mergeron 2024.738940.0__py3-none-any.whl → 2024.738949.0__py3-none-any.whl

mergeron/examples/investigations_stats_obs_tables.py

@@ -14,6 +14,7 @@ from numpy import einsum, row_stack, unique
 import mergeron.core.ftc_merger_investigations_data as fid
 import mergeron.gen.investigations_stats as isl
 from mergeron import DATA_DIR
+from mergeron.gen import INVResolution
 
 if not sys.warnoptions:
     warnings.simplefilter("ignore")
@@ -144,7 +145,7 @@ def invres_stats_odds_ratio_byhhianddelta(
             _invres_rate_table_content.invdata_byhhianddelta = _odds_ratio_data_str
 
             _output_dottex_path = DATA_DIR / INVDATA_DOTTEX_FORMAT_STR.format(
-                f"{_stats_group}_{_data_period_1}_{_merger_class.replace(' ', '')}"
+                f"{_stats_group}_{_data_period_1}_{_merger_class.replace(" ", "")}"
             )
             with _output_dottex_path.open(
                 "w", encoding="utf8"
@@ -168,13 +169,13 @@ def invres_stats_obs_setup(
     _data_array_dict: Mapping,
     _data_periods: tuple[str, str],
     _merger_classes: Sequence[isl.INDGRPConstants | isl.EVIDENConstants],
-    _test_regime: isl.PolicySelector = isl.PolicySelector.CLRN,
+    _invres_spec: INVResolution = INVResolution.CLRN,
     /,
 ) -> tuple[str, ...]:
     _notes_str_base = " ".join((
         "NOTES:",
         isl.LTX_ARRAY_LINEEND,
-        Rf"\(\cdot\) Data for period, {_data_periods[1].replace('-', '--')}",
+        Rf"\(\cdot\) Data for period, {_data_periods[1].replace("-", "--")}",
         "calculated by subtracting reported figures for 1996--{}".format(
             int(_data_periods[1].split("-")[0]) - 1
         ),
@@ -182,7 +183,7 @@ def invres_stats_obs_setup(
     ))
     _stats_group_dict = {
         isl.StatsGrpSelector.FC: {
-            "desc": f"{_test_regime.capitalize()} rates by Firm Count",
+            "desc": f"{_invres_spec.capitalize()} rates by Firm Count",
             "title_str": "By Number of Significant Competitors",
             "hval": "Firm Count",
             "hcol_width": 54,
@@ -195,7 +196,7 @@ def invres_stats_obs_setup(
             )),
         },
         isl.StatsGrpSelector.DL: {
-            "desc": Rf"{_test_regime.capitalize()} rates by range of \(\Delta HHI\)",
+            "desc": Rf"{_invres_spec.capitalize()} rates by range of \(\Delta HHI\)",
             "title_str": R"By Change in Concentration (\Deltah{})",
             "hval": R"$\Delta HHI$",
             "hval_plus": R"{ $[\Delta_L, \Delta_H)$ pts.}",
@@ -217,7 +218,7 @@ def invres_stats_obs_setup(
             )),
         },
         isl.StatsGrpSelector.ZN: {
-            "desc": f"{_test_regime.capitalize()} rates by Approximate Presumption Zone",
+            "desc": f"{_invres_spec.capitalize()} rates by Approximate Presumption Zone",
             "title_str": R"By Approximate \textit{2010 Guidelines} Concentration-Based Standards",
             "hval": "Approximate Standard",
             "hcol_width": 190,
@@ -238,7 +239,7 @@ def invres_stats_obs_setup(
             _merger_classes,
             _stats_group_key,
             _stats_group_dict[_stats_group_key],
-            _test_regime,
+            _invres_spec,
         )
         _output_dottex_pathlist += (_output_dottex_path,)
 
