mergeron 2025.739265.0__tar.gz → 2025.739265.2__tar.gz

{mergeron-2025.739265.0 → mergeron-2025.739265.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: mergeron
-Version: 2025.739265.0
+Version: 2025.739265.2
 Summary: Analyze merger enforcement policy using Python
 License: MIT
 Keywords: merger policy analysis,merger guidelines,merger screening,policy presumptions,concentration standards,upward pricing pressure,GUPPI

{mergeron-2025.739265.0 → mergeron-2025.739265.2}/pyproject.toml

@@ -13,7 +13,7 @@ keywords = [
     "upward pricing pressure",
     "GUPPI",
 ]
-version = "2025.739265.0"
+version = "2025.739265.2"
 
 # Classifiers list: https://pypi.org/classifiers/
 classifiers = [
@@ -61,6 +61,7 @@ urllib3 = "^2.2.2"
 
 [tool.poetry.group.dev.dependencies]
 icecream = ">=2.1.0"
+jinja2 = ">=3.1.5"
 mypy = ">=1.8"
 openpyxl = ">=3.1.2"
 pendulum = ">=3.0.0"
@@ -74,8 +75,7 @@ sphinx-autoapi = ">=3.0"
 sphinx-immaterial = ">=0.11"
 pipdeptree = ">=2.15.1"
 types-openpyxl = ">=3.0.0"
-pyright = "^1.1.380"
-
+virtualenv = ">=20.28.0"
 [tool.ruff]
 
 # Exclude a variety of commonly ignored directories.

{mergeron-2025.739265.0 → mergeron-2025.739265.2}/src/mergeron/__init__.py

@@ -9,7 +9,7 @@ from numpy.typing import NDArray
 
 _PKG_NAME: str = Path(__file__).parent.stem
 
-VERSION = "2025.739265.0"
+VERSION = "2025.739265.2"
 
 __version__ = VERSION
 

{mergeron-2025.739265.0 → mergeron-2025.739265.2}/src/mergeron/core/__init__.py

@@ -4,5 +4,5 @@ from .. import VERSION  # noqa: TID252
 
 __version__ = VERSION
 
-type MPFloat = mp.mpf  # pyright: ignore
-type MPMatrix = mp.matrix  # pyright: ignore
+type MPFloat = mp.mpf  # type: ignore
+type MPMatrix = mp.matrix  # type: ignore

{mergeron-2025.739265.0 → mergeron-2025.739265.2}/src/mergeron/core/empirical_margin_distribution.py

@@ -132,7 +132,7 @@ def mgn_data_getter(  # noqa: PLR0912
         _xl_row[1] = int(_xl_row[1])
         _mgn_dict[_xl_row[0]] = dict(zip(_mgn_row_keys[1:], _xl_row[1:], strict=True))
 
-    _ = _data_archive_path.write_bytes(msgpack.packb(_mgn_dict))  # pyright: ignore
+    _ = _data_archive_path.write_bytes(msgpack.packb(_mgn_dict))
 
     return MappingProxyType(_mgn_dict)
 
@@ -221,7 +221,7 @@ def mgn_data_resampler(
     _x, _w, _ = mgn_data_builder(mgn_data_getter())
 
     _mgn_kde = stats.gaussian_kde(_x, weights=_w, bw_method="silverman")
-    _mgn_kde.set_bandwidth(bw_method=_mgn_kde.factor / 3.0)  # pyright: ignore
+    _mgn_kde.set_bandwidth(bw_method=_mgn_kde.factor / 3.0)
 
     if isinstance(_sample_size, int):
         return np.array(

{mergeron-2025.739265.0 → mergeron-2025.739265.2}/src/mergeron/core/ftc_merger_investigations_data.py

@@ -198,7 +198,7 @@ def construct_data(
                 )
             }
 
-    _ = INVDATA_ARCHIVE_PATH.write_bytes(msgpack.packb(_invdata))  # pyright: ignore
+    _ = INVDATA_ARCHIVE_PATH.write_bytes(msgpack.packb(_invdata))
 
     return MappingProxyType(_invdata)
 

{mergeron-2025.739265.0 → mergeron-2025.739265.2}/src/mergeron/core/guidelines_boundaries.py

