def test_make_calculator_with_multiyear_reform(cps_subsample):
"""
Test Calculator class ctor with multi-year policy reform.
"""
rec = Records.cps_constructor(data=cps_subsample)
year = rec.current_year
# create a Policy object and apply a policy reform
pol = Policy()
reform = {2015: {}, 2016: {}}
reform[2015]['_II_em'] = [5000, 6000] # reform values for 2015 and 2016
reform[2015]['_II_em_cpi'] = False
reform[2016]['_STD_Aged'] = [[1600, 1300, 1600, 1300, 1600]]
pol.implement_reform(reform)
# create a Calculator object using this policy-reform
calc = Calculator(policy=pol, records=rec)
# check that Policy object embedded in Calculator object is correct
assert pol.num_years == Policy.DEFAULT_NUM_YEARS
assert calc.current_year == year
assert calc.policy_param('II_em') == 3950
exp_II_em = [3900, 3950, 5000] + [6000] * (Policy.DEFAULT_NUM_YEARS - 3)
assert np.allclose(calc.policy_param('_II_em'),
np.array(exp_II_em))
calc.increment_year()
calc.increment_year()
assert calc.current_year == 2016
assert np.allclose(calc.policy_param('STD_Aged'),
np.array([1600, 1300, 1600, 1300, 1600]))
def test_calculator_mtr_when_PT_rates_differ():
"""
Test Calculator mtr method in special case.
"""
reform = {2013: {'_II_rt1': [0.40],
'_II_rt2': [0.40],
'_II_rt3': [0.40],
'_II_rt4': [0.40],
'_II_rt5': [0.40],
'_II_rt6': [0.40],
'_II_rt7': [0.40],
'_PT_rt1': [0.30],
'_PT_rt2': [0.30],
'_PT_rt3': [0.30],
'_PT_rt4': [0.30],
'_PT_rt5': [0.30],
'_PT_rt6': [0.30],
'_PT_rt7': [0.30]}}
funit = (
u'RECID,MARS,FLPDYR,e00200,e00200p,e00900,e00900p,extraneous\n'
u'1, 1, 2009, 200000,200000, 100000,100000, 9999999999\n'
)
rec = Records(pd.read_csv(StringIO(funit)))
pol = Policy()
calc1 = Calculator(policy=pol, records=rec)
(_, mtr1, _) = calc1.mtr(variable_str='p23250')
pol.implement_reform(reform)
calc2 = Calculator(policy=pol, records=rec)
(_, mtr2, _) = calc2.mtr(variable_str='p23250')
assert np.allclose(mtr1, mtr2, rtol=0.0, atol=1e-06)
def test_Calculator_mtr_when_PT_rates_differ():
reform = {2013: {'_II_rt1': [0.40],
'_II_rt2': [0.40],
'_II_rt3': [0.40],
'_II_rt4': [0.40],
'_II_rt5': [0.40],
'_II_rt6': [0.40],
'_II_rt7': [0.40],
'_PT_rt1': [0.30],
'_PT_rt2': [0.30],
'_PT_rt3': [0.30],
'_PT_rt4': [0.30],
'_PT_rt5': [0.30],
'_PT_rt6': [0.30],
'_PT_rt7': [0.30]}}
funit = (
u'RECID,MARS,FLPDYR,e00200,e00200p,e00900,e00900p\n'
u'1, 1, 2015, 200000,200000, 100000,100000\n'
)
pol1 = Policy()
rec1 = Records(pd.read_csv(StringIO(funit)))
calc1 = Calculator(policy=pol1, records=rec1)
(_, mtr1, _) = calc1.mtr(variable_str='p23250')
pol2 = Policy()
pol2.implement_reform(reform)
rec2 = Records(pd.read_csv(StringIO(funit)))
calc2 = Calculator(policy=pol2, records=rec2)
(_, mtr2, _) = calc2.mtr(variable_str='p23250')
assert np.allclose(mtr1, mtr2, rtol=0.0, atol=1e-06)
def test_read_json_reform_file_and_implement_reform_a(reform_file):
"""
Test reading and translation of reform file into a reform dictionary
that is then used to call implement_reform method.
NOTE: implement_reform called when policy.current_year == policy.start_year
"""
reform = Policy.read_json_reform_file(reform_file.name)
policy = Policy()
policy.implement_reform(reform)
syr = policy.start_year
amt_tthd = policy._AMT_tthd
assert amt_tthd[2015 - syr] == 200000
assert amt_tthd[2016 - syr] > 200000
assert amt_tthd[2017 - syr] == 300000
assert amt_tthd[2018 - syr] > 300000
ii_em = policy._II_em
assert ii_em[2016 - syr] == 6000
assert ii_em[2017 - syr] == 6000
assert ii_em[2018 - syr] == 7500
assert ii_em[2019 - syr] > 7500
assert ii_em[2020 - syr] == 9000
assert ii_em[2021 - syr] > 9000
amt_em = policy._AMT_em
assert amt_em[2016 - syr, 0] > amt_em[2015 - syr, 0]
assert amt_em[2017 - syr, 0] > amt_em[2016 - syr, 0]
assert amt_em[2018 - syr, 0] == amt_em[2017 - syr, 0]
assert amt_em[2019 - syr, 0] == amt_em[2017 - syr, 0]
assert amt_em[2020 - syr, 0] == amt_em[2017 - syr, 0]
assert amt_em[2021 - syr, 0] > amt_em[2020 - syr, 0]
assert amt_em[2022 - syr, 0] > amt_em[2021 - syr, 0]
def diff_in_revenue(reform_on_II, orig_reform):
policy_func = Policy()
puf = pd.read_csv("./puf.csv")
records_func = Records(puf)
calc_func = Calculator(policy = policy_func, records = records_func)
policy_bench = Policy()
records_bench = Records(puf)
calc_bench = Calculator(policy = policy_bench, records = records_bench)
reform = {
CURRENT_YEAR:{
"_II_rt1":[max(policy_bench._II_rt1[0] *(1 - reform_on_II),0.0)],
"_II_rt2":[max(policy_bench._II_rt2[0] *(1 - reform_on_II),0.0)],
"_II_rt3":[max(policy_bench._II_rt3[0] *(1 - reform_on_II),0.0)],
"_II_rt4":[max(policy_bench._II_rt4[0] *(1 - reform_on_II),0.0)],
"_II_rt5":[max(policy_bench._II_rt5[0] *(1 - reform_on_II),0.0)],
"_II_rt6":[max(policy_bench._II_rt6[0] *(1 - reform_on_II),0.0)],
"_II_rt7":[max(policy_bench._II_rt7[0] *(1 - reform_on_II),0.0)]}
}
policy_func.implement_reform(reform)
policy_func.implement_reform(orig_reform)
calc_func.advance_to_year(CURRENT_YEAR)
calc_bench.advance_to_year(CURRENT_YEAR)
calc_func.calc_all()
calc_bench.calc_all()
ans = ((calc_bench.records._combined*calc_bench.records.s006).sum()-(calc_func.records._combined*calc_func.records.s006).sum())
print("diff in revenue is ", ans)
return ans
def test_Policy_reform_in_start_year():
ppo = Policy(start_year=2013)
reform = {2013: {'_STD_Aged': [[1400, 1100, 1100, 1400, 1400, 1199]]}}
ppo.implement_reform(reform)
assert_allclose(ppo.STD_Aged,
np.array([1400, 1100, 1100, 1400, 1400, 1199]),
atol=0.01, rtol=0.0)
def test_strip_Nones():
x = [None, None]
assert Policy.strip_Nones(x) == []
x = [1, 2, None]
assert Policy.strip_Nones(x) == [1, 2]
x = [[1, 2, 3], [4, None, None]]
assert Policy.strip_Nones(x) == [[1, 2, 3], [4, -1, -1]]
def test_make_calculator_with_policy_reform(cps_subsample):
"""
Test Calculator class ctor with policy reform.
"""
rec = Records.cps_constructor(data=cps_subsample)
year = rec.current_year
# create a Policy object and apply a policy reform
pol = Policy()
reform = {2013: {'_II_em': [4000], '_II_em_cpi': False,
'_STD_Aged': [[1600, 1300, 1300, 1600, 1600]],
'_STD_Aged_cpi': False}}
pol.implement_reform(reform)
# create a Calculator object using this policy reform
calc = Calculator(policy=pol, records=rec)
# check that Policy object embedded in Calculator object is correct
assert calc.current_year == year
assert calc.policy_param('II_em') == 4000
assert np.allclose(calc.policy_param('_II_em'),
np.array([4000] * Policy.DEFAULT_NUM_YEARS))
exp_STD_Aged = [[1600, 1300, 1300,
1600, 1600]] * Policy.DEFAULT_NUM_YEARS
assert np.allclose(calc.policy_param('_STD_Aged'),
np.array(exp_STD_Aged))
assert np.allclose(calc.policy_param('STD_Aged'),
np.array([1600, 1300, 1300, 1600, 1600]))
def test_dec_graph_plots(cps_subsample):
pol = Policy()
rec = Records.cps_constructor(data=cps_subsample)
calc1 = Calculator(policy=pol, records=rec)
year = 2020
calc1.advance_to_year(year)
reform = {
'SS_Earnings_c': {year: 9e99}, # OASDI FICA tax on all earnings
'FICA_ss_trt': {year: 0.107484} # lower rate to keep revenue unchanged
}
pol.implement_reform(reform)
calc2 = Calculator(policy=pol, records=rec)
calc2.advance_to_year(year)
assert calc1.current_year == calc2.current_year
calc1.calc_all()
calc2.calc_all()
fig = calc1.decile_graph(calc2)
assert fig
dt1, dt2 = calc1.distribution_tables(calc2, 'weighted_deciles')
dta = dec_graph_data(dt1, dt2, year,
include_zero_incomes=True,
include_negative_incomes=False)
assert isinstance(dta, dict)
dta = dec_graph_data(dt1, dt2, year,
include_zero_incomes=False,
include_negative_incomes=True)
assert isinstance(dta, dict)
dta = dec_graph_data(dt1, dt2, year,
include_zero_incomes=False,
include_negative_incomes=False)
assert isinstance(dta, dict)
def test_make_Calculator_with_reform_after_start_year():
# create Policy object using custom indexing rates
irates = {2013: 0.01, 2014: 0.01, 2015: 0.02, 2016: 0.01, 2017: 0.03}
parm = Policy(start_year=2013, num_years=len(irates),
inflation_rates=irates)
# specify reform in 2015, which is two years after Policy start_year
reform = {2015: {}, 2016: {}}
reform[2015]['_STD_Aged'] = [[1600, 1300, 1600, 1300, 1600, 1300]]
reform[2015]['_II_em'] = [5000]
reform[2016]['_II_em'] = [6000]
reform[2016]['_II_em_cpi'] = False
parm.implement_reform(reform)
recs = Records(data=TAX_DTA, weights=WEIGHTS, start_year=2009)
calc = Calculator(policy=parm, records=recs)
# compare actual and expected parameter values over all years
exp_STD_Aged = np.array([[1500, 1200, 1200, 1500, 1500, 1200],
[1550, 1200, 1200, 1550, 1550, 1200],
[1600, 1300, 1600, 1300, 1600, 1300],
[1632, 1326, 1632, 1326, 1632, 1326],
[1648, 1339, 1648, 1339, 1648, 1339]])
exp_II_em = np.array([3900, 3950, 5000, 6000, 6000])
assert_array_equal(calc.policy._STD_Aged, exp_STD_Aged)
assert_array_equal(calc.policy._II_em, exp_II_em)
# compare actual and expected values for 2015
calc.increment_year()
calc.increment_year()
assert calc.current_year == 2015
exp_2015_II_em = 5000
assert_array_equal(calc.policy.II_em, exp_2015_II_em)
exp_2015_STD_Aged = np.array([1600, 1300, 1600, 1300, 1600, 1300])
assert_array_equal(calc.policy.STD_Aged, exp_2015_STD_Aged)
def test_Policy_reform_makes_no_changes_before_year():
ppo = Policy(start_year=2013)
reform = {2015: {'_II_em': [4400], '_II_em_cpi': True}}
ppo.implement_reform(reform)
ppo.set_year(2015)
assert_array_equal(ppo._II_em[:3], np.array([3900, 3950, 4400]))
assert ppo.II_em == 4400
def test_Policy_reform_after_start_year():
ppo = Policy(start_year=2013)
reform = {2015: {'_STD_Aged': [[1400, 1100, 1100, 1400, 1400, 1199]]}}
ppo.implement_reform(reform)
ppo.set_year(2015)
assert_array_equal(ppo.STD_Aged,
np.array([1400, 1100, 1100, 1400, 1400, 1199]))
def test_make_Calculator_increment_years_first():
# create Policy object with custom indexing rates and policy reform
irates = {2013: 0.01, 2014: 0.01, 2015: 0.02, 2016: 0.01, 2017: 0.03}
policy = Policy(start_year=2013, inflation_rates=irates,
num_years=len(irates))
reform = {2015: {}, 2016: {}}
reform[2015]['_STD_Aged'] = [[1600, 1300, 1600, 1300, 1600, 1300]]
reform[2015]['_II_em'] = [5000]
reform[2016]['_II_em'] = [6000]
reform[2016]['_II_em_cpi'] = False
policy.implement_reform(reform)
# create Records object by reading 1991 data and saying it is 2009 data
tax_dta = pd.read_csv(TAX_DTA_PATH, compression='gzip')
puf = Records(tax_dta, weights=WEIGHTS, start_year=2009)
# create Calculator object with Policy object as modified by reform
calc = Calculator(policy=policy, records=puf)
# compare expected policy parameter values with those embedded in calc
exp_STD_Aged = np.array([[1500, 1200, 1200, 1500, 1500, 1200],
[1550, 1200, 1200, 1550, 1550, 1200],
[1600, 1300, 1600, 1300, 1600, 1300],
[1632, 1326, 1632, 1326, 1632, 1326],
[1648, 1339, 1648, 1339, 1648, 1339]])
exp_II_em = np.array([3900, 3950, 5000, 6000, 6000])
assert_array_equal(calc.policy._STD_Aged, exp_STD_Aged)
assert_array_equal(calc.policy._II_em, exp_II_em)
def test_make_calculator_increment_years_first(cps_subsample):
"""
Test Calculator inflation indexing of policy parameters.
