def test_response_json(tests_path):
"""
Check that each JSON file can be converted into dictionaries that
can be used to construct objects needed for a Calculator object.
"""
responses_path = os.path.join(tests_path, '..', 'responses', '*.json')
for jpf in glob.glob(responses_path):
# read contents of jpf (JSON parameter filename)
jfile = open(jpf, 'r')
jpf_text = jfile.read()
# check that jpf_text can be used to construct objects
response_file = ('"consumption"' in jpf_text and
'"behavior"' in jpf_text and
'"growdiff_baseline"' in jpf_text and
'"growdiff_response"' in jpf_text)
if response_file:
# pylint: disable=protected-access
(con, beh, gdiff_base,
gdiff_resp) = Calculator._read_json_econ_assump_text(jpf_text)
cons = Consumption()
cons.update_consumption(con)
behv = Behavior()
behv.update_behavior(beh)
growdiff_baseline = Growdiff()
growdiff_baseline.update_growdiff(gdiff_base)
growdiff_response = Growdiff()
growdiff_response.update_growdiff(gdiff_resp)
else: # jpf_text is not a valid JSON response assumption file
print('test-failing-filename: ' +
jpf)
assert False
def test_taxbrain_json(taxbrain_path): # pylint: disable=redefined-outer-name
"""
Check that each JSON parameter file can be converted into dictionaries
that can be used to construct objects needed for a Calculator object.
"""
for jpf in glob.glob(taxbrain_path):
# read contents of jpf (JSON parameter filename)
jfile = open(jpf, 'r')
jpf_text = jfile.read()
# check that jpf_text can be used to construct objects
if '"policy"' in jpf_text:
pol = Calculator.read_json_policy_reform_text(jpf_text)
policy = Policy()
policy.implement_reform(pol)
elif ('"consumption"' in jpf_text and
'"behavior"' in jpf_text and
'"growdiff_baseline"' in jpf_text and
'"growdiff_response"' in jpf_text):
(con, beh, gdiff_base,
gdiff_resp) = Calculator.read_json_econ_assump_text(jpf_text)
cons = Consumption()
cons.update_consumption(con)
behv = Behavior()
behv.update_behavior(beh)
growdiff_baseline = Growdiff()
growdiff_baseline.update_growdiff(gdiff_base)
growdiff_response = Growdiff()
growdiff_response.update_growdiff(gdiff_resp)
else: # jpf_text is not a valid JSON parameter file
print('test-failing-filename: ' +
jpf)
assert False
def reform_warnings_errors(user_mods):
"""
The reform_warnings_errors function assumes user_mods is a dictionary
returned by the Calculator.read_json_param_objects() function.
This function returns a dictionary containing two STR:STR pairs:
{'warnings': '<empty-or-message(s)>', 'errors': '<empty-or-message(s)>'}
In each pair the second string is empty if there are no messages.
Any returned messages are generated using current_law_policy.json
information on known policy parameter names and parameter value ranges.
Note that this function will return one or more error messages if
the user_mods['policy'] dictionary contains any unknown policy
parameter names or if any *_cpi parameters have values other than
True or False. These situations prevent implementing the policy
reform specified in user_mods, and therefore, no range-related
warnings or errors will be returned in this case.
"""
rtn_dict = {
'policy': {
'warnings': '',
'errors': ''
},
'behavior': {
'warnings': '',
'errors': ''
}
}
# create Growfactors object
gdiff_baseline = Growdiff()
gdiff_baseline.update_growdiff(user_mods['growdiff_baseline'])
gdiff_response = Growdiff()
gdiff_response.update_growdiff(user_mods['growdiff_response'])
growfactors = Growfactors()
gdiff_baseline.apply_to(growfactors)
gdiff_response.apply_to(growfactors)
# create Policy object and implement reform
pol = Policy(gfactors=growfactors)
try:
pol.implement_reform(user_mods['policy'],
print_warnings=False,
raise_errors=False)
rtn_dict['policy']['warnings'] = pol.parameter_warnings
rtn_dict['policy']['errors'] = pol.parameter_errors
except ValueError as valerr_msg:
rtn_dict['policy']['errors'] = valerr_msg.__str__()