@@ -156,7 +156,7 @@ class ConcentrationBoundary:
         "ΔHHI", "Combined share", "Pre-merger HHI", "Post-merger HHI"
     ] = field(kw_only=False, default="ΔHHI")
 
-    @measure_name.validator  # pyright: ignore
+    @measure_name.validator
     def __mnv(
         _instance: ConcentrationBoundary, _attribute: Attribute[str], _value: str, /
     ) -> None:
@@ -170,7 +170,7 @@ class ConcentrationBoundary:
 
     threshold: float = field(kw_only=False, default=0.01)
 
-    @threshold.validator  # pyright: ignore
+    @threshold.validator
     def __tv(
         _instance: ConcentrationBoundary, _attribute: Attribute[float], _value: float, /
     ) -> None:

{mergeron-2025.739265.0 → mergeron-2025.739265.2}/src/mergeron/core/guidelines_boundary_functions.py

@@ -909,7 +909,7 @@ def lerp[LerpT: (float, MPFloat, ArrayDouble, ArrayBIGINT)](
     elif _r == 1:
         return _x2
     else:
-        return _r * _x2 + (1 - _r) * _x1  # pyright: ignore
+        return _r * _x2 + (1 - _r) * _x1
 
 
 def round_cust(

{mergeron-2025.739265.0 → mergeron-2025.739265.2}/src/mergeron/core/guidelines_boundary_functions_extra.py

@@ -91,7 +91,7 @@ def hhi_delta_boundary_qdtr(_dh_val: float = 0.01, /) -> GuidelinesBoundaryCalla
 
     _hhi_bdry_area = 2 * (
         _s_nought
-        + mp.quad(lambdify(_s_1, _hhi_bdry, "mpmath"), (_s_nought, 1 - _s_nought))  # pyright: ignore
+        + mp.quad(lambdify(_s_1, _hhi_bdry, "mpmath"), (_s_nought, 1 - _s_nought))
     )
 
     return GuidelinesBoundaryCallable(
@@ -159,7 +159,7 @@ def shrratio_boundary_qdtr_wtd_avg(
                 2
                 * (
                     _s_naught
-                    + mp.quad(lambdify(_s_1, _bdry_func, "mpmath"), (_s_naught, _s_mid))  # pyright: ignore
+                    + mp.quad(lambdify(_s_1, _bdry_func, "mpmath"), (_s_naught, _s_mid))
                 )
                 - (_s_mid**2 + _s_naught**2)
             )
@@ -189,7 +189,7 @@ def shrratio_boundary_qdtr_wtd_avg(
                         ),
                         (0, _s_mid),
                     )
-                ).real  # pyright: ignore
+                ).real
                 - _s_mid**2
             )
 
@@ -209,7 +209,7 @@ def shrratio_boundary_qdtr_wtd_avg(
 
             _bdry_func = solve(_bdry_eqn, _s_2)[0]
             _bdry_area = float(
-                2 * (mp.quad(lambdify(_s_1, _bdry_func, "mpmath"), (0, _s_mid)))  # pyright: ignore
+                2 * (mp.quad(lambdify(_s_1, _bdry_func, "mpmath"), (0, _s_mid)))
                 - _s_mid**2
             )
 

{mergeron-2025.739265.0 → mergeron-2025.739265.2}/src/mergeron/core/pseudorandom_numbers.py

@@ -6,12 +6,15 @@ https://github.com/numpy/numpy/issues/16313.
 
 """
 
+from __future__ import annotations
+
 import concurrent.futures
 from collections.abc import Sequence
 from multiprocessing import cpu_count
 from typing import Literal
 
 import numpy as np
+from attrs import Attribute, define, field
 from numpy.random import PCG64DXSM, Generator, SeedSequence
 
 from .. import VERSION, ArrayDouble  # noqa: TID252
@@ -19,7 +22,8 @@ from .. import VERSION, ArrayDouble  # noqa: TID252
 __version__ = VERSION
 
 NTHREADS = 2 * cpu_count()
-DEFAULT_DIST_PARMS = np.array([0.0, 1.0], np.float64)
+DEFAULT_DIST_PARMS: ArrayDouble = np.array([0.0, 1.0], float)
+DEFAULT_BETA_DIST_PARMS: ArrayDouble = np.array([1.0, 1.0], float)
 
 
 def prng(_s: SeedSequence | None = None, /) -> np.random.Generator:
@@ -106,6 +110,7 @@ def gen_seed_seq_list_default(
     return [SeedSequence(_s, pool_size=8) for _s in generated_entropy[:_sseq_list_len]]
 
 
+@define
 class MultithreadedRNG:
     """Fill given array on demand with pseudo-random numbers as specified.
 