"""
# pylint: disable=too-many-locals
# create Policy object with policy reform
pol = Policy()
reform = {2015: {}, 2016: {}}
std5 = 2000
reform[2015]['_STD_Aged'] = [[std5, std5, std5, std5, std5]]
reform[2015]['_II_em'] = [5000]
reform[2016]['_II_em'] = [6000]
reform[2016]['_II_em_cpi'] = False
pol.implement_reform(reform)
# create Calculator object with Policy object as modified by reform
rec = Records.cps_constructor(data=cps_subsample)
calc = Calculator(policy=pol, records=rec)
# compare expected policy parameter values with those embedded in calc
irates = pol.inflation_rates()
syr = Policy.JSON_START_YEAR
irate2015 = irates[2015 - syr]
irate2016 = irates[2016 - syr]
std6 = std5 * (1.0 + irate2015)
std7 = std6 * (1.0 + irate2016)
exp_STD_Aged = np.array([[1500, 1200, 1200, 1500, 1500],
[1550, 1200, 1200, 1550, 1550],
[std5, std5, std5, std5, std5],
[std6, std6, std6, std6, std6],
[std7, std7, std7, std7, std7]])
act_STD_Aged = calc.policy_param('_STD_Aged')
assert np.allclose(act_STD_Aged[:5], exp_STD_Aged)
exp_II_em = np.array([3900, 3950, 5000, 6000, 6000])
act_II_em = calc.policy_param('_II_em')
assert np.allclose(act_II_em[:5], exp_II_em)
def test_reform_pkey_year():
with pytest.raises(ValueError):
rdict = Policy._reform_pkey_year({4567: {2013: [40000]}})
with pytest.raises(ValueError):
rdict = Policy._reform_pkey_year({'_II_em': 40000})
with pytest.raises(ValueError):
rdict = Policy._reform_pkey_year({'_II_em': {'2013': [40000]}})
def test_calculator_using_nonstd_input(rawinputfile):
"""
Test Calculator using non-standard input records.
"""
# check Calculator handling of raw, non-standard input data with no aging
pol = Policy()
pol.set_year(RAWINPUTFILE_YEAR) # set policy params to input data year
nonstd = Records(data=rawinputfile.name,
gfactors=None, # keeps raw data unchanged
weights=None,
start_year=RAWINPUTFILE_YEAR) # set raw input data year
assert nonstd.array_length == RAWINPUTFILE_FUNITS
calc = Calculator(policy=pol, records=nonstd,
sync_years=False) # keeps raw data unchanged
assert calc.current_year == RAWINPUTFILE_YEAR
calc.calc_all()
assert calc.weighted_total('e00200') == 0
assert calc.total_weight() == 0
varlist = ['RECID', 'MARS']
dframe = calc.dataframe(varlist)
assert isinstance(dframe, pd.DataFrame)
assert dframe.shape == (RAWINPUTFILE_FUNITS, len(varlist))
mars = calc.array('MARS')
assert isinstance(mars, np.ndarray)
assert mars.shape == (RAWINPUTFILE_FUNITS,)
exp_iitax = np.zeros((nonstd.array_length,))
assert np.allclose(calc.array('iitax'), exp_iitax)
mtr_ptax, _, _ = calc.mtr(wrt_full_compensation=False)
exp_mtr_ptax = np.zeros((nonstd.array_length,))
exp_mtr_ptax.fill(0.153)
assert np.allclose(mtr_ptax, exp_mtr_ptax)
def test_make_Calculator_with_reform_after_start_year(records_2009):
# create Policy object using custom indexing rates
irates = {2013: 0.01, 2014: 0.01, 2015: 0.02, 2016: 0.01, 2017: 0.03}
parm = Policy(start_year=2013, num_years=len(irates),
inflation_rates=irates)
# specify reform in 2015, which is two years after Policy start_year
reform = {2015: {}, 2016: {}}
reform[2015]['_STD_Aged'] = [[1600, 1300, 1600, 1300, 1600, 1300]]
reform[2015]['_II_em'] = [5000]
reform[2016]['_II_em'] = [6000]
reform[2016]['_II_em_cpi'] = False
parm.implement_reform(reform)
calc = Calculator(policy=parm, records=records_2009)
# compare actual and expected parameter values over all years
assert np.allclose(calc.policy._STD_Aged,
np.array([[1500, 1200, 1200, 1500, 1500, 1200],
[1550, 1200, 1200, 1550, 1550, 1200],
[1600, 1300, 1600, 1300, 1600, 1300],
[1632, 1326, 1632, 1326, 1632, 1326],
[1648, 1339, 1648, 1339, 1648, 1339]]),
atol=0.5, rtol=0.0) # handles rounding to dollars
assert np.allclose(calc.policy._II_em,
np.array([3900, 3950, 5000, 6000, 6000]))
# compare actual and expected values for 2015
calc.increment_year()
calc.increment_year()
assert calc.current_year == 2015
assert np.allclose(calc.policy.II_em, 5000)
assert np.allclose(calc.policy.STD_Aged,
np.array([1600, 1300, 1600, 1300, 1600, 1300]))
def test_read_json_param_with_suffixes_and_errors():
"""
Test interaction of policy parameter suffixes and reform errors
(fails without 0.10.2 bug fix as reported by Hank Doupe in PB PR#641)
"""
reform = {
u'policy': {
u'_II_brk4_separate': {u'2017': [5000.0]},
u'_STD_separate': {u'2017': [8000.0]},
u'_STD_single': {u'2018': [1000.0]},
u'_II_brk2_headhousehold': {u'2017': [1000.0]},
u'_II_brk4_single': {u'2017': [500.0]},
u'_STD_joint': {u'2017': [10000.0], u'2020': [150.0]},
u'_II_brk2_separate': {u'2017': [1000.0]},
u'_II_brk2_single': {u'2017': [1000.0]},
u'_II_brk2_joint': {u'2017': [1000.0]},
u'_FICA_ss_trt': {u'2017': [-1.0], u'2019': [0.1]},
u'_II_brk4_headhousehold': {u'2017': [500.0]},
u'_STD_headhousehold': {u'2017': [10000.0], u'2020': [150.0]},
u'_ID_Medical_frt': {u'2019': [0.06]},
u'_II_brk4_joint': {u'2017': [500.0]},
u'_ID_BenefitSurtax_Switch_medical': {u'2017': [True]}
}
}
json_reform = json.dumps(reform)
params = Calculator.read_json_param_objects(json_reform, None)
assert isinstance(params, dict)
pol = Policy()
pol.ignore_reform_errors()
pol.implement_reform(params['policy'],
print_warnings=False, raise_errors=False)
assert pol.parameter_errors
assert pol.parameter_warnings
def test_convert(self):
values = {"II_brk2_0": [36000., 38000., 40000.],
"II_brk2_1": [72250., 74000.],
"II_brk2_2": [36500.]
}
ans = package_up_vars(values, first_budget_year=FBY)
pp = Policy(start_year=2013)
pp.set_year(FBY)
# irates are rates for 2015, 2016, and 2017
irates = pp.indexing_rates_for_update(param_name='II_brk2', calyear=FBY,
num_years_to_expand=3)
# User choices propagate through to all future years
# The user has specified part of the parameter up to 2017.
# So, we choose to fill in the propagated value, which is
# either inflated or not.
f2_2016 = int(36500 * (1.0 + irates[0]))
f3_2016 = int(50200 * (1.0 + irates[0]))
f4_2016 = int(74900 * (1.0 + irates[0]))
f5_2016 = int(37450 * (1.0 + irates[0]))
f1_2017 = int(74000 * (1.0 + irates[1]))
f2_2017 = int(f2_2016 * (1.0 + irates[1]))
exp = [[36000, 72250, 36500, 50200, 74900, 37450],
[38000, 74000, f2_2016, 50400, 75300, 37650],
[40000, f1_2017, f2_2017, None, None, None]]
assert ans['_II_brk2'] == exp
assert len(ans) == 1
def test_create_parameters_from_file(policyfile):
with open(policyfile.name) as pfile:
policy = json.load(pfile)
ppo = Policy(parameter_dict=policy)
irates = Policy.default_inflation_rates()
inf_rates = [irates[ppo.start_year + i] for i in range(0, ppo.num_years)]
assert_allclose(ppo._almdep,
Policy.expand_array(np.array([7150, 7250, 7400]),
inflate=True,
inflation_rates=inf_rates,
num_years=ppo.num_years),
atol=0.01, rtol=0.0)
assert_allclose(ppo._almsep,
Policy.expand_array(np.array([40400, 41050]),
inflate=True,
inflation_rates=inf_rates,
num_years=ppo.num_years),
atol=0.01, rtol=0.0)
assert_allclose(ppo._rt5,
Policy.expand_array(np.array([0.33]),
inflate=False,
inflation_rates=inf_rates,
num_years=ppo.num_years),
atol=0.01, rtol=0.0)
assert_allclose(ppo._rt7,
Policy.expand_array(np.array([0.396]),
inflate=False,
inflation_rates=inf_rates,
num_years=ppo.num_years),
atol=0.01, rtol=0.0)
def test_distribution_tables(cps_subsample):
"""
Test distribution_tables method.
