def build_erf_aggregates(variables = None, year = 2006, unit = 1e6):
"""
Fetch the relevant aggregates from erf data
"""
erf = DataCollection(year=year)
if variables is not None and "wprm" not in variables:
variables.append("wprm")
print 'Fetching aggregates from erf %s data' %str(year)
df = erf.get_of_values(variables=variables, table = "erf_menage")
of2erf = get_of2erf()
erf2of = get_erf2of()
df.rename(columns = erf2of, inplace = True)
wprm = df["wprm"]
for col in df.columns:
try:
df[col] = df[col].astype(np.float64)
except:
pass
df = df.mul(wprm, axis = 0)
for col in list(set(df.columns) - set(['ident', 'wprm'])):
try:
df[col] = df[col].sum()/1e6
except:
pass
return df.ix[0:1] # Aggregate so we only need 1 row
def build_erf_aggregates(variables=None, year=2006, unit=1e6):
"""
Fetch the relevant aggregates from erf data
"""
erf = DataCollection(year=year)
if variables is not None and "wprm" not in variables:
variables.append("wprm")
print 'Fetching aggregates from erf %s data' % str(year)
df = erf.get_of_values(variables=variables, table="erf_menage")
of2erf = get_of2erf()
erf2of = get_erf2of()
df.rename(columns=erf2of, inplace=True)
wprm = df["wprm"]
for col in df.columns:
try:
df[col] = df[col].astype(np.float64)
except:
pass
df = df.mul(wprm, axis=0)
for col in list(set(df.columns) - set(['ident', 'wprm'])):
try:
df[col] = df[col].sum() / 1e6
except:
pass
return df.ix[0:1] # Aggregate so we only need 1 row
def preproc(self):
erf_menage = self.erf_menage
erf_eec_indivi = self.erf_eec_indivi
simu_aggr_tables = self.simu_aggr_tables
simu_nonaggr_tables = self.simu_nonaggr_tables
def get_all_ancestors(varlist):
if len(varlist) == 0:
return []
else:
if varlist[0]._parents == set():
return ([varlist[0]] + get_all_ancestors(varlist[1:]))
else:
return ([varlist[0]] +
get_all_ancestors(list(varlist[0]._parents)) +
get_all_ancestors(varlist[1:]))
# We want to get all ancestors + children + the options that we're going to encounter
parents = map(
lambda x: self.simulation.output_table.column_by_name.get(x),
[self.variable])
parents = get_all_ancestors(parents)
options = []
for varcol in parents:
options.extend(varcol._option.keys())
options = list(set(options))
#print options
parents = map(lambda x: x.name, parents)
for var in [self.variable]:
children = set()
varcol = self.simulation.output_table.column_by_name.get(var)
children = children.union(
set(map(lambda x: x.name, varcol._children)))
variables = list(set(parents + list(children)))
#print variables
del parents, children
gc.collect()
def get_var(variable):
variables = [variable]
return self.simulation.aggregated_by_entity(entity="men",
variables=variables,
all_output_vars=False,
force_sum=True)[0]
simu_aggr_tables = get_var(variables[0])
for var in variables[1:]:
simu_aggr_tables = simu_aggr_tables.merge(
get_var(var)[['idmen', var]], on='idmen', how='outer')
# We load the data from erf table in case we have to pick data there
erf_data = DataCollection(year=self.simulation.datesim.year)
os.system('cls')
todo = set(variables + ["ident", "wprm"]).union(set(options))
print 'Variables or equivalents to fetch :'
print todo
'''
Méthode générale pour aller chercher les variables de l'erf/eec
( qui n'ont pas forcément le même nom
et parfois sont les variables utilisées pour créér l'of ):
1 - essayer le get_of2erf, ça doit marcher pour les variables principales ( au moins les aggrégats
que l'on compare )
Si les variables ne sont pas directement dans la table,
elles ont été calculées à partir d'autres variables de données erf/eec
donc chercher dans :
2 - build_survey
3 - model/model.py qui dira éventuellement dans quel module de model/ chercher
Le 'print todo' vous indique quelles variables chercher
( attention à ne pas inclure les enfants directs )
L'utilisation du Ctrl-H est profitable !
'''
fetch_eec = [
'statut', 'titc', 'chpub', 'encadr', 'prosa', 'age', 'naim',
'naia', 'noindiv'
]
fetch_erf = [
'zsali', 'af', 'ident', 'wprm', 'noi', 'noindiv', 'quelfic'
]
erf_df = erf_data.get_of_values(variables=fetch_erf,
table="erf_indivi")
eec_df = erf_data.get_of_values(variables=fetch_eec,
table="eec_indivi")
erf_eec_indivi = erf_df.merge(eec_df, on='noindiv', how='inner')
assert 'quelfic' in erf_eec_indivi.columns, "quelfic not in erf_indivi columns"
del eec_df, erf_df
# We then get the aggregate variables for the menage ( mainly to compare with of )
print 'Loading data from erf_menage table'
erf_menage = erf_data.get_of_values(variables=list(todo) + ['quelfic'],
table="erf_menage")
del todo
gc.collect()
assert 'ident' in erf_menage.columns, "ident not in erf_menage.columns"
from openfisca_france.data.erf import get_erf2of
erf2of = get_erf2of()
erf_menage.rename(columns=erf2of, inplace=True)
# We get the options from the simulation non aggregated tables:
# First from the output_table
# We recreate the noindiv in output_table
self.simulation.output_table.table[
'noindiv'] = 100 * self.simulation.output_table.table.idmen_ind + self.simulation.output_table.table.noi_ind
self.simulation.output_table.table[
'noindiv'] = self.simulation.output_table.table['noindiv'].astype(
np.int64)
s1 = [
var for var in set(options).intersection(
set(self.simulation.output_table.table.columns))
] + ['idmen_ind', 'quimen_ind', 'noindiv']
simu_nonaggr_tables = (self.simulation.output_table.table)[s1]
simu_nonaggr_tables.rename(columns={
'idmen_ind': 'idmen',
'quimen_ind': 'quimen'
},
inplace=True)
assert 'noindiv' in simu_nonaggr_tables.columns
# If not found, we dwelve into the input_table
if (set(s1) -
set(['idmen_ind', 'quimen_ind', 'noindiv'])) < set(options):
assert 'noindiv' in self.simulation.input_table.table.columns, "'noindiv' not in simulation.input_table.table.columns"
s2 = [
var for var in (set(options).intersection(
set(self.simulation.input_table.table.columns)) - set(s1))
] + ['noindiv']
#print s2
temp = self.simulation.input_table.table[s2]
simu_nonaggr_tables = simu_nonaggr_tables.merge(temp,
on='noindiv',
how='inner',
sort=False)
del s2, temp
del s1
gc.collect()
simu_nonaggr_tables = simu_nonaggr_tables[
list(set(options)) + ['idmen', 'quimen', 'noindiv']]
#print options, variables
assert 'idmen' in simu_nonaggr_tables.columns, 'Idmen not in simu_nonaggr_tables columns'
# Check the idmens that are not common
erf_menage.rename(columns={'ident': 'idmen'}, inplace=True)
print "\n"
print 'Checking if idmen is here...'
