def __init__(self,standard=_list_standard[0]):
""" __init__ member function, with default definition of
the used standard. To get the current default standard,
see get_list_standard()[0].
"""
verb("Init of GeoManager()")
self.set_standard(standard)
self._gr=GeoRegion()
def __init__(self,gm=0):
""" __init__ member function.
"""
verb("Init of GeoInfo()")
if gm != 0:
self._gm=gm
else:
self._gm=GeoManager()
self._grp=self._gm._gr.get_pandas()
def __init__(self,):
""" __init__ member function.
"""
#if 'XK' in self._country_list:
# del self._country_list['XK'] # creates bugs in pycountry and is currently a contested country as country
# --- get the UN M49 information and organize the data in the _region_dict
verb("Init of GeoRegion()")
try:
p_m49=pd.read_html(self._source_dict["UN_M49"])[1]
except:
raise CocoaConnectionError('Cannot connect to the UN_M49 '
'wikipedia page. '
'Please check your connection or availability of the page.')
p_m49.columns=['code','region_name']
p_m49['region_name']=[r.split('(')[0].rstrip() for r in p_m49.region_name] # suppress information in parenthesis in region name
p_m49.set_index('code')
self._region_dict.update(p_m49.to_dict('split')['data'])
self._region_dict.update({ "UE":"European Union",
"G7":"G7",
"G8":"G8",
"G20":"G20",
"OECD":"Oecd",
"G77":"G77",
}) # add UE for other analysis
# --- get the UnitedNation GeoScheme and organize the data
try:
p_gs=pd.read_html(self._source_dict["GeoScheme"])[0]
except:
raise CocoaConnectionError('Cannot connect to the UN GeoScheme '
'wikipedia page. '
'Please check your connection or availability of the page.')
p_gs.columns=['country','capital','iso2','iso3','num','m49']
idx=[]
reg=[]
cap=[]
for index, row in p_gs.iterrows():
if row.iso3 != '–' : # meaning a non standard iso in wikipedia UN GeoScheme
for r in row.m49.replace(" ","").split('<'):
idx.append(row.iso3)
reg.append(int(r))
cap.append(row.capital)
self._p_gs=pd.DataFrame({'iso3':idx,'capital':cap,'region':reg})
self._p_gs=self._p_gs.merge(p_m49,how='left',left_on='region',\
right_on='code').drop(["code"],axis=1)
def __init__(self,db=None):
verb("Init of CocoDisplay()")
self.colors = itertools.cycle(Paired12)
self.coco_circle = []
self.coco_line = []
self.base_fig = None
self.hover_tool = None
self.increment = 1
if db == None:
self.info = coge.GeoInfo()
else:
self.info = coge.GeoInfo(db.geo)
def __init__(self, db_name):
'''
Fill the pandas_datase
'''
verb("Init of covid19.DataBase()")
self.database_name = ['jhu', 'spf', 'owid', 'opencovid19']
self.csv_url_parsed = []
self.pandas_datase = {}
self.available_keys_words = []
self.dates = []
self.dicos_countries = {}
self.dict_current_days = {}
self.dict_cumul_days = {}
self.dict_diff_days = {}
self.database_columns_not_computed = {}
self.db = db_name
if self.db != 'spf' and self.db != 'opencovid19':
self.geo = coge.GeoManager('name')
if self.db not in self.database_name:
raise CocoaDbError('Unknown ' + self.db +
'. Available database so far in CoCoa are : ' +
str(self.database_name),
file=sys.stderr)
else:
if self.db == 'jhu':
info('JHU aka Johns Hopkins database selected ...')
self.pandas_datase = self.parse_convert_jhu()
elif self.db == 'spf':
info('SPF aka Sante Publique France database selected ...')
info('... tree differents db from SPF will be parsed ...')
