def recalculate(df):
"""Recalculates fields in the DataFrame for after components have changed.
:param df: DataFrame for use in microdf.
:returns: Nothing. Updates the DataFrame in place.
"""
# Recalculate TPC's Expanded Cash Income measure.
cols = df.columns
if "tpc_eci" in cols:
df.tpc_eci = mdf.tpc_eci(df)
# Recalculate weighted metrics (anything ending in _m).
mcols = cols[cols.str.endswith("_m")]
mdf.add_weighted_metrics(df, mcols)
def recalculate(df):
""" Recalculates fields in the DataFrame for after components have changed.
Args:
df: DataFrame for use in microdf.
Returns:
Nothing. Updates the DataFrame in place.
"""
# Recalculate aggregate income measures.
AGG_INCOME_MEASURES = ['expanded_income', 'aftertax_income', 'tpc_eci']
cols = df.columns
if 'tpc_eci' in cols:
df.tpc_eci = mdf.tpc_eci(df)
# Recalculate weighted metrics (anything ending in _m).
mcols = cols[cols.str.endswith('_m')]
mdf.add_weighted_metrics(df, mcols)
'31': 'Nebraska', '32':'Nevada', '33': 'New Hampshire',
'34': 'New Jersey', '35': 'New Mexico', '36':'New York',
'37':'North Carolina', '38':'North Dakota', '39': 'Ohio',
'40':'Oklahoma', '41': 'Oregon', '42':'Pennslyvania',
'44':'Rhode Island','45':'South Carolina', '46':'South Dakota',
'47': 'Tennessee', '48':'Texas','49':'Utah','50':'Vermont',
'51':'Virginia', '53':'Washington', '54':'West Virginia',
'55':'Wisconsin', '56':'Wyoming'},inplace=True)
person['child'] = person.age < 18
person['adult'] = person.age >= 18
ages = person.groupby(['spmfamunit', 'year'])[['child','adult']].sum()
ages.columns = ['total_children', 'total_adults']
person = person.merge(ages,left_on=['spmfamunit', 'year'], right_index=True)
person['total_people'] = person.total_children + person.total_adults
mdf.add_weighted_metrics(person, ['child', 'adult'], 'weight')
child_pop = person.groupby('state')[['child']].sum()/3
def ca_pov(state, age_group, ca_monthly=0):
target_persons = person[person.state==state].copy(deep=True)
total_population = target_persons.weight.sum()
adult_population = (target_persons.weight * target_persons.adult).sum()
child_population = (target_persons.weight * target_persons.child).sum()
if age_group == 'child':
target_persons = target_persons[target_persons.child]
if age_group == 'adult':
target_persons = target_persons[target_persons.adult]
spending = child_pop/(ca_monthly * 12)
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")
reform = mdf.calc_df(reform=CG_REFORM, group_vars=['MARS'], group_n65=True,
metric_vars=['aftertax_income', 'XTOT'])
reform.columns
### Calculate senior UBI.
Start with total revenue ($ billions).
new_rev_m = base.aftertax_income_m.sum() - reform.aftertax_income_m.sum()
new_rev_m / 1e3
How many seniors are there?
mdf.add_weighted_metrics(reform, 'n65')
n65_total_m = reform.n65_m.sum()
n65_total_m
Divide.
senior_ubi = new_rev_m / reform.n65_m.sum()
senior_ubi
### Add senior UBI to `aftertax_income` and recalculate
reform['ubi'] = senior_ubi * reform.n65
reform['aftertax_income'] = reform.aftertax_income + reform.ubi
mdf.add_weighted_metrics(reform, 'aftertax_income')
import microdf as mdf
tc.__version__
## Load data
Start with a standard `DataFrame`, then add a UBI manually in a reform copy.
base = mdf.calc_df(group_vars=['expanded_income', 'MARS', 'XTOT'],
metric_vars='aftertax_income')
reform = base.copy(deep=True)
UBI_PP = 10000
reform['ubi'] = reform.XTOT * UBI_PP
reform['aftertax_income'] = reform.aftertax_income + reform.ubi
mdf.add_weighted_metrics(reform, 'aftertax_income')
## `agg`
### Change in aftertax income by marital status.
mdf.agg(base, reform, 'MARS', 'aftertax_income')
### Also sum baseline `expanded_income`
mdf.agg(base, reform, 'MARS', 'aftertax_income', 'expanded_income')
### Also sum UBI amount
mdf.add_weighted_metrics(reform, 'ubi') # Creates ubi_m = ubi * s006 / 1e6.
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')