petab1to2: allow skipping validation

petab/v2/petab1to2.py

@@ -16,15 +16,19 @@
 
 from .. import v1, v2
 from ..v1.math import sympify_petab
-from ..v1.yaml import get_path_prefix, load_yaml, validate
+from ..v1.yaml import get_path_prefix, load_yaml
+from ..v1.yaml import validate as validate_yaml
 from ..versions import get_major_version
 from .models import MODEL_TYPE_SBML
 
 __all__ = ["petab1to2"]
 
 
 def petab1to2(
-    yaml_config: Path | str, output_dir: Path | str | None = None
+    yaml_config: Path | str,
+    output_dir: Path | str | None = None,
+    *,
+    validate: bool = True,
 ) -> v2.Problem | None:
     """Convert from PEtab 1.0 to PEtab 2.0 format.
 
@@ -46,31 +50,45 @@ def petab1to2(
     :param output_dir:
         The output directory to save the converted PEtab problem, or ``None``,
         to return a :class:`petab.v2.Problem` instance.
+    :param validate:
+        Whether to lint the input PEtab v1 problem, and the
+        output PEtab v2 problem.
+        If ``True`` (default), both problems are validated.
+        If ``False``, neither problem is validated.
+        The ``yaml_config`` content is validated regardless.
 
     :raises ValueError:
-        If the input is invalid or does not pass linting or if the generated
-        files do not pass linting.
+        If the input is invalid or, if ``validate`` is ``True``, if the input
+        does not pass linting or if the generated files do not pass linting.
     """
     if output_dir is not None:
-        return petab_files_1to2(yaml_config, output_dir)
+        return petab_files_1to2(yaml_config, output_dir, validate=validate)
 
     with TemporaryDirectory() as tmp_dir:
-        petab_files_1to2(yaml_config, tmp_dir)
+        petab_files_1to2(yaml_config, tmp_dir, validate=validate)
         return v2.Problem.from_yaml(Path(tmp_dir, Path(yaml_config).name))
 
 
-def petab_files_1to2(yaml_config: Path | str | dict, output_dir: Path | str):
+def petab_files_1to2(
+    yaml_config: Path | str | dict,
+    output_dir: Path | str,
+    *,
+    validate: bool = True,
+):
     """Convert PEtab files from PEtab 1.0 to PEtab 2.0.
 
 
     :param yaml_config:
         The PEtab problem as dictionary or YAML file name.
     :param output_dir:
         The output directory to save the converted PEtab problem.
+    :param validate:
+        Whether to lint the PEtab v1 problem before and the generated
+        PEtab v2 problem after the conversion. See :func:`petab1to2`.
 
     :raises ValueError:
-        If the input is invalid or does not pass linting or if the generated
-        files do not pass linting.
+        If the input is invalid or, if ``validate`` is ``True``, if the input
+        does not pass linting or if the generated files do not pass linting.
     """
     if isinstance(yaml_config, Path | str):
         yaml_file = str(yaml_config)
@@ -85,7 +103,7 @@ def petab_files_1to2(yaml_config: Path | str | dict, output_dir: Path | str):
     get_dest_path = lambda filename: f"{output_dir}/{filename}"  # noqa: E731
 
     # Validate the original PEtab problem
-    validate(yaml_config, path_prefix=path_prefix)
+    validate_yaml(yaml_config, path_prefix=path_prefix)
     if get_major_version(yaml_config) != 1:
         raise ValueError("PEtab problem is not version 1.")
     petab_problem = v1.Problem.from_yaml(yaml_file or yaml_config)
@@ -94,7 +112,7 @@ def petab_files_1to2(yaml_config: Path | str | dict, output_dir: Path | str):
     petab_problem.condition_df = petab_problem.condition_df.drop(
         columns=[v1.C.CONDITION_NAME], errors="ignore"
     )
-    if v1.lint_problem(petab_problem):
+    if validate and v1.lint_problem(petab_problem):
         raise ValueError("Provided PEtab problem does not pass linting.")
 
     output_dir = Path(output_dir)
@@ -242,6 +260,9 @@ def create_experiment_id(sim_cond_id: str, preeq_cond_id: str) -> str:
     new_yaml_file = output_dir / Path(yaml_file).name
     new_yaml_config.to_yaml(new_yaml_file)
 
+    if not validate:
+        return
+
     # validate updated Problem
     validation_issues = v2.lint_problem(new_yaml_file)
 

tests/v2/test_conversion.py

@@ -1,4 +1,5 @@
 import logging
+from pathlib import Path
 
 import pandas as pd
 import pytest
@@ -170,6 +171,73 @@ def test_petab1to2_empty_conditions_no_preequilibration(tmp_path):
     assert _measured_periods(problem) == [None]
 
 
+def test_petab1to2_validate(tmp_path):
+    """Test that `validate=False` allows converting problems that fail
+    linting for reasons unrelated to the conversion."""
+    v1_problem = v1.Problem(
+        model=SbmlModel.from_antimony(
+            "A -> B; k1 * A; A = 1; B = 0; k1 = 0.5"
+        ),
+        condition_df=v1.get_condition_df(
+            pd.DataFrame({v1.C.CONDITION_ID: ["c0"], "A": [1.0]})
+        ),
+        observable_df=v1.get_observable_df(
+            pd.DataFrame(
+                {
+                    v1.C.OBSERVABLE_ID: ["obs_B"],
+                    v1.C.OBSERVABLE_FORMULA: ["B"],
+                    v1.C.NOISE_FORMULA: [0.1],
+                }
+            )
+        ),
+        measurement_df=v1.get_measurement_df(
+            pd.DataFrame(
+                {
+                    v1.C.OBSERVABLE_ID: ["obs_B", "obs_B"],
+                    v1.C.SIMULATION_CONDITION_ID: ["c0", "c0"],
+                    v1.C.TIME: [1.0, 2.0],
+                    v1.C.MEASUREMENT: [0.3, 0.5],
+                    v1.C.DATASET_ID: ["d1", "d1"],
+                }
+            )
+        ),
+        parameter_df=v1.get_parameter_df(
+            pd.DataFrame(
+                {
+                    v1.C.PARAMETER_ID: ["k1"],
+                    v1.C.PARAMETER_SCALE: [v1.C.LIN],
+                    v1.C.LOWER_BOUND: [1e-3],
+                    v1.C.UPPER_BOUND: [1e3],
+                    v1.C.NOMINAL_VALUE: [0.5],
+                    v1.C.ESTIMATE: [1],
+                }
+            )
+        ),
+        # refers to a dataset that is not in the measurement table
+        visualization_df=pd.DataFrame(
+            {
+                v1.C.PLOT_ID: ["p1"],
+                v1.C.DATASET_ID: ["no_such_dataset"],
+                v1.C.X_VALUES: [v1.C.TIME],
+            }
+        ),
+    )
+    yaml_file = v1_problem.to_files_generic(tmp_path / "v1")
+
+    with pytest.raises(ValueError, match="does not pass linting"):
+        petab1to2(yaml_file)
+
+    problem = petab1to2(yaml_file, validate=False)
+    assert isinstance(problem, Problem)
+    assert len(problem.measurements) == 2
+
+    output_dir = tmp_path / "v2"
+    output_dir.mkdir()
+    petab1to2(yaml_file, output_dir, validate=False)
+    problem = Problem.from_yaml(output_dir / Path(yaml_file).name)
+    assert len(problem.measurements) == 2
+
+
 try:
     import benchmark_models_petab