mergeron 2025.739290.0__tar.gz → 2025.739290.2__tar.gz

{mergeron-2025.739290.0 → mergeron-2025.739290.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: mergeron
-Version: 2025.739290.0
+Version: 2025.739290.2
 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-2025.739290.0 → mergeron-2025.739290.2}/pyproject.toml

@@ -13,7 +13,7 @@ keywords = [
     "upward pricing pressure",
     "GUPPI",
 ]
-version = "2025.739290.0"
+version = "2025.739290.2"
 
 # Classifiers list: https://pypi.org/classifiers/
 classifiers = [

{mergeron-2025.739290.0 → mergeron-2025.739290.2}/src/mergeron/__init__.py

@@ -6,12 +6,13 @@ from pathlib import Path
 from typing import Literal
 
 import numpy as np
+from numpy.random import SeedSequence
 from numpy.typing import NDArray
 from ruamel import yaml
 
 _PKG_NAME: str = Path(__file__).parent.stem
 
-VERSION = "2025.739290.0"
+VERSION = "2025.739290.2"
 
 __version__ = VERSION
 
@@ -66,6 +67,21 @@ type ArrayBIGINT = NDArray[np.int64]
     ),
 )
 
+# Add yaml representer, constructor for SeedSequence
+this_yaml.representer.add_representer(
+    SeedSequence,
+    lambda _r, _d: _r.represent_mapping(
+        "!SeedSequence",
+        {
+            _a: getattr(_d, _a)
+            for _a in ("entropy", "spawn_key", "pool_size", "n_children_spawned")
+        },
+    ),
+)
+this_yaml.constructor.add_constructor(
+    "!SeedSequence", lambda _c, _n, /: SeedSequence(**_c.construct_mapping(_n))
+)
+
 
 @enum.unique
 class RECForm(enum.StrEnum):

{mergeron-2025.739290.0 → mergeron-2025.739290.2}/src/mergeron/core/ftc_merger_investigations_data.py

@@ -8,13 +8,16 @@ Reported row and column totals from source data are not stored.
 
 """
 
+from __future__ import annotations
+
 import shutil
 from collections.abc import Mapping, Sequence
+from dataclasses import dataclass
 from importlib import resources
 from operator import itemgetter
 from pathlib import Path
 from types import MappingProxyType
-from typing import Any, NamedTuple
+from typing import Any
 
 import msgpack  # type: ignore
 import msgpack_numpy as m  # type: ignore
@@ -23,8 +26,9 @@ import re2 as re  # type: ignore
 import urllib3
 from bs4 import BeautifulSoup
 from numpy.testing import assert_array_equal
+from ruamel import yaml
 
-from .. import _PKG_NAME, DATA_DIR, VERSION, ArrayBIGINT  # noqa: TID252
+from .. import _PKG_NAME, DATA_DIR, EMPTY_ARRAYINT, VERSION, ArrayBIGINT  # noqa: TID252
 
 __version__ = VERSION
 
@@ -89,11 +93,27 @@ CNT_FCOUNT_DICT = {
 }
 
 
-class INVTableData(NamedTuple):
+@dataclass(slots=True, frozen=True)
+class INVTableData:
     industry_group: str
     additional_evidence: str
     data_array: ArrayBIGINT
 
+    @classmethod
+    def to_yaml(
+        cls, _r: yaml.representer.SafeRepresenter, _d: INVTableData
+    ) -> yaml.MappingNode:
+        _ret: yaml.MappingNode = _r.represent_mapping(
+            f"!{cls.__name__}", {_a: getattr(_d, _a) for _a in _d.__dataclass_fields__}
+        )
+        return _ret
+
+    @classmethod
+    def from_yaml(
+        cls, _c: yaml.constructor.SafeConstructor, _n: yaml.MappingNode
+    ) -> INVTableData:
+        return cls(**_c.construct_mapping(_n))
+
 
 type INVData = Mapping[str, Mapping[str, Mapping[str, INVTableData]]]
 type _INVData_in = dict[str, dict[str, dict[str, INVTableData]]]
@@ -278,10 +298,13 @@ def _construct_new_period_data(
                 _invdata_cuml_sub_table.data_array,
             )
 