@@ -251,7 +252,7 @@ def _invres_stats_obs_render(
     _merger_classes: Sequence[isl.INDGRPConstants | isl.EVIDENConstants],
     _stats_group: isl.StatsGrpSelector,
     _stats_group_dict: Mapping,
-    _test_regime: isl.PolicySelector = isl.PolicySelector.CLRN,
+    _invres_spec: isl.INVResolution = isl.INVResolution.CLRN,
     /,
 ) -> str:
     _invres_rate_table_content = isl.StatsContainer()
@@ -262,7 +263,7 @@ def _invres_stats_obs_render(
     print(
         f'{_stats_group_dict["desc"]}:', ", ".join([f'"{g}"' for g in _merger_classes])
     )
-    _invres_rate_table_content.test_regime = _test_regime.capitalize()
+    _invres_rate_table_content.test_regime = _invres_spec.capitalize()
     _invres_rate_table_content.obs_summary_type = f"{_stats_group}"
     _invres_rate_table_content.obs_summary_type_title = _stats_group_dict.get(
         "title_str"
@@ -290,7 +291,7 @@ def _invres_stats_obs_render(
     _invres_rate_table_content.obs_merger_class_0 = f"{_merger_classes[0]}"
     _invres_rate_table_content.obs_merger_class_1 = f"{_merger_classes[1]}"
     _invres_rate_table_content.obs_periods_str = (
-        Rf"{' & '.join(_data_periods)} \\".replace("-", "--")
+        Rf"{" & ".join(_data_periods)} \\".replace("-", "--")
     )
 
     _invres_rate_table_content.invdata_notewidth = _stats_group_dict["notewidth"]
@@ -349,7 +350,7 @@ def _invres_stats_obs_render(
                     _table_ind_group,
                     _table_evid_cond,
                     _stats_group,
-                    _test_regime,
+                    _invres_spec,
                     return_type_sel=isl.StatsReturnSelector.CNT,
                     print_to_screen=False,
                 )[1][-1][0]
@@ -361,7 +362,7 @@ def _invres_stats_obs_render(
                 _table_ind_group,
                 _table_evid_cond,
                 _stats_group,
-                _test_regime,
+                _invres_spec,
                 return_type_sel=isl.StatsReturnSelector.RPT,
                 sort_order=_sort_order,
                 print_to_screen=False,
@@ -384,7 +385,7 @@ def _invres_stats_obs_render(
     ])
 
     _invdata_datstr = "".join([
-        f"{' & '.join(_invdata_dat_list[g])} {isl.LTX_ARRAY_LINEEND}"
+        f"{" & ".join(_invdata_dat_list[g])} {isl.LTX_ARRAY_LINEEND}"
         for g in range(len(_invdata_dat_list))
     ])
 
@@ -459,7 +460,7 @@ if __name__ == "__main__":
         isl.EVIDENConstants.ED,
     )  # clstl.INDGRPConstants.IID)
     data_periods = ("1996-2003", "2004-2011")
-    test_regime = isl.PolicySelector.ENFT
+    test_regime = isl.INVResolution.ENFT
 
     # Now generate the various tables summarizing merger investigations data
     invres_stats_byhhianddelta_pathlist = invres_stats_odds_ratio_byhhianddelta(

mergeron/examples/investigations_stats_sim_tables.py

@@ -8,25 +8,32 @@ Format output as LaTeX tables (using TikZ).
 import sys
 import warnings
 from collections.abc import Mapping, Sequence
+from dataclasses import fields
 from datetime import datetime, timedelta
 from io import TextIOWrapper
-from pathlib import Path
 from typing import Any
 
 import numpy as np
-import re2 as re  # type: ignore
-import tables as ptb  # type: ignore
 from attrs import evolve
 
 import mergeron.core.ftc_merger_investigations_data as fid
-import mergeron.core.guidelines_standards as gsl
+import mergeron.core.guidelines_boundaries as gbl
 import mergeron.gen.data_generation as dgl
-import mergeron.gen.guidelines_tests as gtl
 import mergeron.gen.investigations_stats as isl
+import mergeron.gen.upp_tests as utl
 from mergeron import DATA_DIR
-from mergeron.core.guidelines_standards import GuidelinesStandards
 from mergeron.core.proportions_tests import propn_ci
-from mergeron.gen import PCMConstants, PCMSpec, RECConstants, ShareSpec, SHRConstants
+from mergeron.gen import (
+    INVResolution,
+    MarketSampleSpec,
+    PCMConstants,
+    PCMSpec,
+    RECConstants,
+    ShareSpec,
+    SHRConstants,
+    UPPAggrSelector,
+    UPPTestRegime,
+)
 