"""
pol = Policy()
recs = Records.cps_constructor(data=cps_subsample)
calc1 = Calculator(policy=pol, records=recs)
assert calc1.current_year == 2014
calc1.calc_all()
dt1, dt2 = calc1.distribution_tables(None, 'weighted_deciles')
assert isinstance(dt1, pd.DataFrame)
assert dt2 is None
dt1, dt2 = calc1.distribution_tables(calc1, 'weighted_deciles')
assert isinstance(dt1, pd.DataFrame)
assert isinstance(dt2, pd.DataFrame)
reform = {2014: {'_UBI_u18': [1000],
'_UBI_1820': [1000],
'_UBI_21': [1000]}}
pol.implement_reform(reform)
assert not pol.parameter_errors
calc2 = Calculator(policy=pol, records=recs)
calc2.calc_all()
dt1, dt2 = calc1.distribution_tables(calc2, 'weighted_deciles')
assert isinstance(dt1, pd.DataFrame)
assert isinstance(dt2, pd.DataFrame)
def test_parameters_get_default_start_year():
paramdata = Policy.default_data(metadata=True, start_year=2015)
# 1D data, has 2015 values
meta_II_em = paramdata['_II_em']
assert meta_II_em['start_year'] == 2015
assert meta_II_em['row_label'] == ['2015', '2016']
assert meta_II_em['value'] == [4000, 4050]
# 2D data, has 2015 values
meta_std_aged = paramdata['_STD_Aged']
assert meta_std_aged['start_year'] == 2015
assert meta_std_aged['row_label'] == ['2015', '2016']
assert meta_std_aged['value'] == [[1550, 1250, 1250, 1550, 1550, 1250],
[1550, 1250, 1250, 1550, 1550, 1250]]
# 1D data, doesn't have 2015 values, is CPI inflated
meta_amt_thd_marrieds = paramdata['_AMT_thd_MarriedS']
assert meta_amt_thd_marrieds['start_year'] == 2015
assert meta_amt_thd_marrieds['row_label'] == ['2015']
# Take the 2014 parameter value and multiply by inflation for that year
should_be = 41050 * (1.0 + Policy.default_inflation_rates()[2014])
meta_amt_thd_marrieds['value'] == should_be
# 1D data, doesn't have 2015 values, is not CPI inflated
meta_kt_c_age = paramdata['_KT_c_Age']
assert meta_kt_c_age['start_year'] == 2015
assert meta_kt_c_age['row_label'] == ['2015']
assert meta_kt_c_age['value'] == [24]
def taxcalc_results(start_year, reform_dict, itax_clp, ptax_clp):
"""
Use taxcalc package on this computer to compute aggregate income tax and
payroll tax revenue difference (between reform and current-law policy)
for ten years beginning with the specified start_year using the specified
reform_dict dictionary and the two specified current-law-policy results
dictionaries.
Return two aggregate tax revenue difference dictionaries indexed by
calendar year.
"""
pol = Policy()
pol.implement_reform(reform_dict)
calc = Calculator(policy=pol,
records=Records(data=PUF_PATH),
verbose=False)
calc.advance_to_year(start_year)
nyears = NUMBER_OF_YEARS
adts = list()
for iyr in range(-1, nyears - 1):
calc.calc_all()
adts.append(create_diagnostic_table(calc))
if iyr < nyears:
calc.increment_year()
adt = pd.concat(adts, axis=1)
# note that adt is Pandas DataFrame object
itax_ref = adt.xs('Ind Income Tax ($b)').to_dict()
ptax_ref = adt.xs('Payroll Taxes ($b)').to_dict()
itax_diff = {}
ptax_diff = {}
for year in itax_ref:
itax_diff[year] = round(itax_ref[year] - itax_clp[year], 1)
ptax_diff[year] = round(ptax_ref[year] - ptax_clp[year], 1)
return (itax_diff, ptax_diff)
def test_Policy_reform_with_default_cpi_flags():
ppo = Policy(start_year=2013)
reform = {2015: {'_II_em': [4300]}}
ppo.implement_reform(reform)
# '_II_em' has a default cpi_flag of True, so
# in 2016 its value should be greater than 4300
ppo.set_year(2016)
assert ppo.II_em > 4300
def test_reform_with_warning():
"""
Try to use warned out-of-range parameter value in reform.
"""
pol = Policy()
reform = {'ID_Medical_frt': {2020: 0.05}}
pol.implement_reform(reform)
assert pol.parameter_warnings
def test_implement_reform_raises_on_no_year():
"""
Test that implement_reform raises error for missing year.
"""
reform = {'STD_Aged': [1400, 1200, 1400, 1400, 1400]}
ppo = Policy()
with pytest.raises(ValueError):
ppo.implement_reform(reform)
def test_reform_with_out_of_range_error():
"""
Try to use out-of-range values versus other parameter values in a reform.
"""
pol = Policy()
reform = {'SS_thd85': {2020: [20000, 20000, 20000, 20000, 20000]}}
pol.implement_reform(reform, raise_errors=False)
assert pol.parameter_errors
def test_implement_reform_raises_on_early_year():
"""
Test that implement_reform raises error for early year.
"""
ppo = Policy()
reform = {'STD_Aged': {2010: [1400, 1100, 1100, 1400, 1400]}}
with pytest.raises(ValueError):
ppo.implement_reform(reform)
def test_indexing_rates_for_update():
"""
Check private _indexing_rates_for_update method.
"""
pol = Policy()
wgrates = pol._indexing_rates_for_update('_SS_Earnings_c', 2017, 10)
pirates = pol._indexing_rates_for_update('_II_em', 2017, 10)
assert len(wgrates) == len(pirates)
def test_Calculator_current_law_version(records_2009):
policy = Policy()
reform = {2013: {'_II_rt7': [0.45]}}
policy.implement_reform(reform)
calc = Calculator(policy=policy, records=records_2009)
calc_clp = calc.current_law_version()
assert isinstance(calc_clp, Calculator)
assert calc.policy.II_rt6 == calc_clp.policy.II_rt6
assert calc.policy.II_rt7 != calc_clp.policy.II_rt7
def test_read_json_param_and_implement_reform(reform_file, set_year):
"""
Test reading and translation of reform file into a reform dictionary
that is then used to call implement_reform method.
NOTE: implement_reform called when policy.current_year == policy.start_year
"""
policy = Policy()
if set_year:
policy.set_year(2015)
param_dict = Calculator.read_json_param_objects(reform_file.name, None)
policy.implement_reform(param_dict['policy'])
syr = policy.start_year
amt_brk1 = policy._AMT_brk1
assert amt_brk1[2015 - syr] == 200000
assert amt_brk1[2016 - syr] > 200000
assert amt_brk1[2017 - syr] == 300000
assert amt_brk1[2018 - syr] > 300000
ii_em = policy._II_em
assert ii_em[2016 - syr] == 6000
assert ii_em[2017 - syr] == 6000
assert ii_em[2018 - syr] == 7500
assert ii_em[2019 - syr] > 7500
assert ii_em[2020 - syr] == 9000
assert ii_em[2021 - syr] > 9000
amt_em = policy._AMT_em
assert amt_em[2016 - syr, 0] > amt_em[2015 - syr, 0]
assert amt_em[2017 - syr, 0] > amt_em[2016 - syr, 0]
assert amt_em[2018 - syr, 0] == amt_em[2017 - syr, 0]
assert amt_em[2019 - syr, 0] == amt_em[2017 - syr, 0]
assert amt_em[2020 - syr, 0] == amt_em[2017 - syr, 0]
assert amt_em[2021 - syr, 0] > amt_em[2020 - syr, 0]
assert amt_em[2022 - syr, 0] > amt_em[2021 - syr, 0]
add4aged = policy._ID_Medical_frt_add4aged
assert add4aged[2015 - syr] == -0.025
assert add4aged[2016 - syr] == -0.025
assert add4aged[2017 - syr] == 0.0
assert add4aged[2022 - syr] == 0.0
def test_parameters_get_default():
paramdata = Policy.default_data()
assert paramdata['_CDCC_ps'] == [15000]
def test_reform_json_and_output(tests_path):
"""
Check that each JSON reform file can be converted into a reform dictionary
that can then be passed to the Policy class implement_reform method that
generates no reform_errors.
Then use each reform to generate static tax results for small set of
filing units in a single tax_year and compare those results with
expected results from a text file.
"""
# pylint: disable=too-many-statements,too-many-locals
used_dist_stats = [
'c00100', # AGI
'c04600', # personal exemptions
'standard', # standard deduction
'c04800', # regular taxable income
'c05800', # income tax before credits
'iitax', # income tax after credits
'payrolltax', # payroll taxes
'aftertax_income'
] # aftertax expanded income
unused_dist_stats = set(DIST_TABLE_COLUMNS) - set(used_dist_stats)
renamed_columns = {
'c00100': 'AGI',
'c04600': 'pexempt',
'standard': 'stdded',
'c04800': 'taxinc',
'c05800': 'tax-wo-credits',
'iitax': 'inctax',
'payrolltax': 'paytax',
'aftertax_income': 'ataxinc'
}
# embedded function used only in test_reform_json_and_output
def write_distribution_table(calc, resfilename):
"""
Write abbreviated distribution table calc to file with resfilename.
"""
dist, _ = calc.distribution_tables(None, groupby='large_income_bins')
for stat in unused_dist_stats:
del dist[stat]
dist = dist[used_dist_stats]
dist.rename(mapper=renamed_columns, axis='columns', inplace=True)
pd.options.display.float_format = '{:7.0f}'.format
with open(resfilename, 'w') as resfile:
dist.to_string(resfile)
# embedded function used only in test_reform_json_and_output
def res_and_out_are_same(base):
"""
Return True if base.res and base.out file contents are the same;
return False if base.res and base.out file contents differ.
"""
with open(base + '.res') as resfile:
act_res = resfile.read()
with open(base + '.out') as outfile:
exp_res = outfile.read()
# check to see if act_res & exp_res have differences
return not nonsmall_diffs(act_res.splitlines(True),
exp_res.splitlines(True))
# specify Records object containing cases data
tax_year = 2020
cases_path = os.path.join(tests_path, '..', 'reforms', 'cases.csv')
cases = Records(
data=cases_path,
gfactors=None, # keeps raw data unchanged
weights=None,
adjust_ratios=None,
start_year=tax_year) # set raw input data year
# specify list of reform failures
failures = list()
# specify current-law-policy Calculator object
calc1 = Calculator(policy=Policy(), records=cases, verbose=False)
calc1.advance_to_year(tax_year)
calc1.calc_all()
res_path = cases_path.replace('cases.csv', 'clp.res')
write_distribution_table(calc1, res_path)
if res_and_out_are_same(res_path.replace('.res', '')):
os.remove(res_path)
else:
failures.append(res_path)
# read 2017_law.json reform file and specify its parameters dictionary
pre_tcja_jrf = os.path.join(tests_path, '..', 'reforms', '2017_law.json')
pre_tcja = Calculator.read_json_param_objects(pre_tcja_jrf, None)
# check reform file contents and reform results for each reform
reforms_path = os.path.join(tests_path, '..', 'reforms', '*.json')
json_reform_files = glob.glob(reforms_path)
for jrf in json_reform_files:
# determine reform's baseline by reading contents of jrf
with open(jrf, 'r') as rfile:
jrf_text = rfile.read()
pre_tcja_baseline = 'Reform_Baseline: 2017_law.json' in jrf_text
# implement the reform relative to its baseline
reform = Calculator.read_json_param_objects(jrf_text, None)
pol = Policy() # current-law policy
if pre_tcja_baseline:
pol.implement_reform(pre_tcja['policy'])
pol.implement_reform(reform['policy'])
assert not pol.reform_errors
calc2 = Calculator(policy=pol, records=cases, verbose=False)
calc2.advance_to_year(tax_year)
calc2.calc_all()
res_path = jrf.replace('.json', '.res')
write_distribution_table(calc2, res_path)
if res_and_out_are_same(res_path.replace('.res', '')):
os.remove(res_path)
else:
failures.append(res_path)
if failures:
msg = 'Following reforms have res-vs-out differences:\n'
for ref in failures:
msg += '{}\n'.format(os.path.basename(ref))
raise ValueError(msg)
def test_behavioral_response(use_puf_not_cps, puf_subsample, cps_fullsample):
"""
Test that behavioral-response results are the same
when generated from standard Tax-Calculator calls and
when generated from tbi.run_nth_year_taxcalc_model() calls
"""
# specify reform and assumptions
reform_json = """
{"policy": {
"_II_rt5": {"2020": [0.25]},
"_II_rt6": {"2020": [0.25]},
"_II_rt7": {"2020": [0.25]},
"_PT_rt5": {"2020": [0.25]},
"_PT_rt6": {"2020": [0.25]},
"_PT_rt7": {"2020": [0.25]},
"_II_em": {"2020": [1000]}
}}
"""
assump_json = """
{"behavior": {"_BE_sub": {"2013": [0.25]}},
"growdiff_baseline": {},
"growdiff_response": {},
"consumption": {},
"growmodel": {}
}
"""
params = Calculator.read_json_param_objects(reform_json, assump_json)
# specify keyword arguments used in tbi function call
kwargs = {
'start_year': 2019,
'year_n': 0,
'use_puf_not_cps': use_puf_not_cps,
'use_full_sample': False,
'user_mods': {
'policy': params['policy'],
'behavior': params['behavior'],
'growdiff_baseline': params['growdiff_baseline'],
'growdiff_response': params['growdiff_response'],
'consumption': params['consumption'],
'growmodel': params['growmodel']
},
'return_dict': False
}
# generate aggregate results two ways: using tbi and standard calls
num_years = 9
std_res = dict()
tbi_res = dict()
if use_puf_not_cps:
rec = Records(data=puf_subsample)
else:
# IMPORTANT: must use same subsample as used in test_cpscsv.py because
# that is the subsample used by run_nth_year_taxcalc_model
std_cps_subsample = cps_fullsample.sample(frac=0.03, random_state=180)
rec = Records.cps_constructor(data=std_cps_subsample)
for using_tbi in [True, False]:
for year in range(0, num_years):
cyr = year + kwargs['start_year']
if using_tbi:
kwargs['year_n'] = year
tables = run_nth_year_taxcalc_model(**kwargs)
tbi_res[cyr] = dict()
for tbl in ['aggr_1', 'aggr_2', 'aggr_d']:
tbi_res[cyr][tbl] = tables[tbl]
else:
pol = Policy()
calc1 = Calculator(policy=pol, records=rec)
pol.implement_reform(params['policy'])
assert not pol.parameter_errors
beh = Behavior()
beh.update_behavior(params['behavior'])
calc2 = Calculator(policy=pol, records=rec, behavior=beh)
assert calc2.behavior_has_response()
calc1.advance_to_year(cyr)
calc2.advance_to_year(cyr)
calc2 = Behavior.response(calc1, calc2)
std_res[cyr] = dict()
for tbl in ['aggr_1', 'aggr_2', 'aggr_d']:
if tbl.endswith('_1'):
itax = calc1.weighted_total('iitax')
ptax = calc1.weighted_total('payrolltax')
ctax = calc1.weighted_total('combined')
elif tbl.endswith('_2'):
itax = calc2.weighted_total('iitax')
ptax = calc2.weighted_total('payrolltax')
ctax = calc2.weighted_total('combined')
elif tbl.endswith('_d'):
itax = (calc2.weighted_total('iitax') -
calc1.weighted_total('iitax'))
ptax = (calc2.weighted_total('payrolltax') -
calc1.weighted_total('payrolltax'))
ctax = (calc2.weighted_total('combined') -
calc1.weighted_total('combined'))
cols = ['0_{}'.format(year)]
rows = ['ind_tax', 'payroll_tax', 'combined_tax']
datalist = [itax, ptax, ctax]
std_res[cyr][tbl] = pd.DataFrame(data=datalist,
index=rows,
columns=cols)
for col in std_res[cyr][tbl].columns:
val = std_res[cyr][tbl][col] * 1e-9
std_res[cyr][tbl][col] = round(val, 3)
