def generate_authority_file(taxa_list, fileinfo):
''' generates the csv file of the authority file'''
csv_filename = fileinfo.csv_filename("authority_file")
# Create a csv file
f = CSVFile.CSVFile(csv_filename)
# add the header
header = [
"", "Family", "Subfamily", "Tribe", "Genus", "SpecificEpithet",
"SubspecificEpithet", "InfraspecificRank", "InfraspecificEpithet",
"Authorship"
]
f.add_line(header)
# creates the records for each taxon in the list
for i, taxa in enumerate(taxa_list):
if i == 0:
line = ["1"]
else:
line = [f"=A{i + 1} + 1"]
line += [taxa.family]
line += [prep_field(taxa.subfamily)]
line += [prep_field(taxa.tribe)]
line += [prep_field(taxa.genus)]
# if is a genus the specie will be marked as "sp."
if taxa.rank == Taxa.Taxa.rank_genus:
line += ["sp."]
else:
line += [prep_field(taxa.specie)]
line += [prep_field(taxa.subspecie)]
line += [""]
line += [""]
line += [prep_field(taxa.author)]
line += ["".join(f'{link}, ' for link in taxa.links)[:-2]]
f.add_line(line)
f.write()
logger.log_short_report("Authority file saved file in:" + csv_filename)
def parse_file(self):
if self.pathfile and os.path.isfile(self.pathfile):
# read the CSV file containing higher taxonomy
f = CSVFile.CSVFile(self.pathfile)
lines = f.get_table()
# store the already retrived subfamilies and tribes (these are
# lists of AssociatedTaxa)
subfamilies = []
tribes = []
def add_associate(in_higher_tax, rank_name, ranks, genus):
# check if the higher taxonomy (subfamily or tribe) already
# exists and if so add the corresponding genus
# if it doesnt exist add a new higher taxonomy record and
# add the genus to it
for rank in ranks:
if rank.main_taxa == in_higher_tax:
rank.add_associate(genus)
break
else:
new_rank = TaxaList.AssociatedTaxa(in_higher_tax,
rank_name)
new_rank.add_associate(genus)
ranks.append(new_rank)
# skip the file header
for subfamily, tribe, genus in lines[1:]:
add_associate(subfamily, "subfamily", subfamilies, genus)
add_associate(tribe, "tribe", tribes, genus)
logger.log_short_report(
"--- Additional taxonomical information ---")
logger.log_short_report("Retrived subfamilies: " +
str(len(subfamilies)))
logger.log_short_report("Retrived tribes: " + str(len(tribes)))
logger.log_short_report("From file:" + self.pathfile)
return subfamilies, tribes
else:
return None
import sys
import CSVFile
file = CSVFile.CSVFile(sys.argv[1])
file.load()
data = file.getColumn(int(sys.argv[2]), float)
print('Maximo: ' + str(max(data)))
print('Minimo: ' + str(min(data)))
family_name = "Nepticulidae"
ass = Associations()
subfamilies, tribes = ass.find_associations(family_name)
print("--- subfamilies ---")
for sub in subfamilies:
print(sub)
print("--- tribes ---")
for tribe in tribes:
print(tribe)
csv = CSVFile.CSVFile("./funet/" + family_name + "_subfamiles_tribes.csv")
csv.add_line(["Subfamily", "Tribe", "Genus"])
tot_genus = []
for sub in subfamilies:
for genus in sub.associates:
tot_genus.append(genus)
for tribe in tribes:
for genus in tribe.associates:
if genus not in tot_genus:
tot_genus.append(genus)
for genus in tot_genus:
lists['PERCENTPESQS'].append(float(b / t))
lists['PERCENTRANK'].append(float(r) / maximo)
return lists
def getNiveis(listaBolsistas):
niveis = {'SR': [], '1A': [], '1B': [], '1C': [], '1D': [], '2': []}
for bolsista, nivel in listaBolsistas:
niveis[nivel].append(bolsista)
return niveis
todos = CSVFile.CSVFile(sys.argv[1])
bolsistas = CSVFile.CSVFile(sys.argv[2])
todos.load()
bolsistas.load()
listaBolsistas = bolsistas.getColumns([(2, int), (4, str)])
niveis = getNiveis(listaBolsistas)
n1 = niveis['1A'] + niveis['1B'] + niveis['1C'] + niveis['1D']
codes = n1 + niveis['SR'] + niveis['2']
codes = set(codes)
PR = contaRank(todos, codes, 2)
import sys
import CSVFile
bolsistas = CSVFile.CSVFile(sys.argv[1])
bolsistas.load()
ranks = bolsistas.getColumn(3, int)
top100 = 0
top1k = 0
top10k = 0
for rank in ranks:
if rank <= 10000:
top10k = top10k + 1
if rank <= 1000:
top1k = top1k + 1
if rank <= 100:
top100 = top100 + 1
print("Top 100: " + str(top100))
print("Top 1k: " + str(top1k))
print("Top 10k: " + str(top10k))
import sys import CSVFile from operator import itemgetter as getter def calculateRank(todos, codes): for pesq in todos: todos = CSVFile.CSVFile(sys.argv[1]) bolsistas = CSVFile.CSVFile(sys.argv[2]) todos.load() bolsistas.load() codes = bolsistas.getColumn(1, int) todosRankeados = CSVFile.CSVFile()