def get_child_households_profile(geo_code, geo_level, session):
# head of household
# gender
head_gender_dist, total_households = get_stat_data(
['gender of head of household'], geo_level, geo_code, session,
order_by='gender of head of household',
table_name='genderofheadofhouseholdunder18')
female_heads = head_gender_dist['Female']['numerators']['this']
# annual household income
income_dist_data, _ = get_stat_data(
['annual household income'], geo_level, geo_code, session,
exclude=['Unspecified'],
recode=HOUSEHOLD_INCOME_RECODE,
key_order=HOUSEHOLD_INCOME_RECODE.values(),
table_name='annualhouseholdincomeunder18')
# median income
median = calculate_median_stat(income_dist_data)
median_income = HOUSEHOLD_INCOME_ESTIMATE[median]
# type of dwelling
type_of_dwelling_dist, _ = get_stat_data(
['type of main dwelling'], geo_level, geo_code, session,
recode=TYPE_OF_DWELLING_RECODE,
order_by='-total')
informal = type_of_dwelling_dist['Shack']['numerators']['this']
# size of household
household_size_dist, _ = get_stat_data(
['household size', 'age of household head'],
geo_level, geo_code, session
)
return {
'total_households': {
'name': 'Households with heads under 18 years old',
'values': {'this': total_households},
},
'type_of_dwelling_distribution': type_of_dwelling_dist,
'informal': {
'name': 'Child-headed households that are informal dwellings (shacks)',
'values': {'this': percent(informal, total_households)},
'numerators': {'this': informal},
},
'annual_income_distribution': income_dist_data,
'median_annual_income': {
'name': 'Average annual child-headed household income',
'values': {'this': median_income},
},
'household_size_distribution': household_size_dist,
'head_of_household': {
'gender_distribution': head_gender_dist,
'female': {
'name': 'Child-headed households with women as their head',
'values': {'this': percent(female_heads, total_households)},
'numerators': {'this': female_heads},
},
},
}
def get_child_households_profile(geo, session):
# head of household
# gender
head_gender_dist, total_households = get_stat_data(
['gender of head of household'], geo, session,
order_by='gender of head of household',
table_name='genderofheadofhouseholdunder18')
female_heads = head_gender_dist['Female']['numerators']['this']
# annual household income
if geo.version == '2011':
HOUSEHOLD_INCOME_RECODE = HOUSEHOLD_INCOME_RECODE_2011
else:
HOUSEHOLD_INCOME_RECODE = COLLAPSED_ANNUAL_INCOME_CATEGORIES
income_dist_data, _ = get_stat_data(
['annual household income'], geo, session,
exclude=['Unspecified'],
recode=HOUSEHOLD_INCOME_RECODE,
key_order=HOUSEHOLD_INCOME_RECODE.values(),
table_name='annualhouseholdincomeunder18')
# median income
median = calculate_median_stat(income_dist_data)
median_income = HOUSEHOLD_INCOME_ESTIMATE[median]
# type of dwelling
type_of_dwelling_dist, _ = get_stat_data(
['type of main dwelling'], geo, session,
recode=TYPE_OF_DWELLING_RECODE,
order_by='-total')
informal = type_of_dwelling_dist['Shack']['numerators']['this']
return {
'total_households': {
'name': 'Households with heads under 18 years old',
'values': {'this': total_households},
},
'type_of_dwelling_distribution': type_of_dwelling_dist,
'informal': {
'name': 'Child-headed households that are informal dwellings (shacks)',
'values': {'this': percent(informal, total_households)},
'numerators': {'this': informal},
},
'annual_income_distribution': income_dist_data,
'median_annual_income': {
'name': 'Average annual child-headed household income',
'values': {'this': median_income},
},
'head_of_household': {
'gender_distribution': head_gender_dist,
'female': {
'name': 'Child-headed households with women as their head',
'values': {'this': percent(female_heads, total_households)},
'numerators': {'this': female_heads},
},
},
}
def get_economics_profile(geo_code, geo_level, session):
# income
income_dist_data, total_workers = get_stat_data(
['employed individual monthly income'], geo_level, geo_code, session,
exclude=['Not applicable'],
recode=COLLAPSED_INCOME_CATEGORIES,
key_order=COLLAPSED_INCOME_CATEGORIES.values())
# median income
median = calculate_median_stat(income_dist_data)
median_income = ESTIMATED_INCOME_CATEGORIES[median]
# employment status
employ_status, total_workers = get_stat_data(
['official employment status'], geo_level, geo_code, session,
exclude=['Age less than 15 years', 'Not applicable'],
order_by='official employment status',