# compare the two sets of results
# NOTE that the PUF tbi results have been "fuzzed" for privacy reasons,
# so there is no expectation that those results should be identical.
no_diffs = True
cps_dump = False # setting to True produces dump output and test failure
if use_puf_not_cps:
reltol = 0.004 # std and tbi differ if more than 0.4 percent different
dataset = 'PUF'
dumping = False
else: # CPS results are not "fuzzed", so
reltol = 1e-9 # std and tbi should be virtually identical
dataset = 'CPS'
dumping = cps_dump
for year in range(0, num_years):
cyr = year + kwargs['start_year']
do_dump = bool(dumping and cyr >= 2019 and cyr <= 2020)
col = '0_{}'.format(year)
for tbl in ['aggr_1', 'aggr_2', 'aggr_d']:
tbi = tbi_res[cyr][tbl][col]
if do_dump:
txt = 'DUMP of {} {} table for year {}:'
print(txt.format(dataset, tbl, cyr))
print(tbi)
std = std_res[cyr][tbl][col]
if not np.allclose(tbi, std, atol=0.0, rtol=reltol):
no_diffs = False
txt = '***** {} diff in {} table for year {} (year_n={}):'
print(txt.format(dataset, tbl, cyr, year))
print('TBI RESULTS:')
print(tbi)
print('STD RESULTS:')
print(std)
assert no_diffs
assert not dumping
def test_agg(tests_path, puf_fullsample):
"""
Test Tax-Calculator aggregate taxes with no policy reform using
the full-sample puf.csv and a small sub-sample of puf.csv
"""
# pylint: disable=too-many-locals,too-many-statements
nyrs = 10
# create a baseline Policy object containing 2017_law.json parameters
pre_tcja_jrf = os.path.join(tests_path, '..', 'reforms', '2017_law.json')
pre_tcja = Calculator.read_json_param_objects(pre_tcja_jrf, None)
baseline_policy = Policy()
baseline_policy.implement_reform(pre_tcja['policy'])
# create a Records object (rec) containing all puf.csv input records
rec = Records(data=puf_fullsample)
# create a Calculator object using baseline policy and puf records
calc = Calculator(policy=baseline_policy, records=rec)
calc_start_year = calc.current_year
# create aggregate diagnostic table (adt) as a Pandas DataFrame object
adt = calc.diagnostic_table(nyrs)
taxes_fullsample = adt.loc["Combined Liability ($b)"]
# convert adt results to a string with a trailing EOL character
adtstr = adt.to_string() + '\n'
# create actual and expected lists of diagnostic table lines
actual = adtstr.splitlines(True)
aggres_path = os.path.join(tests_path, 'pufcsv_agg_expect.txt')
with open(aggres_path, 'r') as expected_file:
txt = expected_file.read()
expected_results = txt.rstrip('\n\t ') + '\n' # cleanup end of file txt
expect = expected_results.splitlines(True)
# ensure actual and expect lines have differences no more than small value
if sys.version_info.major == 2:
small = 0.0 # tighter test for Python 2.7
else:
small = 0.1 # looser test for Python 3.6
diffs = nonsmall_diffs(actual, expect, small)
if diffs:
new_filename = '{}{}'.format(aggres_path[:-10], 'actual.txt')
with open(new_filename, 'w') as new_file:
new_file.write(adtstr)
msg = 'PUFCSV AGG RESULTS DIFFER FOR FULL-SAMPLE\n'
msg += '-------------------------------------------------\n'
msg += '--- NEW RESULTS IN pufcsv_agg_actual.txt FILE ---\n'
msg += '--- if new OK, copy pufcsv_agg_actual.txt to ---\n'
msg += '--- pufcsv_agg_expect.txt ---\n'
msg += '--- and rerun test. ---\n'
msg += '-------------------------------------------------\n'
raise ValueError(msg)
# create aggregate diagnostic table using unweighted sub-sample of records
fullsample = puf_fullsample
rn_seed = 180 # to ensure sub-sample is always the same
subfrac = 0.05 # sub-sample fraction
subsample = fullsample.sample(frac=subfrac, random_state=rn_seed)
rec_subsample = Records(data=subsample)
calc_subsample = Calculator(policy=baseline_policy, records=rec_subsample)
adt_subsample = calc_subsample.diagnostic_table(nyrs)
# compare combined tax liability from full and sub samples for each year
taxes_subsample = adt_subsample.loc["Combined Liability ($b)"]
reltol = 0.01 # maximum allowed relative difference in tax liability
if not np.allclose(taxes_subsample, taxes_fullsample,
atol=0.0, rtol=reltol):
msg = 'PUFCSV AGG RESULTS DIFFER IN SUB-SAMPLE AND FULL-SAMPLE\n'
msg += 'WHEN subfrac={:.3f}, rtol={:.4f}, seed={}\n'.format(subfrac,
reltol,
rn_seed)
it_sub = np.nditer(taxes_subsample, flags=['f_index'])
it_all = np.nditer(taxes_fullsample, flags=['f_index'])
while not it_sub.finished:
cyr = it_sub.index + calc_start_year
tax_sub = float(it_sub[0])
tax_all = float(it_all[0])
reldiff = abs(tax_sub - tax_all) / abs(tax_all)
if reldiff > reltol:
msgstr = ' year,sub,full,reldiff= {}\t{:.2f}\t{:.2f}\t{:.4f}\n'
msg += msgstr.format(cyr, tax_sub, tax_all, reldiff)
it_sub.iternext()
it_all.iternext()
raise ValueError(msg)
def test_mtr(tests_path, puf_path):
"""
Test Tax-Calculator marginal tax rates with no policy reform using puf.csv
Compute histograms for each marginal tax rate income type using
sample input from the puf.csv file and writing output to a string,
which is then compared for differences with EXPECTED_MTR_RESULTS.
"""
# pylint: disable=too-many-locals,too-many-statements
assert len(PTAX_MTR_BIN_EDGES) == len(ITAX_MTR_BIN_EDGES)
# construct actual results string, res
res = ''
if MTR_NEG_DIFF:
res += 'MTR computed using NEGATIVE finite_diff '
else:
res += 'MTR computed using POSITIVE finite_diff '
res += 'for tax year {}\n'.format(MTR_TAX_YEAR)
# create a Policy object (clp) containing current-law policy parameters
clp = Policy()
clp.set_year(MTR_TAX_YEAR)
# create a Records object (puf) containing puf.csv input records
puf = Records(data=puf_path)
recid = puf.RECID # pylint: disable=no-member
# create a Calculator object using clp policy and puf records
calc = Calculator(policy=clp, records=puf)
res += '{} = {}\n'.format('Total number of data records', puf.array_length)
res += 'PTAX mtr histogram bin edges:\n'
res += ' {}\n'.format(PTAX_MTR_BIN_EDGES)
res += 'ITAX mtr histogram bin edges:\n'
res += ' {}\n'.format(ITAX_MTR_BIN_EDGES)
variable_header = 'PTAX and ITAX mtr histogram bin counts for'
# compute marginal tax rate (mtr) histograms for each mtr variable
for var_str in Calculator.MTR_VALID_VARIABLES:
zero_out = (var_str == 'e01400')
(mtr_ptax, mtr_itax, _) = calc.mtr(variable_str=var_str,
negative_finite_diff=MTR_NEG_DIFF,
zero_out_calculated_vars=zero_out,
wrt_full_compensation=False)
if zero_out:
# check that calculated variables are consistent
assert np.allclose((calc.array('iitax') +
calc.array('payrolltax')),
calc.array('combined'))
assert np.allclose((calc.array('ptax_was') +
calc.array('setax') +
calc.array('ptax_amc')),
calc.array('payrolltax'))
assert np.allclose(calc.array('c21060') - calc.array('c21040'),
calc.array('c04470'))
assert np.allclose(calc.array('taxbc') + calc.array('c09600'),
calc.array('c05800'))
assert np.allclose((calc.array('c05800') +
calc.array('othertaxes') -
calc.array('c07100')),
calc.array('c09200'))
assert np.allclose(calc.array('c09200') - calc.array('refund'),
calc.array('iitax'))
if var_str == 'e00200s':
# only MARS==2 filing units have valid MTR values
mtr_ptax = mtr_ptax[calc.array('MARS') == 2]
mtr_itax = mtr_itax[calc.array('MARS') == 2]
res += '{} {}:\n'.format(variable_header, var_str)
res += mtr_bin_counts(mtr_ptax, PTAX_MTR_BIN_EDGES, recid)
res += mtr_bin_counts(mtr_itax, ITAX_MTR_BIN_EDGES, recid)
# check for differences between actual and expected results
mtrres_path = os.path.join(tests_path, 'pufcsv_mtr_expect.txt')
with open(mtrres_path, 'r') as expected_file:
txt = expected_file.read()
expected_results = txt.rstrip('\n\t ') + '\n' # cleanup end of file txt
if nonsmall_diffs(res.splitlines(True), expected_results.splitlines(True)):
new_filename = '{}{}'.format(mtrres_path[:-10], 'actual.txt')
with open(new_filename, 'w') as new_file:
new_file.write(res)
msg = 'PUFCSV MTR RESULTS DIFFER\n'
msg += '-------------------------------------------------\n'
msg += '--- NEW RESULTS IN pufcsv_mtr_actual.txt FILE ---\n'
msg += '--- if new OK, copy pufcsv_mtr_actual.txt to ---\n'
msg += '--- pufcsv_mtr_expect.txt ---\n'
msg += '--- and rerun test. ---\n'
msg += '-------------------------------------------------\n'
raise ValueError(msg)
def test_2017_law_reform():
"""
Check that policy parameter values in a future year under current-law
policy and under the reform specified in the 2017_law.json file are
sensible.
