Remove deprecated generator data

docs/source/api/data.rst

@@ -10,5 +10,4 @@ Data
    MutableData
    get_data
    Data
-   GeneratorAdapter
    Minibatch

pymc/data.py

@@ -33,18 +33,16 @@
 from pytensor.scalar import Cast
 from pytensor.tensor.elemwise import Elemwise
 from pytensor.tensor.random.basic import IntegersRV
-from pytensor.tensor.type import TensorType
 from pytensor.tensor.variable import TensorConstant, TensorVariable
 
 import pymc as pm
 
-from pymc.pytensorf import GeneratorOp, convert_data, smarttypeX
+from pymc.pytensorf import convert_data
 from pymc.vartypes import isgenerator
 
 __all__ = [
     "ConstantData",
     "Data",
-    "GeneratorAdapter",
     "Minibatch",
     "MutableData",
     "get_data",
@@ -86,51 +84,6 @@ def clone(self):
         return cp
 
 
-class GeneratorAdapter:
-    """Class that helps infer data type of generator.
-
-    It looks at the first item, preserving the order of the resulting generator.
-    """
-
-    def make_variable(self, gop, name=None):
-        var = GenTensorVariable(gop, self.tensortype, name)
-        var.tag.test_value = self.test_value
-        return var
-
-    def __init__(self, generator):
-        if not pm.vartypes.isgenerator(generator):
-            raise TypeError("Object should be generator like")
-        self.test_value = smarttypeX(copy(next(generator)))
-        # make pickling potentially possible
-        self._yielded_test_value = False
-        self.gen = generator
-        self.tensortype = TensorType(self.test_value.dtype, ((False,) * self.test_value.ndim))
-
-    # python3 generator
-    def __next__(self):
-        """Next value in the generator."""
-        if not self._yielded_test_value:
-            self._yielded_test_value = True
-            return self.test_value
-        else:
-            return smarttypeX(copy(next(self.gen)))
-
-    # python2 generator
-    next = __next__
-
-    def __iter__(self):
-        """Return an iterator."""
-        return self
-
-    def __eq__(self, other):
-        """Return true if both objects are actually the same."""
-        return id(self) == id(other)
-
-    def __hash__(self):
-        """Return a hash of the object."""
-        return hash(id(self))
-
-
 class MinibatchIndexRV(IntegersRV):
     _print_name = ("minibatch_index", r"\operatorname{minibatch\_index}")
 
@@ -170,8 +123,6 @@ def is_valid_observed(v) -> bool:
             isinstance(v.owner.op, MinibatchOp)
             and all(is_valid_observed(inp) for inp in v.owner.inputs)
         )
-        # Or Generator
-        or isinstance(v.owner.op, GeneratorOp)
     )
 
 

pymc/pytensorf.py

@@ -36,7 +36,6 @@
     walk,
 )
 from pytensor.graph.fg import FunctionGraph, Output
-from pytensor.graph.op import Op
 from pytensor.scalar.basic import Cast
 from pytensor.scan.op import Scan
 from pytensor.tensor.basic import _as_tensor_variable
@@ -63,10 +62,8 @@
     "compile_pymc",
     "cont_inputs",
     "convert_data",
-    "convert_generator_data",
     "convert_observed_data",
     "floatX",
-    "generator",
     "gradient",
     "hessian",
     "hessian_diag",
@@ -81,20 +78,10 @@
 def convert_observed_data(data) -> np.ndarray | Variable:
     """Convert user provided dataset to accepted formats."""
     if isgenerator(data):
-        return convert_generator_data(data)
+        raise TypeError("Data passed to `observed` cannot be a generator.")
     return convert_data(data)
 
 
-def convert_generator_data(data) -> TensorVariable:
-    warnings.warn(
-        "Generator data is deprecated and we intend to remove it."
-        " If you disagree and need this, please get in touch via https://github.com/pymc-devs/pymc/issues.",
-        DeprecationWarning,
-        stacklevel=2,
-    )
-    return generator(data)
-
-
 def convert_data(data) -> np.ndarray | Variable:
     ret: np.ndarray | Variable
     if hasattr(data, "to_numpy") and hasattr(data, "isnull"):
@@ -625,98 +612,6 @@
         return pytensor.clone_replace(self.tensor, {oldinput: input}, rebuild_strict=False)
 
