def check_if_data_exists_at_less_aggregated_geoscale(df, geoscale,
activityname):
"""
In the event data does not exist at specified geoscale,
check if data exists at less aggregated level
:param df: Either flowbyactivity or flowbysector dataframe
:param geoscale: national, state, or county
:param activityname: str, activity col names to check
:return: str, geoscale to use
"""
if geoscale == 'national':
df = df[(df[fba_activity_fields[0]] == activityname) |
(df[fba_activity_fields[1]] == activityname)]
fips = create_geoscale_list(df, 'state')
df = df[df['Location'].isin(fips)]
if len(df) == 0:
vLog.info("No flows found for %s at the state scale", activityname)
fips = create_geoscale_list(df, 'county')
df = df[df['Location'].isin(fips)]
if len(df) == 0:
vLog.info("No flows found for %s at the county scale",
activityname)
else:
vLog.info(
"Flow-By-Activity data exists for %s at "
"the county level", activityname)
new_geoscale_to_use = 'county'
return new_geoscale_to_use
else:
vLog.info(
"Flow-By-Activity data exists for %s at "
"the state level", activityname)
new_geoscale_to_use = 'state'
return new_geoscale_to_use
if geoscale == 'state':
df = df[(df[fba_activity_fields[0]] == activityname) |
(df[fba_activity_fields[1]] == activityname)]
fips = create_geoscale_list(df, 'county')
df = df[df['Location'].isin(fips)]
if len(df) == 0:
vLog.info("No flows found for %s at the "
"county scale", activityname)
else:
vLog.info(
"Flow-By-Activity data exists for %s "
"at the county level", activityname)
new_geoscale_to_use = 'county'
return new_geoscale_to_use
def check_if_data_exists_at_less_aggregated_geoscale(df, geoscale,
activityname):
"""
In the event data does not exist at specified geoscale, check if data exists at less aggregated level
:param df: Either flowbyactivity or flowbysector dataframe
:param data_to_check: Either an activity name (ex. 'Domestic') or a sector (ex. '1124')
:param geoscale: national, state, or county
:param flowbytype: 'fba' for flowbyactivity, 'fbs' for flowbysector
:return:
"""
if geoscale == 'national':
df = df[(df[fba_activity_fields[0]] == activityname) |
(df[fba_activity_fields[1]] == activityname)]
fips = create_geoscale_list(df, 'state')
df = df[df['Location'].isin(fips)]
if len(df) == 0:
log.info("No flows found for " + activityname +
" at the state scale.")
fips = create_geoscale_list(df, 'county')
df = df[df['Location'].isin(fips)]
if len(df) == 0:
log.info("No flows found for " + activityname +
" at the county scale.")
else:
log.info("Flowbyactivity data exists for " + activityname +
" at the county level")
new_geoscale_to_use = 'county'
return new_geoscale_to_use
else:
log.info("Flowbyactivity data exists for " + activityname +
" at the state level")
new_geoscale_to_use = 'state'
return new_geoscale_to_use
if geoscale == 'state':
df = df[(df[fba_activity_fields[0]] == activityname) |
(df[fba_activity_fields[1]] == activityname)]
fips = create_geoscale_list(df, 'county')
df = df[df['Location'].isin(fips)]
if len(df) == 0:
log.info("No flows found for " + activityname +
" at the county scale.")
else:
log.info("Flowbyactivity data exists for " + activityname +
" at the county level")
new_geoscale_to_use = 'county'
return new_geoscale_to_use
def check_if_data_exists_at_geoscale(df, geoscale, activitynames='All'):
"""
Check if an activity or a sector exists at the specified geoscale
:param df: flowbyactivity dataframe
:param activitynames: Either an activity name (ex. 'Domestic')
or a sector (ex. '1124')
:param geoscale: national, state, or county
:return: str, 'yes' or 'no'
"""
# if any activity name is specified, check if activity data
# exists at the specified geoscale
activity_list = []
if activitynames != 'All':
if isinstance(activitynames, str):
activity_list.append(activitynames)
else:
activity_list = activitynames
# check for specified activity name
df = df[(df[fba_activity_fields[0]].isin(activity_list)) |
(df[fba_activity_fields[1]].isin(activity_list))].reset_index(
drop=True)
else:
activity_list.append('activities')
# filter by geoscale depends on Location System
fips = create_geoscale_list(df, geoscale)
df = df[df['Location'].isin(fips)]
if len(df) == 0:
vLog.info("No flows found for %s at the %s scale",
', '.join(activity_list), geoscale)
exists = "No"
else:
vLog.info("Flows found for %s at the %s scale",
', '.join(activity_list), geoscale)
exists = "Yes"
return exists