = False,
@@ -243,6 +244,12 @@ class RTDCWriter:
             a case, you may specify a tuple `(feature_name, mapping_array)`
             where `feature_name` is the explicit mapping name, e.g.
             `"basinmap3"`.
+        basin_id: str
+            Identifier of the basin. This is the string returned by
+            :meth:`.RTDCBase.get_measurement_identifier`. This is
+            a unique string that identifies the data within a basin.
+            If not specified and `verify=True`, this value is automatically
+            taken from the basin file.
         internal_data: dict or instance of h5py.Group
             A dictionary or an `h5py.Group` containing the basin data.
             The data are copied to the "basin_events" group, if
@@ -310,19 +317,30 @@ class RTDCWriter:
             # We have to import this here to avoid circular imports
             from .load import new_dataset
             # Make sure the basin can be opened by dclab, verify its ID
-            cur_id = self.h5file.attrs.get("experiment:run identifier")
+            ref_id = self.h5file.attrs.get("experiment:run identifier")
             for loc in basin_locs:
                 with new_dataset(loc) as ds:
                     # We can open the file, which is great.
-                    if cur_id:
-                        # Compare the IDs.
-                        ds_id = ds.get_measurement_identifier()
-                        if not (ds_id == cur_id
+                    # Compare the IDs.
+                    bn_id = ds.get_measurement_identifier()
+                    # Check whether `basin_id` matches the actual basin
+                    if basin_id:
+                        if basin_id != bn_id:
+                            raise ValueError(
+                                f"Measurement identifier mismatch for "
+                                f"{loc}: got {bn_id}, expected {basin_id=})!")
+                    else:
+                        # If `basin_id` was not specified, set it here for
+                        # user convenience.
+                        basin_id = bn_id or None
+                    # Check whether the referrer ID matches the basin ID.
+                    if ref_id:
+                        if not (bn_id == ref_id
                                 or (basin_map is not None
-                                    and cur_id.startswith(ds_id))):
+                                    and ref_id.startswith(bn_id))):
                             raise ValueError(