print '\n ERF : '
print 'idmen' in erf_menage.columns
print "\n Simulation output"
print 'idmen' in simu_aggr_tables.columns
print "\n"
#print 'Dropping duplicates of idmen for both tables...'
assert not erf_menage["idmen"].duplicated().any(
), "Duplicated idmen in erf_menage"
#erf_menage.drop_duplicates('idmen', inplace = True)
simu_aggr_tables.drop_duplicates('idmen', inplace=True)
assert not simu_aggr_tables["idmen"].duplicated().any(
), "Duplicated idmen in of"
print 'Checking mismatching idmen... '
s1 = set(erf_menage['idmen']) - (set(simu_aggr_tables['idmen']))
if s1:
print "idmen that aren't in simu_aggr_tables : %s" % str(len(s1))
pass
s2 = (set(simu_aggr_tables['idmen'])) - set(erf_menage['idmen'])
if s2:
print "idmen that aren't in erf_menage : %s" % str(len(s2))
pass
del s1, s2
# Restrict to common idmens and merge
s3 = set(erf_menage['idmen']).intersection(
set(simu_aggr_tables['idmen']))
print "Restricting to %s common idmen... \n" % str(len(s3))
erf_menage = erf_menage[erf_menage['idmen'].isin(s3)]
simu_aggr_tables = simu_aggr_tables[simu_aggr_tables['idmen'].isin(s3)]
del s3
gc.collect()
#print erf_menage.columns
#print simu_aggr_tables.columns
# Compare differences across of and erf dataframes
print "Comparing differences between dataframes... \n"
colcom = (set(erf_menage.columns).intersection(
set(simu_aggr_tables.columns))) - set(['idmen', 'wprm'])
print 'Common variables: '
print colcom
erf_menage.reset_index(inplace=True)
simu_aggr_tables.reset_index(inplace=True)
for col in colcom:
temp = set(
erf_menage['idmen'][erf_menage[col] != simu_aggr_tables[col]])
print "Numbers of idmen that aren't equal on variable %s : %s \n" % (
col, str(len(temp)))
del temp
self.erf_menage = erf_menage
self.erf_eec_indivi = erf_eec_indivi
self.simu_aggr_tables = simu_aggr_tables
self.simu_nonaggr_tables = simu_nonaggr_tables
def test(year=2006, variables=['af']):
simulation = SurveySimulation()
survey_filename = os.path.join(model.DATA_DIR, 'sources', 'test.h5')
simulation.set_config(year=year, survey_filename=survey_filename)
simulation.set_param()
simulation.compute()
# of_aggregates = Aggregates()
# of_aggregates.set_simulation(simulation)
# of_aggregates.compute()
# print of_aggregates.aggr_frame
#
# from openfisca_france.data.erf.aggregates import build_erf_aggregates
# temp = (build_erf_aggregates(variables=variables, year= year))
# print temp
# return
variable = "af"
debugger = Debugger()
debugger.set_simulation(simulation)
debugger.set_variable(variable)
debugger.show_aggregates()
def get_all_ancestors(varlist):
if len(varlist) == 0:
return []
else:
if varlist[0]._parents == set():
return ([varlist[0]] + get_all_ancestors(varlist[1:]))
else:
return ([varlist[0]] +
get_all_ancestors(list(varlist[0]._parents)) +
get_all_ancestors(varlist[1:]))
# We want to get all ancestors + children + the options that we're going to encounter
parents = map(lambda x: simulation.output_table.column_by_name.get(x),
variables)
parents = get_all_ancestors(parents)
options = []
for varcol in parents:
options.extend(varcol._option.keys())
options = list(set(options))
#print options
parents = map(lambda x: x.name, parents)
for var in variables:
children = set()
varcol = simulation.output_table.column_by_name.get(var)
children = children.union(set(map(lambda x: x.name, varcol._children)))
variables = list(set(parents + list(children)))
#print variables
del parents, children
gc.collect()
def get_var(variable):
variables = [variable]
return simulation.aggregated_by_entity(entity="men",
variables=variables,
all_output_vars=False,
force_sum=True)[0]
simu_aggr_tables = get_var(variables[0])
for var in variables[1:]:
simu_aggr_tables = simu_aggr_tables.merge(get_var(var)[['idmen', var]],
on='idmen',
how='outer')
# We load the data from erf table in case we have to pick data there
erf_data = DataCollection(year=year)
os.system('cls')
todo = set(variables + ["ident", "wprm"]).union(set(options))
print 'Variables or equivalents to fetch :'
print todo
'''
Méthode générale pour aller chercher les variables de l'erf/eec
( qui n'ont pas forcément le même nom
et parfois sont les variables utilisées pour créér l'of ):
1 - essayer le get_of2erf, ça doit marcher pour les variables principales ( au moins les aggrégats
que l'on compare )
Si les variables ne sont pas directement dans la table,
elles ont été calculées à partir d'autres variables de données erf/eec
donc chercher dans :
2 - build_survey
3 - model/model.py qui dira éventuellement dans quel module de model/ chercher
Le 'print todo' vous indique quelles variables chercher
( attention à ne pas inclure les enfants directs )
L'utilisation du Ctrl-H est profitable !