table_name='officialemploymentstatus')
# sector
sector_dist_data, _ = get_stat_data(
['type of sector'], geo_level, geo_code, session,
exclude=['Not applicable'],
order_by='type of sector')
# access to internet
internet_access_dist, total_with_access = get_stat_data(
['access to internet'], geo_level, geo_code, session, exclude=['No access to internet'],
order_by='access to internet')
_, total_without_access = get_stat_data(
['access to internet'], geo_level, geo_code, session, only=['No access to internet'])
total_households = total_with_access + total_without_access
return {'individual_income_distribution': income_dist_data,
'median_individual_income': {
'name': 'Average monthly income',
'values': {'this': median_income},
},
'employment_status': employ_status,
'sector_type_distribution': sector_dist_data,
'internet_access_distribution': internet_access_dist,
'internet_access': {
'name': 'Households with internet access',
'values': {'this': percent(total_with_access, total_households)},
'numerators': {'this': total_with_access},
}
}
def get_children_profile(geo, session):
profile = {}
# age
child_adult_dist, _ = get_stat_data(
['age in completed years'], geo, session,
table_name='ageincompletedyearssimplified',
recode={'< 18': 'Children (< 18)',
'18 to 64': 'Adults (>= 18)',
'>= 65': 'Adults (>= 18)'})
# parental survival
survival, total = get_stat_data(
['mother alive', 'father alive'], geo, session)
parental_survival_dist = OrderedDict()
parental_survival_dist['metadata'] = survival['metadata']
parental_survival_dist['Both parents'] = survival['Yes']['Yes']
parental_survival_dist['Both parents']['name'] = 'Both parents'
parental_survival_dist['Neither parent'] = survival['No']['No']
parental_survival_dist['Neither parent']['name'] = 'Neither parent'
parental_survival_dist['One parent'] = survival['Yes']['No']
parental_survival_dist['One parent']['numerators']['this'] += survival['No']['Yes']['numerators']['this']
rest = (total - parental_survival_dist['Both parents']['values']['this']
- parental_survival_dist['Neither parent']['values']['this']
- parental_survival_dist['One parent']['values']['this'])
parental_survival_dist['Uncertain'] = {
'name': 'Uncertain',
'numerators': {'this': rest},
}
# calculate percentage
for data in parental_survival_dist.itervalues():
if 'numerators' in data:
data['values'] = {'this': percent(data['numerators']['this'], total)}
# gender
gender_dist, _ = get_stat_data(
['gender'], geo, session,
table_name='genderunder18')
# school
# NOTE: this data is incompatible with some views (check out
# https://github.com/censusreporter/censusreporter/issues/78)
#
# school_attendance_dist, total_school_aged = get_stat_data(
# ['present school attendance', 'age in completed years'],
# geo, session,
# )
# school_attendance_dist['Yes']['metadata'] = \
# school_attendance_dist['metadata']
# school_attendance_dist = school_attendance_dist['Yes']
# total_attendance = sum(d['numerators']['this'] for d in
# school_attendance_dist.values()
# if 'numerators' in d)
# school attendance
school_attendance_dist, total_school_aged = get_stat_data(
['present school attendance'],
geo, session,
recode=COLLAPSED_ATTENDANCE_CATEGORIES,
)
total_attendance = school_attendance_dist['Yes']['numerators']['this']
# education level
education17_dist, _ = get_stat_data(
['highest educational level'],
geo, session,
recode=COLLAPSED_EDUCATION_CATEGORIES,
table_name='highesteducationallevel17',
key_order=EDUCATION_KEY_ORDER,
)
# employment
employment_dist, total_15to17 = get_stat_data(
['official employment status'],
geo, session,
table_name='officialemploymentstatus15to17',
exclude=['Not applicable']
)
total_in_labour_force = float(sum(v["numerators"]["this"] for k, v
in employment_dist.iteritems()
if COLLAPSED_EMPLOYMENT_CATEGORIES.get(k, None)
== 'In labour force'))
employment_indicators = {
'percent_in_labour_force': {
"name": "Of children between 15 and 17 are in the labour force",
"numerators": {"this": total_in_labour_force},
"values": {"this": percent(total_in_labour_force, total_15to17)}
},
'employment_distribution': employment_dist,
}
# median income
if geo.version == '2011':
recode = COLLAPSED_MONTHLY_INCOME_CATEGORIES
fields = ['individual monthly income']
table_name = 'individualmonthlyincome15to17'
income_dist_data, total_workers = get_stat_data(
fields, geo, session,
exclude=['Not applicable'],