                                 f"Measurement identifier mismatch between "
-                                f"{self.path} ({cur_id}) and {loc} ({ds_id})!")
+                                f"{self.path} ({ref_id}) and {loc} ({bn_id})!")
             if basin_feats:
                 for feat in basin_feats:
                     if not dfn.feature_exists(feat):
@@ -389,6 +407,7 @@ class RTDCWriter:
             "features": None if basin_feats is None else sorted(basin_feats),
             "mapping": basin_map_name,
             "perishable": perishable,
+            "identifier": basin_id,
         }
         if basin_type == "file":
             flocs = []

{dclab-0.65.0.dist-info → dclab-0.66.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dclab
-Version: 0.65.0
+Version: 0.66.0
 Summary: Library for real-time deformability cytometry (RT-DC)
 Author: Benedikt Hartmann, Eoghan O'Connell, Maik Herbig, Maximilian Schlögel, Nadia Sbaa, Paul Müller, Philipp Rosendahl, Raghava Alajangi
 Maintainer-email: Paul Müller <dev@craban.de>

{dclab-0.65.0.dist-info → dclab-0.66.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
 dclab/kde_methods.py,sha256=f0-zDN7ETintvGB3gSzxwgBb53YtT9jZtzI70EAX50g,365
-dclab/_version.py,sha256=BT1Cb9U9MvH-WQX7Cjgfkn_LwsFhZPas-_Emage6tIU,513
+dclab/_version.py,sha256=LxUMbTNTE_mpL3yJaLLTdWd5Zvz3gifurvXDekNg0gY,513
 dclab/util.py,sha256=HFT5ZQV6AW8GIIruVMldukbVVdlMyKH50GUfOogAcxI,5860
 dclab/downsampling.pyx,sha256=OK7zbgGLl5gVyoU8ZBHo9EWwb8C9ChavmLNEvQvC9T0,7258
 dclab/__init__.py,sha256=wyJWhElQRPcq09vUqUnuquTU_KHgHxv6wQxuxQ988Iw,1583
@@ -9,7 +9,7 @@ dclab/http_utils.py,sha256=XHicbHQts5LY3zSNmYqNgAZpKTktotEiwQgJ8d2sBlk,10912
 dclab/polygon_filter.py,sha256=qexmo-rXe06CUPZhN6EMJy4y4B5gXZeqejdvIB2arOE,13480
 dclab/statistics.py,sha256=DWBG_Kj7cn89b_s5mqWYDCMGB881jHcCRFY-KAOBnhE,7598
 dclab/kde_contours.py,sha256=UlU64lrzMQUZH11oZndW7xf7NFCzwP3FcVujwuqXDCI,278
-dclab/downsampling.cpython-312-darwin.so,sha256=VoISot72W8URAW0KHNE5kUGEOB0FP6BGyyMuhh2qhYw,244320
+dclab/downsampling.cpython-312-darwin.so,sha256=8K7if-SPQ-T3kL8YJrbj_6RsBd54VTC_t9fWcmAti7Y,244320
 dclab/isoelastics/iso_LE-2D-FEM-19-volume-deform.txt,sha256=vTcazOlOXo3BQ0NQtGB_IdHKA0neOLXZ_d3JuMU--RE,83358
 dclab/isoelastics/iso_HE-3D-FEM-22-area_um-deform.txt,sha256=IjULG1KO-hClaYPoJJnwPbF2TkS9i9jxF1tbhhQTClY,71350
 dclab/isoelastics/iso_HE-2D-FEM-22-volume-deform.txt,sha256=aLOWxev_hvyP2yWquomcogn3Ze4SBfvqz-qmTOOibNw,97512
@@ -65,17 +65,17 @@ dclab/external/statsmodels/nonparametric/kernel_density.py,sha256=3UyzLuZS68TkNT
