Question

继续我的上一个问题（Matching two string lists that partially match into another list）我偶然发现了另一个问题。也许我应该先发布到目前为止的代码：

#!/usr/bin/env python3.4
# -*- coding: utf-8 -*-

import random
import timeit

def generateSequences(n):

    RandomSequences = []
    dna = ["A","G","C","T"]
    for i in range(int(n)):

        randseq=''

        for i in range(50):
            randseq+=random.choice(dna)

        RandomSequences.append(randseq)

    return RandomSequences

def generatePrefixes(p, RandomSequences):

    First20Chars = [x[:20] for x in RandomSequences]
    RandomChoices = []
    for i in range(p):
        randomPrefix = random.choice(First20Chars)
        RandomChoices.append(randomPrefix)

    return First20Chars, RandomChoices

def searchReadsInList(RandomSequences, RandomChoices):

    start_time = timeit.default_timer()
    Matches_RS_RC = []
    for i in RandomChoices:
        for j in RandomSequences:
            if i in j:
                Matches_RS_RC.append(j)
    elapsed = timeit.default_timer() - start_time
    return Matches_RS_RC, elapsed

def makeSuffixDict(reads, extSize = 30, verbose = True):
    """
    Generates a dictionary with read-suffixes as values from a list of reads.

    Arguments:
    reads: list of str, reads for generating the dictionary
    extSize: int, length of suffixes stored as values in dict
    verbose: bool, whether to print feedback about results
    Returns:
    suffixDict: dict, dictionary with read-suffixes as values
    """
    dict = {}
    if not verbose:
        for i, read in enumerate(reads):
            prefix = read[0:-extSize]
            suffix = read[-extSize:]
            if prefix not in dict:
                dict[prefix] = [suffix]
            else:
                dict[prefix].append(suffix)
    else:
        unambiguous = set()
        ambiguous =  set()
        for i, read in enumerate(reads):
            prefix = read[0:-extSize]
            suffix = read[-extSize:]
            if prefix not in dict:
                dict[prefix] = [suffix]
                unambiguous.add(prefix)
            else:
                dict[prefix].append(suffix)
                if suffix in unambiguous:
                    unambiguous.remove(suffix)

                ambiguous.add(prefix)
        print("Reads:       ", len(reads), "\n",
              "Keys:        ", len(dict), "\n",
              "Unambiguous: ", len(unambiguous), "\n",
              "Ambiguous:   ", len(ambiguous), sep = "")
    return(dict)   


def searchReadsInDict(RandomSequences, RandomChoices):

    makeSuffixDict(RandomSequences)

    Matches_RC_Dict = []
    for i in RandomChoices:
        for j in dict:
            if i in j:
               Matches_RC_Dict.append(j)
    return Matches_RC_Dict


if __name__ == "__main__":
    RandomSequences = generateSequences(15)
    print ("genseq", RandomSequences)
    First20Chars, RandomChoices = generatePrefixes(5, RandomSequences)
    print ("genpre1", First20Chars)
    print ("genpre2", RandomChoices)
    Matches_RS_RC, elapsed = searchReadsInList(RandomSequences, RandomChoices)
    print ("searchList", Matches_RS_RC)
    print ("Time elapsed", elapsed)
    Matches_RC_Dict = searchReadsInDict (RandomSequences, RandomChoices)
    print ("SearchDict", Matches_RC_Dict)

让我感到困扰的是searchReadsInDict。在searchReadsInDict我需要使用提供的makeSuffixDict来创建字典。然后我需要将generatePrefixes随机选择的字符串与字典中的键进行匹配，并将键和值组合成一个字符串并将它们放入一个列表中。为了将一个键和值放在一个字符串中，我找到了几个方法，它们自己工作但是将它们集成到函数中总是会导致错误，我不确定将它们放在函数中的哪个位置。另一个问题是即使运行它，因为它是Matches_RC_Dict的输出是[]。我希望任何人都可以提供帮助。

Answer 1

经过cyphase＆＃39;的许可。来自freenode上的#python频道我想发布他的好答案，以防止对他人不必要的工作：

def searchReadsInDict(RandomSequences, RandomChoices):

    start_time = timeit.default_timer()
    mydict = makeSuffixDict(RandomSequences)

    Matches_RC_Dict = [rc+end for rc in RandomChoices for end in mydict[rc]]
    elapsed_sRD = timeit.default_timer() - start_time
    return Matches_RC_Dict, elapsed_sRD

在字典中搜索，合并键和值然后放入列表

1 个答案: