CS50 问题集 6（DNA）"Python"，我无法计算间歇性 DNA 序列，我的代码在小型数据库中成功，在大型数据库中失败
CS50 Problem Set 6 (DNA) "Python", I can't count Intermittent DNA sequence, my code succeeds in a small database, fail in the large one
我是编程初学者，所以我决定参加 CS50 课程。在问题 Set6 (Python) 中，我编写了代码，它适用于小型数据库，但对于大型数据库却失败了，所以我只寻求有关这个想法的帮助。
这是 course page, and you can download it here（来自 Google 驱动器）
我的代码
import csv
from sys import argv
class DnaTest(object):
"""CLASS HELP: the DNA test, simply give DNA sequence to the program, and it searches in the database to
determine the person who owns the sample.
type the following in cmd to run the program:
python dna.py databases/small.csv sequences/1.txt """
def __init__(self):
# get filename from the command line without directory names "database" and "sequence"
self.sequence_argv = str(argv[2][10:])
self.database_argv = str(argv[1][10:])
# Automatically open and close the database file
with open(f"databases/{self.database_argv}", 'r') as database_file:
self.database_file = database_file.readlines()
# Automatically open and close the sequence file
with open(f"sequences/{self.sequence_argv}", 'r') as sequence_file:
self.sequence_file = sequence_file.readline()
# Read CSV file as a dictionary, function: compare_database_with_sequence()
self.csv_database_dictionary = csv.DictReader(self.database_file)
# Read CSV file to take the first row, function: get_str_list()
self.reader = csv.reader(self.database_file)
# computed dictionary from the sequence file
self.dict_from_sequence = {}
# returns the first row of the CSV file (database file)
def get_str_list(self):
# get first row from CSV file
self.keys = next(self.reader)
# remove 'name' from list, get STR only.
self.keys.remove("name")
return self.keys
# returns dictionary of computed STRs from the sequence file (key(STR): value(count))
def get_str_count_from_sequence(self): # PROBLEM HERE AND RETURN DICTIONARY FROM IT !
for dna_seq in self.get_str_list():
self.dict_from_sequence.update({dna_seq: self.sequence_file.count(dna_seq)})
# compare computed dictionary with the database dictionaries and get the person name
def compare_database_with_sequence(self):
for dictionary in self.csv_database_dictionary:
dict_from_database = dict(dictionary)
dict_from_database.pop('name')
# compare the database dictionaries with sequence computed dictionary
shared_items = {k: self.dict_from_sequence[k] for k in self.dict_from_sequence if
k in dict_from_database and self.dict_from_sequence[k] == int(dict_from_database[k])}
if len(self.dict_from_sequence) == len(shared_items):
dict_from_database = dict(dictionary)
print(dict_from_database['name'])
break
# run the class and its functions (Program control)
if __name__ == '__main__':
RunTest = DnaTest()
RunTest.get_str_count_from_sequence()
RunTest.compare_database_with_sequence()
问题是
在函数 get_str_count_from_sequence(self): 中我使用计数，它是有效的但是对于顺序序列，在序列文件中（示例 5.txt），所需的序列是非顺序的，我无法比较每个数字的连续序列。我搜索了，但没有找到任何简单的东西。有的用Regex模块，有的用re模块，我还没找到解决方法。
测试代码：
来自 CS50 站点：运行 你的程序 python dna.py databases/large.csv sequences/6.txt 你的程序应该输出 Luna
规格
谢谢"Piyush Singh"
我听取了您的建议并使用 re 解决了问题。首先，我使用 re 选择一个组（最长的连续序列）并设置匹配组是一个字典然后我为每个 STR 取最大值然后我清除字典数据以存储下一个 STR在这里我更新了一个比较函数字典（从数据库中读取并从序列文件中计算）
import csv
from sys import argv
import re
class DnaTest(object):
"""CLASS HELP: the DNA test, simply give DNA sequence to the program, and it searches in the database to
determine the person who owns the sample.
