def simulate_reform_cd(year):
assert year is not None
TaxBenefitSystem = openfisca_france_data.init_country()
tax_benefit_system = TaxBenefitSystem()
reform = reform_cd.build_reform(tax_benefit_system)
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
used_as_input_variables = ['sal', 'cho', 'rst', 'age_en_mois', 'smic55'],
year = year,
tax_benefit_system = reform
)
reference_simulation = survey_scenario.new_simulation(debug = True, reference = True)
reform_simulation = survey_scenario.new_simulation(debug = True)
reform_data_frame_by_entity_key_plural = dict(
foyers = pandas.DataFrame(
dict([(name, reference_simulation.calculate_add(name)) for name in [
'impo',
'rfr',
]])
),
)
return reform_data_frame_by_entity_key_plural, reference_simulation
def reform_survey_simulation(reform = None, year = None, ind_variables = None, fam_variables = None,
foy_variables = None, men_variables = None, used_as_input_variables = None,
reform_specific_foy_variables = None):
assert reform is not None
assert year is not None
TaxBenefitSystem = openfisca_france_data.init_country()
tax_benefit_system = TaxBenefitSystem()
reform = reform.build_reform(tax_benefit_system)
input_data_frame = get_input_data_frame(year)
survey_scenario_reform = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
used_as_input_variables = used_as_input_variables,
year = year,
tax_benefit_system = reform
)
reference_simulation = survey_scenario_reform.new_simulation(debug = False, reference = True)
reference_data_frame_by_entity_key_plural = from_simulation_to_data_frame_by_entity_key_plural(
reference_simulation, ind_variables, fam_variables, foy_variables, men_variables)
reform_simulation = survey_scenario_reform.new_simulation(debug = False)
reform_data_frame_by_entity_key_plural = from_simulation_to_data_frame_by_entity_key_plural(
reform_simulation, ind_variables, fam_variables, foy_variables + reform_specific_foy_variables, men_variables)
return reform_data_frame_by_entity_key_plural, reference_data_frame_by_entity_key_plural
def test_survey_simulation():
year = 2009
TaxBenefitSystem = openfisca_france_data.init_country()
tax_benefit_system = TaxBenefitSystem()
input_data_frame = get_input_data_frame(year)
survey_scenario_reform = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
used_as_input_variables = ['sal', 'cho', 'rst', 'age_en_mois', 'smic55'],
year = year,
tax_benefit_system = tax_benefit_system
)
simulation = survey_scenario_reform.new_simulation(debug = False, reference = True)
simulation_data_frame_by_entity_key_plural = dict(
foyers = pandas.DataFrame(
dict([(name, simulation.calculate_add(name)) for name in [
'rfr',
'irpp',
'rbg',
'iaidrdi',
'rng',
'rni',
'ip_net',
'reductions',
'decile_rfr',
'weight_foyers',
]])
),
)
return simulation_data_frame_by_entity_key_plural
def test_calibration():
year = 2009
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
year = year,
)
survey_scenario.initialize_weights()
calibration = Calibration(survey_scenario)
calibration.parameters['method'] = 'linear'
print calibration.initial_total_population
calibration.total_population = calibration.initial_total_population * 1.123
print calibration.total_population
filename = os.path.join(
openfisca_france_data_location,
"openfisca_france_data",
"calibrations",
"calib_2006.csv"
)
calibration.set_inputs_margins_from_file(filename, 2006)
calibration.set_parameters('invlo', 3)
calibration.set_parameters('up', 3)
calibration.set_parameters('method', 'logit')
calibration.calibrate()
def test_calibration():
year = 2006
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
year = year,
)
survey_scenario.initialize_weights()
calibration = Calibration()
calibration.set_survey_scenario(survey_scenario)
calibration.parameters['method'] = 'linear'
print calibration.initial_total_population
calibration.total_population = calibration.initial_total_population * 1.123
print calibration.total_population