-            _invdata_base_sub_table = _invdata_base[_table_type].get(_table_no, None)
+            _invdata_base_sub_table = _invdata_base[_table_type].get(
+                _table_no, INVTableData("", "", EMPTY_ARRAYINT)
+            )
 
             (_invdata_base_ind_group, _invdata_base_evid_cond, _invdata_base_array) = (
-                _invdata_base_sub_table or ("", "", None)
+                getattr(_invdata_base_sub_table, _a)
+                for _a in ("industry_group", "additional_evidence", "data_array")
             )
 
             # Some tables can't be constructed due to inconsistencies in the data

{mergeron-2025.739290.0 → mergeron-2025.739290.2}/src/mergeron/core/guidelines_boundaries.py

@@ -13,6 +13,7 @@ from typing import Literal
 import numpy as np
 from attrs import Attribute, field, frozen, validators
 from mpmath import mp, mpf  # type: ignore
+from ruamel import yaml
 
 from .. import (  # noqa: TID252
     DEFAULT_REC_RATIO,
@@ -21,6 +22,7 @@ from .. import (  # noqa: TID252
     HMGPubYear,
     RECForm,
     UPPAggrSelector,
+    this_yaml,
 )
 from . import guidelines_boundary_functions as gbfn
 
@@ -41,7 +43,23 @@ class HMGThresholds:
     cmcr: float
     ipr: float
 
+    @classmethod
+    def to_yaml(
+        cls, _r: yaml.representer.SafeRepresenter, _d: HMGThresholds
+    ) -> yaml.MappingNode:
+        _ret: yaml.MappingNode = _r.represent_mapping(
+            f"!{cls.__name__}", {_a: getattr(_d, _a) for _a in _d.__dataclass_fields__}
+        )
+        return _ret
+
+    @classmethod
+    def from_yaml(
+        cls, _c: yaml.constructor.SafeConstructor, _n: yaml.MappingNode
+    ) -> HMGThresholds:
+        return cls(**_c.construct_mapping(_n))
 
+
+@this_yaml.register_class
 @frozen
 class GuidelinesThresholds:
     """
@@ -147,7 +165,24 @@ class GuidelinesThresholds:
             ),
         )
 
+    @classmethod
+    def to_yaml(
+        cls, _r: yaml.representer.SafeRepresenter, _d: GuidelinesThresholds
+    ) -> yaml.MappingNode:
+        _ret: yaml.MappingNode = _r.represent_mapping(
+            f"!{cls.__name__}",
+            {_a.name: getattr(_d, _a.name) for _a in _d.__attrs_attrs__},
+        )
+        return _ret
 
+    @classmethod
+    def from_yaml(
+        cls, _c: yaml.constructor.SafeConstructor, _n: yaml.MappingNode
+    ) -> GuidelinesThresholds:
+        return cls(**_c.construct_mapping(_n))
+
+
+@this_yaml.register_class
 @frozen
 class ConcentrationBoundary:
     """Concentration parameters, boundary coordinates, and area under concentration boundary."""
@@ -184,12 +219,12 @@ class ConcentrationBoundary:
         kw_only=False, default=5, validator=validators.instance_of(int)
     )
 
-    coordinates: ArrayDouble = field(init=False, kw_only=True)
-    """Market-share pairs as Cartesian coordinates of points on the concentration boundary."""
-
     area: float = field(init=False, kw_only=True)
     """Area under the concentration boundary."""
 
