mergeron 2025.739341.10__py3-none-any.whl → 2025.739355.1__py3-none-any.whl

mergeron/__init__.py

@@ -15,7 +15,7 @@ from ruamel import yaml
 
 _PKG_NAME: str = Path(__file__).parent.name
 
-VERSION = "2025.739341.10"
+VERSION = "2025.739355.1"
 
 __version__ = VERSION
 

mergeron/core/__init__.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-from collections.abc import Mapping
+from collections.abc import Callable, Mapping
 from decimal import Decimal
 from types import MappingProxyType
 from typing import Any

mergeron/core/empirical_margin_distribution.py

@@ -51,7 +51,7 @@ from scipy import stats  # type: ignore
 
 from .. import NTHREADS, VERSION, ArrayDouble, this_yaml  # noqa: TID252
 from .. import WORK_DIR as PKG_WORK_DIR  # noqa: TID252
-from . import DEFAULT_BITGENERATOR
+from . import DEFAULT_BITGENERATOR, _mappingproxy_from_mapping
 
 __version__ = VERSION
 
@@ -60,7 +60,9 @@ WORK_DIR = globals().get("WORK_DIR", PKG_WORK_DIR)
 
 MGNDATA_ARCHIVE_PATH = WORK_DIR / "damodaran_margin_data_serialized.zip"
 
-type DamodaranMarginData = MappingProxyType[str, MappingProxyType[str, float | int]]
+type DamodaranMarginData = MappingProxyType[
+    str, MappingProxyType[str, MappingProxyType[str, float | int]]
+]
 
 FINANCIAL_INDUSTRIES = {
     _i.upper()
@@ -170,8 +172,8 @@ def margin_data_builder(
 
         _missing = {"GROSS MARGIN": 0.0, "NUMBER OF FIRMS": 0.0}
         gm, fc = zip(*[
-            [_v.get(_sk, _missing).get(_f) for _f in _missing]
-            for _k, _v in _margin_data_dict.items()
+            [_v.get(_sk, _missing)[_f] for _f in _missing]
+            for _v in _margin_data_dict.values()
         ])
 
         average_margin, firm_count = np.array(gm, float), np.array(fc, int)
@@ -223,7 +225,7 @@ def margin_data_getter(
     ws_pat = re.compile(r"\s+")
 
     #  Parse workbooks and save margin data dictionary
-    margin_data_dict = {}
+    margin_data_: dict[str, dict[str, MappingProxyType[str, float]]] = {}
     for _p in (WORK_DIR / "damodaran_margin_data_archive").iterdir():
         xl_wbk = CalamineWorkbook.from_path(_p)
         xl_wks = xl_wbk.get_sheet_by_index(
@@ -231,36 +233,35 @@ def margin_data_getter(
         ).to_python()
         if xl_wks[8][2] != "Gross Margin":
             raise ValueError("Worksheet does not match expected layout.")
+        row_keys: list[str] = [_c.upper() for _c in xl_wks[8][1:]]  # type: ignore
 
-        update = xl_wks[0][1].isoformat()[:10]
-        margin_data_annual = margin_data_dict.setdefault(update, {})
-        row_keys: list[str] = []
-        read_row_flag = False
-        for xl_row in xl_wks:
+        _u = xl_wks[0][1]
+        if not isinstance(_u, datetime.datetime):
+            raise ValueError("Worksheet does not match expected layout.")
+        update: str = _u.isoformat()[:10]
+
+        margin_data_annual = margin_data_.setdefault(update, {})
+        for xl_row in xl_wks[9:]:
             row_key = _s.upper() if isinstance((_s := xl_row[0]), str) else ""
 
-            if ws_pat.sub(" ", row_key) == "INDUSTRY NAME":
-                read_row_flag = True
-                row_keys = [_c.upper() for _c in xl_row]
-                continue
-            elif not read_row_flag or not row_key or row_key.startswith("TOTAL"):
+            if not row_key or row_key.startswith("TOTAL"):
                 continue
             else:
-                xl_row[1] = int(xl_row[1])
+                xl_row[1] = int(xl_row[1])  # type: ignore
                 margin_data_annual |= MappingProxyType({
                     row_key: MappingProxyType(
-                        dict(zip(row_keys[1:], xl_row[1:], strict=True))
+                        dict(zip(row_keys, xl_row[1:], strict=True))  # type: ignore
                     )
                 })
 
-    damodaran_margin_data = MappingProxyType(margin_data_dict)
+    margin_data_map: DamodaranMarginData = _mappingproxy_from_mapping(margin_data_)
     with (
         zipfile.ZipFile(data_archive_path, "w") as _yzp,
         _yzp.open(f"{data_archive_path.stem}.yaml", "w") as _yfh,
     ):
-        this_yaml.dump(damodaran_margin_data, _yfh)
+        this_yaml.dump(margin_data_map, _yfh)
 
