mergeron 2024.739099.2__py3-none-any.whl → 2024.739104.1__py3-none-any.whl

mergeron/gen/upp_tests.py

@@ -11,19 +11,16 @@ from typing import Literal, TypeAlias, TypedDict
 
 import numpy as np
 import tables as ptb  # type: ignore
-from joblib import Parallel, cpu_count, delayed  # type: ignore
 from numpy.random import SeedSequence
 
-from .. import (  # noqa: TID252
-    TF,
-    TI,
+from .. import (  # noqa
     VERSION,
     ArrayBIGINT,
     ArrayBoolean,
     ArrayDouble,
     ArrayFloat,
     ArrayINT,
-    RECConstants,
+    RECTypes,
     UPPAggrSelector,
 )
 from ..core import guidelines_boundaries as gbl  # noqa: TID252
@@ -32,12 +29,10 @@ from . import (
     DataclassInstance,
     INVResolution,
     MarketDataSample,
-    MarketSpec,
     UPPTestRegime,
     UPPTestsCounts,
     UPPTestsRaw,
 )
-from . import data_generation as dgl
 from . import enforcement_stats as esl
 
 __version__ = VERSION
@@ -58,169 +53,37 @@ class INVRESCntsArgs(TypedDict, total=False):
     saved_array_name_suffix: str
 
 
-def sim_enf_cnts_ll(
-    _mkt_sample_spec: MarketSpec,
-    _enf_parm_vec: gbl.HMGThresholds,
-    _sim_test_regime: UPPTestRegime,
+def enf_cnts(
+    _market_data_sample: MarketDataSample,
+    _upp_test_parms: gbl.HMGThresholds,
+    _upp_test_regime: UPPTestRegime,
     /,
-    *,
-    sample_size: int = 10**6,
-    seed_seq_list: list[SeedSequence] | None = None,
-    nthreads: int = 16,
-    save_data_to_file: SaveData = False,
-    saved_array_name_suffix: str = "",
 ) -> UPPTestsCounts:
-    """A function to parallelize data-generation and testing
-
-    The parameters `_sim_enf_cnts_kwargs` are passed unaltered to
-    the parent function, `sim_enf_cnts()`, except that, if provided,
-    `seed_seq_list` is used to spawn a seed sequence for each thread,
-    to assure independent samples in each thread, and `nthreads` defines
-    the number of parallel processes used. The number of draws in
-    each thread may be tuned, by trial and error, to the amount of
-    memory (RAM) available.
+    """Estimate enforcement and clearance counts from market data sample
 
     Parameters
     ----------
+    _market_data_sample
+        Market data sample
 
-    _enf_parm_vec
-        Guidelines thresholds to test against
-
-    _mkt_sample_spec
-        Configuration to use for generating sample data to test
-
-    _sim_test_regime
-        Configuration to use for testing
-
-    saved_array_name_suffix
-        Suffix to add to the array names in the HDF5 file
-
-    save_data_to_file
-        Whether to save data to an HDF5 file, and where to save it
-
-    sample_size
-        Number of draws to simulate
-
-    seed_seq_list
-        List of seed sequences, to assure independent samples in each thread
+    _upp_test_parms
+        Threshold values for various Guidelines criteria
 
-    nthreads
-        Number of parallel processes to use
+    _upp_test_regime
+        Specifies whether to analyze enforcement, clearance, or both
+        and the GUPPI and diversion ratio aggregators employed, with
+        default being to analyze enforcement based on the maximum
+        merging-firm GUPPI and maximum diversion ratio between the
+        merging firms
 
     Returns
     -------
-        Arrays of UPPTestCounts
+    UPPTestsCounts
+        Enforced and cleared counts
 