+    coordinates: ArrayDouble = field(init=False, kw_only=True)
+    """Market-share pairs as Cartesian coordinates of points on the concentration boundary."""
+
     def __attrs_post_init__(self, /) -> None:
         match self.measure_name:
             case "ΔHHI":
@@ -202,10 +237,31 @@ class ConcentrationBoundary:
                 _conc_fn = gbfn.hhi_post_contrib_boundary
 
         _boundary = _conc_fn(self.threshold, dps=self.precision)
-        object.__setattr__(self, "coordinates", _boundary.coordinates)
         object.__setattr__(self, "area", _boundary.area)
+        object.__setattr__(self, "coordinates", _boundary.coordinates)
 
+    @classmethod
+    def to_yaml(
+        cls, _r: yaml.representer.SafeRepresenter, _d: ConcentrationBoundary
+    ) -> yaml.MappingNode:
+        _ret: yaml.MappingNode = _r.represent_mapping(
+            f"!{cls.__name__}",
+            {
+                _a.name: getattr(_d, _a.name)
+                for _a in _d.__attrs_attrs__
+                if _a.name not in ("area", "coordinates")
+            },
+        )
+        return _ret
+
+    @classmethod
+    def from_yaml(
+        cls, _c: yaml.constructor.SafeConstructor, _n: yaml.MappingNode
+    ) -> ConcentrationBoundary:
+        return cls(**_c.construct_mapping(_n))
 
+
+@this_yaml.register_class
 @frozen
 class DiversionRatioBoundary:
     """
@@ -310,12 +366,12 @@ class DiversionRatioBoundary:
 
     """
 
-    coordinates: ArrayDouble = field(init=False, kw_only=True)
-    """Market-share pairs as Cartesian coordinates of points on the diversion ratio boundary."""
-
     area: float = field(init=False, kw_only=True)
     """Area under the diversion ratio boundary."""
 
+    coordinates: ArrayDouble = field(init=False, kw_only=True)
+    """Market-share pairs as Cartesian coordinates of points on the diversion ratio boundary."""
+
     def __attrs_post_init__(self, /) -> None:
         _share_ratio = critical_share_ratio(
             self.diversion_ratio, r_bar=self.recapture_ratio
@@ -359,8 +415,28 @@ class DiversionRatioBoundary:
                 _upp_agg_kwargs |= {"agg_method": _aggregator, "weighting": _wgt_type}
 
         _boundary = _upp_agg_fn(_share_ratio, self.recapture_ratio, **_upp_agg_kwargs)
-        object.__setattr__(self, "coordinates", _boundary.coordinates)
         object.__setattr__(self, "area", _boundary.area)
+        object.__setattr__(self, "coordinates", _boundary.coordinates)
+
+    @classmethod
+    def to_yaml(
+        cls, _r: yaml.representer.SafeRepresenter, _d: DiversionRatioBoundary
+    ) -> yaml.MappingNode:
+        _ret: yaml.MappingNode = _r.represent_mapping(
+            f"!{cls.__name__}",
+            {
+                _a.name: getattr(_d, _a.name)
+                for _a in _d.__attrs_attrs__
+                if _a.name not in ("area", "coordinates")
+            },
+        )
+        return _ret
+
+    @classmethod
+    def from_yaml(
+        cls, _c: yaml.constructor.SafeConstructor, _n: yaml.MappingNode
+    ) -> DiversionRatioBoundary:
+        return cls(**_c.construct_mapping(_n))
 
 
 def guppi_from_delta(

{mergeron-2025.739290.0 → mergeron-2025.739290.2}/src/mergeron/core/pseudorandom_numbers.py

@@ -16,7 +16,7 @@ import numpy as np
 from attrs import Attribute, Converter, define, field
 from numpy.random import PCG64DXSM, Generator, SeedSequence
 
-from .. import NTHREADS, VERSION, ArrayDouble, ArrayFloat, this_yaml  # noqa: TID252
+from .. import NTHREADS, VERSION, ArrayDouble, ArrayFloat  # noqa: TID252
 
 __version__ = VERSION
 
@@ -24,22 +24,6 @@ DEFAULT_DIST_PARMS: ArrayFloat = np.array([0.0, 1.0], float)
 DEFAULT_BETA_DIST_PARMS: ArrayFloat = np.array([1.0, 1.0], float)
 
 
-# Add yaml representer, constructor for SeedSequence
-this_yaml.representer.add_representer(
-    SeedSequence,
-    lambda _r, _d: _r.represent_mapping(
-        "!SeedSequence",
-        {
-            _a: getattr(_d, _a)
-            for _a in ("entropy", "spawn_key", "pool_size", "n_children_spawned")
-        },
-    ),
-)
-this_yaml.constructor.add_constructor(
-    "!SeedSequence", lambda _c, _n, /: SeedSequence(**_c.construct_mapping(_n))
-)
-
-
 def prng(_s: SeedSequence | None = None, /) -> np.random.Generator:
     """Adopt the PCG64DXSM bit-generator, the future default in numpy.default_rng().
 