-    return damodaran_margin_data
+    return margin_data_map
 
 
 def margin_data_downloader() -> None:

mergeron/core/guidelines_boundaries.py

@@ -334,18 +334,18 @@ class DiversionRatioBoundary:
 
         match self.agg_method:
             case UPPAggrSelector.DIS:
-                upp_agg_fn = gbfn.shrratio_boundary_wtd_avg
+                upp_agg_fn = gbfn.diversion_share_boundary_wtd_avg
                 upp_agg_kwargs |= {"agg_method": "distance", "weighting": None}
             case UPPAggrSelector.AVG:
-                upp_agg_fn = gbfn.shrratio_boundary_xact_avg  # type: ignore
+                upp_agg_fn = gbfn.diversion_share_boundary_xact_avg  # type: ignore
             case UPPAggrSelector.MAX:
-                upp_agg_fn = gbfn.shrratio_boundary_max  # type: ignore
+                upp_agg_fn = gbfn.diversion_share_boundary_max  # type: ignore
                 upp_agg_kwargs = {"dps": 10}  # replace here
             case UPPAggrSelector.MIN:
-                upp_agg_fn = gbfn.shrratio_boundary_min  # type: ignore
+                upp_agg_fn = gbfn.diversion_share_boundary_min  # type: ignore
                 upp_agg_kwargs |= {"dps": 10}  # update here
             case _:
-                upp_agg_fn = gbfn.shrratio_boundary_wtd_avg
+                upp_agg_fn = gbfn.diversion_share_boundary_wtd_avg
 
                 aggregator_: Literal["arithmetic mean", "geometric mean", "distance"]
                 if self.agg_method.value.endswith("geometric mean"):

mergeron/core/guidelines_boundary_functions.py

@@ -202,7 +202,7 @@ def hhi_post_contrib_boundary(
 
 
 # hand-rolled root finding
-def shrratio_boundary_wtd_avg(
+def diversion_share_boundary_wtd_avg(
     _delta_star: float = 0.075,
     _r_val: float = DEFAULT_REC_RATIO,
     /,
@@ -370,7 +370,7 @@ def shrratio_boundary_wtd_avg(
     else:
         s_2_oddsum -= s_1_pre
 
-    _s_intcpt = _shrratio_boundary_intcpt(
+    _s_intcpt = _diversion_share_boundary_intcpt(
         s_2_pre,
         _delta_star,
         _r_val,
@@ -406,7 +406,7 @@ def shrratio_boundary_wtd_avg(
     )
 
 
-def shrratio_boundary_xact_avg(
+def diversion_share_boundary_xact_avg(
     _delta_star: float = 0.075,
     _r_val: float = DEFAULT_REC_RATIO,
     /,
@@ -467,47 +467,46 @@ def shrratio_boundary_xact_avg(
         Array of share-pairs, area under boundary, area under boundary.
 
     """
-    _delta_star, _r_val = (mpf(f"{_v}") for _v in (_delta_star, _r_val))
     _s_mid = _delta_star / (1 + _delta_star)
-    _step_size = mp.power(10, -dps)
+    _step_size = 10**-dps
 
     _bdry_start = np.array([(_s_mid, _s_mid)])
-    _s_1 = np.array(mp.arange(_s_mid - _step_size, 0, -_step_size))
+    _s_1 = np.arange(_s_mid - _step_size, 0, -_step_size)
     if recapture_form == "inside-out":
-        _s_intcpt = mp.fdiv(
-            mp.fsub(
-                2 * _delta_star * _r_val + 1, mp.fabs(2 * _delta_star * _r_val - 1)
-            ),
-            2 * mpf(f"{_r_val}"),
+        _s_intcpt: float = (
+            2 * _delta_star * _r_val + 1 - np.abs(2 * _delta_star * _r_val - 1)
+        ) / (2 * _r_val)
+        nr_t1: ArrayDouble = (
+            1 + 2 * _delta_star * _r_val * (1 - _s_1) - _s_1 * (1 - _r_val)
         )
-        nr_t1 = 1 + 2 * _delta_star * _r_val * (1 - _s_1) - _s_1 * (1 - _r_val)
 
-        nr_sqrt_mdr = 4 * _delta_star * _r_val
-        nr_sqrt_mdr2 = nr_sqrt_mdr * _r_val
-        nr_sqrt_md2r2 = nr_sqrt_mdr2 * _delta_star
+        nr_sqrt_mdr: float = 4 * _delta_star * _r_val
+        nr_sqrt_mdr2: float = nr_sqrt_mdr * _r_val
+        nr_sqrt_md2r2: float = nr_sqrt_mdr2 * _delta_star
 
-        nr_sqrt_t1 = nr_sqrt_md2r2 * (_s_1**2 - 2 * _s_1 + 1)
-        nr_sqrt_t2 = nr_sqrt_mdr2 * _s_1 * (_s_1 - 1)
-        nr_sqrt_t3 = nr_sqrt_mdr * (2 * _s_1 - _s_1**2 - 1)
-        nr_sqrt_t4 = (_s_1**2) * (_r_val**2 - 6 * _r_val + 1)
-        nr_sqrt_t5 = _s_1 * (6 * _r_val - 2) + 1
+        nr_sqrt_t1: ArrayDouble = nr_sqrt_md2r2 * (_s_1**2 - 2 * _s_1 + 1)
+        nr_sqrt_t2: ArrayDouble = nr_sqrt_mdr2 * _s_1 * (_s_1 - 1)
+        nr_sqrt_t3: ArrayDouble = nr_sqrt_mdr * (2 * _s_1 - _s_1**2 - 1)
+        nr_sqrt_t4: ArrayDouble = (_s_1**2) * (_r_val**2 - 6 * _r_val + 1)
+        nr_sqrt_t5: ArrayDouble = _s_1 * (6 * _r_val - 2) + 1
 
-        nr_t2_mdr = nr_sqrt_t1 + nr_sqrt_t2 + nr_sqrt_t3 + nr_sqrt_t4 + nr_sqrt_t5
+        nr_t2_mdr: ArrayDouble = (
+            nr_sqrt_t1 + nr_sqrt_t2 + nr_sqrt_t3 + nr_sqrt_t4 + nr_sqrt_t5
+        )
 