"""
# create pre metadata dictionary for 2017_law.json reform in fyear
pol = Policy()
reform_file = os.path.join(CUR_PATH, '..', 'taxcalc', '2017_law.json')
with open(reform_file, 'r') as rfile:
rtext = rfile.read()
pol.implement_reform(Policy.read_json_reform(rtext))
assert not pol.parameter_warnings
pol.set_year(2018)
pre_mdata = dict(pol.items())
# check some policy parameter values against expected values under 2017 law
pre_expect = {
# relation '<' implies asserting that actual < expect
# relation '>' implies asserting that actual > expect
# ... parameters not affected by TCJA and that are not indexed
'AMEDT_ec': {
'relation': '=',
'value': 200000
},
'SS_thd85': {
'relation': '=',
'value': 34000
},
# ... parameters not affected by TCJA and that are indexed
'STD_Dep': {
'relation': '>',
'value': 1050
},
'CG_brk2': {
'relation': '>',
'value': 425800
},
'AMT_CG_brk1': {
'relation': '>',
'value': 38600
},
'AMT_brk1': {
'relation': '>',
'value': 191100
},
'EITC_c': {
'relation': '>',
'value': 519
},
'EITC_ps': {
'relation': '>',
'value': 8490
},
'EITC_ps_MarriedJ': {
'relation': '>',
'value': 5680
},
'EITC_InvestIncome_c': {
'relation': '>',
'value': 3500
},
# ... parameters affected by TCJA and that are not indexed
'ID_Charity_crt_all': {
'relation': '=',
'value': 0.5
},
'II_rt3': {
'relation': '=',
'value': 0.25
},
# ... parameters affected by TCJA and that are indexed
'II_brk3': {
'relation': '>',
'value': 91900
},
'STD': {
'relation': '<',
'value': 7000
},
'II_em': {
'relation': '>',
'value': 4050
},
'AMT_em_pe': {
'relation': '<',
'value': 260000
}
}
assert isinstance(pre_expect, dict)
assert set(pre_expect.keys()).issubset(set(pre_mdata.keys()))
for name in pre_expect:
aval = pre_mdata[name]
if aval.ndim == 2:
act = aval[0][0] # comparing only first item in a vector parameter
else:
act = aval[0]
exp = pre_expect[name]['value']
if pre_expect[name]['relation'] == '<':
assert act < exp, '{} a={} !< e={}'.format(name, act, exp)
elif pre_expect[name]['relation'] == '>':
assert act > exp, '{} a={} !> e={}'.format(name, act, exp)
elif pre_expect[name]['relation'] == '=':
assert act == exp, '{} a={} != e={}'.format(name, act, exp)
def test_round_trip_tcja_reform():
"""
Check that current-law policy has the same policy parameter values in
a future year as does a compound reform that first implements the
reform specified in the 2017_law.json file and then implements the
reform specified in the TCJA.json file. This test checks that the
future-year parameter values for current-law policy (which incorporates
TCJA) are the same as future-year parameter values for the compound
round-trip reform. Doing this check ensures that the 2017_law.json
and TCJA.json reform files are specified in a consistent manner.
"""
# pylint: disable=too-many-locals
fyear = 2020
# create clp metadata dictionary for current-law policy in fyear
pol = Policy()
pol.set_year(fyear)
clp_mdata = dict(pol.items())
# create rtr metadata dictionary for round-trip reform in fyear
pol = Policy()
reform_file = os.path.join(CUR_PATH, '..', 'taxcalc', '2017_law.json')
with open(reform_file, 'r') as rfile:
rtext = rfile.read()
pol.implement_reform(Policy.read_json_reform(rtext))
assert not pol.parameter_warnings
assert not pol.errors
reform_file = os.path.join(CUR_PATH, '..', 'taxcalc', 'TCJA.json')
with open(reform_file, 'r') as rfile:
rtext = rfile.read()
pol.implement_reform(Policy.read_json_reform(rtext))
assert not pol.parameter_warnings
assert not pol.errors
pol.set_year(fyear)
rtr_mdata = dict(pol.items())
# compare fyear policy parameter values
assert clp_mdata.keys() == rtr_mdata.keys()
fail_dump = False
if fail_dump:
rtr_fails = open('fails_rtr', 'w')
clp_fails = open('fails_clp', 'w')
fail_params = list()
msg = '\nRound-trip-reform and current-law-policy param values differ for:'
for pname in clp_mdata.keys():
rtr_val = rtr_mdata[pname]
clp_val = clp_mdata[pname]
if not np.allclose(rtr_val, clp_val):
fail_params.append(pname)
msg += '\n {} in {} : rtr={} clp={}'.format(
pname, fyear, rtr_val, clp_val)
if fail_dump:
rtr_fails.write('{} {} {}\n'.format(pname, fyear, rtr_val))
clp_fails.write('{} {} {}\n'.format(pname, fyear, clp_val))
if fail_dump:
rtr_fails.close()
clp_fails.close()
if fail_params:
raise ValueError(msg)
def test_make_Calculator_deepcopy(records_2009):
parm = Policy()
calc1 = Calculator(policy=parm, records=records_2009)
calc2 = copy.deepcopy(calc1)
assert isinstance(calc2, Calculator)
def test_benefits(tests_path, cps_fullsample):
"""
Test CPS benefits.
"""
# pylint: disable=too-many-locals
benefit_names = [
'ssi', 'mcare', 'mcaid', 'snap', 'wic', 'tanf', 'vet', 'housing'
]
# write benefits_actual.csv file
recs = Records.cps_constructor(data=cps_fullsample)
start_year = recs.current_year
calc = Calculator(policy=Policy(), records=recs, verbose=False)
assert calc.current_year == start_year
year_list = list()
bname_list = list()
benamt_list = list()
bencnt_list = list()
benavg_list = list()
for year in range(start_year, Policy.LAST_BUDGET_YEAR + 1):
calc.advance_to_year(year)
size = calc.array('XTOT')
wght = calc.array('s006')
# compute benefit aggregate amounts and head counts and average benefit
# (head counts include all members of filing unit receiving a benefit,
# which means benavg is f.unit benefit amount divided by f.unit size)
for bname in benefit_names:
ben = calc.array('{}_ben'.format(bname))
benamt = round((ben * wght).sum() * 1e-9, 3)
bencnt = round((size[ben > 0] * wght[ben > 0]).sum() * 1e-6, 3)
benavg = round(benamt / bencnt, 1)
year_list.append(year)
bname_list.append(bname)
benamt_list.append(benamt)
bencnt_list.append(bencnt)
benavg_list.append(benavg)
adict = {
'year': year_list,
'bname': bname_list,
'benamt': benamt_list,
'bencnt': bencnt_list,
'benavg': benavg_list
}
adf = pd.DataFrame(data=adict,
columns=['year', 'bname', 'benamt', 'bencnt', 'benavg'])
ben_act_path = os.path.join(tests_path, 'benefits_actual.csv')
adf.to_csv(ben_act_path, index=False)
# read benefits_expect.csv file
ben_exp_path = os.path.join(tests_path, 'benefits_expect.csv')
edf = pd.read_csv(ben_exp_path)
# compare benefit information
atol = 0.0001
rtol = 0.0
diffs = False
for col in ['benamt', 'bencnt', 'benavg']:
if not np.allclose(adf[col], edf[col], atol=atol, rtol=rtol):
diffs = True
if diffs:
msg = 'CPS BENEFITS RESULTS DIFFER\n'
msg += '-------------------------------------------------\n'
msg += '--- NEW RESULTS IN benefits_actual.txt FILE ---\n'
msg += '--- if new OK, copy benefits_actual.txt to ---\n'
msg += '--- benefits_expect.txt ---\n'
msg += '--- and rerun test. ---\n'
msg += '-------------------------------------------------\n'
raise ValueError(msg)
else:
os.remove(ben_act_path)
def test_validate_param_values_warnings_errors():
"""
Check detection of out_of_range policy parameters in reforms.
"""
pol1 = Policy()
ref1 = {2020: {'_ID_Medical_frt': [0.05]}}
pol1.implement_reform(ref1)
assert len(pol1.reform_warnings) > 0
pol2 = Policy()
ref2 = {2021: {'_ID_Charity_crt_all': [0.61]}}
pol2.implement_reform(ref2)
assert len(pol2.reform_warnings) > 0
pol3 = Policy()
ref3 = {2024: {'_II_brk4': [[0, 0, 0, 0, 0]]}}
pol3.implement_reform(ref3)
assert len(pol3.reform_errors) > 0
pol4 = Policy()
ref4 = {2024: {'_II_brk4': [[0, 9e9, 0, 0, 0]]}}
pol4.implement_reform(ref4)
assert len(pol4.reform_errors) > 0
pol5 = Policy()
ref5 = {2025: {'_ID_BenefitSurtax_Switch': [[False, True, 0, 1, 0, 1, 0]]}}
pol5.implement_reform(ref5)
assert len(pol5.reform_errors) == 0
pol6 = Policy()
ref6 = {2013: {'_STD': [[20000, 25000, 20000, 20000, 25000]]}}
pol6.implement_reform(ref6)
assert pol6.reform_errors == ''
assert pol6.reform_warnings == ''
def test_validate_param_names_types_errors():
"""
Check detection of invalid policy parameter names and types in reforms.
"""
pol0 = Policy()
ref0 = {2020: {'_STD_cpi': 2}}
with pytest.raises(ValueError):
pol0.implement_reform(ref0)
pol1 = Policy()
ref1 = {2020: {'_badname_cpi': True}}
with pytest.raises(ValueError):
pol1.implement_reform(ref1)
pol2 = Policy()
ref2 = {2020: {'_II_em_cpi': 5}}
with pytest.raises(ValueError):
pol2.implement_reform(ref2)
pol3 = Policy()
ref3 = {2020: {'_badname': [0.4]}}
with pytest.raises(ValueError):
pol3.implement_reform(ref3)
pol4 = Policy()
ref4 = {2020: {'_EITC_MinEligAge': [21.4]}}
with pytest.raises(ValueError):
pol4.implement_reform(ref4)
pol5 = Policy()
ref5 = {2025: {'_ID_BenefitSurtax_Switch': [[False, True, 0, 2, 0, 1, 0]]}}
with pytest.raises(ValueError):
pol5.implement_reform(ref5)
pol6 = Policy()
ref6 = {2021: {'_II_em': ['not-a-number']}}
with pytest.raises(ValueError):
pol6.implement_reform(ref6)
def test_correct_Policy_instantiation():
pol = Policy()
assert pol
pol.implement_reform({})
with pytest.raises(ValueError):
pol.implement_reform(list())
with pytest.raises(ValueError):
pol.implement_reform({2099: {'_II_em': [99000]}})
pol.set_year(2019)
with pytest.raises(ValueError):
pol.implement_reform({2018: {'_II_em': [99000]}})
def test_multi_year_reform():
"""
Test multi-year reform involving 1D and 2D parameters.
