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 revenue_breakdown(self):
values = []
for year in self.years + [self.budget_year]:
year_name = year if year != self.budget_year else ("%s budget" % year)
subtotal = 0.0
try:
total = self.results['revenue_breakdown']['1900'][year]
for item, code in self.revenue_breakdown_items:
amount = self.results['revenue_breakdown'][code][year]
subtotal += amount
values.append({
'item': item,
'amount': amount,
'percent': percent(amount, total),
'year': year_name,
})
if total and subtotal and (total != subtotal):
values.append({
'item': 'Other',
'amount': total - subtotal,
'percent': percent(total - subtotal, total),
'year': year_name,
})
except KeyError:
continue
return values
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))
# 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']
_, total_ecd_children = get_stat_data(
['age in completed years'], geo, session,
table_name='ageincompletedyears',
only=['0', '1', '2', '3', '4', '5'])
ecd_children_per_household = ratio(total_ecd_children, total_households)
return {
'total_households': {
'name': 'Households',
'values': {'this': total_households},
},
'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},
},
'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},
}
},
'ecd_children_per_household': {
'name': 'Average number of children (aged 0-5) in each household',
'values': {'this': ecd_children_per_household},
},
}
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_demographics_profile(geo_code, geo_level, session):
pop_dist_data, pop_total = get_stat_data(
['population group'], geo_level, geo_code, session)
youth_pop_dist_data, youth_pop_total = get_stat_data(['age in completed years'], geo_level, geo_code, session, table_name='youth_gender_age_in_completed_years')
youth_gender_data, _ = get_stat_data(['gender'], geo_level, geo_code, session, table_name='youth_gender_population_group')
youth_pop_group_data, _ = get_stat_data(['population group'], geo_level, geo_code, session, table_name='youth_gender_population_group')
final_data = {
'total_population': {
"name": "People",
"values": {"this": pop_total}
},
'youth_population_total': {
"name": "Youth aged 15-24",
"values": {"this": youth_pop_total}
},
'youth_population_perc': {
"name": "Of population are youth aged 15-24",
"values": {"this": percent(youth_pop_total, pop_total)},
},
'youth_population_by_year': youth_pop_dist_data,
'youth_population_by_gender': youth_gender_data,
'youth_population_by_pop_group': youth_pop_group_data
}
geo = geo_data.get_geography(geo_code, geo_level)
if geo.square_kms:
final_data['population_density'] = {
'name': "people per square kilometre",
'values': {"this": pop_total / geo.square_kms}
}
return final_data
def cap_budget_diff(self):
values = []
for year in self.years:
try:
cap_ex_budget = self.results['cap_exp_budget']['4100'][year]
cap_ex_actual = self.results['cap_exp_actual']['4100'][year]
result = percent((cap_ex_actual - cap_ex_budget), cap_ex_budget)
overunder = 'under' if result < 0 else 'over'
if abs(result) < 10:
rating = 'good'
elif abs(result) <= 30:
rating = 'ave'
elif abs(result) > 30:
rating = 'bad'
else:
rating = None
except KeyError:
result = None
rating = None
overunder = None
values.append({
'year': year,
'result': result,
'overunder': overunder,
'rating': rating
})
return values
def wasteful_exp_perc_exp(self):
values = []
aggregate = {}
for item, results in self.results['wasteful_exp'].iteritems():
for year, amount in results.iteritems():
if year in aggregate:
aggregate[year] += amount
else:
aggregate[year] = amount
for year in self.years:
try:
op_ex_actual = self.results['op_exp_actual']['4600'][year]
result = percent(aggregate[year], op_ex_actual)
rating = None
if result == 0:
rating = 'good'
else:
rating = 'bad'
except KeyError:
result = None
rating = None
values.append({'year': year, 'result': result, 'rating': rating})
return values
def expenditure_functional_breakdown(self):
GAPD_categories = {
'Budget & Treasury Office',
'Executive & Council',
'Planning and Development',
'Corporate Services',
}
GAPD_label = 'Governance, Administration, Planning and Development'
results = self.results['expenditure_functional_breakdown']
grouped_results = []
for year, yeargroup in groupby(results, lambda r: r['financial_year_end.year']):
try:
total = self.results['expenditure_breakdown']['4600'][year]
GAPD_total = 0.0
year_name = year if year != self.budget_year else ("%s budget" % year)
for result in yeargroup:
# only do budget for budget year, use auda for others
if self.check_budget_actual(year, result['amount_type.code']):
if result['function.category_label'] in GAPD_categories:
GAPD_total += (result['amount.sum'] or 0)
else:
grouped_results.append({
'amount': result['amount.sum'] or 0,
'percent': percent((result['amount.sum'] or 0), total),
'item': result['function.category_label'],
'year': year_name,
})
grouped_results.append({
'amount': GAPD_total,
'percent': percent(GAPD_total, total),
'item': GAPD_label,
'year': year_name,
})
except KeyError:
continue
return sorted(grouped_results, key=lambda r: (r['year'], r['item']))
def expenditure_trends(self):
values = defaultdict(list)
for year in self.years:
try:
total = self.results['expenditure_breakdown']['4600'][year]
except KeyError:
total = None
try:
staff = percent(self.results['expenditure_breakdown']['3000'][year] +
self.results['expenditure_breakdown']['3100'][year],
total)
except KeyError:
staff = None
try:
contracting = percent(self.results['expenditure_breakdown']['4200'][year], total)
except KeyError:
contracting = None
values['staff'].append({'year': year, 'result': staff})
values['contracting'].append({'year': year, 'result': contracting})
return values
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_education_profile(geo_code, geo_level, session):
youth_completed_grade9, _ = get_stat_data(['completed grade9'], geo_level, geo_code, session, table_name='youth_age_16_to_17_gender_completed_grade9')
youth_gender_completed_grade9, _ = get_stat_data(['gender', 'completed grade9'], geo_level, geo_code, session, table_name='youth_age_16_to_17_gender_completed_grade9')
db_model_gender_completed_grade9 = get_model_from_fields(['gender'], geo_level, table_name='youth_age_16_to_17_gender_completed_grade9')
gender_completed_grade9_data = OrderedDict(( # census data refers to sex as gender
('Female', {
"name": "Female",
"values": {"this": youth_gender_completed_grade9['Female']['Yes']['values']['this']},
"numerators": {"this": youth_gender_completed_grade9['Female']['Yes']['numerators']['this']},
}),
('Male', {
"name": "Male",
"values": {"this": youth_gender_completed_grade9['Male']['Yes']['values']['this']},
"numerators": {"this": youth_gender_completed_grade9['Male']['Yes']['numerators']['this']},
}),
))
add_metadata(gender_completed_grade9_data, db_model_gender_completed_grade9)
youth_education_level, youth_pop_20_to_24 = get_stat_data(['education level'], geo_level, geo_code, session, table_name='youth_age_20_to_24_gender_education_level')
matric_or_equiv = (
youth_education_level['Matric']['numerators']['this'] +
youth_education_level['Tertiary']['numerators']['this'] +
youth_education_level['Some secondary']['numerators']['this'])
final_data = {
'youth_completed_grade9': youth_completed_grade9,
'youth_perc_completed_grade9': {
"name": "Of youth aged 16-17 have completed grade 9",
"values": {"this": youth_completed_grade9['Yes']['values']['this']},
},
'youth_gender_completed_grade9': gender_completed_grade9_data,
'youth_perc_matric': {
"name": "Of youth aged 20-24 have completed matric or matric equivalent",
"values": {"this": percent(matric_or_equiv, youth_pop_20_to_24)},
},
'youth_education_level': youth_education_level
}
return final_data
def rep_maint_perc_ppe(self):
values = []
for year in self.years:
try:
rep_maint = self.results['rep_maint']['5005'][year]
ppe = self.results['ppe']['1300'][year]
invest_prop = self.results['invest_prop']['1401'][year]
result = percent(rep_maint, (ppe + invest_prop))
if abs(result) >= 8:
rating = 'good'
elif abs(result) < 8:
rating = 'bad'
else:
rating = None
except KeyError:
result = None
rating = None