 if not sys.warnoptions:
     warnings.simplefilter("ignore")  # , category="RuntimeWarning")
@@ -42,9 +49,9 @@ def invres_stats_sim_setup(
     _invdata: fid.INVData,
     _data_period: str,
     _merger_class: isl.INDGRPConstants | isl.EVIDENConstants,
-    _invres_parm_vec: gsl.GuidelinesSTD,
-    _sample_spec: dgl.MarketSampleSpec,
-    _invres_stats_kwargs: Mapping[str, Any] | None = None,
+    _invres_parm_vec: gbl.HMGThresholds,
+    _sample_spec: MarketSampleSpec,
+    _invres_stats_kwargs: utl.IVNRESCntsArgs | None = None,
     /,
 ) -> str:
     _table_ind_group = (
@@ -59,10 +66,14 @@ def invres_stats_sim_setup(
     )
 
     _invres_stats_kwargs = _invres_stats_kwargs or {
-        "sim_test_regime": isl.PolicySelector.ENFT
+        "sim_test_regime": UPPTestRegime(INVResolution.ENFT, UPPAggrSelector.MAX, None)
     }
-    _sim_test_regime = _invres_stats_kwargs["sim_test_regime"]
-    _test_regime, _guppi_wgtng_policy, _divr_wgtng_policy = _sim_test_regime
+    _sim_test_regime = _invres_stats_kwargs.get("sim_test_regime")
+
+    _invres_spec, _guppi_wgtng_policy, _divr_wgtng_policy = (
+        getattr(_sim_test_regime, _f.name)
+        for _f in fields(_sim_test_regime)  # type: ignore
+    )
 
     # Get observed rates
     (
@@ -76,7 +87,7 @@ def invres_stats_sim_setup(
             _table_ind_group,
             _table_evid_cond,
             _grp,
-            _test_regime,
+            _invres_spec,
         )
         for _grp in (
             isl.StatsGrpSelector.FC,
@@ -97,7 +108,7 @@ def invres_stats_sim_setup(
 
     # Generate simulated rates
     _start_time = datetime.now()
-    _upp_tests_counts = gtl.sim_invres_cnts_ll(
+    _upp_tests_counts = utl.sim_invres_cnts_ll(
         _invres_parm_vec, _sample_spec_here, _invres_stats_kwargs
     )
     _total_duration = datetime.now() - _start_time
@@ -109,7 +120,7 @@ def invres_stats_sim_setup(
     # Prepare and write/print output tables
     _stats_group_dict = {
         isl.StatsGrpSelector.FC: {
-            "desc": f"{_test_regime.capitalize()} rates by firm count",
+            "desc": f"{_invres_spec.capitalize()} rates by firm count",
             "title_str": "By Number of Significant Competitors",
             "hval": "Firm Count",
             "hcol_width": 54,
@@ -118,7 +129,7 @@ def invres_stats_sim_setup(
             "sim_array": _upp_tests_counts.by_firm_count,
         },
         isl.StatsGrpSelector.DL: {
-            "desc": Rf"{_test_regime.capitalize()} rates by range of $\Delta HHI$",
+            "desc": Rf"{_invres_spec.capitalize()} rates by range of $\Delta HHI$",
             "title_str": R"By Change in Concentration (\Deltah{})",
             "hval": R"$\Delta HHI$",
             "hval_plus": R"{ $[\Delta_L, \Delta_H)$ }",
@@ -137,7 +148,7 @@ def invres_stats_sim_setup(
             "sim_array": _upp_tests_counts.by_delta,
         },
         isl.StatsGrpSelector.ZN: {
-            "desc": f"{_test_regime.capitalize()} rates by Approximate Presumption Zone",
+            "desc": f"{_invres_spec.capitalize()} rates by Approximate Presumption Zone",
             "title_str": "{} {}".format(
                 R"By Approximate \textit{2010 Guidelines}",
                 "Concentration-Based Standards",
@@ -151,7 +162,7 @@ def invres_stats_sim_setup(
     }
 
