taxcalc 4.4.0__py3-none-any.whl → 4.4.1__py3-none-any.whl

taxcalc/tests/test_utils.py

@@ -4,8 +4,6 @@ Tests of Tax-Calculator utility functions.
 # CODING-STYLE CHECKS:
 # pycodestyle test_utils.py
 # pylint --disable=locally-disabled test_utils.py
-#
-# pylint: disable=missing-docstring
 
 import os
 import math
@@ -13,25 +11,29 @@ import random
 import numpy as np
 import pandas as pd
 import pytest
-# pylint: disable=import-error
-from taxcalc import Policy, Records, Calculator
-from taxcalc.utils import (DIST_VARIABLES,
-                           DIST_TABLE_COLUMNS, DIST_TABLE_LABELS,
-                           DIFF_VARIABLES,
-                           DIFF_TABLE_COLUMNS, DIFF_TABLE_LABELS,
-                           SOI_AGI_BINS,
-                           create_difference_table,
-                           weighted_sum, weighted_mean,
-                           wage_weighted, agi_weighted,
-                           expanded_income_weighted,
-                           add_income_table_row_variable,
-                           add_quantile_table_row_variable,
-                           mtr_graph_data, atr_graph_data,
-                           xtr_graph_plot, write_graph_file,
-                           read_egg_csv, read_egg_json, delete_file,
-                           bootstrap_se_ci,
-                           certainty_equivalent,
-                           ce_aftertax_expanded_income)
+from taxcalc.policy import Policy
+from taxcalc.records import Records
+from taxcalc.calculator import Calculator
+from taxcalc.utils import (
+    DIST_VARIABLES,
+    DIST_TABLE_COLUMNS, DIST_TABLE_LABELS,
+    DIFF_VARIABLES,
+    DIFF_TABLE_COLUMNS, DIFF_TABLE_LABELS,
+    SOI_AGI_BINS,
+    create_difference_table,
+    weighted_sum, weighted_mean,
+    wage_weighted, agi_weighted,
+    expanded_income_weighted,
+    add_income_table_row_variable,
+    add_quantile_table_row_variable,
+    mtr_graph_data, atr_graph_data,
+    xtr_graph_plot, write_graph_file,
+    read_egg_csv, read_egg_json, delete_file,
+    bootstrap_se_ci,
+    certainty_equivalent,
+    ce_aftertax_expanded_income,
+    json_to_dict
+)
 
 
 DATA = [[1.0, 2, 'a'],
@@ -56,6 +58,7 @@ DATA_FLOAT = [[1.0, 2, 'a'],
 
 
 def test_validity_of_name_lists():
+    """Test docstring"""
     assert len(DIST_TABLE_COLUMNS) == len(DIST_TABLE_LABELS)
     records_varinfo = Records(data=None)
     assert set(DIST_VARIABLES).issubset(records_varinfo.CALCULATED_VARS |
@@ -68,7 +71,9 @@ def test_validity_of_name_lists():
 
 
 def test_create_tables(cps_subsample):
+    """Test docstring"""
     # pylint: disable=too-many-statements,too-many-branches
+
     # create a current-law Policy object and Calculator object calc1
     rec = Records.cps_constructor(data=cps_subsample)
     pol = Policy()
@@ -108,7 +113,7 @@ def test_create_tables(cps_subsample):
         test_failure = True
         print('diff xbin', tabcol)
         for val in diff[tabcol].values:
-            print('{:.1f},'.format(val))
+            print(f'{val:.1f},')
 
     diff = create_difference_table(calc1.dataframe(DIFF_VARIABLES),
                                    calc2.dataframe(DIFF_VARIABLES),
@@ -136,7 +141,7 @@ def test_create_tables(cps_subsample):
         test_failure = True
         print('diff xdec', tabcol)
         for val in diff[tabcol].values:
-            print('{:.1f},'.format(val))
+            print(f'{val:.1f},')
 