type the following in cmd to run the program:
python dna.py databases/small.csv sequences/1.txt """
def __init__(self):
# get filename from the command line without directory names "database" and "sequence"
self.sequence_argv = str(argv[2][10:])
self.database_argv = str(argv[1][10:])
# Automatically open and close the database file
with open(f"databases/{self.database_argv}", 'r') as database_file:
self.database_file = database_file.readlines()
# Automatically open and close the sequence file
with open(f"sequences/{self.sequence_argv}", 'r') as sequence_file:
self.sequence_file = sequence_file.readline()
# Read CSV file as a dictionary, function: compare_database_with_sequence()
self.csv_database_dictionary = csv.DictReader(self.database_file)
# Read CSV file to take the first row, function: get_str_list()
self.reader = csv.reader(self.database_file)
# computed dictionary from the sequence file
self.dict_from_sequence = {}
self.select_max = {}
# returns the first row of the CSV file (database file)
def get_str_list(self):
# get first row from CSV file
keys = next(self.reader)
# remove 'name' from list, get STR only.
keys.remove("name")
return keys
# returns dictionary of computed STRs from the sequence file (key(STR): value(count))
def get_str_count_from_sequence(self): # PROBLEM HERE AND RETURN DICTIONARY FROM IT !
for str_key in self.get_str_list():
regex = rf"({str_key})+"
matches = re.finditer(regex, self.sequence_file, re.MULTILINE)
# my code
for match in matches:
match_len = len(match.group())
key_len = len(str_key)
self.select_max[match] = match_len
# select max value from results dictionary (select_max)
max_values = max(self.select_max.values())
if max_values >= key_len:
result = int(max_values / key_len)
self.select_max[str_key] = result
self.dict_from_sequence[str_key] = result
# clear compare dictionary to select new key
self.select_max.clear()
# compare computed dictionary with the database dictionaries and get the person name
def compare_database_with_sequence(self):
# comparison function between database dictionary and sequence computed dictionary
def dicts_equal(from_sequence, from_database):
""" return True if all keys and values are the same """
return all(k in from_database and int(from_sequence[k]) == int(from_database[k]) for k in from_sequence) \
and all(k in from_sequence and int(from_sequence[k]) == int(from_database[k]) for k in from_database)
def check_result():
for dictionary in self.csv_database_dictionary:
dict_from_database = dict(dictionary)
dict_from_database.pop('name')
if dicts_equal(self.dict_from_sequence, dict_from_database):
dict_from_database = dict(dictionary)
print(dict_from_database['name'])
return True
if check_result():
pass
else:
print("No match")
# run the class and its functions (Program control)
if __name__ == '__main__':
RunTest = DnaTest()
RunTest.get_str_count_from_sequence()
RunTest.compare_database_with_sequence()
检查解决方案
Run your program as python dna.py databases/small.csv sequences/1.txt. Your program should output Bob.
Run your program as python dna.py databases/small.csv sequences/2.txt. Your program should output No match.
更多检查请访问CS50 DNA问题集
为了得到每个STR的最大连续STR数，我只写了几行代码。思路是：你搜索一个STR，如果找到了，那么你搜索STRx2，如果再找到，再搜索STRx3，以此类推，直到找不到STRxn，那么你的最大数量是n-1。由于STRxn总是连续的，所以你不用担心如果你找到任何东西non-consecutive。除了 sys 和 csv，你不需要 python 库。我的整段代码不到30行
enter code here
import csv
import sys
# check command-line arguments, expect 3 including dna.py
n = len(sys.argv)
if n != 3:
print("Usage: python dna.py data.csv sequence.txt")
exit(0)
with open(sys.argv[1], 'r') as database: # read database
data_lines = csv.reader(database) # read line-by-line, store in data_lines
data = [row for row in data_lines] # convert to list of lists, store in data
with open(sys.argv[2], 'r') as sequences:
dna = sequences.read() # read sequence data, store in string dna
counts = [] # list to store counts of the longest run of consecutive repeats of each STR
for i in range(1, len(data[0])): # loop through all STR
count = 1
string = data[0][i] # assign each STR to a string
while string * count in dna: # if find 1 string, then try to find string*2, and so on
count += 1
counts.append(str(count - 1)) # should be decreased by 1 as initialized to 1. int to str
for j in range(1, len(data)): # loop through all rows in database
if data[j][1:len(data[0])] == counts: # compare only numebrs in each row to counts
print(data[j][0]) # print corresponding name
exit(0)
print('No Match')
我是编程初学者，所以我决定参加 CS50 课程。在问题 Set6 (Python) 中，我编写了代码，它适用于小型数据库，但对于大型数据库却失败了，所以我只寻求有关这个想法的帮助。 这是 course page, and you can download it here（来自 Google 驱动器）
我的代码
import csv
from sys import argv
class DnaTest(object):
"""CLASS HELP: the DNA test, simply give DNA sequence to the program, and it searches in the database to
determine the person who owns the sample.