"""
# specify dimensions of policy Policy object
syr = 2013
nyrs = Policy.DEFAULT_NUM_YEARS
pol = Policy(start_year=syr)
iratelist = pol.inflation_rates()
ifactor = {}
for i in range(0, nyrs):
ifactor[syr + i] = 1.0 + iratelist[i]
wratelist = pol.wage_growth_rates()
wfactor = {}
for i in range(0, nyrs):
wfactor[syr + i] = 1.0 + wratelist[i]
# confirm that parameters have current-law values
assert_allclose(getattr(pol, '_EITC_c'),
Policy._expand_array(np.array(
[[487, 3250, 5372, 6044], [496, 3305, 5460, 6143],
[503, 3359, 5548, 6242], [506, 3373, 5572, 6269],
[510, 3400, 5616, 6318]],
dtype=np.float64),
False,
inflate=True,
inflation_rates=iratelist,
num_years=nyrs),
atol=0.01,
rtol=0.0)
assert_allclose(getattr(pol, '_STD_Dep'),
Policy._expand_array(np.array(
[1000, 1000, 1050, 1050, 1050], dtype=np.float64),
False,
inflate=True,
inflation_rates=iratelist,
num_years=nyrs),
atol=0.01,
rtol=0.0)
assert_allclose(getattr(pol, '_CTC_c'),
Policy._expand_array(np.array([1000] * 5 + [1400] * 4 +
[1500] * 3 + [1600] + [1000],
dtype=np.float64),
False,
inflate=False,
inflation_rates=iratelist,
num_years=nyrs),
atol=0.01,
rtol=0.0)
# this parameter uses a different indexing rate
assert_allclose(getattr(pol, '_SS_Earnings_c'),
Policy._expand_array(np.array(
[113700, 117000, 118500, 118500, 127200],
dtype=np.float64),
False,
inflate=True,
inflation_rates=wratelist,
num_years=nyrs),
atol=0.01,
rtol=0.0)
# specify multi-year reform using a dictionary of year_provisions dicts
reform = {
2015: {
'_CTC_c': [2000]
},
2016: {
'_EITC_c': [[900, 5000, 8000, 9000]],
'_II_em': [7000],
'_SS_Earnings_c': [300000]
},
2017: {
'_SS_Earnings_c': [500000],
'_SS_Earnings_c_cpi': False
},
2019: {
'_EITC_c': [[1200, 7000, 10000, 12000]],
'_II_em': [9000],
'_SS_Earnings_c': [700000],
'_SS_Earnings_c_cpi': True
}
}
# implement multi-year reform
pol.implement_reform(reform)
assert pol.current_year == syr
# move policy Policy object forward in time so current_year is syr+2
# Note: this would be typical usage because the first budget year
# is greater than Policy start_year.
pol.set_year(pol.start_year + 2)
assert pol.current_year == syr + 2
# confirm that actual parameters have expected post-reform values
check_eitc_c(pol, reform, ifactor)
check_ii_em(pol, reform, ifactor)
check_ss_earnings_c(pol, reform, wfactor)
check_ctc_c(pol, reform)
def run():
"""
Execute Calculator.calc_all() method using 'puf.csv' input and
writing truncated ouput to a CSV file named 'results_puf.csv'.
"""
# create a Policy object containing current-law policy (clp) parameters
clp = Policy()
# create a Records object (puf) containing puf.csv input records
puf = Records()
# create a Calculator object using clp policy and puf records
calc = Calculator(policy=clp, records=puf)
calc.calc_all()
rshape = calc.records.e00100.shape
dataf = pd.DataFrame()
for attr in dir(calc.records):
value = getattr(calc.records, attr)
if hasattr(value, "shape"):
if value.shape == rshape:
dataf[attr] = value
# truncate the outputs
col_names = ['EICYB1', 'EICYB2', 'EICYB3', 'NIIT', '_addamt', '_addtax',
'_agep', '_ages', '_agierr', '_alminc', '_amed', '_amt15pc',
'_amt20pc', '_amt25pc', '_amt5pc', '_amtfei', '_amtsepadd',
'_amtstd', '_avail', '_cglong', '_cmbtp', '_comb',
'_combined', '_ctc1', '_ctc2', '_ctcagi', '_ctctax', '_dclim',
'_dwks12', '_dwks16', '_dwks17', '_dwks21', '_dwks25',
'_dwks26', '_dwks28', '_dwks31', '_dwks5', '_dwks9', '_dy',
'_earned', '_eitc', '_exocrd', '_expanded_income', '_feided',
'_feitax', '_fica', '_hasgain', '_ieic', 'c03260',
'_limitratio', '_line17', '_line19', '_line22', '_line30',
'_line31', '_line32', '_line33', '_line34', '_line35',
'_line36', '_modagi', '_nctcr', '_ncu13', '_ngamty', '_noncg',
'_nonlimited', '_num', '_numextra', '_oldfei', '_othadd',
'_othded', '_othertax', '_othtax', '_parents', '_phase2_i',
'_posagi', '_precrd', '_preeitc', '_prexmp', '_refund',
'_regcrd', '_s1291', '_sep', '_sey', 'c09400', 'c03260',
'_seywage', '_standard', '_statax', '_tamt2', '_taxbc',
'_taxinc', '_taxspecial', '_tratio', '_txpyers',
'_val_rtbase', '_val_rtless', '_val_ymax', '_xyztax', '_ymod',
'_ymod1', '_ymod2', '_ymod3', '_ywossbc', '_ywossbe',
'c00100', 'c01000', 'c02500', 'c02650', 'c02700', 'c02900',
'c04100', 'c04200', 'c04470', 'c04500', 'c04600', 'c04800',
'c05100', 'c05200', 'c05700', 'c05750', 'c05800', 'c07100',
'c07150', 'c07180', 'c07220', 'c07230', 'c07240', 'c07300',
'c07600', 'c07970', 'c08795', 'c08800', 'c09200', 'c09600',
'c10300', 'c10950', 'c10960', 'c11055', 'c11070', 'c15100',
'c15200', 'c17000', 'c17750', 'c18300', 'c19200', 'c19700',
'c20400', 'c20500', 'c20750', 'c20800', 'c21040', 'c21060',
'c23650', 'c24505', 'c24510', 'c24516', 'c24517', 'c24520',
'c24530', 'c24534', 'c24540', 'c24550', 'c24560', 'c24570',
'c24580', 'c24597', 'c24598', 'c24610', 'c24615', 'c32800',
'c32840', 'c32880', 'c32890', 'c33000', 'c33200', 'c33400',
'c33465', 'c33470', 'c33475', 'c33480', 'c37703', 'c59430',
'c59450', 'c59460', 'c59485', 'c59490', 'c59560', 'c59660',
'c59680', 'c59700', 'c59720', 'c60000', 'c60130', 'c60200',
'c60220', 'c60240', 'c60260', 'c62100', 'c62100_everyone',
'c62600', 'c62700', 'c62720', 'c62730', 'c62740', 'c62745',
'c62747', 'c62755', 'c62760', 'c62770', 'c62780', 'c62800',
'c62900', 'c63000', 'c63100', 'c82880', 'c82885', 'c82890',
'c82900', 'c82905', 'c82910', 'c82915', 'c82920', 'c82925',
'c82930', 'c82935', 'c82937', 'c82940', 'c87482', 'c87483',
'c87487', 'c87488', 'c87492', 'c87493', 'c87497', 'c87498',
'c87521', 'c87530', 'c87540', 'c87550', 'c87560', 'c87570',
'c87580', 'c87590', 'c87600', 'c87610', 'c87620', 'c87654',
'c87656', 'c87658', 'c87660', 'c87662', 'c87664', 'c87666',
'c87668', 'c87681', 'e00650', 'e02500', 'e08795', 'h82880',
'x04500', 'x07100', 'y07100', 'y62745']
dataf_truncated = dataf[col_names]
# write test output to csv file named 'results_puf.csv'
dataf_truncated.to_csv('results_puf.csv', float_format='%1.3f', sep=',',
header=True, index=False)
def test_implement_reform_Policy_raises_on_no_year():
reform = {'_STD_Aged': [[1400, 1200]]}
ppo = Policy()
with pytest.raises(ValueError):
ppo.implement_reform(reform)
def test_implement_reform_Policy_raises_on_future_year():
ppo = Policy(start_year=2013)
with pytest.raises(ValueError):
reform = {2010: {'_STD_Aged': [[1400, 1100, 1100, 1400, 1400, 1199]]}}
ppo.implement_reform(reform)
def test_Calculator_attr_access_to_policy(records_2009):
policy = Policy()
calc = Calculator(policy=policy, records=records_2009)
assert hasattr(calc.records, 'c01000')
assert hasattr(calc.policy, '_AMT_Child_em')
assert hasattr(calc, 'policy')
def test_reform_json_and_output():
"""
Check that each JSON reform file can be converted into a reform dictionary
that can then be passed to the Policy class implement_reform method that
generates no parameter_errors.
Then use each reform to generate static tax results for small set of
filing units in a single tax_year and compare those results with
expected results from a CSV-formatted file.
"""
# pylint: disable=too-many-statements,too-many-locals
# embedded function used only in test_reform_json_and_output
def write_res_file(calc, resfilename):
"""
Write calc output to CSV-formatted file with resfilename.
"""
varlist = [
'RECID', 'c00100', 'standard', 'c04800', 'iitax', 'payrolltax'
]
# varnames AGI STD TaxInc ITAX PTAX
stats = calc.dataframe(varlist)
stats['RECID'] = stats['RECID'].astype(int)
with open(resfilename, 'w') as resfile:
stats.to_csv(resfile, index=False, float_format='%.2f')
# embedded function used only in test_reform_json_and_output
def res_and_out_are_same(base):
"""
Return True if base.res.csv and base.out.csv file contents are same;
return False if base.res.csv and base.out.csv file contents differ.
"""
resdf = pd.read_csv(base + '.res.csv')
outdf = pd.read_csv(base + '.out.csv')
diffs = False
for col in resdf:
if col in outdf:
if not np.allclose(resdf[col], outdf[col]):
diffs = True
else:
diffs = True
return not diffs
# specify Records object containing cases data
tax_year = 2020
cases_path = os.path.join(CUR_PATH, '..', 'taxcalc', 'cases.csv')
cases = Records(
data=cases_path,
start_year=tax_year, # set raw input data year
gfactors=None, # keeps raw data unchanged
weights=None,
adjust_ratios=None)
# specify list of reform failures
failures = list()
# specify current-law-policy Calculator object
calc = Calculator(policy=Policy(), records=cases, verbose=False)
calc.advance_to_year(tax_year)
calc.calc_all()
res_path = cases_path.replace('cases.csv', 'clp.res.csv')
write_res_file(calc, res_path)
if res_and_out_are_same(res_path.replace('.res.csv', '')):
os.remove(res_path)
else:
failures.append(res_path)
del calc
# read 2017_law.json reform file and specify its parameters dictionary
pre_tcja_jrf = os.path.join(CUR_PATH, '..', 'taxcalc', '2017_law.json')
pre_tcja = Policy.read_json_reform(pre_tcja_jrf)
# check reform file contents and reform results for each reform
reforms_path = os.path.join(CUR_PATH, '..', 'taxcalc', '*.json')
json_reform_files = glob.glob(reforms_path)
for jrf in json_reform_files:
# determine reform's baseline by reading contents of jrf
with open(jrf, 'r') as rfile:
jrf_text = rfile.read()
pre_tcja_baseline = 'Reform_Baseline: 2017_law.json' in jrf_text
# implement the reform relative to its baseline
reform = Policy.read_json_reform(jrf_text)
pol = Policy() # current-law policy
if pre_tcja_baseline:
pol.implement_reform(pre_tcja)
assert not pol.parameter_errors
pol.implement_reform(reform)
assert not pol.parameter_errors
calc = Calculator(policy=pol, records=cases, verbose=False)
calc.advance_to_year(tax_year)
calc.calc_all()
res_path = jrf.replace('.json', '.res.csv')
write_res_file(calc, res_path)
if res_and_out_are_same(res_path.replace('.res.csv', '')):
os.remove(res_path)
else:
failures.append(res_path)
del calc
if failures:
msg = 'Following reforms have res-vs-out differences:\n'
for ref in failures:
msg += '{}\n'.format(os.path.basename(ref))
raise ValueError(msg)
def test_Calculator_create_diagnostic_table(records_2009):
calc = Calculator(policy=Policy(), records=records_2009)
calc.calc_all()
adt = create_diagnostic_table(calc)
assert isinstance(adt, pd.DataFrame)
def fixture_baseline_2017_law():
"""
Read ../taxcalc/2017_law.json and return its policy dictionary.
"""
pre_tcja_jrf = os.path.join(CUR_PATH, '..', 'taxcalc', '2017_law.json')
return Policy.read_json_reform(pre_tcja_jrf)
def calculator_objects(year_n, start_year,
use_puf_not_cps,
use_full_sample,
user_mods,
behavior_allowed):
"""
This function assumes that the specified user_mods is a dictionary
returned by the Calculator.read_json_param_objects() function.
This function returns (calc1, calc2) where
calc1 is pre-reform Calculator object calculated for year_n, and
calc2 is post-reform Calculator object calculated for year_n.
Set behavior_allowed to False when generating static results or
set behavior_allowed to True when generating dynamic results.