recode=recode,
key_order=recode.values(),
table_name=table_name
)
median = calculate_median_stat(income_dist_data)
median_income = ESTIMATED_MONTHLY_INCOME_CATEGORIES[median]
employment_indicators.update({
'median_income': {
'name': 'Average monthly income of employed children between 15 and 17',
'values': {'this': median_income},
}
})
else:
recode = COLLAPSED_ANNUAL_INCOME_CATEGORIES
fields = ['individual annual income']
table_name = 'individualannualincome15to17'
income_dist_data, total_workers = get_stat_data(
fields, geo, session,
exclude=['Not applicable'],
recode=recode,
key_order=recode.values(),
table_name=table_name
)
median = calculate_median_stat(income_dist_data)
median_income = ESTIMATED_ANNUAL_INCOME_CATEGORIES[median]
employment_indicators.update({
'median_annual_income': {
'name': 'Average annual income of employed children between 15 and 17',
'values': {'this': median_income},
}
})
profile.update({
'demographics': {
'child_adult_distribution': child_adult_dist,
'total_children': {
"name": "Children",
"values": {"this": child_adult_dist['Children (< 18)']['numerators']['this']}
},
'gender_distribution': gender_dist,
'parental_survival_distribution': parental_survival_dist,
'percent_no_parent': {
"name": "Of children 14 and under have no living biological parents",
"values": parental_survival_dist["Neither parent"]['values'],
"numerators": parental_survival_dist["Neither parent"]['numerators'],
},
},
'school': {
'school_attendance_distribution': school_attendance_dist,
'percent_school_attendance': {
"name": "School-aged children (5 to 17 years old) are in school",
"numerators": {"this": total_school_aged},
"values": {"this": percent(float(total_attendance),
float(total_school_aged))}
},
'education17_distribution': education17_dist,
},
'employment': employment_indicators
})
return profile
def get_economics_profile(geo, session):
profile = {}
# income
if geo.version == '2011':
# distribution
recode = COLLAPSED_MONTHLY_INCOME_CATEGORIES
fields = ['employed individual monthly income']
income_dist_data, total_workers = get_stat_data(
fields, geo, session,
exclude=['Not applicable'],
recode=recode,
key_order=recode.values())
# median income
median = calculate_median_stat(income_dist_data)
median_income = ESTIMATED_MONTHLY_INCOME_CATEGORIES[median]
profile.update({
'individual_income_distribution': income_dist_data,
'median_individual_income': {
'name': 'Average monthly income',
'values': {'this': median_income},
}
})
else:
# distribution
recode = COLLAPSED_ANNUAL_INCOME_CATEGORIES
fields = ['employed individual annual income']
income_dist_data, total_workers = get_stat_data(
fields, geo, session,
exclude=['Not applicable'],
recode=recode,
key_order=recode.values())
# median income
median = calculate_median_stat(income_dist_data)
median_income = ESTIMATED_ANNUAL_INCOME_CATEGORIES[median]
profile.update({
'individual_annual_income_distribution': income_dist_data,
'median_annual_individual_income': {
'name': 'Average annual income',
'values': {'this': median_income},
}
})
# employment status
employ_status, total_workers = get_stat_data(
['official employment status'], geo, session,
exclude=['Age less than 15 years', 'Not applicable'],
order_by='official employment status',
table_name='officialemploymentstatus')
# sector
sector_dist_data, _ = get_stat_data(
['type of sector'], geo, session,
exclude=['Not applicable'],
order_by='type of sector')
# access to internet
internet_access_dist, total_with_access = get_stat_data(
['access to internet'], geo, session, exclude=['No access to internet'],
order_by='access to internet')
_, total_without_access = get_stat_data(
['access to internet'], geo, session, only=['No access to internet'])
total_households = total_with_access + total_without_access
profile.update({
'employment_status': employ_status,
'sector_type_distribution': sector_dist_data,
'internet_access_distribution': internet_access_dist,
'internet_access': {
'name': 'Households with internet access',
'values': {'this': percent(total_with_access, total_households)},
'numerators': {'this': total_with_access},
}
})
return profile
def get_households_profile(geo, session):
# head of household
# gender
head_gender_dist, total_households = get_stat_data(
['gender of household head'], geo, session,
order_by='gender of household head')
female_heads = head_gender_dist['Female']['numerators']['this']