filename = os.path.join(
openfisca_france_data_location,
"openfisca_france_data",
"calibrations",
"calib_2006.csv"
)
calibration.set_inputs_margins_from_file(filename, 2006)
calibration.set_parameters('invlo', 3)
calibration.set_parameters('up', 3)
calibration.set_parameters('method', 'logit')
calibration.calibrate()
def test_survey_simulation():
year = 2009
TaxBenefitSystem = openfisca_france_data.init_country()
tax_benefit_system = TaxBenefitSystem()
input_data_frame = get_input_data_frame(year)
survey_scenario_reform = SurveyScenario().init_from_data_frame(
input_data_frame=input_data_frame,
used_as_input_variables=['sal', 'cho', 'rst', 'age_en_mois', 'smic55'],
year=year,
tax_benefit_system=tax_benefit_system)
simulation = survey_scenario_reform.new_simulation(debug=False,
reference=True)
simulation_data_frame_by_entity_key_plural = dict(foyers=pandas.DataFrame(
dict([(name, simulation.calculate_add(name)) for name in [
'rfr',
'irpp',
'rbg',
'iaidrdi',
'rng',
'rni',
'ip_net',
'reductions',
'decile_rfr',
'weight_foyers',
]])), )
return simulation_data_frame_by_entity_key_plural
def df_survey_simulation(reductions):
year = 2009
TaxBenefitSystem = openfisca_france_data.init_country()
tax_benefit_system = TaxBenefitSystem()
input_data_frame = get_input_data_frame(year)
survey_scenario_reference = SurveyScenario().init_from_data_frame(
input_data_frame=input_data_frame,
used_as_input_variables=['sal', 'cho', 'rst', 'age_en_mois', 'smic55'],
year=year,
tax_benefit_system=tax_benefit_system)
simulation = survey_scenario_reference.new_simulation()
# from openfisca_core import periods
# period = periods.period('year', 2007)
# period = period.start.offset('first-of', 'month').period('year')
# bareme = simulation.legislation_at(period.start).ir.bareme
data_frame_by_entity_key_plural = dict(foyers=pandas.DataFrame(
dict([(name, simulation.calculate_add(name)) for name in [
'rfr',
'irpp',
'rbg',
'iaidrdi',
'rng',
'ip_net',
'reductions',
'decile_rfr',
'weight_foyers',
] + reductions])), )
return data_frame_by_entity_key_plural
def test_weights_building():
year = 2009
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
year = year,
)
survey_scenario.new_simulation()
return survey_scenario.simulation
def test_weights_building():
year = 2009
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame=input_data_frame,
year=year,
)
survey_scenario.new_simulation()
return survey_scenario.simulation
def test_pivot_table_1d_mean(year=2009):
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame=input_data_frame,
year=year,
)
pivot_table = survey_scenario.compute_pivot_table(columns=['decile_rfr'],
values=['irpp'])
return pivot_table
def varying_survey_simulation(year = 2009, increment = 10, target = 'irpp', varying = 'rni', used_as_input_variables = None):
TaxBenefitSystem = openfisca_france_data.init_country()
tax_benefit_system = TaxBenefitSystem()
input_data_frame = get_input_data_frame(year)
# Simulation 1 : get varying and target
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
used_as_input_variables = used_as_input_variables,
year = year,
tax_benefit_system = tax_benefit_system
)
simulation = survey_scenario.new_simulation(debug = False)
output_data_frame = pandas.DataFrame(
dict([(name, simulation.calculate_add(name)) for name in [
target, varying, 'idfoy_original'
]]))
# Make input_data_frame_by_entity_key_plural from the previous input_data_frame and simulation
input_data_frames_by_entity_key_plural = \
from_input_df_to_entity_key_plural_df(input_data_frame, tax_benefit_system, simulation)
foyers = input_data_frames_by_entity_key_plural['idfoy']
foyers = pandas.merge(foyers, output_data_frame, on = 'idfoy_original')
# Incrementation of varying:
foyers[varying] = foyers[varying] + increment
# On remplace la nouvelle base dans le dictionnaire
input_data_frames_by_entity_key_plural['idfoy'] = foyers