         # Alternative grouping of terms in np.sqrt
-        nr_sqrt_s1sq = (_s_1**2) * (
-            nr_sqrt_md2r2 + nr_sqrt_mdr2 - nr_sqrt_mdr + _r_val**2 - 6 * _r_val + 1
-        )
-        nr_sqrt_s1 = _s_1 * (
+        nr_sqrt_nos1: float = nr_sqrt_md2r2 - nr_sqrt_mdr + 1
+        nr_sqrt_s1: ArrayDouble = _s_1 * (
             -2 * nr_sqrt_md2r2 - nr_sqrt_mdr2 + 2 * nr_sqrt_mdr + 6 * _r_val - 2
         )
-        nr_sqrt_nos1 = nr_sqrt_md2r2 - nr_sqrt_mdr + 1
-
-        nr_t2_s1 = nr_sqrt_s1sq + nr_sqrt_s1 + nr_sqrt_nos1
+        nr_sqrt_s1sq: ArrayDouble = (_s_1**2) * (
+            nr_sqrt_md2r2 + nr_sqrt_mdr2 - nr_sqrt_mdr + _r_val**2 - 6 * _r_val + 1
+        )
+        nr_t2_s1: ArrayDouble = nr_sqrt_s1sq + nr_sqrt_s1 + nr_sqrt_nos1
 
         if not np.isclose(
-            np.einsum("i->", nr_t2_mdr.astype(float)),
-            np.einsum("i->", nr_t2_s1.astype(float)),
+            np.einsum("i->", nr_t2_mdr),
+            np.einsum("i->", nr_t2_s1),
             rtol=0,
             atol=0.5 * dps,
         ):
@@ -516,25 +515,28 @@ def shrratio_boundary_xact_avg(
                 f"with recapture spec, {f'"{recapture_form}"'} is incorrect."
             )
 
-        s_2 = (nr_t1 - np.sqrt(nr_t2_s1)) / (2 * _r_val)
+        s_2: ArrayDouble = (nr_t1 - nr_t2_s1**0.5) / (2 * _r_val)
 
     else:
-        _s_intcpt = mp.fsub(_delta_star + 1 / 2, mp.fabs(_delta_star - 1 / 2))
-        s_2 = (
-            (1 / 2)
+        _s_intcpt: float = _delta_star + 1 / 2 - np.abs(_delta_star - 1 / 2)
+        s_2: ArrayDouble = (
+            0.5
             + _delta_star
             - _delta_star * _s_1
-            - np.sqrt(
-                ((_delta_star**2) - 1) * (_s_1**2)
-                + (-2 * (_delta_star**2) + _delta_star + 1) * _s_1
-                + (_delta_star**2)
-                - _delta_star
-                + (1 / 4)
+            - (
+                (
+                    ((_delta_star**2) - 1) * (_s_1**2)
+                    + (-2 * (_delta_star**2) + _delta_star + 1) * _s_1
+                    + (_delta_star**2)
+                    - _delta_star
+                    + (1 / 4)
+                )
+                ** 0.5
             )
         )
 
     bdry_inner = np.stack((_s_1, s_2), axis=1)
-    bdry_end = np.array([(mpf("0.0"), _s_intcpt)], float)
+    bdry_end = np.array([(0.0, _s_intcpt)], float)
 
     bdry = np.vstack((
         bdry_end,
@@ -542,14 +544,14 @@ def shrratio_boundary_xact_avg(
         _bdry_start,
         bdry_inner[:, ::-1],
         bdry_end[:, ::-1],
-    )).astype(float)
+    ))
     s_2 = np.concatenate((np.array([_s_mid], float), s_2))
 
     bdry_ends = [0, -1]
     bdry_odds = np.array(range(1, len(s_2), 2), int)
     bdry_evns = np.array(range(2, len(s_2), 2), int)
 
-    # Double the are under the curve, and subtract the double counted bit.
+    # Double the area under the curve, and subtract the double counted bit.
     bdry_area_simpson = 2 * _step_size * (
         (4 / 3) * np.sum(s_2.take(bdry_odds))
         + (2 / 3) * np.sum(s_2.take(bdry_evns))
@@ -559,7 +561,7 @@ def shrratio_boundary_xact_avg(
     return GuidelinesBoundary(bdry, round(float(bdry_area_simpson), dps))
 
 
-def shrratio_boundary_min(
+def diversion_share_boundary_min(
     _delta_star: float = 0.075,
     _r_val: float = DEFAULT_REC_RATIO,
     /,
@@ -615,7 +617,7 @@ def shrratio_boundary_min(
     )
 
 
-def shrratio_boundary_max(
+def diversion_share_boundary_max(
     _delta_star: float = 0.075, _: float = DEFAULT_REC_RATIO, /, *, dps: int = 10
 ) -> GuidelinesBoundary:
     R"""
@@ -647,7 +649,7 @@ def shrratio_boundary_max(
     )
 
 
-def _shrratio_boundary_intcpt(
+def _diversion_share_boundary_intcpt(
     s_2_pre: float,
     _delta_star: MPFloat,
     _r_val: MPFloat,
@@ -783,7 +785,7 @@ def boundary_plot(
     mktshare_plot_flag: bool = True,
     mktshare_axes_flag: bool = True,
     backend: Literal["pgf"] | str | None = "pgf",
-) -> tuple[mpl.pyplot, mpl.pyplot.Figure, mpl.axes.Axes, Callable[..., mpl.axes.Axes]]:
+) -> tuple[mpl.figure.Figure, Callable[..., None]]:
     """Set up basic figure and axes for plots of safe harbor boundaries.
 