     """
-    _sample_sz = sample_size
-    _subsample_sz = 10**6
-    _iter_count = int(_sample_sz / _subsample_sz) if _subsample_sz < _sample_sz else 1
-    _thread_count = cpu_count()
-
-    if (
-        _mkt_sample_spec.share_spec.recapture_form != RECConstants.OUTIN
-        and _mkt_sample_spec.share_spec.recapture_rate != _enf_parm_vec.rec
-    ):
-        raise ValueError(
-            "{} {} {}".format(
-                f"Recapture rate from market sample spec, {_mkt_sample_spec.share_spec.recapture_rate}",
-                f"must match the value, {_enf_parm_vec.rec}",
-                "the guidelines thresholds vector.",
-            )
-        )
-
-    _rng_seed_seq_list = [None] * _iter_count
-    if seed_seq_list:
-        _rng_seed_seq_list = list(
-            zip(*[g.spawn(_iter_count) for g in seed_seq_list], strict=True)  # type: ignore
-        )
-
-    _sim_enf_cnts_kwargs: INVRESCntsArgs = INVRESCntsArgs({
-        "sample_size": _subsample_sz,
-        "save_data_to_file": save_data_to_file,
-        "nthreads": nthreads,
-    })
-
-    _res_list = Parallel(n_jobs=_thread_count, prefer="threads")(
-        delayed(sim_enf_cnts)(
-            _mkt_sample_spec,
-            _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}",
-            seed_seq_list=_rng_seed_seq_list_ch,
-        )
-        for _iter_id, _rng_seed_seq_list_ch in enumerate(_rng_seed_seq_list)
-    )
-
-    _res_list_stacks = UPPTestsCounts(*[
-        np.stack([getattr(_j, _k) for _j in _res_list])
-        for _k in ("by_firm_count", "by_delta", "by_conczone")
-    ])
-    upp_test_results = UPPTestsCounts(*[
-        np.column_stack((
-            (_gv := getattr(_res_list_stacks, _g))[0, :, :_h],
-            np.einsum("ijk->jk", np.int64(1) * _gv[:, :, _h:]),
-        ))
-        for _g, _h in zip(
-            _res_list_stacks.__dataclass_fields__.keys(), [1, 1, 3], strict=True
-        )
-    ])
-    del _res_list, _res_list_stacks
-
-    return upp_test_results
-
-
-def sim_enf_cnts(
-    _mkt_sample_spec: MarketSpec,
-    _upp_test_parms: gbl.HMGThresholds,
-    _sim_test_regime: UPPTestRegime,
-    /,
-    *,
-    sample_size: int = 10**6,
-    seed_seq_list: list[SeedSequence] | None = None,
-    nthreads: int = 16,
-    save_data_to_file: SaveData = False,
-    saved_array_name_suffix: str = "",
-) -> UPPTestsCounts:
-    # Generate market data
-    _market_data_sample = dgl.gen_market_sample(
-        _mkt_sample_spec,
-        sample_size=sample_size,
-        seed_seq_list=seed_seq_list,
-        nthreads=nthreads,
-    )
-
-    _invalid_array_names = (
-        ("fcounts", "choice_prob_outgd", "nth_firm_share", "hhi_post")
-        if _mkt_sample_spec.share_spec.dist_type == "Uniform"
-        else ()
-    )
-
-    save_data_to_hdf5(
-        _market_data_sample,
-        saved_array_name_suffix=saved_array_name_suffix,
-        excluded_attrs=_invalid_array_names,
-        save_data_to_file=save_data_to_file,
-    )
-
-    _upp_test_arrays = enf_cnts(_market_data_sample, _upp_test_parms, _sim_test_regime)
-
-    save_data_to_hdf5(
-        _upp_test_arrays,
-        saved_array_name_suffix=saved_array_name_suffix,
-        save_data_to_file=save_data_to_file,
-    )
-
-    return _upp_test_arrays
-
 
-def enf_cnts(
-    _market_data_sample: MarketDataSample,
-    _upp_test_parms: gbl.HMGThresholds,
-    _upp_test_regime: UPPTestRegime,
-    /,
-) -> UPPTestsCounts:
+    _enf_cnts_sim_array = -1 * np.ones((6, 2), np.int64)
     _upp_test_arrays = gen_upp_test_arrays(
         _market_data_sample, _upp_test_parms, _upp_test_regime
     )
@@ -231,12 +94,13 @@ def enf_cnts(
 