# create Behavior object and implement revisions
# Note that Behavior does not have a `parameter_warnings`
# attribute.
behv = Behavior()
try:
behv.update_behavior(user_mods['behavior'])
rtn_dict['behavior']['errors'] = behv.parameter_errors
except ValueError as valerr_msg:
rtn_dict['behavior']['errors'] = valerr_msg.__str__()
return rtn_dict
def test_has_any_response():
syr = 2014
gdiff = Growdiff(start_year=syr)
assert gdiff.has_any_response() is False
gdiff.update_growdiff({2020: {'_AWAGE': [0.01]}})
assert gdiff.current_year == syr
assert gdiff.has_any_response() is True
def test_creation_with_aging(rawinputfile, reformfile0):
"""
Test TaxCalcIO instantiation with/without no policy reform and with aging.
"""
taxyear = 2021
tcio = TaxCalcIO(input_data=rawinputfile.name,
tax_year=taxyear,
reform=reformfile0.name,
assump=None)
assert len(tcio.errmsg) == 0
tcio.init(input_data=rawinputfile.name,
tax_year=taxyear,
reform=reformfile0.name,
assump=None,
growdiff_response=Growdiff(),
aging_input_data=True,
exact_calculations=False)
assert len(tcio.errmsg) == 0
assert tcio.tax_year() == taxyear
taxyear = 2016
tcio = TaxCalcIO(input_data=rawinputfile.name,
tax_year=taxyear,
reform=None,
assump=None)
assert len(tcio.errmsg) == 0
tcio.init(input_data=rawinputfile.name,
tax_year=taxyear,
reform=None,
assump=None,
growdiff_response=None,
aging_input_data=True,
exact_calculations=False)
assert len(tcio.errmsg) == 0
assert tcio.tax_year() == taxyear
def test_init_errors(reformfile0, assumpfile0, year, asm, gdr):
"""
Ensure error messages generated by TaxCalcIO.init method.
"""
recdict = {'RECID': 1, 'MARS': 1, 'e00300': 100000, 's006': 1e8}
recdf = pd.DataFrame(data=recdict, index=[0])
if asm == 'assumpfile0':
assump = assumpfile0.name
else:
assump = asm
if gdr == 'has_gdiff_response':
gdiff_response = Growdiff()
gdiff_response.update_growdiff({2015: {"_ABOOK": [-0.01]}})
else:
gdiff_response = gdr
tcio = TaxCalcIO(input_data=recdf,
tax_year=year,
reform=reformfile0.name,
assump=assump)
assert len(tcio.errmsg) == 0
tcio.init(input_data=recdf,
tax_year=year,
reform=reformfile0.name,
assump=assump,
growdiff_response=gdiff_response,
aging_input_data=False,
exact_calculations=False)
assert len(tcio.errmsg) > 0
def test_chained_cpi_reform(offset):
"""
Test that _cpi_offset policy parameter works as expected.
