Feature: Expr and GenExpr support NumPy binary functions like np.add

[Zeroto521]

With this feature, we can do this now.

import numpy as np

from pyscipopt import Model

m = Model()
x = m.addVar("x")
print(x + np.array([1, 2]))
# Now
# [Expr({Term(x): 1.0, Term(): 1.0}) Expr({Term(x): 1.0, Term(): 2.0})]

# Before
# TypeError                                 Traceback (most recent call last)
# Cell In[3], line 6
#       4 m = Model()
#       5 x = m.addVar("x")
# ----> 6 x + np.array([1, 2])

# File src/pyscipopt/expr.pxi:206, in pyscipopt.scip.Expr.__add__()

# TypeError: Unsupported type <class 'numpy.ndarray'>

[Copilot]

Pull request overview

This PR extends PySCIPOpt’s expression types (Expr/GenExpr) to interoperate with NumPy ufuncs for common binary arithmetic (and np.negative), enabling expressions like x + np.array([...]) to produce arrays of PySCIPOpt expressions instead of raising TypeError.

Changes:

• Extend ExprLike.__array_ufunc__ to handle NumPy binary ufuncs (add/subtract/multiply/divide/true_divide/power) and np.negative, including a numeric-ndarray conversion path.
• Add _to_matrix helper to convert scalar Expr/GenExpr/number arguments into MatrixExpr/MatrixGenExpr for ufunc application.
• Add/adjust tests validating unary and binary ufunc behavior and update the changelog.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 3 comments.

File	Description
src/pyscipopt/expr.pxi	Implements NumPy ufunc dispatch for scalar Expr/GenExpr, including numeric-ndarray handling via matrix wrappers.
tests/test_expr.py	Adds coverage for np.negative and several binary ufuncs with scalar and np.ndarray inputs.
CHANGELOG.md	Documents newly supported NumPy ufunc interoperability.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

type(a) is np.ndarray only catches base ndarray instances; ndarray subclasses (e.g., np.matrix, masked arrays, or third-party subclasses) will bypass the numeric-array conversion path and may still fail for ufuncs like np.add/np.subtract. Consider switching to isinstance(a, np.ndarray) while explicitly excluding MatrixExpr/MatrixGenExpr (or checking a.__class__ is np.ndarray) so numeric subclasses get the same behavior without breaking existing Matrix* handling.

[Zeroto521]

Some subclasses will pass via isinstance. So here I only check np.ndarray with numeric dtype.