def test_correct_Records_instantiation(cit_fullsample):
rec1 = CorpRecords(data=cit_fullsample)
# TODO: Add some checks for records
assert True
rec1.set_current_year(rec1.data_year + 1)
wghts_path = os.path.join(CorpRecords.CUR_PATH,
CorpRecords.CIT_WEIGHTS_FILENAME)
wghts_df = pd.read_csv(wghts_path)
rec2 = CorpRecords(data=cit_fullsample,
gfactors=GrowFactors(),
weights=wghts_df,
start_year=CorpRecords.CITCSV_YEAR)
# TODO: Repeat checks for records
assert True
assert rec2.current_year == rec2.data_year
def test_incorrect_Records_instantiation(cit_crosssample):
with pytest.raises(ValueError):
recs = CorpRecords(data=list())
with pytest.raises(ValueError):
recs = CorpRecords(data=cit_crosssample, data_type='cross-section',
gfactors=list())
with pytest.raises(ValueError):
recs = CorpRecords(data=cit_crosssample, data_type='cross-section',
gfactors=None, weights=list())
with pytest.raises(ValueError):
recs = CorpRecords(data=cit_crosssample, data_type='cross-section',
gfactors=None, weights=None, start_year=list())
with pytest.raises(ValueError):
recs = CorpRecords(data=cit_crosssample, data_type='something wrong',
gfactors=list())
def test_correct_Calculator_instantiation(pit_fullsample, pit_subsample,
gst_sample, cit_crosssample):
syr = Policy.JSON_START_YEAR
pol = Policy()
assert pol.current_year == syr
# specify expected number of filers and aggregate PIT liability
expect_weight = 35.241e6
expect_pitax = 1812.601e9
# expect_corpweight = ???
# expect_citax = ???
# create full-sample Calculator object
rec_full = Records(data=pit_fullsample)
grec = GSTRecords(data=gst_sample)
crec = CorpRecords(data=cit_crosssample)
calc_full = Calculator(policy=pol,
records=rec_full,
gstrecords=grec,
corprecords=crec)
assert isinstance(calc_full, Calculator)
assert calc_full.current_year == syr
assert calc_full.records_current_year() == syr
calc_full.calc_all()
actual_full_weight = calc_full.total_weight()
actual_full_pitax = calc_full.weighted_total('pitax')
assert np.allclose([actual_full_weight], [expect_weight])
assert np.allclose([actual_full_pitax], [expect_pitax])
# TODO: test for corporate results
# create sub-sample Calculator object
"""
def test_increment_year(cit_crosssample, cit_panelsample):
recs = CorpRecords(data=cit_crosssample)
assert recs.current_year == recs.data_year
recs.increment_year()
assert recs.current_year == recs.data_year + 1
recs2 = CorpRecords(data=cit_panelsample, data_type='panel')
assert recs2.current_year == recs2.data_year
recs2.increment_year()
assert recs2.current_year == recs2.data_year + 1
def test_incorrect_Calculator_instantiation(pit_subsample, cit_crosssample):
pol = Policy()
rec = Records(data=pit_subsample)
crec = CorpRecords(data=cit_crosssample)
with pytest.raises(ValueError):
Calculator(policy=None, records=rec, corprecords=crec)
with pytest.raises(ValueError):
Calculator(policy=pol, records=None, corprecords=crec)
with pytest.raises(ValueError):
Policy(num_years=0)
def test_dist_table_sum_row(pit_subsample, cit_crosssample):
rec = Records(data=pit_subsample)
crec = CorpRecords(data=cit_crosssample)
calc = Calculator(policy=Policy(), records=rec, corprecords=crec)
calc.calc_all()
tb1 = create_distribution_table(calc.distribution_table_dataframe(),
'standard_income_bins', 'GTI')
tb2 = create_distribution_table(calc.distribution_table_dataframe(),
'weighted_deciles', 'GTI')
allrow1 = tb1[-1:]
allrow2 = tb2[-4:-3]
assert np.allclose(allrow1, allrow2)
def test_Calculator_results_consistency(pit_fullsample, gst_sample,
cit_crosssample):
# generate calculated-variable dataframe for full sample in second year
recs = Records(data=pit_fullsample)
grecs = GSTRecords(data=gst_sample)
crecs = CorpRecords(data=cit_crosssample)
calc = Calculator(policy=Policy(),
records=recs,
gstrecords=grecs,
corprecords=crecs)
assert isinstance(calc, Calculator)
assert calc.current_year == Policy.JSON_START_YEAR
calc.advance_to_year(Policy.JSON_START_YEAR + 1)
assert calc.current_year == Policy.JSON_START_YEAR + 1
calc.calc_all()
varlist = list(Records.CALCULATED_VARS)
vdf = calc.dataframe(varlist)
assert isinstance(vdf, pd.DataFrame)
# check consistency of calculated results individual by individual
assert np.allclose(vdf['TTI'], vdf['GTI'] - vdf['deductions'])
assert np.allclose(vdf['Aggregate_Income'],
np.maximum(0., vdf['TTI'] - vdf['TI_special_rates']))
assert np.all(vdf['Tax_ST_CG_RATE1'] >= 0.)
assert np.all(vdf['Tax_ST_CG_RATE2'] >= 0.)
assert np.all(vdf['Tax_ST_CG_APPRATE'] == 0.)
assert np.allclose(vdf['Total_Tax_STCG'],
(vdf['Tax_ST_CG_RATE1'] + vdf['Tax_ST_CG_RATE2'] +
vdf['Tax_ST_CG_APPRATE']))
assert np.all(vdf['Tax_LT_CG_RATE1'] >= 0.)
assert np.all(vdf['Tax_LT_CG_RATE2'] >= 0.)