# age
db_model_u18 = get_model_from_fields(
['gender of head of household'], geo.geo_level,
table_name='genderofheadofhouseholdunder18'
)
objects = get_objects_by_geo(db_model_u18, geo, session)
total_under_18 = float(sum(o[0] for o in objects))
# tenure
tenure_data, _ = get_stat_data(
['tenure status'], geo, session,
recode=HOUSEHOLD_OWNERSHIP_RECODE,
order_by='tenure status')
owned = 0
for key, data in tenure_data.iteritems():
if key.startswith('Owned'):
owned += data['numerators']['this']
# annual household income
if geo.version == '2011':
HOUSEHOLD_INCOME_RECODE = HOUSEHOLD_INCOME_RECODE_2011
else:
HOUSEHOLD_INCOME_RECODE = COLLAPSED_ANNUAL_INCOME_CATEGORIES
income_dist_data, _ = get_stat_data(
['annual household income'], geo, session,
exclude=['Unspecified', 'Not applicable'],
recode=HOUSEHOLD_INCOME_RECODE,
key_order=HOUSEHOLD_INCOME_RECODE.values(),
table_name='annualhouseholdincome_genderofhouseholdhead')
# median income
median = calculate_median_stat(income_dist_data)
median_income = HOUSEHOLD_INCOME_ESTIMATE[median]
# type of dwelling
type_of_dwelling_dist, _ = get_stat_data(
['type of dwelling'], geo, session,
recode=TYPE_OF_DWELLING_RECODE,
order_by='-total')
informal = type_of_dwelling_dist['Shack']['numerators']['this']
# household goods
household_goods, _ = get_stat_data(
['household goods'], geo, session,
recode=HOUSEHOLD_GOODS_RECODE,
key_order=sorted(HOUSEHOLD_GOODS_RECODE.values()))
return {'total_households': {
'name': 'Households',
'values': {'this': total_households},
},
'owned': {
'name': 'Households fully owned or being paid off',
'values': {'this': percent(owned, total_households)},
'numerators': {'this': owned},
},
'type_of_dwelling_distribution': type_of_dwelling_dist,
'informal': {
'name': 'Households that are informal dwellings (shacks)',
'values': {'this': percent(informal, total_households)},
'numerators': {'this': informal},
},
'tenure_distribution': tenure_data,
'household_goods': household_goods,
'annual_income_distribution': income_dist_data,
'median_annual_income': {
'name': 'Average annual household income',
'values': {'this': median_income},
},
'head_of_household': {
'gender_distribution': head_gender_dist,
'female': {
'name': 'Households with women as their head',
'values': {'this': percent(female_heads, total_households)},
'numerators': {'this': female_heads},
},
'under_18': {
'name': 'Households with heads under 18 years old',
'values': {'this': total_under_18},
}
},
}
def get_children_profile(geo_code, geo_level, session):
# age
child_adult_dist, _ = get_stat_data(
['age in completed years'], geo_level, geo_code, session,
table_name='ageincompletedyearssimplified',
recode={'< 18': 'Children (< 18)',
'18 to 64': 'Adults (>= 18)',
'>= 65': 'Adults (>= 18)'})
# parental survival
survival, total = get_stat_data(
['mother alive', 'father alive'], geo_level, geo_code, session)
parental_survival_dist = OrderedDict()
parental_survival_dist['metadata'] = survival['metadata']
parental_survival_dist['Both parents'] = survival['Yes']['Yes']
parental_survival_dist['Both parents']['name'] = 'Both parents'
parental_survival_dist['Neither parent'] = survival['No']['No']
parental_survival_dist['Neither parent']['name'] = 'Neither parent'
parental_survival_dist['One parent'] = survival['Yes']['No']
parental_survival_dist['One parent']['numerators']['this'] += survival['No']['Yes']['numerators']['this']
rest = (total - parental_survival_dist['Both parents']['values']['this']
- parental_survival_dist['Neither parent']['values']['this']
- parental_survival_dist['One parent']['values']['this'])
parental_survival_dist['Uncertain'] = {
'name': 'Uncertain',
'numerators': {'this': rest},
}
# calculate percentage
for data in parental_survival_dist.itervalues():
if 'numerators' in data:
data['values'] = {'this': percent(data['numerators']['this'], total)}
# gender
gender_dist, _ = get_stat_data(
['gender'], geo_level, geo_code, session,
table_name='genderunder18')
# school
# NOTE: this data is incompatible with some views (check out
# https://github.com/censusreporter/censusreporter/issues/78)
#
# school_attendance_dist, total_school_aged = get_stat_data(
# ['present school attendance', 'age in completed years'],
# geo_level, geo_code, session,
# )
# school_attendance_dist['Yes']['metadata'] = \
# school_attendance_dist['metadata']
# school_attendance_dist = school_attendance_dist['Yes']
# total_attendance = sum(d['numerators']['this'] for d in
# school_attendance_dist.values()
# if 'numerators' in d)
# school attendance
school_attendance_dist, total_school_aged = get_stat_data(
