def differences(new_filename, old_filename, stat_kind, small=0.0):
"""
Return message string if there are differences at least as large as small;
otherwise (i.e., if there are only small differences) return empty string.
"""
with open(new_filename, 'r') as vfile:
new_text = vfile.read()
with open(old_filename, 'r') as vfile:
old_text = vfile.read()
if nonsmall_diffs(new_text.splitlines(True), old_text.splitlines(True),
small):
new_name = os.path.basename(new_filename)
old_name = os.path.basename(old_filename)
msg = '{} RESULTS DIFFER:\n'.format(stat_kind)
msg += '-------------------------------------------------'
msg += '-------------\n'
msg += '--- NEW RESULTS IN {} FILE ---\n'.format(new_name)
msg += '--- if new OK, copy {} to ---\n'.format(new_name)
msg += '--- {} ---\n'.format(old_name)
msg += '--- and rerun test. '
msg += ' ---\n'
msg += '-------------------------------------------------'
msg += '-------------\n'
else:
msg = ''
os.remove(new_filename)
return msg
def differences(new_filename, old_filename, stat_kind, small=0.0):
"""
Return message string if there are differences at least as large as small;
otherwise (i.e., if there are only small differences) return empty string.
"""
with open(new_filename, 'r') as vfile:
new_text = vfile.read()
with open(old_filename, 'r') as vfile:
old_text = vfile.read()
if nonsmall_diffs(new_text.splitlines(True),
old_text.splitlines(True), small):
new_name = os.path.basename(new_filename)
old_name = os.path.basename(old_filename)
msg = '{} RESULTS DIFFER:\n'.format(stat_kind)
msg += '-------------------------------------------------'
msg += '-------------\n'
msg += '--- NEW RESULTS IN {} FILE ---\n'.format(new_name)
msg += '--- if new OK, copy {} to ---\n'.format(new_name)
msg += '--- {} ---\n'.format(old_name)
msg += '--- and rerun test. '
msg += ' ---\n'
msg += '-------------------------------------------------'
msg += '-------------\n'
else:
msg = ''
os.remove(new_filename)
return msg
def test_run_tax_calc_model(tests_path):
"""
Test tbi.run_nth_year_tax_calc_model function using CPS data.
"""
user_modifications = {
'policy': {
2016: {
'_II_rt3': [0.33],
'_PT_rt3': [0.33],
'_II_rt4': [0.33],
'_PT_rt4': [0.33]
}
},
'consumption': {
2016: {
'_MPC_e20400': [0.01]
}
},
'behavior': {
2016: {
'_BE_sub': [0.25]
}
},
'growdiff_baseline': {},
'growdiff_response': {}
}
res = run_nth_year_tax_calc_model(year_n=2,
start_year=2018,
use_puf_not_cps=False,
use_full_sample=False,
user_mods=user_modifications,
return_dict=True)
assert isinstance(res, dict)
# put actual results in a multiline string
actual_results = ''
for tbl in sorted(res.keys()):
actual_results += 'TABLE {} RESULTS:\n'.format(tbl)
actual_results += json.dumps(
res[tbl], sort_keys=True, indent=4, separators=(',', ': ')) + '\n'
# read expected results from file
expect_fname = 'tbi_cps_expect.txt'
expect_path = os.path.join(tests_path, expect_fname)
with open(expect_path, 'r') as expect_file:
expect_results = expect_file.read()
# ensure actual and expect results have no differences
diffs = nonsmall_diffs(actual_results.splitlines(True),
expect_results.splitlines(True))
if diffs:
actual_fname = '{}{}'.format(expect_fname[:-10], 'actual.txt')
actual_path = os.path.join(tests_path, actual_fname)
with open(actual_path, 'w') as actual_file:
actual_file.write(actual_results)
msg = 'TBI RESULTS DIFFER\n'
msg += '----------------------------------------------\n'
msg += '--- NEW RESULTS IN {} FILE ---\n'
msg += '--- if new OK, copy {} to ---\n'
msg += '--- {} ---\n'
msg += '--- and rerun test. ---\n'
msg += '----------------------------------------------\n'
raise ValueError(msg.format(actual_fname, actual_fname, expect_fname))
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))
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))
def test_run_taxcalc_model(tests_path):
"""
Test tbi.run_nth_year_taxcalc_model function using PUF data.
