Hi there I am having an issue comparing the data I have extracted from the sequence and the database files for now I am doing a sort of in efficient way but later I will fix it I am not sure really how to fix my code.
so for now I am kind of testing out if it works for the small db but when i run my code all I get is the output "nooo" instead of "yaaa" which is just for testing.
if anyone could help me and give me a better way to check because I dont think my is the best way possible please help me because I have been stuck on this question for a while now thank you :D
this is my code:
from sys import argv import csv import re db_file = argv dna_sequence = argv if len(argv) > 3: print("Oops! there are 2 arguments") dna_data =  # reads from database with open(db_file, 'r') as f: reader = csv.reader(f) next(reader) for row in reader: for col in row: dna_data.append(col) # reads dna sequence from the files with open(dna_sequence, 'r') as sq_file: dna_sequence = sq_file.readline().rstrip("\n") # for calculating the amount of formations in the txt file formation_count_large= dna_formations_large = ["AGATC","TTTTTTCT","TCTAG","AATG","GATA","TATC","GAAA","TCTG"] formation_count_small= dna_formations_small = ["AGATC","AATG","TATC"] if db_file == "databases/small.csv": for i in range(3): formation_count_small.append(len(re.findall(dna_formations_small[i], dna_sequence))) else: for i in range(8): formation_count_large.append(len(re.findall(dna_formations_large[i], dna_sequence))) if db_file == "databases/small.csv": for i in range(len(dna_data)): for j in range(3): if dna_data[i] == formation_count_small[j]: print("yaaa") else: print("nooo")