     See, https://matplotlib.org/stable/tutorials/text/pgf.html
@@ -807,9 +809,6 @@ def boundary_plot(
                 R'  "luaotfload.patch_font", embedfull, "embedfull"'
                 R")",
                 R"\end{luacode}",
-                R"\usepackage{mathtools}",
-                R"\usepackage{unicode-math}",
-                R"\setmathfont[math-style=ISO]{STIX Two Math}",
                 R"\setmainfont{STIX Two Text}",
                 r"\setsansfont{Fira Sans Light}",
                 R"\setmonofont[Scale=MatchLowercase,]{Fira Mono}",
@@ -822,6 +821,9 @@ def boundary_plot(
                 R"  Numbers={Monospaced, Lining},",
                 R"  LetterSpace=0.50,",
                 R"  }",
+                R"\usepackage{mathtools}",
+                R"\usepackage{unicode-math}",
+                R"\setmathfont[math-style=ISO]{STIX Two Math}",
                 R"\usepackage[",
                 R"  activate={true, nocompatibility},",
                 R"  tracking=true,",
@@ -831,57 +833,53 @@ def boundary_plot(
 
     # Initialize a canvas with a single figure (set of axes)
     fig_ = plt.figure(figsize=(5, 5), dpi=600)
-    ax_out = fig_.add_subplot()
+    ax_ = fig_.add_subplot()
+    # Set the width of axis grid lines, and tick marks:
+    # both axes, both major and minor ticks
+    # Frame, grid, and face color
+    for _spos0 in "left", "bottom":
+        ax_.spines[_spos0].set_linewidth(0.5)
+        ax_.spines[_spos0].set_zorder(5)
+    for _spos1 in "top", "right":
+        ax_.spines[_spos1].set_linewidth(0.0)
+        ax_.spines[_spos1].set_zorder(0)
+        ax_.spines[_spos1].set_visible(False)
+    ax_.set_facecolor("#E6E6E6")
+
+    ax_.grid(linewidth=0.5, linestyle=":", color="grey", zorder=1)
+    ax_.tick_params(axis="both", which="both", width=0.5)
+
+    # Tick marks skip, size, and rotation
+    # x-axis
+    for _t in ax_.get_xticklabels():
+        _t.update({"fontsize": 6, "rotation": 45, "ha": "right"})
+    # y-axis
+    for _t in ax_.get_yticklabels():
+        _t.update({"fontsize": 6, "rotation": 0, "ha": "right"})
 
     def _set_axis_def(
-        ax1_: mpa.Axes,
+        ax0_: mpa.Axes,
         /,
         *,
         mktshare_plot_flag: bool = False,
         mktshare_axes_flag: bool = False,
-    ) -> mpa.Axes:
-        # Set the width of axis grid lines, and tick marks:
-        # both axes, both major and minor ticks
-        # Frame, grid, and face color
-        for _spos0 in "left", "bottom":
-            ax1_.spines[_spos0].set_linewidth(0.5)
-            ax1_.spines[_spos0].set_zorder(5)
-        for _spos1 in "top", "right":
-            ax1_.spines[_spos1].set_linewidth(0.0)
-            ax1_.spines[_spos1].set_zorder(0)
-            ax1_.spines[_spos1].set_visible(False)
-        ax1_.set_facecolor("#E6E6E6")
-
-        ax1_.grid(linewidth=0.5, linestyle=":", color="grey", zorder=1)
-        ax1_.tick_params(axis="x", which="both", width=0.5)
-        ax1_.tick_params(axis="y", which="both", width=0.5)
-
-        # Tick marks skip, size, and rotation
-        # x-axis
-        plt.setp(
-            ax1_.xaxis.get_majorticklabels(),
-            horizontalalignment="right",
-            fontsize=6,
-            rotation=45,
-        )
-        # y-axis
-        plt.setp(
-            ax1_.yaxis.get_majorticklabels(), horizontalalignment="right", fontsize=6
-        )
-
+    ) -> None:
         if mktshare_plot_flag:
+            # Axis scale
+            ax0_.set_xlim(0, 1)
+            ax0_.set_ylim(0, 1)
+            ax0_.set_aspect(1.0)
+
             # Plot the ray of symmetry
-            ax1_.plot(
+            ax0_.plot(
                 [0, 1], [0, 1], linewidth=0.5, linestyle=":", color="grey", zorder=1
             )
 
-            # Axis scale
-            ax1_.set_xlim(0, 1)
-            ax1_.set_ylim(0, 1)
-            ax1_.set_aspect(1.0)
-
-            # Truncate the axis frame to a triangle:
-            ax1_.add_patch(
+            # Truncate the axis frame to a triangle bounded by the other diagonal:
+            ax0_.plot(
+                [0, 1], [1, 0], linestyle="-", linewidth=0.5, color="black", zorder=1
+            )
+            ax0_.add_patch(
                 mpp.Rectangle(
                     xy=(1.0025, 0.00),
                     width=1.1 * mp.sqrt(2),
@@ -894,48 +892,36 @@ def boundary_plot(
                     zorder=5,
                 )
             )
-            # Feasible space is bounded by the other diagonal:
-            ax1_.plot(
-                [0, 1], [1, 0], linestyle="-", linewidth=0.5, color="black", zorder=1
-            )
 