     _stats_table_name = dottex_format_str.format(
-        _test_regime.capitalize(),
+        _invres_spec.capitalize(),
         _merger_class.replace(" ", ""),
         _data_period.split("-")[1],
     )
@@ -177,8 +188,8 @@ def invres_stats_sim_render(
     _merger_class: isl.INDGRPConstants | isl.EVIDENConstants,
     _stats_group: isl.StatsGrpSelector,
     _stats_group_dict_sub: Mapping[str, Any],
-    _invres_parm_vec: gsl.GuidelinesSTD,
-    _sim_test_regime: gtl.UPPTestRegime,
+    _invres_parm_vec: gbl.HMGThresholds,
+    _sim_test_regime: UPPTestRegime,
     _stats_table_file: TextIOWrapper,
     /,
 ) -> None:
@@ -203,7 +214,13 @@ def invres_stats_sim_render(
         _stats_table_content.dbar,
         _stats_table_content.cmcr_bound,
         _stats_table_content.ipr_bound,
-    ) = (rf"{_s * 100:.1f}\%" for _s in _invres_parm_vec[1:])
+    ) = (
+        rf"{_s * 100:.1f}\%"
+        for _s in (
+            getattr(_invres_parm_vec, _f)
+            for _f in ("rec", "guppi", "divr", "cmcr", "ipr")
+        )
+    )
 
     # Prepare and write/print output tables
     _stats_cis_wilson_notestr = " ".join((
@@ -216,9 +233,9 @@ def invres_stats_sim_render(
         isl.LTX_ARRAY_LINEEND,
     ))
 
-    _eg_count = (_relfreq_eg := 0.01) * _sim_sample_sz
+    _eg_count = int(_relfreq_eg := 0.01) * _sim_sample_sz
     _stats_sim_ci_eg = 100 * np.array(
-        propn_ci(0.50 * _eg_count, _eg_count, method="Exact")
+        propn_ci(int(0.50 * _eg_count), _eg_count, method="Exact")
     )
     _stats_sim_notestr = " ".join((
         Rf"\(\cdot\) Simulated {_stats_table_content.test_res} rates are estimated by",
@@ -250,7 +267,7 @@ def invres_stats_sim_render(
     _stats_table_content.stats_cis_notewidth = _stats_group_dict_sub["notewidth"]
     _stats_cis_numobs_notestr = " ".join((
         R"\(\cdot\) Estimates for Proportion {} are based on".format(
-            "Enforced" if _invres_select == isl.PolicySelector.ENFT else "Cleared"
+            "Enforced" if _invres_select == INVResolution.ENFT else "Cleared"
         ),
         f"{_obs_sample_sz:,d} total observations (investigated mergers).",
     ))
@@ -361,22 +378,9 @@ if __name__ == "__main__":
     sample_sz_base = 10**7
     pcm_dist_type, pcm_dist_parms = PCMConstants.EMPR, None
 
-    save_data_to_file_flag = False
-    save_data_to_file: gtl.SaveData = False
-    if save_data_to_file_flag:
-        h5path = DATA_DIR / Path(__file__).with_suffix(".h5").name
-        blosc_filters = ptb.Filters(complevel=3, complib="blosc:lz4", fletcher32=True)
-        h5datafile = ptb.open_file(
-            str(h5path),
-            mode="w",
-            title="Datasets, Sound GUPPI Safeharbor",
-            filters=blosc_filters,
-        )
-        save_data_to_file = (True, h5datafile, "/")
-
     sim_test_regime = (
-        (isl.PolicySelector.CLRN, gtl.UPPAggrSelector.MAX, None),
-        (isl.PolicySelector.ENFT, gtl.UPPAggrSelector.OSD, None),
+        UPPTestRegime(INVResolution.CLRN, utl.UPPAggrSelector.MAX, None),
+        UPPTestRegime(INVResolution.ENFT, utl.UPPAggrSelector.OSD, None),
     )[1]
     invres_stats_kwargs = {"sim_test_regime": sim_test_regime}
 
@@ -387,16 +391,16 @@ if __name__ == "__main__":
                 continue
 
             print(
-                f"{sim_test_regime[0].capitalize()} rates and c.i.s",
+                f"{sim_test_regime.resolution.capitalize()} rates and c.i.s",
                 f"for the class of mergers, '{merger_class}',",
                 f"for study period, {study_period}:",
             )
             stats_table_content.obs_period = study_period.split("-")
 
             invres_parm_vec = (
-                GuidelinesStandards(2010).presumption
+                gbl.GuidelinesThresholds(2010).presumption
                 if study_period.split("-")[1] == data_periods[1].split("-")[1]
-                else GuidelinesStandards(1992).presumption
+                else gbl.GuidelinesThresholds(1992).presumption
             )
 
             mkt_sample_spec = dgl.MarketSampleSpec(
@@ -406,26 +410,17 @@ if __name__ == "__main__":
                 hsr_filing_test_type=dgl.SSZConstants.HSR_NTH,
             )
 