['present school attendance'],
geo_level, geo_code, session,
)
total_attendance = school_attendance_dist['Yes']['numerators']['this']
# education level
education17_dist, _ = get_stat_data(
['highest educational level'],
geo_level, geo_code, session,
recode=COLLAPSED_EDUCATION_CATEGORIES,
table_name='highesteducationallevel17',
key_order=EDUCATION_KEY_ORDER,
)
# employment
employment_dist, total_15to17 = get_stat_data(
['official employment status'],
geo_level, geo_code, session,
table_name='officialemploymentstatus15to17',
exclude=['Not applicable']
)
total_in_labour_force = float(sum(v["numerators"]["this"] for k, v
in employment_dist.iteritems()
if COLLAPSED_EMPLOYMENT_CATEGORIES.get(k, None)
== 'In labour force'))
# median income
income_dist_data, total_workers = get_stat_data(
['individual monthly income'], geo_level, geo_code, session,
exclude=['Not applicable'],
recode=COLLAPSED_INCOME_CATEGORIES,
key_order=COLLAPSED_INCOME_CATEGORIES.values(),
table_name='individualmonthlyincome15to17'
)
median = calculate_median_stat(income_dist_data)
median_income = ESTIMATED_INCOME_CATEGORIES[median]
return {
'demographics': {
'child_adult_distribution': child_adult_dist,
'total_children': {
"name": "Children",
"values": {"this": child_adult_dist['Children (< 18)']['numerators']['this']}
},
'gender_distribution': gender_dist,
'parental_survival_distribution': parental_survival_dist,
'percent_no_parent': {
"name": "Of children 14 and under have no living biological parents",
"values": parental_survival_dist["Neither parent"]['values'],
"numerators": parental_survival_dist["Neither parent"]['numerators'],
},
},
'school': {
'school_attendance_distribution': school_attendance_dist,
'percent_school_attendance': {
"name": "School-aged children (5 to 17 years old) are in school",
"numerators": {"this": total_school_aged},
"values": {"this": percent(float(total_attendance),
float(total_school_aged))}
},
'education17_distribution': education17_dist,
},
'employment': {
'percent_in_labour_force': {
"name": "Of children between 15 and 17 are in the labour force",
"numerators": {"this": total_in_labour_force},
"values": {"this": percent(total_in_labour_force, total_15to17)}
},
'employment_distribution': employment_dist,
'median_income': {
'name': 'Average monthly income of employed children between 15 and 17',
'values': {'this': median_income},
},
}
}
def get_households_profile(geo_code, geo_level, session):
# head of household
# gender
head_gender_dist, total_households = get_stat_data(
['gender of household head'], geo_level, geo_code, session,
order_by='gender of household head')
female_heads = head_gender_dist['Female']['numerators']['this']
# age
db_model_u18 = get_model_from_fields(
['gender of head of household'], geo_level,
table_name='genderofheadofhouseholdunder18'
)
objects = get_objects_by_geo(db_model_u18, geo_code, geo_level, session)
total_under_18 = float(sum(o[0] for o in objects))
# tenure
tenure_data, _ = get_stat_data(
['tenure status'], geo_level, geo_code, session,
order_by='tenure status')
owned = 0
for key, data in tenure_data.iteritems():
if key.startswith('Owned'):
owned += data['numerators']['this']
# annual household income
income_dist_data, _ = get_stat_data(
['annual household income'], geo_level, geo_code, session,
exclude=['Unspecified'],
recode=HOUSEHOLD_INCOME_RECODE,
key_order=HOUSEHOLD_INCOME_RECODE.values(),
table_name='annualhouseholdincome_genderofhouseholdhead')
# median income
median = calculate_median_stat(income_dist_data)
median_income = HOUSEHOLD_INCOME_ESTIMATE[median]
# type of dwelling
type_of_dwelling_dist, _ = get_stat_data(
['type of dwelling'], geo_level, geo_code, session,
recode=TYPE_OF_DWELLING_RECODE,
order_by='-total')
informal = type_of_dwelling_dist['Shack']['numerators']['this']
# household goods
household_goods, _ = get_stat_data(
['household goods'], geo_level, geo_code, session,
total=total_households,
recode=HOUSEHOLD_GOODS_RECODE,
exclude=['total households'],
key_order=sorted(HOUSEHOLD_GOODS_RECODE.values()))
return {'total_households': {
'name': 'Households',
'values': {'this': total_households},
},
'owned': {
'name': 'Households fully owned or being paid off',
