This is my solution to CS50 pset6 DNA problem in python. It works fine on small database but gives this traceback and error:
File "E:\CS50x\pset6-dna\dna.py", line 35, in main
STR_match[STR[i]] = longest_match(sequence,STR[i])
Index error: List Index Out of range
I have tried print on various variables but can't figure out the problem.
import csv
import sys
def main():
# TODO: Check for command-line usage
if len(sys.argv) != 3:
print("Usage: python dna.py database.csv sequence.txt")
sys.exit(1)
# TODO: Read database file into a variable
dna_database =[]
with open(sys.argv[1], "r") as dna_data_file:
reader = csv.DictReader(dna_data_file)
for row in reader:
dna_database.append(row)
# TODO: Read DNA sequence file into a variable
with open(sys.argv[2], "r") as load_sequence:
sequence = load_sequence.read()
# TODO: Find longest match of each STR in DNA sequence
STR = list(dna_database[0].keys())[1:]
STR_match ={}
for i in range(len(dna_database)):
# print(dna_database)
STR_match[STR[i]] = longest_match(sequence,STR[i])
# print(len(STR) + 1)
# print(len(dna_database[0].keys()))
# print(STR_match[STR[i]])
# print(longest_match(sequence,STR[i]))
# TODO: Check database for matching profiles
for i in range(len(dna_database)):
matches = 0
for j in range(len(STR)):
if int(STR_match[STR[j]]) == int(dna_database[i][STR[j]]):
matches += 1
if matches == len(STR):
print(dna_database[i]['name'])
sys.exit(0)
print("No Match")
return
def longest_match(sequence, subsequence):
"""Returns length of longest run of subsequence in sequence."""
# Initialize variables
longest_run = 0
subsequence_length = len(subsequence)
sequence_length = len(sequence)
# Check each character in sequence for most consecutive runs of subsequence
for i in range(sequence_length):
# Initialize count of consecutive runs
count = 0
# Check for a subsequence match in a "substring" (a subset of characters) within sequence
# If a match, move substring to next potential match in sequence
# Continue moving substring and checking for matches until out of consecutive matches
while True:
# Adjust substring start and end
start = i + count * subsequence_length
end = start + subsequence_length
# If there is a match in the substring
if sequence[start:end] == subsequence:
count += 1
# If there is no match in the substring
else:
break
# Update most consecutive matches found
longest_run = max(longest_run, count)
# After checking for runs at each character in seqeuence, return longest run found
return longest_run
main()