'''
fetch_eec = [
'statut', 'titc', 'chpub', 'encadr', 'prosa', 'age', 'naim', 'naia',
'noindiv'
]
fetch_erf = ['zsali', 'af', 'ident', 'wprm', 'noi', 'noindiv', 'quelfic']
erf_df = erf_data.get_of_values(variables=fetch_erf, table="erf_indivi")
eec_df = erf_data.get_of_values(variables=fetch_eec, table="eec_indivi")
erf_eec_indivi = erf_df.merge(eec_df, on='noindiv', how='inner')
assert 'quelfic' in erf_eec_indivi.columns, "quelfic not in erf_indivi columns"
del eec_df, erf_df
# We then get the aggregate variables for the menage ( mainly to compare with of )
print 'Loading data from erf_menage table'
erf_menage = erf_data.get_of_values(variables=list(todo) + ['quelfic'],
table="erf_menage")
del todo
gc.collect()
assert 'ident' in erf_menage.columns, "ident not in erf_menage.columns"
from openfisca_france.data.erf import get_erf2of
erf2of = get_erf2of()
erf_menage.rename(columns=erf2of, inplace=True)
# We get the options from the simulation non aggregated tables:
# First from the output_table
# We recreate the noindiv in output_table
simulation.output_table.table[
'noindiv'] = 100 * simulation.output_table.table.idmen_ind + simulation.output_table.table.noi_ind
simulation.output_table.table['noindiv'] = simulation.output_table.table[
'noindiv'].astype(np.int64)
s1 = [
var for var in set(options).intersection(
set(simulation.output_table.table.columns))
] + ['idmen_ind', 'quimen_ind', 'noindiv']
simu_nonaggr_tables = (simulation.output_table.table)[s1]
simu_nonaggr_tables.rename(columns={
'idmen_ind': 'idmen',
'quimen_ind': 'quimen'
},
inplace=True)
assert 'noindiv' in simu_nonaggr_tables.columns
# If not found, we dwelve into the input_table
if (set(s1) - set(['idmen_ind', 'quimen_ind', 'noindiv'])) < set(options):
assert 'noindiv' in simulation.input_table.table.columns, "'noindiv' not in simulation.input_table.table.columns"
s2 = [
var for var in (set(options).intersection(
set(simulation.input_table.table.columns)) - set(s1))
] + ['noindiv']
#print s2
temp = simulation.input_table.table[s2]
simu_nonaggr_tables = simu_nonaggr_tables.merge(temp,
on='noindiv',
how='inner',
sort=False)
del s2, temp
del s1
gc.collect()
simu_nonaggr_tables = simu_nonaggr_tables[list(set(options)) +
['idmen', 'quimen', 'noindiv']]
#print options, variables
assert 'idmen' in simu_nonaggr_tables.columns, 'Idmen not in simu_nonaggr_tables columns'
# Check the idmens that are not common
erf_menage.rename(columns={'ident': 'idmen'}, inplace=True)
print "\n"
print 'Checking if idmen is here...'
print '\n ERF : '
print 'idmen' in erf_menage.columns
print "\n Simulation output"
print 'idmen' in simu_aggr_tables.columns
print "\n"
#print 'Dropping duplicates of idmen for both tables...'
assert not erf_menage["idmen"].duplicated().any(
), "Duplicated idmen in erf_menage"
#erf_menage.drop_duplicates('idmen', inplace = True)
simu_aggr_tables.drop_duplicates('idmen', inplace=True)
assert not simu_aggr_tables["idmen"].duplicated().any(
), "Duplicated idmen in of"
print 'Checking mismatching idmen... '
s1 = set(erf_menage['idmen']) - (set(simu_aggr_tables['idmen']))
if s1:
print "idmen that aren't in simu_aggr_tables : %s" % str(len(s1))
pass
s2 = (set(simu_aggr_tables['idmen'])) - set(erf_menage['idmen'])
if s2:
print "idmen that aren't in erf_menage : %s" % str(len(s2))
pass
del s1, s2
# Restrict to common idmens and merge
s3 = set(erf_menage['idmen']).intersection(set(simu_aggr_tables['idmen']))
print "Restricting to %s common idmen... \n" % str(len(s3))
erf_menage = erf_menage[erf_menage['idmen'].isin(s3)]
simu_aggr_tables = simu_aggr_tables[simu_aggr_tables['idmen'].isin(s3)]
del s3
gc.collect()
#print erf_menage.columns
#print simu_aggr_tables.columns
# Compare differences across of and erf dataframes
print "Comparing differences between dataframes... \n"
colcom = (set(erf_menage.columns).intersection(
set(simu_aggr_tables.columns))) - set(['idmen', 'wprm'])
print 'Common variables: '
print colcom
erf_menage.reset_index(inplace=True)
simu_aggr_tables.reset_index(inplace=True)
for col in colcom:
temp = set(
erf_menage['idmen'][erf_menage[col] != simu_aggr_tables[col]])
print "Numbers of idmen that aren't equal on variable %s : %s \n" % (
col, str(len(temp)))
del temp
# Detect the biggest differences
bigtable = merge(erf_menage,
simu_aggr_tables,
on='idmen',
how='inner',
suffixes=('_erf', '_of'))
print 'Length of new dataframe is %s' % str(len(bigtable))
#print bigtable.columns
bigtable.set_index('idmen', drop=False, inplace=True)
already_met = []
options_met = []
for col in colcom:
bigtemp = None
table = bigtable[and_(bigtable[col + '_erf'] != 0,
bigtable[col + '_of'] != 0)]
table[col] = (table[col + '_erf'] - table[col + '_of']
) / table[col + '_erf'] #Difference relative
table[col] = table[col].apply(lambda x: abs(x))
print 'Minimum difference between the two tables for %s is %s' % (
col, str(table[col].min()))
print 'Maximum difference between the two tables for %s is %s' % (
col, str(table[col].max()))
print table[col].describe()
try:
assert len(table[col]) == len(table['wprm_of']), "PINAGS"
dec, values = mwp(table[col],
np.arange(1, 11),
table['wprm_of'],
2,
return_quantiles=True)
#print sorted(values)
dec, values = mwp(table[col],
np.arange(1, 101),
table['wprm_erf'],
2,
return_quantiles=True)
#print sorted(values)[90:]
del dec, values
gc.collect()
except:
#print 'Weighted percentile method didnt work for %s' %col
pass
print "\n"
# Show the relevant information for the most deviant households
table.sort(columns=col, ascending=False, inplace=True)
#print table[col][0:10].to_string()
if bigtemp is None:
bigtemp = {
'table': table[[col, col + '_of', col + '_erf',
'idmen']][0:10],
'options': None
}
bigtemp['table'][col + 'div'] = bigtemp['table'][
col + '_of'] / bigtemp['table'][col + '_erf']
print bigtemp['table'].to_string()
'''
bigtemp is the table which will get filled little by little by the relevant variables.
Up to the last rows of code 'table' refers to a table of aggregated values,
while 'options is a table of individual variables.
The reason we call it in a dictionnary is also because we modify it inside the recursive function 'iter_on parents',
and it causes an error in Python unless for certain types like dictionnary values.