     _stats_rowlen = 6
     # Clearance/enforcement counts --- by firm count
-    _firm_counts_weights = np.unique(_fcounts)
-    if _firm_counts_weights is not None and np.all(_firm_counts_weights >= 0):
-        _max_firm_count = len(_firm_counts_weights)
+    _firm_counts_list = np.unique(_fcounts)
+    if _firm_counts_list is not None and np.all(_firm_counts_list >= 0):
+        # _max_firm_count = len(_firm_counts_list)
+        _max_firm_count = max(_firm_counts_list)
 
         _enf_cnts_sim_byfirmcount_array = -1 * np.ones(_stats_rowlen, np.int64)
-        for _firm_cnt in 2 + np.arange(_max_firm_count):
+        for _firm_cnt in 1 + np.arange(1, _max_firm_count):
             _firm_count_test = _fcounts == _firm_cnt
 
             _enf_cnts_sim_byfirmcount_array = np.vstack((
@@ -353,12 +217,10 @@ def gen_upp_test_arrays(
         getattr(_upp_test_parms, _f) for _f in ("guppi", "divr", "cmcr", "ipr")
     )
 
-    _enf_resolution, _guppi_aggregator, _divr_aggregator = (
-        getattr(_sim_test_regime, _f)
-        for _f in ("resolution", "guppi_aggregator", "divr_aggregator")
+    _guppi_array, _ipr_array, _cmcr_array = (
+        np.empty_like(_market_data.price_array) for _ in range(3)
     )
 
-    _guppi_array = np.empty_like(_market_data.divr_array)
     np.einsum(
         "ij,ij,ij->ij",
         _market_data.divr_array,
@@ -367,18 +229,53 @@ def gen_upp_test_arrays(
         out=_guppi_array,
     )
 
-    _ipr_array = np.empty_like(_market_data.divr_array)
-    np.divide(_guppi_array, (1 - _market_data.divr_array[:, ::-1]), out=_ipr_array)
+    np.divide(
+        np.einsum("ij,ij->ij", _market_data.pcm_array, _market_data.divr_array),
+        1 - _market_data.divr_array,
+        out=_ipr_array,
+    )
 
-    _cmcr_array = np.empty_like(_market_data.divr_array)
     np.divide(_ipr_array, 1 - _market_data.pcm_array, out=_cmcr_array)
 
-    _test_measure_seq = (_market_data.divr_array, _guppi_array, _cmcr_array, _ipr_array)
+    (_divr_test_vector,) = _compute_test_value_seq(
+        (_market_data.divr_array,),
+        _market_data.frmshr_array,
+        _sim_test_regime.divr_aggregator,
+    )
+
+    (_guppi_test_vector, _cmcr_test_vector, _ipr_test_vector) = _compute_test_value_seq(
+        (_guppi_array, _cmcr_array, _ipr_array),
+        _market_data.frmshr_array,
+        _sim_test_regime.guppi_aggregator,
+    )
+    del _cmcr_array, _ipr_array, _guppi_array
 
+    if _sim_test_regime.resolution == INVResolution.ENFT:
+        _upp_test_arrays = UPPTestsRaw(
+            _guppi_test_vector >= _g_bar,
+            (_guppi_test_vector >= _g_bar) | (_divr_test_vector >= _divr_bar),
+            _cmcr_test_vector >= _cmcr_bar,
+            _ipr_test_vector >= _ipr_bar,
+        )
+    else:
+        _upp_test_arrays = UPPTestsRaw(
+            _guppi_test_vector < _g_bar,
+            (_guppi_test_vector < _g_bar) & (_divr_test_vector < _divr_bar),
+            _cmcr_test_vector < _cmcr_bar,
+            _ipr_test_vector < _ipr_bar,
+        )
+
+    return _upp_test_arrays
+
+
+def _compute_test_value_seq(
+    _test_measure_seq: tuple[ArrayDouble, ...],
+    _wt_array: ArrayDouble,
+    _aggregator: UPPAggrSelector,
+) -> tuple[ArrayDouble, ...]:
     _wt_array = (
-        _market_data.frmshr_array
-        / np.einsum("ij->i", _market_data.frmshr_array)[:, None]
-        if _guppi_aggregator
+        _wt_array / np.einsum("ij->i", _wt_array)[:, None]
+        if _aggregator
         in (
             UPPAggrSelector.CPA,
             UPPAggrSelector.CPD,
@@ -388,7 +285,7 @@ def gen_upp_test_arrays(
         else EMPTY_ARRAY_DEFAULT
     )
 