'values': {'this': percent(owned, total_households)},
'numerators': {'this': owned},
},
'type_of_dwelling_distribution': type_of_dwelling_dist,
'informal': {
'name': 'Households that are informal dwellings (shacks)',
'values': {'this': percent(informal, total_households)},
'numerators': {'this': informal},
},
'tenure_distribution': tenure_data,
'household_goods': household_goods,
'annual_income_distribution': income_dist_data,
'median_annual_income': {
'name': 'Average annual household income',
'values': {'this': median_income},
},
'head_of_household': {
'gender_distribution': head_gender_dist,
'female': {
'name': 'Households with women as their head',
'values': {'this': percent(female_heads, total_households)},
'numerators': {'this': female_heads},
},
'under_18': {
'name': 'Households with heads under 18 years old',
'values': {'this': total_under_18},
}
},
}
def get_child_households_profile(geo, session):
# head of household
# gender
head_gender_dist, total_households = get_stat_data(
["gender of head of household"],
geo,
session,
table_universe="Households headed by children under 18",
order_by="gender of head of household",
)
female_heads = head_gender_dist["Female"]["numerators"]["this"]
# annual household income
if geo.version == "2011":
HOUSEHOLD_INCOME_RECODE = HOUSEHOLD_INCOME_RECODE_2011
else:
HOUSEHOLD_INCOME_RECODE = COLLAPSED_ANNUAL_INCOME_CATEGORIES
income_dist_data, _ = get_stat_data(
["annual household income"],
geo,
session,
exclude=["Unspecified"],
recode=HOUSEHOLD_INCOME_RECODE,
key_order=HOUSEHOLD_INCOME_RECODE.values(),
table_name="annualhouseholdincomeunder18",
)
# median income
median = calculate_median_stat(income_dist_data)
median_income = HOUSEHOLD_INCOME_ESTIMATE[median]
# type of dwelling
type_of_dwelling_dist, _ = get_stat_data(
["type of main dwelling"],
geo,
session,
recode=TYPE_OF_DWELLING_RECODE,
order_by="-total",
)
informal = type_of_dwelling_dist["Shack"]["numerators"]["this"]
return {
"total_households": {
"name": "Households with heads under 18 years old",
"values": {"this": total_households},
},
"type_of_dwelling_distribution": type_of_dwelling_dist,
"informal": {
"name": "Child-headed households that are informal dwellings (shacks)",
"values": {"this": percent(informal, total_households)},
"numerators": {"this": informal},
},
"annual_income_distribution": income_dist_data,
"median_annual_income": {
"name": "Average annual child-headed household income",
"values": {"this": median_income},
},
"head_of_household": {
"gender_distribution": head_gender_dist,
"female": {
"name": "Child-headed households with women as their head",
"values": {"this": percent(female_heads, total_households)},
"numerators": {"this": female_heads},
},
},
}
def get_children_profile(geo, session):
profile = {}
# age
child_adult_dist, _ = get_stat_data(
["age in completed years"],
geo,
session,
table_name="ageincompletedyearssimplified",
recode={
"< 18": "Children (< 18)",
"18 to 64": "Adults (>= 18)",
">= 65": "Adults (>= 18)",
},
key_order=["Children (< 18)", "Adults (>= 18)"],
)
# parental survival
survival, total = get_stat_data(["mother alive", "father alive"], geo, session)
parental_survival_dist = OrderedDict()
parental_survival_dist["metadata"] = survival["metadata"]
parental_survival_dist["Both parents"] = survival["Yes"]["Yes"]
parental_survival_dist["Both parents"]["name"] = "Both parents"
parental_survival_dist["Neither parent"] = survival["No"]["No"]
parental_survival_dist["Neither parent"]["name"] = "Neither parent"
parental_survival_dist["One parent"] = survival["Yes"]["No"]
parental_survival_dist["One parent"]["numerators"]["this"] += survival["No"]["Yes"][
"numerators"
]["this"]
rest = (
total
- parental_survival_dist["Both parents"]["numerators"]["this"]
- parental_survival_dist["Neither parent"]["numerators"]["this"]
- parental_survival_dist["One parent"]["numerators"]["this"]
)
parental_survival_dist["Uncertain"] = {
"name": "Uncertain",
"numerators": {"this": rest},
"values": {"this": percent(rest, total)},
}
# gender
gender_dist, _ = get_stat_data(
["gender"], geo, session, table_universe="Children under 18"
)