     tabcol = 'share_of_change'
     expected = [0.0,
@@ -154,13 +159,13 @@ def test_create_tables(cps_subsample):
                 100.0,
                 13.2,
                 8.3,
-                1.4,]
+                1.4]
     if not np.allclose(diff[tabcol].values.astype('float'), expected,
                        atol=0.1, rtol=0.0):
         test_failure = True
         print('diff xdec', tabcol)
         for val in diff[tabcol].values:
-            print('{:.1f},'.format(val))
+            print(f'{val:.1f},')
 
     tabcol = 'pc_aftertaxinc'
     expected = [np.nan,
@@ -184,7 +189,7 @@ def test_create_tables(cps_subsample):
         test_failure = True
         print('diff xdec', tabcol)
         for val in diff[tabcol].values:
-            print('{:.1f},'.format(val))
+            print(f'{val:.1f},')
 
     # test creating various distribution tables
 
@@ -212,7 +217,7 @@ def test_create_tables(cps_subsample):
         test_failure = True
         print('dist xdec', tabcol)
         for val in dist[tabcol].values:
-            print('{:.1f},'.format(val))
+            print(f'{val:.1f},')
 
     tabcol = 'count_ItemDed'
     expected = [0.0,
@@ -236,7 +241,7 @@ def test_create_tables(cps_subsample):
         test_failure = True
         print('dist xdec', tabcol)
         for val in dist[tabcol].values:
-            print('{:.1f},'.format(val))
+            print(f'{val:.1f},')
 
     tabcol = 'expanded_income'
     expected = [0.0,
@@ -260,7 +265,7 @@ def test_create_tables(cps_subsample):
         test_failure = True
         print('dist xdec', tabcol)
         for val in dist[tabcol].values:
-            print('{:.1f},'.format(val))
+            print(f'{val:.1f},')
 
     tabcol = 'aftertax_income'
     expected = [0.0,
@@ -284,7 +289,7 @@ def test_create_tables(cps_subsample):
         test_failure = True
         print('dist xdec', tabcol)
         for val in dist[tabcol].values:
-            print('{:.1f},'.format(val))
+            print(f'{val:.1f},')
 
     dist, _ = calc2.distribution_tables(None, 'standard_income_bins')
     assert isinstance(dist, pd.DataFrame)
@@ -308,7 +313,7 @@ def test_create_tables(cps_subsample):
         test_failure = True
         print('dist xbin', tabcol)
         for val in dist[tabcol].values:
-            print('{:.1f},'.format(val))
+            print(f'{val:.1f},')
 
     tabcol = 'count_ItemDed'
     expected = [0.0,
@@ -330,10 +335,10 @@ def test_create_tables(cps_subsample):
         test_failure = True
         print('dist xbin', tabcol)
         for val in dist[tabcol].values:
-            print('{:.1f},'.format(val))
+            print(f'{val:.1f},')
 
     if test_failure:
-        assert 1 == 2
+        assert False, 'ERROR: test failure'
 
 
 def test_diff_count_precision():
@@ -409,11 +414,11 @@ def test_diff_count_precision():
     cilo = bsd['cilo'] * 1e-3
     cihi = bsd['cihi'] * 1e-3
     if dump:
-        res = '{}EST={:.1f} B={} alpha={:.3f} se={:.2f} ci=[ {:.2f} , {:.2f} ]'
-        print(
-            res.format('STANDARD-BIN10: ',
-                       data_estimate, bs_samples, alpha, stderr, cilo, cihi)
+        res = (
+            f'EST={data_estimate:.1f} B={bs_samples} alpha={alpha:.3f} '
+            f'se={stderr:.2f} ci=[ {cilo:.2f} , {cihi:.2f} ]'
         )
+        print(f'STANDARD-BIN10: {res}')
     assert abs((stderr / 1.90) - 1) < 0.0008
     # NOTE: a se of 1.90 thousand implies that when comparing the difference
     #       in the weighted number of filing units in STANDARD bin 10 with a
@@ -442,11 +447,11 @@ def test_diff_count_precision():
     cilo = bsd['cilo'] * 1e-3
     cihi = bsd['cihi'] * 1e-3
     if dump:
-        res = '{}EST={:.1f} B={} alpha={:.3f} se={:.2f} ci=[ {:.2f} , {:.2f} ]'
-        print(
-            res.format('STANDARD-BIN11: ',
-                       data_estimate, bs_samples, alpha, stderr, cilo, cihi)
+        res = (
+            f'EST={data_estimate:.1f} B={bs_samples} alpha={alpha:.3f} '
+            f'se={stderr:.2f} ci=[ {cilo:.2f} , {cihi:.2f} ]'
         )
+        print(f'STANDARD-BIN11: {res}')
     assert abs((stderr / 0.85) - 1) < 0.0040
     # NOTE: a se of 0.85 thousand implies that when comparing the difference
     #       in the weighted number of filing units in STANDARD bin 11 with a
@@ -468,6 +473,7 @@ def test_diff_count_precision():
 