"""
# pylint: disable=too-many-arguments,too-many-locals
# pylint: disable=too-many-branches,too-many-statements
check_user_mods(user_mods)
# specify Consumption instance
consump = Consumption()
consump_assumptions = user_mods['consumption']
consump.update_consumption(consump_assumptions)
# specify growdiff_baseline and growdiff_response
growdiff_baseline = GrowDiff()
growdiff_response = GrowDiff()
growdiff_base_assumps = user_mods['growdiff_baseline']
growdiff_resp_assumps = user_mods['growdiff_response']
growdiff_baseline.update_growdiff(growdiff_base_assumps)
growdiff_response.update_growdiff(growdiff_resp_assumps)
# create pre-reform and post-reform GrowFactors instances
growfactors_pre = GrowFactors()
growdiff_baseline.apply_to(growfactors_pre)
growfactors_post = GrowFactors()
growdiff_baseline.apply_to(growfactors_post)
growdiff_response.apply_to(growfactors_post)
# create sample pd.DataFrame from specified input file and sampling scheme
tbi_path = os.path.abspath(os.path.dirname(__file__))
if use_puf_not_cps:
# first try TaxBrain deployment path
input_path = 'puf.csv.gz'
if not os.path.isfile(input_path):
# otherwise try local Tax-Calculator deployment path
input_path = os.path.join(tbi_path, '..', '..', 'puf.csv')
sampling_frac = 0.05
sampling_seed = 2222
else: # if using cps input not puf input
# first try Tax-Calculator code path
input_path = os.path.join(tbi_path, '..', 'cps.csv.gz')
if not os.path.isfile(input_path):
# otherwise read from taxcalc package "egg"
input_path = None # pragma: no cover
full_sample = read_egg_csv('cps.csv.gz') # pragma: no cover
sampling_frac = 0.03
sampling_seed = 180
if input_path:
full_sample = pd.read_csv(input_path)
if use_full_sample:
sample = full_sample
else:
sample = full_sample.sample(frac=sampling_frac,
random_state=sampling_seed)
# create pre-reform Calculator instance
if use_puf_not_cps:
recs1 = Records(data=sample,
gfactors=growfactors_pre)
else:
recs1 = Records.cps_constructor(data=sample,
gfactors=growfactors_pre)
policy1 = Policy(gfactors=growfactors_pre)
calc1 = Calculator(policy=policy1, records=recs1, consumption=consump)
while calc1.current_year < start_year:
calc1.increment_year()
calc1.calc_all()
assert calc1.current_year == start_year
# specify Behavior instance
behv = Behavior()
behavior_assumps = user_mods['behavior']
behv.update_behavior(behavior_assumps)
# always prevent both behavioral response and growdiff response
if behv.has_any_response() and growdiff_response.has_any_response():
msg = 'BOTH behavior AND growdiff_response HAVE RESPONSE'
raise ValueError(msg)
# optionally prevent behavioral response
if behv.has_any_response() and not behavior_allowed:
msg = 'A behavior RESPONSE IS NOT ALLOWED'
raise ValueError(msg)
# create post-reform Calculator instance
if use_puf_not_cps:
recs2 = Records(data=sample,
gfactors=growfactors_post)
else:
recs2 = Records.cps_constructor(data=sample,
gfactors=growfactors_post)
policy2 = Policy(gfactors=growfactors_post)
policy_reform = user_mods['policy']
policy2.implement_reform(policy_reform)
calc2 = Calculator(policy=policy2, records=recs2,
consumption=consump, behavior=behv)
while calc2.current_year < start_year:
calc2.increment_year()
assert calc2.current_year == start_year
# delete objects now embedded in calc1 and calc2
del sample
del full_sample
del consump
del growdiff_baseline
del growdiff_response
del growfactors_pre
del growfactors_post
del behv
del recs1
del recs2
del policy1
del policy2
# increment Calculator objects for year_n years and calculate
for _ in range(0, year_n):
calc1.increment_year()
calc2.increment_year()
calc1.calc_all()
if calc2.behavior_has_response():
calc2 = Behavior.response(calc1, calc2)
else:
calc2.calc_all()
# return calculated Calculator objects
return (calc1, calc2)
def test_mtr_pt_active(puf_subsample):
"""
Test whether including wages in active income causes
MTRs on e00900p and e26270 to be less than -1 (i.e., -100%)
"""
# pylint: disable=too-many-locals
rec = Records(data=puf_subsample)
reform_year = 2018
# create current-law Calculator object, calc1
pol1 = Policy()
calc1 = Calculator(policy=pol1, records=rec)
calc1.advance_to_year(reform_year)
calc1.calc_all()
mtr1_e00900p = calc1.mtr('e00900p')[2]
mtr1_e26270 = calc1.mtr('e26270')[2]
assert min(mtr1_e00900p) > -1
assert min(mtr1_e26270) > -1
# change PT rates, calc2
reform2 = {reform_year: {'_PT_rt7': [0.35]}}
pol2 = Policy()
pol2.implement_reform(reform2)
calc2 = Calculator(policy=pol2, records=rec)
calc2.advance_to_year(reform_year)
calc2.calc_all()
mtr2_e00900p = calc2.mtr('e00900p')[2]
mtr2_e26270 = calc2.mtr('e26270')[2]
assert min(mtr2_e00900p) > -1
assert min(mtr2_e26270) > -1
# change PT_wages_active_income
reform3 = {reform_year: {'_PT_wages_active_income': [True]}}
pol3 = Policy()
pol3.implement_reform(reform3)
calc3 = Calculator(policy=pol3, records=rec)
calc3.advance_to_year(reform_year)
calc3.calc_all()
mtr3_e00900p = calc3.mtr('e00900p')[2]
mtr3_e26270 = calc3.mtr('e26270')[2]
assert min(mtr3_e00900p) > -1
assert min(mtr3_e26270) > -1
# change PT rates and PT_wages_active_income
reform4 = {reform_year: {'_PT_wages_active_income': [True],
'_PT_rt7': [0.35]}}
pol4 = Policy()
pol4.implement_reform(reform4)
calc4 = Calculator(policy=pol4, records=rec)
calc4.advance_to_year(reform_year)
calc4.calc_all()
mtr4_e00900p = calc4.mtr('e00900p')[2]
mtr4_e26270 = calc4.mtr('e26270')[2]
assert min(mtr4_e00900p) > -1
assert min(mtr4_e26270) > -1
def convert_defaults(pcl):
'''
Function to convert default Tax-Calculator policy parameters to
ParamTools compliant parameters.
'''
type_map = {
"real": "float",
"boolean": "bool",
"integer": "int",
"string": "str",
}
new_pcl = defaultdict(dict)
new_pcl["schema"] = POLICY_SCHEMA
LAST_YEAR = TC_LAST_YEAR
pol = Policy()
pol.set_year(TC_LAST_YEAR)
for param, item in pcl.items():
values = []
pol_val = getattr(pol, f"_{param}").tolist()
min_year = min(item["value_yrs"])
if isinstance(pol_val[0], list):
for year in range(len(pol_val)):
if min_year + year > LAST_YEAR:
break
for dim1 in range(len(pol_val[0])):
values.append({
"year": min_year + year,
item["vi_name"]: item["vi_vals"][dim1],
"value": pol_val[year][dim1]
})
else:
for year in range(len(pol_val)):
if min_year + year > LAST_YEAR:
break
values.append({
"year": min_year + year,
"value": pol_val[year]
})
new_pcl[param]['value'] = values
new_pcl[param]['title'] = pcl[param]["long_name"]
new_pcl[param]['type'] = type_map[pcl[param]["value_type"]]
new_pcl[param]["validators"] = {"range": pcl[param]["valid_values"]}
# checkbox if indexable
if item["indexable"]:
if item["indexed"]:
new_pcl[param]["checkbox"] = True
else:
new_pcl[param]["checkbox"] = False
to_keep = list(POLICY_SCHEMA["additional_members"].keys()) + [
"description", "notes",
]
for k in to_keep:
if k in pcl[param]:
new_pcl[param][k] = pcl[param][k]
return new_pcl
def test_agg(tests_path, cps_fullsample):
"""
Test current-law aggregate taxes using cps.csv file.
"""
# pylint: disable=too-many-statements,too-many-locals
nyrs = 10
# create a baseline Policy object containing current law policy parameters
baseline_policy = Policy()
# create a Records object (rec) containing all cps.csv input records
recs = Records.cps_constructor(data=cps_fullsample)
# create a Calculator object using baseline policy and cps records
calc = Calculator(policy=baseline_policy, records=recs)
calc_start_year = calc.current_year
# create aggregate diagnostic table (adt) as a Pandas DataFrame object
adt = calc.diagnostic_table(nyrs)
taxes_fullsample = adt.loc["Combined Liability ($b)"]
# convert adt to a string with a trailing EOL character
actual_results = adt.to_string() + '\n'
# read expected results from file
aggres_path = os.path.join(tests_path, 'cpscsv_agg_expect.txt')
with open(aggres_path, 'r') as expected_file:
txt = expected_file.read()
expected_results = txt.rstrip('\n\t ') + '\n' # cleanup end of file txt
# ensure actual and expected results have no nonsmall differences
diffs = nonsmall_diffs(actual_results.splitlines(True),
expected_results.splitlines(True))
if diffs:
new_filename = '{}{}'.format(aggres_path[:-10], 'actual.txt')
with open(new_filename, 'w') as new_file:
new_file.write(actual_results)
msg = 'CPSCSV AGG RESULTS DIFFER\n'
msg += '-------------------------------------------------\n'
msg += '--- NEW RESULTS IN cpscsv_agg_actual.txt FILE ---\n'
msg += '--- if new OK, copy cpscsv_agg_actual.txt to ---\n'
msg += '--- cpscsv_agg_expect.txt ---\n'
msg += '--- and rerun test. ---\n'
msg += '-------------------------------------------------\n'
raise ValueError(msg)
# create aggregate diagnostic table using unweighted sub-sample of records
rn_seed = 180 # to ensure sub-sample is always the same
subfrac = 0.03 # sub-sample fraction
subsample = cps_fullsample.sample(frac=subfrac, random_state=rn_seed)
recs_subsample = Records.cps_constructor(data=subsample)
calc_subsample = Calculator(policy=baseline_policy, records=recs_subsample)
adt_subsample = calc_subsample.diagnostic_table(nyrs)
# compare combined tax liability from full and sub samples for each year
taxes_subsample = adt_subsample.loc["Combined Liability ($b)"]
msg = ''
for cyr in range(calc_start_year, calc_start_year + nyrs):
if cyr == calc_start_year:
reltol = 0.014
else:
reltol = 0.006
if not np.allclose(
taxes_subsample[cyr], taxes_fullsample[cyr], atol=0.0,
rtol=reltol):
reldiff = (taxes_subsample[cyr] / taxes_fullsample[cyr]) - 1.
line1 = '\nCPSCSV AGG SUB-vs-FULL RESULTS DIFFER IN {}'
line2 = '\n when subfrac={:.3f}, rtol={:.4f}, seed={}'
line3 = '\n with sub={:.3f}, full={:.3f}, rdiff={:.4f}'
msg += line1.format(cyr)
msg += line2.format(subfrac, reltol, rn_seed)
msg += line3.format(taxes_subsample[cyr], taxes_fullsample[cyr],
reldiff)
if msg:
raise ValueError(msg)
def test_multi_year_reform():
"""
Test multi-year reform involving 1D and 2D parameters.