'''
#print "\n"
# If variable is a Prestation, we show the dependancies
varcol = simulation.output_table.column_by_name.get(col)
if isinstance(varcol, Prestation):
'''
For the direct children
'''
if not varcol._children is None:
ch_to_fetch = list(varcol._children)
ch_to_fetch = map(lambda x: x.name, ch_to_fetch)
ch_fetched = []
if set(ch_to_fetch) <= set(simu_aggr_tables.columns):
print "Variables which need %s to be computed :\n %s \n" % (
col, str(ch_to_fetch))
for var in ch_to_fetch:
if var + '_of' in table.columns:
ch_fetched.append(var + '_of')
else:
ch_fetched.append(var)
elif set(ch_to_fetch) <= set(simu_aggr_tables.columns).union(
erf_menage.columns):
print "Variables which need %s to be computed (some missing picked in erf):\n %s \n" % (
col, str(ch_to_fetch))
for var in ch_to_fetch:
if var in simu_aggr_tables.columns:
if var + '_of' in table.columns:
ch_fetched.append(var + '_of')
elif var + '_erf' in table.columns:
ch_fetched.append(var + '_erf')
else:
ch_fetched.append(var)
else:
print "Variables which need %s to be computed (some missing):\n %s \n" % (
col, str(ch_to_fetch))
for var in ch_to_fetch:
if var in simu_aggr_tables.columns:
if var + '_of' in table.columns:
ch_fetched.append(var + '_of')
elif var in erf_menage.columns:
if var + '_erf' in table.columns:
ch_fetched.append(var + '_erf')
print table[[col] + ch_fetched][0:10]
print "\n"
del ch_to_fetch, ch_fetched
'''
For the parents
'''
def iter_on_parents(varcol):
if (varcol._parents == set() and varcol._option
== {}) or varcol.name in already_met:
return
else:
par_to_fetch = list(varcol._parents)
par_to_fetch = map(lambda x: x.name, par_to_fetch)
par_fetched = []
if set(par_fetched) <= set(simu_aggr_tables.columns):
#print "Variables the prestation %s depends of :\n %s \n" %(varcol.name, str(par_fetched))
for var in par_fetched:
if var + '_of' in table.columns:
par_fetched.append(var + '_of')
else:
par_fetched.append(var)
elif set(par_fetched) <= set(
simu_aggr_tables.columns).union(
erf_menage.columns):
#print "Variables the prestation %s depends of (some missing picked in erf):\n %s \n" %(varcol.name,str(par_fetched))
for var in par_fetched:
if var in simu_aggr_tables.columns:
if var + '_of' in table.columns:
par_fetched.append(var + '_of')
elif var + '_erf' in table.columns:
par_fetched.append(var + '_erf')
else:
par_fetched.append(var)
else:
for var in par_fetched:
if var in simu_aggr_tables.columns:
if var + '_of' in table.columns:
par_fetched.append(var + '_of')
elif var in erf_menage.columns:
if var + '_erf' in table.columns:
par_fetched.append(var + '_erf')
if len(par_fetched) > 0:
#print "Variables the prestation %s depends of (some missing):\n %s \n" %(varcol.name, str(par_fetched))
pass
else:
#print "Variables the prestation %s depends of couldn't be found :\n %s \n" %(varcol.name, str(par_fetched))
pass
if len(par_fetched) > 0:
temp = table[[col, 'idmen'] + par_fetched][0:10]
bigtemp['table'] = pd.merge(temp,
bigtemp['table'],
how='inner')
#print temp.to_string(), "\n"
if varcol._option != {} and not set(
varcol._option.keys()) < set(options_met):
vars_to_fetch = list(
set(varcol._option.keys()) - set(options_met))
#print "and the options to current variable %s for the id's with strongest difference :\n %s \n" %(varcol.name, varcol._option.keys())
liste = [i for i in range(0, 10)]
liste = map(lambda x: table['idmen'].iloc[x], liste)
temp = simu_nonaggr_tables[
['idmen', 'quimen', 'noindiv'] +
vars_to_fetch][simu_nonaggr_tables['idmen'].isin(
table['idmen'][0:10])]
temp_sorted = temp[temp['idmen'] == liste[0]]
for i in xrange(1, 10):
temp_sorted = temp_sorted.append(
temp[temp['idmen'] == liste[i]])
if bigtemp['options'] is None:
bigtemp['options'] = temp_sorted
bigtemp['options'] = bigtemp['options'].merge(
erf_eec_indivi, on='noindiv', how='outer')
else:
bigtemp['options'] = bigtemp['options'].merge(
temp_sorted,
on=['noindiv', 'idmen', 'quimen'],
how='outer')
# temp_sorted.set_index(['idmen', 'quimen'], drop = True, inplace = True) # If we do that
del temp, temp_sorted
gc.collect()
already_met.append(varcol.name)
options_met.extend(varcol._option.keys())
for var in varcol._parents:
iter_on_parents(var)
iter_on_parents(varcol)
# We merge the aggregate table with the option table ( for each individual in entity )
bigtemp['table'] = bigtemp['table'].merge(bigtemp['options'],
how='left',
on='idmen',
suffixes=('(agg)',
'(ind)'))
# Reshaping the table to group by descending error on col, common entities
bigtemp['table'].sort(columns=['af', 'quimen'],
ascending=[False, True],
inplace=True)
bigtemp['table'] = bigtemp['table'].groupby(['idmen', 'quimen'],
sort=False).sum()
print "Table of values for %s dependencies : \n" % col
print bigtemp['table'].to_string()
del bigtemp['table'], bigtemp['options']
gc.collect()
def preproc(self):
erf_menage = self.erf_menage
erf_eec_indivi = self.erf_eec_indivi
simu_aggr_tables = self.simu_aggr_tables
simu_nonaggr_tables = self.simu_nonaggr_tables
def get_all_ancestors(varlist):
if len(varlist) == 0:
return []
else:
if varlist[0]._parents == set():
return ([varlist[0]]
+ get_all_ancestors(varlist[1:]))
else:
return ([varlist[0]]
+ get_all_ancestors(list(varlist[0]._parents))
+ get_all_ancestors(varlist[1:]))
# We want to get all ancestors + children + the options that we're going to encounter
parents = map(lambda x: self.simulation.output_table.column_by_name.get(x), [self.variable])
parents = get_all_ancestors(parents)
options = []
for varcol in parents:
options.extend(varcol._option.keys())
options = list(set(options))
#print options
parents = map(lambda x: x.name, parents)
for var in [self.variable]:
children = set()
varcol = self.simulation.output_table.column_by_name.get(var)
children = children.union(set(map(lambda x: x.name, varcol._children)))
variables = list(set(parents + list(children)))
#print variables
del parents, children
gc.collect()
def get_var(variable):
variables =[variable]
return self.simulation.aggregated_by_entity(entity="men", variables=variables,
all_output_vars = False, force_sum=True)[0]
simu_aggr_tables = get_var(variables[0])
for var in variables[1:]:
simu_aggr_tables = simu_aggr_tables.merge(get_var(var)[['idmen', var]], on = 'idmen', how = 'outer')
# We load the data from erf table in case we have to pick data there
erf_data = DataCollection(year= self.simulation.datesim.year)
os.system('cls')
todo = set(variables + ["ident", "wprm"]).union(set(options))
print 'Variables or equivalents to fetch :'
print todo
'''
Méthode générale pour aller chercher les variables de l'erf/eec
( qui n'ont pas forcément le même nom
et parfois sont les variables utilisées pour créér l'of ):
1 - essayer le get_of2erf, ça doit marcher pour les variables principales ( au moins les aggrégats
que l'on compare )
Si les variables ne sont pas directement dans la table,
elles ont été calculées à partir d'autres variables de données erf/eec
donc chercher dans :
2 - build_survey
3 - model/model.py qui dira éventuellement dans quel module de model/ chercher
Le 'print todo' vous indique quelles variables chercher
( attention à ne pas inclure les enfants directs )
L'utilisation du Ctrl-H est profitable !