# https://www.data.gouv.fr/fr/datasets/donnees-hospitalieres-relatives-a-lepidemie-de-covid-19/
# Parse and convert spf data structure to JHU one for historical raison
# hosp Number of people currently hospitalized
# rea Number of people currently in resuscitation or critical care
# rad Total amount of patient that returned home
# dc Total amout of deaths at the hospital
# 'sexe' == 0 male + female
cast = {'dep': 'string'}
rename = {'jour': 'date', 'dep': 'location'}
constraints = {'sexe': 0}
url = "https://www.data.gouv.fr/fr/datasets/r/63352e38-d353-4b54-bfd1-f1b3ee1cabd7"
spf1 = self.csv_to_pandas_index_location_date(
url,
rename_columns=rename,
constraints=constraints,
cast=cast)
self.csv_url_parsed.append(url)
# https://www.data.gouv.fr/fr/datasets/donnees-hospitalieres-relatives-a-lepidemie-de-covid-19/
# incid_hosp string Nombre quotidien de personnes nouvellement hospitalisées
# incid_rea integer Nombre quotidien de nouvelles admissions en réanimation
# incid_dc integer Nombre quotidien de personnes nouvellement décédées
# incid_rad integer Nombre quotidien de nouveaux retours à domicile
url = "https://www.data.gouv.fr/fr/datasets/r/6fadff46-9efd-4c53-942a-54aca783c30c"
spf2 = self.csv_to_pandas_index_location_date(
url, rename_columns=rename, cast=cast)
self.csv_url_parsed.append(url)
# https://www.data.gouv.fr/fr/datasets/donnees-relatives-aux-resultats-des-tests-virologiques-covid-19/
# T Number of tests performed
# P Number of positive tests
constraints = {'cl_age90': 0}
url = "https://www.data.gouv.fr/fr/datasets/r/406c6a23-e283-4300-9484-54e78c8ae675"
spf3 = self.csv_to_pandas_index_location_date(
url,
rename_columns=rename,
constraints=constraints,
cast=cast)
self.csv_url_parsed.append(url)
#https://www.data.gouv.fr/fr/datasets/indicateurs-de-suivi-de-lepidemie-de-covid-19/#_
# tension hospitaliere
# Vert : taux d’occupation compris entre 0 et 40% ;
# Orange : taux d’occupation compris entre 40 et 60% ;
# Rouge : taux d'occupation supérieur à 60%.
# R0
# vert : R0 entre 0 et 1 ;
# Orange : R0 entre 1 et 1,5 ;
# Rouge : R0 supérieur à 1,5.
cast = {'departement': 'string'}
rename = {'extract_date': 'date', 'departement': 'location'}
columns_skipped=['region','libelle_reg','libelle_dep','tx_incid_couleur','R_couleur',\
'taux_occupation_sae_couleur','tx_pos_couleur','nb_orange','nb_rouge']
url = "https://www.data.gouv.fr/fr/datasets/r/4acad602-d8b1-4516-bc71-7d5574d5f33e"
spf4 = self.csv_to_pandas_index_location_date(
url,
rename_columns=rename,
separator=',',
encoding="ISO-8859-1",
cast=cast)
self.csv_url_parsed.append(url)
result = pd.concat([spf1, spf2, spf3, spf4],
axis=1,
sort=False)
self.pandas_datase = self.pandas_index_location_date_to_jhu_format(
result, columns_skipped=columns_skipped)
elif self.db == 'opencovid19':
info('OPENCOVID19 selected ...')
rename = {'jour': 'date', 'maille_nom': 'location'}
constraints = {'granularite': 'pays'}
columns_skipped = [
'maille_code', 'source_nom', 'source_url',
'source_archive', 'source_type'
]
url = 'https://raw.githubusercontent.com/opencovid19-fr/data/master/dist/chiffres-cles.csv'
opencovid19 = self.csv_to_pandas_index_location_date(
url,
constraints=constraints,
rename_columns=rename,
separator=',')
self.csv_url_parsed.append(url)
self.pandas_datase = self.pandas_index_location_date_to_jhu_format(
opencovid19, columns_skipped=columns_skipped)
elif self.db == 'owid':
info('OWID aka \"Our World in Data\" database selected ...')
columns_keeped = [
'total_cases', 'new_cases', 'total_deaths', 'new_deaths',
'total_cases_per_million', 'new_cases_per_million',
'total_deaths_per_million', 'new_deaths_per_million',
'total_tests', 'new_tests', 'total_tests_per_thousand',
'new_tests_per_thousand', 'new_tests_smoothed',
'new_tests_smoothed_per_thousand', 'stringency_index'
]
drop_field = {'location': ['International', 'World']}
url = "https://raw.githubusercontent.com/owid/covid-19-data/master/public/data/owid-covid-data.csv"
owid = self.csv_to_pandas_index_location_date(
url, separator=',', drop_field=drop_field)
self.csv_url_parsed.append(url)
self.pandas_datase = self.pandas_index_location_date_to_jhu_format(
owid, columns_keeped=columns_keeped)
self.fill_cocoa_field()
info('Few information concernant the selected database : ',
self.get_db())
info('Available which key-words for: ',
self.get_available_keys_words())
if self.get_db() != 'opencovid19':
info('Example of location : ',
', '.join(random.choices(self.get_locations(),
k=5)), ' ...')
else:
info('Only available location: ', self.get_locations())
info('Last date data ', self.get_dates()[-1])