             # Axis Tick-mark locations
             # One can supply an argument to mpt.AutoMinorLocator to
             # specify a fixed number of minor intervals per major interval, e.g.:
             # minorLocator = mpt.AutoMinorLocator(2)
             # would lead to a single minor tick between major ticks.
-            minor_locator = mpt.AutoMinorLocator(5)
-            major_locator = mpt.MultipleLocator(0.05)
-            for axs_ in ax1_.xaxis, ax1_.yaxis:
-                if axs_ == ax1_.xaxis:
-                    _majorticklabels_rot = 45
-                elif axs_ == ax1_.yaxis:
-                    _majorticklabels_rot = 0
-                # x-axis
-                axs_.set_major_locator(major_locator)
-                axs_.set_minor_locator(minor_locator)
+            for axs_ in ax0_.xaxis, ax0_.yaxis:
+                axs_.set_major_locator(mpt.MultipleLocator(0.05))
+                axs_.set_minor_locator(mpt.AutoMinorLocator(5))
                 # It"s always x when specifying the format
                 axs_.set_major_formatter(mpt.StrMethodFormatter("{x:>3.0%}"))
 
             # Hide every other tick-label
-            for axl_ in ax1_.get_xticklabels(), ax1_.get_yticklabels():
-                plt.setp(axl_[::2], visible=False)
+            for axl_ in ax0_.get_xticklabels(), ax0_.get_yticklabels():
+                for _t in axl_[::2]:
+                    _t.set_visible(False)
 
             # Axis labels
             if mktshare_axes_flag:
                 # x-axis
-                ax1_.set_xlabel("Firm 1 Market Share, $s_1$", fontsize=10)
-                ax1_.xaxis.set_label_coords(0.75, -0.1)
+                ax0_.set_xlabel("Firm 1 Market Share, $s_1$", fontsize=10)
+                ax0_.xaxis.set_label_coords(0.75, -0.1)
                 # y-axis
-                ax1_.set_ylabel("Firm 2 Market Share, $s_2$", fontsize=10)
-                ax1_.yaxis.set_label_coords(-0.1, 0.75)
-
-        return ax1_
+                ax0_.set_ylabel("Firm 2 Market Share, $s_2$", fontsize=10)
+                ax0_.yaxis.set_label_coords(-0.1, 0.75)
 
-    ax_out = _set_axis_def(
-        ax_out,
+    _set_axis_def(
+        ax_,
         mktshare_plot_flag=mktshare_plot_flag,
         mktshare_axes_flag=mktshare_axes_flag,
     )
 
-    return plt, fig_, ax_out, _set_axis_def
+    return fig_, _set_axis_def

mergeron/core/guidelines_boundary_functions_extra.py

@@ -7,11 +7,9 @@ poor performance
 
 """
 
-from collections.abc import Callable
 from typing import Literal
 
 import numpy as np
-from attrs import frozen
 from mpmath import mp, mpf  # type: ignore
 from scipy.spatial.distance import minkowski as distance_function  # type: ignore
 from sympy import lambdify, simplify, solve, symbols  # type: ignore
@@ -96,7 +94,7 @@ def hhi_delta_boundary_qdtr(_dh_val: float = 0.01, /) -> GuidelinesBoundaryCalla
     )
 
 
-def shrratio_boundary_qdtr_wtd_avg(
+def diversion_share_boundary_qdtr_wtd_avg(
     _delta_star: float = 0.075,
     _r_val: float = DEFAULT_REC_RATIO,
     /,
@@ -211,7 +209,7 @@ def shrratio_boundary_qdtr_wtd_avg(
     )
 
 
-def shrratio_boundary_distance(
+def diversion_share_boundary_distance(
     _delta_star: float = 0.075,
     _r_val: float = DEFAULT_REC_RATIO,
     /,
@@ -220,14 +218,14 @@ def shrratio_boundary_distance(
     weighting: Literal["own-share", "cross-product-share"] | None = "own-share",
     recapture_form: Literal["inside-out", "proportional"] = "inside-out",
     dps: int = 5,
-) -> gbf.GuidelinesBoundary:
+) -> GuidelinesBoundary:
     R"""
     Share combinations for the share-ratio boundaries using various aggregators.
 
     Reimplements the arithmetic-averages and distance estimations from function,
-    `shrratio_boundary_wtd_avg` but uses the Minkowski-distance function,
+    `diversion_share_boundary_wtd_avg` but uses the Minkowski-distance function,
     `scipy.spatial.distance.minkowski` for all aggregators. This reimplementation
-    is useful for testing the output of `shrratio_boundary_wtd_avg`
+    is useful for testing the output of `diversion_share_boundary_wtd_avg`
     but runs considerably slower.
 
     Parameters
@@ -330,7 +328,7 @@ def shrratio_boundary_distance(
     else:
         s_2_oddsum -= s_1_pre
 
-    s_intcpt = gbf._shrratio_boundary_intcpt(
+    s_intcpt = gbf._diversion_share_boundary_intcpt(
         s_1_pre,
         _delta_star,
         _r_val,
@@ -360,20 +358,20 @@ def shrratio_boundary_distance(
 
     bdry_points.append((mpf("0.0"), s_intcpt))
     # Points defining boundary to point-of-symmetry
-    return gbf.GuidelinesBoundary(
+    return GuidelinesBoundary(
         np.vstack((bdry_points[::-1], np.flip(bdry_points[1:], 1))),
         round(float(bdry_area_total), dps),
     )
 
 
-def shrratio_boundary_xact_avg_mp(
+def diversion_share_boundary_xact_avg_mp(
     _delta_star: float = 0.075,
     _r_val: float = DEFAULT_REC_RATIO,
     /,
     *,
     recapture_form: Literal["inside-out", "proportional"] = "inside-out",
     dps: int = 5,
-) -> gbf.GuidelinesBoundary:
+) -> GuidelinesBoundary:
     R"""
     Share combinations along the simple average diversion-ratio boundary.
 