 
 def test_weighted_mean():
+    """Test docstring"""
     dfx = pd.DataFrame(data=DATA, columns=['tax_diff', 's006', 'label'])
     grouped = dfx.groupby('label')
     diffs = grouped.apply(weighted_mean, 'tax_diff', include_groups=False)
@@ -477,18 +483,21 @@ def test_weighted_mean():
 
 
 def test_wage_weighted():
+    """Test docstring"""
     dfx = pd.DataFrame(data=WEIGHT_DATA, columns=['var', 's006', 'e00200'])
     wvar = wage_weighted(dfx, 'var')
     assert round(wvar, 4) == 2.5714
 
 
 def test_agi_weighted():
+    """Test docstring"""
     dfx = pd.DataFrame(data=WEIGHT_DATA, columns=['var', 's006', 'c00100'])
     wvar = agi_weighted(dfx, 'var')
     assert round(wvar, 4) == 2.5714
 
 
 def test_expanded_income_weighted():
+    """Test docstring"""
     dfx = pd.DataFrame(data=WEIGHT_DATA,
                        columns=['var', 's006', 'expanded_income'])
     wvar = expanded_income_weighted(dfx, 'var')
@@ -496,6 +505,7 @@ def test_expanded_income_weighted():
 
 
 def test_weighted_sum():
+    """Test docstring"""
     dfx = pd.DataFrame(data=DATA, columns=['tax_diff', 's006', 'label'])
     grouped = dfx.groupby('label')
     diffs = grouped.apply(weighted_sum, 'tax_diff', include_groups=False)
@@ -508,6 +518,7 @@ EPSILON = 1e-5
 
 
 def test_add_income_trow_var():
+    """Test docstring"""
     dta = np.arange(1, 1e6, 5000)
     vdf = pd.DataFrame(data=dta, columns=['expanded_income'])
     vdf = add_income_table_row_variable(vdf, 'expanded_income', SOI_AGI_BINS)
@@ -520,6 +531,7 @@ def test_add_income_trow_var():
 
 
 def test_add_quantile_trow_var():
+    """Test docstring"""
     dfx = pd.DataFrame(data=DATA, columns=['expanded_income', 's006', 'label'])
     dfb = add_quantile_table_row_variable(dfx, 'expanded_income',
                                           100, decile_details=False,
@@ -537,6 +549,7 @@ def test_add_quantile_trow_var():
 
 
 def test_dist_table_sum_row(cps_subsample):
+    """Test docstring"""
     rec = Records.cps_constructor(data=cps_subsample)
     calc = Calculator(policy=Policy(), records=rec)
     calc.calc_all()
@@ -566,6 +579,7 @@ def test_dist_table_sum_row(cps_subsample):
 
 
 def test_diff_table_sum_row(cps_subsample):
+    """Test docstring"""
     rec = Records.cps_constructor(data=cps_subsample)
     # create a current-law Policy object and Calculator calc1
     pol = Policy()
@@ -595,6 +609,7 @@ def test_diff_table_sum_row(cps_subsample):
 
 
 def test_mtr_graph_data(cps_subsample):
+    """Test docstring"""
     recs = Records.cps_constructor(data=cps_subsample)
     calc = Calculator(policy=Policy(), records=recs)
     year = calc.current_year
@@ -607,7 +622,7 @@ def test_mtr_graph_data(cps_subsample):
                        income_measure='expanded_income',
                        dollar_weighting=True)
     with pytest.raises(ValueError):
-        mtr_graph_data(None, year, mars=list())
+        mtr_graph_data(None, year, mars=[])
     with pytest.raises(ValueError):
         mtr_graph_data(None, year, mars='ALL', mtr_variable='e00200s')
     with pytest.raises(ValueError):
@@ -627,6 +642,7 @@ def test_mtr_graph_data(cps_subsample):
 