# school
# NOTE: this data is incompatible with some views (check out
# https://github.com/censusreporter/censusreporter/issues/78)
#
# school_attendance_dist, total_school_aged = get_stat_data(
# ['present school attendance', 'age in completed years'],
# geo, session,
# )
# school_attendance_dist['Yes']['metadata'] = \
# school_attendance_dist['metadata']
# school_attendance_dist = school_attendance_dist['Yes']
# total_attendance = sum(d['numerators']['this'] for d in
# school_attendance_dist.values()
# if 'numerators' in d)
# school attendance
school_attendance_dist, total_school_aged = get_stat_data(
["present school attendance"],
geo,
session,
recode=COLLAPSED_ATTENDANCE_CATEGORIES,
)
total_attendance = school_attendance_dist["Yes"]["numerators"]["this"]
# education level
education17_dist, _ = get_stat_data(
["highest educational level"],
geo,
session,
table_universe="17-year-old children",
recode=COLLAPSED_EDUCATION_CATEGORIES,
key_order=EDUCATION_KEY_ORDER,
)
# employment
employment_dist, total_15to17 = get_stat_data(
["official employment status"],
geo,
session,
table_universe="Children 15 to 17",
exclude=["Not applicable"],
)
total_in_labour_force = float(
sum(
v["numerators"]["this"]
for k, v in employment_dist.iteritems()
if COLLAPSED_EMPLOYMENT_CATEGORIES.get(k, None) == "In labour force"
)
)
employment_indicators = {
"percent_in_labour_force": {
"name": "Of children between 15 and 17 are in the labour force",
"numerators": {"this": total_in_labour_force},
"values": {"this": percent(total_in_labour_force, total_15to17)},
},
"employment_distribution": employment_dist,
}
# median income
# monthly or annual
if geo.version == "2011":
income_dist_data, total_workers = get_stat_data(
["individual monthly income"],
geo,
session,
table_universe="Children 15 to 17 who are employed",
exclude=["Not applicable"],
recode=COLLAPSED_MONTHLY_INCOME_CATEGORIES,
key_order=COLLAPSED_MONTHLY_INCOME_CATEGORIES.values(),
)
median = calculate_median_stat(income_dist_data)
median_income = ESTIMATED_MONTHLY_INCOME_CATEGORIES[median]
employment_indicators.update(
{
"median_income": {
"name": "Average monthly income of employed children between 15 and 17",
"values": {"this": median_income},
}
}
)
else:
income_dist_data, total_workers = get_stat_data(
["individual annual income"],
geo,
session,
table_universe="Children 15 to 17 who are employed",
exclude=["Not applicable"],
recode=COLLAPSED_ANNUAL_INCOME_CATEGORIES,
key_order=COLLAPSED_ANNUAL_INCOME_CATEGORIES.values(),
)
median = calculate_median_stat(income_dist_data)
median_income = ESTIMATED_ANNUAL_INCOME_CATEGORIES[median]
employment_indicators.update(
{
"median_annual_income": {
"name": "Average annual income of employed children between 15 and 17",
"values": {"this": median_income},
}
}
)
profile.update(
{
"demographics": {
"child_adult_distribution": child_adult_dist,
"total_children": {
"name": "Children",
"values": {
"this": child_adult_dist["Children (< 18)"]["numerators"][
"this"
]
},
},
"gender_distribution": gender_dist,
"parental_survival_distribution": parental_survival_dist,
"percent_no_parent": {
"name": "Of children 14 and under have no living biological parents",
"values": parental_survival_dist["Neither parent"]["values"],
"numerators": parental_survival_dist["Neither parent"][
"numerators"
],
},
},
"school": {
"school_attendance_distribution": school_attendance_dist,
"percent_school_attendance": {
"name": "School-aged children (5 to 17 years old) are in school",
"numerators": {"this": total_school_aged},
"values": {
"this": percent(
float(total_attendance), float(total_school_aged)
)
},
},
"education17_distribution": education17_dist,
},
"employment": employment_indicators,
}
)
return profile
def get_economics_profile(geo, session):
profile = {}
# income
if geo.version == "2011":
# distribution
recode = COLLAPSED_MONTHLY_INCOME_CATEGORIES
fields = ["employed individual monthly income"]
income_dist_data, total_workers = get_stat_data(
fields,
geo,
session,
exclude=["Not applicable"],
recode=recode,
key_order=recode.values(),
)
# median income
median = calculate_median_stat(income_dist_data)
median_income = ESTIMATED_MONTHLY_INCOME_CATEGORIES[median]
profile.update(
{
"individual_income_distribution": income_dist_data,
"median_individual_income": {
"name": "Average monthly income",
"values": {"this": median_income},
},
}
)
else:
# distribution
recode = COLLAPSED_ANNUAL_INCOME_CATEGORIES
fields = ["employed individual annual income"]
income_dist_data, total_workers = get_stat_data(
fields,
geo,
session,
exclude=["Not applicable"],
recode=recode,
key_order=recode.values(),
)
# median income
median = calculate_median_stat(income_dist_data)