{mergeron-2025.739290.0 → mergeron-2025.739290.2}/src/mergeron/gen/__init__.py

@@ -40,7 +40,7 @@ __version__ = VERSION
 DEFAULT_FCOUNT_WTS = np.asarray((_nr := np.arange(6, 0, -1)) / _nr.sum(), float)
 
 
-@dataclass
+@dataclass(slots=True, frozen=True)
 class SeedSequenceData:
     share: SeedSequence
     pcm: SeedSequence
@@ -654,3 +654,20 @@ for _typ in (
             ),
         ),
     )
+
+for _typ in (MarketSampleData, SeedSequenceData, UPPTestsCounts):
+    _, _ = (
+        this_yaml.representer.add_representer(
+            _typ,
+            lambda _r, _d: _r.rpresent_mapping(
+                f"!{_d.__class__.__name__}",
+                {_a: getattr(_d, _a) for _a in _d.__dataclass_fields__},
+            ),
+        ),
+        this_yaml.constructor.add_constructor(
+            _typ,
+            lambda _c, _n: globals().get(
+                _n.tag.lstrip("!")(**_c.construct_mapping(_n))
+            ),
+        ),
+    )

{mergeron-2025.739290.0 → mergeron-2025.739290.2}/src/mergeron/gen/data_generation.py

@@ -34,7 +34,7 @@ from .data_generation_functions import (
     gen_margin_price_data,
     gen_share_data,
 )
-from .upp_tests import SaveData, compute_upp_test_counts
+from .upp_tests import compute_upp_test_counts
 
 __version__ = VERSION
 
@@ -51,12 +51,6 @@ class SamplingFunctionKWArgs(TypedDict, total=False):
     nthreads: int
     """number of parallel threads to use"""
 
-    save_data_to_file: SaveData
-    """optionally save data to HDF5 file"""
-
-    saved_array_name_suffix: str
-    """optionally specify a suffix for the HDF5 array names"""
-
 
 def _seed_data_conv(_v: SeedSequenceData | None, _i: MarketSample) -> SeedSequenceData:
     if isinstance(_v, SeedSequenceData):
@@ -104,9 +98,9 @@ class MarketSample:
             and _v.firm2_pcm_constraint == FM2Constraint.MNL
         ):
             raise ValueError(
-                f'Specification of "recapture_form", "{self.share_spec.recapture_form}" '
-                "requires Firm 2 margin must have property, "
-                f'"{FM2Constraint.IID}" or "{FM2Constraint.SYM}".'
+                f'Specification of "PCMSpec.firm2_pcm_constraint", as {FM2Constraint.MNL!r} '
+                f'requires that "ShareSpec.recapture_form" be {RECForm.INOUT!r} '
+                f"or {RECForm.OUTIN!r}, not {RECForm.FIXED!r} as presently specified"
             )
 
     price_spec: PriceSpec = field(
@@ -484,7 +478,7 @@ class MarketSample:
             {
                 _a.name: getattr(_d, _a.name)
                 for _a in _d.__attrs_attrs__
-                if _a.type not in (MarketSampleData, UPPTestsCounts)
+                if _a.name not in ("data", "enf_counts")
             },
         )
         return _ret

{mergeron-2025.739290.0 → mergeron-2025.739290.2}/src/mergeron/gen/data_generation_functions.py

@@ -46,8 +46,8 @@ def gen_share_data(
     _sample_size: int,
     _share_spec: ShareSpec,
     _fcount_rng_seed_seq: SeedSequence | None,
-    _mktshr_rng_seed_seq: SeedSequence | None = None,
-    _nthreads: int = NTHREADS,
+    _mktshr_rng_seed_seq: SeedSequence,
+    _nthreads: int,
     /,
 ) -> ShareDataSample:
     """Helper function for generating share data.
@@ -69,9 +69,9 @@ def gen_share_data(
 