"""
user_modifications = {
'policy': {
2016: {'_II_rt3': [0.33],
'_PT_rt3': [0.33],
'_II_rt4': [0.33],
'_PT_rt4': [0.33]}
},
'consumption': {
2016: {'_MPC_e20400': [0.01]}
},
'growdiff_baseline': {
},
'growdiff_response': {
}
}
res = run_nth_year_taxcalc_model(year_n=2, start_year=2018,
use_puf_not_cps=True,
use_full_sample=False,
user_mods=user_modifications,
return_dict=True)
assert isinstance(res, dict)
# put actual results in a multiline string
actual_results = ''
for tbl in sorted(res.keys()):
actual_results += 'TABLE {} RESULTS:\n'.format(tbl)
actual_results += json.dumps(res[tbl], sort_keys=True,
indent=4, separators=(',', ': ')) + '\n'
# read expected results from file
expect_fname = 'tbi_puf_expect.txt'
expect_path = os.path.join(tests_path, expect_fname)
with open(expect_path, 'r') as expect_file:
expect_results = expect_file.read()
# ensure actual and expect results have no differences
diffs = nonsmall_diffs(actual_results.splitlines(True),
expect_results.splitlines(True))
if diffs:
actual_fname = '{}{}'.format(expect_fname[:-10], 'actual.txt')
actual_path = os.path.join(tests_path, actual_fname)
with open(actual_path, 'w') as actual_file:
actual_file.write(actual_results)
msg = 'TBI RESULTS DIFFER\n'
msg += '----------------------------------------------\n'
msg += '--- NEW RESULTS IN {} FILE ---\n'
msg += '--- if new OK, copy {} to ---\n'
msg += '--- {} ---\n'
msg += '--- and rerun test. ---\n'
msg += '----------------------------------------------\n'
raise ValueError(msg.format(actual_fname, actual_fname, expect_fname))
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 + '.out') as outfile:
exp_res = outfile.read()
exp = exp_res.splitlines(True)
with open(base + '.res') as resfile:
act_res = resfile.read()
act = act_res.splitlines(True)
# check that act & exp have differences no more than small value
diffs = nonsmall_diffs(act, exp, small=1e-6)
return not diffs
def test_run_tax_calc_model(using_puf, tests_path):
res = run_nth_year_tax_calc_model(year_n=2,
start_year=2018,
use_puf_not_cps=using_puf,
use_full_sample=False,
user_mods=USER_MODS,
return_dict=True)
assert isinstance(res, dict)
# put actual results in a multiline string
actual_results = ''
for tbl in sorted(res.keys()):
actual_results += 'TABLE {} RESULTS:\n'.format(tbl)
actual_results += json.dumps(
res[tbl], sort_keys=True, indent=4, separators=(',', ': ')) + '\n'
# read expected results from file
if using_puf:
expect_fname = 'tbi_puf_expect.txt'
else:
expect_fname = 'tbi_cps_expect.txt'
expect_path = os.path.join(tests_path, expect_fname)
with open(expect_path, 'r') as expect_file:
expect_results = expect_file.read()
# ensure actual and expect results have no differences
diffs = nonsmall_diffs(actual_results.splitlines(True),
expect_results.splitlines(True))
if diffs:
actual_fname = '{}{}'.format(expect_fname[:-10], 'actual.txt')
actual_path = os.path.join(tests_path, actual_fname)
with open(actual_path, 'w') as actual_file:
actual_file.write(actual_results)
msg = 'TBI RESULTS DIFFER\n'
msg += '----------------------------------------------\n'
msg += '--- NEW RESULTS IN {} FILE ---\n'
msg += '--- if new OK, copy {} to ---\n'
msg += '--- {} ---\n'
msg += '--- and rerun test. ---\n'
msg += '----------------------------------------------\n'
raise ValueError(msg.format(actual_fname, actual_fname, expect_fname))
def differences(afilename, efilename):
"""
Check for differences between results in afilename and efilename files.
"""
with open(afilename, 'r') as afile:
actres = afile.read()
with open(efilename, 'r') as efile:
expres = efile.read()
diffs = nonsmall_diffs(actres.splitlines(True), expres.splitlines(True),
0.0)
if diffs:
afname = os.path.basename(afilename)
efname = os.path.basename(efilename)
msg = 'COMPARE RESULTS DIFFER\n'
msg += '-------------------------------------------------\n'
msg += '--- NEW RESULTS IN {} FILE ---\n'
msg += '--- if new OK, copy {} to ---\n'
msg += '--- {} ---\n'
msg += '--- and rerun test. ---\n'
msg += '-------------------------------------------------\n'
raise ValueError(msg.format(afname, afname, efname))
else:
os.remove(afilename)
def differences(afilename, efilename):
"""
Check for differences between results in afilename and efilename files.
"""
with open(afilename, 'r') as afile:
actres = afile.read()
with open(efilename, 'r') as efile:
expres = efile.read()
diffs = nonsmall_diffs(actres.splitlines(True),
expres.splitlines(True), 0.0)
if diffs:
afname = os.path.basename(afilename)
efname = os.path.basename(efilename)
msg = 'COMPARE RESULTS DIFFER\n'
msg += '-------------------------------------------------\n'
msg += '--- NEW RESULTS IN {} FILE ---\n'
msg += '--- if new OK, copy {} to ---\n'
msg += '--- {} ---\n'
msg += '--- and rerun test. ---\n'
msg += '-------------------------------------------------\n'
raise ValueError(msg.format(afname, afname, efname))
else:
os.remove(afilename)
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_agg(tests_path):
"""
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 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 cps.csv input records
rec = Records.cps_constructor()
# create a Calculator object using baseline policy and cps 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 ($b)"]
# convert adt to a string with a trailing EOL character
actual_results = adt.to_string() + '\n'
# read expected results from file
aggres_path = os.path.join(tests_path, 'cpscsv_agg_expect.txt')
with open(aggres_path, 'r') as expected_file:
txt = expected_file.read()
expected_results = txt.rstrip('\n\t ') + '\n' # cleanup end of file txt
# ensure actual and expected results have no nonsmall differences
if sys.version_info.major == 2:
small = 0.0 # tighter test for Python 2.7
else:
small = 0.1 # looser test for Python 3.6
diffs = nonsmall_diffs(actual_results.splitlines(True),
expected_results.splitlines(True), small)
if diffs:
new_filename = '{}{}'.format(aggres_path[:-10], 'actual.txt')
with open(new_filename, 'w') as new_file:
new_file.write(actual_results)
msg = 'CPSCSV AGG RESULTS DIFFER\n'
msg += '-------------------------------------------------\n'
msg += '--- NEW RESULTS IN cpscsv_agg_actual.txt FILE ---\n'
msg += '--- if new OK, copy cpscsv_agg_actual.txt to ---\n'
msg += '--- cpscsv_agg_expect.txt ---\n'
msg += '--- and rerun test. ---\n'
msg += '-------------------------------------------------\n'
raise ValueError(msg)
# create aggregate diagnostic table using unweighted sub-sample of records
cps_filepath = os.path.join(tests_path, '..', 'cps.csv.gz')
fullsample = pd.read_csv(cps_filepath)
rn_seed = 180 # to ensure sub-sample is always the same