@@ -114,93 +119,102 @@ class MultithreadedRNG:
     If a seed sequence is provided, it is used in a thread-safe way
     to generate repeatable i.i.d. draws. All arguments are validated
     before commencing multithreaded random number generation.
+    """
 
-    Parameters
-    ----------
-    __out_array
-        The output array to which generated data are written.
-        Its dimensions define the size of the sample.
-    dist_type
-        Distribution for the generated random numbers
-    dist_parms
-        Parameters, if any, for tailoring random number generation
-    seed_sequence
-        SeedSequence object for generating repeatable draws.
-    nthreads
-        Number of threads to spawn for random number generation.
+    values: ArrayDouble = field(kw_only=False, default=None)
+    """Output array to which generated data are over-written
 
+    Array-length defines the number of i.i.d. (vector) draws.
     """
 
-    def __init__(
-        self,
-        __out_array: ArrayDouble,
-        /,
-        *,
-        dist_type: Literal[
-            "Beta", "Dirichlet", "Gaussian", "Normal", "Random", "Uniform"
-        ] = "Uniform",
-        dist_parms: ArrayDouble | None = DEFAULT_DIST_PARMS,
-        seed_sequence: SeedSequence | None = None,
-        nthreads: int = NTHREADS,
-    ):
-        self.thread_count = nthreads
-
-        __seed_sequence = seed_sequence or SeedSequence(pool_size=8)
-        self._random_generators = [
-            prng(_t) for _t in __seed_sequence.spawn(self.thread_count)
-        ]
-
-        self.sample_sz = len(__out_array)
-
-        if dist_type not in (_rdts := ("Beta", "Dirichlet", "Normal", "Uniform")):
-            raise ValueError("Specified distribution must be one of {_rdts}")
-
-        if not (dist_parms is None or isinstance(dist_parms, Sequence | np.ndarray)):
-            raise ValueError(
-                "When specified, distribution parameters must be a list, tuple or Numpy array"
-            )
-            if isinstance(dist_parms, Sequence):
-                dist_parms = np.array(dist_parms)
-            elif not dist_parms.any():
-                dist_parms = None
-
-        self.dist_type = dist_type
-
-        if dist_parms is None or np.array_equal(dist_parms, DEFAULT_DIST_PARMS):
-            match dist_type:
-                case "Uniform":
-                    self.dist_type = "Random"
-                case "Normal":
-                    self.dist_type = "Gaussian"
-                case "Beta" | "Dirichlet":
-                    raise ValueError(
-                        f"parameter specification, {f'"{dist_parms}"'} "
-                        f"is invalid for specified distribution, f{'"{dist_type}"'}."
-                    )
-                case _:
-                    raise ValueError(
-                        f"Invalid distributions specified, {f'"{dist_type}"'}."
-                    )
+    dist_type: Literal[
+        "Beta", "Dirichlet", "Gaussian", "Normal", "Random", "Uniform"
+    ] = field(kw_only=True, default="Uniform")
+    """Distribution for the generated random numbers.
+
+    Default is "Uniform".
+     """
+
+    @dist_type.validator
+    def __dtv(
+        _instance: MultithreadedRNG, _attribute: Attribute[str], _value: str, /
+    ) -> None:
+        if _value not in (
+            _rdts := ("Beta", "Dirichlet", "Gaussian", "Normal", "Random", "Uniform")
+        ):
+            raise ValueError(f"Specified distribution must be one of {_rdts}")
+
+    dist_parms: ArrayDouble | None = field(kw_only=True, default=DEFAULT_DIST_PARMS)
+    """Parameters, if any, for tailoring random number generation
+    """
 