values.append({'year': year, 'result': result, 'rating': rating})
return values
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_demographics_profile(geo, session):
# population group
pop_dist_data, total_pop = get_stat_data(
['population group'], geo, session, table_dataset='Census 2011')
# language
language_data, _ = get_stat_data(
['language'], geo, session, order_by='-total')
language_most_spoken = language_data[language_data.keys()[0]]
# age groups
age_dist_data, total_age = get_stat_data(
['age groups in 5 years'], geo, session,
table_name='agegroupsin5years',
recode=COLLAPSED_AGE_CATEGORIES,
key_order=('0-9', '10-19',
'20-29', '30-39',
'40-49', '50-59',
'60-69', '70-79',
'80+'))
# sex
sex_data, _ = get_stat_data(
['gender'], geo, session, table_name='gender')
final_data = {
'language_distribution': language_data,
'language_most_spoken': language_most_spoken,
'population_group_distribution': pop_dist_data,
'age_group_distribution': age_dist_data,
'sex_ratio': sex_data,
'total_population': {
"name": "People",
"values": {"this": total_pop},
}
}
if geo.square_kms:
final_data['population_density'] = {
'name': "people per square kilometre",
'values': {"this": total_pop / geo.square_kms},
}
# median age/age category
db_model_age = get_model_from_fields(
['age in completed years'], geo.geo_level,
table_name='ageincompletedyears'
)
objects = sorted(
get_objects_by_geo(db_model_age, geo, session),
key=lambda x: int(getattr(x, 'age in completed years'))
)
# median age
median = calculate_median(objects, 'age in completed years')
final_data['median_age'] = {
"name": "Median age",
"values": {"this": median},
}
# age category
age_dist, _ = get_stat_data(
['age in completed years'], geo, session,
table_name='ageincompletedyearssimplified',
key_order=['Under 18', '18 to 64', '65 and over'],
recode={'< 18': 'Under 18',
'>= 65': '65 and over'})
final_data['age_category_distribution'] = age_dist
# citizenship
citizenship_dist, _ = get_stat_data(
['citizenship'], geo, session,
order_by='-total')
sa_citizen = citizenship_dist['Yes']['numerators']['this']
final_data['citizenship_distribution'] = citizenship_dist
final_data['citizenship_south_african'] = {
'name': 'South African citizens',
'values': {'this': percent(sa_citizen, total_pop)},
'numerators': {'this': sa_citizen},
}
# migration
province_of_birth_dist, _ = get_stat_data(
['province of birth'], geo, session,
exclude_zero=True, order_by='-total')
final_data['province_of_birth_distribution'] = province_of_birth_dist
def region_recode(field, key):
if key == 'Born in South Africa':
return 'South Africa'
else:
return {
'Not applicable': 'Other',
}.get(key, key)
region_of_birth_dist, _ = get_stat_data(
['region of birth'], geo, session,
exclude_zero=True, order_by='-total',
recode=region_recode)
if 'South Africa' in region_of_birth_dist:
born_in_sa = region_of_birth_dist['South Africa']['numerators']['this']
else:
born_in_sa = 0
final_data['region_of_birth_distribution'] = region_of_birth_dist
final_data['born_in_south_africa'] = {
'name': 'Born in South Africa',
'values': {'this': percent(born_in_sa, total_pop)},
'numerators': {'this': born_in_sa},
}
return final_data
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_profile(geo_code, geo_level, profile_name=None):
api_query_strings = {
'aggregate': '{cube}/aggregate?aggregates={aggregate}&cut={cut}&drilldown=item.code|item.label|financial_period.period&page=0',
'facts': '{cube}/facts?&cut={cut}&drilldown=item.code|item.label|financial_period.period&page=0',
}
line_items = {
'op_exp_actual': {
'cube': 'incexp',
'aggregate': 'amount.sum',
'cut': {
'item.code': '4600',
'amount_type.label': 'Audited Actual',
'demarcation.code': str(geo_code),
'period_length.length': 'year',
},
'query_type': 'aggregate',
},
'op_exp_budget': {
'cube': 'incexp',
'aggregate': 'amount.sum',
'cut': {
'item.code': '4600',
'amount_type.label': 'Adjusted Budget',
'demarcation.code': str(geo_code),
},
'query_type': 'aggregate',
},
'cash_flow': {
'cube': 'cflow',
'aggregate': 'amount.sum',
'cut': {
'item.code': '4200',
'amount_type.label': 'Audited Actual',
'demarcation.code': str(geo_code),
'period_length.length': 'year'
},
'query_type': 'aggregate',
},
'cap_exp_actual': {
'cube': 'capital',
'aggregate': 'asset_register_summary.sum',
'cut': {
'item.code': '4100',
'amount_type.label': 'Audited Actual',
'demarcation.code': str(geo_code),
'period_length.length': 'year'
},
'query_type': 'aggregate',
},
'cap_exp_budget': {
'cube': 'capital',
'aggregate': 'asset_register_summary.sum',
'cut': {
'item.code': '4100',
'amount_type.label': 'Adjusted Budget',
'demarcation.code': str(geo_code),
},
'query_type': 'aggregate',
},
'rep_maint': {
'cube': 'repmaint',
'aggregate': 'amount.sum',
'cut': {
'item.code': '5005',
'amount_type.label': 'Audited Actual',
'demarcation.code': str(geo_code),
'period_length.length': 'year'
},
'query_type': 'aggregate',
},
'ppe': {
'cube': 'bsheet',
'aggregate': 'amount.sum',
'cut': {
'item.code': '1300',
'amount_type.label': 'Audited Actual',
'demarcation.code': str(geo_code),
'period_length.length': 'year',
},
'query_type': 'aggregate',
},
'invest_prop': {
'cube': 'bsheet',
'aggregate': 'amount.sum',
'cut': {
'item.code': '1401',
'amount_type.label': 'Audited Actual',
'demarcation.code': str(geo_code),
'period_length.length': 'year',
},
'query_type': 'aggregate',
},
'officials': {
'cube': 'officials',
'facts': '',
'cut': {
'municipality.demarcation_code': str(geo_code),
},
'query_type': 'facts',
},
'contact_details' : {
'cube': 'municipalities',
'facts': '',
'cut': {
'municipality.demarcation_code': str(geo_code),
},
'query_type': 'facts',
}
}
api_response = {}
results = defaultdict(dict)
for item, params in line_items.iteritems():
if params['query_type'] == 'aggregate':
url = API_URL + api_query_strings['aggregate'].format(
aggregate=params['aggregate'],
cube=params['cube'],
cut='|'.join('{!s}:{!r}'.format(k, v) for (k, v) in params['cut'].iteritems()).replace("'", '"')
)
elif params['query_type'] == 'facts':
url = API_URL + api_query_strings['facts'].format(
facts=params['facts'],
cube=params['cube'],
cut='|'.join('{!s}:{!r}'.format(k, v) for (k, v) in params['cut'].iteritems()).replace("'", '"')
)
api_response[item] = requests.get(url, verify=False).json()
if params['query_type'] == 'facts':
results[item] = facts_from_response(item, api_response, line_items)
else:
for year in YEARS:
results[item][year] = aggregate_from_response(item, year, api_response, line_items)
cash_coverage = {}
op_budget_diff = {}
cap_budget_diff = {}
rep_maint_perc_ppe = {}
for year in YEARS:
cash_coverage[year] = ratio(
results['cash_flow'][year],
(results['op_exp_actual'][year] / 12),
1)
op_budget_diff[year] = percent(
(results['op_exp_budget'][year] - results['op_exp_actual'][year]),
results['op_exp_budget'][year],
1)
cap_budget_diff[year] = percent(
(results['cap_exp_budget'][year] - results['cap_exp_actual'][year]),
results['cap_exp_budget'][year])
rep_maint_perc_ppe[year] = percent(results['rep_maint'][year],
(results['ppe'][year] + results['invest_prop'][year]))
mayoral_staff = []
exclude_roles = ['Speaker', 'Secretary of Speaker']
for official in results['officials']:
if not official['role.role'] in exclude_roles:
mayoral_staff.append({
'role': official['role.role'],
'title': official['contact_details.title'],
'name': official['contact_details.name'],
'office_phone': official['contact_details.phone_number'],
'fax_number': official['contact_details.fax_number'],
'email': official['contact_details.email_address']
})
muni_contact = results['contact_details'][0]
contact_details = {
'street_address_1': muni_contact['municipality.street_address_1'],
'street_address_2': muni_contact['municipality.street_address_2'],
'street_address_3': muni_contact['municipality.street_address_3'],
'street_address_4': muni_contact['municipality.street_address_4'],
'postal_address_1': muni_contact['municipality.postal_address_1'],
'postal_address_2': muni_contact['municipality.postal_address_2'],
'postal_address_3': muni_contact['municipality.postal_address_3'],
'phone_number': muni_contact['municipality.phone_number'],
'url': muni_contact['municipality.url'].lower()
}
return {
'cash_coverage': cash_coverage,
'op_budget_diff': op_budget_diff,
'cap_budget_diff': cap_budget_diff,
'rep_maint_perc_ppe': rep_maint_perc_ppe,
'mayoral_staff': mayoral_staff,
'contact_details': contact_details}
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_profile(geo_code, geo_level, profile_name=None):
api_query_strings = {
'aggregate': '{cube}/aggregate?aggregates={aggregate}&cut={cut}&drilldown=item.code|item.label|financial_period.period&page=0&order=financial_period.period:desc',
'facts': '{cube}/facts?&cut={cut}&fields={fields}&page=0',
}
# Census data
table = get_datatable('population_2011')
_, total_pop = table.get_stat_data(geo_level, geo_code, percent=False)
line_items = {
'op_exp_actual': {
'cube': 'incexp',
'aggregate': 'amount.sum',
'cut': {
'item.code': '4600',
'amount_type.label': 'Audited Actual',
'demarcation.code': str(geo_code),
'period_length.length': 'year',
},
'query_type': 'aggregate',
},
'op_exp_budget': {
'cube': 'incexp',
'aggregate': 'amount.sum',
'cut': {
'item.code': '4600',
'amount_type.label': 'Adjusted Budget',
'demarcation.code': str(geo_code),
},
'query_type': 'aggregate',
},
'cash_flow': {
'cube': 'cflow',
'aggregate': 'amount.sum',
'cut': {
'item.code': '4200',
'amount_type.label': 'Audited Actual',
'demarcation.code': str(geo_code),
'period_length.length': 'year'
},
'query_type': 'aggregate',
},
'cap_exp_actual': {
'cube': 'capital',
'aggregate': 'asset_register_summary.sum',
'cut': {
'item.code': '4100',
'amount_type.label': 'Audited Actual',
'demarcation.code': str(geo_code),
'period_length.length': 'year'
},
'query_type': 'aggregate',
},
'cap_exp_budget': {
'cube': 'capital',
'aggregate': 'asset_register_summary.sum',
'cut': {
'item.code': '4100',
'amount_type.label': 'Adjusted Budget',
'demarcation.code': str(geo_code),
},
'query_type': 'aggregate',
},
'rep_maint': {
'cube': 'repmaint',
'aggregate': 'amount.sum',
'cut': {
'item.code': '5005',
'amount_type.label': 'Audited Actual',
'demarcation.code': str(geo_code),
'period_length.length': 'year'
},
'query_type': 'aggregate',
},
'ppe': {
'cube': 'bsheet',
'aggregate': 'amount.sum',
'cut': {
'item.code': '1300',
'amount_type.label': 'Audited Actual',
'demarcation.code': str(geo_code),
'period_length.length': 'year',
},
'query_type': 'aggregate',
},
'invest_prop': {
'cube': 'bsheet',
'aggregate': 'amount.sum',
'cut': {
'item.code': '1401',
'amount_type.label': 'Audited Actual',
'demarcation.code': str(geo_code),
'period_length.length': 'year',
},
'query_type': 'aggregate',
},
'officials': {
'query_type': 'facts',
'cube': 'officials',
'cut': {
'municipality.demarcation_code': str(geo_code),
},
'fields': [
'role.role',
'contact_details.title',
'contact_details.name',
'contact_details.email_address',
'contact_details.phone_number',
'contact_details.fax_number'],
'annual': False,
'value_label': ''
},
'contact_details' : {
'query_type': 'facts',
'cube': 'municipalities',
'cut': {
'municipality.demarcation_code': str(geo_code),
},
'fields': [
'municipality.phone_number',
'municipality.street_address_1',
'municipality.street_address_2',
'municipality.street_address_3',
'municipality.street_address_4',
'municipality.url'
],
'annual': False,
'value_label': ''
},
'audit_opinions' : {
'query_type': 'facts',
'cube': 'audit_opinions',
'cut': {
'municipality.demarcation_code': str(geo_code),
},
'fields': [
'opinion.code',
'opinion.label',
'financial_year_end.year'
],
'annual': True,
'value_label': 'opinion.label'
}
}
api_response = {}
results = defaultdict(dict)
years = set()
for item, params in line_items.iteritems():
if params['query_type'] == 'aggregate':
url = API_URL + api_query_strings['aggregate'].format(
aggregate=params['aggregate'],
cube=params['cube'],
cut='|'.join('{!s}:{!r}'.format(k, v) for (k, v) in params['cut'].iteritems()).replace("'", '"')
)
elif params['query_type'] == 'facts':
url = API_URL + api_query_strings['facts'].format(
cube=params['cube'],
cut='|'.join('{!s}:{!r}'.format(k, v) for (k, v) in params['cut'].iteritems()).replace("'", '"'),
fields=','.join(field for field in params['fields'])
)
api_response[item] = requests.get(url, verify=False).json()
if params['query_type'] == 'facts':
if params['annual']:
results[item], years = annual_facts_from_response(item, api_response, line_items, years)
else:
results[item] = facts_from_response(item, api_response, line_items)
else:
results[item], years = aggregate_from_response(item, api_response, line_items, years)
cash_coverage = OrderedDict()
op_budget_diff = OrderedDict()
cap_budget_diff = OrderedDict()
rep_maint_perc_ppe = OrderedDict()
for year in sorted(list(years), reverse=True):
try:
cash_coverage[year] = ratio(
results['cash_flow'][year],
(results['op_exp_actual'][year] / 12),
1)
except KeyError:
cash_coverage[year] = None
try:
op_budget_diff[year] = percent(
(results['op_exp_budget'][year] - results['op_exp_actual'][year]),
results['op_exp_budget'][year],
1)
except KeyError:
op_budget_diff[year] = None
try:
cap_budget_diff[year] = percent(
(results['cap_exp_budget'][year] - results['cap_exp_actual'][year]),
results['cap_exp_budget'][year])
except KeyError:
cap_budget_diff[year] = None
try:
rep_maint_perc_ppe[year] = percent(results['rep_maint'][year],
(results['ppe'][year] + results['invest_prop'][year]))
except KeyError:
rep_maint_perc_ppe[year] = None
cash_at_year_end = OrderedDict([
(k, v) for k, v in results['cash_flow'].iteritems()
])
mayoral_staff = []
exclude_roles = ['Speaker', 'Secretary of Speaker']
for official in results['officials']:
if not official['role.role'] in exclude_roles:
mayoral_staff.append({
'role': official['role.role'],
'title': official['contact_details.title'],
'name': official['contact_details.name'],
'office_phone': official['contact_details.phone_number'],
'fax_number': official['contact_details.fax_number'],
'email': official['contact_details.email_address']
})
muni_contact = results['contact_details'][0]
contact_details = {
'street_address_1': muni_contact['municipality.street_address_1'],
'street_address_2': muni_contact['municipality.street_address_2'],
'street_address_3': muni_contact['municipality.street_address_3'],
'street_address_4': muni_contact['municipality.street_address_4'],
'phone_number': muni_contact['municipality.phone_number'],
'url': muni_contact['municipality.url'].lower()
}
audit_opinions = OrderedDict(sorted(results['audit_opinions'].items(), key=lambda t: t[0], reverse=True))
return {
'total_population': total_pop,
'cash_coverage': cash_coverage,
'op_budget_diff': op_budget_diff,
'cap_budget_diff': cap_budget_diff,
'rep_maint_perc_ppe': rep_maint_perc_ppe,
'mayoral_staff': mayoral_staff,
'contact_details': contact_details,
'audit_opinions': audit_opinions,
'cash_at_year_end': cash_at_year_end}
def set_percent_values(data, total):
for fields in data.values():
fields["values"] = {"this": percent(fields["numerators"]["this"], total)}
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_demographics_profile(geo_code, geo_level, session):
# population group
pop_dist_data, total_pop = get_stat_data(
['population group'], geo_level, geo_code, session)
# language
language_data, _ = get_stat_data(
['language'], geo_level, geo_code, session, order_by='-total')
language_most_spoken = language_data[language_data.keys()[0]]
# age groups
age_dist_data, total_age = get_stat_data(
['age groups in 5 years'], geo_level, geo_code, session,
table_name='agegroupsin5years',
recode=COLLAPSED_AGE_CATEGORIES,
key_order=('0-9', '10-19',
'20-29', '30-39',
'40-49', '50-59',
'60-69', '70-79',
'80+'))
# sex
db_model_sex = get_model_from_fields(['gender'], geo_level, table_name='gender')
query = session.query(func.sum(db_model_sex.total)) \
.filter(db_model_sex.gender == 'Male')
query = query.filter(db_model_sex.geo_code == geo_code)
total_male = query.one()[0]
sex_data = OrderedDict(( # census data refers to sex as gender
('Female', {
"name": "Female",
"values": {"this": round((total_pop - total_male) / total_pop * 100, 2)},
"numerators": {"this": total_pop - total_male},
}),
('Male', {
"name": "Male",
"values": {"this": round(total_male / total_pop * 100, 2)},
"numerators": {"this": total_male},
}),
))
add_metadata(sex_data, db_model_sex)