'''
fetch_eec = ['statut','titc','chpub','encadr','prosa','age','naim','naia','noindiv']
fetch_erf = ['zsali','af','ident','wprm','noi','noindiv','quelfic']
erf_df = erf_data.get_of_values(variables= fetch_erf, table="erf_indivi")
eec_df = erf_data.get_of_values(variables= fetch_eec, table="eec_indivi")
erf_eec_indivi = erf_df.merge(eec_df, on ='noindiv', how = 'inner' )
assert 'quelfic' in erf_eec_indivi.columns, "quelfic not in erf_indivi columns"
del eec_df, erf_df
# We then get the aggregate variables for the menage ( mainly to compare with of )
print 'Loading data from erf_menage table'
erf_menage = erf_data.get_of_values(variables= list(todo) + ['quelfic'], table="erf_menage")
del todo
gc.collect()
assert 'ident' in erf_menage.columns, "ident not in erf_menage.columns"
from openfisca_france.data.erf import get_erf2of
erf2of = get_erf2of()
erf_menage.rename(columns = erf2of, inplace = True)
# We get the options from the simulation non aggregated tables:
# First from the output_table
# We recreate the noindiv in output_table
self.simulation.output_table.table['noindiv'] = 100 * self.simulation.output_table.table.idmen_ind + self.simulation.output_table.table.noi_ind
self.simulation.output_table.table['noindiv'] = self.simulation.output_table.table['noindiv'].astype(np.int64)
s1 = [var for var in set(options).intersection(set(self.simulation.output_table.table.columns))] + ['idmen_ind', 'quimen_ind', 'noindiv']
simu_nonaggr_tables = (self.simulation.output_table.table)[s1]
simu_nonaggr_tables.rename(columns = {'idmen_ind' : 'idmen', 'quimen_ind':'quimen'}, inplace = True)
assert 'noindiv' in simu_nonaggr_tables.columns
# If not found, we dwelve into the input_table
if (set(s1)- set(['idmen_ind', 'quimen_ind','noindiv'])) < set(options):
assert 'noindiv' in self.simulation.input_table.table.columns, "'noindiv' not in simulation.input_table.table.columns"
s2 = [var for var in (set(options).intersection(set(self.simulation.input_table.table.columns)) - set(s1))] + ['noindiv']
#print s2
temp = self.simulation.input_table.table[s2]
simu_nonaggr_tables = simu_nonaggr_tables.merge(temp, on = 'noindiv', how = 'inner', sort = False)
del s2, temp
del s1
gc.collect()
simu_nonaggr_tables = simu_nonaggr_tables[list(set(options)) + ['idmen', 'quimen','noindiv']]
#print options, variables
assert 'idmen' in simu_nonaggr_tables.columns, 'Idmen not in simu_nonaggr_tables columns'
# Check the idmens that are not common
erf_menage.rename(columns = {'ident' : 'idmen'}, inplace = True)
print "\n"
print 'Checking if idmen is here...'
print '\n ERF : '
print 'idmen' in erf_menage.columns
print "\n Simulation output"
print 'idmen' in simu_aggr_tables.columns
print "\n"
#print 'Dropping duplicates of idmen for both tables...'
assert not erf_menage["idmen"].duplicated().any(), "Duplicated idmen in erf_menage"
#erf_menage.drop_duplicates('idmen', inplace = True)
simu_aggr_tables.drop_duplicates('idmen', inplace = True)
assert not simu_aggr_tables["idmen"].duplicated().any(), "Duplicated idmen in of"
print 'Checking mismatching idmen... '
s1 = set(erf_menage['idmen']) - (set(simu_aggr_tables['idmen']))
if s1:
print "idmen that aren't in simu_aggr_tables : %s" %str(len(s1))
pass
s2 = (set(simu_aggr_tables['idmen'])) - set(erf_menage['idmen'])
if s2:
print "idmen that aren't in erf_menage : %s" %str(len(s2))
pass
del s1, s2
# Restrict to common idmens and merge
s3 = set(erf_menage['idmen']).intersection(set(simu_aggr_tables['idmen']))
print "Restricting to %s common idmen... \n" %str(len(s3))
erf_menage = erf_menage[erf_menage['idmen'].isin(s3)]
simu_aggr_tables = simu_aggr_tables[simu_aggr_tables['idmen'].isin(s3)]
del s3
gc.collect()
#print erf_menage.columns
#print simu_aggr_tables.columns
# Compare differences across of and erf dataframes
print "Comparing differences between dataframes... \n"
colcom = (set(erf_menage.columns).intersection(set(simu_aggr_tables.columns))) - set(['idmen','wprm'])
print 'Common variables: '
print colcom
erf_menage.reset_index(inplace = True)
simu_aggr_tables.reset_index(inplace = True)
for col in colcom:
temp = set(erf_menage['idmen'][erf_menage[col] != simu_aggr_tables[col]])
print "Numbers of idmen that aren't equal on variable %s : %s \n" %(col, str(len(temp)))
del temp
self.erf_menage = erf_menage
self.erf_eec_indivi = erf_eec_indivi
self.simu_aggr_tables = simu_aggr_tables
self.simu_nonaggr_tables = simu_nonaggr_tables
def test(year=2006, variables = ['af']):
simulation = SurveySimulation()
survey_filename = os.path.join(model.DATA_DIR, 'sources', 'test.h5')
simulation.set_config(year=year, survey_filename=survey_filename)
simulation.set_param()
simulation.compute()
# of_aggregates = Aggregates()
# of_aggregates.set_simulation(simulation)
# of_aggregates.compute()
# print of_aggregates.aggr_frame
#
# from openfisca_france.data.erf.aggregates import build_erf_aggregates
# temp = (build_erf_aggregates(variables=variables, year= year))
# print temp
# return
variable= "af"
debugger = Debugger()
debugger.set_simulation(simulation)
debugger.set_variable(variable)
debugger.show_aggregates()
def get_all_ancestors(varlist):
if len(varlist) == 0:
return []
else:
if varlist[0]._parents == set():
return ([varlist[0]]
+ get_all_ancestors(varlist[1:]))
else:
return ([varlist[0]]
+ get_all_ancestors(list(varlist[0]._parents))
+ get_all_ancestors(varlist[1:]))
# We want to get all ancestors + children + the options that we're going to encounter
parents = map(lambda x: simulation.output_table.column_by_name.get(x), variables)
parents = get_all_ancestors(parents)
options = []
for varcol in parents:
options.extend(varcol._option.keys())
options = list(set(options))
#print options
parents = map(lambda x: x.name, parents)
for var in variables:
children = set()
varcol = simulation.output_table.column_by_name.get(var)
children = children.union(set(map(lambda x: x.name, varcol._children)))
variables = list(set(parents + list(children)))
#print variables
del parents, children
gc.collect()
def get_var(variable):
variables =[variable]
return simulation.aggregated_by_entity(entity="men", variables=variables,
all_output_vars = False, force_sum=True)[0]
simu_aggr_tables = get_var(variables[0])
for var in variables[1:]:
simu_aggr_tables = simu_aggr_tables.merge(get_var(var)[['idmen', var]], on = 'idmen', how = 'outer')
# We load the data from erf table in case we have to pick data there
erf_data = DataCollection(year=year)
os.system('cls')
todo = set(variables + ["ident", "wprm"]).union(set(options))
print 'Variables or equivalents to fetch :'
print todo
'''
Méthode générale pour aller chercher les variables de l'erf/eec
( qui n'ont pas forcément le même nom
et parfois sont les variables utilisées pour créér l'of ):
1 - essayer le get_of2erf, ça doit marcher pour les variables principales ( au moins les aggrégats
que l'on compare )
Si les variables ne sont pas directement dans la table,
elles ont été calculées à partir d'autres variables de données erf/eec
donc chercher dans :
2 - build_survey
3 - model/model.py qui dira éventuellement dans quel module de model/ chercher
Le 'print todo' vous indique quelles variables chercher
( attention à ne pas inclure les enfants directs )
L'utilisation du Ctrl-H est profitable !