 
 def test_atr_graph_data(cps_subsample):
+    """Test docstring"""
     pol = Policy()
     rec = Records.cps_constructor(data=cps_subsample)
     calc = Calculator(policy=pol, records=rec)
@@ -636,7 +652,7 @@ def test_atr_graph_data(cps_subsample):
     with pytest.raises(ValueError):
         atr_graph_data(None, year, mars=0)
     with pytest.raises(ValueError):
-        atr_graph_data(None, year, mars=list())
+        atr_graph_data(None, year, mars=[])
     with pytest.raises(ValueError):
         atr_graph_data(None, year, atr_measure='badtax')
     calc.calc_all()
@@ -651,6 +667,7 @@ def test_atr_graph_data(cps_subsample):
 
 
 def test_xtr_graph_plot(cps_subsample):
+    """Test docstring"""
     recs = Records.cps_constructor(data=cps_subsample)
     calc = Calculator(policy=Policy(), records=recs)
     mtr = 0.20 * np.ones_like(cps_subsample['e00200'])
@@ -673,11 +690,14 @@ def test_xtr_graph_plot(cps_subsample):
 
 
 def temporary_filename(suffix=''):
+    """Function docstring"""
     # Return string containing the temporary filename.
-    return 'tmp{}{}'.format(random.randint(10000000, 99999999), suffix)
+    rint = random.randint(10000000, 99999999)
+    return f'tmp{rint}{suffix}'
 
 
 def test_write_graph_file(cps_subsample):
+    """Test docstring"""
     recs = Records.cps_constructor(data=cps_subsample)
     calc = Calculator(policy=Policy(), records=recs)
     mtr = 0.20 * np.ones_like(cps_subsample['e00200'])
@@ -699,7 +719,7 @@ def test_write_graph_file(cps_subsample):
                 os.remove(htmlfname)
             except OSError:
                 pass  # sometimes we can't remove a generated temporary file
-        assert 'write_graph_file()_ok' == 'no'
+        assert False, 'ERROR: write_graph_file() failed'
     # if try was successful, try to remove the file
     if os.path.isfile(htmlfname):
         try:
@@ -709,6 +729,7 @@ def test_write_graph_file(cps_subsample):
 
 
 def test_ce_aftertax_income(cps_subsample):
+    """Test docstring"""
     # test certainty_equivalent() function with con>cmin
     con = 5000
     cmin = 1000
@@ -752,19 +773,22 @@ def test_ce_aftertax_income(cps_subsample):
 
 
 def test_read_egg_csv():
+    """Test docstring"""
     with pytest.raises(ValueError):
         read_egg_csv('bad_filename')
 
 
 def test_read_egg_json():
+    """Test docstring"""
     with pytest.raises(ValueError):
         read_egg_json('bad_filename')
 
 
 def test_create_delete_temp_file():
+    """Test docstring"""
     # test temporary_filename() and delete_file() functions
     fname = temporary_filename()
-    with open(fname, 'w') as tmpfile:
+    with open(fname, 'w', encoding='utf-8') as tmpfile:
         tmpfile.write('any content will do')
     assert os.path.isfile(fname) is True
     delete_file(fname)
@@ -772,6 +796,7 @@ def test_create_delete_temp_file():
 
 
 def test_bootstrap_se_ci():
+    """Test docstring"""
     # Use treated mouse data from Table 2.1 and
     # results from Table 2.2 and Table 13.1 in
     # Bradley Efron and Robert Tibshirani,
@@ -787,6 +812,13 @@ def test_bootstrap_se_ci():
 
 
 def test_table_columns_labels():
+    """Test docstring"""
     # check that length of two lists are the same
     assert len(DIST_TABLE_COLUMNS) == len(DIST_TABLE_LABELS)
     assert len(DIFF_TABLE_COLUMNS) == len(DIFF_TABLE_LABELS)
+
+
+def test_invalid_json_to_dict():
+    """Test docstring"""
+    with pytest.raises(ValueError):
+        json_to_dict('invalid_json_text')

