def get_data_from_row(row):
genus, sp, subsp, state, fed_status, state_status, notes, source = row
name = tax_resolve(genus, sp, subsp)
spp_id = spp_ids.get(name, None)
if fed_status:
data_row = [fed_status, state_status, notes, '', 'http://www.mendeley.com/c/5405261894/g/2058663/listings-and-occurrences-for-each-state/', '']
elif state_status:
data_row = [fed_status, state_status, '', notes, '', source]
else:
data_row = [fed_status, '', '', notes, '', source]
return spp_id, state, data_row
def test_apple(self):
for l, r in [('appleb', 'apple'),
('applb', 'apple'),
('apple', 'apple'),
('a', 'a'),
('ap', 'ap'),
('appl', 'apple'),
('bionan', 'bionan'),
('banann', 'banana'),
('bannans', 'banana'),
]:
self.assertEqual(tax_resolve(l, self.syn1), r)
def test_apple(self):
for l, r in [('appleb', 'apple'),
('applb', 'apple'),
('apple', 'apple'),
('a', 'a'),
('ap', 'ap'),
('appl', 'apple'),
('bionan', 'bionan'),
('banann', 'banana'),
('bannans', 'banana'),
('bannnna', 'banana'),
('orangee', 'Orange'),
('Orangee', 'Orange'),
]:
new_name = tax_resolve(l, syns=self.syn1)
new_name = new_name if new_name else l
self.assertEqual(new_name, r)
def get_spp_id(genus, species, subspecies, com_name, taxon, spp_code_dict):
'''Get spp_id from spp_id dictionary. Returns:
a spp_id string if this is a known or unknown species,
None if only an ambiguous common_name was given'''
try:
result = spp_code_dict[com_name.lower()]
return result
except KeyError: pass
sci_name = tax_resolve.scientific_name(genus, species, subspecies)
try:
# return species id for species, if we have one
return spp_code_dict[sci_name]
except KeyError:
for delimiter in (' x ', ' X ', '/'):
# hybrids and slashes
if len(species.split(delimiter)) > 1:
children = species.split(delimiter)
if all([get_spp_id(child) for child in children]):
# create a new species id for the hybrid/slash
new_spp_id = tax_resolve.new_spp_id(taxon, genus, species, subspecies)
else:
# we don't have a species code for all of the species in the hybrid/slash
return None
else:
new_name = tax_resolve.tax_resolve(genus, species, subspecies, com_name=com_name, known_species=spp_code_dict.keys(), taxon=taxon)
if new_name != sci_name:
print '==> corrected to %s' % new_name,
sys.stdout.flush()
if new_name:
try:
return spp_code_dict[new_name]
except KeyError:
corrected_sci_name = (new_name.split('(')[0].strip()).split()
new_spp_id = tax_resolve.new_spp_id(taxon, *corrected_sci_name)
if new_spp_id:
spp_code_dict[new_name] = new_spp_id
pickle.dump(spp_code_dict, open(os.path.join(DATA_DIR, '%s.spp_codes.cache' % taxon), 'w'), protocol=-1)
return new_spp_id
return None
return names
else:
return names + [""]
datadir = "../data/"
taxonomy_files = ["beetles_clean.csv", "ebird_tax_clean.csv", "mammals.csv", "mosquitoes.csv", "plants.csv"]
status_table = get_csv_file(datadir + "status.csv") # using csv due to commas in comment fields
status_table = remove_spaces(status_table[:])
header = status_table[0]
del (status_table[0])
spp_ids = import_taxonomy_files(taxonomy_files, datadir)
status_table_clean = []
status_table_notadded = []
for row in status_table:
genus, sp, subsp, state, fed_status, st_status, notes, source = row
name = tax_resolve(genus, sp, subsp)
spp_id = spp_ids.get(name, None)
if spp_id:
new_row = [spp_id] + get_genus_sp_subsp(name) + row[3:]
status_table_clean.append(new_row)
else:
status_table_notadded.append(row)
status_table_notadded.insert(0, header)
export_to_csv(status_table_notadded, "../data/status_notentered.csv")
header.insert(0, "spp_id")
status_table_clean.insert(0, header)
export_to_csv(status_table_clean, "../data/status_clean.csv")
def test_mosquitos(self):
for to_test in ['Aedes clivis', 'Aedes clivid', 'Ochlerotatus clivis', 'Ochlerotatus clivid', 'Ochlarodadus clivus']:
self.assertEqual(tax_resolve(to_test, self.syn2), 'Aedes clivis')
def test_mosquitos_case_sensitivty(self):
for to_test in ['Aedes clivis', 'Aedes Clivid', 'ochlerotatus clivis', 'Ochlerotatus Clivid']:
self.assertEqual(tax_resolve(to_test, syns=self.syn2), 'Aedes clivis')