-            # A file to write tables to, and a hierarchy under which to store the data
-            if save_data_to_file:
-                h5hier_pat = re.compile(r"\W")
-                h5hier = f"/{h5hier_pat.sub("_", f"{merger_class} {study_period}")}"
-                save_data_to_file = (True, save_data_to_file[1], h5hier)
-
             table_dottex_name = invres_stats_sim_setup(
                 invdata_array_dict,
                 study_period,
                 merger_class,
                 invres_parm_vec,
                 mkt_sample_spec,
-                invres_stats_kwargs,
+                invres_stats_kwargs,  # type: ignore
             )
             table_dottex_namelist += (table_dottex_name,)
 
     isl.render_table_pdf(
         table_dottex_namelist,
-        dottex_format_str.format(f"{sim_test_regime[0]}".capitalize(), "All", "All"),
+        dottex_format_str.format(sim_test_regime.resolution.capitalize(), "All", "All"),
     )
-
-    if save_data_to_file:
-        save_data_to_file[1].close()

mergeron/examples/plotSafeHarbs_symbolically.py

@@ -1,7 +1,7 @@
 """
 
 Solve for, and plot, weighted-average GUPPI boundaries using sympy,
-as a check against the numerical solutions in mergeron.core.guidelines_standards
+as a check against the numerical solutions in mergeron.core.guidelines_boundaries
 
 """
 

mergeron/examples/sound_guppi_safeharbor.py

@@ -1,43 +1,39 @@
-import re
 from datetime import datetime, timedelta
 from itertools import product as iterprod
 from pathlib import Path
 from typing import Literal
 
 import numpy as np
-import tables as ptb  # type: ignore
 
-import mergeron.core.guidelines_standards as gsl
+import mergeron.core.guidelines_boundaries as gbl
 import mergeron.gen.data_generation as dgl
-import mergeron.gen.guidelines_tests as gtl
 import mergeron.gen.investigations_stats as isl
+import mergeron.gen.upp_tests as utl
 from mergeron import DATA_DIR
+from mergeron.core.pseudorandom_numbers import DIST_PARMS_DEFAULT
 from mergeron.gen import (
-    EMPTY_ARRAY_DEFAULT,
-    FCOUNT_WTS_DEFAULT,
+    INVResolution,
     MarketSampleSpec,
     PCMConstants,
     PCMSpec,
     ShareSpec,
     SHRConstants,
-)
-
-tests_of_interest: tuple[gtl.UPPTestRegime, ...] = (
-    gtl.UPPTestRegime(
-        isl.PolicySelector.CLRN, gtl.UPPAggrSelector.MAX, gtl.UPPAggrSelector.MAX
-    ),
-    gtl.UPPTestRegime(
-        isl.PolicySelector.ENFT, gtl.UPPAggrSelector.MIN, gtl.UPPAggrSelector.MIN
-    ),
+    UPPAggrSelector,
+    UPPTestRegime,
 )
 
 PROG_PATH = Path(__file__)
 
+tests_of_interest: tuple[UPPTestRegime, ...] = (
+    UPPTestRegime(INVResolution.CLRN, UPPAggrSelector.MAX, UPPAggrSelector.MAX),
+    UPPTestRegime(INVResolution.ENFT, UPPAggrSelector.MIN, UPPAggrSelector.MIN),
+)
+
 
 def analyze_invres_data(
     _sample_size: int = 10**6,
-    _hmg_std_pub_year: Literal[1992, 2010, 2023] = 1992,
-    _test_sel: gtl.UPPTestRegime = tests_of_interest[1],
+    _hmg_pub_year: Literal[1992, 2010, 2023] = 1992,
+    _test_regime: UPPTestRegime = tests_of_interest[1],
     /,
     *,
     save_data_to_file_flag: bool = False,
@@ -51,39 +47,35 @@ def analyze_invres_data(
     _sample_size
         Number of draws (mergers) to analyze
 
-    _hmg_std_pub_year
+    _hmg_pub_year
         Guidelines version for ∆HHI standard
 
-    _test_sel
+    _test_regime
         Specifies analysis of enforcement rates or, alternatively, clearance rates
 
     save_data_to_file_flag
         If True, simulated data are save to file (hdf5 format)
 