-    match _guppi_aggregator:
+    match _aggregator:
         case UPPAggrSelector.AVG:
             _test_value_seq = (
                 1 / 2 * np.einsum("ij->i", _g)[:, None] for _g in _test_measure_seq
@@ -428,30 +325,7 @@ def gen_upp_test_arrays(
             )
         case _:
             raise ValueError("GUPPI/diversion ratio aggregation method is invalid.")
-    del _cmcr_array, _guppi_array
-    (_divr_test_vector, _guppi_test_vector, _cmcr_test_vector, _ipr_test_vector) = (
-        _test_value_seq
-    )
-
-    if _divr_aggregator == UPPAggrSelector.MAX:
-        _divr_test_vector = _market_data.divr_array.max(axis=1, keepdims=True)
-
-    if _enf_resolution == INVResolution.ENFT:
-        _upp_test_arrays = UPPTestsRaw(
-            _guppi_test_vector >= _g_bar,
-            (_guppi_test_vector >= _g_bar) | (_divr_test_vector >= _divr_bar),
-            _cmcr_test_vector >= _cmcr_bar,
-            _ipr_test_vector >= _ipr_bar,
-        )
-    else:
-        _upp_test_arrays = UPPTestsRaw(
-            _guppi_test_vector < _g_bar,
-            (_guppi_test_vector < _g_bar) & (_divr_test_vector < _divr_bar),
-            _cmcr_test_vector < _cmcr_bar,
-            _ipr_test_vector < _ipr_bar,
-        )
-
-    return _upp_test_arrays
+    return tuple(_test_value_seq)
 
 
 def initialize_hd5(
@@ -494,11 +368,7 @@ def save_data_to_hdf5(
 
 
 def save_array_to_hdf5(
-    _array_obj: ArrayFloat[TF]
-    | ArrayINT[TI]
-    | ArrayDouble
-    | ArrayBIGINT
-    | ArrayBoolean,
+    _array_obj: ArrayFloat | ArrayINT | ArrayDouble | ArrayBIGINT | ArrayBoolean,
     _array_name: str,
     _h5_group: ptb.Group,
     _h5_file: ptb.File,

{mergeron-2024.739099.2.dist-info → mergeron-2024.739104.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mergeron
-Version: 2024.739099.2
+Version: 2024.739104.1
 Summary: Merger Policy Analysis using Python
 License: MIT
 Keywords: merger policy analysis,merger guidelines,merger screening,policy presumptions,concentration standards,upward pricing pressure,GUPPI