"""
# specify dimensions of policy Policy object
syr = 2013
nyrs = 10
# specify assumed inflation rates
irates = {
2013: 0.02,
2014: 0.02,
2015: 0.02,
2016: 0.03,
2017: 0.03,
2018: 0.04,
2019: 0.04,
2020: 0.04,
2021: 0.04,
2022: 0.04
}
ifactor = {}
for i in range(0, nyrs):
ifactor[syr + i] = 1.0 + irates[syr + i]
iratelist = [irates[syr + i] for i in range(0, nyrs)]
# specify assumed inflation rates
wrates = {
2013: 0.0276,
2014: 0.0419,
2015: 0.0465,
2016: 0.0498,
2017: 0.0507,
2018: 0.0481,
2019: 0.0451,
2020: 0.0441,
2021: 0.0437,
2022: 0.0435
}
wfactor = {}
for i in range(0, nyrs):
wfactor[syr + i] = 1.0 + wrates[syr + i]
wratelist = [wrates[syr + i] for i in range(0, nyrs)]
# instantiate policy Policy object
ppo = Policy(start_year=syr,
num_years=nyrs,
inflation_rates=irates,
wage_growth_rates=wrates)
# confirm that parameters have current-law values
assert_allclose(getattr(ppo, '_AMT_thd_MarriedS'),
Policy.expand_array(np.array([40400, 41050]),
inflate=True,
inflation_rates=iratelist,
num_years=nyrs),
atol=0.01,
rtol=0.0)
assert_allclose(getattr(ppo, '_EITC_c'),
Policy.expand_array(np.array([[487, 3250, 5372, 6044],
[496, 3305, 5460, 6143],
[503, 3359, 5548, 6242],
[506, 3373, 5572, 6269]]),
inflate=True,
inflation_rates=iratelist,
num_years=nyrs),
atol=0.01,
rtol=0.0)
assert_allclose(getattr(ppo, '_II_em'),
Policy.expand_array(np.array([3900, 3950, 4000, 4050]),
inflate=True,
inflation_rates=iratelist,
num_years=nyrs),
atol=0.01,
rtol=0.0)
assert_allclose(getattr(ppo, '_CTC_c'),
Policy.expand_array(np.array([1000]),
inflate=False,
inflation_rates=iratelist,
num_years=nyrs),
atol=0.01,
rtol=0.0)
# this parameter uses a different inflating rate
assert_allclose(getattr(ppo, '_SS_Earnings_c'),
Policy.expand_array(np.array(
[113700, 117000, 118500, 118500]),
inflate=True,
inflation_rates=wratelist,
num_years=nyrs),
atol=0.01,
rtol=0.0)
# specify multi-year reform using a dictionary of year_provisions dicts
reform = {
2015: {
'_AMT_thd_MarriedS': [60000],
'_CTC_c': [2000]
},
2016: {
'_EITC_c': [[900, 5000, 8000, 9000]],
'_II_em': [7000],
'_SS_Earnings_c': [300000]
},
2017: {
'_AMT_thd_MarriedS': [80000],
'_SS_Earnings_c': [500000],
'_SS_Earnings_c_cpi': False
},
2019: {
'_EITC_c': [[1200, 7000, 10000, 12000]],
'_II_em': [9000],
'_SS_Earnings_c': [700000],
'_SS_Earnings_c_cpi': True
}
}
# implement multi-year reform
ppo.implement_reform(reform)
assert ppo.current_year == syr
# move policy Policy object forward in time so current_year is syr+2
# Note: this would be typical usage because the first budget year
# is greater than Policy start_year.
ppo.set_year(ppo.start_year + 2)
assert ppo.current_year == syr + 2
# confirm that actual parameters have expected post-reform values
check_amt_thd_marrieds(ppo, reform, ifactor)
check_eitc_c(ppo, reform, ifactor)
check_ii_em(ppo, reform, ifactor)
check_ss_earnings_c(ppo, reform, wfactor)
check_ctc_c(ppo, reform)
def test_behavioral_response(puf_subsample):
"""
Test that behavioral-response results are the same
when generated from standard Tax-Calculator calls and
when generated from tbi.run_nth_year_taxcalc_model() calls
"""
# specify reform and assumptions
reform_json = """
{"policy": {
"_II_rt5": {"2020": [0.25]},
"_II_rt6": {"2020": [0.25]},
"_II_rt7": {"2020": [0.25]},
"_PT_rt5": {"2020": [0.25]},
"_PT_rt6": {"2020": [0.25]},
"_PT_rt7": {"2020": [0.25]},
"_II_em": {"2020": [1000]}
}}
"""
assump_json = """
{"behavior": {"_BE_sub": {"2013": [0.25]}},
"growdiff_baseline": {},
"growdiff_response": {},
"consumption": {},
"growmodel": {}
}
"""
params = Calculator.read_json_param_objects(reform_json, assump_json)
# specify keyword arguments used in tbi function call
kwargs = {
'start_year': 2019,
'year_n': 0,
'use_puf_not_cps': True,
'use_full_sample': False,
'user_mods': {
'policy': params['policy'],
'behavior': params['behavior'],
'growdiff_baseline': params['growdiff_baseline'],
'growdiff_response': params['growdiff_response'],
'consumption': params['consumption'],
'growmodel': params['growmodel']
},
'return_dict': False
}
# generate aggregate results two ways: using tbi and standard calls
num_years = 9
std_res = dict()
tbi_res = dict()
for using_tbi in [True, False]:
for year in range(0, num_years):
cyr = year + kwargs['start_year']
if using_tbi:
kwargs['year_n'] = year
tables = run_nth_year_taxcalc_model(**kwargs)
tbi_res[cyr] = dict()
for tbl in ['aggr_1', 'aggr_2', 'aggr_d']:
tbi_res[cyr][tbl] = tables[tbl]
else:
rec = Records(data=puf_subsample)
pol = Policy()
calc1 = Calculator(policy=pol, records=rec)
pol.implement_reform(params['policy'])
assert not pol.parameter_errors
beh = Behavior()
beh.update_behavior(params['behavior'])
calc2 = Calculator(policy=pol, records=rec, behavior=beh)
assert calc2.behavior_has_response()
calc1.advance_to_year(cyr)
calc2.advance_to_year(cyr)
calc2 = Behavior.response(calc1, calc2)
std_res[cyr] = dict()
for tbl in ['aggr_1', 'aggr_2', 'aggr_d']:
if tbl.endswith('_1'):
itax = calc1.weighted_total('iitax')
ptax = calc1.weighted_total('payrolltax')
ctax = calc1.weighted_total('combined')
elif tbl.endswith('_2'):
itax = calc2.weighted_total('iitax')
ptax = calc2.weighted_total('payrolltax')
ctax = calc2.weighted_total('combined')
elif tbl.endswith('_d'):
itax = (calc2.weighted_total('iitax') -
calc1.weighted_total('iitax'))
ptax = (calc2.weighted_total('payrolltax') -
calc1.weighted_total('payrolltax'))
ctax = (calc2.weighted_total('combined') -
calc1.weighted_total('combined'))
cols = ['0_{}'.format(year)]
rows = ['ind_tax', 'payroll_tax', 'combined_tax']
datalist = [itax, ptax, ctax]
std_res[cyr][tbl] = pd.DataFrame(data=datalist,
index=rows,
columns=cols)
# compare the two sets of results
# NOTE that the tbi results have been "fuzzed" for PUF privacy reasons,
# so there is no expectation that the results should be identical.
no_diffs = True
reltol = 0.004 # std and tbi differ if more than 0.4 percent different
for year in range(0, num_years):
cyr = year + kwargs['start_year']
col = '0_{}'.format(year)
for tbl in ['aggr_1', 'aggr_2', 'aggr_d']:
tbi = tbi_res[cyr][tbl][col]
std = std_res[cyr][tbl][col]
if not np.allclose(tbi, std, atol=0.0, rtol=reltol):
no_diffs = False
print('**** DIFF for year {} (year_n={}):'.format(cyr, year))
print('TBI RESULTS:')
print(tbi)
print('STD RESULTS:')
print(std)
assert no_diffs
def test_create_parameters():
p = Policy()
assert p
def calculators(year_n, start_year,
use_puf_not_cps,
use_full_sample,
user_mods):
"""
This function assumes that the specified user_mods is a dictionary
returned by the Calculator.read_json_param_objects() function.
This function returns (calc1, calc2) where
calc1 is pre-reform Calculator object for year_n, and
calc2 is post-reform Calculator object for year_n.
Neither Calculator object has had the calc_all() method executed.
"""
# pylint: disable=too-many-locals,too-many-branches,too-many-statements
check_user_mods(user_mods)
# specify Consumption instance
consump = Consumption()
consump_assumptions = user_mods['consumption']
consump.update_consumption(consump_assumptions)
# specify growdiff_baseline and growdiff_response
growdiff_baseline = GrowDiff()
growdiff_response = GrowDiff()
growdiff_base_assumps = user_mods['growdiff_baseline']
growdiff_resp_assumps = user_mods['growdiff_response']
growdiff_baseline.update_growdiff(growdiff_base_assumps)
growdiff_response.update_growdiff(growdiff_resp_assumps)
# create pre-reform and post-reform GrowFactors instances
growfactors_pre = GrowFactors()
growdiff_baseline.apply_to(growfactors_pre)
growfactors_post = GrowFactors()
growdiff_baseline.apply_to(growfactors_post)
growdiff_response.apply_to(growfactors_post)
# create sample pd.DataFrame from specified input file and sampling scheme
tbi_path = os.path.abspath(os.path.dirname(__file__))
if use_puf_not_cps:
# first try TaxBrain deployment path
input_path = 'puf.csv.gz'
if not os.path.isfile(input_path):
# otherwise try local Tax-Calculator deployment path
input_path = os.path.join(tbi_path, '..', '..', 'puf.csv')
sampling_frac = 0.05
sampling_seed = 2222
else: # if using cps input not puf input
# first try Tax-Calculator code path
input_path = os.path.join(tbi_path, '..', 'cps.csv.gz')
if not os.path.isfile(input_path):
# otherwise read from taxcalc package "egg"
input_path = None # pragma: no cover
full_sample = read_egg_csv('cps.csv.gz') # pragma: no cover
sampling_frac = 0.03
sampling_seed = 180
if input_path:
full_sample = pd.read_csv(input_path)
if use_full_sample:
sample = full_sample
else:
sample = full_sample.sample(frac=sampling_frac,
random_state=sampling_seed)
# create pre-reform Calculator instance
if use_puf_not_cps:
recs1 = Records(data=sample,
gfactors=growfactors_pre)
else:
recs1 = Records.cps_constructor(data=sample,
gfactors=growfactors_pre)
policy1 = Policy(gfactors=growfactors_pre)
calc1 = Calculator(policy=policy1, records=recs1, consumption=consump)
while calc1.current_year < start_year:
calc1.increment_year()
assert calc1.current_year == start_year
# create post-reform Calculator instance
if use_puf_not_cps:
recs2 = Records(data=sample,
gfactors=growfactors_post)
else:
recs2 = Records.cps_constructor(data=sample,
gfactors=growfactors_post)
policy2 = Policy(gfactors=growfactors_post)
policy_reform = user_mods['policy']
policy2.implement_reform(policy_reform)
calc2 = Calculator(policy=policy2, records=recs2, consumption=consump)
while calc2.current_year < start_year:
calc2.increment_year()
assert calc2.current_year == start_year
# delete objects now embedded in calc1 and calc2
del sample
del full_sample
del consump
del growdiff_baseline
del growdiff_response
del growfactors_pre
del growfactors_post
del recs1
del recs2
del policy1
del policy2
# increment Calculator objects for year_n years
for _ in range(0, year_n):
calc1.increment_year()
calc2.increment_year()
# return Calculator objects
return (calc1, calc2)
def propagate_user_list(x,
name,
defaults,
cpi,
first_budget_year,
multi_param_idx=-1):
"""
Dispatch to either expand_1D or expand2D depending on the dimension of x
Parameters:
-----------
x : list from user to propagate forward in time. The first value is for
year 'first_budget_year'. The value at index i is the value for
budget year first_budget_year + i.
defaults: list of default values; our result must be at least this long
name: the parameter name for looking up the indexing rate
cpi: Bool
first_budget_year: int
multi_param_idx: int, optional. If this parameter is multi-valued, this
is the index for which the values for 'x' apply. So, for exampe, if
multi_param_idx=0, the values for x are typically for the 'single'
filer status. -1 indidcates that this is not a multi-valued
parameter
Returns:
--------
list of length 'num_years'. if 'cpi'==True, the values will be inflated
based on the last value the user specified
"""
# x must have a real first value
assert len(x) > 0
assert x[0] not in ("", None)
num_years = max(len(defaults), len(x))
is_rate = any([i < 1.0 for i in x])
current_policy = Policy(start_year=2013)
current_policy.set_year(first_budget_year)
# irates are rates for 2015, 2016, and 2017
if cpi:
irates = current_policy._indexing_rates_for_update(
param_name=name,
calyear=first_budget_year,
num_years_to_expand=num_years)
else:
irates = [0.0] * num_years
ans = [None] * num_years
for i in range(num_years):
if i < len(x):
if is_wildcard(x[i]):
if multi_param_idx > -1:
ans[i] = defaults[i][multi_param_idx]
else:
ans[i] = defaults[i]
else:
ans[i] = x[i]
if ans[i] is not None:
continue
else:
newval = ans[i - 1] * (1.0 + irates[i - 1])
ans[i] = newval if is_rate else int(newval)
return ans