-        elif dist_type == "Dirichlet":
-            if len(dist_parms) != __out_array.shape[1]:
+    @dist_parms.validator
+    def __dpv(
+        _instance: MultithreadedRNG, _attribute: Attribute[str], _value: ArrayDouble, /
+    ) -> None:
+        if _value is not None:
+            if not isinstance(_value, Sequence | np.ndarray):
                 raise ValueError(
-                    f"Insufficient shape parameters for requested Dirichlet sample "
-                    f"of size, {__out_array.shape}"
+                    "When specified, distribution parameters must be a list, tuple or Numpy array"
                 )
 
-        elif (_lrdp := len(dist_parms)) != 2:
-            raise ValueError(f"Expected 2 parameters, got, {_lrdp}")
-
-        self.dist_parms = dist_parms
+            elif (
+                _instance.dist_type != "Dirichlet"
+                and (_lrdp := len(_value)) != (_trdp := 2)
+            ) or (
+                _instance.dist_type == "Dirichlet"
+                and (_lrdp := len(_value)) != (_trdp := _instance.values.shape[1])
+            ):
+                raise ValueError(f"Expected {_trdp} parameters, got, {_lrdp}")
+
+            elif (
+                _instance.dist_type in ("Beta", "Dirichlet")
+                and (np.array(_value) <= 0.0).any()
+            ):
+                raise ValueError(
+                    "Shape and location parameters must be strictly positive"
+                )
 
-        self.values = __out_array
-        self.executor = concurrent.futures.ThreadPoolExecutor(self.thread_count)
+    seed_sequence: SeedSequence | None = field(kw_only=True, default=None)
+    """Seed sequence for generating random numbers."""
 
-        self.step_size = (len(self.values) / self.thread_count).__ceil__()
+    nthreads: int = field(kw_only=True, default=NTHREADS)
+    """Number of threads to spawn for random number generation."""
 
     def fill(self) -> None:
-        """Fill the provided output array with random numbers as specified."""
+        """Fill the provided output array with random number draws as specified."""
+
+        if (
+            self.dist_parms is None
+            or not (
+                _dist_parms := np.array(self.dist_parms)  # one-shot conversion
+            ).any()
+        ):
+            if self.dist_type == "Beta":
+                _dist_parms = DEFAULT_BETA_DIST_PARMS
+            elif self.dist_type == "Dirichlet":
+                _dist_parms = np.ones(self.values.shape[1], float)
+            else:
+                _dist_parms = DEFAULT_DIST_PARMS
+
+        if self.dist_parms is None or np.array_equal(
+            self.dist_parms, DEFAULT_DIST_PARMS
+        ):
+            if self.dist_type == "Uniform":
+                _dist_type = "Random"
+            elif self.dist_type == "Normal":
+                _dist_type = "Gaussian"
+        else:
+            _dist_type = self.dist_type
+
+        _step_size = (len(self.values) / self.nthreads).__ceil__()
+        # int; function gives float unsuitable for slicing
+
+        _seed_sequence = self.seed_sequence or SeedSequence(pool_size=8)
+
+        _random_generators = tuple(
+            prng(_t) for _t in _seed_sequence.spawn(self.nthreads)
+        )
 