final_data = {
'language_distribution': language_data,
'language_most_spoken': language_most_spoken,
'population_group_distribution': pop_dist_data,
'age_group_distribution': age_dist_data,
'sex_ratio': sex_data,
'total_population': {
"name": "People",
"values": {"this": total_pop},
}
}
geo = geo_data.get_geography(geo_code, geo_level)
if geo.square_kms:
final_data['population_density'] = {
'name': "people per square kilometre",
'values': {"this": total_pop / geo.square_kms},
}
# median age/age category
db_model_age = get_model_from_fields(
['age in completed years'], geo_level,
table_name='ageincompletedyears'
)
objects = sorted(
get_objects_by_geo(db_model_age, geo_code, geo_level, session),
key=lambda x: int(getattr(x, 'age in completed years'))
)
# median age
median = calculate_median(objects, 'age in completed years')
final_data['median_age'] = {
"name": "Median age",
"values": {"this": median},
}
# age category
age_dist, _ = get_stat_data(
['age in completed years'], geo_level, geo_code, session,
table_name='ageincompletedyearssimplified',
key_order=['Under 18', '18 to 64', '65 and over'],
recode={'< 18': 'Under 18',
'>= 65': '65 and over'})
final_data['age_category_distribution'] = age_dist
# citizenship
citizenship_dist, _ = get_stat_data(
['citizenship'], geo_level, geo_code, session,
order_by='-total')
sa_citizen = citizenship_dist['Yes']['numerators']['this']
final_data['citizenship_distribution'] = citizenship_dist
final_data['citizenship_south_african'] = {
'name': 'South African citizens',
'values': {'this': percent(sa_citizen, total_pop)},
'numerators': {'this': sa_citizen},
}
# migration
province_of_birth_dist, _ = get_stat_data(
['province of birth'], geo_level, geo_code, session,
exclude_zero=True, order_by='-total')
final_data['province_of_birth_distribution'] = province_of_birth_dist
def region_recode(field, key):
if key == 'Born in South Africa':
return 'South Africa'
else:
return key
region_of_birth_dist, _ = get_stat_data(
['region of birth'], geo_level, geo_code, session,
exclude_zero=True, order_by='-total',
recode=region_recode)
if 'South Africa' in region_of_birth_dist:
born_in_sa = region_of_birth_dist['South Africa']['numerators']['this']
else:
born_in_sa = 0
final_data['region_of_birth_distribution'] = region_of_birth_dist
final_data['born_in_south_africa'] = {
'name': 'Born in South Africa',
'values': {'this': percent(born_in_sa, total_pop)},
'numerators': {'this': born_in_sa},
}
return final_data
def get_education_profile(geo, session, display_profile, comparative=False):
youth_completed_grade9, _ = get_stat_data(
['completed grade9'],
geo,
session,
table_universe='Youth aged 16 to 17',
table_dataset='Census and Community Survey',
key_order=('Completed', 'Not completed'))
youth_completed_grade9_by_gender, _ = get_stat_data(
['completed grade9', 'gender'],
geo,
session,
table_universe='Youth aged 16 to 17',
table_dataset='Census and Community Survey',
percent_grouping=['gender'],
slices=['Completed'],
key_order={'gender': GENDER_ORDER})
youth_education_level, youth_pop_20_to_24 = get_stat_data(
['education level'],
geo,
session,
table_universe='Youth aged 20 to 24',
table_dataset='Census and Community Survey',
key_order=EDUCATION_LEVEL_KEY_ORDER)
youth_perc_matric = None
if youth_education_level['Matric/matric equivalent']['numerators']['this']:
matric_or_equiv = (
youth_education_level['Matric/matric equivalent']['numerators']
['this'] +
youth_education_level['Any tertiary']['numerators']['this'])
youth_perc_matric = percent(matric_or_equiv, youth_pop_20_to_24)
youth_education_attendance, _ = get_stat_data(
['attendance'],
geo,
session,
table_universe='Youth',
table_dataset='Census and Community Survey',
table_fields=['attendance', 'age in completed years', 'gender'])
youth_education_attending_by_age, _ = get_stat_data(
['attendance', 'age in completed years'],
geo,
session,
table_universe='Youth',
table_dataset='Census and Community Survey',
table_fields=['attendance', 'age in completed years', 'gender'],
table_name='youth_education_attendance_age_incompleted_years_gender',
percent_grouping=['age in completed years'],
slices=['Yes'])
youth_education_attending_by_gender, _ = get_stat_data(
['attendance', 'gender'],
geo,
session,
table_universe='Youth',
table_dataset='Census and Community Survey',
table_fields=['attendance', 'age in completed years', 'gender'],
percent_grouping=['gender'],
slices=['Yes'],
key_order={'gender': GENDER_ORDER})
final_data = {
'youth_completed_grade9': youth_completed_grade9,
'youth_perc_completed_grade9': {
'name': 'Of youth aged 16-17 have completed grade 9 or higher',
'values': {
'this': youth_completed_grade9['Completed']['values']['this']
}
},
'youth_completed_grade9_by_gender': youth_completed_grade9_by_gender,
'youth_education_level': youth_education_level,
'youth_perc_matric': {
"name":
"Of youth aged 20-24 have completed matric/matric equivalent or higher",
"values": {
"this": youth_perc_matric
}
},
'youth_perc_attending': {
"name": "Of youth aged 15-24 attend an educational institution",
"values": {
"this": youth_education_attendance['Yes']['values']['this']
}
},
'youth_education_attending_by_age': youth_education_attending_by_age,
'youth_education_attending_by_gender':
youth_education_attending_by_gender,
}
if display_profile == 'WC':
with dataset_context(year='2017'):
youth_average_mean_score_by_year, _ = get_stat_data(
['year'],
geo,
session,
table_universe=
'Average mean score in both language and mathematics',
percent=False)
youth_average_language_score_by_year, _ = get_stat_data(
['year'],
geo,
session,
table_universe='Average score in language',
percent=False)
youth_average_maths_score_by_year, _ = get_stat_data(
['year'],
geo,
session,
table_universe='Average score in mathematics',
percent=False)
youth_language_outcome_latest, _ = get_stat_data(
['year', 'outcome'],
geo,
session,
table_universe='Percentage passed in language',
key_order={'outcome': ['Passed', 'Failed']},
percent=False,
slices=['2017'])
youth_maths_outcome_latest, _ = get_stat_data(
['year', 'outcome'],
geo,
session,
table_universe='Percentage passed in mathematics',
key_order={'outcome': ['Passed', 'Failed']},
percent=False,
slices=['2017'])
with dataset_context(year='2017'):
youth_matric_outcome_by_year, _ = get_stat_data(
['year'],
geo,
session,
table_universe='Matric pass rate',
only={'outcome': ['Passed']},
percent=False)
youth_matric_outcome_latest, _ = get_stat_data(
['year', 'outcome'],
geo,
session,
table_universe='Matric pass rate',
key_order={'outcome': ['Passed', 'Failed']},
percent=False,
slices=['2017'])
youth_matric_throughput_rate_by_year, _ = get_stat_data(
['year'],
geo,
session,
table_universe='Matric passes as a % of grade 8 enrolment',
only={'outcome': ['Passed']},
percent=False)
youth_matric_throughput_latest, _ = get_stat_data(
['year', 'outcome'],
geo,
session,
table_universe='Matric passes as a % of grade 8 enrolment',
key_order={'outcome': ['Passed', 'Dropped out or failed']},
percent=False,
slices=['2017'])
youth_bachelor_passes_by_year, _ = get_stat_data(
['year'],
geo,
session,
table_universe='Bachelor passes as a % of grade 8 enrolment',
only={'outcome': ['Bachelor pass']},
percent=False)
youth_bachelor_outcome_latest, _ = get_stat_data(
['year', 'outcome'],
geo,
session,
table_universe='Bachelor passes as a % of grade 8 enrolment',
key_order={'outcome': ['Bachelor pass', 'No bachelor pass']},
percent=False,
slices=['2017'])
youth_student_dropout_rate_by_year, _ = get_stat_data(
['year'],
geo,
session,
table_universe='Dropout rates between grade 10 and matric',
only={'outcome': ['Dropped out']},
percent=False)
youth_student_dropout_rate_latest, _ = get_stat_data(
['year', 'outcome'],
geo,
session,
table_universe='Dropout rates between grade 10 and matric',
percent=False,
slices=['2017'])
final_data.update({
'youth_ave_mean_score_latest': {
"name": "Average mean score in both language and mathematics",
"values": {
"this":
youth_average_mean_score_by_year['2017']['values']['this']
}
},
'youth_ave_mean_score_by_year':
youth_average_mean_score_by_year,
'youth_ave_language_score_latest': {
"name": "Average score in language",
"values": {