{mergeron-2024.739099.2.dist-info → mergeron-2024.739104.1.dist-info}/RECORD

@@ -1,9 +1,9 @@
 mergeron/License.txt,sha256=7iX-y0EyjkbVJKJLS4ZKzuuE1wd0lryfsD_IytLG8lQ,1246
-mergeron/__init__.py,sha256=A0iVjdlUd_UZWbclyBnPrbCH-JYk_JaMxVv8Dp5y-yU,1541
+mergeron/__init__.py,sha256=MXow5RSpGz49ggTHygQKv5TIJd5iRpTKyQyT9sYGdm4,1455
 mergeron/core/__init__.py,sha256=KtjBlZOl7jwBCAUhrTJB9PdrN39YLYytNiSUSM_gRmA,62
 mergeron/core/damodaran_margin_data.py,sha256=rMrgN1Qtw572a0ftY97OOj4otq8ldlLrcOi-bcE-org,8554
-mergeron/core/ftc_merger_investigations_data.py,sha256=oL_4yrNPpjuNIluBsDc51lYd2Z4NBBrd7-sHKd3FCbg,28129
-mergeron/core/guidelines_boundaries.py,sha256=Lv-7EE7b2SiudpRjW3gFY1uHu-K0UdesewwiqaqjcOw,15585
+mergeron/core/ftc_merger_investigations_data.py,sha256=qGAjjXEyqwS1PKKxvJGsSkr0sfI--4oyLss9I1qCNR4,28247
+mergeron/core/guidelines_boundaries.py,sha256=Iu7MBg3WzaRUALOobNmzmv_g7l-Njk1k7Y-esLBZBbk,15541
 mergeron/core/guidelines_boundary_functions.py,sha256=gohb7Uj1AjJQtD5ew7bVZZjGhJEYCjNNAPB1o6TsA9M,29683
 mergeron/core/guidelines_boundary_functions_extra.py,sha256=t84dMsaMKnYUNuvvGrMCP6vI8MDn88PJOgGZlNe1Zts,11280
 mergeron/core/pseudorandom_numbers.py,sha256=cJEWDTfy9CUTzR_di6Fm1Vl1Le6xWoU8wFHbYVMEuLI,9225
@@ -20,13 +20,12 @@ mergeron/data/jinja2_LaTeX_templates/mergeron_table_collection_template.tex.jinj
 mergeron/data/jinja2_LaTeX_templates/setup_tikz_tables.tex,sha256=1hw3RINDtBrh9ZEToMIiNFIu9rozcPwRly69-5O_0UQ,3207
 mergeron/demo/__init__.py,sha256=KtjBlZOl7jwBCAUhrTJB9PdrN39YLYytNiSUSM_gRmA,62
 mergeron/demo/visualize_empirical_margin_distribution.py,sha256=v1xFJumBX2Ooye82kSSgly-_GpFVkYSDqBwM__rcmZY,2363
-mergeron/gen/__init__.py,sha256=a60dpqC8G8J518Tb3qEJvTvFnVTYSmgZfhciVckokfw,17051
-mergeron/gen/_data_generation_functions.py,sha256=tBdzpo-6WjwnHTB3uy2B6TE0e0Ajx0rgi6fVtW9I1b4,27386
-mergeron/gen/data_generation.py,sha256=dj9otFi1OE3Eo7f32BD0ZXm9Xvlg0fCp4DDQ_XhDN_w,8479
-mergeron/gen/enforcement_stats.py,sha256=p-CgaOo2qh5G9QZjCxZdbVazXeb_AJ_ABDOc2Kdtt-Q,27438
-mergeron/gen/market_sample.py,sha256=HkzRFTKBXYIs2HbAyVDUiUHo9nCtAciSn5sohR-34cM,4282
-mergeron/gen/upp_tests.py,sha256=ZnV_x2TQqhJuWnnG9aTLnw1OBisgHCwHYxy94OK8W9E,16846
+mergeron/gen/__init__.py,sha256=A-co8RQL-QTsgfErF2O6qC3zcYYR56F6m9PBjH_M1kk,16564
+mergeron/gen/data_generation.py,sha256=_sjFm426uIj0MkoMIWQyL8hq3P4XbBIKe0kMUy7aVps,16449
+mergeron/gen/data_generation_functions.py,sha256=Pglv9rzeb2mG1SKp01AtkILJdvggDQvDnK-u90019po,28505
+mergeron/gen/enforcement_stats.py,sha256=ANnviFnoSUAwZOM5cMG1WrZwbkjuUohplRn5fQmd8Bs,27410
+mergeron/gen/upp_tests.py,sha256=iDtfy-lc7uSnBK37f_AxDIz3mO7Gf7-G5tHbX3QRDI0,12647
 mergeron/py.typed,sha256=frcCV1k9oG9oKj3dpUqdJg1PxRT2RSN_XKdLCPjaYaY,2
-mergeron-2024.739099.2.dist-info/METADATA,sha256=dyRrp-CAzkssNWLw44aQ-AbKKeuPFleWqEYaRPxaLG0,10922
-mergeron-2024.739099.2.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-mergeron-2024.739099.2.dist-info/RECORD,,
+mergeron-2024.739104.1.dist-info/METADATA,sha256=A4K7HcIzkIoT7KUmlNOqUic42V1psF1kxNgtIih5l68,10922
+mergeron-2024.739104.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+mergeron-2024.739104.1.dist-info/RECORD,,