'''
fetch_eec = ['statut','titc','chpub','encadr','prosa','age','naim','naia','noindiv']
fetch_erf = ['zsali','af','ident','wprm','noi','noindiv','quelfic']
erf_df = erf_data.get_of_values(variables= fetch_erf, table="erf_indivi")
eec_df = erf_data.get_of_values(variables= fetch_eec, table="eec_indivi")
erf_eec_indivi = erf_df.merge(eec_df, on ='noindiv', how = 'inner' )
assert 'quelfic' in erf_eec_indivi.columns, "quelfic not in erf_indivi columns"
del eec_df, erf_df
# We then get the aggregate variables for the menage ( mainly to compare with of )
print 'Loading data from erf_menage table'
erf_menage = erf_data.get_of_values(variables= list(todo) + ['quelfic'], table="erf_menage")
del todo
gc.collect()
assert 'ident' in erf_menage.columns, "ident not in erf_menage.columns"
from openfisca_france.data.erf import get_erf2of
erf2of = get_erf2of()
erf_menage.rename(columns = erf2of, inplace = True)
# We get the options from the simulation non aggregated tables:
# First from the output_table
# We recreate the noindiv in output_table
simulation.output_table.table['noindiv'] = 100 * simulation.output_table.table.idmen_ind + simulation.output_table.table.noi_ind
simulation.output_table.table['noindiv'] = simulation.output_table.table['noindiv'].astype(np.int64)
s1 = [var for var in set(options).intersection(set(simulation.output_table.table.columns))] + ['idmen_ind', 'quimen_ind', 'noindiv']
simu_nonaggr_tables = (simulation.output_table.table)[s1]
simu_nonaggr_tables.rename(columns = {'idmen_ind' : 'idmen', 'quimen_ind':'quimen'}, inplace = True)
assert 'noindiv' in simu_nonaggr_tables.columns
# If not found, we dwelve into the input_table
if (set(s1)- set(['idmen_ind', 'quimen_ind','noindiv'])) < set(options):
assert 'noindiv' in simulation.input_table.table.columns, "'noindiv' not in simulation.input_table.table.columns"
s2 = [var for var in (set(options).intersection(set(simulation.input_table.table.columns)) - set(s1))] + ['noindiv']
#print s2
temp = simulation.input_table.table[s2]
simu_nonaggr_tables = simu_nonaggr_tables.merge(temp, on = 'noindiv', how = 'inner', sort = False)
del s2, temp
del s1
gc.collect()
simu_nonaggr_tables = simu_nonaggr_tables[list(set(options)) + ['idmen', 'quimen','noindiv']]
#print options, variables
assert 'idmen' in simu_nonaggr_tables.columns, 'Idmen not in simu_nonaggr_tables columns'
# Check the idmens that are not common
erf_menage.rename(columns = {'ident' : 'idmen'}, inplace = True)
print "\n"
print 'Checking if idmen is here...'
print '\n ERF : '
print 'idmen' in erf_menage.columns
print "\n Simulation output"
print 'idmen' in simu_aggr_tables.columns
print "\n"
#print 'Dropping duplicates of idmen for both tables...'
assert not erf_menage["idmen"].duplicated().any(), "Duplicated idmen in erf_menage"
#erf_menage.drop_duplicates('idmen', inplace = True)
simu_aggr_tables.drop_duplicates('idmen', inplace = True)
assert not simu_aggr_tables["idmen"].duplicated().any(), "Duplicated idmen in of"
print 'Checking mismatching idmen... '
s1 = set(erf_menage['idmen']) - (set(simu_aggr_tables['idmen']))
if s1:
print "idmen that aren't in simu_aggr_tables : %s" %str(len(s1))
pass
s2 = (set(simu_aggr_tables['idmen'])) - set(erf_menage['idmen'])
if s2:
print "idmen that aren't in erf_menage : %s" %str(len(s2))
pass
del s1, s2
# Restrict to common idmens and merge
s3 = set(erf_menage['idmen']).intersection(set(simu_aggr_tables['idmen']))
print "Restricting to %s common idmen... \n" %str(len(s3))
erf_menage = erf_menage[erf_menage['idmen'].isin(s3)]
simu_aggr_tables = simu_aggr_tables[simu_aggr_tables['idmen'].isin(s3)]
del s3
gc.collect()
#print erf_menage.columns
#print simu_aggr_tables.columns
# Compare differences across of and erf dataframes
print "Comparing differences between dataframes... \n"
colcom = (set(erf_menage.columns).intersection(set(simu_aggr_tables.columns))) - set(['idmen','wprm'])
print 'Common variables: '
print colcom
erf_menage.reset_index(inplace = True)
simu_aggr_tables.reset_index(inplace = True)
for col in colcom:
temp = set(erf_menage['idmen'][erf_menage[col] != simu_aggr_tables[col]])
print "Numbers of idmen that aren't equal on variable %s : %s \n" %(col, str(len(temp)))
del temp
# Detect the biggest differences
bigtable = merge(erf_menage, simu_aggr_tables, on = 'idmen', how = 'inner', suffixes=('_erf','_of'))
print 'Length of new dataframe is %s' %str(len(bigtable))
#print bigtable.columns
bigtable.set_index('idmen', drop = False, inplace = True)
already_met = []
options_met = []
for col in colcom:
bigtemp = None
table = bigtable[and_(bigtable[col+'_erf']!=0,bigtable[col+'_of']!=0)]
table[col] = (table[col+'_erf'] - table[col+'_of']) / table[col+'_erf'] #Difference relative
table[col] = table[col].apply(lambda x: abs(x))
print 'Minimum difference between the two tables for %s is %s' %(col, str(table[col].min()))
print 'Maximum difference between the two tables for %s is %s' %(col, str(table[col].max()))
print table[col].describe()
try:
assert len(table[col]) == len(table['wprm_of']), "PINAGS"
dec, values = mwp(table[col], np.arange(1,11), table['wprm_of'], 2, return_quantiles=True)
#print sorted(values)
dec, values = mwp(table[col], np.arange(1,101), table['wprm_erf'], 2, return_quantiles=True)
#print sorted(values)[90:]
del dec, values
gc.collect()
except:
#print 'Weighted percentile method didnt work for %s' %col
pass
print "\n"
# Show the relevant information for the most deviant households
table.sort(columns = col, ascending = False, inplace = True)
#print table[col][0:10].to_string()
if bigtemp is None:
bigtemp = {'table' : table[[col, col+'_of', col+'_erf', 'idmen']][0:10],
'options' : None}
bigtemp['table'][col+'div'] = bigtemp['table'][col+'_of'] / bigtemp['table'][col+'_erf']
print bigtemp['table'].to_string()
'''
bigtemp is the table which will get filled little by little by the relevant variables.
