Python Records.read_var_info方法代码示例

# 需要导入模块: from taxcalc import Records [as 别名]
# 或者: from taxcalc.Records import read_var_info [as 别名]
def test_calc_and_used_vars(tests_path):
    """
    Runs two kinds of tests on variables used in the calcfunctions.py file:

    (1) Checks that each var in Records.CALCULATED_VARS is actually calculated

    If test (1) fails, a variable in Records.CALCULATED_VARS was not
    calculated in any function in the calcfunctions.py file.  With the
    exception of a few variables listed in this test, all
    Records.CALCULATED_VARS must be calculated in the calcfunctions.py file.

    (2) Check that each variable that is calculated in a function and
    returned by that function is an argument of that function.
    """
    # pylint: disable=too-many-locals
    funcpath = os.path.join(tests_path, '..', 'calcfunctions.py')
    gfd = GetFuncDefs()
    fnames, fargs, cvars, rvars = gfd.visit(ast.parse(open(funcpath).read()))
    # Test (1):
    # .. create set of vars that are actually calculated in calcfunctions.py
    all_cvars = set()
    for fname in fnames:
        if fname == 'BenefitSurtax':
            continue  # because BenefitSurtax is not really a function
        all_cvars.update(set(cvars[fname]))
    # .. add to all_cvars set variables calculated in Records class
    all_cvars.update(set(['num', 'sep', 'exact']))
    # .. add to all_cvars set variables calculated elsewhere
    all_cvars.update(set(['mtr_paytax', 'mtr_inctax']))
    all_cvars.update(set(['benefit_cost_total', 'benefit_value_total']))
    # .. check that each var in Records.CALCULATED_VARS is in the all_cvars set
    Records.read_var_info()
    found_error1 = False
    if not Records.CALCULATED_VARS <= all_cvars:
        msg1 = ('all Records.CALCULATED_VARS not calculated '
                'in calcfunctions.py\n')
        for var in Records.CALCULATED_VARS - all_cvars:
            found_error1 = True
            msg1 += 'VAR NOT CALCULATED: {}\n'.format(var)
    # Test (2):
    faux_functions = ['EITCamount', 'ComputeBenefit', 'BenefitPrograms',
                      'BenefitSurtax', 'BenefitLimitation']
    found_error2 = False
    msg2 = 'calculated & returned variables are not function arguments\n'
    for fname in fnames:
        if fname in faux_functions:
            continue  # because fname is not a genuine function
        crvars_set = set(cvars[fname]) & set(rvars[fname])
        if not crvars_set <= set(fargs[fname]):
            found_error2 = True
            for var in crvars_set - set(fargs[fname]):
                msg2 += 'FUNCTION,VARIABLE: {} {}\n'.format(fname, var)
    # Report errors for the two tests:
    if found_error1 and found_error2:
        raise ValueError('{}\n{}'.format(msg1, msg2))
    if found_error1:
        raise ValueError(msg1)
    if found_error2:
        raise ValueError(msg2)

# 需要导入模块: from taxcalc import Records [as 别名]
# 或者: from taxcalc.Records import read_var_info [as 别名]
def test_validity_of_name_lists():
    assert len(DIST_TABLE_COLUMNS) == len(DIST_TABLE_LABELS)
    Records.read_var_info()
    assert set(DIST_VARIABLES).issubset(Records.CALCULATED_VARS | {'s006'})
    extra_vars_set = set(['num_returns_StandardDed',
                          'num_returns_ItemDed',
                          'num_returns_AMT'])
    assert (set(DIST_TABLE_COLUMNS) - set(DIST_VARIABLES)) == extra_vars_set

# 需要导入模块: from taxcalc import Records [as 别名]
# 或者: from taxcalc.Records import read_var_info [as 别名]
MAX_SIZE = 100000  # maximum size of sample to draw from puf.csv

DEBUG = False  # True implies no variable randomization or record sampling

TRACE = False  # True implies tracing output written to stdout

# specify set of variables not included in xYY.csv file
if DEBUG:
    DROP_VARS = set(['filer'])
else:
    DROP_VARS = set(['filer', 's006', 'cmbtp',
                     'nu05', 'nu13', 'elderly_dependents',
                     'e09700', 'e09800', 'e09900', 'e11200'])

# specify set of variables whose values are not to be randomized
Records.read_var_info()
if DEBUG:
    SKIP_VARS = Records.USABLE_READ_VARS
else:
    SKIP_VARS = set(['RECID', 'MARS', 'DSI', 'MIDR', 'FLPDYR',
                     'age_head', 'age_spouse',
                     'nu18', 'n1820', 'n21',
                     'XTOT', 'EIC', 'n24', 'f2441',
                     'f6251'])

ANNUAL_DRIFT = 0.03
NORM_STD_DEV = 0.25


def randomize_data(xdf, taxyear, rnseed):
    """