def query_seqs_in_file(filename, new_dir_path):
print "printing out sequences!"
try:
os.stat(new_dir_path)
except:
os.mkdir(new_dir_path)
records = SeqIO.parse(filename, "fastq")
i = 0
file_names=[]
json_dest = new_dir_path+"data.json"
for record in records:
print "printing out a sequence!"
print "%s: %d" % (record.id, len(record.seq))
xml_obj = blastquery.query(record.seq)
# print str(xml_obj.read())
xml_dest=new_dir_path+"file_"+str(i)+".xml"
with open(xml_dest,'w') as open_file:
open_file.write(xml_obj.read())
open_file.close()
file_names.append(xml_dest)
species_counts = classifier.getSpeciesFromXMLs(file_names,0)
with open(json_dest,'w') as open_file:
json.dump(species_counts,open_file)
open_file.close()
i+=1
import os
from classifier import getSpeciesFromXMLs
from confusionMat import getConfusionMatrix
# Python's open() assumes current working directory, so relative path is okay for this call.
# Otherwise, absolute path is needed.
xmls = []
for file in os.listdir(os.getcwd()):
if file.endswith(".xml"):
xmls.append(file)
speciesDict = getSpeciesFromXMLs(xmls,1)
confusionMat = getConfusionMatrix("Salmo salar", xmls, speciesDict)
# Prints out answer to question 3
for key in confusionMat:
print key + " : " + str(confusionMat[key])
