Update petab.v2 (#361)

* Adapt petab.v2 to the updated specs draft.

* Make the new pydantic objects the primary objects and generate the DataFrames only on demand. 

Validation is still a bit rough. We'll need nicer error messages and pydantic settings are too lax for validating files.

Author: dweindl

doc/modules.rst

@@ -16,6 +16,7 @@ API Reference
    petab.v1.core
    petab.v1.distributions
    petab.v1.lint
+   petab.v1.math
    petab.v1.measurements
    petab.v1.models
    petab.v1.observables

petab/v1/lint.py

@@ -53,6 +53,9 @@
     "observable_table_has_nontrivial_noise_formula",
 ]
 
+#: Regular expression pattern for valid PEtab IDs
+_petab_id_pattern = re.compile(r"^[a-zA-Z_]\w*$")
+
 
 def _check_df(df: pd.DataFrame, req_cols: Iterable, name: str) -> None:
     """Check if given columns are present in DataFrame
@@ -1041,10 +1044,13 @@ def assert_model_parameters_in_condition_or_parameter_table(
                 mapping_df[MODEL_ENTITY_ID],
                 strict=True,
             )
-            # mapping table entities mapping to already allowed parameters
-            if to_id in allowed_in_condition_cols
-            # mapping table entities mapping to species
-            or model.is_state_variable(to_id)
+            if not pd.isna(to_id)
+            and (
+                # mapping table entities mapping to already allowed parameters
+                to_id in allowed_in_condition_cols
+                # mapping table entities mapping to species
+                or model.is_state_variable(to_id)
+            )
         }
 
     allowed_in_parameter_table = (
@@ -1186,7 +1192,7 @@ def is_valid_identifier(x: str) -> bool:
     if pd.isna(x):
         return False
 
-    return re.match(r"^[a-zA-Z_]\w*$", x) is not None
+    return _petab_id_pattern.match(x) is not None
 
 
 def check_ids(ids: Iterable[str], kind: str = "") -> None:

petab/v1/math/sympify.py

@@ -15,6 +15,11 @@
 def sympify_petab(expr: str | int | float) -> sp.Expr | sp.Basic:
     """Convert PEtab math expression to sympy expression.
 
+    .. note::
+
+        All symbols in the returned expression will have the `real=True`
+        assumption.
+
     Args:
         expr: PEtab math expression.
 
@@ -26,14 +31,22 @@ def sympify_petab(expr: str | int | float) -> sp.Expr | sp.Basic:
         The sympy expression corresponding to `expr`.
         Boolean values are converted to numeric values.
     """
+    if isinstance(expr, sp.Expr):
+        # TODO: check if only PEtab-compatible symbols and functions are used
+        return expr
+
     if isinstance(expr, int) or isinstance(expr, np.integer):
         return sp.Integer(expr)
     if isinstance(expr, float) or isinstance(expr, np.floating):
         return sp.Float(expr)
 
-    # Set error listeners
-    input_stream = InputStream(expr)
+    try:
+        input_stream = InputStream(expr)
+    except TypeError as e:
+        raise TypeError(f"Error parsing {expr!r}: {e.args[0]}") from e
+
     lexer = PetabMathExprLexer(input_stream)
+    # Set error listeners
     lexer.removeErrorListeners()
     lexer.addErrorListener(MathErrorListener())
 

petab/v2/C.py

@@ -125,28 +125,14 @@
 
 #: Condition ID column in the condition table
 CONDITION_ID = "conditionId"
-# TODO: removed?
-#: Condition name column in the condition table
-CONDITION_NAME = "conditionName"
 #: Column in the condition table with the ID of an entity that is changed
 TARGET_ID = "targetId"
-#: Column in the condition table with the operation type
-OPERATION_TYPE = "operationType"
 #: Column in the condition table with the new value of the target entity
 TARGET_VALUE = "targetValue"
-# operation types:
-OT_CUR_VAL = "setCurrentValue"
-OT_NO_CHANGE = "noChange"
-
-OPERATION_TYPES = [
-    OT_CUR_VAL,
-    OT_NO_CHANGE,
-]
 
 CONDITION_DF_COLS = [
     CONDITION_ID,
     TARGET_ID,
-    OPERATION_TYPE,
     TARGET_VALUE,
 ]
 
@@ -161,25 +147,25 @@
 
 # OBSERVABLES
 
-#: Observable name column in the observables table
+#: Observable name column in the observable table
 OBSERVABLE_NAME = "observableName"
-#: Observable formula column in the observables table
+#: Observable formula column in the observable table
 OBSERVABLE_FORMULA = "observableFormula"
-#: Noise formula column in the observables table
+#: Noise formula column in the observable table
 NOISE_FORMULA = "noiseFormula"
-#: Observable transformation column in the observables table
+#: Observable transformation column in the observable table
 OBSERVABLE_TRANSFORMATION = "observableTransformation"
-#: Noise distribution column in the observables table
+#: Noise distribution column in the observable table
 NOISE_DISTRIBUTION = "noiseDistribution"
 
