python - CS50 PSET6 - DNA - 适用于 SMALL 但不适用于 LARGE 数据库

Question

我正在使用 CS50 并被困在这个 pset6 上。

我制作了这段代码，它适用于“小型”给定数据库。在“大”上，我的 DNA 序列值错误。就像，使用 debug50 我得到 Albus 序列应该是 15,49,38... 而我的序列是 21,55,64...

怎么了？以及为什么它适用于小型数据库而不是大型数据库？

谢谢您的帮助！

# Import ARGV and CSV library
from sys import argv, exit
import pandas as pd
import csv

# Check if argv has 3 arguments (program name, cvs file and dna sequence)
while True:
    if len(argv) != 3:
        print("Usage: python dna.py data.csv sequence.txt")
        exit(1)
    else:
        break

with open(argv[2], 'r', encoding="UTF-8") as txt:
    dna_seq = txt.read()
#Find the number of STR - AGATC,TTTTTTCT,AATG,TCTAG,GATA,TATC,GAAA,TCTG
AGATC = dna_seq.count("AGATC")
TTTTTTCT = dna_seq.count("TTTTTTCT")
AATG = dna_seq.count("AATG")
TCTAG = dna_seq.count("TCTAG")
GATA = dna_seq.count("GATA")
TATC = dna_seq.count("TATC")
GAAA = dna_seq.count("GAAA")
TCTG = dna_seq.count("TCTG")

name = 0
if argv[1] == "databases/small.csv":

    with open(argv[1], 'r') as csv_file:
        reader = csv.DictReader(csv_file)
        for row in reader:
            dna_db = row['name'], row['AGATC'], row['AATG'], row['TATC']
            dna_db = list(dna_db)

            seq = [AGATC, AATG, TATC]
            seq = [str(x) for x in seq]

            if dna_db[1:4] == seq:
                name = dna_db[:1]
                break
            else:
                name = "No match"

elif argv[1] == "databases/large.csv":

    with open(argv[1], 'r') as csv_file:
        reader = csv.DictReader(csv_file)
        for row in reader:
            dna_db = row['name'], row['AGATC'], row['TTTTTTCT'], row['AATG'], row['TCTAG'], 
row['GATA'], row['TATC'], row['GAAA'], row['TCTG']
            dna_db = list(dna_db)

            seq = [AGATC,TTTTTTCT,AATG,TCTAG,GATA,TATC,GAAA,TCTG]
            seq = [str(x) for x in seq]

            if dna_db[1:9] == seq:
                name = dna_db[:1]
                break
            else:
                name = "No match"

print(name)

标签： pythoncs50dna-sequence