mergeron/gen/market_sample.py

@@ -1,143 +0,0 @@
-"""
-Methods to generate data for analyzing merger enforcement policy.
-
-"""
-
-from __future__ import annotations
-
-from attrs import define
-from numpy.random import SeedSequence
-
-from .. import VERSION  # noqa: TID252
-from ..core.guidelines_boundaries import HMGThresholds  # noqa: TID252
-from . import MarketSpec, UPPTestRegime
-from .data_generation import gen_market_sample
-from .upp_tests import SaveData, enf_cnts, save_data_to_hdf5, sim_enf_cnts_ll
-
-__version__ = VERSION
-
-
-@define(slots=False)
-class MarketSample(MarketSpec):
-    def generate_sample(
-        self,
-        /,
-        *,
-        sample_size: int,
-        seed_seq_list: list[SeedSequence] | None,
-        nthreads: int,
-        save_data_to_file: SaveData,
-    ) -> None:
-        """Generate market data
-
-        Parameters
-        ----------
-        sample_size
-            Size of the market sample drawn
-
-        seed_seq_list
-            List of :code:`numpy.random.SeedSequence` objects
-
-        nthreads
-            Number of threads to use
-
-        save_data_to_file
-            Save data to given HDF5 file, at specified group node
-
-        Returns
-        -------
-        None
-
-        Notes
-        -----
-        See documentation for :class:`mergeron.gen.data_generation.gen_market_sample`
-        for more information, and :func:`mergeron.gen.data_generation.parse_seed_seq_list`
-        on the specification of :code:`seed_seq_list`.
-
-        """
-        self.data = gen_market_sample(
-            self,
-            sample_size=sample_size,
-            seed_seq_list=seed_seq_list,
-            nthreads=nthreads,
-        )
-
-        _invalid_array_names = (
-            ("fcounts", "choice_prob_outgd", "nth_firm_share", "hhi_post")
-            if self.share_spec.dist_type == "Uniform"
-            else ()
-        )
-
-        if save_data_to_file:
-            save_data_to_hdf5(
-                self.data,
-                excluded_attrs=_invalid_array_names,
-                save_data_to_file=save_data_to_file,
-            )
-
-    def estimate_enf_counts(
-        self,
-        _enf_parm_vec: HMGThresholds,
-        _upp_test_regime: UPPTestRegime,
-        /,
-        *,
-        sample_size: int = 10**6,
-        seed_seq_list: list[SeedSequence] | None,
-        nthreads: int,
-        save_data_to_file: SaveData = False,
-    ) -> None:
-        """Generate market data
-
-        Parameters
-        ----------
-        _enf_parm_vec
-            Threshold values for various Guidelines criteria
-
-        _upp_test_regime
-            Specifies whether to analyze enforcement, clearance, or both
-            and the GUPPI and diversion ratio aggregators employed, with
-            default being to analyze enforcement based on the maximum
-            merging-firm GUPPI and maximum diversion ratio between the
-            merging firms
-
-        sample_size
-            Size of the market sample drawn
-
-        seed_seq_list
-            List of :code:`numpy.random.SeedSequence` objects
-
-        nthreads
-            Number of threads to use
-
-        save_data_to_file
-            Save data to given HDF5 file, at specified group node
-
-        Returns
-        -------
-        None
-
-        Notes
-        -----
-        See documentation for :class:`mergeron.gen.MarketSpec` for details on specifying
-        how shares, margins, prices, and diversion ratios are generated, and whether to restrict
-        the sample to draws representing mergers that meet the HSR filing requirements. See
-        :class:`mergeron.gen.MarketDataSample` on the sample data generated; see,
-        :func:`mergeron.gen.data_generation.parse_seed_seq_list` on
-        the specification of :code:`seed_seq_list`.
-
-        """
-
-        if getattr(self, "market_data_sample", None) is None:
-            self.enf_counts = sim_enf_cnts_ll(
-                self,
-                _enf_parm_vec,
-                _upp_test_regime,
-                sample_size=sample_size,
-                seed_seq_list=seed_seq_list,
-                nthreads=nthreads,
-                save_data_to_file=save_data_to_file,
-            )
-        else:
-            self.enf_counts = enf_cnts(self.data, _enf_parm_vec, _upp_test_regime)
-            if save_data_to_file:
-                save_data_to_hdf5(self.enf_counts, save_data_to_file=save_data_to_file)