# 2e simulation à partir de input_data_frame_by_entity_key_plural:
# TODO: fix used_as_input_variabels in the from_input_df_to_entity_key_plural_df() function
used_as_input_variables = used_as_input_variables + [varying]
TaxBenefitSystem = openfisca_france_data.init_country()
tax_benefit_system = TaxBenefitSystem()
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame = None,
input_data_frames_by_entity_key_plural = input_data_frames_by_entity_key_plural,
used_as_input_variables = used_as_input_variables,
year = year,
tax_benefit_system = tax_benefit_system,
)
simulation = survey_scenario.new_simulation(debug = False)
output_data_frame2 = pandas.DataFrame(
dict([(name, simulation.calculate_add(name)) for name in [
target, varying, 'idfoy_original'
]]))
output_data_frame2.rename(columns = {varying: '{}_2'.format(varying),
target: '{}_2'.format(target)}, inplace = True)
merged = pandas.merge(output_data_frame, output_data_frame2, on = 'idfoy_original')
merged['marginal_rate'] = marginal_rate_survey(merged, '{}'.format(target), '{}_2'.format(target), 'rni', 'rni_2')
merged['average_rate'] = average_rate(target = merged[target], varying = merged[varying])
return merged
def create_survey_scenario(year = None):
assert year is not None
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
used_as_input_variables = ['salaire_imposable', 'cho', 'rst', 'age_en_mois'],
year = year,
)
return survey_scenario
def test_weights_building():
year = 2009
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
used_as_input_variables = ['sal', 'cho', 'rst', 'age_en_mois'],
year = year,
)
survey_scenario.new_simulation()
return survey_scenario.simulation
def create_survey_scenario(year=None):
assert year is not None
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame=input_data_frame,
year=year,
)
survey_scenario.initialize_weights()
return survey_scenario
def test_weights_building():
year = 2009
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame=input_data_frame,
used_as_input_variables=['sal', 'cho', 'rst', 'age_en_mois'],
year=year,
)
survey_scenario.new_simulation()
return survey_scenario.simulation
def create_survey_scenario(year = None):
assert year is not None
input_data_frame = get_input_data_frame(year)
assert "wprm" in input_data_frame.columns
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
tax_benefit_system = base.france_data_tax_benefit_system,
year = year,
)
return survey_scenario
def create_survey_scenario(year = None):
assert year is not None
input_data_frame = get_input_data_frame(year)
assert "wprm" in input_data_frame.columns
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
tax_benefit_system = base.france_data_tax_benefit_system,
year = year,
)
return survey_scenario
def test_inflation():
year = 2009
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame=input_data_frame,
year=year,
)
survey_scenario.new_simulation()
target_by_variable = dict(salaire_imposable=1.2e08)
survey_scenario.inflate(target_by_variable=target_by_variable)
def test_pivot_table_1d_mean(year = 2009):
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
year = year,
)
pivot_table = survey_scenario.compute_pivot_table(
columns = ['decile_rfr'],
values = ['irpp']
)
return pivot_table
def build_by_extraction(year = None):
assert year is not None
df = get_input_data_frame(year)
output = df.ix[0:1]
for symbol in ['fam', 'foy', 'men']:
output['id{}_original'.format(symbol)] = output['id{}'.format(symbol)]
output.loc[0, 'sali'] = 20000
output.loc[1, 'sali'] = 10000
output['wprm'] = 100
output.to_csv(csv_file_realpath)
output.to_hdf(hdf5_file_realpath)
def build_by_extraction(year = None):
assert year is not None
df = get_input_data_frame(year)
output = df.ix[0:1]
for symbol in ['fam', 'foy', 'men']:
output['id{}_original'.format(symbol)] = output['id{}'.format(symbol)]
output.loc[0, 'sali'] = 20000
output.loc[1, 'sali'] = 10000
output['wprm'] = 100
output.to_csv(csv_file_realpath)