"""
# specify reform without using cpi_offset parameter
pem = 10000
bare_reform = {2022: {'_II_em': [pem]}}
with_reform = {2022: {'_II_em': [pem]}, 2020: {'_cpi_offset': [offset]}}
syr = Policy.JSON_START_YEAR
pol_bare = Policy(start_year=syr)
pol_bare.implement_reform(bare_reform)
pol_with = Policy(start_year=syr)
pol_with.implement_reform(with_reform)
# check relative _II_em values in the two reforms for several years
pem_bare = pol_bare._II_em
pem_with = pol_with._II_em
if offset == 0:
assert pem_with[2019 - syr] == pem_bare[2019 - syr]
assert pem_with[2020 - syr] == pem_bare[2020 - syr]
assert pem_with[2021 - syr] == pem_bare[2021 - syr]
assert pem_with[2022 - syr] == pem
assert pem_bare[2022 - syr] == pem
assert pem_with[2023 - syr] == pem_bare[2023 - syr]
elif offset < 0:
assert pem_with[2019 - syr] == pem_bare[2019 - syr]
assert pem_with[2020 - syr] == pem_bare[2020 - syr]
assert pem_with[2021 - syr] < pem_bare[2021 - syr]
assert pem_with[2022 - syr] == pem
assert pem_bare[2022 - syr] == pem
assert pem_with[2023 - syr] < pem_bare[2023 - syr]
# check exact _II_em values for 2023, which are
# equal to 2022 values indexed by 2022 inflation rates
unchained_cpi = pol_bare.inflation_rates()[2022 - syr]
assert pem_bare[2023 - syr] == round(pem * (1 + unchained_cpi), 2)
chained_cpi = unchained_cpi + offset
assert pem_with[2023 - syr] == round(pem * (1 + chained_cpi), 2)
# check that _STD value for 2023 with chained CPI indexing is
# equal to _STD value for 2023 when specifying chained CPI indexing
# as a difference in assumed inflation rates
if offset != 0:
# ... compute _STD value using difference-in-growth-factors approach
growfactors = Growfactors()
growdiff = Growdiff()
growdiff.update_growdiff({2020: {'_ACPIU': [offset]}})
growdiff.apply_to(growfactors)
pol = Policy(gfactors=growfactors, start_year=syr)
pol.implement_reform(bare_reform)
# ... compare the _STD values derived from the two approaches
assert_allclose(pol_with._STD[2023 - syr],
pol._STD[2023 - syr],
atol=0.01,
rtol=0.0)
def test_init_errors(reformfile0, reformfilex1, reformfilex2, baselinebad,
assumpfile0, year, base, ref, asm, gdr):
"""
Ensure error messages generated by TaxCalcIO.init method.
"""
# pylint: disable=too-many-arguments,too-many-locals
recdict = {'RECID': 1, 'MARS': 1, 'e00300': 100000, 's006': 1e8}
recdf = pd.DataFrame(data=recdict, index=[0])
if base == 'reformfile0':
baseline = reformfile0.name
elif base == 'baselinebad':
baseline = baselinebad.name
else:
baseline = base
if ref == 'reformfile0':
reform = reformfile0.name
elif ref == 'reformfilex1':
reform = reformfilex1.name
elif ref == 'reformfilex2': # specify compound reform
reform = '{}+{}'.format(reformfilex1.name, reformfilex2.name)
else:
reform = ref
if asm == 'assumpfile0':
assump = assumpfile0.name
else:
assump = asm
if gdr == 'has_gdiff_response':
gdiff_response = Growdiff()
gdiff_response.update_growdiff({2015: {"_ABOOK": [-0.01]}})
else:
gdiff_response = gdr
tcio = TaxCalcIO(input_data=recdf,
tax_year=year,
baseline=baseline,
reform=reform,
assump=assump)
assert not tcio.errmsg
tcio.init(input_data=recdf,
tax_year=year,
baseline=baseline,
reform=reform,
assump=assump,
growdiff_response=gdiff_response,
aging_input_data=False,
exact_calculations=False)
assert tcio.errmsg
def test_update_and_apply_growdiff():
syr = 2013
nyrs = 5
lyr = syr + nyrs - 1
gdiff = Growdiff(start_year=syr, num_years=nyrs)
# update Growdiff instance
diffs = {2014: {'_AWAGE': [0.01]}, 2016: {'_AWAGE': [0.02]}}
gdiff.update_growdiff(diffs)
expected_wage_diffs = [0.00, 0.01, 0.01, 0.02, 0.02]
assert_allclose(gdiff._AWAGE, expected_wage_diffs, atol=0.0, rtol=0.0)
# apply growdiff to Growfactors instance
gf = Growfactors()
pir_pre = gf.price_inflation_rates(syr, lyr)
wgr_pre = gf.wage_growth_rates(syr, lyr)
gfactors = Growfactors()
gdiff.apply_to(gfactors)
pir_pst = gfactors.price_inflation_rates(syr, lyr)
wgr_pst = gfactors.wage_growth_rates(syr, lyr)
expected_wgr_pst = [
wgr_pre[i] + expected_wage_diffs[i] for i in range(0, nyrs)
]
assert_allclose(pir_pre, pir_pst, atol=0.0, rtol=0.0)
assert_allclose(wgr_pst, expected_wgr_pst, atol=1.0e-9, rtol=0.0)
def test_correct_but_not_useful_growdiff_ctor():
gdiff = Growdiff(growdiff_dict={})
assert gdiff
def test_incorrect_growdiff_ctor():
with pytest.raises(ValueError):
gdiff = Growdiff(growdiff_dict=list())
with pytest.raises(ValueError):
gdiff = Growdiff(num_years=0)
def dropq_calculate(year_n, start_year, taxrec_df, user_mods, behavior_allowed,
mask_computed):
"""
The dropq_calculate function assumes specified user_mods is
a dictionary returned by the Calculator.read_json_parameter_files()
function with an extra key:value pair that is specified as
'gdp_elasticity': {'value': <float_value>}.