"this":
youth_average_language_score_by_year['2017']['values']
['this']
}
},
'youth_ave_language_score_by_year':
youth_average_language_score_by_year,
'youth_ave_maths_score_latest': {
"name": "Average score in mathematics",
"values": {
"this":
youth_average_maths_score_by_year['2017']['values']['this']
}
},
'youth_ave_maths_score_by_year':
youth_average_maths_score_by_year,
'youth_language_outcome_latest':
youth_language_outcome_latest,
'youth_maths_outcome_latest':
youth_maths_outcome_latest,
'youth_matric_pass_rate_latest': {
"name": "Of students writing matric passed",
"values": {
"this":
youth_matric_outcome_latest['Passed']['values']['this']
}
},
'youth_matric_outcome_latest':
youth_matric_outcome_latest,
'youth_matric_outcome_by_year':
youth_matric_outcome_by_year,
'youth_matric_throughput_rate_latest': {
"name": "Of Grade 8 students go on to pass matric",
"values": {
"this":
youth_matric_throughput_latest['Passed']['values']['this']
}
},
'youth_matric_throughput_latest':
youth_matric_throughput_latest,
'youth_matric_throughput_rate_by_year':
youth_matric_throughput_rate_by_year,
'youth_bachelor_passes_latest': {
"name":
"Of Grade 8 students go on to pass matric with a bachelor's pass",
"values": {
"this":
youth_bachelor_outcome_latest['Bachelor pass']['values']
['this']
}
},
'youth_bachelor_outcome_latest':
youth_bachelor_outcome_latest,
'youth_bachelor_passes_by_year':
youth_bachelor_passes_by_year,
'youth_student_dropout_rate_latest': {
"name": "Of students drop out between grade 10 and matric",
"values": {
"this":
youth_student_dropout_rate_latest['Dropped out']['values']
['this']
}
},
'youth_student_dropout_rate_by_year':
youth_student_dropout_rate_by_year
})
return final_data
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_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_service_delivery_profile(geo, session):
# water source
water_src_data, total_wsrc = get_stat_data(
['source of water'], geo, session,
recode=SHORT_WATER_SOURCE_CATEGORIES,
order_by='-total')
if 'Service provider' in water_src_data:
total_water_sp = water_src_data['Service provider']['numerators']['this']
else:
total_water_sp = 0.0
# refuse disposal
db_model_ref = get_model_from_fields(['refuse disposal'], geo.geo_level)
objects = get_objects_by_geo(db_model_ref, geo, session, order_by='-total')
refuse_disp_data = OrderedDict()
total_ref = 0.0
total_ref_sp = 0.0
for obj in objects:
attr = getattr(obj, 'refuse disposal')
disp = SHORT_REFUSE_DISPOSAL_CATEGORIES[attr]
refuse_disp_data[disp] = {
"name": disp,
"numerators": {"this": obj.total},
}
total_ref += obj.total
if attr.startswith('Removed by local authority'):
total_ref_sp += obj.total
set_percent_values(refuse_disp_data, total_ref)
add_metadata(refuse_disp_data, db_model_ref)
# electricity
if geo.version == '2011':
elec_attrs = ['electricity for cooking',
'electricity for heating',
'electricity for lighting']
db_model_elec = get_model_from_fields(elec_attrs, geo.geo_level)
objects = get_objects_by_geo(db_model_elec, geo, session)
total_elec = 0.0
total_some_elec = 0.0
elec_access_data = {
'total_all_elec': {
"name": "Have electricity for everything",
"numerators": {"this": 0.0},
},
'total_some_not_all_elec': {
"name": "Have electricity for some things",
"numerators": {"this": 0.0},
},
'total_no_elec': {
"name": "No electricity",
"numerators": {"this": 0.0},
}
}
for obj in objects:
total_elec += obj.total
has_some = False
has_all = True
for attr in elec_attrs:
val = not getattr(obj, attr).startswith('no ')
has_all = has_all and val
has_some = has_some or val
if has_some:
total_some_elec += obj.total
if has_all:
elec_access_data['total_all_elec']['numerators']['this'] += obj.total
elif has_some:
elec_access_data['total_some_not_all_elec']['numerators']['this'] += obj.total
else:
elec_access_data['total_no_elec']['numerators']['this'] += obj.total
set_percent_values(elec_access_data, total_elec)
add_metadata(elec_access_data, db_model_elec)
# toilets
toilet_data, total_toilet = get_stat_data(
['toilet facilities'], geo, session,
exclude_zero=True,
recode=COLLAPSED_TOILET_CATEGORIES,
order_by='-total')
total_flush_toilet = 0.0
total_no_toilet = 0.0
for key, data in toilet_data.iteritems():
if key.startswith('Flush') or key.startswith('Chemical'):
total_flush_toilet += data['numerators']['this']
if key == 'None':
total_no_toilet += data['numerators']['this']
profile = {
'water_source_distribution': water_src_data,
'percentage_water_from_service_provider': {
"name": "Are getting water from a regional or local service provider",
"numerators": {"this": total_water_sp},
"values": {"this": percent(total_water_sp, total_wsrc)},
},
'refuse_disposal_distribution': refuse_disp_data,
'percentage_ref_disp_from_service_provider': {
"name": "Are getting refuse disposal from a local authority or private company",
"numerators": {"this": total_ref_sp},
"values": {"this": percent(total_ref_sp, total_ref)},
},
'percentage_flush_toilet_access': {
"name": "Have access to flush or chemical toilets",
"numerators": {"this": total_flush_toilet},
"values": {"this": percent(total_flush_toilet, total_toilet)},
},
'percentage_no_toilet_access': {
"name": "Have no access to any toilets",
"numerators": {"this": total_no_toilet},
"values": {"this": percent(total_no_toilet, total_toilet)},
},
'toilet_facilities_distribution': toilet_data,
}
if geo.version == '2011':
profile.update({
'percentage_electricity_access': {
"name": "Have electricity for at least one of cooking, heating or lighting",
"numerators": {"this": total_some_elec},
"values": {"this": percent(total_some_elec, total_elec)},
},
'electricity_access_distribution': elec_access_data,
})
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))
# 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']
_, total_ecd_children = get_stat_data(['age in completed years'],
geo,
session,
table_name='ageincompletedyears',
only=['0', '1', '2', '3', '4', '5'])
ecd_children_per_household = ratio(total_ecd_children, total_households)
return {
'total_households': {
'name': 'Households',
'values': {
'this': total_households
},
},
'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
},
},
'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
},
}
},
'ecd_children_per_household': {
'name': 'Average number of children (aged 0-5) in each household',
'values': {
'this': ecd_children_per_household
},
},
}
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_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},
},
},
}
def get_ecd_centres_profile(geo, session):
children_age_groups, total_children = get_stat_data(
['age in completed years'], geo, session,
table_name='ageincompletedyears',
only=['3', '4', '5', '6'],
recode=ECD_AGE_CATEGORIES,
percent=False,
key_order=['0-2', '3-5', '6-7'])
children_3_to_5 = children_age_groups['3-5']['values']['this']
# This will not be needed when the column names for centres are changed.
reg_recode = {
'registration_incomplete-access_denied': 'Registration incomplete',
'registration_incomplete-closed': 'Registration incomplete',
'registration_incomplete-not_found': 'Registration incomplete',
}
table = get_datatable('ecd_centres_by_registration')
ecd_centres_by_registration, total_ecd_centres = table.get_stat_data(
geo, percent=True, recode=reg_recode)
table = get_datatable('ecd_children_enrolled')
children_enrolled, _ = table.get_stat_data(
geo, percent=False)
children_enrolled['children_enrolled_age_3_to_5']['name'] = 'Children enrolled in ECD centres'
children_3_to_5_coverage = percent(
children_enrolled['children_enrolled_age_3_to_5']['values']['this'],
children_3_to_5)
children_3_to_5_per_ecd_centre = ratio(
children_3_to_5,
total_ecd_centres)
children_3_to_5_per_ecd_centre_enrolled = ratio(
children_enrolled['children_enrolled_age_3_to_5']['values']['this'],
total_ecd_centres)
table = get_datatable('ecd_centres_by_type')
ecd_centres_by_type, _ = table.get_stat_data(
geo,
key_order=['community_based', 'home_based', 'school_based', 'other', 'not_specified'])
table = get_datatable('ecd_grade_r')
grade_r, _ = table.get_stat_data(
geo, percent=False)
grade_r['centres_with_grade_r_learners']['name'] = "Centres with Grade R learners"
