def select_closest_flowline(self, similarity_cutoff=0.6):
"""Select closest flowline.
Selects closest flowline from flowlines_data, including all evaluation information
for the flowline. Although name similarity is not considered for selection it is used
to document if a name matched flowline is available. Requires output from hydrolink_flowlines.
"""
if self.status == 1:
df = utils.df_for_selection(self.flowlines_data)
df = df.rename(columns={"lengthkm": "nhdplusv2 flowline length km",
"reachcode": "nhdplusv2 flowline reachcode",
"gnis_name": "nhdplusv2 flowline gnis name",
"comid": "nhdplusv2 comid",
"terminalflag": "nhdplusv2 terminal flag",
"permanent_identifier": "nhdplusv2 flowline permanent identifier"
})
self.total_count_flowlines = df.shape[0]
self.name_match_in_buffer = df.loc[df['flowline name similarity'] >= similarity_cutoff].shape[0]
df = df.nsmallest(1, 'meters from flowline', keep='all')
if df.shape[0] > 1:
self.message = f'multiple flowlines with same snap distance for id: {self.source_id}. Use name_match method.'
self.error_handling()
else:
self.hydrolink_flowline = ((df.to_dict('records'))[0])
def select_closest_flowline_w_name_match(self, similarity_cutoff=0.6):
"""Select closest flowline with matching water name.
HydroLink data to the closest NHD feature with a name similarity that meets the specified
similarity_cutoff. If no flowlines meet similarity cutoff the method HydroLinks data to the
closest NHD feature. Requires output from hydrolink_flowlines.
"""
if self.status == 1:
df = utils.df_for_selection(self.flowlines_data)
df = df.rename(
columns={
"lengthkm": "nhdhr flowline length km",
"reachcode": "nhdhr flowline reachcode",
"gnis_name": "nhdhr flowline gnis name",
"permanent_identifier":
"nhdhr flowline permanent identifier"
})
self.total_count_flowlines = df.shape[0]
df_1 = df.loc[df['flowline name similarity'] == 1.0]
df_similarity = df.loc[
df['flowline name similarity'] >= similarity_cutoff]
# only 1 flowline has extact matching name
if df_1.shape[0] == 1:
self.hydrolink_flowline = ((df.to_dict('records'))[0])
# more than 1 flowline has exact matching name, grab closest of matching name flowlines
elif df_1.shape[0] > 1:
df_1 = df_1.nsmallest(1, 'meters from flowline', keep='all')
if df_1.shape[0] > 1:
self.message = f'multiple flowlines with same snap distance for id: {self.source_id}.'
self.error_handling()
else:
self.hydrolink_flowline = ((df_1.to_dict('records'))[0])
# only one flowline has matching name meeting similarity cutoff
elif df_1.shape[0] == 0 and df_similarity.shape[0] == 1:
self.hydrolink_flowline = ((
df_similarity.to_dict('records'))[0])
# select closest flowline meeting name match similarity cutoff
elif df_1.shape[0] == 0 and df_similarity.shape[0] > 1:
df_similarity = df_similarity.nsmallest(1,
'meters from flowline',
keep='all')
if df_similarity.shape[0] > 1:
self.message = f'multiple flowlines with same snap distance for id: {self.source_id}.'
self.error_handling()
else:
self.hydrolink_flowline = ((
df_similarity.to_dict('records'))[0])
# no flowlines with name match, select closest
else:
df = df.nsmallest(1, 'meters from flowline', keep='all')
if df.shape[0] > 1:
self.message = f'multiple flowlines with same snap distance for id: {self.source_id}.'
self.error_handling()
else:
self.hydrolink_flowline = ((df.to_dict('records'))[0])