assert np.allclose(vdf['Total_Tax_LTCG'],
vdf['Tax_LT_CG_RATE1'] + vdf['Tax_LT_CG_RATE2'])
assert np.allclose(vdf['Total_Tax_Cap_Gains'],
vdf['Total_Tax_STCG'] + vdf['Total_Tax_LTCG'])
assert np.all(vdf['tax_Aggregate_Income'] >= 0.)
assert np.all(vdf['tax_TI_special_rates'] >= 0.)
assert np.all(vdf['rebate_agri'] >= 0.)
exp = vdf['tax_Aggregate_Income'] + vdf['tax_TI_special_rates']
exp -= vdf['rebate_agri']
assert np.allclose(vdf['tax_TTI'], exp)
assert np.all(vdf['rebate'] >= 0.)
assert np.all(vdf['surcharge'] >= 0.)
assert np.all(vdf['cess'] >= 0.)
assert np.all(vdf['pitax'] >= 0.)
exp = vdf['tax_TTI'] - vdf['rebate'] + vdf['surcharge'] + vdf['cess']
assert np.allclose(vdf['pitax'], exp)
def test_calculator_mtr(pit_fullsample, gst_sample, cit_crosssample):
"""
Test Calculator mtr method.
"""
recs = Records(data=pit_fullsample)
grecs = GSTRecords(data=gst_sample)
crecs = CorpRecords(data=cit_crosssample)
calcx = Calculator(policy=Policy(),
records=recs,
gstrecords=grecs,
corprecords=crecs)
calcx.calc_all()
pitax_x = calcx.array('pitax')
GTIx = calcx.array('GTI')
calc = Calculator(policy=Policy(),
records=recs,
gstrecords=grecs,
corprecords=crecs)
recs_pre_SALARIES = copy.deepcopy(calc.array('SALARIES'))
mtr_pitax = calc.mtr(variable_str='SALARIES',
zero_out_calculated_vars=True)
recs_post_SALARIES = calc.array('SALARIES')
assert np.allclose(recs_post_SALARIES, recs_pre_SALARIES)
assert np.allclose(calc.array('pitax'), pitax_x)
assert np.allclose(calc.array('GTI'), GTIx)
with pytest.raises(ValueError):
calc.mtr(variable_str='bad_income_type')
mtr_pit = calc.mtr(variable_str='SALARIES', calc_all_already_called=True)
assert isinstance(mtr_pit, np.ndarray)
mtr_pit = calc.mtr(variable_str='PRFT_GAIN_BP_OTHR_SPECLTV_BUS',
calc_all_already_called=True)
assert isinstance(mtr_pit, np.ndarray)
mtr_pit = calc.mtr(variable_str='SALARIES', calc_all_already_called=True)
assert np.allclose(mtr_pitax, mtr_pit)
assert np.allclose(calc.array('pitax'), pitax_x)
assert np.allclose(calc.array('GTI'), GTIx)
def test_create_distribution_tables(pit_fullsample, cit_crosssample):
# pylint: disable=too-many-statements,too-many-branches
# create a current-law Policy object and Calculator object calc1
rec = Records(data=pit_fullsample)
crec = CorpRecords(data=cit_crosssample)
pol = Policy()
calc1 = Calculator(policy=pol, records=rec, corprecords=crec)
calc1.calc_all()
# create a policy-reform Policy object and Calculator object calc2
reform = {2017: {'_rate2': [0.06]}}
pol.implement_reform(reform)
calc2 = Calculator(policy=pol, records=rec, corprecords=crec)
calc2.calc_all()
test_failure = False
# test creating various distribution tables
dist, _ = calc2.distribution_tables(None, 'weighted_deciles')
assert isinstance(dist, pd.DataFrame)
tabcol = 'pitax'
expected = [
0.000, 0.000, 0.000, 0.000, 0.000, 1.962, 5.711, 14.602, 45.503,
163.177, 397.795, 1018.520, 1647.270, 331.218, 384.399, 302.903
]
if not np.allclose(dist[tabcol].values, expected):
test_failure = True
print('dist xdec', tabcol)
for val in dist[tabcol].values:
print('{:.3f},'.format(val))
tabcol = 'GTI'
expected = [
0.000, 0.000, 688.359, 893.687, 1107.005, 1332.670, 1605.580, 1824.545,
2327.660, 2818.092, 3848.954, 6071.569, 22518.121, 2490.655, 2119.235,
1461.678
]
if not np.allclose(dist[tabcol].tolist(), expected):
test_failure = True
print('dist xdec', tabcol)
for val in dist[tabcol].values:
print('{:.3f},'.format(val))
dist, _ = calc2.distribution_tables(None, 'standard_income_bins')
assert isinstance(dist, pd.DataFrame)
tabcol = 'pitax'
expected = [
0.000, 0.000, 8.334, 279.113, 542.762, 401.310, 415.751, 0.000, 0.000,
0.000, 0.000, 1647.270
]
if not np.allclose(dist[tabcol], expected):
test_failure = True
print('dist xbin', tabcol)
for val in dist[tabcol].values:
print('{:.3f},'.format(val))
tabcol = 'GTI'
expected = [
0.000, 0.000, 5884.790, 7399.792, 4810.526, 2392.643, 2030.370, 0.000,
0.000, 0.000, 0.000, 22518.121
]
if not np.allclose(dist[tabcol].tolist(), expected):
test_failure = True
print('dist xdec', tabcol)
for val in dist[tabcol].values:
print('{:.3f},'.format(val))
"""
def test_increment_year(cit_fullsample):
recs = CorpRecords(data=cit_fullsample)
assert recs.current_year == recs.data_year
recs.increment_year()
assert recs.current_year == recs.data_year + 1