type the following in cmd to run the program:
python dna.py databases/small.csv sequences/1.txt """
def __init__(self):
# get filename from the command line without directory names "database" and "sequence"
self.sequence_argv = str(argv[2][10:])
self.database_argv = str(argv[1][10:])
# Automatically open and close the database file
with open(f"databases/{self.database_argv}", 'r') as database_file:
self.database_file = database_file.readlines()
# Automatically open and close the sequence file
with open(f"sequences/{self.sequence_argv}", 'r') as sequence_file:
self.sequence_file = sequence_file.readline()
# Read CSV file as a dictionary, function: compare_database_with_sequence()
self.csv_database_dictionary = csv.DictReader(self.database_file)
# Read CSV file to take the first row, function: get_str_list()
self.reader = csv.reader(self.database_file)
# computed dictionary from the sequence file
self.dict_from_sequence = {}
# returns the first row of the CSV file (database file)
def get_str_list(self):
# get first row from CSV file
self.keys = next(self.reader)
# remove 'name' from list, get STR only.
self.keys.remove("name")
return self.keys
# returns dictionary of computed STRs from the sequence file (key(STR): value(count))
def get_str_count_from_sequence(self): # PROBLEM HERE AND RETURN DICTIONARY FROM IT !
for dna_seq in self.get_str_list():
self.dict_from_sequence.update({dna_seq: self.sequence_file.count(dna_seq)})
# compare computed dictionary with the database dictionaries and get the person name
def compare_database_with_sequence(self):
for dictionary in self.csv_database_dictionary:
dict_from_database = dict(dictionary)
dict_from_database.pop('name')
# compare the database dictionaries with sequence computed dictionary
shared_items = {k: self.dict_from_sequence[k] for k in self.dict_from_sequence if
k in dict_from_database and self.dict_from_sequence[k] == int(dict_from_database[k])}
if len(self.dict_from_sequence) == len(shared_items):
dict_from_database = dict(dictionary)
print(dict_from_database['name'])
break
# run the class and its functions (Program control)
if __name__ == '__main__':
RunTest = DnaTest()
RunTest.get_str_count_from_sequence()
RunTest.compare_database_with_sequence()
问题是
在函数 get_str_count_from_sequence(self): 中我使用计数，它是有效的但是对于顺序序列，在序列文件中（示例 5.txt），所需的序列是非顺序的，我无法比较每个数字的连续序列。我搜索了，但没有找到任何简单的东西。有的用Regex模块，有的用re模块，我还没找到解决方法。
测试代码：
来自 CS50 站点：运行 你的程序 python dna.py databases/large.csv sequences/6.txt 你的程序应该输出 Luna
规格
谢谢"Piyush Singh"
我听取了您的建议并使用 re 解决了问题。首先，我使用 re 选择一个组（最长的连续序列）并设置匹配组是一个字典然后我为每个 STR 取最大值然后我清除字典数据以存储下一个 STR在这里我更新了一个比较函数字典（从数据库中读取并从序列文件中计算）
import csv
from sys import argv
import re
class DnaTest(object):
"""CLASS HELP: the DNA test, simply give DNA sequence to the program, and it searches in the database to
determine the person who owns the sample.