         def _fill(
             _rng: np.random.Generator,
@@ -213,37 +227,35 @@ class MultithreadedRNG:
         ) -> None:
             _sz: tuple[int, ...] = _out[_first:_last].shape
             match _dist_type:
-                case "Random":
-                    _rng.random(out=_out[_first:_last])
-                case "Uniform":
-                    _uni_l, _uni_h = _dist_parms
-                    _out[_first:_last] = _rng.uniform(_uni_l, _uni_h, size=_sz)
-                case "Dirichlet":
-                    _out[_first:_last] = _rng.dirichlet(_dist_parms, size=_sz[:-1])
                 case "Beta":
                     _shape_a, _shape_b = _dist_parms
                     _out[_first:_last] = _rng.beta(_shape_a, _shape_b, size=_sz)
+                case "Dirichlet":
+                    _out[_first:_last] = _rng.dirichlet(_dist_parms, size=_sz[:-1])
+                case "Gaussian":
+                    _rng.standard_normal(out=_out[_first:_last])
                 case "Normal":
                     _mu, _sigma = _dist_parms
                     _out[_first:_last] = _rng.normal(_mu, _sigma, size=_sz)
+                case "Random":
+                    _rng.random(out=_out[_first:_last])
+                case "Uniform":
+                    _uni_l, _uni_h = _dist_parms
+                    _out[_first:_last] = _rng.uniform(_uni_l, _uni_h, size=_sz)
                 case _:
-                    _rng.standard_normal(out=_out[_first:_last])
-
-        futures = {}
-        for i in range(self.thread_count):
-            _range_first = i * self.step_size
-            _range_last = min(len(self.values), (i + 1) * self.step_size)
-            args = (
-                _fill,
-                self._random_generators[i],
-                self.dist_type,
-                self.dist_parms,
-                self.values,
-                _range_first,
-                _range_last,
-            )
-            futures[self.executor.submit(*args)] = i  # type: ignore
-        concurrent.futures.wait(futures)
-
-    def __del__(self) -> None:
-        self.executor.shutdown(False)
+                    "Unreachable. The validator would have rejected this as invalid."
+
+        with concurrent.futures.ThreadPoolExecutor(self.nthreads) as _executor:
+            for i in range(self.nthreads):
+                _range_first = i * _step_size
+                _range_last = min(len(self.values), (i + 1) * _step_size)
+
+                _executor.submit(
+                    _fill,
+                    _random_generators[i],
+                    _dist_type,
+                    _dist_parms,
+                    self.values,
+                    _range_first,
+                    _range_last,
+                )

{mergeron-2025.739265.0 → mergeron-2025.739265.2}/src/mergeron/demo/visualize_empirical_margin_distribution.py

@@ -45,7 +45,7 @@ with warnings.catch_warnings():
     ])
 
 mgn_kde = stats.gaussian_kde(mgn_data_obs, weights=mgn_data_wts, bw_method="silverman")
-mgn_kde.set_bandwidth(bw_method=mgn_kde.factor / 3.0)  # pyright: ignore
+mgn_kde.set_bandwidth(bw_method=mgn_kde.factor / 3.0)
 
 mgn_ax.plot(
     (_xv := np.linspace(0, BIN_COUNT, 10**5) / BIN_COUNT),

{mergeron-2025.739265.0 → mergeron-2025.739265.2}/src/mergeron/gen/__init__.py

@@ -70,7 +70,7 @@ class SHRDistribution(enum.StrEnum):
     DIR_FLAT_CONSTR = "Flat Dirichlet - Constrained"
     """Impose minimum probablility weight on each firm-count
 
-    Only firm-counts with probability weight of no less than 3%
+    Only firm-counts with probability weight of 3% or more
     are included for data generation.
     """
 
@@ -119,7 +119,7 @@ class ShareSpec:
     dist_type: SHRDistribution = field(default=SHRDistribution.DIR_FLAT)
     """See :class:`SHRDistribution`"""
 
-    @dist_type.validator  # pyright: ignore
+    @dist_type.validator
     def __dtv(
         _i: ShareSpec, _a: Attribute[SHRDistribution], _v: SHRDistribution
     ) -> None:
@@ -152,7 +152,7 @@ class ShareSpec:
 
     """
 
-    @dist_parms.validator  # pyright: ignore
+    @dist_parms.validator
     def __dpv(
         _i: ShareSpec,
         _a: Attribute[ArrayFloat | ArrayINT | None],
@@ -205,7 +205,7 @@ class ShareSpec:
 
     """
 
-    @recapture_ratio.validator  # pyright: ignore
+    @recapture_ratio.validator
     def __rrv(_i: ShareSpec, _a: Attribute[float], _v: float) -> None:
         if _v and not (0 < _v <= 1):
             raise ValueError("Recapture ratio must lie in the interval, [0, 1).")
@@ -265,7 +265,7 @@ class PCMSpec:
 
     """
 
-    @dist_parms.validator  # pyright: ignore
+    @dist_parms.validator
     def __dpv(
         _i: PCMSpec, _a: Attribute[ArrayDouble | None], _v: ArrayDouble | None
     ) -> None:

{mergeron-2025.739265.0 → mergeron-2025.739265.2}/src/mergeron/gen/data_generation.py

@@ -85,7 +85,7 @@ class MarketSample:
     )
     """Margin specification, see :class:`PCMSpec`"""
 
-    @pcm_spec.validator  # pyright: ignore
+    @pcm_spec.validator
     def __psv(self, _a: Attribute[PCMSpec], _v: PCMSpec, /) -> None:
         if (
             self.share_spec.recapture_form == RECForm.FIXED
@@ -437,8 +437,8 @@ class MarketSample:
                 _enf_parm_vec,
                 _sim_test_regime,
                 **_sim_enf_cnts_kwargs,
-                saved_array_name_suffix=f"{saved_array_name_suffix}_{_iter_id:0{2 + int(np.ceil(np.log10(_iter_count)))}d}",  # pyright: ignore
-                seed_seq_list=_rng_seed_seq_list_ch,  # pyright: ignore
+                saved_array_name_suffix=f"{saved_array_name_suffix}_{_iter_id:0{2 + int(np.ceil(np.log10(_iter_count)))}d}",
+                seed_seq_list=_rng_seed_seq_list_ch,
             )
             for _iter_id, _rng_seed_seq_list_ch in enumerate(_rng_seed_seq_list)
         )

{mergeron-2025.739265.0 → mergeron-2025.739265.2}/src/mergeron/gen/data_generation_functions.py

@@ -138,7 +138,7 @@ def gen_market_shares_uniform(
 
     """
 
-    _frmshr_array = np.empty((_s_size, 2), dtype=np.float64)
+    _frmshr_array: ArrayDouble = np.empty((_s_size, 2), dtype=np.float64)
 
     _dist_parms_mktshr = _dist_parms_mktshr or DEFAULT_DIST_PARMS
     _mrng = MultithreadedRNG(
@@ -151,10 +151,11 @@ def gen_market_shares_uniform(
     _mrng.fill()
     # Convert draws on U[0, 1] to Uniformly-distributed draws on simplex, s_1 + s_2 <= 1
     _frmshr_array.sort(axis=1)
-    _frmshr_array = np.column_stack((
-        _frmshr_array[:, 0],
-        _frmshr_array[:, 1] - _frmshr_array[:, 0],
-    ))
+
+    _frmshr_array = np.array(
+        (_frmshr_array[:, 0], _frmshr_array[:, 1] - _frmshr_array[:, 0]),
+        _frmshr_array.dtype,
+    ).T  # faster than np.stack() and variants
 
     # Keep only share combinations representing feasible mergers
     # This is a no-op for 64-bit floats, but is necessary for 32-bit floats

{mergeron-2025.739265.0 → mergeron-2025.739265.2}/src/mergeron/gen/upp_tests.py

@@ -331,11 +331,11 @@ def initialize_hd5(
     _h5_title = f"HMG version: {_hmg_pub_year}; Test regime: {_test_regime}"
     if _h5_path.is_file():
         _h5_path.unlink()
-    _h5_file = ptb.open_file(_h5_path, mode="w", title=_h5_title)  # pyright: ignore
+    _h5_file = ptb.open_file(_h5_path, mode="w", title=_h5_title)
     _save_data_to_file: SaveData = (True, _h5_file, _h5_file.root)
     _next_subgroup_name_root = "enf_{}_{}_{}_{}".format(
         _hmg_pub_year,
-        *(getattr(_test_regime, _f.name).name for _f in _test_regime.__attrs_attrs__),  # pyright: ignore
+        *(getattr(_test_regime, _f.name).name for _f in _test_regime.__attrs_attrs__),
     )
     return _save_data_to_file, _next_subgroup_name_root
 
@@ -383,7 +383,7 @@ def save_array_to_hdf5(
         _h5_array_name,
         atom=ptb.Atom.from_dtype(_array_obj.dtype),
         shape=_array_obj.shape,
-        filters=ptb.Filters(complevel=3, complib="blosc:lz4hc", fletcher32=True),  # pyright: ignore
+        filters=ptb.Filters(complevel=3, complib="blosc:lz4hc", fletcher32=True),
     )
     _h5_array[:] = _array_obj