Add petab-compatible sympy string-printer

Add a sympy Printer to stringify sympy expressions in a petab-compatible way.
For example, we need to avoid `str(sympy.sympify("x^2"))` -> `'x**2'`.

Closes PEtab-dev#362.

Author: dweindl

petab/v1/math/__init__.py

@@ -1,3 +1,4 @@
 """Functions for parsing and evaluating mathematical expressions."""
 
+from .printer import PetabStrPrinter, petab_math_str  # noqa: F401
 from .sympify import sympify_petab  # noqa: F401

petab/v1/math/printer.py

@@ -0,0 +1,91 @@
+"""A PEtab-compatible sympy string-printer."""
+
+from itertools import chain, islice
+
+import sympy as sp
+from sympy.printing.str import StrPrinter
+
+
+class PetabStrPrinter(StrPrinter):
+    """A PEtab-compatible sympy string-printer."""
+
+    #: Mapping of sympy functions to PEtab functions
+    _func_map = {
+        "asin": "arcsin",
+        "acos": "arccos",
+        "atan": "arctan",
+        "acot": "arccot",
+        "asec": "arcsec",
+        "acsc": "arccsc",
+        "asinh": "arcsinh",
+        "acosh": "arccosh",
+        "atanh": "arctanh",
+        "acoth": "arccoth",
+        "asech": "arcsech",
+        "acsch": "arccsch",
+        "Abs": "abs",
+    }
+
+    def _print_BooleanTrue(self, expr):
+        return "true"
+
+    def _print_BooleanFalse(self, expr):
+        return "false"
+
+    def _print_Pow(self, expr: sp.Pow):
+        """Custom printing for the power operator"""
+        base, exp = expr.as_base_exp()
+        return f"{self._print(base)} ^ {self._print(exp)}"
+
+    def _print_Infinity(self, expr):
+        """Custom printing for infinity"""
+        return "inf"
+
+    def _print_NegativeInfinity(self, expr):
+        """Custom printing for negative infinity"""
+        return "-inf"
+
+    def _print_Function(self, expr):
+        """Custom printing for specific functions"""
+
+        if expr.func.__name__ == "Piecewise":
+            return self._print_Piecewise(expr)
+
+        if func := self._func_map.get(expr.func.__name__):
+            return f"{func}({', '.join(map(self._print, expr.args))})"
+
+        return super()._print_Function(expr)
+
+    def _print_Piecewise(self, expr):
+        """Custom printing for Piecewise function"""
+        # merge the tuples and drop the final `True` condition
+        str_args = map(
+            self._print,
+            islice(chain.from_iterable(expr.args), 2 * len(expr.args) - 1),
+        )
+        return f"piecewise({', '.join(str_args)})"
+
+    def _print_Min(self, expr):
+        """Custom printing for Min function"""
+        return f"min({', '.join(map(self._print, expr.args))})"
+
+    def _print_Max(self, expr):
+        """Custom printing for Max function"""
+        return f"max({', '.join(map(self._print, expr.args))})"
+
+
+def petab_math_str(expr: sp.Basic | sp.Expr | None) -> str:
+    """Convert a sympy expression to a PEtab-compatible math expression string.
+
+    :example:
+    >>> expr = sp.sympify("x**2 + sin(y)")
+    >>> petab_math_str(expr)
+    'x ^ 2 + sin(y)'
+    >>> expr = sp.sympify("Piecewise((1, x > 0), (0, True))")
+    >>> petab_math_str(expr)
+    'piecewise(1, x > 0, 0)'
+    """
+    if expr is None:
+        return ""
+
+    return PetabStrPrinter().doprint(expr)

petab/v1/math/sympify.py

@@ -5,6 +5,7 @@
 from antlr4 import CommonTokenStream, InputStream
 from antlr4.error.ErrorListener import ErrorListener
 
+from . import petab_math_str
 from ._generated.PetabMathExprLexer import PetabMathExprLexer
 from ._generated.PetabMathExprParser import PetabMathExprParser
 from .SympyVisitor import MathVisitorSympy, bool2num
@@ -13,30 +14,30 @@
 
 
 def sympify_petab(
-    expr: str | int | float, evaluate: bool = True
+    expr: str | int | float | sp.Basic, evaluate: bool = True
 ) -> 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.
         evaluate: Whether to evaluate the expression.
 
     Raises:
         ValueError: Upon lexer/parser errors or if the expression is
-        otherwise invalid.
+            otherwise invalid.
 
     Returns:
         The sympy expression corresponding to `expr`.
         Boolean values are converted to numeric values.
 
+        .. note::
+
+          All symbols in the returned expression will have the ``real=True``
+          assumption.
 