Up to the last rows of code 'table' refers to a table of aggregated values,
while 'options is a table of individual variables.
The reason we call it in a dictionnary is also because we modify it inside the recursive function 'iter_on parents',
and it causes an error in Python unless for certain types like dictionnary values.
'''
#print "\n"
# If variable is a Prestation, we show the dependancies
varcol = simulation.output_table.column_by_name.get(col)
if isinstance(varcol, Prestation):
'''
For the direct children
'''
if not varcol._children is None:
ch_to_fetch = list(varcol._children)
ch_to_fetch = map(lambda x: x.name, ch_to_fetch)
ch_fetched = []
if set(ch_to_fetch) <= set(simu_aggr_tables.columns):
print "Variables which need %s to be computed :\n %s \n" %(col, str(ch_to_fetch))
for var in ch_to_fetch:
if var + '_of' in table.columns:
ch_fetched.append(var + '_of')
else:
ch_fetched.append(var)
elif set(ch_to_fetch) <= set(simu_aggr_tables.columns).union(erf_menage.columns):
print "Variables which need %s to be computed (some missing picked in erf):\n %s \n" %(col, str(ch_to_fetch))
for var in ch_to_fetch:
if var in simu_aggr_tables.columns:
if var + '_of' in table.columns:
ch_fetched.append(var + '_of')
elif var + '_erf' in table.columns:
ch_fetched.append(var + '_erf')
else:
ch_fetched.append(var)
else:
print "Variables which need %s to be computed (some missing):\n %s \n" %(col, str(ch_to_fetch))
for var in ch_to_fetch:
if var in simu_aggr_tables.columns:
if var + '_of' in table.columns:
ch_fetched.append(var + '_of')
elif var in erf_menage.columns:
if var + '_erf' in table.columns:
ch_fetched.append(var + '_erf')
print table[[col] + ch_fetched][0:10]
print "\n"
del ch_to_fetch, ch_fetched
'''
For the parents
'''
def iter_on_parents(varcol):
if (varcol._parents == set() and varcol._option == {}) or varcol.name in already_met:
return
else:
par_to_fetch = list(varcol._parents)
par_to_fetch = map(lambda x: x.name, par_to_fetch)
par_fetched = []
if set(par_fetched) <= set(simu_aggr_tables.columns):
#print "Variables the prestation %s depends of :\n %s \n" %(varcol.name, str(par_fetched))
for var in par_fetched:
if var + '_of' in table.columns:
par_fetched.append(var + '_of')
else:
par_fetched.append(var)
elif set(par_fetched) <= set(simu_aggr_tables.columns).union(erf_menage.columns):
#print "Variables the prestation %s depends of (some missing picked in erf):\n %s \n" %(varcol.name,str(par_fetched))
for var in par_fetched:
if var in simu_aggr_tables.columns:
if var + '_of' in table.columns:
par_fetched.append(var + '_of')
elif var + '_erf' in table.columns:
par_fetched.append(var + '_erf')
else:
par_fetched.append(var)
else:
for var in par_fetched:
if var in simu_aggr_tables.columns:
if var + '_of' in table.columns:
par_fetched.append(var + '_of')
elif var in erf_menage.columns:
if var + '_erf' in table.columns:
par_fetched.append(var + '_erf')
if len(par_fetched) > 0:
#print "Variables the prestation %s depends of (some missing):\n %s \n" %(varcol.name, str(par_fetched))
pass
else:
#print "Variables the prestation %s depends of couldn't be found :\n %s \n" %(varcol.name, str(par_fetched))
pass
if len(par_fetched) > 0:
temp = table[[col, 'idmen'] + par_fetched][0:10]
bigtemp['table'] = pd.merge(temp, bigtemp['table'], how = 'inner')
#print temp.to_string(), "\n"
if varcol._option != {} and not set(varcol._option.keys()) < set(options_met):
vars_to_fetch = list(set(varcol._option.keys())-set(options_met))
#print "and the options to current variable %s for the id's with strongest difference :\n %s \n" %(varcol.name, varcol._option.keys())
liste = [i for i in range(0,10)]
liste = map(lambda x: table['idmen'].iloc[x], liste)
temp = simu_nonaggr_tables[['idmen', 'quimen','noindiv']
+ vars_to_fetch][simu_nonaggr_tables['idmen'].isin(table['idmen'][0:10])]
temp_sorted = temp[temp['idmen'] == liste[0]]
for i in xrange(1,10):
temp_sorted = temp_sorted.append(temp[temp['idmen'] == liste[i]])
if bigtemp['options'] is None:
bigtemp['options'] = temp_sorted
bigtemp['options'] = bigtemp['options'].merge(erf_eec_indivi, on = 'noindiv', how = 'outer')
else:
bigtemp['options'] = bigtemp['options'].merge(temp_sorted, on = ['noindiv','idmen','quimen'], how = 'outer')
# temp_sorted.set_index(['idmen', 'quimen'], drop = True, inplace = True) # If we do that
del temp, temp_sorted
gc.collect()
already_met.append(varcol.name)
options_met.extend(varcol._option.keys())
for var in varcol._parents:
iter_on_parents(var)
iter_on_parents(varcol)
# We merge the aggregate table with the option table ( for each individual in entity )
bigtemp['table'] = bigtemp['table'].merge(bigtemp['options'],
how = 'left',
on = 'idmen',
suffixes = ('(agg)', '(ind)'))
# Reshaping the table to group by descending error on col, common entities
bigtemp['table'].sort(columns = ['af','quimen'], ascending = [False,True], inplace = True)
bigtemp['table'] = bigtemp['table'].groupby(['idmen','quimen'], sort = False).sum()
print "Table of values for %s dependencies : \n" %col
print bigtemp['table'].to_string()
del bigtemp['table'], bigtemp['options']
gc.collect()
def check_converted():
#Retrieving the input and output files for analysis :
store = HDFStore(survey_test)
input_df = store['survey_2006']
output = HDFStore(survey3_test)
df_fam = output['survey_2006/fam']
df_foy = output['survey_2006/foy']