taxcalc/utils.py

@@ -172,7 +172,8 @@ def add_quantile_table_row_variable(dframe, income_measure, num_quantiles,
     and the top decile is broken into three subgroups
     (90-95, 95-99, and top 1%).
     """
-    # pylint: disable=too-many-arguments,too-many-locals
+    # pylint: disable=too-many-arguments,too-many-positional-arguments
+    # pylint: disable=too-many-locals
     assert isinstance(dframe, pd.DataFrame)
     assert income_measure in dframe
     assert 's006' in dframe
@@ -272,7 +273,7 @@ def get_sums(dframe):
     -------
     Pandas Series object containing column sums indexed by dframe column names.
     """
-    sums = dict()
+    sums = {}
     for col in dframe.columns.values.tolist():
         if col != 'table_row':
             sums[col] = dframe[col].sum()
@@ -353,6 +354,7 @@ def create_distribution_table(vdf, groupby, income_measure,
     if pop_quantiles:
         assert groupby == 'weighted_deciles'
     # sort the data given specified groupby and income_measure
+    dframe = None
     if groupby == 'weighted_deciles':
         dframe = add_quantile_table_row_variable(vdf, income_measure, 10,
                                                  pop_quantiles=pop_quantiles,
@@ -544,6 +546,7 @@ def create_difference_table(vdf1, vdf2, groupby, tax_to_diff,
     else:
         df2['count'] = df2['s006']
     # add table_row column to df2 given specified groupby and income_measure
+    dframe = None
     if groupby == 'weighted_deciles':
         dframe = add_quantile_table_row_variable(
             df2, baseline_expanded_income, 10,
@@ -680,7 +683,7 @@ def create_diagnostic_table(dframe_list, year_list):
         agi = vdf['c00100']
         odict['AGI ($b)'] = round((agi * wghts).sum() * in_billions, 3)
         # number of itemizers
-        val = (wghts[vdf['c04470'] > 0.].sum())
+        val = wghts[vdf['c04470'] > 0.].sum()
         odict['Itemizers (#m)'] = round(val * in_millions, 2)
         # itemized deduction
         ided1 = vdf['c04470'] * wghts
@@ -761,7 +764,7 @@ def create_diagnostic_table(dframe_list, year_list):
     assert isinstance(year_list[0], int)
     assert isinstance(dframe_list[0], pd.DataFrame)
     # construct diagnostic table
-    tlist = list()
+    tlist = []
     for year, vardf in zip(year_list, dframe_list):
         odict = diagnostic_table_odict(vardf)
         ddf = pd.DataFrame(data=odict, index=[year], columns=odict.keys())
@@ -854,8 +857,8 @@ def mtr_graph_data(vdf, year,
     -------
     dictionary object suitable for passing to xtr_graph_plot utility function
     """
-    # pylint: disable=too-many-arguments,too-many-statements
-    # pylint: disable=too-many-locals,too-many-branches
+    # pylint: disable=too-many-arguments,,too-many-positional-arguments
+    # pylint: disable=too-many-locals,too-many-branches,too-many-statements
     # check validity of function arguments
     # . . check income_measure value
     weighting_function = weighted_mean
@@ -930,26 +933,25 @@ def mtr_graph_data(vdf, year,
     lines['base'] = mtr1_series
     lines['reform'] = mtr2_series
     # construct dictionary containing merged data and auto-generated labels
-    data = dict()
+    data = {}
     data['lines'] = lines
     if dollar_weighting:
-        income_str = 'Dollar-weighted {}'.format(income_str)
-        mtr_str = 'Dollar-weighted {}'.format(mtr_str)
-    data['ylabel'] = '{} MTR'.format(mtr_str)
-    xlabel_str = 'Baseline {} Percentile'.format(income_str)
+        income_str = f'Dollar-weighted {income_str}'
+        mtr_str = f'Dollar-weighted {mtr_str}'
+    data['ylabel'] = f'{mtr_str} MTR'
+    xlabel_str = f'Baseline {income_str} Percentile'
     if mars != 'ALL':
-        xlabel_str = '{} for MARS={}'.format(xlabel_str, mars)
+        xlabel_str = f'{xlabel_str} for MARS={mars}'
     data['xlabel'] = xlabel_str
-    var_str = '{}'.format(mtr_variable)
+    var_str = f'{mtr_variable}'
     if mtr_variable == 'e00200p' and alt_e00200p_text != '':
-        var_str = '{}'.format(alt_e00200p_text)
+        var_str = f'{alt_e00200p_text}'
     if mtr_variable == 'e00200p' and mtr_wrt_full_compen:
-        var_str = '{} wrt full compensation'.format(var_str)
-    title_str = 'Mean Marginal Tax Rate for {} by Income Percentile'
-    title_str = title_str.format(var_str)
+        var_str = f'{var_str} wrt full compensation'
+    title_str = f'Mean Marginal Tax Rate for {var_str} by Income Percentile'
     if mars != 'ALL':
-        title_str = '{} for MARS={}'.format(title_str, mars)
-    title_str = '{} for {}'.format(title_str, year)
+        title_str = f'{title_str} for MARS={mars}'
+    title_str = f'{title_str} for {year}'
     data['title'] = title_str
     return data
 