     :example:
-    >>> from petab.math import sympify_petab
+    >>> from petab.v1.math import sympify_petab
     >>> sympify_petab("sin(0)")
     0
     >>> sympify_petab("sin(0)", evaluate=False)
@@ -61,9 +62,8 @@ def sympify_petab(
     >>> sympify_petab("2", evaluate=True)
     2.00000000000000
     """
-    if isinstance(expr, sp.Expr):
-        # TODO: check if only PEtab-compatible symbols and functions are used
-        return expr
+    if isinstance(expr, sp.Basic):
+        return sympify_petab(petab_math_str(expr))
 
     if isinstance(expr, int) or isinstance(expr, np.integer):
         return sp.Integer(expr)
@@ -95,10 +95,17 @@ def sympify_petab(
     visitor = MathVisitorSympy(evaluate=evaluate)
     expr = visitor.visit(tree)
     expr = bool2num(expr)
-    # check for `False`, we'll accept both `True` and `None`
-    if expr.is_extended_real is False:
-        raise ValueError(f"Expression {expr} is not real-valued.")
-
+    try:
+        # check for `False`, we'll accept both `True` and `None`
+        if expr.is_extended_real is False:
+            raise ValueError(f"Expression {expr} is not real-valued.")
+    except AttributeError as e:
+        # work-around for `sp.sec(0, evaluate=False).is_extended_real` error
+        if str(e) not in (
+            "'One' object has no attribute '_eval_is_extended_real'",
+            "'Float' object has no attribute '_eval_is_extended_real'",
+        ):
+            raise
     return expr
 
 

petab/v2/core.py

@@ -25,7 +25,7 @@
 from typing_extensions import Self
 
 from ..v1.lint import is_valid_identifier
-from ..v1.math import sympify_petab
+from ..v1.math import petab_math_str, sympify_petab
 from . import C, get_observable_df
 
 __all__ = [
@@ -273,23 +273,8 @@ def to_df(self) -> pd.DataFrame:
         for record in records:
             obs = record[C.OBSERVABLE_FORMULA]
             noise = record[C.NOISE_FORMULA]
-            record[C.OBSERVABLE_FORMULA] = (
-                None
-                if obs is None
-                # TODO: we need a custom printer for sympy expressions
-                #  to avoid '**'
-                #  https://github.com/PEtab-dev/libpetab-python/issues/362
-                else str(obs)
-                if not obs.is_number
-                else float(obs)
-            )
-            record[C.NOISE_FORMULA] = (
-                None
-                if noise is None
-                else str(noise)
-                if not noise.is_number
-                else float(noise)
-            )
+            record[C.OBSERVABLE_FORMULA] = petab_math_str(obs)
+            record[C.NOISE_FORMULA] = petab_math_str(noise)
         return pd.DataFrame(records).set_index([C.OBSERVABLE_ID])
 
     @classmethod

tests/v1/math/test_math.py

@@ -6,9 +6,9 @@
 import sympy as sp
 import yaml
 from sympy.abc import _clash
-from sympy.logic.boolalg import Boolean
+from sympy.logic.boolalg import Boolean, BooleanFalse, BooleanTrue
 
-from petab.math import sympify_petab
+from petab.v1.math import petab_math_str, sympify_petab
 
 
 def test_sympify_numpy():
@@ -29,6 +29,20 @@ def test_evaluate():
     assert str(act) == "Piecewise((1.0, 1.0 > 2.0), (0.0, True))"
 
 
+def test_assumptions():
+    # in PEtab, all symbols are expected to be real-valued
+    assert sympify_petab("x").is_real
+
+    # non-real symbols are changed to real
+    assert sympify_petab(sp.Symbol("x", real=False)).is_real
+
+
+def test_printer():
+    assert petab_math_str(None) == ""
+    assert petab_math_str(BooleanTrue()) == "true"
+    assert petab_math_str(BooleanFalse()) == "false"
+
+
 def read_cases():
     """Read test cases from YAML file in the petab_test_suite package."""
     yaml_file = importlib.resources.files("petabtests.cases").joinpath(
@@ -60,29 +74,35 @@ def read_cases():
 @pytest.mark.parametrize("expr_str, expected", read_cases())
 def test_parse_cases(expr_str, expected):
     """Test PEtab math expressions for the PEtab test suite."""
-    result = sympify_petab(expr_str)
-    if isinstance(result, Boolean):
-        assert result == expected
+    sym_expr = sympify_petab(expr_str)
+    if isinstance(sym_expr, Boolean):
+        assert sym_expr == expected
     else:
         try:
-            result = float(result.evalf())
+            result = float(sym_expr.evalf())
             assert np.isclose(result, expected), (
                 f"{expr_str}: Expected {expected}, got {result}"
             )
         except TypeError:
-            assert result == expected, (
+            assert sym_expr == expected, (
                 f"{expr_str}: Expected {expected}, got {result}"
             )
 
+    # test parsing, printing, and parsing again
+    resympified = sympify_petab(petab_math_str(sym_expr))
+    if sym_expr.is_number:
+        assert np.isclose(float(resympified), float(sym_expr))
+    else:
+        assert resympified.equals(sym_expr), (sym_expr, resympified)
+
 
 def test_ids():
     """Test symbols in expressions."""
     assert sympify_petab("bla * 2") == 2.0 * sp.Symbol("bla", real=True)
 
     # test that sympy expressions that are invalid in PEtab raise an error
-    # TODO: handle these cases after
-    #   https://github.com/PEtab-dev/libpetab-python/pull/364
-    # sympify_petab(sp.Symbol("föö"))
+    with pytest.raises(ValueError):
+        sympify_petab(sp.Symbol("föö"))
 
 
 def test_syntax_error():

tests/v2/test_problem.py

@@ -133,7 +133,9 @@ def test_modify_problem():
         }
     ).set_index([OBSERVABLE_ID])
     assert_frame_equal(
-        problem.observable_df[[OBSERVABLE_FORMULA, NOISE_FORMULA]],
+        problem.observable_df[[OBSERVABLE_FORMULA, NOISE_FORMULA]].map(
+            lambda x: float(x) if x != "" else None
+        ),
         exp_observable_df,
         check_dtype=False,
     )