仅当使用Python 3.3在特定范围内比较两个csv文件后才打印这些值

Question

我是编程新手，我有两个CSV文件，我正在尝试比较它们。第一个文件snp.csv如下所示：

chrom   position    ref var gene        var
1       21421       G   T   WASH7P      snp.LOH
1       1251593     T   C   CPSF3L      snp.somatic
6       107474777   -   A   PDSS2       indel.somatic
14      106586168   G   T   ADAM6       snp.LOH

第二个文件quad.csv如下所示：

chrom   Start   End     Sequence
1       21420   21437   GGGACGGGGAGGGTTGGG
1       23058   23078   GGGCTGGGGCGGGGGGAGGG
1       23515   23534   GGGAAGGGACAGGGCAGGG
1       45098   45118   GGGAAAGGGCAGGGCCCGGG
3       1148    1173    GGGCCGGGCAAGGCCGGGTGCAGGG

我想要比较这两个文件，如果两个chrom值匹配，我只想打印那些位置值(在snp.csv文件中)在起始值和结束值(在quad.csv文件中)范围内的文件。因此，我正在寻找一种解决方案，它将给我类似于以下内容(基本上是带有quad.csv文件的开始、结束和序列值的snp.csv文件)

chrom   position    ref var gene    var     Start   End     Sequence
1       21421       G   T   WASH7P  snp.LOH 21420   21437   GGGACGGGGAGGGTTGGG

我搜索了一些帖子，发现了一些有趣的答案，这对我有很大帮助，但我仍然遇到一些问题。我还在学习Python…

这是我到目前为止的脚本，我知道我的range函数有问题...我被卡住了

import csv

snp_file = open("snp.csv", "r")
quad_file = open("quad.csv", "r")
out_file = open("results.csv", "wb")

snp = csv.reader(snp_file, delimiter='\t')
quad = csv.reader(quad_file, delimiter='\t')
out = csv.reader(out_file, delimiter='\t')



quadlist = [row for row in quad]

for snp_row in snp:
    row = 1
    found = False
    for quad_row in quadlist:
        results_row = snp_row
        if snp_row[0] == quad_row[0]:
            quad_pos = range(quad_row[1], quad_row[2])
            if snp_row[1] in quad_pos:
                results_row.append(quad_row)
                found = True
                break
        row = row + 1
    if not found:
        pass
    print (results_row)



snp.close()
quad.close()
out.close()

Answer 1

from bisect import bisect_right
from collections import defaultdict
import csv

TOO_HIGH = 2147483647   # higher than any actual gene position
SNP_FMT  = "{0:<7} {1:<11} {2:3} {3:3} {4:11} {5:15}".format
QUAD_FMT = " {1:<7} {2:<7} {3}".format

def line_to_quad(line):
    row = line.split()
    return int(row[0]), int(row[1]), int(row[2]), row[3]

def line_to_snp(line):
    row = line.split()
    return int(row[0]), int(row[1]), row[2], row[3], row[4], row[5]

class Quads:
    @classmethod
    def from_file(cls, fname):
        with open(fname, "rU") as inf:
            next(inf, None)   # skip header line
            quads = (line_to_quad(line) for line in inf)
            return cls(quads)

    def __init__(self, rows):
        self.chromosomes = defaultdict(list)
        for row in rows:
            self.chromosomes[row[0]].append(row[1:])
        for segs in self.chromosomes.values():
            segs.sort()

    def find_match(self, chromosome, position):
        segs = self.chromosomes[chromosome]
        index = bisect_right(segs, (position, TOO_HIGH, "")) - 1
        try:
            seg = segs[index]
            if seg[0] <= position <= seg[1]:
                return (chromosome,) + seg
        except IndexError:
            pass

def main():
    quads = Quads.from_file("quad.csv")

    print(  # header
        SNP_FMT("chrom", "position", "ref", "var", "gene", "var") +
        QUAD_FMT("chrom", "Start", "End", "Sequence")
    )

    with open("snp.csv") as inf:
        next(inf, None)   # skip header line
        for line in inf:
            snp = line_to_snp(line)
            quad = quads.find_match(snp[0], snp[1])
            if quad:
                print(SNP_FMT(*snp) + QUAD_FMT(*quad))

if __name__=="__main__":
    main()

这给了我们

chrom   position    ref var gene        var             Start   End     Sequence
1       21421       G   T   WASH7P      snp.LOH         21420   21437   GGGACGGGGAGGGTTGGG