     """
 
-    _recapture_form, _dist_type_mktshr, _dist_parms_mktshr, _firm_count_prob_wts = (
+    _dist_type_mktshr, _firm_count_prob_wts, _dist_parms_mktshr, _recapture_form = (
         getattr(_share_spec, _f)
-        for _f in ("recapture_form", "dist_type", "dist_parms", "firm_counts_weights")
+        for _f in ("dist_type", "firm_counts_weights", "dist_parms", "recapture_form")
     )
 
     _ssz = _sample_size
@@ -126,8 +126,8 @@ def gen_share_data(
 def gen_market_shares_uniform(
     _s_size: int,
     _dist_parms_mktshr: ArrayDouble,
-    _mktshr_rng_seed_seq: SeedSequence | None = None,
-    _nthreads: int = NTHREADS,
+    _mktshr_rng_seed_seq: SeedSequence,
+    _nthreads: int,
     /,
 ) -> ShareDataSample:
     """Generate merging-firm shares from Uniform distribution on the 3-D simplex.
@@ -159,13 +159,12 @@ def gen_market_shares_uniform(
         nthreads=_nthreads,
     )
     _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.array(
-        (_frmshr_array[:, 0], _frmshr_array[:, 1] - _frmshr_array[:, 0]),
-        _frmshr_array.dtype,
-    ).T  # faster than np.stack() and variants
+    # Convert draws on U[0, 1] to Uniformly-distributed draws on simplex, s_1 + s_2 <= 1
+    _frmshr_array = np.hstack((
+        _frmshr_array.min(axis=1, keepdims=True),
+        np.abs(np.diff(_frmshr_array, axis=1)),
+    ))
 
     # Keep only share combinations representing feasible mergers
     # This is a no-op for 64-bit floats, but is necessary for smaller floats
@@ -199,8 +198,8 @@ def _gen_market_shares_dirichlet_multimarket(
     _dist_type_dir: SHRDistribution,
     _dist_parms_dir: ArrayDouble,
     _firm_count_wts: ArrayDouble,
-    _fcount_rng_seed_seq: SeedSequence | None = None,
-    _mktshr_rng_seed_seq: SeedSequence | None = None,
+    _fcount_rng_seed_seq: SeedSequence | None,
+    _mktshr_rng_seed_seq: SeedSequence,
     _nthreads: int = NTHREADS,
     /,
 ) -> ShareDataSample:
@@ -341,8 +340,8 @@ def gen_market_shares_dirichlet(
     _dir_alphas: ArrayDouble,
     _s_size: int,
     _recapture_form: RECForm,
-    _mktshr_rng_seed_seq: SeedSequence | None = None,
-    _nthreads: int = NTHREADS,
+    _mktshr_rng_seed_seq: SeedSequence,
+    _nthreads: int,
     /,
 ) -> ShareDataSample:
     """Dirichlet-distributed shares with fixed firm-count.
@@ -497,7 +496,7 @@ def gen_margin_price_data(
     _hsr_filing_test_type: SSZConstant,
     _pcm_rng_seed_seq: SeedSequence,
     _pr_rng_seed_seq: SeedSequence | None,
-    _nthreads: int = NTHREADS,
+    _nthreads: int,
     /,
 ) -> tuple[MarginDataSample, PriceDataSample]:
     """Generate margin and price data for mergers in the sample.
@@ -680,8 +679,8 @@ def _gen_margin_data(
     _price_array: ArrayDouble,
     _aggregate_purchase_prob: ArrayDouble,
     _pcm_spec: PCMSpec,
-    _pcm_rng_seed_seq: SeedSequence | None,
-    _nthreads: int = NTHREADS,
+    _pcm_rng_seed_seq: SeedSequence,
+    _nthreads: int,
     /,
 ) -> MarginDataSample:
     _dist_type_pcm, _dist_firm2_pcm, _dist_parms_pcm = (