@@ -515,12 +513,12 @@ def shrratio_boundary_xact_avg_mp(
         + (1 / 3) * np.sum(s_2.take(bdry_ends))
     ) - mp.power(_s_mid, 2)
 
-    return gbf.GuidelinesBoundary(bdry, float(mp.nstr(bdry_area_simpson, dps)))
+    return GuidelinesBoundary(bdry, float(mp.nstr(bdry_area_simpson, dps)))
 
 
-# shrratio_boundary_wtd_avg_autoroot
+# diversion_share_boundary_wtd_avg_autoroot
 # this function is about half as fast as the manual one! ... and a touch less precise
-def _shrratio_boundary_wtd_avg_autoroot(
+def _diversion_share_boundary_wtd_avg_autoroot(
     _delta_star: float = 0.075,
     _r_val: float = DEFAULT_REC_RATIO,
     /,
@@ -687,7 +685,7 @@ def _shrratio_boundary_wtd_avg_autoroot(
     else:
         s_2_oddsum -= s_1_pre
 
-    _s_intcpt = gbf._shrratio_boundary_intcpt(
+    _s_intcpt = gbf._diversion_share_boundary_intcpt(
         s_2_pre,
         _delta_star,
         _r_val,

mergeron/gen/__init__.py

@@ -4,8 +4,10 @@ from __future__ import annotations
 
 import enum
 import io
+import zipfile
 from collections.abc import Sequence
 from operator import attrgetter
+from typing import IO
 
 import h5py  # type: ignore
 import numpy as np
@@ -370,7 +372,11 @@ class PCMSpec:
         _v: ArrayFloat | Sequence[ArrayDouble] | None,
     ) -> None:
         if _i.dist_type.name.startswith("BETA"):
-            if _v is None or not any(_v.shape):
+            if (
+                _v is None
+                or not hasattr(_v, "len")
+                or (isinstance(_v, np.ndarray) and not any(_v.shape))
+            ):
                 pass
             elif np.array_equal(_v, DEFAULT_DIST_PARMS):
                 raise ValueError(
@@ -521,7 +527,9 @@ class MarketSampleData:
         return byte_stream.getvalue()
 
     @classmethod
-    def from_h5f(cls, _hfh: io.BufferedReader) -> MarketSampleData:
+    def from_h5f(
+        cls, _hfh: io.BufferedReader | zipfile.ZipExtFile | IO[bytes]
+    ) -> MarketSampleData:
         """Load market sample data from HDF5 file."""
         with h5py.File(_hfh, "r") as _h5f:
             _retval = cls(**{_a: _h5f[_a][:] for _a in _h5f})

mergeron/gen/data_generation.py

@@ -445,20 +445,22 @@ class MarketSample:
             this_yaml.dump(self, _yfh)
 
         if save_dataset:
-            if all((_ndt := self.dataset is None, _net := self.enf_counts is None)):
+            if self.dataset is None and self.enf_counts is None:
                 raise ValueError(
                     "No dataset and/or enforcement counts available for saving. "
                     "Generate some data or set save_dataset to False to proceed."
                 )
 
-            if not _ndt:
-                with (zpath / f"{name_root}_dataset.h5").open("wb") as _hfh:
-                    _hfh.write(self.dataset.to_h5bin())
+            else:
+                if self.dataset is not None:
+                    with (zpath / f"{name_root}_dataset.h5").open("wb") as _hfh:
+                        _hfh.write(self.dataset.to_h5bin())
 
-            if not _net:
-                with (zpath / f"{name_root}_enf_counts.yaml").open("w") as _yfh:
-                    this_yaml.dump(self.enf_counts, _yfh)
+                if self.enf_counts is not None:
+                    with (zpath / f"{name_root}_enf_counts.yaml").open("w") as _yfh:
+                        this_yaml.dump(self.enf_counts, _yfh)
 
+    @staticmethod
     def from_archive(
         zip_: zipfile.ZipFile, _subdir: str = "", /, *, restore_dataset: bool = False
     ) -> MarketSample:
@@ -466,27 +468,28 @@ class MarketSample:
         zpath = zipfile.Path(zip_, at=_subdir)
         name_root = f"{_PKG_NAME}_market_sample"
 
-        market_sample_ = this_yaml.load((zpath / f"{name_root}.yaml").read_text())
+        market_sample_: MarketSample = this_yaml.load(
+            (zpath / f"{name_root}.yaml").read_text()
+        )
 
         if restore_dataset:
-            if not any((
-                (_dt := (_dp := zpath / f"{name_root}_dataset.h5").is_file()),
-                (_et := (_ep := zpath / f"{name_root}_enf_counts.yaml").is_file()),
-            )):
+            _dt = (_dp := zpath / f"{name_root}_dataset.h5").is_file()
+            _et = (_ep := zpath / f"{name_root}_enf_counts.yaml").is_file()
+            if not (_dt or _et):
                 raise ValueError(
                     "Archive has no sample data to restore. "
                     "Delete second argument, or set it False, and rerun."
                 )
-
-            if _dt:
-                with _dp.open("rb") as _hfh:
+            else:
+                if _dt:
+                    with _dp.open("rb") as _hfh:
+                        object.__setattr__(
+                            market_sample_, "dataset", MarketSampleData.from_h5f(_hfh)
+                        )
+                if _et:
                     object.__setattr__(
-                        market_sample_, "dataset", MarketSampleData.from_h5f(_hfh)
+                        market_sample_, "enf_counts", this_yaml.load(_ep.read_text())
                     )
-            if _et:
-                object.__setattr__(
-                    market_sample_, "enf_counts", this_yaml.load(_ep.read_text())
-                )
         return market_sample_
 