 dclab/external/statsmodels/nonparametric/__init__.py,sha256=-GEWgwsF27ems5WTBvR1zo4SWJ0pRTWyHVagnIYer3g,43
 dclab/external/statsmodels/nonparametric/kernels.py,sha256=fuy4kStFz2ZA9pqgfUb4cly-YBpXLu4TJ9-ZujayuIw,1075
 dclab/external/skimage/measure.py,sha256=y1idCqD9TUxp3-QnOiWR_d674OKaeqBJ4MN2-gVP6ro,247
-dclab/external/skimage/_pnpoly.cpython-312-darwin.so,sha256=hyjzTiOR3tCBI2msIPdXbqv2z2MiaPInTDgRfpG5MCE,207712
+dclab/external/skimage/_pnpoly.cpython-312-darwin.so,sha256=5LO25ADnw1i6GUSXZ9J2LLlCovioxJydJMqq_E4ttcs,207712
 dclab/external/skimage/LICENSE,sha256=ivsSBvn3c0R9mOctWRRdza7C7wdZSRYgCVxlVqUdlB8,1452
 dclab/external/skimage/pnpoly.py,sha256=r8hFNiTz5XlUoNZjosqA0iyv1FPn0l7ewbplgFgkdaw,1347
 dclab/external/skimage/_find_contours.py,sha256=16v5eeTZBmevG8SSuXtJ6yUpVPhwfSmtc8pDD0nuuOU,9340
 dclab/external/skimage/__init__.py,sha256=-B2QUKHAFzQuBWuuKvPDC5JIl0Zb-x3OGmbwPaE9VwQ,72
-dclab/external/skimage/_find_contours_cy.cpython-312-darwin.so,sha256=8taTwKJ_52CSDYj-Q9ezu7QIZRxFqeD6SUJKzAlYlEQ,188984
+dclab/external/skimage/_find_contours_cy.cpython-312-darwin.so,sha256=bEmnBFsLcGt5M0oHBALMmTDlgCbco_geXP1Stm1uzCE,188984
 dclab/external/skimage/_pnpoly.pyx,sha256=Qdn6xPazDschBqbr46DzB75MB2MnqvdnoTSBMK7kUGE,2504
 dclab/external/skimage/_find_contours_cy.pyx,sha256=pZJOBhMHzYEMkcz4WQVyjn7jDNrdjCfet47FU1hRAxk,7161
 dclab/external/skimage/_shared/geometry.pxd,sha256=kRsu9ifv_rL3kbRIgSLf86p0hn2oTMp6s013lZ9bBZM,346
 dclab/external/skimage/_shared/__init__.py,sha256=2sHZwTtJSlMTa3Q2YSvQW7jrPLMUSqDJQa-ROe5zfcw,37
-dclab/external/skimage/_shared/geometry.cpython-312-darwin.so,sha256=bO0otFuAiH_nkszPkgwZPFlAKXe8UcVm9YCapjrr1Io,38496
+dclab/external/skimage/_shared/geometry.cpython-312-darwin.so,sha256=_Cb99JQYxV_cV7jrCnjOx6sXBsLMXzPwInQnb0Yt6gk,38496
 dclab/external/skimage/_shared/geometry.pyx,sha256=miCHUh6mBDbRRIoaF_0xAER1MRzsCAzFdlYQZhV7RmE,1667
 dclab/definitions/feat_logic.py,sha256=_Rr2vK-nbRNjxk5Kf8Iohs_Q3jzUe9EZJgxB9vMwxwE,5379
 dclab/definitions/meta_parse.py,sha256=YdaTdM8DAMsIFn5ITH9OHYGTXeAOBGWtx22oVjxXcWk,2393
@@ -86,14 +86,14 @@ dclab/definitions/meta_logic.py,sha256=wCgb7DPRHaR8DCWw_VbwNkpslUnazzWfgX0iS8oEe
 dclab/rtdc_dataset/config.py,sha256=MvBteFya3R6Ch3U6UgTakCsJoBgVykTxS_Z25STWPHU,17432
 dclab/rtdc_dataset/check.py,sha256=lJNaz4QTe2WNlxik6zSohRHTiAYuP_bKOzSDjPGTUS0,35006
 dclab/rtdc_dataset/meta_table.py,sha256=ucqBNrgI6rDAuQFuMRckY8lp1LpnYAoRgEsLObWTJCE,648
-dclab/rtdc_dataset/feat_basin.py,sha256=iBGhuRkIy-zbonIjYHCQdLd3V3_cebpBfDTvqyLzJK4,26921
+dclab/rtdc_dataset/feat_basin.py,sha256=pSrKSayNjkf_RY3OprE5CPNIUR46r2cd2o1NnkpspAU,27990