The function returns (calc1, calc2, mask) where
calc1 is pre-reform Calculator object calculated for year_n,
calc2 is post-reform Calculator object calculated for year_n, and
mask is boolean array if compute_mask=True or None otherwise
"""
# pylint: disable=too-many-arguments,too-many-locals,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 pre-reform Calculator instance
recs1 = Records(data=taxrec_df.copy(deep=True), 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
# optionally compute mask
if mask_computed:
# create pre-reform Calculator instance with extra income
recs1p = Records(data=taxrec_df.copy(deep=True),
gfactors=growfactors_pre)
# add one dollar to total wages and salaries of each filing unit
recs1p.e00200 += 1.0 # pylint: disable=no-member
recs1p.e00200p += 1.0 # pylint: disable=no-member
policy1p = Policy(gfactors=growfactors_pre)
# create Calculator with recs1p and calculate for start_year
calc1p = Calculator(policy=policy1p,
records=recs1p,
consumption=consump)
while calc1p.current_year < start_year:
calc1p.increment_year()
calc1p.calc_all()
assert calc1p.current_year == start_year
# compute mask that shows which of the calc1 and calc1p results differ
res1 = results(calc1.records)
res1p = results(calc1p.records)
mask = (res1.iitax != res1p.iitax)
else:
mask = None
# 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
recs2 = Records(data=taxrec_df.copy(deep=True), 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()
calc2.calc_all()
assert calc2.current_year == start_year
# 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 and mask
return (calc1, calc2, mask)
def calculate_baseline_and_reform(year_n, start_year, taxrec_df, user_mods):
"""
calculate_baseline_and_reform function assumes specified user_mods is
a dictionary returned by the Calculator.read_json_parameter_files()
function with an extra key:value pair that is specified as
'gdp_elasticity': {'value': <float_value>}.
"""
# 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 pre-reform Calculator instance
recs1 = Records(data=taxrec_df.copy(deep=True), 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
# Create pre-reform Calculator instance with extra income
recs1p = Records(data=taxrec_df.copy(deep=True), gfactors=growfactors_pre)
# add one dollar to total wages and salaries of each filing unit
recs1p.e00200 += 1.0 # pylint: disable=no-member
policy1p = Policy(gfactors=growfactors_pre)
calc1p = Calculator(policy=policy1p, records=recs1p, consumption=consump)
while calc1p.current_year < start_year:
calc1p.increment_year()
calc1p.calc_all()
assert calc1p.current_year == start_year
# Construct mask to show which of the calc1 and calc1p results differ
soit1 = results(calc1)
soit1p = results(calc1p)
mask = (soit1._iitax != soit1p._iitax) # pylint: disable=protected-access
# Specify Behavior instance
behv = Behavior()
behavior_assumps = user_mods['behavior']
behv.update_behavior(behavior_assumps)
# 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)
# Create post-reform Calculator instance with behavior
recs2 = Records(data=taxrec_df.copy(deep=True), 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()
calc2.calc_all()
assert calc2.current_year == start_year
# Seed random number generator with a seed value based on user_mods
seed = random_seed(user_mods)
print('seed={}'.format(seed))
np.random.seed(seed) # pylint: disable=no-member
# 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 results and mask
soit1 = results(calc1)
soit2 = results(calc2)
return soit1, soit2, mask
def calculate(year_n, start_year, use_puf_not_cps, use_full_sample, user_mods,
behavior_allowed):
"""
The calculate function assumes the specified user_mods is a dictionary
returned by the Calculator.read_json_param_objects() function.