     @classmethod

mergeron/gen/data_generation_functions.py

@@ -438,11 +438,13 @@ def gen_divr_array(
     """
     divr_array: ArrayDouble
     if _recapture_form == RECForm.FIXED:
-        divr_array = _recapture_ratio * _frmshr_array[:, ::-1] / (1 - _frmshr_array)  # type: ignore
+        divr_array = np.divide(
+            _recapture_ratio * _frmshr_array[:, ::-1], 1 - _frmshr_array
+        )
 
     else:
         purchprob_array = _aggregate_purchase_prob * _frmshr_array
-        divr_array = purchprob_array[:, ::-1] / (1 - purchprob_array)
+        divr_array = np.divide(purchprob_array[:, ::-1], 1 - purchprob_array)
 
     divr_assert_test = (
         (np.round(np.einsum("ij->i", _frmshr_array), 15) == 1)
@@ -616,7 +618,7 @@ def gen_margin_price_data(
             # Revenue ratio has been 10-to-1 since inception
             # Thus, a simple form of the HSR filing test would impose a 10-to-1
             # ratio restriction on the merging firms' revenues
-            rev_ratio = (rev_array.min(axis=1) / rev_array.max(axis=1)).round(4)
+            rev_ratio = np.divide(rev_array.min(axis=1), rev_array.max(axis=1)).round(4)
             hsr_filing_test = rev_ratio >= test_rev_ratio_inv
             # del _rev_array, _rev_ratio
         case SSZConstant.HSR_NTH:

{mergeron-2025.739341.10.dist-info → mergeron-2025.739355.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: mergeron
-Version: 2025.739341.10
+Version: 2025.739355.1
 Summary: Python for analyzing merger enforcement policy
 License: MIT
 Keywords: merger enforcement policy,merger guidelines,merger screening,enforcement presumptions,concentration standards,diversion ratio,upward pricing pressure,GUPPI
@@ -18,23 +18,22 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3 :: Only
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: Implementation :: CPython
-Requires-Dist: aenum (>=3.1.15,<4.0.0)
-Requires-Dist: attrs (>=23.2)
-Requires-Dist: bs4 (>=0.0.1)
-Requires-Dist: certifi (>=2023.11.17)
-Requires-Dist: h5py (>=3.13.0,<4.0.0)
-Requires-Dist: jinja2 (>=3.1)
-Requires-Dist: joblib (>=1.3)
-Requires-Dist: linuxdoc (>=20240924,<20240925)
-Requires-Dist: lxml (>=5.3.1,<6.0.0)
-Requires-Dist: matplotlib (>=3.8)
-Requires-Dist: mpmath (>=1.3)
-Requires-Dist: python-calamine (>=0.3.1,<0.4.0)
-Requires-Dist: ruamel-yaml (>=0.18.10,<0.19.0)
-Requires-Dist: scipy (>=1.12)
-Requires-Dist: sympy (>=1.12)
-Requires-Dist: types-beautifulsoup4 (>=4.11.2)
-Requires-Dist: urllib3 (>=2.2.2,<3.0.0)
+Requires-Dist: aenum (>=3.1.15)
+Requires-Dist: attrs (>=25.3.0)
+Requires-Dist: beautifulsoup4 (>=4.13.3)
+Requires-Dist: certifi (>=2025.1.31)
+Requires-Dist: h5py (>=3.13.0)
+Requires-Dist: jinja2 (>=3.1.6)
+Requires-Dist: joblib (>=1.4.2)
+Requires-Dist: lxml (>=5.3.2)
+Requires-Dist: matplotlib (>=3.10.1)
+Requires-Dist: mpmath (>=1.3.0)
+Requires-Dist: python-calamine (>=0.3.2)
+Requires-Dist: ruamel-yaml (>=0.18.10)
+Requires-Dist: scipy (>=1.15.2)
+Requires-Dist: sympy (>=1.13.3)
+Requires-Dist: types-beautifulsoup4 (>=4.12.0)
+Requires-Dist: urllib3 (>=2.3.0)
 Project-URL: Documentation, https://capeconomics.github.io/mergeron/
 Project-URL: Repository, https://github.com/capeconomics/mergeron.git
 Description-Content-Type: text/x-rst
@@ -87,8 +86,8 @@ To install the package, use the following shell command:
     pip install mergeron
 
 
-Documentation 
+Documentation
 -------------
 
-Usage guide and API reference available `here <https://capeconomics.github.io/mergeron/>`_.
+Usage guide and API reference are `available <https://capeconomics.github.io/mergeron/>`_.
 

