INNER CODE UNIT · Python
per_missing_data
nickjcroucher/gubbins · python/gubbins/PreProcessFasta.py:51
per_missing_data = number_of_gaps*100/sequence_length
sequences_to_missing_data[record.id] = per_missing_data
if self.verbose:
print("Sample " + str(record.id) + " has missing data percentage of " +
str(per_missing_data))
input_handle.close()
return sequences_to_missing_data
def taxa_missing_too_much_data(self):
taxa_to_remove = []
for taxa, percentage_missing in self.calculate_sequences_missing_data_percentage().items():
if percentage_missing > self.filter_percentage:
taxa_to_remove.append(taxa)
print("Excluded sequence " + taxa + " because it had " + str(percentage_missing) +
" percentage missing data while a maximum of " + str(self.filter_percentage) + " is allowed")
return taxa_to_remove