def update_geo(self, max_tries=3):
'''
Updates the new missing geo_locations
'''
country = 'Peru'
# Loads cases
cases = self.build_cases()
# loads geo
df_geo = geo.get_geo(country)
# Finds missing locations
merged = cases.merge(df_geo, on=['geo_id'], how='left')
missing = merged.loc[
merged.lon.isna(),
['geo_id', 'departement', 'province']].drop_duplicates()
#Updates
if missing.shape[0] == 0:
print(self.ident + 'Found zero new places.')
else:
print(self.ident +
'Found {} new places. Updating'.format(missing.shape[0]))
print('')
for ind, row in missing.iterrows():
print(self.ident + ' Finding: {}, {}, {} ({})'.format(
country, row.departement, row.province, row.geo_id))
tries = 0
while tries < max_tries:
try:
lon, lat = geo.geolocate(country, row.departement,
row.province)
print(' Done! Location: {},{}'.format(lat, lon))
geo.save_new_location(row.geo_id, country,
row.departement, row.province,
lon, lat)
break
except:
time.sleep(15)
tries += 1
if tries == max_tries:
print(
self.ident +
' Could not find location. Please enter it manually'
)
print()
def update_geo(self, max_tries=3):
'''
Updates the new missing geo_locations
'''
country = 'Mexico'
geo_file_location = os.path.join(self.raw_folder, 'geo',
self.get('geo_file_name'))
# loads geo
df_geo = geo.get_geo(country)
df_geo["geo_id"] = df_geo["geo_id"].astype(int)
# Loads cases
cases = self.build_cases()
cases["geo_id"] = cases["geo_id"].astype(int)
# Finds missing locations
merged = cases.merge(df_geo, on=['geo_id'], how='left')
missing = merged.loc[merged.lon.isna(), ['geo_id']].drop_duplicates()
# Reads the CSV
df_geo_names = pd.read_csv(geo_file_location)
df_geo_names.set_index(['geo_id'])
df_geo_names = df_geo_names.rename(columns={'name': 'geo_name'})
# merges
missing = missing.merge(df_geo_names, on='geo_id')
#Updates
if missing.shape[0] == 0:
print(self.ident + 'Found zero new places.')
else:
print(self.ident +
'Found {} new places. Updating'.format(missing.shape[0]))
print('')
for ind, row in missing.iterrows():
print(self.ident + ' Finding: {}, {}, {} ({})'.format(
country, row.state, row.geo_name, row.geo_id))
tries = 0
while tries < max_tries:
try:
lon, lat = geo.geolocate(country, row.state,
row.geo_name)
print(' Done! Location: {},{}'.format(lat, lon))
geo.save_new_location(row.geo_id, country, row.state,
row.geo_name, lon, lat)
break
except:
time.sleep(15)
tries += 1
if tries == max_tries:
print(
self.ident +
' Could not find location. Please enter it manually'
)
print()
def update_geo(self, max_tries=3):
'''
Updates the new missing geo_locations
'''
country = 'Germany'
geo_file_location = os.path.join(self.raw_folder, 'geo',
self.get('geo_file_name'))
# loads geo
df_geo = geo.get_geo(country)
# Loads cases
cases = self.build_cases()
# Finds missing locations
merged = cases.merge(df_geo, on=['geo_id'], how='left')
missing = merged.loc[merged.lon.isna(), ['geo_id']].drop_duplicates()
# Reads the JSON
with open(geo_file_location) as json_file:
geo_names = json.load(json_file)
df_geo_names = pd.DataFrame.from_dict(
geo_names, orient='index').reset_index().drop(
['note'], axis=1).rename(columns={
'index': 'geo_id',
'name': 'geo_name'
})
df_geo_names.geo_name = df_geo_names.geo_name.apply(clean_name)
# merges
missing = missing.merge(df_geo_names, on='geo_id')
#Updates
if missing.shape[0] == 0:
print(self.ident + 'Found zero new places.')
else:
print(self.ident +
'Found {} new places. Updating'.format(missing.shape[0]))
print('')
for ind, row in missing.iterrows():
print(self.ident + ' Finding: {}, {}, {} ({})'.format(
country, row.state, row.geo_name, row.geo_id))
tries = 0
while tries < max_tries:
try:
lon, lat = geo.geolocate(country, row.state,
row.geo_name)
print(' Done! Location: {},{}'.format(lat, lon))
geo.save_new_location(row.geo_id, country, row.state,
row.geo_name, lon, lat)
break
except:
time.sleep(15)
tries += 1
if tries == max_tries:
print(
self.ident +
' Could not find location. Please enter it manually'
)
print()