fix unit ids not retrieved corectly

Author: JR-1991

pyenzyme/sbml/serializer.py

@@ -4,6 +4,7 @@
 from pathlib import Path
 from typing import Callable, List
 
+import rich
 import libsbml
 import pandas as pd
 from loguru import logger
@@ -18,6 +19,7 @@
 from pyenzyme.sbml.versions import v2
 from pyenzyme.tabular import to_pandas
 from pyenzyme.units.units import UnitDefinition
+from pyenzyme.tools import to_dict_wo_json_ld
 
 MAPPINGS = tools.read_static_file("pyenzyme.sbml", "mappings.toml")
 NSMAP = {"enzymeml": "https://www.enzymeml.org/v2"}
@@ -438,20 +440,33 @@ def _get_sbml_kind(unit_type: pe.UnitType):
         raise ValueError(f"Unit type {unit_type} not found in libsbml")
 
 
-def _get_unit_id(unit: pe.UnitDefinition) -> str | None:
+def _get_unit_id(unit: pe.UnitDefinition | None) -> str | None:
     """Helper function to get the unit from the list of units."""
 
     if unit is None:
         return None
 
-    if unit.id is None:
-        raise ValueError(f"Unit {unit.name} does not have an ID")
+    for unit2 in units:
+        if _same_unit(unit, unit2):
+            return unit2.id
 
-    return unit.id
 
+    raise ValueError(f"Unit {unit.name} not found in the list of units")
+
+def _same_unit(unit1: pe.UnitDefinition, unit2: pe.UnitDefinition) -> bool:
+    """Check if two units are the same."""
+
+    unit1 = to_dict_wo_json_ld(unit1)
+    unit2 = to_dict_wo_json_ld(unit2)
+
+    del unit1["id"]
+    del unit2["id"]
+
+    return unit1 == unit2
 
 def _validate_sbml(sbmldoc: libsbml.SBMLDocument) -> None:
     """Validate the SBML document using the libSBML function."""
+
     sbml_errors = sbmldoc.checkConsistency()
     valid = True
 

pyenzyme/sbml/versions/v2.py

@@ -179,7 +179,7 @@ class MeasurementAnnot(
 
     id: str = attr(name="id")
     name: str | None = attr(name="name", default=None)
-    time_unit: str = attr(name="timeUnit")
+    time_unit: str | None = attr(name="timeUnit")
     conditions: ConditionsAnnot | None = element(tag="conditions", default=None)
     species_data: list[SpeciesDataAnnot] = element(
         tag="speciesData",
@@ -291,7 +291,7 @@ class PHAnnot(
         value (float): The pH value.
     """
 
-    value: float = attr(name="value")
+    value: float | None = attr(name="value")
 
 
 class TemperatureAnnot(

pyenzyme/tabular.py

@@ -16,7 +16,7 @@
 def to_pandas(
     enzmldoc: EnzymeMLDocument,
     ignore: list[str] | None = None,
-) -> pd.DataFrame:
+) -> pd.DataFrame | None:
     """This function converts an EnzymeMLDocument object to a pandas DataFrame.
 
     The resulting DataFrame contains the following columns:
@@ -38,6 +38,9 @@ def to_pandas(
         ValueError: If the measurement does not contain species data.
     """
 
+    if not enzmldoc.measurements:
+        return None
+
     if ignore is None:
         ignore = []
 
@@ -305,11 +308,17 @@ def _measurement_to_pandas(measurement: Measurement) -> pd.DataFrame:
 
     _validate_measurement(measurement)
 
-    data = {"time": measurement.species_data[0].time}
+    data = {"time": _get_time_array(measurement)}
     for species in measurement.species_data:
-        data[species.species_id] = species.data
+        if len(species.data) > 0:
+            data[species.species_id] = species.data
+
     return pd.DataFrame(data)
 
+def _get_time_array(measurement: Measurement):
+    for meas_data in measurement.species_data:
+        if len(meas_data.time) > 0:
+            return meas_data.time
 
 def _validate_measurement(meas: Measurement) -> None:
     """Validates a Measurement object"""
@@ -321,6 +330,7 @@ def _validate_measurement(meas: Measurement) -> None:
             {
                 species.species_id + "_time": species.time
                 for species in meas.species_data
+                if len(species.time) > 0
             }
         )
     except ValueError: