def test_import_optional():
match = "Missing .*notapackage.* pip .* conda .* notapackage"
with pytest.raises(ImportError, match=match):
import_optional_dependency("notapackage")
result = import_optional_dependency("notapackage", raise_on_missing=False)
assert result is None
def test_no_version_raises():
name = "fakemodule"
module = types.ModuleType(name)
sys.modules[name] = module
VERSIONS[name] = "1.0.0"
with pytest.raises(ImportError, match="Can't determine .* fakemodule"):
import_optional_dependency(name)
def test_bad_version():
name = "fakemodule"
module = types.ModuleType(name)
module.__version__ = "0.9.0"
sys.modules[name] = module
VERSIONS[name] = "1.0.0"
match = "microdf requires .*1.0.0.* of .fakemodule.*'0.9.0'"
with pytest.raises(ImportError, match=match):
import_optional_dependency("fakemodule")
with tm.assert_produces_warning(UserWarning):
result = import_optional_dependency("fakemodule", on_version="warn")
assert result is None
module.__version__ = "1.0.0" # exact match is OK
result = import_optional_dependency("fakemodule")
assert result is module
def static_baseline_calc(recs, year):
"""Creates a static Calculator object.
:param recs: Records object.
:param year: Year to advance to.
:returns: Calculator object.
"""
tc = import_optional_dependency("taxcalc")
calc = tc.Calculator(records=recs, policy=tc.Policy())
calc.advance_to_year(year)
calc.calc_all()
return calc
def calc_df(
records=None,
policy=None,
year=2020,
reform=None,
group_vars=None,
metric_vars=None,
group_n65=False,
):
"""Creates a pandas DataFrame for given Tax-Calculator data.
s006 is always included, and RECID is used as an index.
:param records: An optional Records object. If not provided, uses CPS
records. (Default value = None)
:param policy: An optional Policy object. If not provided, uses default
Policy.
:param year: An optional year to advance to. If not provided, defaults to
2020.
:param reform: An optional reform to implement for the Policy object.
(Default value = None)
:param group_vars: An optional list of column names to include in the
DataFrame. (Default value = None)
:param metric_vars: An optional list of column names to include and
calculate weighted sums of (in millions named as *_m) in the DataFrame.
(Default value = None)
:param group_n65: Whether to calculate and group by n65. Defaults to False.
:returns: A pandas DataFrame. market_income is also always calculated.
"""
tc = import_optional_dependency("taxcalc")
# Assign defaults.
if records is None:
records = tc.Records.cps_constructor()
if policy is None:
policy = tc.Policy()
if reform is not None:
policy.implement_reform(reform)
# Calculate.
calc = tc.Calculator(records=records, policy=policy, verbose=False)
calc.advance_to_year(year)
calc.calc_all()
# Get a deduplicated list of all columns.
if group_n65:
group_vars = group_vars + [
"age_head",
"age_spouse",
"elderly_dependents",
]
# Include expanded_income and benefits to produce market_income.
all_cols = mdf.listify(
[
"RECID",
"s006",
"expanded_income",
"aftertax_income",
mdf.BENS,
group_vars,
metric_vars,
]
)
df = calc.dataframe(all_cols)
# Create core elements.
df["market_income"] = mdf.market_income(df)
df["bens"] = df[mdf.BENS].sum(axis=1)
df["tax"] = df.expanded_income - df.aftertax_income
if group_n65:
df["n65"] = n65(df.age_head, df.age_spouse, df.elderly_dependents)
df.drop(
["age_head", "age_spouse", "elderly_dependents"],
axis=1,
inplace=True,
)
# Add calculated columns for metrics.
mdf.add_weighted_metrics(df, metric_vars)
# Set RECID to int and set it as index before returning.
df["RECID"] = df.RECID.map(int)
return df.set_index("RECID")
def test_xlrd_version_fallback():
""" """
pytest.importorskip("xlrd")
import_optional_dependency("xlrd")
def calc_df(records=None,
policy=None,
year=2019,
reform=None,
group_vars=None,
metric_vars=None,
group_n65=False):
"""Creates a pandas DataFrame for given Tax-Calculator data.
s006 is always included, and RECID is used as an index.
Args:
records: An optional Records object. If not provided, uses CPS records.
policy: An optional Policy object. If not provided, uses default
Policy.
year: An optional year to advance to. If not provided, defaults to
2019.
reform: An optional reform to implement for the Policy object.
group_vars: An optional list of column names to include in the
DataFrame.
metric_vars: An optional list of column names to include and calculate
weighted sums of (in millions named as *_m) in the DataFrame.
group_n65: Whether to calculate and group by n65. Defaults to False.
Returns:
A pandas DataFrame. market_income is also always calculated.
"""
tc = import_optional_dependency("taxcalc")
# Assign defaults.
if records is None:
records = tc.Records.cps_constructor()
if policy is None:
policy = tc.Policy()
if reform is not None:
policy.implement_reform(reform)
# Calculate.
calc = tc.Calculator(records=records, policy=policy, verbose=False)
calc.advance_to_year(year)
calc.calc_all()
# TODO: Make n65, ECI, etc. part of the list of columns you can request.
# Get a deduplicated list of all columns.
if group_n65:
group_vars = group_vars + ['age_head', 'age_spouse',
'elderly_dependents']
# Include expanded_income and benefits to produce market_income.
all_cols = mdf.listify(
['RECID', 's006', 'expanded_income', 'aftertax_income',
mdf.BENS, group_vars, metric_vars])
df = calc.dataframe(all_cols)
# Create core elements.
df['market_income'] = mdf.market_income(df)
df['bens'] = df[mdf.BENS].sum(axis=1)
df['tax'] = df.expanded_income - df.aftertax_income
if group_n65:
df['n65'] = n65(df.age_head, df.age_spouse, df.elderly_dependents)
df.drop(['age_head', 'age_spouse', 'elderly_dependents'], axis=1,
inplace=True)
# Add calculated columns for metrics.
mdf.add_weighted_metrics(df, metric_vars)
# Set RECID to int and set it as index before returning.
df['RECID'] = df.RECID.map(int)
return df.set_index('RECID')