output.to_hdf(hdf5_file_realpath)
def test_inflation():
year = 2009
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
year = year,
)
survey_scenario.new_simulation()
target_by_variable = dict(
salaire_imposable = 1.2e08
)
survey_scenario.inflate(target_by_variable = target_by_variable)
def create_survey_scenario(data_year=2009, year=2013, reform=None):
assert year is not None
assert data_year is not None
input_data_frame = get_input_data_frame(data_year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame=input_data_frame,
tax_benefit_system=reform,
reference_tax_benefit_system=base.france_data_tax_benefit_system,
year=year,
)
return survey_scenario
def build_by_extraction(year=None):
assert year is not None
df = get_input_data_frame(year)
output = df.ix[0:1]
for symbol in ['fam', 'foy', 'men']:
output['id{}_original'.format(symbol)] = output['id{}'.format(symbol)]
output.loc[0, 'sali'] = 20000
output.loc[1, 'sali'] = 10000
output['wprm'] = 100
store = pandas.HDFStore(hdf5_file_realpath)
store.put(str(year), output)
store.close()
def create_survey_scenario(data_year = 2009, year = 2013, reform = None):
assert year is not None
assert data_year is not None
input_data_frame = get_input_data_frame(data_year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
tax_benefit_system = reform,
reference_tax_benefit_system = base.france_data_tax_benefit_system,
year = year,
)
return survey_scenario
def survey_simulate(used_as_input_variables, year, ind_variables = None, fam_variables = None, foy_variables = None,
men_variables = None):
year = year
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
used_as_input_variables = used_as_input_variables,
year = year,
)
simulation = survey_scenario.new_simulation()
data_frame_by_entity_key_plural = from_simulation_to_data_frame_by_entity_key_plural(
simulation, ind_variables, fam_variables, foy_variables, men_variables)
return data_frame_by_entity_key_plural, simulation
def test_survey_simulation():
year = 2009
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
used_as_input_variables = ['sal', 'cho', 'rst', 'age_en_mois', 'smic55'],
year = year,
)
simulation = survey_scenario.new_simulation()
data_frame_by_entity_key_plural = dict(
individus = pandas.DataFrame(
dict([(name, simulation.calculate(name)) for name in [
'idmen',
'quimen',
'idfoy',
'quifoy',
'idfam',
'quifam',
'age',
'champm_individus',
'sal',
'salaire_net',
# 'smic55',
'txtppb',
# salsuperbrut # TODO bug in 2006
]])
),
familles = pandas.DataFrame(
dict([(name, simulation.calculate_add(name)) for name in [
'af_nbenf',
'af',
'weight_familles',
]])
),
menages = pandas.DataFrame(
dict([(name, simulation.calculate(name)) for name in [
'revdisp',
]])
),
)
(data_frame_familles.weight_familles * data_frame_familles.af).sum() / 1e9 > 10
return data_frame_by_entity_key_plural, simulation
def test_survey_simulation():
year = 2009
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame=input_data_frame,
used_as_input_variables=['sal', 'cho', 'rst', 'age_en_mois', 'smic55'],
year=year,
)
simulation = survey_scenario.new_simulation()
data_frame_by_entity_key_plural = dict(
individus=pandas.DataFrame(
dict([
(name, simulation.calculate(name)) for name in [
'idmen',
'quimen',
'idfoy',
'quifoy',
'idfam',
'quifam',
'age',
'champm_individus',
'sal',
'salaire_net',
# 'smic55',
'txtppb',
# salsuperbrut # TODO bug in 2006
]
])),
familles=pandas.DataFrame(
dict([(name, simulation.calculate_add(name)) for name in [
'af_nbenf',
'af',
'weight_familles',
]])),
menages=pandas.DataFrame(
dict([(name, simulation.calculate(name)) for name in [
'revdisp',
]])),
)
(data_frame_familles.weight_familles *
data_frame_familles.af).sum() / 1e9 > 10
return data_frame_by_entity_key_plural, simulation
def test_survey_simulation():
year = 2009
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
year = year,
)
simulation = survey_scenario.new_simulation(trace = True)