-#: Mandatory columns of observables table
+#: Mandatory columns of observable table
 OBSERVABLE_DF_REQUIRED_COLS = [
     OBSERVABLE_ID,
     OBSERVABLE_FORMULA,
     NOISE_FORMULA,
 ]
 
-#: Optional columns of observables table
+#: Optional columns of observable table
 OBSERVABLE_DF_OPTIONAL_COLS = [
     OBSERVABLE_NAME,
     OBSERVABLE_TRANSFORMATION,
@@ -382,14 +368,17 @@
 PETAB_ENTITY_ID = "petabEntityId"
 #: Model entity ID column in the mapping table
 MODEL_ENTITY_ID = "modelEntityId"
+#: Arbitrary name
+NAME = "name"
+
 #: Required columns of the mapping table
 MAPPING_DF_REQUIRED_COLS = [PETAB_ENTITY_ID, MODEL_ENTITY_ID]
 
 # MORE
 
 #: Simulated value column in the simulation table
 SIMULATION = "simulation"
-#: Residual value column in the residuals table
+#: Residual value column in the residual table
 RESIDUAL = "residual"
 #: ???
 NOISE_VALUE = "noiseValue"

petab/v2/__init__.py

@@ -5,27 +5,31 @@
 
 from warnings import warn
 
-# TODO: remove v1 star imports
-from ..v1.calculate import *  # noqa: F403, F401, E402
-from ..v1.composite_problem import *  # noqa: F403, F401, E402
-from ..v1.core import *  # noqa: F403, F401, E402
-from ..v1.format_version import __format_version__  # noqa: F401, E402
-from ..v1.mapping import *  # noqa: F403, F401, E402
-from ..v1.measurements import *  # noqa: F403, F401, E402
-from ..v1.observables import *  # noqa: F403, F401, E402
-from ..v1.parameter_mapping import *  # noqa: F403, F401, E402
-from ..v1.parameters import *  # noqa: F403, F401, E402
-from ..v1.sampling import *  # noqa: F403, F401, E402
-from ..v1.sbml import *  # noqa: F403, F401, E402
-from ..v1.simulate import *  # noqa: F403, F401, E402
-from ..v1.yaml import *  # noqa: F403, F401, E402
-
 warn(
     "Support for PEtab2.0 and all of petab.v2 is experimental "
     "and subject to changes!",
     stacklevel=1,
 )
 
+# TODO: move this module to v2
+from petab.v1.mapping import (  # noqa: F403, F401, E402
+    get_mapping_df,
+    write_mapping_df,
+)
+from petab.v1.measurements import (  # noqa: F401, E402
+    get_measurement_df,
+    write_measurement_df,
+)
+from petab.v1.observables import (  # noqa: F401, E402
+    get_observable_df,
+    write_observable_df,
+)
+from petab.v1.parameters import (  # noqa: F401, E402
+    get_parameter_df,
+    write_parameter_df,
+)
+from petab.v1.yaml import load_yaml  # noqa: F401, E402
+
 # import after v1
 from ..version import __version__  # noqa: F401, E402
 from . import (  # noqa: F401, E402
@@ -38,5 +42,5 @@
     write_experiment_df,
 )
 from .lint import lint_problem  # noqa: F401, E402
-from .models import Model  # noqa: F401, E402
-from .problem import Problem  # noqa: F401, E402
+from .models import MODEL_TYPE_PYSB, MODEL_TYPE_SBML, Model  # noqa: F401, E402
+from .problem import Problem, ProblemConfig  # noqa: F401, E402

petab/v2/conditions.py

@@ -5,12 +5,8 @@
 from pathlib import Path
 
 import pandas as pd
-import sympy as sp
 
-from .. import v2
-from ..v1.math import sympify_petab
-from .C import *
-from .lint import assert_no_leading_trailing_whitespace
+from ..v1.lint import assert_no_leading_trailing_whitespace
 
 __all__ = [
     "get_condition_df",
@@ -50,19 +46,3 @@ def write_condition_df(df: pd.DataFrame, filename: str | Path) -> None:
     """
     df = get_condition_df(df)
     df.to_csv(filename, sep="\t", index=False)
-
-
-def get_condition_table_free_symbols(problem: v2.Problem) -> set[sp.Basic]:
-    """Free symbols from condition table assignments.
-
-    Collects all free symbols from the condition table `targetValue` column.
-
-    :returns: Set of free symbols.
-    """
-    if problem.condition_df is None:
-        return set()
-
-    free_symbols = set()
-    for target_value in problem.condition_df[TARGET_VALUE]:
-        free_symbols |= sympify_petab(target_value).free_symbols
-    return free_symbols