median_income = ESTIMATED_ANNUAL_INCOME_CATEGORIES[median]
profile.update(
{
"individual_annual_income_distribution": income_dist_data,
"median_annual_individual_income": {
"name": "Average annual income",
"values": {"this": median_income},
},
}
)
# employment status
employ_status, total_workers = get_stat_data(
["official employment status"],
geo,
session,
exclude=["Age less than 15 years", "Not applicable"],
order_by="official employment status",
table_name="officialemploymentstatus",
)
# sector
sector_dist_data, _ = get_stat_data(
["type of sector"],
geo,
session,
exclude=["Not applicable"],
order_by="type of sector",
)
profile.update(
{
"employment_status": employ_status,
"sector_type_distribution": sector_dist_data,
}
)
# access to internet
if current_context().get("year") == "latest":
internet_access_dist, total_households = get_stat_data(
["access to internet"],
geo,
session,
recode=INTERNET_ACCESS_RECODE,
table_name="accesstointernet_2016",
)
profile.update({"internet_access_distribution": internet_access_dist})
else:
internet_access_dist, total_with_access = get_stat_data(
["access to internet"],
geo,
session,
exclude=["No access to internet"],
order_by="access to internet",
)
_, total_without_access = get_stat_data(
["access to internet"], geo, session, only=["No access to internet"]
)
total_households = total_with_access + total_without_access
profile.update(
{
"internet_access_distribution": internet_access_dist,
"internet_access": {
"name": "Households with internet access",
"values": {"this": percent(total_with_access, total_households)},
"numerators": {"this": total_with_access},
},
}
)
return profile
def get_households_profile(geo, session):
# head of household
# gender
head_gender_dist, total_households = get_stat_data(
["gender of household head"],
geo,
session,
table_universe="Households",
order_by="gender of household head",
)
female_heads = head_gender_dist["Female"]["numerators"]["this"]
# age
u18_table = get_datatable("genderofheadofhouseholdunder18")
objects = u18_table.get_rows_for_geo(geo, session)
total_under_18 = float(sum(o[0] for o in objects))
# tenure
tenure_data, _ = get_stat_data(
["tenure status"],
geo,
session,
table_universe="Households",
recode=HOUSEHOLD_OWNERSHIP_RECODE,
order_by="-total",
)
owned = 0
for key, data in tenure_data.iteritems():
if key.startswith("Owned"):
owned += data["numerators"]["this"]
# annual household income
if geo.version == "2011":
HOUSEHOLD_INCOME_RECODE = HOUSEHOLD_INCOME_RECODE_2011
else:
HOUSEHOLD_INCOME_RECODE = COLLAPSED_ANNUAL_INCOME_CATEGORIES
income_dist_data, _ = get_stat_data(
["annual household income"],
geo,
session,
table_universe="Households",
exclude=["Unspecified", "Not applicable"],
recode=HOUSEHOLD_INCOME_RECODE,
key_order=HOUSEHOLD_INCOME_RECODE.values(),
)
# median income
median = calculate_median_stat(income_dist_data)
median_income = HOUSEHOLD_INCOME_ESTIMATE[median]
# type of dwelling
type_of_dwelling_dist, _ = get_stat_data(
["type of dwelling"],
geo,
session,
table_universe="Households",
recode=TYPE_OF_DWELLING_RECODE,
order_by="-total",
)
informal = type_of_dwelling_dist["Shack"]["numerators"]["this"]
# household goods
household_goods, _ = get_stat_data(
["household goods"],
geo,
session,
table_universe="Households",
recode=HOUSEHOLD_GOODS_RECODE,
key_order=sorted(HOUSEHOLD_GOODS_RECODE.values()),
)
return {
"total_households": {
"name": "Households",
"values": {"this": total_households},
},
"owned": {
"name": "Households fully owned or being paid off",
"values": {"this": percent(owned, total_households)},
"numerators": {"this": owned},
},
"type_of_dwelling_distribution": type_of_dwelling_dist,
"informal": {
"name": "Households that are informal dwellings (shacks)",
"values": {"this": percent(informal, total_households)},
"numerators": {"this": informal},
},
"tenure_distribution": tenure_data,
"household_goods": household_goods,
"annual_income_distribution": income_dist_data,
"median_annual_income": {
"name": "Average annual household income",
"values": {"this": median_income},
},
"head_of_household": {
"gender_distribution": head_gender_dist,
"female": {
"name": "Households with women as their head",
"values": {"this": percent(female_heads, total_households)},
"numerators": {"this": female_heads},
},
"under_18": {
"name": "Households with heads under 18 years old",
"values": {"this": total_under_18},
},
},
}