subfrac = 0.03 # sub-sample fraction
subsample = fullsample.sample(frac=subfrac, random_state=rn_seed)
rec_subsample = Records(data=subsample,
gfactors=Growfactors(),
weights=Records.CPS_WEIGHTS_FILENAME,
adjust_ratios=Records.CPS_RATIOS_FILENAME,
start_year=Records.CPSCSV_YEAR)
calc_subsample = Calculator(policy=baseline_policy, records=rec_subsample)
adt_subsample = calc_subsample.diagnostic_table(nyrs)
# compare combined tax liability from full and sub samples for each year
taxes_subsample = adt_subsample.loc["Combined Liability ($b)"]
reltol = 0.01 # maximum allowed relative difference in tax liability
# TODO: skip first year because of BUG in cps_weights.csv file
taxes_subsample = taxes_subsample[1:] # TODO: eliminate code
taxes_fullsample = taxes_fullsample[1:] # TODO: eliminate code
if not np.allclose(
taxes_subsample, taxes_fullsample, atol=0.0, rtol=reltol):
msg = 'CPSCSV 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_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
recs = Records(data=puf_fullsample)
# create a Calculator object using baseline policy and puf 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 ($b)"]
# convert adt results to a string with a trailing EOL character
adtstr = adt.to_string(float_format='%8.1f') + '\n'
# create actual and expected lists of diagnostic table lines
actual = adtstr.splitlines(True)
aggres_path = os.path.join(tests_path, 'pufcsv_agg_expect.txt')
with open(aggres_path, 'r') as expected_file:
txt = expected_file.read()
expected_results = txt.rstrip('\n\t ') + '\n' # cleanup end of file txt
expect = expected_results.splitlines(True)
# ensure actual and expect lines have differences no more than small value
diffs = nonsmall_diffs(actual, expect)
if diffs:
new_filename = '{}{}'.format(aggres_path[:-10], 'actual.txt')
with open(new_filename, 'w') as new_file:
new_file.write(adtstr)
msg = 'PUFCSV AGG RESULTS DIFFER FOR FULL-SAMPLE\n'
msg += '-------------------------------------------------\n'
msg += '--- NEW RESULTS IN pufcsv_agg_actual.txt FILE ---\n'
msg += '--- if new OK, copy pufcsv_agg_actual.txt to ---\n'
msg += '--- pufcsv_agg_expect.txt ---\n'
msg += '--- and rerun test. ---\n'
msg += '-------------------------------------------------\n'
raise ValueError(msg)
# create aggregate diagnostic table using unweighted sub-sample of records
fullsample = puf_fullsample
rn_seed = 2222 # to ensure sub-sample is always the same
subfrac = 0.05 # sub-sample fraction
subsample = fullsample.sample(frac=subfrac, random_state=rn_seed)
recs_subsample = Records(data=subsample)
calc_subsample = Calculator(policy=baseline_policy, records=recs_subsample)
adt_subsample = calc_subsample.diagnostic_table(nyrs)
# compare combined tax liability from full and sub samples for each year
taxes_subsample = adt_subsample.loc["Combined Liability ($b)"]
msg = ''
for cyr in range(calc_start_year, calc_start_year + nyrs):
reltol = 0.01 # maximum allowed relative difference in tax liability
if not np.allclose(taxes_subsample[cyr], taxes_fullsample[cyr],
atol=0.0, rtol=reltol):
reldiff = (taxes_subsample[cyr] / taxes_fullsample[cyr]) - 1.