# Currently there's no data available for these datapoints.
# They are displayed in the template to promote this fact.
registered_ecd_programmes = {
"name": "Registered ECD programmes",
"values": {"this": None},
}
children_in_ecd_programmes = {
"name": "Children in programmes",
"values": {"this": None},
}
children_in_play_groups = {
"name": "Children in play groups",
"values": {"this": None},
}
children_grade_r_age = {
"name": "Children of Grade R age (6 years)",
"values": {"this": children_age_groups['6']['values']['this']}
}
schools_with_grade_r_learners = {
"name": "Schools with Grade R learners",
"values": {"this": None}
}
return {
"total_ecd_centres": {
"name": "Number of ECD centres",
"values": {"this": total_ecd_centres}
},
"ecd_centres_by_registration": ecd_centres_by_registration,
"ecd_centres_by_type": ecd_centres_by_type,
"registered_ecd_programmes": registered_ecd_programmes,
"children_enrolled_age_3_to_5": children_enrolled['children_enrolled_age_3_to_5'],
"children_3_to_5_coverage": {
"name": "Children living in the area who are enrolled in ECD centres. (Children enrolled in centres / Children living in the area)",
"values": {"this": children_3_to_5_coverage}
},
"children_3_to_5_per_ecd_centre": {
"name": "Average number of children living in the area for each ECD centre",
"values": {"this": children_3_to_5_per_ecd_centre}
},
"children_3_to_5_per_ecd_centre_enrolled": {
"name": "Average number of children enrolled in each ECD centre",
"values": {"this": children_3_to_5_per_ecd_centre_enrolled}
},
"children_in_ecd_programmes": children_in_ecd_programmes,
"children_in_play_groups": children_in_play_groups,
"children_grade_r_age": children_grade_r_age,
"ecd_centres_with_grade_r_learners": grade_r['centres_with_grade_r_learners'],
"schools_with_grade_r_learners": schools_with_grade_r_learners
}
def get_demographics_profile(geo, session):
# population group
pop_dist_data, total_pop = get_stat_data(
["population group"], geo, session, table_dataset="Census and Community Survey"
)
# language
language_data, _ = get_stat_data(
["language"],
geo,
session,
table_dataset="Census and Community Survey",
order_by="-total",
)
language_most_spoken = language_data[language_data.keys()[0]]
# age groups
age_dist_data, total_age = get_stat_data(
["age groups in 5 years"],
geo,
session,
table_dataset="Census and Community Survey",
recode=COLLAPSED_AGE_CATEGORIES,
key_order=(
"0-9",
"10-19",
"20-29",
"30-39",
"40-49",
"50-59",
"60-69",
"70-79",
"80+",
),
)
# sex
sex_data, _ = get_stat_data(
["gender"],
geo,
session,
table_universe="Population",
table_dataset="Census and Community Survey",
)
final_data = {
"language_distribution": language_data,
"language_most_spoken": language_most_spoken,
"population_group_distribution": pop_dist_data,
"age_group_distribution": age_dist_data,
"sex_ratio": sex_data,
"total_population": {"name": "People", "values": {"this": total_pop}},
}
if geo.square_kms:
final_data["population_density"] = {
"name": "people per square kilometre",
"values": {"this": total_pop / geo.square_kms},
}
# median age/age category
age_table = get_datatable("ageincompletedyears")
objects = sorted(
age_table.get_rows_for_geo(geo, session),
key=lambda x: int(getattr(x, "age in completed years")),
)
# median age
median = calculate_median(objects, "age in completed years")
final_data["median_age"] = {"name": "Median age", "values": {"this": median}}
# age category
age_dist, _ = get_stat_data(
["age in completed years"],
geo,
session,
table_dataset="Census and Community Survey",
table_name="ageincompletedyearssimplified",
key_order=["Under 18", "18 to 64", "65 and over"],
recode={"< 18": "Under 18", ">= 65": "65 and over"},
)
final_data["age_category_distribution"] = age_dist
# citizenship
citizenship_dist, _ = get_stat_data(
["citizenship"],
geo,
session,
table_dataset="Census and Community Survey",
order_by="-total",
)
sa_citizen = citizenship_dist["Yes"]["numerators"]["this"]
final_data["citizenship_distribution"] = citizenship_dist
final_data["citizenship_south_african"] = {
"name": "South African citizens",
"values": {"this": percent(sa_citizen, total_pop)},
"numerators": {"this": sa_citizen},
}
# migration
province_of_birth_dist, _ = get_stat_data(
["province of birth"],
geo,
session,
table_dataset="Census and Community Survey",
exclude_zero=True,
order_by="-total",
)
final_data["province_of_birth_distribution"] = province_of_birth_dist
def region_recode(field, key):
if key == "Born in South Africa":
return "South Africa"
else:
return {"Not applicable": "Other"}.get(key, key)
region_of_birth_dist, _ = get_stat_data(
["region of birth"],
geo,
session,
table_dataset="Census and Community Survey",
exclude_zero=True,
order_by="-total",
recode=region_recode,
)
if "South Africa" in region_of_birth_dist:
born_in_sa = region_of_birth_dist["South Africa"]["numerators"]["this"]
else:
born_in_sa = 0
final_data["region_of_birth_distribution"] = region_of_birth_dist
final_data["born_in_south_africa"] = {
"name": "Born in South Africa",
"values": {"this": percent(born_in_sa, total_pop)},
"numerators": {"this": born_in_sa},
}
return final_data
def get_service_delivery_profile(geo, session):
# water source
water_src_data, total_wsrc = get_stat_data(
['source of water'], geo, session,
recode=SHORT_WATER_SOURCE_CATEGORIES,
order_by='-total')
if 'Service provider' in water_src_data:
total_water_sp = water_src_data['Service provider']['numerators']['this']
else:
total_water_sp = 0.0
# electricity
elec_attrs = ['electricity for cooking',
'electricity for heating',
'electricity for lighting']
db_model_elec = get_model_from_fields(elec_attrs, geo.geo_level)
objects = get_objects_by_geo(db_model_elec, geo, session)
total_elec = 0.0
total_some_elec = 0.0
elec_access_data = {
'total_all_elec': {
"name": "Have electricity for everything",
"numerators": {"this": 0.0},
},
'total_some_not_all_elec': {
"name": "Have electricity for some things",
"numerators": {"this": 0.0},
},
'total_no_elec': {
"name": "No electricity",
"numerators": {"this": 0.0},
}
}
for obj in objects:
total_elec += obj.total
has_some = False
has_all = True
for attr in elec_attrs:
val = not getattr(obj, attr).startswith('no ')
has_all = has_all and val
has_some = has_some or val
if has_some:
total_some_elec += obj.total
if has_all:
elec_access_data['total_all_elec']['numerators']['this'] += obj.total
elif has_some:
elec_access_data['total_some_not_all_elec']['numerators']['this'] += obj.total
else:
elec_access_data['total_no_elec']['numerators']['this'] += obj.total
for data, total in zip((elec_access_data,), (total_elec,)):
for fields in data.values():
fields["values"] = {"this": percent(fields["numerators"]["this"], total)}
add_metadata(elec_access_data, db_model_elec)
# toilets
toilet_data, total_toilet = get_stat_data(
['toilet facilities'], geo, session,
exclude_zero=True,
recode=COLLAPSED_TOILET_CATEGORIES,
order_by='-total')
total_flush_toilet = 0.0
total_no_toilet = 0.0
for key, data in toilet_data.iteritems():
if key.startswith('Flush') or key.startswith('Chemical'):
total_flush_toilet += data['numerators']['this']
if key == 'None':
total_no_toilet += data['numerators']['this']
return {
'water_source_distribution': water_src_data,
'percentage_water_from_service_provider': {
"name": "Are getting water from a regional or local service provider",
"numerators": {"this": total_water_sp},
"values": {"this": percent(total_water_sp, total_wsrc)},
},
'percentage_electricity_access': {
"name": "Have electricity for at least one of cooking, heating or lighting",
"numerators": {"this": total_some_elec},
"values": {"this": percent(total_some_elec, total_elec)},
},
'electricity_access_distribution': elec_access_data,
'percentage_flush_toilet_access': {
"name": "Have access to flush or chemical toilets",
"numerators": {"this": total_flush_toilet},
"values": {"this": percent(total_flush_toilet, total_toilet)},
},
'percentage_no_toilet_access': {
"name": "Have no access to any toilets",
"numerators": {"this": total_no_toilet},
"values": {"this": percent(total_no_toilet, total_toilet)},
},
'toilet_facilities_distribution': toilet_data,
}
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_ecd_centres_profile(geo, session):
children_age_groups, total_children = get_stat_data(
['age in completed years'],
geo,
session,
table_name='ageincompletedyears',
only=['3', '4', '5', '6'],
recode=ECD_AGE_CATEGORIES,
percent=False,
key_order=['0-2', '3-5', '6-7'])
children_3_to_5 = children_age_groups['3-5']['values']['this']
# This will not be needed when the column names for centres are changed.
reg_recode = {
'registration_incomplete-access_denied': 'Registration incomplete',
'registration_incomplete-closed': 'Registration incomplete',
'registration_incomplete-not_found': 'Registration incomplete',
}
table = get_datatable('ecd_centres_by_registration')
ecd_centres_by_registration, total_ecd_centres = table.get_stat_data(
geo, percent=True, recode=reg_recode)
table = get_datatable('ecd_children_enrolled')
children_enrolled, _ = table.get_stat_data(geo, percent=False)
children_enrolled['children_enrolled_age_3_to_5'][
'name'] = 'Children enrolled in ECD centres'
children_3_to_5_coverage = percent(
children_enrolled['children_enrolled_age_3_to_5']['values']['this'],
children_3_to_5)
children_3_to_5_per_ecd_centre = ratio(children_3_to_5, total_ecd_centres)
children_3_to_5_per_ecd_centre_enrolled = ratio(
children_enrolled['children_enrolled_age_3_to_5']['values']['this'],
total_ecd_centres)
table = get_datatable('ecd_centres_by_type')
ecd_centres_by_type, _ = table.get_stat_data(geo,
key_order=[
'community_based',
'home_based',
'school_based', 'other',
'not_specified'
])
table = get_datatable('ecd_grade_r')
grade_r, _ = table.get_stat_data(geo, percent=False)
grade_r['centres_with_grade_r_learners'][
'name'] = "Centres with Grade R learners"