@@ -1067,17 +1069,17 @@ def atr_graph_data(vdf, year,
     # include only percentiles with average income no less than min_avginc
     lines = lines[included]
     # construct dictionary containing plot lines and auto-generated labels
-    data = dict()
+    data = {}
     data['lines'] = lines
-    data['ylabel'] = '{} Average Tax Rate'.format(atr_str)
+    data['ylabel'] = f'{atr_str} Average Tax Rate'
     xlabel_str = 'Baseline Expanded-Income Percentile'
     if mars != 'ALL':
-        xlabel_str = '{} for MARS={}'.format(xlabel_str, mars)
+        xlabel_str = f'{xlabel_str} for MARS={mars}'
     data['xlabel'] = xlabel_str
     title_str = 'Average Tax Rate by Income Percentile'
     if mars != 'ALL':
-        title_str = '{} for MARS={}'.format(title_str, mars)
-    title_str = '{} for {}'.format(title_str, year)
+        title_str = f'{title_str} for MARS={mars}'
+    title_str = f'{title_str} for {year}'
     data['title'] = title_str
     return data
 
@@ -1148,7 +1150,7 @@ def xtr_graph_plot(data,
     raster graphics file.  There is no option to make the bokeh.plotting
     figure generate a vector graphics file such as an EPS file.
     """
-    # pylint: disable=too-many-arguments
+    # pylint: disable=too-many-arguments,too-many-positional-arguments
     if title == '':
         title = data['title']
     fig = bp.figure(width=width, height=height, title=title)
@@ -1238,13 +1240,13 @@ def pch_graph_data(vdf, year, pop_quantiles=False):
     # include only percentiles with average income no less than min_avginc
     line = line[included]
     # construct dictionary containing plot line and auto-generated labels
-    data = dict()
+    data = {}
     data['line'] = line
     data['ylabel'] = 'Change in After-Tax Expanded Income'
     data['xlabel'] = 'Baseline Expanded-Income Percentile'
     title_str = ('Percentage Change in After-Tax Expanded Income '
                  'by Income Percentile')
-    title_str = '{} for {}'.format(title_str, year)
+    title_str = f'{title_str} for {year}'
     data['title'] = title_str
     return data
 