type the following in cmd to run the program:
python dna.py databases/small.csv sequences/1.txt """
def __init__(self):
# get filename from the command line without directory names "database" and "sequence"
self.sequence_argv = str(argv[2][10:])
self.database_argv = str(argv[1][10:])
# Automatically open and close the database file
with open(f"databases/{self.database_argv}", 'r') as database_file:
self.database_file = database_file.readlines()
# Automatically open and close the sequence file
with open(f"sequences/{self.sequence_argv}", 'r') as sequence_file:
self.sequence_file = sequence_file.readline()
# Read CSV file as a dictionary, function: compare_database_with_sequence()
self.csv_database_dictionary = csv.DictReader(self.database_file)
# Read CSV file to take the first row, function: get_str_list()
self.reader = csv.reader(self.database_file)
# computed dictionary from the sequence file
self.dict_from_sequence = {}
self.select_max = {}
# returns the first row of the CSV file (database file)
def get_str_list(self):
# get first row from CSV file
keys = next(self.reader)
# remove 'name' from list, get STR only.
keys.remove("name")
return keys
# returns dictionary of computed STRs from the sequence file (key(STR): value(count))
def get_str_count_from_sequence(self): # PROBLEM HERE AND RETURN DICTIONARY FROM IT !
for str_key in self.get_str_list():
regex = rf"({str_key})+"
matches = re.finditer(regex, self.sequence_file, re.MULTILINE)
# my code
for match in matches:
match_len = len(match.group())
key_len = len(str_key)
self.select_max[match] = match_len
# select max value from results dictionary (select_max)
max_values = max(self.select_max.values())
if max_values >= key_len:
result = int(max_values / key_len)
self.select_max[str_key] = result
self.dict_from_sequence[str_key] = result
# clear compare dictionary to select new key
self.select_max.clear()
# compare computed dictionary with the database dictionaries and get the person name
def compare_database_with_sequence(self):
# comparison function between database dictionary and sequence computed dictionary
def dicts_equal(from_sequence, from_database):
""" return True if all keys and values are the same """
return all(k in from_database and int(from_sequence[k]) == int(from_database[k]) for k in from_sequence) \
and all(k in from_sequence and int(from_sequence[k]) == int(from_database[k]) for k in from_database)
def check_result():
for dictionary in self.csv_database_dictionary:
dict_from_database = dict(dictionary)
dict_from_database.pop('name')
if dicts_equal(self.dict_from_sequence, dict_from_database):
dict_from_database = dict(dictionary)
print(dict_from_database['name'])
return True
if check_result():
pass
else:
print("No match")
# run the class and its functions (Program control)
if __name__ == '__main__':
RunTest = DnaTest()
RunTest.get_str_count_from_sequence()
RunTest.compare_database_with_sequence()
检查解决方案
Run your program as python dna.py databases/small.csv sequences/1.txt. Your program should output Bob.
Run your program as python dna.py databases/small.csv sequences/2.txt. Your program should output No match.
更多检查请访问CS50 DNA问题集
为了得到每个STR的最大连续STR数，我只写了几行代码。思路是：你搜索一个STR，如果找到了，那么你搜索STRx2，如果再找到，再搜索STRx3，以此类推，直到找不到STRxn，那么你的最大数量是n-1。由于STRxn总是连续的，所以你不用担心如果你找到任何东西non-consecutive。除了 sys 和 csv，你不需要 python 库。我的整段代码不到30行
enter code here
import csv
import sys
# check command-line arguments, expect 3 including dna.py
n = len(sys.argv)
if n != 3:
print("Usage: python dna.py data.csv sequence.txt")
exit(0)
with open(sys.argv[1], 'r') as database: # read database
data_lines = csv.reader(database) # read line-by-line, store in data_lines
data = [row for row in data_lines] # convert to list of lists, store in data
with open(sys.argv[2], 'r') as sequences:
dna = sequences.read() # read sequence data, store in string dna
counts = [] # list to store counts of the longest run of consecutive repeats of each STR
for i in range(1, len(data[0])): # loop through all STR
count = 1
string = data[0][i] # assign each STR to a string
while string * count in dna: # if find 1 string, then try to find string*2, and so on
count += 1
counts.append(str(count - 1)) # should be decreased by 1 as initialized to 1. int to str
for j in range(1, len(data)): # loop through all rows in database
if data[j][1:len(data[0])] == counts: # compare only numebrs in each row to counts
print(data[j][0]) # print corresponding name
exit(0)
print('No Match')