mergeron-2025.739355.1.dist-info/RECORD

@@ -0,0 +1,20 @@
+mergeron/__init__.py,sha256=EuIMqkVajtF2FCtP2VIkeEc9Kw9k4ZR5_dRZjxHbXHs,5773
+mergeron/core/__init__.py,sha256=4Y_q-Qu7gXENVKHS-lNebn5mPZDy9oPHFwUV7fAW9Nw,3269
+mergeron/core/empirical_margin_distribution.py,sha256=aqQ7JYpliHSjHpzyPRkYW9LhJfp-aAlSifRxYx3Dmbo,11623
+mergeron/core/ftc_merger_investigations_data.py,sha256=k4TDkP1rDBmN4uKOYF0SUvSRkYmyVhbsBvLUKDYJqOo,28537
+mergeron/core/guidelines_boundaries.py,sha256=noacM3NmhzqPKLPGm7HEvLKX2UlRI1DCw1kxDa2cFXk,15586
+mergeron/core/guidelines_boundary_functions.py,sha256=yyq2Fn41OwfeSSlKdnvkVwaPMvUalp6_MCOXt49DbKY,28606
+mergeron/core/guidelines_boundary_functions_extra.py,sha256=JompgWmwnwcWsodXrZbvzY_OXw-7ppb_H_Gsz9-fpgI,22080
+mergeron/core/pseudorandom_numbers.py,sha256=-mPveXjJJ446NrBMAmWIa2jI6j0Px0xcCJTGEEsn3bo,10149
+mergeron/data/__init__.py,sha256=CbqheFSkXEe7NOfuAV-NLaaEiNzl9pVCndGjtUUOj9g,1846
+mergeron/data/damodaran_margin_data_serialized.zip,sha256=Wc1v9buSrYTWWAravG8W9nPbgsU07zMtSAR2RvMQU5s,623482
+mergeron/data/ftc_merger_investigations_data.zip,sha256=tiB2TLFyS9LMSFIv8DBA_oEEx12DU4MyjHni4NlsRMU,24002
+mergeron/gen/__init__.py,sha256=bRGGIFBqIVw4-zZ4AKwcNbOTM9aHKegPj7w_7MJV9-I,23856
+mergeron/gen/data_generation.py,sha256=L44YNtxso-Ya50YT71rnG-el4_PgGn4vtoA7rFDD194,17487
+mergeron/gen/data_generation_functions.py,sha256=AaDG0XxpTYsx_2fuUkE20b7bdFq9kfQMWvGIhEFiERw,26106
+mergeron/gen/enforcement_stats.py,sha256=etTax-sBSn8DveF-IxuBJDdX0XSBD6oFU9vaZe6cYks,14387
+mergeron/gen/upp_tests.py,sha256=gRJISQ2jGmIDmFOvaTIkvYooI4mK-QbgkfgL46RrRio,7445
+mergeron/py.typed,sha256=frcCV1k9oG9oKj3dpUqdJg1PxRT2RSN_XKdLCPjaYaY,2
+mergeron-2025.739355.1.dist-info/METADATA,sha256=qmUfVT8DcCL6o3cgQz-wK_mWvmANZbE9wSg8FSaxGXs,3864
+mergeron-2025.739355.1.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
+mergeron-2025.739355.1.dist-info/RECORD,,

mergeron-2025.739341.10.dist-info/RECORD

@@ -1,20 +0,0 @@
-mergeron/__init__.py,sha256=9ZcHQeCALXJpkK-1dqEmimUlO2oPqxDfqICuDaJDvig,5774
-mergeron/core/__init__.py,sha256=NChJfOkahbGPa1Ll1fO3agY5-IoDlEra3xNkXPnKIVM,3259
-mergeron/core/empirical_margin_distribution.py,sha256=ZidHSloXyGiloO4pgdiQpSaruxXPqVlqfwGgKfLVA2M,11524
-mergeron/core/ftc_merger_investigations_data.py,sha256=k4TDkP1rDBmN4uKOYF0SUvSRkYmyVhbsBvLUKDYJqOo,28537
-mergeron/core/guidelines_boundaries.py,sha256=Ct6JiuFjSVuCz-m-yeUc50xTC7F4tLgsyqXitb_nObI,15551
-mergeron/core/guidelines_boundary_functions.py,sha256=ycz0W5tV9oJ9vVH83IVaprOW4RmG68q8t1QROkQcwxU,29048
-mergeron/core/guidelines_boundary_functions_extra.py,sha256=bFRpPGKPHhuhXI67GlEOKtQrNo7WVTK7yMd9NlHCc-M,22095
-mergeron/core/pseudorandom_numbers.py,sha256=-mPveXjJJ446NrBMAmWIa2jI6j0Px0xcCJTGEEsn3bo,10149
-mergeron/data/__init__.py,sha256=CbqheFSkXEe7NOfuAV-NLaaEiNzl9pVCndGjtUUOj9g,1846
-mergeron/data/damodaran_margin_data_serialized.zip,sha256=Wc1v9buSrYTWWAravG8W9nPbgsU07zMtSAR2RvMQU5s,623482
-mergeron/data/ftc_merger_investigations_data.zip,sha256=tiB2TLFyS9LMSFIv8DBA_oEEx12DU4MyjHni4NlsRMU,24002
-mergeron/gen/__init__.py,sha256=vr4B3AynBeohLPYeb6kD_iPdEOtta-dUfA7_Bi-l-jI,23649
-mergeron/gen/data_generation.py,sha256=M7RBJO8distfdFPFQcQM4Mpfi2Etxy9HEw5EoyjWDow,17347
-mergeron/gen/data_generation_functions.py,sha256=f6aLBg6JNqOoBq57k3ovevgvtaLfIAfT-ATzZl11CEA,26076
-mergeron/gen/enforcement_stats.py,sha256=etTax-sBSn8DveF-IxuBJDdX0XSBD6oFU9vaZe6cYks,14387
-mergeron/gen/upp_tests.py,sha256=gRJISQ2jGmIDmFOvaTIkvYooI4mK-QbgkfgL46RrRio,7445
-mergeron/py.typed,sha256=frcCV1k9oG9oKj3dpUqdJg1PxRT2RSN_XKdLCPjaYaY,2
-mergeron-2025.739341.10.dist-info/METADATA,sha256=4Bxc0ThL53E7MhJtYfWnIj27yMN_YWOmhFo5Te5Z0Xs,3931
-mergeron-2025.739341.10.dist-info/WHEEL,sha256=fGIA9gx4Qxk2KDKeNJCbOEwSrmLtjWCwzBz351GyrPQ,88
-mergeron-2025.739341.10.dist-info/RECORD,,