data_frame_by_entity_key_plural = survey_scenario.create_data_frame_by_entity_key_plural(
variables = [
'aspa',
'aide_logement_montant_brut',
'idmen',
'quimen',
'idfoy',
'quifoy',
'idfam',
'quifam',
'age',
'activite',
'br_rmi_i',
'champm_individus',
'pensions_alimentaires_percues',
'salaire_imposable',
'salaire_net',
'smic55',
'txtppb',
'af_nbenf',
'af',
'br_rmi',
'rsa',
'rstnet',
'weight_familles',
'revdisp',
]
)
assert (
data_frame_by_entity_key_plural['familles'].weight_familles * data_frame_by_entity_key_plural['familles'].af
).sum() / 1e9 > 10
return data_frame_by_entity_key_plural, simulation
def test_survey_simulation():
year = 2009
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame=input_data_frame,
year=year,
)
simulation = survey_scenario.new_simulation(trace=True)
data_frame_by_entity_key_plural = survey_scenario.create_data_frame_by_entity_key_plural(
variables=[
'aspa',
'aide_logement_montant_brut',
'idmen',
'quimen',
'idfoy',
'quifoy',
'idfam',
'quifam',
'age',
'activite',
'br_rmi_i',
'champm_individus',
'pensions_alimentaires_percues',
'salaire_imposable',
'salaire_net',
'smic55',
'txtppb',
'af_nbenf',
'af',
'br_rmi',
'rsa',
'rstnet',
'weight_familles',
'revdisp',
])
assert (data_frame_by_entity_key_plural['familles'].weight_familles *
data_frame_by_entity_key_plural['familles'].af).sum() / 1e9 > 10
return data_frame_by_entity_key_plural, simulation
def simulate_reform_cd(year):
assert year is not None
TaxBenefitSystem = openfisca_france_data.init_country()
tax_benefit_system = TaxBenefitSystem()
reform = reform_cd.build_reform(tax_benefit_system)
input_data_frame = get_input_data_frame(year)
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame=input_data_frame,
used_as_input_variables=['sal', 'cho', 'rst', 'age_en_mois', 'smic55'],
year=year,
tax_benefit_system=reform)
reference_simulation = survey_scenario.new_simulation(debug=True,
reference=True)
reform_simulation = survey_scenario.new_simulation(debug=True)
reform_data_frame_by_entity_key_plural = dict(foyers=pandas.DataFrame(
dict([(name, reference_simulation.calculate_add(name)) for name in [
'impo',
'rfr',
]])), )
return reform_data_frame_by_entity_key_plural, reference_simulation
def df_survey_simulation(reductions):
year = 2009
TaxBenefitSystem = openfisca_france_data.init_country()
tax_benefit_system = TaxBenefitSystem()
input_data_frame = get_input_data_frame(year)
survey_scenario_reference = SurveyScenario().init_from_data_frame(
input_data_frame = input_data_frame,
used_as_input_variables = ['sal', 'cho', 'rst', 'age_en_mois', 'smic55'],
year = year,
tax_benefit_system = tax_benefit_system
)
simulation = survey_scenario_reference.new_simulation()
# from openfisca_core import periods
# period = periods.period('year', 2007)
# period = period.start.offset('first-of', 'month').period('year')
# bareme = simulation.legislation_at(period.start).ir.bareme
data_frame_by_entity_key_plural = dict(
foyers = pandas.DataFrame(
dict([(name, simulation.calculate_add(name)) for name in [
'rfr',
'irpp',
'rbg',
'iaidrdi',
'rng',
'ip_net',
'reductions',
'decile_rfr',
'weight_foyers',
] + reductions
])
),
)
return data_frame_by_entity_key_plural
def varying_survey_simulation(year=2009,
increment=10,
target='irpp',
varying='rni',
used_as_input_variables=None):
TaxBenefitSystem = openfisca_france_data.init_country()
tax_benefit_system = TaxBenefitSystem()
input_data_frame = get_input_data_frame(year)
# Simulation 1 : get varying and target
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame=input_data_frame,
used_as_input_variables=used_as_input_variables,
year=year,
tax_benefit_system=tax_benefit_system)
simulation = survey_scenario.new_simulation(debug=False)
output_data_frame = pandas.DataFrame(
dict([(name, simulation.calculate_add(name))
for name in [target, varying, 'idfoy_original']]))
# Make input_data_frame_by_entity_key_plural from the previous input_data_frame and simulation
input_data_frames_by_entity_key_plural = \