 
-class GeneratorOp(Op):
-    """
-    Generator Op is designed for storing python generators inside pytensor graph.
-
-    __call__ creates TensorVariable
-        It has 2 new methods
-        - var.set_gen(gen): sets new generator
-        - var.set_default(value): sets new default value (None erases default value)
-
-    If generator is exhausted, variable will produce default value if it is not None,
-    else raises `StopIteration` exception that can be caught on runtime.
-
-    Parameters
-    ----------
-    gen: generator that implements __next__ (py3) or next (py2) method
-        and yields np.arrays with same types
-    default: np.array with the same type as generator produces
-    """
-
-    __props__ = ("generator",)
-
-    def __init__(self, gen, default=None):
-        warnings.warn(
-            "generator data is deprecated and will be removed in a future release", FutureWarning
-        )
-        from pymc.data import GeneratorAdapter
-
-        super().__init__()
-        if not isinstance(gen, GeneratorAdapter):
-            gen = GeneratorAdapter(gen)
-        self.generator = gen
-        self.set_default(default)
-
-    def make_node(self, *inputs):
-        gen_var = self.generator.make_variable(self)
-        return Apply(self, [], [gen_var])
-
-    def perform(self, node, inputs, output_storage, params=None):
-        if self.default is not None:
-            output_storage[0][0] = next(self.generator, self.default)
-        else:
-            output_storage[0][0] = next(self.generator)
-
-    def do_constant_folding(self, fgraph, node):
-        return False
-
-    __call__ = pytensor.config.change_flags(compute_test_value="off")(Op.__call__)
-
-    def set_gen(self, gen):
-        from pymc.data import GeneratorAdapter
-
-        if not isinstance(gen, GeneratorAdapter):
-            gen = GeneratorAdapter(gen)
-        if not gen.tensortype == self.generator.tensortype:
-            raise ValueError("New generator should yield the same type")
-        self.generator = gen
-
-    def set_default(self, value):
-        if value is None:
-            self.default = None
-        else:
-            value = np.asarray(value, self.generator.tensortype.dtype)
-            t1 = (False,) * value.ndim
-            t2 = self.generator.tensortype.broadcastable
-            if not t1 == t2:
-                raise ValueError("Default value should have the same type as generator")
-            self.default = value
-
-
-def generator(gen, default=None):
-    """
-    Create a generator variable with possibility to set default value and new generator.
-
-    If generator is exhausted variable will produce default value if it is not None,
-    else raises `StopIteration` exception that can be caught on runtime.
-
-    Parameters
-    ----------
-    gen: generator that implements __next__ (py3) or next (py2) method
-        and yields np.arrays with same types
-    default: np.array with the same type as generator produces
-
-    Returns
-    -------
-    TensorVariable
-        It has 2 new methods
-        - var.set_gen(gen): sets new generator
-        - var.set_default(value): sets new default value (None erases default value)
-    """
-    return GeneratorOp(gen, default)()
-
-
 def ix_(*args):
     """
     PyTensor np.ix_ analog.

tests/test_data.py

@@ -13,11 +13,9 @@
 #   limitations under the License.
 
 import io
-import itertools as it
 
 from os import path
 
-import cloudpickle
 import numpy as np
 import pytensor
 import pytensor.tensor as pt
@@ -29,7 +27,7 @@
 import pymc as pm
 
 from pymc.data import MinibatchOp
-from pymc.pytensorf import GeneratorOp, floatX
+from pymc.pytensorf import floatX
 
 
 class TestData:
@@ -495,97 +493,6 @@ def integers_ndim(ndim):
         i += 1
 
 
-@pytest.mark.usefixtures("strict_float32")
-class TestGenerator:
-    def test_basic(self):
-        generator = pm.GeneratorAdapter(integers())
-        gop = GeneratorOp(generator)()
-        assert gop.tag.test_value == np.float32(0)
-        f = pytensor.function([], gop)
-        assert f() == np.float32(0)
-        assert f() == np.float32(1)
-        for _ in range(2, 100):
-            f()
-        assert f() == np.float32(100)
-
-    def test_ndim(self):
-        for ndim in range(10):
-            res = list(it.islice(integers_ndim(ndim), 0, 2))
-            generator = pm.GeneratorAdapter(integers_ndim(ndim))
-            gop = GeneratorOp(generator)()
-            f = pytensor.function([], gop)
-            assert ndim == res[0].ndim
-            np.testing.assert_equal(f(), res[0])
-            np.testing.assert_equal(f(), res[1])
-
-    def test_cloning_available(self):
-        gop = pm.generator(integers())
-        res = gop**2
-        shared = pytensor.shared(pm.floatX(10))
-        res1 = pytensor.clone_replace(res, {gop: shared})
-        f = pytensor.function([], res1)
-        assert f() == np.float32(100)
-
-    def test_default_value(self):
-        def gen():
-            for i in range(2):
-                yield pm.floatX(np.ones((10, 10)) * i)
-
-        gop = pm.generator(gen(), np.ones((10, 10)) * 10)
-        f = pytensor.function([], gop)
-        np.testing.assert_equal(np.ones((10, 10)) * 0, f())
-        np.testing.assert_equal(np.ones((10, 10)) * 1, f())
-        np.testing.assert_equal(np.ones((10, 10)) * 10, f())
-        with pytest.raises(ValueError):
-            gop.set_default(1)
-
-    def test_set_gen_and_exc(self):
-        def gen():
-            for i in range(2):
-                yield pm.floatX(np.ones((10, 10)) * i)
-
-        gop = pm.generator(gen())
-        f = pytensor.function([], gop)
-        np.testing.assert_equal(np.ones((10, 10)) * 0, f())
-        np.testing.assert_equal(np.ones((10, 10)) * 1, f())
-        with pytest.raises(StopIteration):
-            f()
-        gop.set_gen(gen())
-        np.testing.assert_equal(np.ones((10, 10)) * 0, f())
-        np.testing.assert_equal(np.ones((10, 10)) * 1, f())
-
-    def test_pickling(self, datagen):
-        gen = pm.generator(datagen)
-        cloudpickle.loads(cloudpickle.dumps(gen))
-        bad_gen = pm.generator(integers())
-        with pytest.raises(TypeError):
-            cloudpickle.dumps(bad_gen)
-
-    def test_gen_cloning_with_shape_change(self, datagen):
-        gen = pm.generator(datagen)
-        gen_r = pt.random.normal(size=gen.shape).T
-        X = gen.dot(gen_r)
-        res, _ = pytensor.scan(lambda x: x.sum(), X, n_steps=X.shape[0])
-        assert res.eval().shape == (50,)
-        shared = pytensor.shared(datagen.data.astype(gen.dtype))
-        res2 = pytensor.clone_replace(res, {gen: shared**2})
-        assert res2.eval().shape == (1000,)
-
-
-def gen1():
-    i = 0
-    while True:
-        yield np.ones((10, 100)) * i
-        i += 1
-
-
-def gen2():
-    i = 0
-    while True:
-        yield np.ones((20, 100)) * i
-        i += 1
-
-
 @pytest.mark.usefixtures("strict_float32")
 class TestMinibatch:
     data = np.random.rand(30, 10)