The 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
stime = time.time()
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 = 180
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( # pylint: disable=no-member
frac=sampling_frac,
random_state=sampling_seed)
if use_puf_not_cps:
print('puf-read-time= {:.1f}'.format(time.time() - stime))
else:
print('cps-read-time= {:.1f}'.format(time.time() - stime))
# 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)
afile.write(contents)
afile.close()
# must close and then yield for Windows platform
yield afile
if os.path.isfile(afile.name):
try:
os.remove(afile.name)
except OSError:
pass # sometimes we can't remove a generated temporary file
# for fixture args, pylint: disable=redefined-outer-name
@pytest.mark.parametrize("year, asm, gdr", [
(2000, 'assumpfile0', Growdiff()),
(2099, None, None),
(2020, None, dict()),
(2020, 'assumpfile0', 'has_gdiff_response'),
])
def test_init_errors(reformfile0, assumpfile0, year, asm, gdr):
"""
Ensure error messages generated by TaxCalcIO.init method.
"""
recdict = {'RECID': 1, 'MARS': 1, 'e00300': 100000, 's006': 1e8}
recdf = pd.DataFrame(data=recdict, index=[0])
if asm == 'assumpfile0':
assump = assumpfile0.name
else:
assump = asm
if gdr == 'has_gdiff_response':
])
def test_ctor_errors(input_data, baseline, reform, assump, outdir):
"""
Ensure error messages are generated by TaxCalcIO.__init__.
"""
tcio = TaxCalcIO(input_data=input_data,
tax_year=2013,
baseline=baseline,
reform=reform,
assump=assump,
outdir=outdir)
assert tcio.errmsg
@pytest.mark.parametrize('year, base, ref, asm, gdr', [
(2000, 'reformfile0', 'reformfile0', 'assumpfile0', Growdiff()),
(2099, 'reformfile0', 'reformfile0', None, None),
(2020, 'reformfile0', 'reformfile0', None, dict()),
(2020, 'reformfile0', 'reformfile0', 'assumpfile0', 'has_gdiff_response'),
(2020, 'reformfile0', 'reformfilex1', 'assumpfile0', 'has_gdiff_response'),
(2020, 'reformfile0', 'reformfilex2', 'assumpfile0', 'has_gdiff_response'),
(2020, 'baselinebad', 'reformfile0', 'assumpfile0', 'has_gdiff_response')
])
def test_init_errors(reformfile0, reformfilex1, reformfilex2, baselinebad,
assumpfile0, year, base, ref, asm, gdr):
"""
Ensure error messages generated by TaxCalcIO.init method.
"""
# pylint: disable=too-many-arguments,too-many-locals
recdict = {'RECID': 1, 'MARS': 1, 'e00300': 100000, 's006': 1e8}
recdf = pd.DataFrame(data=recdict, index=[0])
def calculate(year_n, start_year, use_puf_not_cps, use_full_sample, user_mods,
behavior_allowed):
"""
The calculate function assumes the specified user_mods is a dictionary
returned by the Calculator.read_json_param_objects() function.