     """
-    _invres_parm_vec = gsl.GuidelinesStandards(_hmg_std_pub_year).presumption
+    _invres_parm_vec = gbl.GuidelinesThresholds(_hmg_pub_year).presumption
 
-    _save_data_to_file: gtl.SaveData = False
+    _save_data_to_file: utl.SaveData = False
     if save_data_to_file_flag:
-        _h5_hier_pat = re.compile(r"\W")
-        _blosc_filters = ptb.Filters(
-            complevel=3, complib="blosc:lz4hc", fletcher32=True
-        )
-        _h5_datafile = ptb.open_file(
-            DATA_DIR / PROG_PATH.with_suffix(".h5").name,
-            mode="w",
-            title=f"GUPPI Safeharbor {_test_sel.resolution.capitalize()} Rate Module",
-            filters=_blosc_filters,
-        )
-        _h5_hier = f"/{_h5_hier_pat.sub("_", f"Standards from {_hmg_std_pub_year} Guidelines")}"
+        _h5_path = DATA_DIR / PROG_PATH.with_suffix(".h5").name
+        (_, _h5_file, _h5_group), _h5_subgroup_name = utl.initialize_hd5(
+            _h5_path, _hmg_pub_year, _test_regime
+        )  # type: ignore
 
-        _save_data_to_file = (True, _h5_datafile, _h5_hier)
+        _h5_group = _h5_file.create_group(
+            _h5_group, _h5_subgroup_name, f"{_invres_parm_vec}"
+        )
+        _save_data_to_file = (True, _h5_file, _h5_group)
 
     # ##
     #   Print summaries of intrinsic clearance/enforcement rates by ∆HHI,
     #   with asymmetric margins
     #  ##
-    for _recapture_spec_test, _pcm_dist_test_tup, _pcm_dist_firm2_test in iterprod(
+    for _recapture_spec_test, _pcm_dist_test, _pcm_dist_firm2_test in iterprod(
         (dgl.RECConstants.INOUT, dgl.RECConstants.FIXED),
         [
             tuple(
@@ -92,7 +84,7 @@ def analyze_invres_data(
                     (
                         np.array((0, 1), dtype=np.float64),
                         np.array((10, 10), dtype=np.float64),
-                        np.empty(2),
+                        None,
                     ),
                     strict=True,
                 )
@@ -102,52 +94,64 @@ def analyze_invres_data(
         (dgl.FM2Constants.IID, dgl.FM2Constants.MNL),
     ):
         if _recapture_spec_test == "proportional" and (
-            _pcm_dist_test_tup[0] != "Uniform" or _pcm_dist_firm2_test == "MNL-dep"
+            _pcm_dist_test[0] != "Uniform" or _pcm_dist_firm2_test == "MNL-dep"
         ):
+            continue
             # When margins are specified as symmetric, then
             # recapture_spec must be proportional and
             # margins distributions must be iid;
-            continue
 
-        _pcm_dist_type_test, _pcm_dist_parms_test = _pcm_dist_test_tup
+        _pcm_dist_type_test, _pcm_dist_parms_test = _pcm_dist_test
 
         print()
         print(
-            f"Simulated {_test_sel.resolution.capitalize()} rates by range of ∆HHI",
+            f"Simulated {_test_regime.resolution.capitalize()} rates by range of ∆HHI",
             f'recapture-rate calibrated, "{_recapture_spec_test}"',
             f'Firm 2 margins, "{_pcm_dist_firm2_test}"',
-            f"and margins distributed {_pcm_dist_type_test}{_pcm_dist_parms_test}:",
+            f"and margins distributed as, {_pcm_dist_type_test}{
+                _pcm_dist_parms_test if _pcm_dist_type_test.name == "BETA" else ""
+            }:",
             sep="; ",
         )
 
-        _ind_sample_spec = MarketSampleSpec(
+        _mkt_sample_spec = MarketSampleSpec(
             _sample_size,
             _invres_parm_vec.rec,
             share_spec=ShareSpec(
-                _recapture_spec_test,
-                SHRConstants.UNI,
-                EMPTY_ARRAY_DEFAULT,
-                FCOUNT_WTS_DEFAULT,
+                _recapture_spec_test, SHRConstants.UNI, DIST_PARMS_DEFAULT, None
             ),
             pcm_spec=PCMSpec(
                 _pcm_dist_type_test, _pcm_dist_firm2_test, _pcm_dist_parms_test
             ),
         )
 