# Currently there's no data available for these datapoints.
# They are displayed in the template to promote this fact.
registered_ecd_programmes = {
"name": "Registered ECD programmes",
"values": {
"this": None
},
}
children_in_ecd_programmes = {
"name": "Children in programmes",
"values": {
"this": None
},
}
children_in_play_groups = {
"name": "Children in play groups",
"values": {
"this": None
},
}
children_grade_r_age = {
"name": "Children of Grade R age (6 years)",
"values": {
"this": children_age_groups['6']['values']['this']
}
}
schools_with_grade_r_learners = {
"name": "Schools with Grade R learners",
"values": {
"this": None
}
}
return {
"total_ecd_centres": {
"name": "Number of ECD centres",
"values": {
"this": total_ecd_centres
}
},
"ecd_centres_by_registration":
ecd_centres_by_registration,
"ecd_centres_by_type":
ecd_centres_by_type,
"registered_ecd_programmes":
registered_ecd_programmes,
"children_enrolled_age_3_to_5":
children_enrolled['children_enrolled_age_3_to_5'],
"children_3_to_5_coverage": {
"name":
"Children living in the area who are enrolled in ECD centres. (Children enrolled in centres / Children living in the area)",
"values": {
"this": children_3_to_5_coverage
}
},
"children_3_to_5_per_ecd_centre": {
"name":
"Average number of children living in the area for each ECD centre",
"values": {
"this": children_3_to_5_per_ecd_centre
}
},
"children_3_to_5_per_ecd_centre_enrolled": {
"name": "Average number of children enrolled in each ECD centre",
"values": {
"this": children_3_to_5_per_ecd_centre_enrolled
}
},
"children_in_ecd_programmes":
children_in_ecd_programmes,
"children_in_play_groups":
children_in_play_groups,
"children_grade_r_age":
children_grade_r_age,
"ecd_centres_with_grade_r_learners":
grade_r['centres_with_grade_r_learners'],
"schools_with_grade_r_learners":
schools_with_grade_r_learners
}
def get_service_delivery_profile(geo, session):
# water source
water_src_data, total_wsrc = get_stat_data(
["source of water"],
geo,
session,
recode=SHORT_WATER_SOURCE_CATEGORIES,
order_by="-total",
)
# water from a service provider
total_water_sp = 0.0
perc_water_sp = 0.0
if current_context().get("year") == "latest":
water_supplier_data, total_wspl = get_stat_data(
["supplier of water"],
geo,
session,
recode=SHORT_WATER_SUPPLIER_CATEGORIES,
order_by="-total",
)
water_sp = ["Service provider", "Water scheme"]
for key in water_sp:
if key in water_supplier_data:
total_water_sp += water_supplier_data[key]["numerators"]["this"]
perc_water_sp = percent(total_water_sp, total_wspl)
else:
if "Service provider" in water_src_data:
total_water_sp = water_src_data["Service provider"]["numerators"]["this"]
perc_water_sp = percent(total_water_sp, total_wsrc)
percentage_water_from_service_provider = {
"name": "Are getting water from a regional or local service provider",
"numerators": {"this": total_water_sp},
"values": {"this": perc_water_sp},
}
# refuse disposal
refuse_disp_data, total_ref = get_stat_data(
["refuse disposal"],
geo,
session,
recode=SHORT_REFUSE_DISPOSAL_CATEGORIES,
order_by="-total",
)
total_ref_sp = 0.0
for k, v in refuse_disp_data.iteritems():
if k.startswith("Service provider"):
total_ref_sp += v["numerators"]["this"]
sp_name_2011 = (
"Are getting refuse disposal from a local authority or private company"
)
sp_name_2016 = "Are getting refuse disposal from a local authority, private company or community members"
percentage_ref_disp_from_service_provider = {
"name": sp_name_2011
if str(current_context().get("year")) == "2011"
else sp_name_2016,
"numerators": {"this": total_ref_sp},
"values": {"this": percent(total_ref_sp, total_ref)},
}
# electricity
if geo.version == "2011" and str(current_context().get("year")) == "2011":
elec_attrs = [
"electricity for cooking",
"electricity for heating",
"electricity for lighting",
]
elec_table = get_datatable("electricityforcooking_electricityforheating_electr")
objects = elec_table.get_rows_for_geo(geo, session)
total_elec = 0.0
total_some_elec = 0.0
elec_access_data = {
"total_all_elec": {
"name": "Have electricity for everything",
"numerators": {"this": 0.0},
},
"total_some_not_all_elec": {
"name": "Have electricity for some things",
"numerators": {"this": 0.0},
},
"total_no_elec": {"name": "No electricity", "numerators": {"this": 0.0}},
}
for obj in objects:
total_elec += obj.total
has_some = False
has_all = True
for attr in elec_attrs:
val = not getattr(obj, attr).startswith("no ")
has_all = has_all and val
has_some = has_some or val
if has_some:
total_some_elec += obj.total
if has_all:
elec_access_data["total_all_elec"]["numerators"]["this"] += obj.total
elif has_some:
elec_access_data["total_some_not_all_elec"]["numerators"][
"this"
] += obj.total
else:
elec_access_data["total_no_elec"]["numerators"]["this"] += obj.total
set_percent_values(elec_access_data, total_elec)
add_metadata(
elec_access_data,
elec_table,
elec_table.get_release(current_context().get("year")),
)
if current_context().get("year") == "latest":
# We don't have this data for 2011
elec_access, _ = get_stat_data(
["access to electricity"],
geo,
session,
table_universe="Population",
recode=ELECTRICITY_ACCESS_RECODE,
order_by="-total",
)
# toilets
toilet_data, total_toilet = get_stat_data(
["toilet facilities"],
geo,
session,
exclude_zero=True,
recode=COLLAPSED_TOILET_CATEGORIES,
order_by="-total",
)
total_flush_toilet = 0.0
total_no_toilet = 0.0
for key, data in toilet_data.iteritems():
if key.startswith("Flush") or key.startswith("Chemical"):
total_flush_toilet += data["numerators"]["this"]
if key == "None":
total_no_toilet += data["numerators"]["this"]
profile = {
"water_source_distribution": water_src_data,
"percentage_water_from_service_provider": percentage_water_from_service_provider,
"refuse_disposal_distribution": refuse_disp_data,
"percentage_ref_disp_from_service_provider": percentage_ref_disp_from_service_provider,
"percentage_flush_toilet_access": {
"name": "Have access to flush or chemical toilets",
"numerators": {"this": total_flush_toilet},
"values": {"this": percent(total_flush_toilet, total_toilet)},
},
"percentage_no_toilet_access": {
"name": "Have no access to any toilets",
"numerators": {"this": total_no_toilet},
"values": {"this": percent(total_no_toilet, total_toilet)},
},
"toilet_facilities_distribution": toilet_data,
}
if current_context().get("year") == "latest":
profile.update(
{
"water_supplier_distribution": water_supplier_data,
"electricity_access": elec_access,
"percentage_no_electricity_access": {
"name": "Have no access to electricity",
"numerators": elec_access["No access to electricity"]["numerators"],
"values": elec_access["No access to electricity"]["values"],
},
}
)
if geo.version == "2011":
profile.update(
{
"percentage_electricity_access": {
"name": "Have electricity for at least one of cooking, heating or lighting",
"numerators": {"this": total_some_elec},
"values": {"this": percent(total_some_elec, total_elec)},
},
"electricity_access_distribution": elec_access_data,
}
)
return profile
def get_service_delivery_profile(geo, session):
# water source
water_src_data, total_wsrc = get_stat_data(
['source of water'],
geo,
session,
recode=SHORT_WATER_SOURCE_CATEGORIES,
order_by='-total')
if 'Service provider' in water_src_data:
total_water_sp = water_src_data['Service provider']['numerators'][
'this']
else:
total_water_sp = 0.0
# electricity
elec_attrs = [
'electricity for cooking', 'electricity for heating',
'electricity for lighting'
]
db_model_elec = get_model_from_fields(elec_attrs, geo.geo_level)
objects = get_objects_by_geo(db_model_elec, geo, session)
total_elec = 0.0
total_some_elec = 0.0
elec_access_data = {
'total_all_elec': {
"name": "Have electricity for everything",
"numerators": {
"this": 0.0
},
},
'total_some_not_all_elec': {
"name": "Have electricity for some things",
"numerators": {
"this": 0.0
},
},
'total_no_elec': {
"name": "No electricity",
"numerators": {
"this": 0.0
},
}
}
for obj in objects:
total_elec += obj.total
has_some = False
has_all = True
for attr in elec_attrs:
val = not getattr(obj, attr).startswith('no ')
has_all = has_all and val
has_some = has_some or val
if has_some:
total_some_elec += obj.total
if has_all:
elec_access_data['total_all_elec']['numerators'][
'this'] += obj.total
elif has_some:
elec_access_data['total_some_not_all_elec']['numerators'][
'this'] += obj.total
else:
elec_access_data['total_no_elec']['numerators'][
'this'] += obj.total
for data, total in zip((elec_access_data, ), (total_elec, )):
for fields in data.values():
fields["values"] = {
"this": percent(fields["numerators"]["this"], total)
}
add_metadata(elec_access_data, db_model_elec)
# toilets
toilet_data, total_toilet = get_stat_data(
['toilet facilities'],
geo,