df_men = output['survey_2006/men']
df_ind = output['survey_2006/ind']
year = 2006
erf = DataCollection(year=year)
df = erf.get_of_values(table = "erf_indivi")
df2 = erf.get_of_values(table = "eec_indivi")
print '\n'
print df.loc[df.ident==6030189, :].to_string()
print df2.loc[df2.ident==6030189, :].to_string()
print len(np.unique(input_df['idfoy'].values))
print len(np.unique(input_df.loc[input_df['quifoy']==0,'idfoy'].values))
liste = [601228002, 602671302, 602016402, 603069602, 601365902, 602679402, 602680905, 603074902, 600848302,
602684902, 601508802, 601427302, 601774602, 600466102, 603448202, 603091202, 602437502, 603224003,
603093102, 601261802, 601000002, 601789602, 601660602, 600350102, 601927802, 601797902, 601667902,
601537502, 600227602, 602854502, 602071902, 600144702, 602205702, 600769302, 601096602, 602609202,
601301302, 602220302, 602486102, 601376802, 601570902, 600654802, 601443202, 603412402, 603412902,
601055502, 602893001, 601189902, 601850602, 600539902, 602507002, 601460902, 602511602, 601200902,
601601802, 600946903, 600428502, 600953502, 601084802, 601350102, 600829602, 600174402]
liste_men = np.unique(input_df.loc[input_df.idfoy.isin(liste), 'idmen'].values)
print liste_men
print df.loc[df.ident.isin(liste_men), ['noi', 'noindiv', 'ident', 'declar1', 'declar2', 'persfip', 'persfipd', 'quelfic']].head(30).to_string()
print input_df.loc[input_df.idfoy.isin(liste), :].head(30).to_string()
# print input_df.loc[input_df.idfoy==603018901,
# ['idfoy', 'quifoy', 'idfam', 'quifam', 'idmen', 'quimen', 'noi']].to_string()
#
# print input_df.loc[input_df.idfam==603018902,
# ['idfoy', 'quifoy', 'idfam', 'quifam', 'idmen', 'quimen', 'noi']].to_string()
return
# df_foy['noindiv'] = df_foy['noi'] ; del df_foy['noi']
# df_fam['noindiv'] = df_fam['noi'] ; del df_fam['noi']
# df_men['noindiv'] = df_men['noi'] ; del df_men['noi']
# print df_fam, df_foy, df_men
# check_structure(store['survey_2006'])
# control(input_df, verbose=True, verbose_columns=['noindiv'])
# control(df_foy, verbose=True, verbose_columns=['noindiv'])
# print input_df.duplicated('noindiv').sum(), len(input_df)
# print df_foy.duplicated('noindiv').sum(), len(df_foy)
# print df_fam.duplicated('noindiv').sum(), len(df_fam)
# print df_men.duplicated('noindiv').sum(), len(df_men)
# print df_ind.head(10).to_string()
print ' FAM'
print sorted(df_fam.columns)
print ' FOY'
print sorted(df_foy.columns)
print ' MEN'
print sorted(df_men.columns)
print ' IND'
print sorted(df_ind.columns)
# print df_fam.columns
print ' INPUT'
print sorted(input_df.columns)
def check_converted():
#Retrieving the input and output files for analysis :
store = HDFStore(survey_test)
input_df = store['survey_2006']
output = HDFStore(survey3_test)
df_fam = output['survey_2006/fam']
df_foy = output['survey_2006/foy']
df_men = output['survey_2006/men']
df_ind = output['survey_2006/ind']
year = 2006
erf = DataCollection(year=year)
df = erf.get_of_values(table="erf_indivi")
df2 = erf.get_of_values(table="eec_indivi")
print '\n'
print df.loc[df.ident == 6030189, :].to_string()
print df2.loc[df2.ident == 6030189, :].to_string()
print len(np.unique(input_df['idfoy'].values))
print len(np.unique(input_df.loc[input_df['quifoy'] == 0, 'idfoy'].values))
liste = [
601228002, 602671302, 602016402, 603069602, 601365902, 602679402,
602680905, 603074902, 600848302, 602684902, 601508802, 601427302,
601774602, 600466102, 603448202, 603091202, 602437502, 603224003,
603093102, 601261802, 601000002, 601789602, 601660602, 600350102,
601927802, 601797902, 601667902, 601537502, 600227602, 602854502,
602071902, 600144702, 602205702, 600769302, 601096602, 602609202,
601301302, 602220302, 602486102, 601376802, 601570902, 600654802,
601443202, 603412402, 603412902, 601055502, 602893001, 601189902,
601850602, 600539902, 602507002, 601460902, 602511602, 601200902,
601601802, 600946903, 600428502, 600953502, 601084802, 601350102,
600829602, 600174402
]
liste_men = np.unique(input_df.loc[input_df.idfoy.isin(liste),
'idmen'].values)
print liste_men
print df.loc[df.ident.isin(liste_men), [
'noi', 'noindiv', 'ident', 'declar1', 'declar2', 'persfip', 'persfipd',
'quelfic'
]].head(30).to_string()
print input_df.loc[input_df.idfoy.isin(liste), :].head(30).to_string()
# print input_df.loc[input_df.idfoy==603018901,
# ['idfoy', 'quifoy', 'idfam', 'quifam', 'idmen', 'quimen', 'noi']].to_string()
#
# print input_df.loc[input_df.idfam==603018902,
# ['idfoy', 'quifoy', 'idfam', 'quifam', 'idmen', 'quimen', 'noi']].to_string()
return
# df_foy['noindiv'] = df_foy['noi'] ; del df_foy['noi']
# df_fam['noindiv'] = df_fam['noi'] ; del df_fam['noi']
# df_men['noindiv'] = df_men['noi'] ; del df_men['noi']
# print df_fam, df_foy, df_men
# check_structure(store['survey_2006'])
# control(input_df, verbose=True, verbose_columns=['noindiv'])
# control(df_foy, verbose=True, verbose_columns=['noindiv'])
# print input_df.duplicated('noindiv').sum(), len(input_df)
# print df_foy.duplicated('noindiv').sum(), len(df_foy)
# print df_fam.duplicated('noindiv').sum(), len(df_fam)
# print df_men.duplicated('noindiv').sum(), len(df_men)
# print df_ind.head(10).to_string()
print ' FAM'
print sorted(df_fam.columns)
print ' FOY'
print sorted(df_foy.columns)
print ' MEN'
print sorted(df_men.columns)
print ' IND'
print sorted(df_ind.columns)
# print df_fam.columns
print ' INPUT'
print sorted(input_df.columns)