def calculate_regional_average(cls, val_type, datadict, iso3):
countryinfo = Country.get_country_info_from_iso3(iso3)
level = 3
while level != 0:
region_level = cls.region_levels[level]
region_prefix = region_level
column = Column.parse('#region+code+%s' % region_prefix)
regioncode = countryinfo[column.get_display_tag(
sort_attributes=True)]
if regioncode:
regioncode = int(regioncode)
column = Column.parse('#region+%s+name+preferred' %
region_prefix)
regionname = countryinfo[column.get_display_tag(
sort_attributes=True)]
countries_in_region = Country.get_countries_in_region(
regioncode)
avg = cls.calculate_average(datadict, countries_in_region)
if avg:
logger.warning('%s: %s - Using %s (%s) average' %
(iso3, val_type, regionname, region_level))
return avg, regioncode
level -= 1
logger.warning('%s: %s - Using global average' % (iso3, val_type))
return cls.calculate_average(datadict), '001'
def test_get_countries_in_region(self):
assert Country.get_countries_in_region('Eastern Asia') == ['CHN', 'HKG', 'JPN', 'KOR', 'MAC',
'MNG', 'PRK', 'TWN']
assert len(Country.get_countries_in_region('Africa')) == 60
assert Country.get_countries_in_region(13) == ['BLZ', 'CRI', 'GTM', 'HND', 'MEX', 'NIC', 'PAN',
'SLV']
assert Country.get_countries_in_region('Channel Islands') == ['GGY', 'JEY']
assert len(Country.get_countries_in_region('NOTEXIST')) == 0
with pytest.raises(LocationError):
Country.get_countries_in_region('NOTEXIST', exception=LocationError)
def check_regions(iso_list: list) -> list:
""" check which regions are available in dataset or if it has data for all continents -> World
Args:
iso_list: list of available countries as iso-codes
Returns:
A set with regions available in the dataset
"""
regions = set()
if iso_list:
for cc in REGION_CODE.keys():
[
regions.add(REGION_CODE[cc]) for iso in iso_list
if iso in Country.get_countries_in_region(cc, use_live=False)
]
if regions == set(REGION_CODE.values()):
return ["Welt"]
if not regions:
logging.info(
"geographischer Geltungsbereich -> keine Regionen erkannt")
return ["N/A"]
else:
return ["N/A"]
return list(sorted(regions))
from hdx.hdx_configuration import Configuration
from hdx.data.dataset import Dataset
from hdx.location.country import Country
import os
# Setup hdx access
conf = Configuration.create(hdx_site='prod', user_agent='A_Quick_Example', hdx_read_only=True, project_config_dict = {})
# Search for datasets with the keyword we want
datasets = Dataset.search_in_hdx('Requirements and Funding Data', rows=800)
# Get a list of the names of the actual csv-files
resources = Dataset.get_all_resources(datasets)
# Get all the three-digit country codes
africaCodes = [x.lower() for x in Country.get_countries_in_region('Africa')]
# Delete current files before getting new versions
filelist = [ f for f in os.listdir("csv") if f.endswith(".CSV") ]
for f in filelist:
os.remove(os.path.join("csv", f))
# Download all the files that match the naming pattern of the files we want
for resource in resources:
for countryCode in africaCodes:
if "fts_requirements_funding_" + countryCode + ".csv" == resource['name']:
resource.download('csv')