-        _invres_cnts_kwargs = {
-            "sim_test_regime": _test_sel,
-            "save_data_to_file": _save_data_to_file,
-        }
+        if _save_data_to_file:
+            _h5_file.flush()
+
+            _h5_subgrp_name = "invres_rec{}_pcm{}_fm2res{}".format(
+                _recapture_spec_test.name,
+                _pcm_dist_type_test.name,
+                _pcm_dist_firm2_test.name,
+            )
+
+            _h5_subgroup = _h5_file.create_group(
+                _h5_group, _h5_subgrp_name, title=f"{_mkt_sample_spec}"
+            )
+            _save_data_to_file = (True, _h5_file, _h5_subgroup)
+
+        _invres_cnts_kwargs = utl.IVNRESCntsArgs(
+            sim_test_regime=_test_regime, save_data_to_file=_save_data_to_file
+        )
 
         _start_time = datetime.now()
 
-        upp_test_counts = gtl.sim_invres_cnts_ll(
-            _invres_parm_vec, _ind_sample_spec, _invres_cnts_kwargs
+        upp_test_counts = utl.sim_invres_cnts_ll(
+            _invres_parm_vec, _mkt_sample_spec, _invres_cnts_kwargs
         )
         _run_duration = datetime.now() - _start_time
         print(
             f"Simulation completed in {_run_duration / timedelta(seconds=1):.6f} secs.",
-            f"on {_ind_sample_spec.sample_size:,d} draws",
+            f"on {_mkt_sample_spec.sample_size:,d} draws",
             sep=", ",
         )
 
@@ -166,10 +170,11 @@ def analyze_invres_data(
         ])
         print(_stats_teststr_val)
         del _stats_hdr_list, _stats_dat_list, _stats_teststr_val
-        del _pcm_dist_test_tup, _pcm_dist_firm2_test, _recapture_spec_test
+        del _pcm_dist_test, _pcm_dist_firm2_test, _recapture_spec_test
         del _pcm_dist_type_test, _pcm_dist_parms_test
 
-    if save_data_to_file_flag:
+    if _save_data_to_file:
+        _h5_file.flush()
         _save_data_to_file[1].close()  # type: ignore
 
 

mergeron/examples/summarize_ftc_investigations_data.py

@@ -16,13 +16,13 @@ for data_period in invdata:
         print(leader_str, table_type, "-->")
         leader_str += "\t"
         for table_no in (isd11 := isd1[table_type]):
-            (invdata_indugrp, invdata_evid_cond, table_data_array) = isd11[table_no]
+            (invdata_ind_group, invdata_evid_cond, table_data_array) = isd11[table_no]
             print(
                 leader_str,
                 table_no,
                 " \N{EM DASH} ",
-                invdata_indugrp,
-                f", {invdata_evid_cond or 'N/A'}",
+                invdata_ind_group,
+                f", {invdata_evid_cond or "N/A"}",
                 ", ",
                 sep="",
                 end="",
@@ -39,6 +39,6 @@ data_period, data_type, table_no = ("2004-2011", "HHI and Delta", "Table 3.3")
 print(f"Investigations data, {data_period}, by {data_type}, {table_no}")
 print(
     "{}, {}\n{}".format(
-        *invdata[data_period][f"By{data_type.replace(' ', '')}"][table_no]
+        *invdata[data_period][f"By{data_type.replace(" ", "")}"][table_no]
     )
 )

mergeron/examples/visualize_empirical_margin_distribution.py

@@ -14,7 +14,7 @@ from scipy import stats  # type: ignore
 
 import mergeron.core.damodaran_margin_data as dmgn
 from mergeron import DATA_DIR
-from mergeron.core.guidelines_standards import boundary_plot
+from mergeron.core.guidelines_boundaries import boundary_plot
 
 PROG_PATH = Path(__file__)
 
@@ -97,4 +97,4 @@ if __name__ == "__main__":
     mgn_ax.set_ylabel("Relative Frequency", fontsize=10)
 
     mgn_fig.tight_layout()
-    plt.savefig(PROG_PATH.with_suffix(".pdf"))
+    plt.savefig(DATA_DIR / PROG_PATH.with_suffix(".pdf").name)