The function returns (calc1, calc2, mask) where
calc1 is pre-reform Calculator object calculated for year_n,
calc2 is post-reform Calculator object calculated for year_n, and
mask is boolean array marking records with reform-induced iitax diffs
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
stime = time.time()
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 = 180
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( # pylint: disable=no-member
frac=sampling_frac,
random_state=sampling_seed)
if use_puf_not_cps:
print('puf-read-time= {:.1f}'.format(time.time() - stime))
else:
print('cps-read-time= {:.1f}'.format(time.time() - stime))
# create pre-reform Calculator instance
if use_puf_not_cps:
recs1 = Records(data=copy.deepcopy(sample), gfactors=growfactors_pre)
else:
recs1 = Records.cps_constructor(data=copy.deepcopy(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
# compute mask array
res1 = calc1.dataframe(DIST_VARIABLES)
if use_puf_not_cps:
# create pre-reform Calculator instance with extra income
recs1p = Records(data=copy.deepcopy(sample), gfactors=growfactors_pre)
# add one dollar to the income of each filing unit to determine
# which filing units undergo a resulting change in tax liability
recs1p.e00200 += 1.0 # pylint: disable=no-member
recs1p.e00200p += 1.0 # pylint: disable=no-member
policy1p = Policy(gfactors=growfactors_pre)
# create Calculator with recs1p and calculate for start_year
calc1p = Calculator(policy=policy1p,
records=recs1p,
consumption=consump)
while calc1p.current_year < start_year:
calc1p.increment_year()
calc1p.calc_all()
assert calc1p.current_year == start_year
# compute mask showing which of the calc1 and calc1p results differ;
# mask is true if a filing unit's income tax liability changed after
# a dollar was added to the filing unit's wage and salary income
res1p = calc1p.dataframe(DIST_VARIABLES)
mask = np.logical_not( # pylint: disable=no-member
np.isclose(res1.iitax, res1p.iitax, atol=0.001, rtol=0.0))
assert np.any(mask)
else: # if use_cps_not_cps is False
# indicate that no fuzzing of reform results is required
mask = np.zeros(res1.shape[0], dtype=np.int8)
# 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=copy.deepcopy(sample), gfactors=growfactors_post)
else:
recs2 = Records.cps_constructor(data=copy.deepcopy(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()
calc2.calc_all()
assert calc2.current_year == start_year
# 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 and mask
return (calc1, calc2, mask)
def run_nth_year_gdp_elast_model(year_n,
start_year,
taxrec_df,
user_mods,
return_json=True):
"""
The run_nth_year_gdp_elast_model function assumes user_mods is a
dictionary returned by the Calculator.read_json_parameter_files()
function with an extra key:value pair that is specified as
'gdp_elasticity': {'value': <float_value>}.
"""
# pylint: disable=too-many-arguments,too-many-locals,too-many-statements
check_user_mods(user_mods)
# Only makes sense to run for budget years 1 through n-1 (not for year 0)
assert year_n > 0
# Specify value of gdp_elasticity
gdp_elasticity = user_mods['gdp_elasticity']['value']
# Specify Consumption instance
consump = Consumption()
consump_assumps = user_mods['consumption']
consump.update_consumption(consump_assumps)
# 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 pre-reform Calculator instance
records1 = Records(data=taxrec_df.copy(deep=True),
gfactors=growfactors_pre)
policy1 = Policy(gfactors=growfactors_pre)
calc1 = Calculator(policy=policy1, records=records1, consumption=consump)
while calc1.current_year < start_year:
calc1.increment_year()
assert calc1.current_year == start_year
# Create post-reform Calculator instance
records2 = Records(data=taxrec_df.copy(deep=True),
gfactors=growfactors_post)
policy2 = Policy(gfactors=growfactors_post)
policy_reform = user_mods['policy']
policy2.implement_reform(policy_reform)
calc2 = Calculator(policy=policy2, records=records2, consumption=consump)
while calc2.current_year < start_year:
calc2.increment_year()
assert calc2.current_year == start_year
# Seed random number generator with a seed value based on user_mods
seed = random_seed(user_mods)
np.random.seed(seed) # pylint: disable=no-member
for _ in range(0, year_n - 1):
calc1.increment_year()
calc2.increment_year()
calc1.calc_all()
calc2.calc_all()
# Assert that the current year is one behind the year we are calculating
assert (calc1.current_year + 1) == (start_year + year_n)
assert (calc2.current_year + 1) == (start_year + year_n)
# Compute gdp effect
gdp_effect = proportional_change_gdp(calc1, calc2, gdp_elasticity)
# Return gdp_effect results
if return_json:
gdp_df = pd.DataFrame(data=[gdp_effect], columns=['col0'])
gdp_elast_names_i = [
x + '_' + str(year_n) for x in GDP_ELAST_ROW_NAMES
]
gdp_elast_total = create_json_table(gdp_df,
row_names=gdp_elast_names_i,
num_decimals=5)
gdp_elast_total = dict((k, v[0]) for k, v in gdp_elast_total.items())
return gdp_elast_total
else:
return gdp_effect