session,
exclude_zero=True,
recode=COLLAPSED_TOILET_CATEGORIES,
order_by='-total')
total_flush_toilet = 0.0
total_no_toilet = 0.0
for key, data in toilet_data.iteritems():
if key.startswith('Flush') or key.startswith('Chemical'):
total_flush_toilet += data['numerators']['this']
if key == 'None':
total_no_toilet += data['numerators']['this']
return {
'water_source_distribution': water_src_data,
'percentage_water_from_service_provider': {
"name":
"Are getting water from a regional or local service provider",
"numerators": {
"this": total_water_sp
},
"values": {
"this": percent(total_water_sp, total_wsrc)
},
},
'percentage_electricity_access': {
"name":
"Have electricity for at least one of cooking, heating or lighting",
"numerators": {
"this": total_some_elec
},
"values": {
"this": percent(total_some_elec, total_elec)
},
},
'electricity_access_distribution': elec_access_data,
'percentage_flush_toilet_access': {
"name": "Have access to flush or chemical toilets",
"numerators": {
"this": total_flush_toilet
},
"values": {
"this": percent(total_flush_toilet, total_toilet)
},
},
'percentage_no_toilet_access': {
"name": "Have no access to any toilets",
"numerators": {
"this": total_no_toilet
},
"values": {
"this": percent(total_no_toilet, total_toilet)
},
},
'toilet_facilities_distribution': toilet_data,
}
def get_education_profile(geo, session, display_profile, comparative=False):
youth_completed_grade9, _ = get_stat_data(
['completed grade9'], geo, session,
table_universe='Youth aged 16 to 17',
table_dataset='Census and Community Survey',
key_order=('Completed', 'Not completed'))
youth_completed_grade9_by_gender, _ = get_stat_data(
['completed grade9', 'gender'], geo, session,
table_universe='Youth aged 16 to 17',
table_dataset='Census and Community Survey',
percent_grouping=['gender'], slices=['Completed'],
key_order={'gender': GENDER_ORDER})
youth_education_level, youth_pop_20_to_24 = get_stat_data(
['education level'], geo, session,
table_universe='Youth aged 20 to 24',
table_dataset='Census and Community Survey',
key_order=EDUCATION_LEVEL_KEY_ORDER)
youth_perc_matric = None
if youth_education_level['Matric/matric equivalent']['numerators']['this']:
matric_or_equiv = (
youth_education_level['Matric/matric equivalent']['numerators']['this'] +
youth_education_level['Any tertiary']['numerators']['this'])
youth_perc_matric = percent(matric_or_equiv, youth_pop_20_to_24)
youth_education_attendance, _ = get_stat_data(
['attendance'], geo, session,
table_universe='Youth',
table_dataset='Census and Community Survey',
table_fields=['attendance', 'age in completed years', 'gender'])
youth_education_attending_by_age, _ = get_stat_data(
['attendance', 'age in completed years'], geo, session,
table_universe='Youth',
table_dataset='Census and Community Survey',
table_fields=['attendance', 'age in completed years', 'gender'],
table_name='youth_education_attendance_age_incompleted_years_gender',
percent_grouping=['age in completed years'], slices=['Yes'])
youth_education_attending_by_gender, _ = get_stat_data(
['attendance', 'gender'], geo, session,
table_universe='Youth',
table_dataset='Census and Community Survey',
table_fields=['attendance', 'age in completed years', 'gender'],
percent_grouping=['gender'], slices=['Yes'],
key_order={'gender': GENDER_ORDER})
final_data = {
'youth_completed_grade9': youth_completed_grade9,
'youth_perc_completed_grade9': {
'name': 'Of youth aged 16-17 have completed grade 9 or higher',
'values': {'this': youth_completed_grade9['Completed']['values']['this']}
},
'youth_completed_grade9_by_gender': youth_completed_grade9_by_gender,
'youth_education_level': youth_education_level,
'youth_perc_matric': {
"name": "Of youth aged 20-24 have completed matric/matric equivalent or higher",
"values": {"this": youth_perc_matric}
},
'youth_perc_attending': {
"name": "Of youth aged 15-24 attend an educational institution",
"values": {"this": youth_education_attendance['Yes']['values']['this']}
},
'youth_education_attending_by_age': youth_education_attending_by_age,
'youth_education_attending_by_gender': youth_education_attending_by_gender,
}
if display_profile == 'WC':
with dataset_context(year='2017'):
youth_average_mean_score_by_year, _ = get_stat_data(
['year'], geo, session,
table_universe='Average mean score in both language and mathematics',
percent=False)
youth_average_language_score_by_year, _ = get_stat_data(
['year'], geo, session,
table_universe='Average score in language',
percent=False)
youth_average_maths_score_by_year, _ = get_stat_data(
['year'], geo, session,
table_universe='Average score in mathematics',
percent=False)
youth_language_outcome_latest, _ = get_stat_data(
['year', 'outcome'], geo, session,
table_universe='Percentage passed in language',
key_order={'outcome': ['Passed', 'Failed']},
percent=False, slices=['2017'])
youth_maths_outcome_latest, _ = get_stat_data(
['year', 'outcome'], geo, session,
table_universe='Percentage passed in mathematics',
key_order={'outcome': ['Passed', 'Failed']},
percent=False, slices=['2017'])
with dataset_context(year='2017'):
youth_matric_outcome_by_year, _ = get_stat_data(
['year'], geo, session,
table_universe='Matric pass rate',
only={'outcome': ['Passed']},
percent=False)
youth_matric_outcome_latest, _ = get_stat_data(
['year', 'outcome'], geo, session,
table_universe='Matric pass rate',
key_order={'outcome': ['Passed', 'Failed']},
percent=False, slices=['2017'])
youth_matric_throughput_rate_by_year, _ = get_stat_data(
['year'], geo, session,
table_universe='Matric passes as a % of grade 8 enrolment',
only={'outcome': ['Passed']},
percent=False)
youth_matric_throughput_latest, _ = get_stat_data(
['year', 'outcome'], geo, session,
table_universe='Matric passes as a % of grade 8 enrolment',
key_order={'outcome': ['Passed', 'Dropped out or failed']},
percent=False, slices=['2017'])
youth_bachelor_passes_by_year, _ = get_stat_data(
['year'], geo, session,
table_universe='Bachelor passes as a % of grade 8 enrolment',
only={'outcome': ['Bachelor pass']},
percent=False)
youth_bachelor_outcome_latest, _ = get_stat_data(
['year', 'outcome'], geo, session,
table_universe='Bachelor passes as a % of grade 8 enrolment',
key_order={'outcome': ['Bachelor pass', 'No bachelor pass']},
percent=False, slices=['2017'])
youth_student_dropout_rate_by_year, _ = get_stat_data(
['year'], geo, session,
table_universe='Dropout rates between grade 10 and matric',
only={'outcome': ['Dropped out']},
percent=False)
youth_student_dropout_rate_latest, _ = get_stat_data(
['year', 'outcome'], geo, session,
table_universe='Dropout rates between grade 10 and matric',
percent=False, slices=['2017'])
final_data.update({
'youth_ave_mean_score_latest': {
"name": "Average mean score in both language and mathematics",
"values": {"this": youth_average_mean_score_by_year['2017']['values']['this']}
},
'youth_ave_mean_score_by_year': youth_average_mean_score_by_year,
'youth_ave_language_score_latest': {
"name": "Average score in language",
"values": {"this": youth_average_language_score_by_year['2017']['values']['this']}
},
'youth_ave_language_score_by_year': youth_average_language_score_by_year,
'youth_ave_maths_score_latest': {
"name": "Average score in mathematics",
"values": {"this": youth_average_maths_score_by_year['2017']['values']['this']}
},
'youth_ave_maths_score_by_year': youth_average_maths_score_by_year,
'youth_language_outcome_latest': youth_language_outcome_latest,
'youth_maths_outcome_latest': youth_maths_outcome_latest,
'youth_matric_pass_rate_latest': {
"name": "Of students writing matric passed",
"values": {"this": youth_matric_outcome_latest['Passed']['values']['this']}
},
'youth_matric_outcome_latest': youth_matric_outcome_latest,
'youth_matric_outcome_by_year': youth_matric_outcome_by_year,
'youth_matric_throughput_rate_latest': {
"name": "Of Grade 8 students go on to pass matric",
"values": {"this": youth_matric_throughput_latest['Passed']['values']['this']}
},
'youth_matric_throughput_latest': youth_matric_throughput_latest,
'youth_matric_throughput_rate_by_year': youth_matric_throughput_rate_by_year,
'youth_bachelor_passes_latest': {
"name": "Of Grade 8 students go on to pass matric with a bachelor's pass",
"values": {"this": youth_bachelor_outcome_latest['Bachelor pass']['values']['this']}
},
'youth_bachelor_outcome_latest': youth_bachelor_outcome_latest,
'youth_bachelor_passes_by_year': youth_bachelor_passes_by_year,
'youth_student_dropout_rate_latest': {
"name": "Of students drop out between grade 10 and matric",
"values": {"this": youth_student_dropout_rate_latest['Dropped out']['values']['this']}
},
'youth_student_dropout_rate_by_year': youth_student_dropout_rate_by_year
})
return final_data
