dcnum 0.22.0__tar.gz → 0.22.1__tar.gz

{dcnum-0.22.0 → dcnum-0.22.1}/CHANGELOG

@@ -1,3 +1,5 @@
+0.22.1
+ - fix: compute pipeline identifier of origin dataset for basin mapping
 0.22.0
  - fix: GPUSegmenter did not perform mask postprocessing
    (this was not actually fixed in 0.21.0)

{dcnum-0.22.0/src/dcnum.egg-info → dcnum-0.22.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dcnum
-Version: 0.22.0
+Version: 0.22.1
 Summary: numerics toolbox for imaging deformability cytometry
 Author: Maximilian Schlögel, Paul Müller
 Maintainer-email: Paul Müller <dev@craban.de>

{dcnum-0.22.0 → dcnum-0.22.1}/src/dcnum/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.22.0'
-__version_tuple__ = version_tuple = (0, 22, 0)
+__version__ = version = '0.22.1'
+__version_tuple__ = version_tuple = (0, 22, 1)

{dcnum-0.22.0 → dcnum-0.22.1}/src/dcnum/logic/ctrl.py

@@ -1,5 +1,6 @@
 import collections
 import datetime
+import hashlib
 import json
 import logging
 from logging.handlers import QueueListener
@@ -461,9 +462,17 @@ class DCNumJobRunner(threading.Thread):
                 # This is the identifier appendix that we use to identify this
                 # dataset. Note that we only override the run identifier when
                 # segmentation did actually take place.
-                mid_ap = "dcn-" + self.pphash[:7]
-                # This is the current measurement identifier (may be empty).
-                mid_cur = hw.h5.attrs.get("experiment:run identifier", "")
+                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()))
                 # 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

{dcnum-0.22.0 → dcnum-0.22.1/src/dcnum.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dcnum
-Version: 0.22.0
+Version: 0.22.1
 Summary: numerics toolbox for imaging deformability cytometry
 Author: Maximilian Schlögel, Paul Müller
 Maintainer-email: Paul Müller <dev@craban.de>

{dcnum-0.22.0 → dcnum-0.22.1}/tests/test_logic_pipeline.py

@@ -21,6 +21,67 @@ def get_log(hd: read.HDF5Data,
         raise KeyError(f"Log starting with {startswith} not found!")
 
 
+@pytest.mark.parametrize("override_attrs,delete_keys,meas_id", [
+    # standard
+    [{"experiment:run identifier": "peter"},
+     [],
+     "peter"],
+    # from metadata (input file)
+    [{"experiment:run identifier": ""},
+     [],
+     "d5a40aed-0b6c-0412-e87c-59789fdd28d0"],
+    # from metadata (input file)
+    [{},
+     ["experiment:run identifier"],
+     "d5a40aed-0b6c-0412-e87c-59789fdd28d0"],
+    # from metadata (manual)
+    [{"experiment:time": "12:01",
+      "experiment:date": "2024-06-23",
+      "setup:identifier": "RC-peter-pan-and-friends",
+      },
+     ["experiment:run identifier"],
+     "f0cfdc6f-93c7-c093-d135-a20f3e5bdbfa"],
+    # delete everything, this is the hash of none-none-none
+    [{},
+     ["setup:identifier", "experiment:time", "experiment:run identifier",
+      "setup:identifier"],
+     "07d18822-3045-4e6b-da0b-f1a16c80132a"],
+])
+def test_basin_experiment_identifier_correct(
+        override_attrs, delete_keys, meas_id):
+    """Make sure the measurement identifier computed by dcnum is correct"""
+    path_orig = retrieve_data("fmt-hdf5_cytoshot_full-features_2023.zip")
+    path_out = path_orig.with_name("out.rtdc")
+
+    # modify input file
+    with h5py.File(path_orig, "a") as h5in:
+        for key in override_attrs:
+            h5in.attrs[key] = override_attrs[key]
+        for key in delete_keys:
+            if key in h5in.attrs:
+                h5in.attrs.pop(key)
+
+    job = logic.DCNumPipelineJob(path_in=path_orig,
+                                 path_out=path_out,
+                                 background_code="copy",
+                                 segmenter_code="thresh",
+                                 segmenter_kwargs={"thresh": -5},
+                                 feature_kwargs={"volume": False,
+                                                 "haralick": False,
+                                                 "brightness": False,
+                                                 },
+                                 basin_strategy="tap",
+                                 debug=True)
+    with logic.DCNumJobRunner(job=job) as runner:
+        runner.run()
+
+    with h5py.File(path_out) as hout:
+        appid = hout.attrs["pipeline:dcnum hash"]
+        eri_exp = f"{meas_id}_dcn-{appid[:7]}"
+        # this is the actual test
+        assert hout.attrs["experiment:run identifier"] == eri_exp
+
+
 def test_basin_strategy_drain_mapped_input():
     """When basin strategy is "drain", features are mapped from the input
 
@@ -683,7 +744,9 @@ def test_simple_pipeline(debug):
         # test for general metadata
         assert h5.attrs["experiment:sample"] == "data"
         assert h5.attrs["experiment:date"] == "2022-04-21"
-        assert h5.attrs["experiment:run identifier"] == f"dcn-{pp_hash[:7]}"
+        assert h5.attrs["experiment:run identifier"] == \
+               (f"d5a40aed-0b6c-0412-e87c-59789fdd28d0_"
+                f"dcn-{pp_hash[:7]}")
 
 
 @pytest.mark.parametrize("debug", [True, False])
@@ -750,7 +813,9 @@ def test_simple_pipeline_no_offset_correction(debug):
         # test for general metadata
         assert h5.attrs["experiment:sample"] == "data"
         assert h5.attrs["experiment:date"] == "2022-04-21"
-        assert h5.attrs["experiment:run identifier"] == f"dcn-{pp_hash[:7]}"
+        assert h5.attrs["experiment:run identifier"] == \
+               (f"d5a40aed-0b6c-0412-e87c-59789fdd28d0_"
+                f"dcn-{pp_hash[:7]}")
 
 
 def test_simple_pipeline_in_thread():