@@ -1286,7 +1288,7 @@ def pch_graph_plot(data,
     -----
     See Notes to xtr_graph_plot function.
     """
-    # pylint: disable=too-many-arguments
+    # pylint: disable=too-many-arguments,too-many-positional-arguments
     if title == '':
         title = data['title']
     fig = bp.figure(width=width, height=height, title=title)
@@ -1309,8 +1311,13 @@ def pch_graph_plot(data,
     fig.yaxis.axis_label_text_font_size = '12pt'
     fig.yaxis.axis_label_text_font_style = 'normal'
     fig.yaxis[0].formatter = PrintfTickFormatter(format='%.1f')
-    # return fig  # bokeh 3.4.1 cannot save this figure for some unknown reason
-    return None
+    # bokeh cannot save this fig saying:
+    #   bokeh.core.serialization.SerializationError:
+    #   can't serialize <class 'range'>
+    # so the "return fig" statement is replaced by Python's implicit
+    # "return None" until the above logic can be made compatible with
+    # modern bokeh packages
+    # return fig
 
 
 def write_graph_file(figure, filename, title):
@@ -1471,7 +1478,7 @@ def ce_aftertax_expanded_income(df1, df2,
         cmin = 1000
     # compute aggregate combined tax revenue and aggregate after-tax income
     billion = 1.0e-9
-    cedict = dict()
+    cedict = {}
     cedict['tax1'] = weighted_sum(df1, 'combined') * billion
     cedict['tax2'] = weighted_sum(df2, 'combined') * billion
     if require_no_agg_tax_change:
@@ -1495,8 +1502,8 @@ def ce_aftertax_expanded_income(df1, df2,
     ati2 = df2['expanded_income'] - df2['combined']
     # calculate certainty-equivaluent after-tax income in df1 and df2
     cedict['crra'] = crras
-    ce1 = list()
-    ce2 = list()
+    ce1 = []
+    ce2 = []
     for crra in crras:
         eu1 = expected_utility(ati1, prob, crra, cmin)
         ce1.append(certainty_equivalent(eu1, crra, cmin))
@@ -1517,8 +1524,8 @@ def read_egg_csv(fname, index_col=None):
         path_in_egg = implibres.files('taxcalc').joinpath(fname)
         with implibres.as_file(path_in_egg) as rname:
             vdf = pd.read_csv(rname, index_col=index_col)
-    except Exception:
-        raise ValueError(f'could not read {fname} data from egg')
+    except Exception as exc:
+        raise ValueError(f'could not read {fname} data from egg') from exc
     # cannot call read_egg_ function in unit tests
     return vdf  # pragma: no cover
 
@@ -1531,10 +1538,10 @@ def read_egg_json(fname):
     try:
         path_in_egg = implibres.files('taxcalc').joinpath(fname)
         with implibres.as_file(path_in_egg) as rname:
-            vdf = json.loads(rname)
-    except Exception:
-        raise ValueError(f'could not read {fname} data from egg')
-    # cannot call read_egg_ function in unit tests
+            pdict = json.loads(rname)
+    except Exception as exc:
+        raise ValueError(f'could not read {fname} data from package') from exc
+    # cannot call read_egg_ function in pytest unit tests
     return pdict  # pragma: no cover
 
 
@@ -1557,7 +1564,7 @@ def bootstrap_se_ci(data, seed, num_samples, statistic, alpha):
     assert isinstance(num_samples, int)
     assert callable(statistic)  # function that computes statistic from data
     assert isinstance(alpha, float)
-    bsest = dict()
+    bsest = {}
     bsest['seed'] = seed
     np.random.seed(seed)
     dlen = len(data)
@@ -1607,7 +1614,7 @@ def json_to_dict(json_text):
         linenum = 0
         for line in text_lines:
             linenum += 1
-            msg += '{:04d}{}'.format(linenum, line) + '\n'
+            msg += f'{linenum:04d}{line}\n'
         msg += bline + '\n'
-        raise ValueError(msg)
+        raise ValueError(msg) from valerr
     return ordered_dict

taxcalc/validation/taxsim35/taxsim_emulation.json

@@ -36,14 +36,10 @@
 //      income of the receiving spouse, if made under a
 //      divorce or separation agreement executed after
 //      Dec. 31, 2018.
-
-// (4) PT_qbid_limit_switch = false implies TAXSIM35-like QBI deduction logic.
 {
     "AMT_child_em_c_age": {"2013": 24},
 
     "EITC_excess_InvestIncome_rt": {"2013": 1.0},
 
-    "ALD_AlimonyReceived_hc": {"2019": 1.0},
-
-    "PT_qbid_limit_switch": {"2018": false}
+    "ALD_AlimonyReceived_hc": {"2019": 1.0}
 }