line1 = '\nPUFCSV 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_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
recs = Records(data=puf_fullsample)
# create a Calculator object using baseline policy and puf 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 ($b)"]
# convert adt results to a string with a trailing EOL character
adtstr = adt.to_string(float_format='%8.1f') + '\n'
# create actual and expected lists of diagnostic table lines
actual = adtstr.splitlines(True)
aggres_path = os.path.join(tests_path, 'pufcsv_agg_expect.txt')
with open(aggres_path, 'r') as expected_file:
txt = expected_file.read()
expected_results = txt.rstrip('\n\t ') + '\n' # cleanup end of file txt
expect = expected_results.splitlines(True)
# ensure actual and expect lines have differences no more than small value
diffs = nonsmall_diffs(actual, expect)
if diffs:
new_filename = '{}{}'.format(aggres_path[:-10], 'actual.txt')
with open(new_filename, 'w') as new_file:
new_file.write(adtstr)
msg = 'PUFCSV AGG RESULTS DIFFER FOR FULL-SAMPLE\n'
msg += '-------------------------------------------------\n'
msg += '--- NEW RESULTS IN pufcsv_agg_actual.txt FILE ---\n'
msg += '--- if new OK, copy pufcsv_agg_actual.txt to ---\n'
msg += '--- pufcsv_agg_expect.txt ---\n'
msg += '--- and rerun test. ---\n'
msg += '-------------------------------------------------\n'
raise ValueError(msg)
# create aggregate diagnostic table using unweighted sub-sample of records
fullsample = puf_fullsample
rn_seed = 2222 # to ensure sub-sample is always the same
subfrac = 0.05 # sub-sample fraction
subsample = fullsample.sample(frac=subfrac, random_state=rn_seed)
recs_subsample = Records(data=subsample)
calc_subsample = Calculator(policy=baseline_policy, records=recs_subsample)
adt_subsample = calc_subsample.diagnostic_table(nyrs)
# compare combined tax liability from full and sub samples for each year
taxes_subsample = adt_subsample.loc["Combined Liability ($b)"]
msg = ''
for cyr in range(calc_start_year, calc_start_year + nyrs):
reltol = 0.01 # maximum allowed relative difference in tax liability
if not np.allclose(
taxes_subsample[cyr], taxes_fullsample[cyr], atol=0.0,
rtol=reltol):
reldiff = (taxes_subsample[cyr] / taxes_fullsample[cyr]) - 1.
line1 = '\nPUFCSV 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_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 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 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 ($b)"]
# convert adt to a string with a trailing EOL character
actual_results = adt.to_string(float_format='%8.1f') + '\n'
# read expected results from file
aggres_path = os.path.join(tests_path, 'cpscsv_agg_expect.txt')
with open(aggres_path, 'r') as expected_file:
txt = expected_file.read()
expected_results = txt.rstrip('\n\t ') + '\n' # cleanup end of file txt
# ensure actual and expected results have no nonsmall differences
diffs = nonsmall_diffs(actual_results.splitlines(True),
expected_results.splitlines(True))
if diffs:
new_filename = '{}{}'.format(aggres_path[:-10], 'actual.txt')
with open(new_filename, 'w') as new_file:
new_file.write(actual_results)
msg = 'CPSCSV AGG RESULTS DIFFER\n'
msg += '-------------------------------------------------\n'
msg += '--- NEW RESULTS IN cpscsv_agg_actual.txt FILE ---\n'
msg += '--- if new OK, copy cpscsv_agg_actual.txt to ---\n'
msg += '--- cpscsv_agg_expect.txt ---\n'
msg += '--- and rerun test. ---\n'
msg += '-------------------------------------------------\n'
raise ValueError(msg)
# create aggregate diagnostic table using unweighted sub-sample of records
rn_seed = 180 # to ensure sub-sample is always the same
subfrac = 0.03 # sub-sample fraction
subsample = cps_fullsample.sample(frac=subfrac, random_state=rn_seed)
recs_subsample = Records.cps_constructor(data=subsample)
calc_subsample = Calculator(policy=baseline_policy, records=recs_subsample)
adt_subsample = calc_subsample.diagnostic_table(nyrs)
# compare combined tax liability from full and sub samples for each year
taxes_subsample = adt_subsample.loc["Combined Liability ($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_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_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)