from_input_df_to_entity_key_plural_df(input_data_frame, tax_benefit_system, simulation)
foyers = input_data_frames_by_entity_key_plural['idfoy']
foyers = pandas.merge(foyers, output_data_frame, on='idfoy_original')
# Incrementation of varying:
foyers[varying] = foyers[varying] + increment
# On remplace la nouvelle base dans le dictionnaire
input_data_frames_by_entity_key_plural['idfoy'] = foyers
# 2e simulation à partir de input_data_frame_by_entity_key_plural:
# TODO: fix used_as_input_variabels in the from_input_df_to_entity_key_plural_df() function
used_as_input_variables = used_as_input_variables + [varying]
TaxBenefitSystem = openfisca_france_data.init_country()
tax_benefit_system = TaxBenefitSystem()
survey_scenario = SurveyScenario().init_from_data_frame(
input_data_frame=None,
input_data_frames_by_entity_key_plural=
input_data_frames_by_entity_key_plural,
used_as_input_variables=used_as_input_variables,
year=year,
tax_benefit_system=tax_benefit_system,
)
simulation = survey_scenario.new_simulation(debug=False)
output_data_frame2 = pandas.DataFrame(
dict([(name, simulation.calculate_add(name))
for name in [target, varying, 'idfoy_original']]))
output_data_frame2.rename(columns={
varying: '{}_2'.format(varying),
target: '{}_2'.format(target)
},
inplace=True)
merged = pandas.merge(output_data_frame,
output_data_frame2,
on='idfoy_original')
merged['marginal_rate'] = marginal_rate_survey(merged, '{}'.format(target),
'{}_2'.format(target),
'rni', 'rni_2')
merged['average_rate'] = average_rate(target=merged[target],
varying=merged[varying])
return merged
del df['is{}'.format(p)], df['p{}'.format(p)]
df['decile_of_{}'.format(
variable)] = number_of_quantile - df['decile_of_{}'.format(variable)]
return
if __name__ == '__main__':
import logging
import time
log = logging.getLogger(__name__)
import sys
logging.basicConfig(level=logging.INFO, stream=sys.stdout)
start = time.time()
year = 2009
input_data_frame = get_input_data_frame(year)
revimp = input_data_frame[[
'salaire_imposable', 'quifoy', 'idfoy_original'
]][input_data_frame.quifoy == 0]
# revimp.revimp[np.isnan(revimp.revimp)] = 0
ind_variables = [
'idmen', 'quimen', 'idfoy', 'salaire_imposable', 'salaire_net'
]
# foy_variables = ['irpp', 'decile_rfr', 'decile_rni', 'weight_foyers', 'idfoy_original', 'rfr']
foy_variables = [
'irpp', 'decile_rfr', 'weight_foyers', 'idfoy_original', 'rfr'
]
used_as_input_variables = [
'salaire_imposable', 'cho', 'rst', 'age_en_mois', 'smic55'
]
df['decile_of_{}'.format(variable)] = df['decile_of_{}'.format(variable)] + df['is{}'.format(p)].astype('int')
del df['is{}'.format(p)], df['p{}'.format(p)]
df['decile_of_{}'.format(variable)] = number_of_quantile - df['decile_of_{}'.format(variable)]
return
if __name__ == '__main__':
import logging
import time
log = logging.getLogger(__name__)
import sys
logging.basicConfig(level = logging.INFO, stream = sys.stdout)
start = time.time()
year = 2009
input_data_frame = get_input_data_frame(year)
revimp = input_data_frame[['salaire_imposable', 'quifoy', 'idfoy_original']][input_data_frame.quifoy == 0]
# revimp.revimp[np.isnan(revimp.revimp)] = 0
ind_variables = ['idmen', 'quimen', 'idfoy', 'salaire_imposable', 'salaire_net']
# foy_variables = ['irpp', 'decile_rfr', 'decile_rni', 'weight_foyers', 'idfoy_original', 'rfr']
foy_variables = ['irpp', 'decile_rfr', 'weight_foyers', 'idfoy_original', 'rfr']
used_as_input_variables = ['salaire_imposable', 'cho', 'rst', 'age_en_mois', 'smic55']
df_by_entity_key_plural, simulation = survey_simulate(used_as_input_variables, year, ind_variables,
foy_variables = foy_variables)
df_foyers = df_by_entity_key_plural['foyers'][['weight_foyers', 'idfoy_original', 'rfr']]
df = pandas.merge(df_foyers, revimp, on = 'idfoy_original')
weight = 'weight_foyers'
number_of_quantile = 10
# make_weighted_deciles_of_variable(df, 'revimp', weight, number_of_quantile)