 dclab/rtdc_dataset/fmt_s3.py,sha256=bU3V_WGyqJhxPCH80X_nlNqq-jXcgoZKv_aUBIqwaL8,11877
 dclab/rtdc_dataset/feat_temp.py,sha256=XbDIS1iUUkRH0Zp9uVlwvK_untJ7hkOnKshK1Drsnt8,3694
 dclab/rtdc_dataset/__init__.py,sha256=MUHSGVQJ4Zc0IyU2lf01dpDWyOyNveHip-UjSkmPNvQ,486
-dclab/rtdc_dataset/core.py,sha256=LjddGHdqZINXKUQcvCyCDmOofdBzyJIXN_z_C-zWGnM,34777
-dclab/rtdc_dataset/export.py,sha256=SzQJpq9YfYfQFsIc3mnITwBwr2w7tYRMrvoPAzo3YPs,33427
+dclab/rtdc_dataset/core.py,sha256=HNRia2qxlDwCK52ypJ9TsOTlTLqszOEvYtAoCH2od3w,34896
+dclab/rtdc_dataset/export.py,sha256=l-c_HGrrxVum-MLqIWvlz_eJWi0C-GAiMsChXOV3lAE,33657
 dclab/rtdc_dataset/fmt_dict.py,sha256=gumVQOiVVDFUKow_483PY7cxInqo-NiBBnBhIU8s4lg,3009
-dclab/rtdc_dataset/writer.py,sha256=BqP4QSzHxCSxp9z7_cJF2v04taO3ZXE3Wg6zJY6fMao,41819
+dclab/rtdc_dataset/writer.py,sha256=MdqEFf4hpoBjjvNbp120BWCdaP1XjEyS3hxO2WNwApw,42845
 dclab/rtdc_dataset/filter.py,sha256=AFPUBzOIi3pqXgUdMQ5CIi9ZeGOKC71rfSZKLMLgtog,10023
 dclab/rtdc_dataset/fmt_http.py,sha256=vXVxRLXZp2_V1v3xk4lu4VUHYXfNHJdsRkVt3trC1RU,3374
 dclab/rtdc_dataset/load.py,sha256=5_xGw2P8Mjs0gW-vGr2Kn28j6Qv3BvvMvguMibC_mM4,2761
@@ -134,9 +134,9 @@ dclab/rtdc_dataset/fmt_tdms/event_image.py,sha256=-jp7Z-N91e4ieumYQ1huMicj7PMJqw
 dclab/rtdc_dataset/fmt_tdms/event_trace.py,sha256=Vkym0QKSw2mq1XZl5n8wDkgHXmaZwQGiMAV5AuRSJkE,5215
 dclab/rtdc_dataset/fmt_tdms/exc.py,sha256=WzrMqnyrzp8gsT8Pf7JKqGGv43ewx7d_qgtirURppRI,813
 dclab/rtdc_dataset/fmt_tdms/event_contour.py,sha256=kjo0wJx9F0gmmOOyR0NoLw6VEtSl3h63WXXkcbfnoS8,9627
-dclab-0.65.0.dist-info/RECORD,,
-dclab-0.65.0.dist-info/WHEEL,sha256=mer8vOuI-KlBtJIdzgyZALHdls6RZGRaE6RPt7dfKrk,138
-dclab-0.65.0.dist-info/entry_points.txt,sha256=eOpjgznu-eW-9utUpLU-77O5098YyUEgGF3ksGMdtec,273
-dclab-0.65.0.dist-info/top_level.txt,sha256=irvwZMgs1edY1Zj60ZFk7Almb9Zhk4k6E6aC4YPFnnM,6
-dclab-0.65.0.dist-info/METADATA,sha256=aDIGhFsgmVOULuMhp6vIRdd3uoJppcjW7tahpDRi-Dg,4766
-dclab-0.65.0.dist-info/licenses/LICENSE,sha256=gLDaVZWRrlnLdyfOrR0qfWjLbOVcjvoJ-kCLUK0fyXA,15360
+dclab-0.66.0.dist-info/RECORD,,
+dclab-0.66.0.dist-info/WHEEL,sha256=mer8vOuI-KlBtJIdzgyZALHdls6RZGRaE6RPt7dfKrk,138
+dclab-0.66.0.dist-info/entry_points.txt,sha256=eOpjgznu-eW-9utUpLU-77O5098YyUEgGF3ksGMdtec,273
+dclab-0.66.0.dist-info/top_level.txt,sha256=irvwZMgs1edY1Zj60ZFk7Almb9Zhk4k6E6aC4YPFnnM,6
+dclab-0.66.0.dist-info/METADATA,sha256=Mxx90M0sUHGcyezYK-_cY6xy60fYvg0GLc99e6y_3Jk,4766
+dclab-0.66.0.dist-info/licenses/LICENSE,sha256=gLDaVZWRrlnLdyfOrR0qfWjLbOVcjvoJ-kCLUK0fyXA,15360